From 1888e0775ce1ed6cdded6b6e008e2c047b5bb328 Mon Sep 17 00:00:00 2001 From: Morten Hjorth-Jensen Date: Sun, 18 Aug 2024 22:06:49 +0200 Subject: [PATCH] update --- .../_build/.doctrees/environment.pickle | Bin 676458 -> 266973 bytes .../_build/.doctrees/exercisesweek34.doctree | Bin 37724 -> 37691 bytes .../_build/.doctrees/exercisesweek35.doctree | Bin 35295 -> 35251 bytes .../_build/.doctrees/intro.doctree | Bin 53594 -> 52909 bytes .../_build/.doctrees/week34.doctree | Bin 778588 -> 534891 bytes .../_build/.doctrees/week35.doctree | Bin 917823 -> 523860 bytes .../_build/html/_images/week34_73_1.png | Bin 0 -> 38196 bytes .../_build/html/_images/week35_146_0.png | Bin 23864 -> 23864 bytes .../_build/html/_images/week35_181_1.png | Bin 27987 -> 27987 bytes .../html/_sources/exercisesweek34.ipynb | 40 +- .../html/_sources/exercisesweek35.ipynb | 66 +- .../_build/html/_sources/week34.ipynb | 850 +-- .../_build/html/_sources/week35.ipynb | 870 ++- .../_build/html/exercisesweek34.html | 121 +- .../_build/html/exercisesweek35.html | 121 +- doc/LectureNotes/_build/html/genindex.html | 117 - doc/LectureNotes/_build/html/intro.html | 119 - doc/LectureNotes/_build/html/objects.inv | Bin 1394 -> 998 bytes .../_build/html/reports/exercisesweek34.log | 4 +- .../_build/html/reports/week34.log | 71 +- .../_build/html/reports/week35.log | 131 +- doc/LectureNotes/_build/html/search.html | 117 - doc/LectureNotes/_build/html/searchindex.js | 2 +- doc/LectureNotes/_build/html/week34.html | 958 +-- doc/LectureNotes/_build/html/week35.html | 426 +- .../jupyter_execute/exercisesweek34.ipynb | 44 +- .../_build/jupyter_execute/exercisesweek34.py | 2 +- .../jupyter_execute/exercisesweek35.ipynb | 68 +- .../_build/jupyter_execute/exercisesweek35.py | 4 +- .../_build/jupyter_execute/week34.ipynb | 1590 ++--- .../_build/jupyter_execute/week34.py | 208 +- .../_build/jupyter_execute/week34_73_1.png | Bin 0 -> 38196 bytes .../_build/jupyter_execute/week35.ipynb | 1252 ++-- .../_build/jupyter_execute/week35.py | 12 +- .../_build/jupyter_execute/week35_146_0.png | Bin 23864 -> 23864 bytes .../_build/jupyter_execute/week35_181_1.png | Bin 27987 -> 27987 bytes doc/LectureNotes/week34.ipynb | 4856 +++++++++++++ doc/LectureNotes/week35.ipynb | 6038 +++++++++++++++++ 38 files changed, 13132 insertions(+), 4955 deletions(-) create mode 100644 doc/LectureNotes/_build/html/_images/week34_73_1.png create mode 100644 doc/LectureNotes/_build/jupyter_execute/week34_73_1.png create mode 100644 doc/LectureNotes/week34.ipynb create mode 100644 doc/LectureNotes/week35.ipynb diff --git a/doc/LectureNotes/_build/.doctrees/environment.pickle b/doc/LectureNotes/_build/.doctrees/environment.pickle index ca0bc694617e216bfb1c65398dc622684cff840a..7c5c3ac397701efed8bf32a37e2ca81418e1cff8 100644 GIT binary patch literal 266973 zcmd?S378zmaVAQTAnyAH&mx*62ITaB00~Dbz?B3 zU>$2&q}0?o)O}d8EI)ar^=--W`J}aM9kxID`I0R^ACfFz&$6G_(%N2W_m7OK%B;%j znaad8p7zn-XA#qt6%~N zuG!!5Yvn`APj8>u@tT?QGXver+-7s;cz0R3QEIn5uk5#Gx)1GqIPhA*&dEyEs|Q|v z=V{L^f$GH0W8%NwQO|AF>2JKX^Qc#9cUs=@M%xQ^j*iinb`FK)f|>53pj8r7@3f{0 zBBe%s+@F}~t_;PC{$6x|AH?!3ZJhO5Ex+sqLcAq4w?5HvCp^fwsyRJD{Sk}??dh6F ztckvw=`O3ZCu^haiZ_X0*YdBUV~xg{=(lyU!Dyq|_8WC3zdArqlq#cRZfmsdokLfz z9}&Me?TQ~bL}F-YXr{ZW=634TuG4Nu@2;z($HYhcdfRJ_yCr;lajE78fnS28V}8Bt zwJM#l(N3#2)7?;Mx0}JfojWI|`N>eDg$`L&?KG$Hdfe`kneOF~WXzj+uDi6wKk{(&ky2x_*{n>1lVE7VZ-e@f-^dL= z_0~>e|J)G$6Md?DXsqR;E71FsZUDy7WfP6YM9mv@>uznjjW3S+W#VoHI<)1E*4?w{ z-kI(_CmT~<%PTu$)6U(lQ)zkQ_iT&!4SPX!IQnJVy$^A>IQs#?-8s+&~X7JlgyM1Bu_)((ir{bi5!$cjmcH zcazYUpwVfSyqaG>Ga7Wp$Nh8k)kXErB&qVV-7QVG?$v@(w_GM=YX^|FIa&$=A{%s? z&6XDgqf8;-;ZN6!^*{u2KpM!4Ob%v=k1L&YzFFWC| zb)s>L&UZWQN&~&R;aH>9_Ug_9Rs6S7d`JxV8Pc5QbjzQpK&2P%zGe3={3K+mH6|J} z-6iy&p=KQlxW+qIs&&fLk!^G=_<90nWy4K34f)OK`q*fx;+4)c8_;nWgQY_UM@C1W zZ{T<7=}KpEEEp<}fgQFRGhX*9fDS4yhGU~N8quCa55wM|V^#<*#@(|%On}f5@xz!K zcr;AV!K+PvWc|h_O#1F2~?%)JMlXkbwy)H)=JvHHi_1QB0Wo3* zjh4_A`GoY?n`}bFHR$?Ar`_zdVeMc?0QJJ4(wM?nl+D}zq=!Z`N3Q9v3`fvt2`1j7 ze%u=U!tK4$$X)@*g-{>xxK)x0ky4bPyQ1d8CZhKy{5pDQNwYjIewpD>rVQCp{{30v zO+lZ`)l7H4^}Ml@bZBTA2B_1$Jn-5bG1H}BTpybIc4GoYC>+=EBtXL;`fafQtPXWu z5p@mO8v~>d&e@1!;3m5*PN;lKp#J>*V*C8~gVWzUFyCo!` z_nBAOTe+>W?s#Q=WkY3SWm9EyWlLpuWm{#>vz1$)tK3n!v$C&pSLN=?J(YVaFR9#D z8Lk|Du5v#bJb?dyu<}sl*t3=6l@pbRE00uu;JM0U&s83;JW+Y_$TgKwGnIyEH|d=__gg$ zj8-s1!|Fmkow9#+2v)Mje=5(5b370ATM}S>S1Ir>v$PncFN@Esuf;!Nw1h^w3_CvQ zLph=Smy-EfGD>r#56k;@{PE=D#b@>mp1*$Pi1WiUr)Dazq@SMDf4W)y>Gd<+6O{jxol{%3{yvgqDX^c z5gYuO%DX$=l|0FfjyK363Quftz~6zX9N~XCH$b38mp+@_DOjG)mmw22+Y%h?;E zN#b&h!d7FZ^3m>+gN;&0_|BqTqe_V1H5IhL8D-?ljdAS4j zUpMobnaU?&@yT~4wF!S%O1(#RgMYz1Fgyk|g~RAMB{&R$H}mX6{}ccB+;h*iXT~Z& z3rAgi>66_xLECMU>~PA&)Naceu1$Dw(?Uj`)fib-s<=&zg zuGux!SIa_!kZq08`L*Oz-CFGs+19vKP@PXA4hPU+iJq2#uK80@ly9%$@-FVRR znz6$fbxBVqH^P%>p*y``%Ja_bN$JFjtRGXasM-MW_?6U;saI5(z3%mo;>)#Z2L=n> z?$!n!a(EcUn7dE_9-H3r*UyY~m&8N9@{<^=)oZX4e`1Co#e<(8ZIh1_Gr-Sol+W~W z&P{HTO_C#?9}mgL(GZC+alJt_&bYxT*+3t0+~g72Bw{lfO5ETFWP^AxM1zW3JekoV z3C&nWizGJV87-3FRAq~lq9-w`%XZ0u#mu(k;}n@BI%j3OBt`IIx+XzomvIDvCh(ccC%UU?@l|!t?SW?| zqD6Rnv5eMq*ECxVtoVWl5Ry1RVV0ThEtrgV^iV^UDy2sbH=G$(hQXJr>p#%;|1-(OI{KDVO~se7cJH39isdL13nP8G?6Y zK*)2iz7zd}f5Q>wb`UOFnPZWLRU(!*)D|9o^}S)+#fX8?%!FlJ{Qlw=Janv*)!!~} zH_Gm``pZ)B%jo!Id**obDpnWKKjE)7N-oyIi0BEgb20yoU_{(x3wv}}({bcY;8%Ak zw6^IP!uR~pGtsm2&%hZvKNG*}On6wCpKFIp-0{xSPfw2`EK(29=MadNyNkm%Bz5)m zkht=R`28hBKh%fl$I4qPFGT;w+Dyb`uqcH`No)M>(oTE4ctk zhz&qB;nm5W*g|2OaYXfqFD%tsh%6$$092oi-(5p(CL81rB8){#eEIC^cFUiHS~uD> z%^>D94%Zu@gwdc$k-+C-A}fUZ&+!__AN@`Xz8LUz6@+SP6t0Q89l9TK9?R8TE1Su2 z5fSXJqR;{9c0jS5iU>zMnO=NP`gI>({e-t?C$tnX;%WS6XU!km$?Csn=+2$wh!-Kn z8HCn?ouMyIgOE$rkHU2XyqBW zD>Bw5dl{?ixPvwUN)gqhr5{$duo50c^`4lC=`6!)Y1G5AurZ z=<)U_Vj~l(eynOjKU@T6IoyX;XLDL2xuT9(Jp$Prz&?JQEW{fA4Z|l2Q=Oj?4^~XN zbqaF^BFHOMcnQ|#O}}(zdgeLNZdLgAs6SDs5FNZ2qPrpaGgNf~CXOE>%n*0a`f$;Q zg&zJjTK1Yyq9Y5U=au(X-WUCwZFLxGqrooqy1SNa@Tm6``ZluqlI7*%A%932Ov~Dc zqr&J>%uO=1oPI?-%WEO_C}}K1xUV&e{y=I({<=IsZ?~W7kk6;kSf~6v>awTZz3i!j zp2T8<+9ZsFv29-(**Re=FRi+;{YylKgcgJp?z;@oU{y~xZ^rAy-Lq1x?HPP+fcJC6|c*p(pF)6D5feKMr3M!DR8l z_{nndVi+;TltfgCAafbX2o3e>Gx0+XQGhE%EU^BaQQixq7jhoECw^%cP>~PR@rh2_9;u7(C2l)g3J(@gOwi4xrW_HBA%)d^cxu^UZGT!py z*h>5YbBB}(hHDsiiJn#7Sn0-6a8F0U>vYqw-w@CVhsb3SkuHlyPY|n=ip(8N5g<(d z(7fM(I>hfVQ?Ns$uooEQ%23)Mx?>Xljd(OV<(Fwl%6C~-F~J}ZP2m{7j<^6m5n;?N zM3RH@IbbS!vPKX`qOH{OMM^A%1wV%?1~Z2cYNM5UzE-?H)k1u*K0&i29E4@aN%&9W z6}J|%KvB)uzOEJ_Eur1fBo#fQ$Y=a-#66>bBhLdLX%s@X+M@`?V-{B)a_Wy0g7I`f zq0;Deij~Iye!lXi_}_1?ye0Z~^a+Zylp?+cx=&pA+!jr0N^p870{ZlwneJorMqh@x zCH0qHIQ1}KE@?h;;WVQjp;)^l{PKAt97XLV?bB)6#_4cUz@5+wk?sr8Q`{1vpO^uV z>|cpIUamY;hRUUKF4?im@p(sY1T=-3J+8S;E_-hE`Zu%y&%s1 z1)}d|pYmbP#sv5=xv)(SVO-b+#4NiT7=WQ@8VfVL>q#pqONQiWYqT*YmNX)G8q?#k ztI(34LUJ2JR6ZIN*}d+ipZNtT4+pqaOBD4%IKUCnY?BzUQqRR7uYc{2X;O-bkof*dGh*a&JXN(I zHzB%9y&O29D^Yd`PG_7V-L7*SQ|1s_QN#PN0CgvwXXv-{PTR!-tt}c*7#v!OuBE1N zJ7)WQMA$hnGU7xXMk#|j=zzmU)PP@RnFHsUgC~xSh~7Al3_`@wEBLdo;3R|Kl(nQx zZ|__d_bT&4FAnf4gVATA&V_OWZKs6%y64;ziZdksBmoDIiSp2y)SKMK6})00?a&f! zd|LEv%|Gio;8eink2?clFGe3B6hVP`j5sK>=;9q}Am|SvLDHHY2~(WIwOUMS2)c6! z37!G!Fz23o#oN#Zf^A^Oj=Kb%^QyuyLBC%2TGRt~3AA@Q2e1el!;;yVs-POfMJlK{ z?QrJVK@~@-hIN`(9&#S_Yc*%gbDD@>L1QRuBtG4)xNT<&{SdZX2FYMmIyKRz?o71Y zG0|G!LPa5=$~sNogWV_4#Unw8->h$M)2Cqc%8p-mI1Hx1D3W^zz$ilrX%3Jvs<#IP z`^^1GVTY*2AOyis^3FAZ>9|`9yg`R-4N>4$N6F9-;J|k<1csl;U#Vjbk!eXbCYwTE zk4(w|SQJp&wr$WM8*;EwI!GB@@l&J#XVF9~W}A!?{Vj&#UCRVw=)!{yX9{^as$p>e zwL_nQaPm8N7Md>36l{Co(5XYkI5xQLC4v%BMmG}6#3Z=5?z$|F)y5An+oG*1Ld;tU z@yNCpN3wu&n8VBpB~i-aCD5w$`vTY_^zo<>3hMAQ?c>D&|eTpd}%(By4@a$vi2 zb0(VjdHarmp__JW-yz7tmH^SvIL<*YVO9yyw5sgTsI%1QdDsP3MCwdZi^raj=&|I7 z8y)C(sAKZsM5C<$AQUk1PwalGLefLZqQ) zC#Vc4uP56QH*C|m2Lk8D8`Y1c`5^iVNK9Rb^VseulB6}Yp?B&3wD)xp*sgMOC(%n` z-+J|O@F+6gLVN;6wGKO+8`Uu>lsKYA0toP20x;y9S3WZwAI07Xh1qB)hb~yLkbC0uqyD4=Z-LchqkemZSHV7wrOhK$U zFqN=A<6`t-VyZh;q_C-v9jxk61m@QGJwY+*;&@mM1t`ZHI7^c#{s*jzSzhIq=BIFI zVf3iIQbm0sk24<8@Sq3?81PeKD#nD0)s>IVm>}~;ok9lFJ=^fh4%M<1Tb;TvlVbYC zUWpDU?_Xm!LagvHVbVzq>)FCv;@sVrrc%3+ualB&xv6spA{ zUnLfbR1GAGfyD9xof1}bR}WAyF!@oKoeI`DR7;JI%6P9>J>5D=@hAK)7mNs&i!359 z#k+S!6~?72_TD;leJ=rm_%dQe^F{ujk`u{ zu8KYwhTbSFeCgu@2&X>2V@8P*M9s=RrWIuExZPva?g^z`Ob*i$)fr2WA|`gz+AHy> z`YZ($pQHbYxLO@$;zGTF#{47&p%M076Fs8bAD5oQ&sIdwIuwL`F8+O8^g9i;o0%|tvTN((j+B;I=X;iE^LmAHvHhx`-Tr5JauSf zg^lvW7gA+RI`8Dx~fC_P-LQNoz3fbZYtaZ_Y z6OM@U3U>^%69VV)Hy=kltKE2<>$$XCB7@AqOs??92IQ z!Z{~6FF*7+>dBGAp_<}nV%pRzC~}T+%lDA347uTvS-~=Ix zb!34csXU2_;CV^;w0}IvOb6;+eUkM+`e&}BMgNdtc5{_ zsSEYQNJwxA{{8p0eqH49MBAlM!!TY8GmqkuMVwtnI*f}%9CSkEF89cSc1V3Cy&(rX zkLD}r$4U1LVv=k+sBQ!Q!hWA{ysxKi6*W)Hs&NpxdPbc_*TNw9^>MLlC{ged@g$Ok zNbl{s4ExWnJptDWl6tTOab}3sIxKTpdCU)}z#7r;Mkknw1Xve+Mz^4AqDP8Z65X^Z zdXQ-WW5#8-beBX07pz$uBLa1Zhk_%&2D8@*`({h@u+(ax(mJlth;S$R*j>RrO9l(k z@x?dYQ~begH@`woS}R4X(CI{rg|J-bi-7b68QQFlp7 z@vp`>q(NB+_IE8NFQJCOdv__tW8vyU!@5hTih!b|w55S_V-&S&q1I_d8~eB1@~9{u zg7*@MvZ@r8{y?13vwM_W=9ZEu&lpA7MPw+#HnO)imzqt^0O%DO(HGW=HoZD#13jI+ zYtR7RXJ-PuH_jkU`&?xk&Bg2KO@1KsjdoK;&$d#ywK<9!qq<8G8tfM=ok2-cP*DWD zj)(Xtc>$gJQyug%GT`OWHfEZzdMGYS>2Aa*!LapeO*m8aa#&w9BZgvkY5Y)B1gww$ zjM~CAJ6@f}a1~C3d|dXJCaTptJ3(tFHjeJB_}D~-?0WQy(ql1QerIj`PV_*& z<;V|VJrZw^3pegHP)Z;>d=1o!H8oMsLiK6lccG+fX$nfV>MrFG0iOZ69iggmqwGYR zSf&ahG}lH;S!D(E6r36wG6_cFHP4#xu_)CORe18%72z}C6=8JL8`zgB7kC@g#~G`< z%2efC{GGLlol~eo*u572`v+p9iM?&nuj(d9w$@{jtzJue zRuQ*qP;n;hUJ^<5X!cl%ryNY6xe@g;{D+*+*U1LxbHu$ch>?_!-luJu;rq>62NPwg zm}i50E@pnrsfbQ=mx^6hNE-SvDcYu&AUo+H>4!iFt=1AnK%xqRmNqyJz-^s@I@I9) z#qajo<61cpH`y#mlxeLMPS4m@PFoY@)XP-VCS1oVTj)f}2nwQmWs@z+cghWvj?o@L zawZja*NZk>3<2L(#A*~08^q)A_t9_(Ia7U}R__rAOd_&d!8FQ^L=k87T;G{nc_e?aVh1}t<9{BD|4F_ZYHy+- z64f0ncWYDbbO4XYMbHO3V!})*{JbI2cu;Jy#AyZ56X1%ypD1;Q4@Wy@!xzFWoip8y zLmbw`u1v8vl>d^kPujT}*;Cq$8uNKrD)xGqJgnciEExL&n-n-v#^Pr6x!Cs1YceeO zLYGc$5G~Y>^RuhfXQ3+5(si8NHPzR~F5HN@?&joPg83G z-_`Mk)U#YP7n83{SAIDD)K$u-#u3eMr#yVR4(*+hp8*=4C zpO%AIX5d+LVogj92hto_7}uFaKXYLh+HXyLz3QHIInqFEgj?<7FVRduzi&*v#jfSd zk;}C2(|%{XkY)>~DB$NxaAZMc!;w2W-3{ULhh_mNHdoof_^nI)j+_e&95$_lV!-~8 zd2Ca9iH7w+ca?~UW2FvDNSg_|mtu8>I&UoZ!+Z!PbDXjv{uXtrD5plRJ_lb3WA+T{ ztPr-KLqurfD{RHHIOhd>8OX=wLtUIGg)ucXHNUV_ppVd`ams`?97Fxax~$@2LyicF!&rAWiPZp(M1kFcQsGl%HOuIU^=fH; zv{mVeaEDdpvhG})aJnm_WEU_dFPm0?IPZbB3XDd31v=d&h)7VC8Y3Ewzg;u;4}ay+ zRiAm&J1f$(+`>P8@zwWyO8ywO{L>eH`}6Y0-Q4o8|Mhpz$RGFckKcOhvzy{^9ya`^ zZ=Leu-@pk9;BiZ7=`!A3tCFZv5MA{M-Nd@N+lCzug}G_N~wU zY5dzA{M&b5{ekD>-|h^5`{%#^Ubev!UGlw8EnJwes`TsXOTKXB&&Os_{IbGZ1#cp@ zsr=g?9s6wj8;ibr#b5oW4=Ki-+x_!5RwQhm_;uw6pWdaIaQ^K_9t9TUZqpv6KuEB9 z<%h2MNc{B>v02?FXy(M}Mtr z?f<3fiRiEO@44aCIEx9j|CE%hmnbS-d0TgRxLXUkBRYJ6_ldwv1khHpqHo7$e>#vs zVf4+4f!{TQzoM?%O@G9**&gvIn%n3PbwZ=p!e@zww(d@1?TIKu%eZTjs}Jo$!{dPB?!B zcLEM+lpg2*k7tLsW_7~zi(g#B;cZ!+Fu9C7VdaZN6W*TH34aiF!m1ZZC(LAZ!q8II zgcUE6PIw`!6RvoXIZN-z>V!3+v$Xa_q6zQJ?1W7`9Ikqibi%u`I>Eh+J7M9Aq!Zqq z)d}wj-R9*ll1_L}Rww-T7ugi~UeO83aKb~eA_Ud<>CcaRjR(tuPEdV+Rv-RBIJvBO zktos!^gcTFLkqZ*E=4DOFyr}$l;=Mpp7#oKjV@NgTuVWYBBis0#Re}^+S?kmJN`Ed zi&4B7eNx?bIsf-={P)!UsBM+bGgKsY6K3D|Bp}@J;Ngv!Kq>(Dk)Yy=s-I6{kaZWHM!cF5ENhRVun7CIvDG;|GFTj^Onv?^HOzR9GJL9< zZqHOl(4sSj8yJ-OYP{LK%ooMd;XNM6>>$~AIhQ5iUrTVTll+5-+1H5 zWp1at7{{bj+gQTRmEnFc{ zc8=qI1Z==O?zNGYIFl4L?@QHDe4^UK|3LQYEAU_Htug!;pD*)&#`!-L{!f+vQxpF= zf?RjCj(=7g_#ena@$ot2**(&zoh5M&`s3n+#5RuRbq=9CTI}C(cn@mgu;HX^HUwDC zR|zI<y-?(lgF>WY^JO|(FltbQ+@pfjq%iLse6By* zm=H(W_w3lr7R>1vtU1N~H;EplSnM2}?&xuvJPt8YG~D%3d`n0D$D`HYJ(lV#)>17= zNkzfcIizypQ|xKO3Qn<~U6{F>vkZS@EyL233=|ukLx$2Jl>VqE@9%TOWdN=-0;5y& z96F$%O6!lg^=a`3pVe{*dz`S(mF|cV`~3%0f-Ljg__q7#9zd-f!@4wU>RCZz+|MU3RfNB6)S_z1K4nmvc?I*a=6t(8NHBk z5?d#olcH(|e!SQfDJVko={-k{z_CdFq~sS$jHMpEK&dI@I)~H)(NU>RRN=?#HQ;57N#^kU48P*FP-*uy*@R4-vnN_SzTSmI}l zC9Z~R@CB)nOF`i|WZxiA#8w(1<^3(O^(iS+b`$3H4aU4CM;C>q=iqQD1$DT3H{p9L zzcVlIxmVwh@$8lVmTD;pQC5i z9*Qn`!bxG?8E4O}NhQj7&OCp5K6$RbRCv^)bla5Sy>l?UcZM1M?Igq1&*E={$bN(W z^PBvi&+~u2DETIktFV2mW}cg?;g~3j_HWu_0R|PLLTP zpQk#B{|Tq7rILC6_$K3zhmYU?MTL0`=~KP z8eBhWOCk-IXOQ=2F1iW-g}a!CzB#R`WM}@3_5hbq+%V$PVRqsaL%ty(x>8!8g#)cA zT${8JIp1O7|CIG!xNM7X2nbx`q%VaX<|Y4(-)37plPK^=K1vv>ygK?gRGsAVr&x!>gw08hae-^H6K;g3uI%T|y2`Wt%D#oH*enasv~E$vY-@7XpEI zk$7@jMI3+^;?1KIr{DqaViFM!rjc)RnLaiCv1OlErEl{GtRlUp#(B4y>rb>M+`9j? zNJMm6VmeG}cxDU6W+QGP?2k*ip@4%bLcWSnLov;%<}%Z_TxZOWW-eFTl92Xkg)NES z0ruRntOX`Y9||J5n13tDM)Eo>Ix*>r7d6zoTWl~8a zrTngnXEK8FYSa1xB9l1k-!JYi#>}YtljV1NmYt)_3}dz=q)ixQ%;!50vG=eq&Nad^ zDlX8ZY#F7+=vt5#iic3B;~ejlXpM}Xg!C?QWao6Mp`?kV3%Z4RZ5erCB zd|GUb7wJqbuL#+SILamPiglKaj-@Br68ezg*#C$z$C^cXzb%QhK9~%WkPA6ev0bwu zA-R}irm|fP4vx?zOmyBBZj6Bn(mEfPnVrUUFyg`&x(e+y&W_J;dCXpA9sGS`IP&UX zu^_IKB1vLbsOZ;=s0I>}KsC!ny6j1Fk}lV$vM(F6sVUy?*plcwBW98@!EZ6-m*Y7Rzls@Iq+|JQW6m@z|HYO> z-?7~EfC6Ax0Y@jXsjf%2S0hI5nx*|(o@^>4;1UjjI3`Xm4;SlrU1`jZhSwHb5`D+( zu2UWo0Ay{^8xG%EKu$oJR@HpXBtn=TjzdhA8tXd)E{GB%f55n#@{ZZN3b>_2$XO)R zSx#~YLOJQ5p`1mfqPi%=REF~sT|MqIW?EB^du&PcT|MrksW#G%W8xaz5x7(6Oy>|C zUFM+fIP#`RZK&iJCzH`B+KCZ=0d!b3D#l%uS2gw(XcDGbnlwXP^;-;B#-c|u7Tq9T zF_4~6{xy_Q(Tt_KW_ZRtYnm};OQP?Zu{16YN+PZN&d5D)EJ9x7mKEZocva7RnU2I8 zjCs(Ic)cx&z9X?aLc-a#&l&O9ckVPDI*uBXaa5J;)zA6}UGqI*iNR?@fU*4<<4(zo z?d}-c;;v$N0B^C=EQUgb=O`8vLMfwhxvm30Y0Rsp10S~~(RUrVE7pPC`*0`n88X?^ zw0>$#)uUW#8FywkYq;V7&l1t`gfd(ZCDw{RGVZ3lT5*@uirrYVlbA&kvj{Pxlxn#c zi`g>?utHal-#2DjQ;#p(lIXj7II(){*@tW9aZN^Tw%ozo%^B$bVJvW7pdAVHo?=}x z9IvERgTGQo^WTg))6o33Es4IPS%}d@{pB#O;KYFDIzw4|n4FYzy}_7Xx2#{QuY$z% z)*|ZJXz;dZx2}@HQ(;}D!+MP|a~iBy+LGuyta8+$v{dZa(}3oTN6dGo%+ zSpA>I-I5op8!-)wuzHc1FD98UM$E^y8?a>o_p8PnYQX)HEeUBiKgHP3cW!jUX$-cJ z#&~}sQneiV!TBtaM0}hHLGufC}X2s5AWZX9x^R6lG zT0z2M&bFN%t~$`b{+|*G){(2mHBlsP370)(q^xIe%JAK3+y!~zySh+fPDL(S;WU+! zUUlTstQp`oW5zUW_Slk;!}%75cfMzU&7$H!KuGxkfgR$Isl5h0TQPJ`8jF_~x-A7! zN02Nc5d5j*DQhZt%$O$)wU^nF=sRjx3vb!uJp=+gag#)s5^}V43dCFKQc1^hcWYcky%`* z@z)a&WE7bGm@x|)1Ru5~(RT>e(s7hDn~UQpn>b7_iAKhA2IjYoMam1zy27}^Q&I4g zz$l|~>I=r)Xc+ybEs4HkwCz9zXQ8FS0>bQtw~nUkHS@f{DE`03Lgz)XP{19`;5r#5 z5C%|koq#o?i0WI$>}jz6gDr`^!+KSCj2JB(=7{>t-jt!-yrN(J|J8*MF>?23jr?4C zB%`uwgE3TZAtVUt?h@-x;1S5h*pD2x6nyn@v1&K>~p`x zhfxdNM)sc)v%Fh{dsA2rmwj}zF@uuN&wS(wP1-IUwbTa2-pv@qg{%6tOxY@Ia?7iA zBzPf*$~2p?2V#LSOB!t7`@V&3{eHKNks0k}$yljmwqUS!823!x5x1c*MtsFvR+ujZ zr&W3x{Ef!kXgC#YN%VbqEk1}+uSTbx46?<)G9Jf`+0To|l0rHBzJfuJyV_WIShF0%MW#;?UtzYpW)x3x#*)p|Zovsa^Hs)8;hELj(NNa;d zPEw{ddFzk`3CYEjZ3%w3Nle_|d+|1j*<9tThAyi=9B&x=jxmJUT1!2UdFjCOSsTXw zoAFmQ-TP-j;vyEGUlH$3I&_Y2f20eT%U;P%t!QRz$fjb`>iJpIXr11@BHn|9z53#c zN-&ADc!J{wj|_0Tq#KO+*WB@U$FI*M@0pw8j8={K~7)aN;XS7 zM(!?S5pxa~AcreCB#)x#E8E@LOh9mYIq$nCWy(Rbw5#4dK(3+T$vG4`)wloM|WlJJAgx1^ZUQQT>4l%pPm^g4WXtUFH zM7{o?Lu(G~!o}fa@*um4U&c|d+yd8S)0QlH4X$jJrrV1CP6i8w6a3jkmam_*ZpO&Zt=Vabt-z#rudL(bG?w_o-HT zKPMYaG2vpZJ<)1RwJS+=n5`k>`6XlN^WrJpq-M-yF=SG)=9gzVN}o68O2g!Hwj`u6 z_^d4nxo%?3xS(}YpWLI;{A1KeRvmp;=a*ORIG?HuhHvV+Ebk#~4*!?x^@XP(4enyi^; z9BC(bR?Pq6Eb~8X%$xG_n-Do^nI^gsV;Bk);>nDaK=ImZe`|%(4dcQd<&o z*ewM^enkpeI%n|`yOLPHTBzPOG2vO9J7Wk@Ow{rd?hLhE^rvS;{C=N5Qw<2D7lEL zFp_I}OB$>Oo^jXYRfF4*jSFR?IvZ8CSRXi|D@rb6*%Wh>QPMqT%&(>mqqZc{+F)Tx zq%q>;y9Ei!#Xs7X01y{Am-l%T9LzrbzOdku1((qO?Rd@1`I!N6jUz5+d;|pvPvFmu zpp*5adPT1X;>N|R4>am$8?{cGBUZB+x9SUVnZ*ZY~kIU6_!jvr4=8$DaGVfa;J!E<(ZcMH}qofa1Rp@R|>&j!U(y{;_t z*JSx2zhumj2F0grNytI>^Ni+vuQ<2zp<=XSqfBvnv8^owwOQIRZeKGNF)wacgh!9j zt_<7`*eD7fHRLjupMPP@lZM=%*^XSGCpiMydvLoB1v;&NkdG@vdOBrc-0+o{YZxOYGtA06yN9;7y1Z%k6uGj&)^ zBGP93Hp6z4aYyAHWjhgIk7q|*SHSWh84`)p^X#29xIun_UZlF+m{kqa>upKM!FL_2 z#eAF1m-hf4Ih7I)PZAN<5i0dkJ&mJv}}Wq&Qc# z9#9Ecup{YX_whTdP$!JLIIluI+C!nDE{dz6qb?Fv7U(k3MRdp_x(NRfJw!LehCL($ zM5K5bR{yB6NSfk3XiFlkcou%Pbk*6US&)!i^vP@3e0r*(=1iRvV^wU=NPBv{TCwWA z+PIVRsvZskPV!f5g#5*eyfsk61d1-6V*s}CEqq`~$mLqH4eD=6t`J1w+fIM$Nu3sDE1s7FfDDD@0M_#H%xdQRp+~=h9T*1$I*vgu$Ggkk>SQt&u{#KBq+a~vlXMbc74BAeVB6Trr^4dTaM_SdgO$P%%3vkGplk|8S|upvD}t~9P~>BiFwcc zZ5Wvj+Pp?bP9L{z(^?=2S#}e~>o#M-@{YQVg&^h();Z!V0ak`@y~mg#4Xj&iN%S48 zn@_e-v4p}4EZICPkb5^?Sv&LW5wC>jhiHqpbtr>O#aagubXG{8PJbzn|kX-!A>@$hAU$ypruMY1?9A9;eZnjIQ zRmOAHpVt}pY+n7rVPi2*e3wG3C`Z=0A;j{U@YfnMqG`#i1c{62UtO#8`fwTUYk)0p z2(4yUv(DL?5&3cBj>wCMqaxx;e&cc_X|LC1Ib$C&=1ha=L$)O35c&Y4+{+oW9zwS~ z+CnM_YmXD1mUGx|;UwwV;Z4ru=C3o{Uo!5Iym0R-OtC~bRG?KHCy9#6kjzj375@yc z?(@d1YWRPS!81M$%eEkM700vb{E7RA({+OBhYZL+8cUfMkkti_UW1$B1d0t3-JLby z{@$1st;7GumV_K|->@YiXHJIwf@V%0_7)^07d$^$kdS@B^S1?wFy8X!+2Soda|6~k z?TS-=dBPKwK}T_wXalQ~3DmCB?yZFNs{U*oUAcAR{H!KP(#+_}r?a9fyNti8Y5I^L zaS><#y|OwIbN+*MT!Dnu5}z_j`(IDAaC?K>ns$zgYY9fMLm7Ra==ZKA4YpJx#+{aJ zsWhm%w<#5tC}+l+Pmzt*0*z2MI${#jN)XBx2W}T;nX{9|{AwT{vn3&i@I$O8z5EB; znMQ1`qmxPK_DP5C5Tgt{9Vrmj=OuxkyE$Wg&RF2Q7+)vysS(FT!7&{MsBo;nnc)s} zj9Js*Y}u0NJDeN$y8+55snD3lGFHOQ$Rh`n81`txz`fsCw7kG=!fEH=tw_AlSOjmy z;A~lX6AQD_Z0|AVM?>qKwj}zF*4hJD^9BwoIqdggl#S~Ce4l2CuH|782 zev2Vqv8hkaX?H;Jcto@_w5klY%D;kfMuFi{V-7Wp7uk~NJH~sXN>OaEM;Sep_BsOq zx6x|5$mo*!MW_LgyS3>6&ydyfTB-d8mNXduUB+FLcZlB_*Of}y=&C~&O$>dCqC}$M zfJTU>PPrN9b`2SGtLehcwj}zl3s)TTytbHa4>ZnF*b|qou^B&?^pa+4$f!PIEM#6( zuPjW0OELeJVlLTSpHsohs4^KbW=aF^q%DcQgSX+RUq3^!PH{L}rgNL!gaLcTSg^c+ zZNzN`f-_DrX1KN)C$^k3W=DgnV@sm%P~{EbbZ2YGu>FX!ka=NCT|c@o>$Hpa8-HCx z={>e2`i|0YG@xiKwc;RKI2HOqbP8fX;h_NgX%R6>MpcqVa~|k1=D%UwWqC2*9}iU; zrBdc_j`ZUy0Y&CiBuO>F87E?V#+Y|aV}8w+MBg=L@F4afo)!6~qa)6Et1;=g;>bLA z%&%cX3yw?)u&NjnXGtWL!|YYogTFKGh`f4GER;h@ij5l9yO5;lio^CoNw8B#kwkHy zGcG;+rZJlu6x5NPacSZTV>UI|m)er(JM4EvbAtxI@V@fme_Mi# z)PuQ*up-=Q+&y{6KV3k@E?ZI|h_7Nkjaa4c?cZh0uci@0wj|OTVVUmZj_0(L1qsQ; z&9*_GFzNV~i<@*@hm*gk+L-3HV_v(`C?|tH)z8Gq#=0>?*;+{wW+odypOtJpWBgT3 zw(hxUy#4iCwqAXRz1#`@8VRvC|(TpD0_|Z@uZ5(){u4PrY-ZctkL|2?v5`713hX9O^~^(xSFJ$97zlf-eXwbZQKQU zVco&7Dl$a714Y6OXB^;g6&67mnHhP~cNnv%0sVGc61jo4b~-m5I_I@YKIOwH+;_6o z$T-NXS0l#oSB<61i{WP6l@M|#;&w=WGj|GN8OhOKGG<6a>{Eh7Pk*%c-g8@r^zH}; z>@?4+%ykA%939y~HWVRE=P*tKJVUo7)H4oLxiC_U>0cOkVO~u4#h7N7>54Et7KIQK z(RvcI7>lXGo>jv8XU1G>!2gLY2{}~%h;?Va7xZ^Y4cV`|sVMXs7b6&xSQOrBd!x62BRmf!lA(*a$Gehq8&;(mRI)UvgfbU(&2XHyLA**Tg&|RVeL+7qPyR{h+8$ zk-LG&k5sB z%d0)ZQhPW*q!bTi&r4hlq{y65nvAvhQDf#crFqbn#Klya^scT8RvK%9tTb)oPP0&& zbaI&@+!@Zy>`IdnA$ZD|c};2Rwj}zlG`NPQ4$L8TOKNr^iaW^tr_lj z8;hG4Zo0&c`Gqq=<;18b5@%4*RhkspNLYZ3=)pUTS<}FLyDf<{m=@7k8PMg0k_8FL z1;+#}NJuU?;b}oaa^YP_a2uEUy!GOyvDY7MOo&pwo||UB9OtqB+*nhx#{r3$naBR) ztUUHtjlZg?_*Vppi?|A(vsb&BE!fsojJcUuy26#XkB zHs5RCMPk2WDtR6K$h}{4EVY$9K{}WTe2#=oId_Cxr&>A@~k71#vPhhM_vklExgbNZkp_oSX%g09l;VsHKRjg_(il$x@wj}zlUK=0v0~||_42pArHdf(o1}&S{qYVT7 zHe=E90==m)74cRq3Eoov_@W~jORF~<^P{2FwIz{8%fgA3elR;s79=DWe`xCj5Et-+ z-*$2R;2pSSinc*IkKq0t?C?D1(h3I z)3AfnSQnRCu~Xd9c&EypfTQdN|ZtH#{sHl7Shidx@V0=$_pKt z1^Q-D;YmR#BOm%YV_r0bUTaID?+9%@;wwW%IKk5IGrw^r5z*o31boS zB6daL4D-l~)&!3Vav4d%QiQ~1f=QW_R zD%vTU9CA0#_S$y&5~KQi#^UEib$g*4@n2N&ofP~R<9)8G`OH}7{;n~D8pL0+CDC_? z*OEIt*+5((`=W}B=M39-j77=|+dAO@3!b9lQx&0%yx@N`=0!v3pKVF>9igH;gbQii zMzift`cL!KB8XGcMTg!w8KX>&M8kI(*{iPV*V1N4IgkrEUsV=L1hXtMx~QU_QDVH+ zm`@G$O|~S`s9U(f(v#+pgarx7#b<3-;$i&h?H4!xDyUhrxD|?YMORZkgy0l*~U56aPp6G8LsH%q-D?_^Wg6oi<+~8aZi*u z;#8D;xY&Q?De;V@S<#G^F)LcHH*87BkyT^h=6j90hVLP$Ifp&B-9Z&x3Lfn-!}A_v zf%3z{_XyOA;}J)(=esm3bNfzXRy25KY)RyX$2w?x<^GOe6D7VpdIptTUlOWWTQX|D zW-Mo3)UGUyg?!?C9vV|h0!~h!OS5vhziiBuhTks=5*N{^tvu$6Bkr;+TIw11{9hUi znYZUx!IvRk!hTP5c9u2!zl}N3y8BOUNyy>y$Bfu~TeE9MO5r)NN?{dkiz?xc;8rTM zK38K#Zqe2Afv9uTeUlJbo=m zNG|4>97V&^n@49U`&>^7`Fw;T6x-jTlv;k_ub$GmCYOh%ySR%3oN zrP(D&Ttstw{Ud(R!Or8SX{!rDJ-7(b^9EDEBr(bN3PbdA<1Wby(e;J1l5h%Cv@HK?tZF}Lj6+^k+fi_13HY7>mY~>a(w!LfsmosK@c!P-7{M#A>DS6@EACtg zITVxi1UM`*hsv5O^R%=r#!P9zZL}rPci`?Bq1#kE=j1d_)&_2F002Fn? zBJqkcLfpqOIjaMHfwWi!?lbPHyo31OLLg)=Y3mRa{0bFS&hK3fuLJ+W}hq-V!7z6A-%MZY||s}Ip>q0MQble8>+@ZcWlCM4&L zIoh(iJ!RbEdDZQj0*V)iSD{njwdj}kNVh;$r;NOE-Iy;;na&6j7twLMOW9oDxDzhy zN4+t{2MoknH{o{+_{3@|^GM(B1yN#P-)`K2d4avVplnnq3OS3AllO-wy>kIQuNtER zLY3Jjb6enBjQQ4pf8Lga9KUa1-I;IK4|~NK^>BC3pjhy84T$K-SFvAHvGb$i|-k3KH&!4d+k;c=)q{~@>&4~pG$wj|rg{u(m=NdoS zzG@g7Jsk>J9G{fVbXJO-Zd_Es!t5!{qSbIhdSa#l+|S3gYdn$ zROzM0YLjiisLL`-l`da|F0Iz-gEymhdGH=L{;D=)jtCMx4b=Rf;&|C4k;$%z=i%n{7$t#=tsxj^aMi z3DNn(Dfdf%%&>ggSfaeJQ0<@KDDvPHKWkZ5andJ^S<&$MIYFYQ8Jl-MYkydqG)>p# zHm2${dGKWk`t6k4p-Y9zF9wGo3!tj}c(2AYs%FTY~Uy`~F)XiGwl)&I+ug!I2yBQMDRn!{>a zTZ~nwaE>(`BZQZ|pq;W8>4&UTE1mgSCTRXmcXa_fHNg!f?F2W9Ezbz~E;D9C(~rf1 z#Kp4}MatB;INjfgEH%RZ9F*g$-x!U+JViWwDj-(6r|~0*^L130;|P zi~W0XOV+Jd7{lvJd301eNikksFu@WAUPvXbuiS*MX%Muu`LI%I&}_b9%p}nv>4gf8h2t| zWbY~Xk*vjWmQ}6Ag{Z|q6%~2HpdIfFOJJX6MP6mhxQ6~KZAnNgGR+D!-%G5a3^hrX z<%rDAaM=}OH#we7UuH%4apTU&s|Z6Gijb_+5rJB_>>>{S4PhRHD-rl5C$73n;%@dTqy8o1j>wBT4z~y;q4k0YvEe9rh8TVX zWI#`U+bVTiyF|wwj}xv^tPAXFNX3ygq%5brVa5V!g*d`Xluqo=Y@7# z;oO9n&k&UsOiLpjO>-)yOZ6M=ePiAV(Wh z{04j~)E$|K|1IOMYU=kJg2Y7(K;8Nv70Z@8r6^T(pb=l|Owp$UjaJL6@pjzkH2YMp zz>Wk1^>@ZymJ_J%-hwYB6Zxo8ELm6x7E2a8?MjYvc~+3=o5t*F2!Gv{gdEy`$x1Tc zL8f&o);NKx<)?O$WHn$IS8tmir&}9u-Sx;dNSr2_t2hq4JS)+^!k8Hiq@}hba)V@@ zw%dHVG3B<(;z&IQHjpZL_4D|8wqm?)HI^^$u-j5-Gk;>pHA^_6B;-#4E#o-MUB(<~ zpbZHU7twZJbs8HX;@}&ODyHORHXgG#Wl$b5?t;9aTrIZI$(@nRX(lpRR&T_ZF%6rO zwj|_$I>zwMx7FM7C^jt9`VQQYgT6b_z@>8j(_+v$;?hSf%e>SKd^0%`T;HDen@Ck zhM9i9u^gI4y~mbBTB9tMM{D@gN2DmZfxOI?Vxt zm4$vSxHcAOWQ%GHl`{pZjMUW@V|FyCHrkTN4VC?pYrl(|CE!Jn`=IQ#O^(~my;?D1 z_ZiEVcPwr}rFH2H&F=4Vu^3lIS}$%lJkP9TxQgL-KKBA@V}9JiK#5ha+RD z@iAjIG&nwLOCk-2#X3PQHP}d6kdR#TX{oX11ZIqu)AmZ0y8l!sy;WF$%nI^n#@(7% zLDm-d&<2Gg#qr3XlME1Hu0ku8ZdJQfH`CE>)61qsQ;XRb5#3B$f1E|Bqi$HmR~ ztv>E`TA0P_9xlFXok_-Es#nFiyv^5}ij}QxBwl7NuaK3?+hF`vO|jMr5*N`qy6Uip zsSZJCN)XI`Gx6+Ad6?g3+yyy1zI%0HT;a6X^TyznSsv6LW41J8Zm}gH2V0TBoo^57 zssp&(rBTC)ZWP&c!Xa{;he*<&n!PDQ_?WSv`5~mMTVhUA7)m#IWma7JWyWl25I$^6 zqVEuHJ>``;NLiv-ffYO3!gXh9$Kbu%Sj4>GU4goqkjE5oN&2q zm{|vBHi@e}Ywk20SsWl(@|vh;sVBXOZm&iR*%yqZ%M01&!X#ZhD!41E+$o4~_Z|0+maMCap1t{5qvPkwxN zV?pXyRw>s?Y$D2t_pCBzNCRuREr~Q(77IVQcI2^cK|*pdhdXO+ohg0kNE_%VCfXS| zcJySjg0nk!bJnH(#{Hhx5?sSKQD#}~;$*F#EHPW*5I@Rxbn4i8*b1-|5x1S6^I<2&9e!C^=?f#p$d-+JFfX!q7shc8 zSP_y^s)QshvZNwy5(~=Lx<`W2Gm(B*EPv+lp{_CC8uCxtl90prFTvC0p8}vs;8CR; z_fFzkxH(%h#0zfh*Am1jj1#{pG;vjA%x?nCjCAMsY@yg49|Zazwj}zF<__g1C^FIe z({p!Ro1UDW4c>cU(wvq@*R?F}GClvBWz{Rfgn1 z3l(kCO>Kz*SG{>rG=OTxdX+sLQio)wU3cSCp*G7cl)mv-wE;0MNc6;D{+-Y@@lhzz zIUk9+Nq@{1>W#*t=ImfxyPiIkM20Ogi_)GoW<~4u*V&SgL+`Z=TrbDcdW@{0oT_)O zSIkm>%=rA2u|)atq1>r=E-O~KI4e^531e0?e13vE*Vr=I9v`$}1ZD9KU;IR?bR5V& znM%rJH{s6zJ!6UUcK*gf0M3fhl~fUD@k|W>vesU|Ys`=a!Ix}F$RYB1TM}}PWJS23 zIdYDHYO69^N7`7zQ|U@%zMM>hI!ilNp3An+kDISeUEM2SS((RT#A9^ulWJl!-1|$6 zdD8UfySCs<{plBSu&~t*!f>7woq6T(!T1U9qPw+sJ4SB6xR>${`zx@IJmgUx`4aM| zjQtEB{RU&6G~~9~lIS~f1E)M(rz|(X9)*{PO-jl!Fe8l`WdM>u=6{WGJ!aeid2!u= zQkF;pu|XDFk0611vS<)Wpun7wbAQN~MGfZrZAtVU=9?d;eOPjEhITa^q{#Kuu!!K4 zcM55vHyP}faW~`z`{qK2j5*T)eXAhRbLH4` z^=|9%Tzj(BzNgof>q|KePH6!$k#{G~VA^7pcuShjXeq*!}2xU3ZzhKOp zhSAU3l8}S$r))_`Cz>^-pH8&(&|iBD%bR+;Gl|%FfPGl^A55xI#&cGjzccQZyo$4~ zFd6bh2mPW%Jvo>&wsm~dm={e^zAi}g9L)0{23m6J*oeqSC;MCe%-y_VpkIrVrG?gH zAW}){KwOeF5SJP=q4n<~TM}|0UM5J)yIEZ|d~o=f)8N3U*Gj^Xe#oHgG8QJU?ysg} zuTgapbECK=OR{1;L&mIV(A;cGA`Oj&fs;0p2cQKB$wi-*tE*17s9=yz*l7FBl*5~T z$O$<;iNxg%#()PYivpM9l2Gfyk^ZUc@C~9LGg6T=B6Gp zMjtm8CNDLCO3Wn*FT z1H32f@u> zXK=r5+#z|v-BrNBW2k3Ck!2AQVc<>i5kQed@j5XpWWG{||6hz*)!_dpTN1h9w_d01 z!AT~yPMN}TvjuC!-Ei5X*NOsb!IeAuwFtSDPDEk3kRpjf8XEMh8CiBLkWLF88@#Gt?JOj&Z-o zxF_?D{+ASxQ6-6sEHI{C2png)g*6D%z)9Yh`5z16xYIb(~Ttg@`wl8{=&>spik2z6O%5mz}`kdR!IZ1c&)1xnrCb#Y7Gu0K%g zAn8t()S}e?;d;=)<_;wP5ao;t+Y%~R-M1*JX8VLOXxSP_GG|t^4dYWGNV1ykCyc+U z*{mNIBre{>wc!B#H{MGz+=RhK;b8h$pzJ0*(!XRZan63mCQtG#1KyDK=E7TP=5*wRDosTt7M8uHZW5!=Bsj;J%oo6?ibV0*h{%AGepfBGU?-%(4QP8Glt% z!b=2+o>pM~lNs@JuWzzRKH_12gRzL&!(Qvy?#g(A7o5byJ+nw}n=u<&PhV?GLJs$< z7_44(thU+W;)6IaxP|hwHp;o_umUj)hQ}>bqQTL`&I)%TH3Yhb?=q+l8FxiqP;mon zBujKQIrxtbUx;KW#TDWeHHVk9KShl<{ zZoATYgbQ+u`ed!w9Pdmvr-g}j zg|m|INxJ%DR+Y~f_eow=SzD+RN9;c{M~a$c)V=^Fmk%4*(18tukdcB-aY48C9-dH)c))^)GEn~D)#F-nR2z2Zo z4%uK4RQR%{*_(}-)Bqf?B_Rjf4YnlYG|Or<57Vp#3CRU7f-OkMzWDA1#z5Y4abqC+ zQ6OB!yyWb15Zy>`;vGb0*rkw&=bR|D8)L{X-RTTW`sKPmQEBfObavmedrxAVRbLi| zLfXb!kv)K@M^d4XP>E$2^eN+SY2%Y2b>UJawnT2 z62<$6Ql5gzi)_r^ZrndPvFP56N|^WpkZf`N>OT+DXTik4;B-;;q zL8;}V+!7-O^9{}xN1YZbqUjE46#PYZ*e1qBH}_i%*v}bvOkThSa7IwfKTS3%{^NwI zj@C~bGo_*RUu;Q83;UlL@c9mY-F=cyGjMk}`%vH}0{pRYN99$3I|_7e1AGkR&xM$DGZc;q3WS)& zMhz$b)`dqhE`*##A^yOaNlhVs&z3~r72-~z5Mw*`Im2a9M03h7Pk4?rcj6?txwYW} z=&&mM592P%s|vTXDvT9fAz`sa5~>>;angT2P53us9yLw)wk?UiYeG?ILP=`EQ8x%0 z0{%H|f#JK1xHC9E%S6p}>JBpEr3mpFNg{Sz(K$nN4*08$8Pj0C!j?qeVZKJdTn5Z1 zT|_%XWUcAdOFo};lbp}zYRo_$G!{1R(7l?0#Jy9*t8loOSNzaw>vQ+8F((>w_u7)^ zJ97I3avqS|@4Epmf@~o|gHmyvQiM{`#yA~OREFh_-D>6bpTtQz7ea^;uNZeyUc~QY z#8LXH%2;UtTgH%(3c%$NmDP5#7|MBf407S$k&2oBDq zN7@oapR`#M<%kpwO~u>tyui>cEcVNBFC?mz=zRH@Yub>_Tx&QkFy=?Y@q6F5IPN{% zXdzD`)?r=^u;Er7+SiHv7m`8K6q~~?Jrp#tC(kEKq@cB=!DtT{_io;SdRqZ2Z^$NA zW>Pj}jaW9e@+2F3{*i2&0^DHCqNV`bY)SNeAYV7q7;obyLQeo($Ay2W)As8)K&@8G z%CP5X&%hov7CA4l+i*4@^DKa4o{LGIH4q;(W=8|@uq}x+h!!)hoU}Q|VnIT3amF@E zL|mZ8_`Mf5zjkkwU)w!Le(iYUtT#yswq3X5+L|cCmhc*?<8f~7b;fXJD=78GT)DN^ z8h=aEzE=qn7c;l^@BxZ!`Qwq5rt31>TuBijJPu8WX-a%Ss9Fl4mf> z1+v{feS=NVM~r(tC&Jx_3#CNggmHs7i6`!`;jR&nqOMWn!sLF4u8}tcYF6t*#u8|H z^8s7EvCZur5}^YZYrjWZaF3noMyKU8rs}h9pcPxJqkANrH^Cc5PZcPV1W6Z9m1HWcVLe3e#%xW~>8AA^3Q-X+; zh4zia>T;azMtG~PP>`fj7{1Hk|E+OXxIDvKj;1&mX{sRf4d+YI%}q4`-zY7=~Sh{t&eaX%rAJY%LP zrHOOCfe!XEW7agV7u%BPJJ`1iuqg+Wav-q82rG2N0VA_}2G&#<{9VS~lXsl&W$?>I z%>@XfhkSZUa?oe!z>qPAnhxA-OQP>OaEH(V$|fmJz|qJ-lwM>!?^D%}KJVL;VJ&#r zxP$U)!ELMso;uZMd3oXV4)N$L@}_PIP8qYPslf?b5`9;Ly+RGfcOZ#`*`1<;9ui4> zDVV7HLKzTc8fnK)d>>EB`diXq1(-JOn!E}SngL1;v1mmpnkWfFEkGz*Q4uW!Po@#i z8gr=OAJ~#e<8KjFkbwzaXjqVtT)ekGPG*lxK_YA2qYZ1($Ba8TuNLLbCVbSG1x-zU z)Rsiw0m_pcNT8MH1%~dojfKt&on1EJ3 tIR2(BiN51#nF&ZhYe|FA{%7N^$&2>9 zWfT6fC%}0tWn5j$ zhXEqccP8MAx#{E^H+g$;wH=3?Z`wIOD^iksu8{L~<8NttcD*3cGvqw)S^w3Kdfu7Z zv@;U+ZZh1XJ>?<)ps}3ULtg9C?wZ1s;HMa&tvm0BjX$n+@&Q{Cav0rbOF|B2hWdgA z^K}=(1+q%-zqo_>?nAii3?~-{v<^XrY0Mq-QO+^#oTj_vc~3a5x@wD*1{N*{QMVLV zGbJ>$`r3Gazt*@9vXzngA~nFpHpc36_*AGuatZM&GI&JIZLt#r0& zn|qY=O-1o9?gC_Vs6L;tLaYV_!Ob=Ff(8MT$rVQt7M&5-l@JnrW6quecB@sSM+m7Yn&BY7%H04%XuTHP?0K?R_Vr)98N*m_Ph*}<3?klbnUV+{rp47AkFDrxFCVOR;?{I)v!}qi%#=jvu+G|TSw+!EqRkWy3>uTu{B2}|XBfOg+M)#o zZ)S85yopxLW6fU(>jb1ZsLhXp*2_&vgpSrm1c8#i%Tzz*X&*X<1?191{TxqC%OdWn z?GznG0E}H8{JIuUV( zv{_e-<%lVX(2b>iKkNd2Z?GA78rIa#wKo~c_h<_f6iOVSBDf(xcEODgnmWfX-mT4w z0?j*2NrVo~TsnXuk&pFU%{|%t4w1}T{$*G0Ftq08cUj`H+j{f{Vm0^Ckqk{C$GkSu4MKOY>>#85Y8!& zy%N05M2TS1=pn9U&e9gUel4S@*qMV}PA+%Y72$EGsJ=^^2SxQuOi6gfc`>6m))N&k ztt{4Th7&vXvrwOIJ9f213YhnWFHT;KyyXOai80)(EqqW6&xjV~QWG{ByWGe6z&#Fb zVeVrhZkU4UE^VF^Om~=)2pv=J)JM47)Xr$s-eiml+QJ0Ir~|`bc|av|qhOKK{YFwRHd4Ry zkJ{f-%=uYU5*~z43ld{qovhyFx};z*48K&IMv=f~qynwz@xmRx2TQ;hr->oZF973jVGdb>5FVSCs7s z`SK87KEanyiA(*0Pdcev@ST>tB~GeNSY@`-9onB{BXBw?vJpCdJ-K+E4n@ojNQ&D{ zDYm3BKIy@Z!9huBi=fo7Rxs|e&Da+&4irSN2Q1+*n*L&6_X$?mRodbO#K@V6y%gX} z1Zt3c#a6q;_Huld8OUfeAd79HLgKI>(Xd-L_HEvoTdlrShBmy>QUb*j!tfIVQS6Hr zo1w1e{jmir-RB2F=S5b}TeQ^^6rZyY?v|xsZwN?%VQ8^H^{|veY<3h!p4iNo#TSU*cYkjLEtJ5*unNCni9gvX4ImJZLHFm{m2G-gPH!Mw%kD>Jv~Z| zB_9k_;hS1av1i%kTfy=nZH5#qA7CI_(TFX*p?qz*%f1AMnhq?sFU92wWXF0Us7dTW ziZAt}Q2CWL{XK2Lf@->nH;Tp8`s};f-&B(7{yI7wPh)YUqEWvwq-?eCwDS!c_Uww_S6eya926|K)RC2^9po~)~N z{K{J2qRqahttVBjZ_@szqV@AlNt`6DTXnULUs>z@+U#p;-BPul)c&TT^|&dCTCID- z%aKbtbKy+sEv3^|v4;jFQj6SX>(jD5cEaj^Z8(rkAEEv=Mq@>6z3~D|P{u+$esZTP z@J1cplaIIqIIkgJGY#d8iV|Dfo!YPkwYKvR^GwJoLQ_LDFXRMeDssk-riufN;tF|v z@;kH{RZR3Pg2YK2N-f@;#-bga7IuW3&-=u1UO--v-rvOw@&e=bX>D}`#Vs0*dt5ib zOszpasm+f9&qJmpydwJmBRtkU!$q<`zKlk~A{I<3Cq~B@bzsjyjXT|lPcwo)))qG? zf(vE;okqOGZLE|NqhOa?sd=w#{Xm-)1-$Q>k_a6<9yX28tslQ8tPbYHXezldTuMdft>o=qjHh%1dHtL)$^2c=*vG9?i@N~Z~w zlC>yd*`gdWkgF55-mBcUYjdMuxW$x2=ooV4Ho}NvP@Dar zcu?iGO0C>%?GGv{?>8k;t8#-Oz%8g)*^;@(Xh6c_VuVqI>E6d6;Y55vDuTSgLcdE} z^+C-=C;o_6fbY`gN3o{2nUV+{N5j}5K4=YTFxp?xR!vZ}M;U*_Gl0LGPK&zO=3 z-2ehaC-;FJ;CTl2m)ar+1y&=Pxd-AC+UzJG{?wF2Eri|riTo%Uu0|QJ!FO&uX5|wpa>b$WB9YZ=e6tqz7vSE&Hn(uCe;D-$`#*e%FOTx& zF}^%5F7<7W1gz^6Vb8-N9Di$p_P3-#&8(1^D@dHg389vXCVd)os(xqT&es+$pdy`C z>}Zx~x*a!9r|Y#ptLSu{DT($9ENd8+v7W_QOQ_3UZic-YXHig?kHao5i-$bT&`-3W?O=RFO`{&1d}hkBSl-!W*>J6x0wlc!sbF z@jysSFPt}tDR#?N#6*OsDlrv{xKW!=#UidVB@wzstf*MTYE%R`alOcHPKXyn(Xn|O zbsiyA$Q(#@elyU2ow5IrwnBnpzrw?Qb*w-FiF4qvl}d#B=6%vqAm0gbUKQ|uZRQlf z?=>Y+3%J)Y8oB=Ax6!~37fUfkId_%F3A7{0XKYMI?#fsXUh*$7e zvR|WM7(o&mcJW>qJuc6ilJJVya}4cRckxEmLi?~C6(xp!NocT-ZCk%sn@^>rE;1z% zx<%+W);=@Pf1R=4p{IZbT!;cc=p za2x~2mB?<)u>xVMHa7}{O@hQpY-(cF(YnR9G`BI&=8A~dcQpq?#ojD+7E1G7hHSaE zl7g1FkuvMBhSrOldxUzaHfuLv$-6Bz5(Y?|9Sb6XI9 zWvSj~xb|xc6cnz`=pc6&d7hiPiwYupwZE<)vdff2Eg}Yed~cY*<=TLR$HfS}9OJ5a z)_!VE^XSkYv=RfEES<+z+tq3C44cS}+8PdOBD15SsRwVEM6TjZv6JhxSy1fc8bRVD z*1Vl^u}>bsu7t&`bD#BnuePv3^*uc**XpWxQgr=p?awQ^ewQf;uQc4naE)~>Ip>ms z)mKWp3$f``ZypEj)fR__PccA`YKs>Xpt;eK;LlxC_4rd@`a5kV6qvqXN}?7fgL==a zI=NsPknp&WRp$(>jW|t+c3R9^R{8dFy`9wdmDo^C`>RJ@_i-kpABdpGWm|L~n~)Ty zg6-IQoaV~$H#e1$6M^Zdh*PemSPAKKQ`vH+rZS0iiGl^-?1(aL=6(^1x5uA@KNIlB za+(L@$C5ZhVxWBSi}>d>CF1CuVL(3c1*bJ1KU$TY*q_e!mXAA=2U5wTl_?K9ZIZnF z;keVxac`|;c_(I1im4(#o6V$$%EQtEen+2w2FluFKP&$BKqt0T;_q=YOvSZUI&rM5 z$p~J9lOUnEdYW25N_xo%N_yO{q{kgCCGGyzg#Y)n)SMWA30V1+!l2yTDqn83FSkbI zX2|!dJH)=n)*@F=(Q8T3>*&w9^k)P8IiLP)#Geyc=+FJi|M{Ph^3V2ZZe0V-9U?7V zHiDLZt z%3Ut$l`IwYdZqRj(&?M%&#m<5Hu`fr{+yt|+Rfu>QoX8G;a~pm*O?uaC24XYg$F6M z#gnVjH4ji#=swV>TD*@m`VsnbKmB=d1l=xBbSr+*(yc+GZP0nD>VJt@MFSFE|7*x} zVp6VfU3hX=xHcbR7vuGj>U9{3K1JcEcusIx#66dtm%jG-quN%l;Mz}B7QX%o_EGAM z>vS@ku>wOIxYOv$O-4AjQa)9-Ng*RGeEoy=x0C_Ew*`rlI3}LG7vU9;q^zS945}}c zhbJ7BPybX^qlb9#^{lqo^#@;yiV-3_E4ia7M8RE5aHovDp4R3;QT^{sNqD91w~XFc z50PiM2aPrasO}St&VqA8DgX$F=Z?5e2+dq=1{7#!nUV+{nz_4hdKp5gah0?Mn`ld@ zJ9fo;{ROD;V+_(pZ2^N8p?O%pWDdo&JZ~PHg*yeKE46u0FuKB&MCcf`Z4p6oBipn2 z!FbVMglg_FA~$P`5)_ekAVL9qDcC3Rq5$!F?N2K}++a!~bRe4DQ&{{Mct5lH@6#3_ zsQO#@UToxi-MND>zm_jvy#DcuQ zXnj*#=%8qwhQO+0aRSi*OiR#E(#Ha7~2kC~DP9mUG&64j%U+A}BqQ=9#ucqnI1 zc>ZHgX@68v`;(?5LRb5={V+q!cVWjDO?+Vl=hMG>n+wLA^ z&D8$7f=H(+iO>;g-%ST{d#f)#JZf(;8XL5Q30f>V;Qt_YN4dv4C|I1M{cQz{wWcIO z$704_Os1eo$>vJwcwT@~)BUac1f$ZUEmlxeW=6BbS4{GSHscta(-def*JeP0<}yEtZ{f@6H5PzxtX$6S)n34z`h+PM>xm2QnSz^o;!l#Pb zn*nT(;PD&w`g$&ke3n6QcgwLQ&1UepwjzU?!LDdgXaa%JgeJsJU}!=fJrk=e^PBl< zenp#c#fZLSN+NV4(sZo#bz?N&Wi$8>ZB+y{gHb!>{<}773ef**N+NWiD_*zmRug~C zt=?w1W^4#=h%mBK?lkSMD~Pn2k_a70BZC$KvLtIdrVXB9Y}RRu7PKhM z#=M4=t9VPtT;57|j30+}W&E=<ltk!AE!%bsetd&gdMLt9kyxP3 zrV9v=j2&y4e*B!bXdc_jB;o4jt0VPZWn5pSt%#twF2fFbDM?JacM3_+M6w__w#^en zBIJSm3T?&|kS{SM5jx20d6dY#rvja!CU%`7a*UNpSamm@M(D7*bhJN*T*$IChGZQY@9#R?9J*+*e9fj_LEv;Tml=6>}IeB@wzgY&JKCW$1!u ziZ$Vs#(*9h$GzGr3u+vj%#8zGZIW22G2X4stYRYXG9?kZiPYJZ>#O_g+-C?M)fOoz zgn@SL{+;&c6;QrlN+NVn<{cc$VGRjRJ?<{F`W@aAJjWpYMq9+7AkB{!iAQqnsjX|( z67*|rHWaXaX-Xn=u;y+n6tGezPJ+S75=b&~yZkL`6YRo{3d+ z9;@a&=5j8f@H#guv^i4HjG2-M9nCW~N4C>`M=E<10x$7zTce zF+HR$eo#!iqVZUt$A8S_pUyia{wq7O)k1nun<)j>mz$CZ9oAWg1~4F@2sx4dY&IDg z%qFe$Mn8xRo?*ydqb*uc$Yw>4g0~nZW#cj8EhczV@j0f=fr3xTltk$GoKY8_$d-5p zzQ+-9hOZS#6>AU+{1#()kGA+hF??xV3}XpYut%*JvmZ;g_5v!Q+cO-+o!Z;q#7Cb19kp?(Y;DLCIm{x$?r_GE4 zVJMIzuk49Uco(HOw~XG9pPiYMeu z^_>c1UkYBXC^Jj`TfXsz{}z8>s`!A;W_zjjUw|bM|H#?ijd)=BLigZ+ZDp`1(k*tP zLGW(5j^!?6btkilZn^t*PZp7ByE(4J@>Fgp(_0pClrDbnXWHZ`7*cjp^uXe3K?W9A zD@P~jLQs2M6)gy0V+<^OOI%=i_75&7kZ**udB&Tn);sv@1=B*|)iBRiv7^VzSb2()xIA(JLVoq(QLJAiv7Ld6M;wb&+{deZ z++SKk{0d zpH>^QbF_s}D$lj1Btkc}8GG~n@l5J!s!GY^NRxgesrv-O+oLU3P$N#j@VwTPL@k~=O`qh#3t7ayB?A&37a;{t>DVlz zrW8tpgYo>3zpyKJ*-{?TR%%d7nMP~26lN#p@}m^;2edz~7{y0SNrVo^`G*FEBD=VU zyT8&Aigd*f$0K|5XzBqGoo0gN_ybp!5bcxO^}hIEDm_%Q^?j7I80zn7t12ke=V6_2 zs7|L3qGEoPMJ3;IvIQ1ZG|()n+AM!pn^DCq{@#>C=w`8`$`;%>^2;K$k13u{3{Ybo zPYu=#JOjSNFh8#?dQg~`U{hqJL+|n)t71JSSXYYqbJ`p!cs^rFB6K{v0^u3ivBO^- z2Y-!GU9>T*RjsZ-sK!z$wV(1KYe!PB8m{^L}PvwrC3ww79ik?*>nC ztD4`W{Z&Qt=bMrUUGrTR(f|)#VL3k}Jcqb-l)oTovxVsCeq@5b#>n++D0WnZc&(r`vhSV;tzi{SX4 zxC^^f5k&^-g(t2b>`_r-{BO}#Q&9ZRLzOD!6qC17PVzlvIb%5VC+-@Dl(VsC>aaGW zib=e|ltkzzv11e_u?+LYFq))QjHhY?+>Ie!HkbRgRT$J$D&^OmNu`7ZG7F7#Q%@B z@vOG8g4)K!XezlI&vB7muqmve z)%>X3hXNkOTz3_ZN=-din+*l5S*9dH2kXqeSb-3|U=i$*s_I7TUjBZb&WjA^Mr|bo zEoEm#X<150A%Z_biddtiDYY=3r_Gmw@42QVLdW-vhK2D&eYC)DF|rA5@q;3JM&p7y zLjUSYZJrcVuP`MMI;t_8QDEh9)+_~<%4T>7?p0}GS+S~0t9CYUG~Z=}Z`M{tP=uGm zZPX`=7>s+ej95LtUYj)q=o?H){P_WWpSCK30!>|^Rch_~LG2GJ@V(EJMCkA>J%AI$ z-AFa;09)k1n0arykFwhDs6c4o8y8Qd5(suORu3=$d7Q~zt)Y$@PA zW=bM-a5XE^(O1I%sjZ5jAXC{~t(MKFv_Gi8_oOL_(BX^jJ(@vym?UO9;eB6!;n&~g z4fF<=$2ptB8oHbw%^uAl$V*b33(#N{SA}w>HbV-Oou(v0hjQuWBzx%P^MKM_02MWD zF^_o5G!iYqf4G$M1FG>J!@5CR1wl*TnbEkAA!d;b=mW*mLx>V8Izz4uF~|^u3`#Y7 zjy78gxNA*Ggb1#5N}hNSgHk_m{1ao+BRIFOYWBMnPre+B_OD)rb6TsMiQONo>tfgY zw%=3(Ieb}o4%-W`7|ve5zdw4q^!ks=t+JJN zP$F&x@1(=-YE1R}hjNBAc%1YhZPf%FC!HO2eZvq_3-S4cY!q*jjGDr%Fl;2@WB6Q`ia+M!hi6fjW_J}U!B1hu+RJK%*@j)V1=12-hHi&@4ew0iI zFr4RVD+*Lv;u%E5Xo&x)7Qxc)WzM%s9s`c2{ zf0z~zhNzCkx{Di=H;J%LxpX!!78Vkz!>J;l(Bj8`RFv2duFzIfP(#?@8Nw=T&L=Tr zBxa13m&E3Ns(346ju0E-mD+qN7IDawMCcZ=qGA!NQ4vsU#daW$6{VofXlvc(s!n^W z|2kuTgSJ9~V!y(}esxSVzl^vznG`LpXmVvwqCvC!T5aYOz+YoZq84zS;hf~c+cy5~ zbExGsAmMTGO+mt7l8v}PG@QK?v24`p4~c_SDYET!#-#HpTZ*CXZ|MQ7bZi79xS!lf2|E`eX}L4IIZzaVj!E(z=60t zuvmiU`Imf3`&)_?eq4}fsQxZ{%=O>7FCB-=9(f&5yr9VHwLVokb?&ofzppKAK+QUc za7#Q1=UL(@2A&jU|D*Qj6=i?t#L8}{YkO9s(lNi$4KXh?*FDs>a+ntTORo28yzyhK z_&;h(9#rvjvBQW@=dR&URsXZvOepGq+LVM>*Zt0vgjeIT5sa$F{g&Wj%+2NCs3Jow zLqw>Yh1fBDRIR2degu^zzo~`u2{zL+w~oyqP^o#H{iBH^fiO^{7Mv529gLA$#Bt54 zfuEtxzGC2~o09MhJS5ZVqM0&x9+4}5Hvk76JPBKo0XY2T68tqbfj!y^2wGDu6*FxW z2}D!jO5hJ6q9VIfn=1v`i%dy`j_hon11%K0)7b)$t?S{_=pjZeuPt0q)aJR+qGF!fPS+ni9bJ}|5{rWL4j_tb@Wr( zA5`G`xG9Oy;nUdn;B%nVc#mt`pJ=NfC~TwJFY!ZdwiIyx$&^Is;7+B6^5S?R+nb8l z9Legx#SopcEv(*bn`jhmmlLT%Z&u+&Qx$q^_Wx~4B6JjHZ?*ENBNzrBv2bj*3}h5p z>F;(ndWeyEX=upMY3CL0+=B#SbvDpPwOLRKO2m{z=n!FbPlT6>tn#B$^*aM`v9<_7 zYcX2&6FkJ~Y}va|`?HGjx0;eTdCFhiK>4f7to)3&2>QyevnT7Y_GcC4515iTdCFhY zK>2H=^53E@g1++Wc(vcE{aHo%jwy-ImA{nQ=Rpg;Ts#$lMNYY&Dv6^I3y9|AR?U8J zG~VNq^GR(L1O@L*(Xx{aGM*_`Fy(%#B+f%DARJRg28oQ<>_4Q`q6MoNYGoirroGFRWVLIuP zNsG6KH45scyR{|Y*Tr0KZ7HxhM95uH(*1ynJK~PvnwSWH>ZMGC}hfPU@4z8ZNxes5xR~h1uX)7Wq#H008 zzh9d(1?3N$k_a7Tu~41J(&=&7`Xj=s98DDmBJl{HJjNcAa5(mNW`n=R=>DU&0)nE; z>)Wmb9AJecKsac5cA9XCB?%-f-pKJg+FU8fe#?|Z=*XVFyT%7vY{n4&u93>t4L_>E zUSUN4s4aL;)Out*R$2ohwlJmQY=Cj%yDQG@zN+NVL5uQC+N|4_=^?2!QW;(#G z50g7MKm;ev7M@U9aaQ+wg=R4e0DO?F{Rutf_G$j!_aMO3wIS4)*_Sd5I9$<*xs4Y}bh;X1Z9Zlfp zO2Or3?e8nNyxx>V=(wD=Jr7q#D^pAl(VTcPQb@pDQT@5bTeIOZ!1IjSN3}%`irV5R z8Z5~(h2u=3TnU~lPJMMwcf3!V9Rnvw_|#6|8*9y%?wIS*k6a5i|p0;a#DjrcSJ z_-$=*g8~?-%;BN)LA&e_NjA{-SJ~+%Y+^K;Zp80 zJpZLFPEdGoraSluKZgE@AGlG_VTk8n6xOInAVmP}#CdjSDoa2%ZU6~YaSDYxh2nZthzLam$X8xMg{H-VOV`a1C?f3t=2baGp(4;Ii@5+H=X$hv#^6y<}jb3 zy-c2cjN=Gu=KfCfAcNbhEo4w|=hIpCg3B16mdytu3nrD4-lNTi0@vlHBtnO)O_X$@ z3RH~#s=VeNgL0F$C_zDK=Mq=pMFHY<+MiZ{xZadR=s>g|D5lbBE;a zC=?x0w3F#H7ZKt{!Qunj-&U~rOH&e|W3m0v0QPYvvzQP~V2}u>F$@j63Z-65dn10c zoIMr3a!2Cnl2usBj&leCHelgT3O(BN&_;i08Y`lV{Wr9g7Zm%g*zAeznk0R!B0bKE zuLxi1Jt1lg2_F*4+Yc+`uWdZbbhX+TT{Nm}W{MbSzfvQX-Aeg7LD5IMpg)<%*F3%#84STq<9v={M@X z&UmiZR!Gnywjv5%F%u8ZRji_k1ATY_SsZOe0>xZ`Vxps|){g76nNt8?V@e`)z!x3F zxbT8(p@{IH0|=c)#gNvR+<~LNogDFLhV#|h;s%8?BD~0Z1-~)LF9%4H16>uqS7|e& z!1oGM5~0I4`=Tn$c#yBg{A~0PgLR{}a6!SE9rYoEMz}#Z(Cf5WP$0U-ltkzdb-_~{ zy;RJ_kTYxAN)+kP_JaeZd?6VhS{B({>MtS2#Oj)Te!*X37~ik0fS@pT!C8YP5RR=< z0`xRlf>>M#5Q6{`6>lQ$UTvlnVBc*@B6MKa0@%usf*VMz+wrlFGz%N#+$uvF4Ea~J zRTC8QvkCHwY*;7;{uSA1_BCjDkw>*zR1DznOi6@p0PXv&LMmB8$riKl{-(0_CPVgH zZDE2!)&aK~=7#rGsfF=3+TT{N__ZmC(6N|uAVm(2kwm;u6Y<)2hf$b*aahBLsZr^X zDELt7!w&5aD-cXIB@sFVXwxjXlxF%d#?B)YFXkWMyGH9Y*+NP^S!?9S8LYFl1rAzd zP7|F;mt&qWffrge#|nb0wYgCcTwzKgbOh(CqrZLmY;W2ctns-x(SwZIE476TirRuY zBRaUDF_#KnhqU=n@H%KpB6PfFZ%-X_XFOdqRu+95J;XS@R$I8BIL*N^4aA+8lC0)V z!RR&GJSZ3)GbIr^Mzb!67g7mCtA@utI)&&}MGjoL)!$cW@C+mLUTx8WA~ZYNOT5um z(E;kzfwx%UNK)-N+@sBc0?<26NrVp2LTa`E$uew+*p5Ai2>1uQHmCa$L%cXJ=tpX# zhZ(XjYYQ6`vW47a9Z6#EL!ZlREM8$&DO-E*KiuUIfP?}9igbvDrJy~r063!G<(M7hz(~0`)U?+T%fm)?4X3)ZOYBU2r zrPBx6p%_+bJwBD1ty`NB1+rzPBtnPm3~z2pZ2XahNt|au16{0Q(}=33TORl=hVoKv z@qAA;Qt#_5~0ICzY?EmOP0>d!r3HliS}cBq6Znsf6*2)D3A-hC{2k9m$LM#c>O|~ z4+XEEnUV+{uQl)|$!Dv!J6FL5{}SwA$h)D&D(>nvogFh0jB)F(utpneqgX6+B@;6$ zRZv4RtbkV}tGJ=p*&WuT&7p$+L{k!>qkq~7(5}}r3h+GRx?Ef2pk;S4Mv-pCB6_ja zI5z4(ou$o=0%DgbiO@k@UR_4rP0(V1vK0%F{h99VI9Y^T9qJ*f`!d73Ut1YL;q3;z zYPl3ZW9|Ub#QIp8hSl|6ZQc~DcbSq19qaj31(xBA$dODrobCMkWt1WC$ycX5LD<>}T#w?BM?FriaDY%a_B@sIA zGvOE`PMa2$wVaIiBU}Fw#_mjQ!Gf0CS>y~OBB_arnM!Eg75p=_IZ)6!-IPS==uG#v z1Y!pf?Rcx%-dFDdMrMz;P(hKIUbR&ZJBf%ZwX?HR`|}Dc7nza>5tc4n9P!$=88bP3 zDNMN{luyK8Tx#wy8hIg$eO2?gaZ7I~Ut8|7FPVgsh8JGmn@uMRLxZ@y<`viabFV&F zc8_BgA06r8>V1DW$yuC>e6^_#bKul|rU^W5@4lp9=^S}vGpj`BMAo1N+7(5c zg*{IKo|vcM*fD>mPEgIPslL2Zn9`;sLNr^p+WA%IYHvPpU~i*ywVe|^$aeKUZ6Sk# zw;-CQ)4xTx4Cl5MvQ_)r)N1Cv+I%S0%sr+gLdUC1oSNl!$>gc%-dX68ZC91*t(6CV zjj?=8TLD3_?BbKPAc5$9F|bwJ6)Ok3s=$6(n<)j@M@&hC4(vj#5%9JX7hEox*ym76 z7i$O0BRtF?KB+BiP!Jc{x@x26zqOwN+NXZW{S`y6_wO0fb}0? zoI3Y}HQ1TOflO*SQ_yMG=0HJbiYbZE(W$BXc2NUT)yxH~GEeXtqqtUE0YOV!O_f>O z0>(~IWvCtXgl-%ghn z`!2e)+wY*u6#Jcg?_G3hweP0OWcwce@!fQpVeg{LBzr$yCfb+MrPaQWE<5bKblF*Q z+DWp4mEiEyLNKQlQ6Y;dat{~zfyFz=zoBe@tQ&8P-#PxKvi)6|+&TW{vi%1)a|$vG zSMWnSCm^%M%}hjQz|BlT=1p#9GBO`?Gfl{R&&@R7TrN42G3tlYH>n$3oB}S+J`*1} zMR4&dPM!jWuIJg?eX;*NF2AI7yuMbCNiBI7ys8$VuY- zA2~^!KhH_xJTgZRBhI&R5}bQTt(NRg0=sw9{Yiq|M>t9B{+g4-ZtGm}0KkN*H*kh{ zzmk*0`x`h(y#Ey^iT7`El6e1}ObQya=Lv$%I|;iDZiY<%N;gBM{{}ZhrvF!N2Bz=H zu|~=<8FF;Y2i3_!jy0SlIWFTQ$?;lF66^PJ60Db;8Pa;QxngQCb+zb=NU}{J`_7kw zY?C1S1x^y#U&y48XXY8=5&FitoTP8Onv?a*{0I2~Ls)G%XcW$O4vel5BU6ObXhs=Zw#g*GkcwA^Lxl zmcRzyTeyIe;=L_yhIlG+hLrMlPLdw}mXoB1UvQH2(0r<(LVAdC5_<5^JX?Od1>e4j z?zf0<-^WS%!nZg{U--RD3XbNyL_9q~Sky(Fp>NwVDIU7j%@Et4=L~W6giMNunidL5 zlLVz@Zia00EY~v)!&@YpMC&$eYPY=2o;^_&_ zkaSH^L5Bod#!2Gz<(wo=3oTZwL1eP@~l@xc|0H3Zl=t z86w&>MLa}uT`ZI0p{$#shsth-zWix7LxtieZiXuC2~(NYPU@?4xf$xK>~=HgtJrxr z(}K*soFQd?g_ESrCpk&VoZcpglFHU`lC*R=C&^fE;3OIA`#DK9j#NwR&0lO)@ZWm0IoeVU*lN+l;r&`V@eJaQ9fNa_#Dr1<^oZic{mfit9!NT(o) zIu*aaoHL}HBbHprx)e5ISA&)>!wlJt|D zBuRhBNfK_{3_*p2TP%};%7t!*sHEKtS=_rgBMNdw{ceAz6YTyMJs!b%@||fI2NZGYPERU>N(H`P z_)!cQuE2Qd#dR2rjXwu}CeWV+^yek?XD$6%M}N+xKO5-J`SfQa{W(N`E~7tJ(VqhS zxrP3`iT>P5e{Q2cx6_~d=+8&!&;9i0LHw}_&a}Q%+A8!EvpspMx0FgJsU{Ho+=?p= zY2GXt^K!(Ymm^la9P#Yshg7nim0Zbb>rZEUp=DtLh4QUsr;}~NN>=|W zHSVBgqteN|l__6QcG`O4nQUf@_e-hQY0CE6SeOzf-UBXoj^hd=({It)Y9vt;njXp` zW4n(uCsG{rh@OzYqT-Z4ic-|(=3uUU^h?Q^kjUl43m@1Evrgi3_6L#jE5!aVe%fPy zg#J1$LioM;y*VhLy=Y+@9CkYFgBB2;0=ja4*_`i3-o9VF`hfULi)wr92a!H*e++*y z$?W>qlN-3u&IE;P%53sniY&@2ZoG|O=X)p)1aghrSBNoWJLUDF_Z@=>wiHy2*} z`evRSl8>|v#0x#%{2IMX6F$R2CBs4^!$Kj$LLb9I9m7H!!$JqcLIuM@1H(cA!$SUH zA^xzCepm=UEMy-Rq7MtnhlSwBh1|nJ?Bhb}<3i|RA@i^hd00q%TnIcY9R9vhcMM*`G&IHg7@rJ`ZI<8OvRs@%QuyKZ!SB{0F`+G=R>hd z4y)fyc&w}DU1#cUVFZY1Mg^fB^_f-FCl?T1Gci!M=i|plB&Qq@4@LIH`>nbZ7gSO7 zF9@RTKLW%ZNT>H=J-F2IHA0$ivrz=i4pG)dLdlK7R1KQ2`KaiQXm z3zd6ZsNCO*WkjmFFWmU)x6{A7Pz_8@4FZ`$*_k4(w1g1j==^L)FN4~ZOERgewx$wA zZm(`Fqpe7$MHd9UeJIXp+lo_j(%E>D-YD>6&U8f3=%2x59(_l6;7|$Q>fmsZdk2{?Z1yO=}@F6}Pqfj2$>r77$BK%1Yd{nYWQS3ws z9(Fpbe=X$V39CHpe>4fv&{PgPGx*VDwnW5J8MNOPzSdsKK}4&EsN3;lc(6kzd(d(h zum=$)G9IdHPo@fjufh<5j~s&s$OQa4rIb(i6kuzEcyQoSr(?j1qZId}*-i{(^VHyV zx<3`trT!i|)B``Z3={{`J%b2Ch`u*ac4qXU^FbTyxjNxMT*Ii2O1+rLE&^z(#q3G+ zY&(AJNm^-4lfn4$Ycu^i?I@!C6?(9%vIocTl!{h)=U32Mn4Rf`Dn+L_iG-Et$w5@n zNt%mWLZRp;i93Z-AA$iv67;PG?i#rB&CU!wLZ}1MLeEk1Wq>k)ksxX%1Y53+a0?@f z-yo*&tn!7MzkjIxi@9HJaGLU^4F9yLRx4qGcEUsOB!`1;|E@A;nOYv1^9 z{nMOJtvRWDt(1IGb?M{lUw$52Ci&Wa$6JfMGcCNuc!VYceUheX7|w#eS7YeHGH81M9q)yr9Z6w<@55TO}Fg&!OX2& zYhIE@8BSSoWufNK$JQUee|WxRYwqiRaN(tkH`TBOS*Y>!z4ZM1re@_!P1h`bvH5uI zOQFiLR^md9xsR>?zWsGSl59iN-!Ekucj}Ejy${u@7`RZ!#sAV1Kl-VZ<+-8d&Gy&oD1f>-zL#FO z>udiezcgvWn|{9jyR~1E3a~<{EvuJ`q%NojR?T6@xX;|VRB{-Z_t8(Bzxjb0h@cDV zulZh@ddX@`xTBiCaN{5Dd$`orU5hJTqTZeVrN_2j>MHQ}pKAKqleI5}V+e^?ivX-^_fZ1y9uYw-+$na&b{CNsC|z>?YS2-O|QQE zY5U#C4aDvD-~utJd+mE;`o5QU@*A7lzL@{W%bM@5e&e|PUcBeLVr+%+$v{1QA4fB; zJM=e_qiLUhAXj?mXD5jxSuvKJc}m|7Gg360l%&2jZgT&;8v~t?cS;(}}aHN|?4@nGca8u-IzUi2o!R!-;Bly5fj0C9=vmvFXjq`ml=HH8g?ZyoT$1#9sBMu!O)W^;J?(| tap%kPHGz literal 676458 zcmeFa37A~RRWEMYvUbgAU%XzcZE0jr&uH}`*^Wo6ZLQJBb{0G1JKcAtyVaZfcF$<6 zI17-(g3baNLm(j}5D5Q}K-iKH9{-nrAb~8rKwcmT$%98&!V*XV0TRga|D8Jb-m1H_ z`c}=f;QNHX&zhNAb#cj@_uz-*{{IxRYzP8qUdD({YE##_3DLLmoJHw!O%0E8XC{ds?wH%0DLaIk z;MHtnO6&w>EDOQ_KW5Ukiw}x9f$a@~zp7BH zIAe7v$5^onw&Z4?ZLe>+&X|g<5Exjwjv6pLn*0I_63Ea$oe)@{}64aarI zrg^BjvrmA8%8c8@*s9n?D4^}@ZLvw(eEUefUM_+^hwP?pjSw?k=%8KATi&p>{BaBB z+pT7y2Cl9`cJ0I?K~uRlS(|Myp&vu_ zDim;)b3RvY<%y9^Fcx?{0kg91_S=Vw^_lAUSgzpY&edzsaTtT8Lx)DkMxk%Ocj?(e zt1|8m<;Q^z+l^VLeFKCJC^m*;EjQ-Fu7Ja^H(<;PfyIP9RfGu;S|T2d+pa^y1Ptzn z?(#7Aj0BmvWrdk~4Z{K)0gz>oszYiBD?!pC8CF{5CPqST4DuOw8uYbi+Z%}CV@}l` zhkg=fRacCCB5^qeSFJiW;Q$OwNWNAs+l>lF7)CM4yf`rfiMg$D7jRo-Gr+f|?Vc+a z-6kkqC13;TF&8|l02P9YQBf>6!QzFa+8E11!_j?%bKc1bFk^PPT$>()nX5H~uE-YB zW2aIFiL1c+TB})aHDT>wM5nhD`+bCW}>YXh}UkA)d_gC{u>)7(aiOa8smD=4!Tm zz53_|0?M)tlIM1BI-ol-Q zH75&e3+oE&3mXa>3!4hN3R?=hpDpaUSh%}zPhnqSf8pN3eTDlA&nrAo7%3dNSU8Ff z590ra3J(`fJX<(fI8}J0@Mz&h7Yi@GSa`hfMBydJZYqqS!;=NOFkZ+N^6kav9hOpI z;@QGvq0nBha%{|X%J2ioqI_bA8wRZ*J71|)i=_HP`9`gtuT59+v}sR{6);1?>OwuO zd~s?BRs4Sm86h90dHk4j3Xl{_W+(~+=YBsXEy+RINh zU@4sZp<=EHs0@K>t;!_WuH?tNlOOL1Ki=%YCO5lMd>RD9 zdW5L;KeJbP?6hw`(x_EH+9Y{Rc*knitWh{oaBHkbg=zBLAh#=BcPfw-y6#dQJMHWt zCs!0-B9(9lt;1L=RY+q`IPk6V%ux(wp{!lMdA9-_-&_T!irixeNojD}n+{>l7G8*5 zE;eUCa2}%)^mhHgJqjFrpx>9_jt};BfjZ>4@ZdcoGe; z({ZOA=iKgyPOM0J7@+7iHMnBi9C$FqN+gfmB_=$D-pr+S0WE1uS7(} zuOvO(6A@k*&Yp+}1)S)^$SV=)@+*;tkyli~`#jl`_%KPVdm=L8FGi%m4=>5*J!-4d zzV$KaQF+F~^n*cUmj^9!UwKRhy5^~4+|u^d8?_RQMudU>;|M?cPIGUSW~aTxd+M7T z{)%(*HM8UGCBZaN_$Ao)QXbKpCuX@Rm@v4hAe)q_gWJloEj~AJm%8i{o+Y@sDVu$> z>eI{}&c{3W)N_ZI#yj|Y;0~{dckuOqJN$s`a0%njeV>(meSCfW;STM12Va-C!yDoq ze9hqwv+)l8Xyp!Xk{#k!n!CJ3cJa~lhc9<{o9qx6P=73Qk9Q>W2#eHb?xcUD^ngi3%0{TnY9R5mR z@44UK$bRB0k>;<+<_MUuW_?ZeV=&?7Z^-5dn6UbNQ}$yp;pT5go5P0Vs;dL5$!~|X zX<@WEtR+jL&0*=Ukj)Vi!u?jse*W|j9;WN!9m34oq;!bPBrLNVf)0pdj5QD{oGrW; zzg3*3jkQ&Kg;)jpi>>zJ(s)(`CR*d|WgKLsHO_3|J?(yqPnGQRyRmo`0d>5+SO&D) zt1#~&DCRzhsO>?DM9;Q&V7;;nuZ($3FZDo#{(dPhw8!j*W6!#7yPp@X_^Mb%iO?24 zzYL-30^E6koGskbA@*3nvd3;OnzGASmGIILpQhOutHsj-z-;>(4X2U@WX}Y{NEA25@Bn^?Xc*kFlc*et2vRqJL?uF12ia*6uhw_?@ZVTpF%aU@Rgj{ zM3Luf)W<|q_ie05lkSp?FQiYcw zd|5B%&dtnT6#e?VzsHJ`Rmx((X(zbr!jGY7228$9Mb1>X8rU!uHRH1da(!L+Q2R1=IIr6nXn%jqdX z{!Rnw83|(YcWD(oTL=TR+mVOEEiGQeNjcif!yg{?~qR6+24+bsE#fx524O0?9C4h{j zPa`zcsm=zC9K{7z243LHId%fw4nY8N<~JP5W(y zA1bs1DwxxLelOb9;~Qe$-VnLQ2hwKJs0Ha9smRP|3X)^;hvwyoW}h}j3U+7=_5y=k z8A|H}J1X#RMAO)GF;7EMzRR?V2?n`3idYw`2%X{+zKpqt$OBW#8%X&rs|0Y=BIFuH zQ8f^e1-HW$gPB8?sn&?JuNLo5H;_W9PSPw12Voh~w#BFMid_y+pu|sLU;9PWUud^K zN%?J*914C%YRLZ`sc`s6V<58897DDev$)d8)e&4X5ljb^P4Zu-bW-s9YYVRnet&)8 z4gT-`Cnyx1^YI#JKQZ^Y&7ahi{M|5ep7fpB_KW8YzRUzl=+B=!bT6kUVLm!{m_A1+ z9Vr37aNYp>iA@RnY!tS3#SkgrF!VxHM0nCu+!CRmm;q1^;yGS{Vyzc#SgbV1T6MTN z4t!4GoBOUlr@>s9Fw~LItP^<^9;nDsqUJ!j0BVo50yz5@NKodBR5I{v0Dzmxg{?ct zbipnlt}MF;*KFOB#`13gGeBRba_aq5cO$R5p!?0*Ln2 zAAX;thjW0cCGvUT4R9oVnnVVy)WzVV+(!C6#;(6YAb(X@KW-xuWjke>131hK`Z_Ey zav@Y1MGL1e4rJ>6{9|BEJnKNf<82IA;2;-vk}-kpn)ZD?*~Zl(WMIjApd8-@IgV)s zTdBj~Q5zPD*Tvhcyu$AZ_6rKr-A6S-nBH~WH@F1zX~e_3Z?a%D;b;yFzj)~OJD&HFTQ58_u>GYke*B5YAAe$aa?slL_~W;3-L`$d zH9TzHy49*USka24=yU?3rcDhHt-pnRPo7V8mtD@?43$MdGw3C>dy5 zCoyFXp%-<001HsNVqKtT&sa?x3$&)_K$${lC0I*cgMN(mGd^JJ;OMC3GmNsTRlos; zHNOMD%rv{!g+r%Kj0$c%gCwhu(UbhyCpix*Fl8;t)7!(#02LXQwIpoI7s8D`*TnA@NE4VmGa6@WJc343xpDw92AS)tYSByAWe;_%E~UdXJHK%=U%JqDer2IpZHSP_Ytq!urJLQ0P*KT>N!zdaq3jgz&eA^@R)p+?DY zrH#KxvN~F8vMws$B$XJDUHm~rGR80%a>*qb*!FmJ+jf=HLdO7wpbm*Y2AKKGNn#!e ziMze@rIv~~|LLKs0;RXYP2TZRlP4FZO<%1h%W(-3oEZN8yN{tLNRUrLQLV#vYpXgY zg%bO)h+rX|VpY`tx&!J6^xpJ^5PFj!KweUpZjpZl9X+DyE4L(Az$iPrutI?rF^-Uu zpn?L81KX|p?z_+0woMm0kM6+gJVefc0PA`aJ*FVm9GFU2p9wMgFfmoF5~_TN#}-!g zsFStJ{GNd5vp5)5LoO=T2c~Ee#Xmq*%G(UMm3!_KnN(m*{JkEGT!-FD0z<{3- zQ!yq~tgeb+#w3|HVhR~dd#YBIH`g>1qvCfx()C*DuTmC8Kez z$Y{ug6YuY!f=;;DaL8RmL**)hSC|~LMQOOdLTO(;WJwU-N{RP_1OY#}!tquy+^(b+ z{M8Yo;O!?t5UU|PeG$?0b`wxmDer};K&iS6LoIJW@(p64NClIkUQ#SCz!Y!OOX<%k zFc$tO%uWI89NKPzkIHzjSUv3-qxch^%LOBXte0ha?bl#8_WNWNCc7p6#0OM}FnEU|!iu#9uSV#A1+ec>nAaRyxzkrXd|ay>Ut=zxC{ zn=!DzqE)GSi5D-UOkK_+fPox__{e7N->lWk&Xj`?CYKh&G9fWTSghj?(Fl%c^I(d| z0>^f*uGToAvzA{IO%xPDrUg-B@fP-SL5s(*(h<8%5LLj|2Kbp&`Z@aoDh?7xk&NqY zRC=tueIm;{EFSM!%5ut3FMuqHg8`iqu;G`wuyuuyB?1aF1@Xf~&&uZ2lCs&#B$=JU^ z`H2gU!$LUI6#K){=)&U|AmqTglzn;Tf;Z>5&&Urwjx9IH;n22=3ju863ig5cx#jyv z*9XI`Fd!7?3m!^{x1q!~KL=*cx4d74` z%71mU1mAF|%DXvMaBSH5;KkKy4>&=HVjWu`Kq@W%J|P}bO2c%magKl;yEgg??eU}S zNzBVl@+)403njZ9(^oAVlJeseghZXxAVv=k+sBQzlVN0Yp-q+I3v$7** z)gXvmT6&E#jjo14C{`!L#>!B^i;t5?79zd(DZJIb`4n6$Q0l-I1eqaLYp={@<%yz8 zdr%M!ueID+pMW*~XW|xgmEWY8CBdc*enX-K3=o%WX)o~$E?BeH`v9sS4+TfXGR$7f zUGWl#49xXFRT`QIx%J)wO*Pv=m77tH3{5n=a8noSlB{y@mhM58-%{mhI7Ad zGlg60W2iBz+7zL|mg?L&lr*^og}_^Qh>wvM(5gPw0*{da&yO`R(|FZGL0L+BJw^$J zty8YUnX2Z!`l4Ae6x&OKMo|&4Hu%%;3)k#qY2!k6=hn&QyfZ~90Zfe8o9R@u7@k45 zO|qN!MZXH6yJsOf2#{3eQ~lUpxp(zezrz&o>24E`pm4xA)8MaMroK z+_T*eLTr-U>t#RkXh=ygaH#+S!&zda@IUCrHA5KJK294XEI~fjbG*;Af4Jo~hOxJP zxKPACTV&V$R}_u~aQU6p!8?9~e9Mv_!g?gwLG0~quA!7bGJF-(iZwM<&qDQS;<-@L z)iec#d$pJHh=9+4+>Y>fgHFkbHnB_*W?E%1ANKI@vB}e$1(ePPCVbji^W(76VYUlQ{&o;vngVKnShY zLPbEL3WJt5I5EX;oP#=);r<2hb~*;2a4P7sQGm$PTFaZBaqd|MH#Q9!H{&EE4dZwWbDx`QmYF9ZhR z+bwqn6c$q&y3k`VAIM#z#0y3_|jPToC2$>VhvPYjlQMlY*k$V7~ z8Q}YJsf|i6#xNVUn$GO8 z-}BMIX87RO6Tz?KyP@{R4vWw0C(2mdsJ4rfA$U!O1)t~AsU7@<+DUG^QEl^7iI%PtYa%qm1CXPh4#85YgnYIH6-8uV9)*(7tICW3p0gR2cNn@`P2lW8TPb8@pbPoir^g_ zgyHSOC)pwXI*HH+96O4M1`;n^Ec{>qIC#Mipe2*E8nK;>k6F}y5>;%Ta?;wq_2h#jKFvTYpNGe-4y^i$IhXmHI^?s)SlfT_PO8*}8W8gls z_7J+>n|S8`ihdFK0h>jb9dI~6tO?XHP#^kk1$B@UUl zd5Xyq2X`npd+cie1QY-8q9Gt(MJ29-!)F%w=QYU2A}xin#6p{YpjiM7=an5>7}VJL zkGZG~{WnLxUb3fbj8M>HCGtI@UICyN4^Qh9UFE$GGKdYYG_hwjZE4=yH8{T5T(E@KpQFA zS7T+08h3;`yj&0*863hS{uVX5C?yA1FTziRy*h^)GlXpDj43)70e13P90P`Z9OU2g znO~NlzL}n$9%8yFzCVnm$1r-j!HmxVT-DQPq+TAuFwO9IyKFF9> z7_|DuaX_?9V$9zs(P}S2G=?hlSfc*O**SZ3G5K&8_x$UB`P4c2a5q2v>JLA=AsC@v$FF_$4ECgZHpA=pt^rY`>uZB&_ju2~{`cQa zwtRvm-~GVCg&~_xPy4U>`1QXYHAIYa|ALz~{ZO=tQSV<+yEq(eVhZ{fJiYLp(IzIO zf58u2_f)ir>FHna+E1N|HZfWK3w~_h(nu3bw?O{tfB63KXcG&j|LT8R^~q=x%cp<& zS2leiu-^jC3a1awV=!~`v(KLR?ckXQbj6px|Lw}m&HcXqS1Upjws^Yor=H%a%%%M7 zZI40yXmv$f(p)BC<=bz1hc}0LZ0~Cw`~&Za$L;>3&-;@1#A9;*2i`XBJ@I(E`ob@) z@}77sUHh8cPVb4w$#vIX{AGRu=Ru&f?%gjq?LF~Wdeh%-c+h*|5xxC2t2cO0JO=LW zdw0=$;^BPnuCapm#KZYW|6llhJe(i=-se9Nl?Ws6eE!1!_hSLC`6JHfUu&K6Kyt6o z{rivp{6|aQK=2T#zp?Kv-+1K?9KML1ERuN*03?|OpacVT~M zUVI}?_n{M*6gj-!pR(_q#jlY`c@I6~8GWz(RXh!*@}1P+tIsa_BWT(kyaRVD1|51# zZ+hlK{1N&5J@J=z3p7>dOo5?%PjvHPCy}PmBVG%T-XW2`JNOkUqkKnD=>um#oQ2w(5sTYa6Xm({6{b%(Gq6N9)=P)(eVyplDK=|+oHSgrTM?YQ;q>)8p24>u@ZYFtFqtOewh8_8(r@LW`U&`>ZYO&7i(@i|2LGLu|ht+PQ-sR*+bvwJ1F$ zV>f(0E8n0Ay;7tz7R4G8eI#5QM@9SC!+>``1CYTHvmz=*fW5xEsdIJQTRLK8M+Z|m z4eB9*2}cEp@a9x%gG09E8La8=W1f`0;QjnR_<5qVzVxT~dF=WtgbDX2F=4|BWs`{{W5v8sIi`J#Cs{QY+=}zScs!cKq<37)Oj_J(FGG@zj!UUKIOyj27q)o2oB?9;olWBMPk5n(xTVM9 z?Z^H?+O!uW@$ip4hkMl(qDU`{^XSA6C^qdy3GHuJ+FzW+#2>kXxs0-kD-;0j^F6G=>X(^_W2<|~8=FG*s;9amV|XDo>c`_{20Tz7?N!jnl%_~%W`1nUZ6 zf}O;K4|>DlN{M8QCo$olytL1)|Gg}jpM-lZiOZkd$m8v%|K{@ia5q5fD%1W zT8vBQM2Tg?p7zds#x66|fELTxCsL(zFx~>mv=^R5H6j%!uRe|~rZ}M!hhBR3Yl^!^ z0i*PG>X^`u16k<&jOJ|Vr_iG{j_b;mlQ!t<*A&IE8Q!J$sEWqci)(p<8h%@X1ODY7 zbQ}csjfg%=gL6Re#<6ScR(mn-6sEobg{^T>GFf^nKFzcWJh3tQr||^j{VZX<^*{>* zW3P>6TSstPh;^jazm)7{$5DJIohFJ-&xJ`%`%>u_@QKp@z(1h9^ltnlZv7&D z;`8t2AHTvsevN;;kAHkX{5Xc4Kcx@i*V1p|AJ9Y9k6q~5HCiiA5jls76XLF%CT>2o z4&$HC4#vi81!8BG^-9Vi)Z1ID?Da8#FX<(4xQ`XXTNex%;eBu%2{oIth`k?+uGb>rJNY zZ;dHi9ifcM4ZBcw-5I(wh;I_cF*dc1=HgNv8Sifzw@RnzpW1yGr(NO1L+gNdq4l730{cwG zdFc_*k_;`F1?kN8G4vOc%Giy5M$~hua6{h#Qrx>Ed>G7u@dlaQo;SaielMUEJ>Jg4;bF zZl9SWZd9wMi5qqcUviwHoyWqL=7<}W(COl~s|#+sJlwuEN8G4w@ckF9I}Do^-|=_Mr73j)BHb>PebcM;Z+rZY6N9;6PK$ zD?L1d+gEUwXT-;!6C|d01upe8i>h25nT4qGtqbJ`PB+9sN!Cu>#S?QM262k7O^k4? zQ#dvlC(v5=;9`pkDj&k${9wrv zrfzPanBv3Q6qmes=z_?|rBcH#w67CV!~u7L%A*Z&AYquMzE+V^_FkW&q01#m#O+H`V-YLPA+2#>a2e1N&r zo+Edt(y|M8_A__xx)gVKR4ANCjEKz%64Uz=bEKDwD!b5|WqR-47mRr&>?|y*8gK~< zTJv3|>F4K26V*s|q3I5$=^kWSlwgq{#uD=b1?&=Kru8P%^S(LKL*>uaIGb%0Y!ZWtid-e=k#HG$zb!*_@$&-=nh330V)3@hH6BY7x zp((?9uopDRTzhy>L>!Y;Z!rGLmg>eH!m9$R!RvzmeT+Z+upr?`Sve#egXEoW-GzZW z1Lehi*Qj2>4Nnou<_L>v-ZV#=spPH;&8z%a7>D|C=v>Gq$D0|mtzpbeYl>Jzeti_G zZKz(Y3&w~1$jI(4kr4>di;UdeB{DQWAel4!!kj4$<8M?R?c^W3`Nv-VahLev>FGWA z100}=ye=H5u%5yr7AfSgveHT^P*=~T8nnWyDzw+nDEodFu81RJJleudb6A35y>U>i zJ;MrdnZM0EeNeC_sB)S&ZKF!RF1)^d1lJkivZHW-MsO;c(F`+6=S8OS@%f~(^pm2J z2X(Z#s(vz3p(siNxl)e`<+#R;O36y13XICKN}{5Q%9u)`0*MNPN}{HRN^eS{YKBT% zN}?)-%0Wt^l7osWN}?WuiULX^pHB(%lE`&aV!9-9%9NZfiM%SMHcKKaN$JCq$N^Ha zt|T&Ulo}JqB9tf*B@RF+QQD^@ayOJ@DTz!8r8G(+FF^?ev5CJ#;rWt?u~Xo>Bx24K zx-E(LD}^(~=He2C14|;NM`5y(h;UI5sw5&w6ap%VI1U9wN+PO3L4lH3+0z2JBv!Gs zG%Shr9WAIzVpT*-k&;+XkTYHq9yK|rCE;a~YgQ8e6*(Lw;Wf}ST@rIGO?V|SYtb}N z61JSoF55^lGi)npaEMbrOG1I#3vsEWEJo#m(&gi=a@pZ4c7rn1NNJ|1JY7nc@QxLm zPNhS)0bGe8?yVTY+2&q(>uS1Vjc)KozTck2%@KtTFEcVrgM-LBbrV&h3AL^2)Kq#G zX{0Fjd=)sLmzJOtR1ruT8h8GBbJjlRFv#xW+mzcB^z5xmHp`YQpV6L2cbNFYLKf^! zEkckLE`HdT!fhzI;<;jzZSibq`%Sn>^{Jw73GeEZq1@X(V)z9M$sBeGJvjUbZi8`$ zD}@pwpiXtzPxlXd)0RC+Oe~Itr84s_x3TLf%=z$!=t&ym@ruwpz$L8ys}V3 zG0mywGSRnusWv__b2(!QLfWS(QxJFKMP@8(fsWF9gh(vr-%7HPyd{>-9<*>h7E1er z%hc6j+)mM-X@0LZ+tMo2Et&WT7bs@~loh{eVSHS_M;o=6UcF0zxGbwfZ#G+qlBLLG z#gCZXpJs%3 z|2+KDFW=}51`kuQ=3Qz{w5mu=;S~H_{<71HZvK*~-xx6N};| zqBvmz8p2>1+1q-*0-*?w&_V~TgT zDTtnn{AQZ+4%Behdeth_c)2FxJI;BVR(4^N)3rAXHm6N)TESXkCK(s_W<7j4p5x=I zn2|+sSw5+aSxlBsn1blJEH^x;2+-S~7^^+%)QKhctTu6JCAT3H5|?lY2suSwi{tWo zl{P*xd3~QLh@Q)9{~0IW%F!|s+_0)GvAF?GK%Sx~j@a^x5T=95i||J9__+;pg2a-4 zk2agqN`8N);nA5TsWYAA5O{RbuO6LQWxsn?kg2H0lDK-jOB?B!dc4yVM9 z?Kt7sRo5CtsTi1P9j0poE$j;Sy=g9DAcK7#TQ9;!dk%0|H9oD)qO_{9FGG_sg^Wlu zDnw(}Wg4>%(U`T}V8uXsLityZMnyB0#x>(p+BnBFpc1-C1ZZFXnYyDUE2s%Jf-ygN*@A)=JgxIC@{o3(L`>A(h4 z5Ixs{{eceb+Gkblb7Zn-X#G^1uKKysyoC!{%QYO{F^LU-O1>f#l9>}E)`}5rHl-c$ z`=wUw!kV4P%o3Sdkm;vX^VxvRj!A$OarL-g8|j#O>^B9`bM>$S^+4J9$y%d=y=<4r z9dz%`f}YSOIIW;9Dd^qVszf+gNvj5bWn7v$ZOmfQe9{y|&!w3Oq`7CGHIf%+`|)-? zxrHz6ex-VYW%@(fWT%yBM#^+g7WHg2cpG$$BR(#l-q5QxH8Ds~mOM zp()N&;?2rV;N*l1b@%Qp(D!N+oK~R9Al=KgECONJU#F47Q9Q0H&HlJF-=mFLOq%a9 z1re2|K`2y4Q@MuF0EEP%Wm=v?SojBlYNwx#E9KIj52|Wx>9>O#(!bLdTe42x*Qti| z<3SB+N!BoaS^KLoefvuR!XO`L%<1b6ITIZDrT|S2QO97x9k%h8>d2O0>B{->)?-|6 zU!Tc)Sc*k7VHqr$r4i^$O0g}{Mk*$hYXk@bp_t|{kfinUq z$7!KVaU2Iygyoa=C6?74+H6TVLfTs~4U4dPmXXhfkqYXxWz3StSW-pe32lU8!g|;g zL{wM?^Q4?=d8`|NkXT%GX_Yay)FX$SDW_bk)B4)x{m7I=&)4WdHGBv%?^LGqzR6hB z?MY!c!Ukg=;ITHoQd@FqwebM#zE5-3Mr1VaCD)1OEYpl1eDHI28pls&iDt4f0nLh? zNyxarOdI!@;$C2RcXE#Ae}~5n2W!~>lS9Eea@9CfgviaIBsC#red(?&zMs)%L0a+M zn8`7wA{VV-8c9j_9ZRfAf15U9G1>g2DF`{7e}ct3-!s5QQE?zdNcjOFJH#O)q0^4N zSaiRqOpag}3Z@mESb}#6j~os)vf3 z!}hgHUzXrMXp@>&f;X|xjFc1YcMyUM;Tn=-Le=u$X=4_X8>owS85ZQ zR+KkpJc*IJPvsLKk*blOtB)mAR=rFcv6v7qn1blJ5c`mfX_b+Ke>!1p7j0xg{hT&2 zX$94f`lk>!q4AYa)$}vksKi9`Hd7Ei7tIEgvNww7EvwQhH;bs!<+xpVe(ThUMfC}7 z;?jz0Lk7j@z%Cm>E+nypYNOxN#waGSkC=jpO3WZWBSSpAUN-w4e>2)d}2EDucjb+F0E~c zr|dG0wewel3R~zbt6)_h9`>oX%~K*sU#_g07s{@EJ#5yZC+^c_oBq}-&9 zVNAx?n}X=Mj5mzrOD#la3Nzpi9f*S?<6`T^PMuhSN3@AcJ0>?~Y=K=iik&hj6ILt- zwGoO5>;Y2{Jr~%@M~iNYs*e(!qDUKy=bSbvX~ol*!F@prE{aqV790g_JYrIDOhNQq zD%Y#^fR@-^Pj#XRGP-0>me?D#$xJJ;8!{@M*$AGB{1Vn0uhqsXCchsv1<`Z)MMjQV zbi(fJY(Q{es2=3dB=KN?IBX*tE z8gvw~h|(OxMW~Umn*Qr7(Ld2R%#3?C2*)ydw4E`aNJMbX35pc)C#+OHtBq<* z{GTxe(R1-{rOJT=4P2Mlv<}kpfcLNtT2;uLGN4w1(9^!eqW+#X@o7c9mA5tu?6Wz6 zJ(pDjc~0NP`b=V5}T33BmB}{sLqQl=UZ3xYHe`` z_QwZQL`L}`(~ia2kMu78;l&QMSbWVzT%TFzS!;dm)0 za#&gFw^+;%X_KFJIB&!8Wxzix@eeA7vW$PWh~tu!4X}O361GMh(MB*P;)A9j5=H#n z!mAcsMgJw8*l8Nv*+ho>%;DpYNEuJqm0~%vld*F*mS$C((zMdtER1u*DYv8)Jq(rk zHeoZwIc=0;@++8vNR;1vif!!yyNMy{Z)!9wXHdM>BMhfwoXYc<2sw%{qt;{)30rwFQx2Gk*YI4KfZ6(1#kqK!*T zLZ3AS(Q^rHAHm_a^=zKDZ6c!S)={`roN_2$eKK4@8kU^Kdo0nbSNF=dyd9_B`ZQ1~ z!l!{^*6c3_6`^XFV0B#5-!m1HJeTp?rXYGQ>AlB`l_E#j#3>uf1?K*V&b(aA(=9)K z4Q*KJhA>zIw)IQ{?!>`;0d3;ct>AL@;IwL9O%iR1+OQ_B4Yz9J8yokxn1YCEgF$jq z<~Ml{kpT#a#h;t*Wb$^4-H&}!9rw$0JZR3iGJe;ncjwe0_0Flo{+&}6D|+ZUtB|6X zJ{{~Fv$aK-JQEQI5^o>)eA3RbmuP=Arh6|IAUZOA{;SZh3pOboK3}g@=?rz;e4BT2 zc4S3!sg7(aUZG8XN~X833pOKR)4q=+4&@;v12>>QY5UPL+Bn5T^0X-kIS{8=s`FiZ zzWIzp)deUY3J%{vazDPO>=ON0azCq0VtUEpA`gk9sQ&VCR3w+MrQ@fyaf(Uqr%XZg zTym=d7u&m{GGxfw@n)9O$F&JcE2q`c!S*py#FJ1H^1Iro#KiMErXYGQo*O90L)(?=O=w!N-6(=R!Gl zY7rWH6E7qgdJZvr4wyKsVzu6CTB2}&(4sX5w&UWIGI^q1p_s>+uiOKd4AR~ZdJiFq z;Ki^4^zb{ZJ?qxY&l)V|%d}r0w8!HSyV{@?r;mcvtl&{LV3Bed9^5EQxsFYJ^`YmpVZMgH4Xbp@8@)_E+$;8wI>_3>1H9U4wvf4^1M@<`n1+S zx=Hl_$*hN@V$H8ja+G#!V-=Ih4pR`)7-UUB$aNEI#+=qoJ#yD>eMDR_;_sC?+$tmM zi%W{gYCEEWKQ_ChdxiCCQk!>a_3E|^UzXuvo^=Rwx}Hd2o;2GeR7T~s(TgdVZ3;pv zSQpV6&o+aj-rAL%1e!4NMU+O-^)gsZovsyK7xuzGVmxdy^j>9Ix3xKuR@OL=nkiwi z!mulpWa~^xa9Fx(=o6}`E^4D0lliL!h|6c_Z#hW!CW_PVL>UI|NN-h~25SGyI1aDi zR3e4kDf+X>eo>njX+^dL`?Ecqc@np2vSyrdww=IPG5?E`%>OTFV;7Uu&zpjfqw{A? zK}hq@`qE4DZ)_uOI&C*ZbR{{y6}Af9ISNj@M1H@7|2DmGwVY#4-gD6_$ayloprAsR0OyMX$WFn}gss1p~;C!IACgh;{AFn)H}9*VEfv z|I96Tk;3i@bOWQSdRqwvvuCvti)qyJ1&EF|cixxPcPR%^ljrQmYs7lP8fi6al=t6n zk@zNXT{f9!Jc*o{W(oRMY3V!byhwny3!39o5SG?aq z16&ao79|&c6-L;5H-y1z@F{K9q*a4EvA^G=jp}Sv+5&yxh^{EP2xwExQ9^C^C$;g7 zX~V}%K}5B|z>-K~#L0I95E6?Qm?lIB3mnkSb*ffw(Rri@a9ql!mHs@a zu2{Nme%3rhY+`lA-y~I6EYkjJOwFzlAUe7?^S`9r7~!ZjE9ec4o7|

z*&f8$-QI+yORIr3zUP;?*(o=ht5%iO{i-DQ<2G%KVxrh$3PO&xn^~Ikz0lmuhlKU%k6|ViD~6_opX*rYo(u*3nrlK3?K(sK^jYsIRDLV-pipS%A2V)^1pt zO>pmkI6m6lhxA8zrdq2|U0LL?noxjE`)wB6tTv<4iftHi^iubFgAfk$A;9g4)olTkn2#H0H zyoQZur)z4e)H*d@!mf;{r`M?$tKQ#fGdZp5;UM5Je%YFbU$C}Yl~g14Wo?XNn)8>Y zAbKvdO($v%%GO(lWU?Nn2{+P&CZ^8aSZe+2d$b&CZ_ZSJAurW~astLs5nDoq)e3Et zVq#lr3Zmy?yXi=)0e1=~Ca7YYvChErYn+P+uUlsp;T~;b(+<3wGZT!hY8-I!DQ>f3 zY!yK!RL$(vMl2@CAyW{k1!?TBkCKCqnoJzTje(eVns%`~$O|qy)Kqc5;5+hC)lU(K z*SepR(vvT+&b&~YuW5B=G(&4}x&>Ygf94CX@#qBA5L>Wx53k_69=5V7>5SD!wTX%8 z*{A?<8J8Oy&mt>y;^af4XZ>UME!>b%tcI<3$6hSO3)+OIl_I8Gx+%C?#PP*+Pd!pW zS;kKp@`=Sb=e2Q)38Q5SLJs-{%X7Zh3F}5@+$OKlk;=!d;jfvtuXUOAO-~u@PkaV_jI0{#Bd3X%&g@)xxF`yRl;@pLs=?DK;YE9J_zk zMkl5)Uo!;}6_tUsrNVIf!~lfE;wsa{pqC$e;8OXq&iNZ-5A}{SPOjBxpw=wvf9|tR zP2m)~My^1v>QvF04k>8qYeBkf$A9T)IN|$A|zZ%oJ+XaZr=+Uhjv0QOn zC+;8@(bf=4+wo=|@29j$O&;$t2Dew^lnTbkkN?WCzB(zydt4ip7}p;%1tCY-5fs+kU|Ml)&e&B5O2IHmYza=>Q`#uS#8x#0(Q~og z2PY08cCknNq%%$1QBXQ-Jw~TYj!>W-hy3LcJ@E})IAmh{(n z{x$$1vDhXE=~(w`>{qQm>Qv!9iBqdi(9L!cwMuAb{rRdkXVdBr&KL`D;=2?AMLD*{ z_CzeN3IB>VA~7xbTW0R%yK?kqh3g}ExUVjDx{10kzI!!n>$~=5iLBn(Blos#sS>dz zzCpQ?wAX8roUuM_%wi&1ZVEyUp(O&u{12fWk2R1A!rJ3ht6?1}HgJ;krNtYTuKw#R z?mM+Pl6C;@%uF*yI7^_Bogj*`%8*P@09F18UfphORAchr!NTh_L_12=wD`D>f9kt)sEx7JXF+b^u>iXljO0HxL|5LbE$w9WCrT5eD~lFmek*;DJ}77ZH*0@2rs;1IATDEcWv{G`#GL<76;~i( zwZw-@(ze%AjeN0cH)gEk;#z`H9J~kKhxpz$gu#~Tx3rm-QdI3bl?qFgGh@xC&_-*4 znnxR*EQx8w^=JzMw+oZZ*$1`pjS2bvrXb`H{x#N<`3~lYJ#};-3Ee(v(H&xxfv1xM zy!yPb;JbHc8GlKe;IuNnMdVX`jI#n`Is;I_SP^G}JMd@PsKvzjMN<$x7w7r|wu>@K zDm13CjFqr8`skss3_J8;!7bi2KW==?jYmeQa$Noj}I8Wg7jC#o_{l2F2xf!noliAiXyDTtm+ zXe&ub2nfSSI3y2MX~9g}$1%PzmEug8=Z-WT^JsFC{6r!daly}>2#Q#bC7K?aFoBXsQ9#A|U z5$*J>Dhpf1Uy*S_fuXC7VNAw#QxH9u@m{}D6#ME?Mo*=^)&PWCYcy?SbYbdnuww%v zx63mw+K|<98j<}5hA>$EZ`Ni_TKVq@>PjVTbk!k~CWbymQGC*HE+a@&r`&|&y56LX zZA=%QGX>FeUAXRq<1~d|bg(u>VNYDT#%BC{*h{)pN0#b`w24eB)$21AU@7L`T!1B; z>+`Dc5~@soOB<<}@IGh?qUXX}cf43VN3l+ECR?J*l-z{{_E*}3r4`tETw)+F;}oN3 zgjG=`9Mtk9ZFFLy`ZH4yJr`Bl5KjA29a(J4Huq{t61jeKVbUQNi?zQVlhQ&{5IvXD zh(DlcEH#24n>Q5}T^?w*7^eG}@tl@203oq>&NNEyB^?i3 z-lXFi9QZ}m#x%E`aGHf$J{HOhqkB{p47%7#^EPSK}f}aktqmS9#;JIIycp_{cWM(8VHLSlN7k8HZ9b*dnd?PWL5ZrXZvW^+SP=KE;c2a1GSkx1Z;A2RxLZPH;WS81ad6ZCg_E@)$?bHm~DP9s;Oe7HEFuTe`l z$gEQ*mf?UlgVGO8$Hz{@?U4Lt>=av?kQ}{D8=;uQwg?a%{n5^Q&rKcDdwn@zr+HFk zt~GG#_~>@Bp$KVOM{pY8Il3gFnsA`X+(5BRAJ%4JTAA*{?ar)m$z{4COpiq&$V9ZB z$jk<0s$x$n;XSI2bxiPwOhHJSJi@v&-wXQvQbP{J-Bc8MO^6YUNz4y#HJx0cT70S% zEnJ%uB-W3bHk;Dw$9}0F34Sh-$-(@9%&bCYNI?>cg3H=y#}uS!3ZmxCr@>+=hmRcKb5k!e-vVW~nna%!I`NSr}IH)v91BV+**q6b%LqZSk9cjil&2GLj<(B*}a0SKv591}DE zA+g|urvV6w#ivX&d0ra(;N?wYuRUIy6s39{H_hG{lbM2ZvHUcpLyv7tn&jqla!oFqSt(wu}~GzHOf^;-W}(Z#X!$e>sUX=4@cW{73;I`m;de_NZhw1VD{ znf7tZ<^*mLe|*uggr(KDwDE~a>t9VlM5Sfm#7aMy9VP=15{m~+3Gw{kLzmYN-i}+Q zXd9&UDDL0E4$l)d9ntH!gH}yBu-7hD!p=i!Fz}A=ym5Y3i9~p!cf32vJKnAR)tJid z5FiY^W8-AurU!A_VxwNR!C;YWuyILuvtUO~>+al*hyNqmv?mY$7{_siPC;TQ%r-DY z^aU6OEAk~t-t!r4lw#sIWhxHSl;I}w$s!j$SvlN15uU9(cVlTxYm=T{8Wi`6U^kXRh=ji%f_Vm;L==FTC=Ba69@ z+mpzPPhwBIb)r>n;<`m#p%|Xt+Bz??ZvDQtDAMZI9ndX71zc)b^j!|92rkwnDiozl zP`Qt5BNb=_JryYmeGI<~WtSaA%z&{)8b5+e}!aDaJZ3JT?zS9&$&qchN+~GK@X~njNFNGtV{NhtpLJ4`nmuTY>lhBJzLG)ZgS$PN-(z>;JvsfuU%~y*c zPDvLXI_G7KGCUGB-(|_ZTALMVB|D@X$c3D*N(&`|nHCvcRHdG96w~)>;~A6sD@;K| zrEcH`OHZ0Z5(Xe77FpBT--|yTzP#}#>yU%$X*wsc*>Jjto%RP|rw?fhELk^+-o&ue zfuyk0Z)txurfDA(APmAzrg4r{ocyC)hAp@pwhZxR9{hi%O=?O8|_p z;^BJ)%Gn7YqrmfBnv}U+pp8mQJm2lPc#MO#*B@vV%c8`WN6(;=>kEtOl08{!+qGGh zc2HfP8TatS`8+hHlmwidK9?rta<^(D6_Z~^fVhlCZRH7D9C4Rq(IRck`D5BdrsaGe zd>O*U<9mqNN!IK^ZA@b9K5Pm?TC)QzvH7-UH;v}Jb7GakD(iHkmct#vjYw#{TW6MB zU7OgnlDj$M`q(O?g-*BfuvP5dHA$AQqK#TilqFLTQBfLrjneVt@oNA=V$o%KG`7F% zN34ThL@&pSowMXIgiB|V`>_7JU7N#c^=AXZdwyh(af^8~34x-wYU2}Anl}p&m(kqb z`e@N@VdwGFwABTn9$bXzID-+vgk_TM6&BHNYqKP+h;GeHNz6qZxtJTnQd3QK;@uV> z(#9_)vfnZVAxGE;S?cp`vNL>_;j}#?YQ`0Q2}u*bB0g!VH(0WNqfK^t$?^?`gg3{_s*^`KtrGJf8ZL`&@718#L9Z_#&i;4b9X+59IS zbauBkhB2}2H3cDu=Ps7~e4GDUI>=Y447>7OTL!v{{u_1@6zdg4S$Z(2AT-9>s2StgxMjDu}vck%aeXjjXi713Y1w z^-gWfV|wxqQxH)-F>uSIXU8+X0SJjjuROaO57TL(^%UL8G#S4V1&?(@WE#`Miw?I{=guL?SwDF25(;o>Cm(g+CuWT-`>`5E;qgtEh z0|tVuoAA4Z_{3@|@krnHoFK7azoX5-w1T}iqij^j3Oci(llO;*y>lUYUN!m$getR5 z;&4~dBiAAqwg&Pp==NdoSD9BTBQOxk-q?}np83&%+{A91G`N<6@`kh zOhgM;8!?#B`dlvFpb1I#@}M^MFNO^qs*u)^Lmv zUUuAO#9l-jS*fPA8Io41`ZL(632Z27C$Ld$c|ypysf|cXKb{gGE}yN)Ql`en>Hd~) zsS)<)pd4TQ#?m;FBn{1XSy(@=&7-u!%8Hy0XvumruQ<7pR{q{ujh#iAG}wPs8_}3B z-)IU#4)!;gf{=rqRqDUwV82l=Yi#R4v5^;B`3}!G)}!!f!;{eU(Z1Nf7xZM^`nWc; z(&`qfo4o}Xs%*!BDE90*GY*P=fTm&;5^64fR~xCA9{r90(a|W(|2pWthj6+9iXEqL zRDDqt%M7aJv=~U%=u<5WwS3lTG;nOoL99-#BZ;%)Q z*5ZQHtgDiWJfYhRc7}yypJYY;RvYn{^#9rvgtQ`m!3s3rORS*;H3^sHh|JDN-WFpw zJf3x5W<^+?>D9_$C_xdzbvhzYYv*lY3c`|4IP0KK8`GHNmz#pMksIy;oW4cWN^t?eNFp79J(EUJxNR93{^ph93bsl5(`mjwP0c z?AAszCh{GoAfh5SnD3>_z!Q!E2#H0P^?~VT!ed8qU0RXO0r17OkJZiP#PVp*c&cX0@Hv7G_$tJ(j^4GJ+3MZM{v6;$~#mV*?hrf(^lh zh0V^vn_io0$r4Hr^4dhil-f20(Q|d$9_Yk@Ai%C3zS*e=QR6*Ug|;>e(yGGt1XWN^ z%S@_CT$XfE)kR<31@3EkNS(^oO5p={s@#LX#ZH7=(M8Uk~u#q<}*a41=7+; z`_r5%)1~nn?fv{7K}2O^;L}OBkn^zyAS4#QVw$TWEReQ8dU@0KdwD5S%saS% z%S)7;ZWODzVjT`8#ZGHgaz=woPX?64XGZ1V$&T6wP*>=PP z)!v&aO3Fk&Di=`Z6@mqn1x~w?qgpiiqvyg zUA5pU`tOO^(yuKNKi(&P#3cA(mbksufe-^vhUX2c z`mBvNX@3li5{lG)_mZ|K3imSN*~}|s){|wo^~f`AA4jEizz1P{nGaAEpAT8)18u%z zKCqGY`GB4QA3~~?V6PWz(-G6Cg{B~)8fCCfl1nX~H4H#VEPCXRt>^Gp4(lJXNtkTn z^L&RstZVzV8JyN8ZOCvu47g=G%<&0TJ9lg26VsW!rXYGQt%FCM8j67%$j4zxh08x0 zPLr2Sw2Z>}*XO*v3Fews*=|^m+U1r*=VH*Hb1?_is^KYTULdk2JgLpLw3=`TX9#+9 zV=u2tw^(Em-CPueOOOQJ*(su%>H!tH6>F1F*ztrm_A$MAktv9t>&-eE+oU3Hu6VB4 z%$9LZdPEVDyRc+mrA=5`$*#}P$QET8DrSnP5^`AIr;ScbR4+FLky=#dYp(+~u9$!q zLGFXH={7uWH+Jg95_^|6eQ71O36=1gIOla>AATHzDtN)>D zj`r(di<_7p!y<^aGV4F7O=w!yuR^pbz=x(pnMDB0lNMDU)5ayn^pBc?kR#={S#I;a zsPf8(;gILacL@t8+Q_o`x;8OsW#iWt6E<6UQo35K(a$tP|u?gN>vC2#H0HmKv*0Va8}!O($2V z7N2TG_YB9ISwW6!vo-CQU7g|68x)Kb$0H%ten=aYn39Z`f{2R8K*CZMDqEWE$dCNZt> zu0w&1hhs!=N+x_|(r(=^YvUA?++Ui4=(*%JdhQUe$Q8vXi8E8XV=tCk|F-$@o@3Kh zdz0@R5q`A6Ho!0Nkya+%wZ1|dqnON=nu16zGh;VmgSg|fY|p@v#YuuWr;fswYS^1- zck09<+oMfg+JUw)Q=uD31$J2#J4Ip%kGkypi*joes7G2y~W9v-mOH0~7OEJ;bz=`9h!=;?CS zU3F{|@*w|@HeNB6`Z)ojqv7tj4maKKb+0%k3uO?L;Hc2ySYo!qX?~RLXjQQXvEgDV zBCb6@Uxb|$m-!`SrRN5UCHud$Ihaau|Qa6ofP;tbhL{jme=yPNO*GS1eP~i%y)Z<0Mm|lT;fe zZZ5D@izB@*Tz;E(%3%j&en7J7eoveEX;t@dCht)$bXBDL6v{12DDKfUgvjnzub`lOl7uc%uN%Agl(nc*Nq3caSNE@?BfSC7rXzu~kqluHVicL&K zlMa~E7_=se4Qw`!jdce{M#M{J3}LX~k7%0z7c8S z&d31YkTet0ods>&V$yU>LG)aj+m$P!$V4BA&fP(gdU$%)c#kFg25lCkmGJEuS6&K5 zhC4QJB@H22CsahfRvXKhtbfoHL{!!Wo}P3TdBQgUA+g|ko;z$qD{J~ zEi}$b(~FV%{e?yN=a04ZDtQ1ALlU#CFTFU zb3Q^-QoNZN{4d(1rerXVUX7kgBBK?FwP^pOjY^E`Uo{0Ghu&9MaGj!+#-XQGluC8Z zcM4U;n^`{BZJ!_iKQ;g$A4-`z=aWK|i<1JB8?{l1$!DDa(Q#DFyBEK16jk9CU;IRi za~#NCiR5CEyD;q=fmznSlFG*{n5iLvq$Srq+6cu&aHlBv`I`aIoMprQ6Bl?;i!!L z1RwqN+Bn4|*ER*wbIA>yad4fo+yHwVULy7;DaXK!*2)z44+}E=Yb@9IYcn9NT(_fw z#iu}Qkj0K8P@tYH>UtC?Vopf4|C%<6F){zLDTtnn`Hn|u`;{D=o?Z0@DN;OTEFw75 z9g(!wn=I@vYO^7&ub`Jv#hbII=1kintRJbf4EoGA8anHU*Jd+{P~NEu+mE z;>kE=GZ#CI(Ha;%dMJ`^P0^oayWsX-ImH&HRv+iMfZfTwI>9DnExv0ijkhfI7oYzj zKwLf_`R3D&8s6vx zKwOeE5M6B~V*IU}f{+8T!XoMv@G)IS_Kh4GIbqc}FzPhI;)ph~P~NOfOj@Dz)3Mhm zHVLp%+>#|pv7R?+qY@L%bEY7oqA@UV(nj(CGyoy7=+Sbu?{tIe1nFRnX0aY|c%zN1 zAfMD`X?g{z``Ba!Hj08I96$OoZA4<~@ljI{Jr~U8kyf)tg=IM_U!0h5XzxTZA-#Wz zek`u9Ym=B(T-Rl6AIEGIM@4c8hm-!JHcm0g{k*xX1X z%V@(Ly;@3O!#87-tu?5ETb&M<$4`x2tBpuZFsn>K^jE=TN{y>VD_4V=(%8ajM_+$h*HJz7Iui$rulpz-&GD)fyqH| z{nuHzPiiwHt#Ef{aNZco*ic)U1w|Nm(|q!ePf@T=ObVH=jEnyXZB%38e~~GO)Z#Z@ zr|rf8CgoP1!g7}i)`+{|l1Hx*1lEFAY4atm7VM#eP?#>HNc@mSO!TZ7Np_$wt_a_! zjcrU3UM@g%Tn)~9`tyNN1XSsiuK^baU7;Se) zvE1LO&B?TKe_jR|RiZe{1Y_z2!9j*wSOYH&9JUTv9z~~uzN97VJG4=cDZ$%KK}c)x zR#OmiUBs&RUu#`7Q2JTa{Ipl7hk=J(g>VyV)8_;;_|CHuVU>-EP?$sd`@PezG9Z3;qa5wB}?_~GfY)FQ5OG5{g5_oZVzAH zQnyuI$v;Fn{ld183YK0SRI_ayoS(%8(VSS#_S&RswsqQH zjoGZ#0>tH;xYiwn|HfM=M(QxwC>)HQ29(@|NBW)G6eo}L7@yngQ8We2cq6XFELcIT zNSZWuYoikrzz$Ooa-d~RLCE3GYA~na-ZvL4Fx-z_-r>Ib@Ofj{7Zdou zn1YB3+`zYz?itVN1|TFBlct1ttFhz%$?nou>&v1PvJG$f{i0kb*HSGi*Q)oL;_wGFKN3~gzJn&;|Z(DNU@5Cs#%QFID+^Fd} z?D2tqS{s>|TuzvRkVEWY7VUhycypSeL$aL{Bo_O$Hk;CleSYWqrZ%22jd;owM9(!s zf3gm#f&S|(`!{PdB(3b{VXl9ZHgYk6KW7ReDsY2|TF&)6K^TCLSlnSsh&R`t_)nhe z?+nlNzZ}f<_c#l3;AX(JYs+&`Ft zkc05=Sood10prAecLyzG?7MeoX>J^vA2&KSv`qZDb=t_pB)D3DxQt_Oi@hDZ#X)%X|eI5K}ak6+v4MEuQoa{>FhEE zA;;G+3%JwxGOg~;jBgi*L;ClLS>ir16iKP~iG@a3syA4Wk86{iR*;#@xG<1D+KJbo zd18?1h8Jq%6O-hlrXZq{H1K$&)5N3Q0EEP%i@i41r^Ej88#En?)l*fksbzXvf`TG$?LI_JG%nGo zAczFlXf!4!CMt^inz%)y$uI6GF7bcvJ#V}3ysEzEcHJT7pU>~-XxDq^opZl;zvrHl zXz@wYDMUC4-~A*{!Y@{8<;X|kN%+Uvgz_t$FmSR-_{Z4aA{FW*Qp8c52(YHo%1FX` z6MKN~u?t8O##ATa-)1XD$o;FSh@=sI9pQI-lCUlAqG3-JCVdc!US1=?$wEU;{=h*I zBK6fF%&`v_rJV)@l7zXTlgzd<2eDm}iPhqyRo$7*lQufBExkJn#zdy$grgy+kdf&k z*(jXUgr=t^nhiRsJf5vFsV~Qxim+Z^*2VP&CIM~gOXtOckp!#@E7`@O+eNHP>cUz< zH?J;CK56J>>qp3+Ybqj3-eAN}CJi{!7>G!;_>gIr7fu@XJjs)W4eF%f)A6LiXA{b= zgu=kdCJh7ZZ;=Xhixkmz($IB(e%8o8)j7l6?DElMG1WQ4U2Me&xM!J)NZR1-rXrG_ z0IScGdV-s#q6N59?tPMbf=kq%;OlWu@L{%L`L$0NI9X5dLH4&ug?gV9@qe@@_y)Ut zG+9iwC-^E`F#_&OrXrG_;Pa*;lAZvo&y;$CN2a0$^aM}s)Dv{y9XRV)y?%|_6Z|ml z3FfWt<w^I9X3HoBb_Pp=OwhNGjB6Qp6wk?BQZ|G356dgxXa5jP-2A2;w!SBD4`3 zANws67iVDiz^jf{U>iZC7z!^gTq1ot*RNKZ*@VXPxIBD1+h$#!%jK0CSQw(tu1t$0 zj%?j^mq_tJI#eyHy>4tGEyueHS>}4tPy* z!^s&NE*FPkd#GOaAsk}j)fQjFSLt;{BJ%wcc7f{h-GY3D-LB`>q}}46zM9zWO1q`w zzPwu%JM)PVTKCh1bli=IYW zCs6*(RD^XXYx^oga7_Y|72w50c@a?V;lgEkQBhYq5PJ*t3zi zl!lo75pn$o+ZbJ3GYXk7U8D*AJNw&&#dl0aSZA>!i4>HH&xPkIa%|nRvtJ!0wckQ| zr>(KH-k9h~1s;<6C$YPv{uquVsN|e`oXl2=U_HT9gmtX^C_+jjpJyt(Q*`L)m!wE>Z+yc$HKl6GPHu1UMxMi?%f4yR9L>qp4% zHWgu=yivF)rMVkPK=Oy##iC2zEZ`Jr^ewi61by99gmv`%ep=zqe;uK}j$I(S(2pyW zOKWKReJ%Tg1md5Xim(VVjLx(a7B(U@7$$EM%OObk<{gBtTy8e0Q?JP$MnWHz)?x&w znO6ltY0$4!AQGVu_mMLRlIhQB5u6QlUC0-R(8*$X=f*1~SK5mkRYS45t`E13E3`U% z*py`w?CFE1A}m%1#5MJha7r7Wx;U&3KV%n}ZgrS)ggMgZf1j-@=`Ox&D#Bv@h`I~d z6WJ^GM55i3PTj>M4

u*NO$&l)4KPVW+!@_e&y!dELb+(mHSCoe&D|jw3xI55m7U z9~pTF|9Keyc?AD?ul$EphZ9XjSga0+YfH341{+Kc^s5k${*W(RA2A2X}9oulyQBh|xhc-ai3+5?f`3XsYJ=yj0))|VL#4$&dd{Btou);eP`kragf=yU zV`#G&uJ24?>lnioAG86D#&9JwwRe~nc*5+j(9kAi`|7>xh#24B1Y`K{@{u>op}hNt z&KF&Ufzcqd7i8jw7^QM}y~aDdQe;T*#patc=8c1sfK#rH29T^9PH0ER)n;QV1RL7t z*u|zhu3l6a3d6pI*5M!u0eD5i1z%ou1moZWxQoV#<7Y6Ako^o>MKY3p%2Y(s8vhw9 zN7ql2`+#u03Zd~L#}Jk7Ec!cwdz@{OF1Xonp*Ykja{QoBe$M_pf$|em5!RtB=yR$; z-G@o=A+J`1b{YD=sA$?gg@6{XvvpLp5C94NVDv)$+GAS4R)S!fYbqj(i8C;SS|m=G z*f$%9NVGtI5Caj37U-5_AR^HM{Ra(12rXb`z3)kO1zoE&f{|avuAsND>q&lxBn+I) z74#{}Dx3w;cE-7Ms zpoX)49eS2#B4ZzaQk2m4L3SDC^B0Cr)@tu(e~Tb}yQzo->070UwyoA+S%o_nYbFoe zBphekF_|!UA14~0WtWL2!ilvSL7b#b?)r7;4ZNPt6hF;Yk5K;?M0WHRX7l#L%Byep zR@r!N*t5^M3N`^Vm%ZCOgG_$PHd>d-{DKIgCH64H|33`AfJ0KZu+S1O?Ehw~K+63; zO+_TF?LQD*x0g+eAzvU|#TUsRAxxTBCvO!IvmttVhEk^o5!Jl)-I=G89&lobNHQ2} zDHpsl;5CFp&+#Ig&DMkPnqex!I_RGZeO7OGVBD2@lcskOTOopSov8@xD9=ox6b)~;->O5J+}(b2ET|t; zAx`ov;=7q`sxH2zX?&vFtVvzrAJmnAdm3960`7pR2<3!%noCQB7<2lI<%1BB zeWy6+Qn7V>5~1D2Hd7bc8FGLVuI{eXbCQez&tfY=klk)7LK~U!q;l!zR=FYrj(HAN zUie2=UYQqE#WvZ)Nbap{Yjw$;1s;~Dt+-31G&Py?lgnlMO~R zAbBEQ^&vY;DKqP6^9%y`N4C+r0Ol9eQ|m}K($D=pTLn_?A2k(`G@1`1x^B-6&%dtW zLCj8cUUs|z2t=FlVram9zEZ2=*E85yZz9Yev5P?$=1RDb0Cq%SbEO>_uY{Bx1o02p ziV?)$GZkSS@$@YL#N!%l)rw7+M`kEye?(BzFSIqyp8F&%yjhkjq-OVY&@yUcrks>qKW2TLVI8rKt$(bY_c5U#BU0-UCSH zdbUxzWah{zo;pLIlY@Tt_X(H1rXs9!S+uKFft)B6uhDSif0hT!McIhdIbDb6kkT{R zChAgJT&Tu6x)~iw7dOUMgTQKdOMQm5WxDk4kM zph6_a#<+iNAR^HMPb~~YgvZAFI~_!I|1jjzo#h(rD>!|XA%CFmt#q!24Zez~yf7{A ztJl48yr(bSEW!kr+kLOug6&eJ100zXA60#q%`(4&ilWFIRml{=Ba7ivq+|OQ`>Ui9 zep8A#ic8cu6T6rlE5(`QZA>gJn$9k-SuY=!9rqy!w+hboVi#F9j#0085Y~KZ6PRGWi%?fs zgL**${q?{WNa!hSkzG03B6q}vEpBW}oPYb+YmfCw`#PJgCuv{HOhsr@H{QRSx7lly zixKkN9&Vz|Gl+2~+cwQkZ(@F7KBf+rh{*eZ$=T zpz1q=UR5MhmW{8NZDIM3Ab}d&VqF6B3JuWAMa__d&@2rgub(`~R)`=NHWiVy7~fPx zGA+W2U@)giw6N4$&x8nIqvNuR_T*$m9YpERSXJJ@E)(6VGOHk+qw(AyHA+>J<7hj5 z9a|MrNnUFz!aAPid*p&AHIQD91L>Yo$eot6C8+ZPBK!xo(Ygo=1zhaVAu~v{PC-4M zLj60oas=w%nu^edYCKlXy~=Ar;w=a@vaM2v0CYLKA^DFWxgWAE(o z7u#BJ^cE^DS4s3G_Z&hK#90cs&Z7xwe0js{No*wvz~fCtB#rG@QxVB9i`A$L!>oab zLyKoQWx}&=XvKg+{kHEO(tZ{-GOgu$OPv417k5@uII!~&AL$Wz(1BEPQ_C6d_+2`h2pN4T5)Ez%CI zl_J`9WbH538IL9BC7Ib^76&0q8;~*;R@soru^~d)ik+zFbX+;A;=G8R*(kewG+9iX z5B`Hgps?_jgP9*%A*X=o>S(FN91C?)#KgL_r~_!N>JcDC9boN9kwV)q_Bm91uQp@RqxRAY~mlX4j?RBqq5Eks=>AuQ(YND_LyoX&- zx)oqUVH7NdIYw^!EEl3jy3mxtNQh4)jOYi{;giQf;THW-E!?p5lt?VBAR0JXMZR|qQZMv5rao-(C z+vvtNW+&Y#8%b^0%+`|BhE1j-tk;HXWo;OQ+Td)d2MtjlDrLCTBs!!2Wg!Sr!J^PRt?W09Gtn%tU+#eD*;k~5L6ALYVPdGX*-J!rv@1D6NIVGno= zsnw>!u>CbG&eSP=|98 zxeoIyu!&s{YT(CGg7Ysp3>p`Eb8xp=L?jclKPV&!!d%UuHI#w0kH5s$?Eazx#Q6l< zfK$lR+ELSPVoYT3l_q zeGs0nU4L}X*RF`p*VayQzP1}~0Lp}ZYc6(rc10&_%B*2zb$qrqz{Z(hK}BgycD8m4 z`&*>;-6TaE&9k-Zwuqgr_`Zr90g~gkm6&Qk9BhLBw-_BN!B838|BEnUM5kGDW`J=6 z!t2bLvBT0gunW42UFw>IC$1}~_hiC-gUD>mN`OTpe~O9*2AudAG5t{PPUoEMJ&SDt zsW-Q?>&?B#PCI6r_`fh7s_7x$Ho1r3!6NVgWbE^u@t_5{HpgmChq&U7yzUNlt6Yau zqejyoRhsWamtaE6{cnHjQ5&l22i$WKEcs?*7;R_G> z7{A)y+r&!vd$wW(^G8iZSjW6d_6gz`D7xfUDi03&bqMg}B)53uGvUl=!G0T2|A<{2 zx~MO}c3yO&i*K6;-&_pVg0<`d((M8+!dd{SLz1CBZ@MP~9m#YAZHD(%Y!yj0 zSZON4dNsIER)fJ_I8B1lU2GHjaH7=010~@A2L3=I| zg?rcqtXqq;j}@NFR)JKLJ55Dc2c&aKpt$ksynr3ReQcw3(U~19yp637;rJF)5!N{x z9tkLD4P_whN7+TAOS@~w3ZG=FNGiZ5OhsfXfI(-S^!KR`;OOp1 z_w4uOEsr55ip+)?ePG8A;(o(vC>%S%xnd@7>c|!G-t&o%##fO_G&4xJahNGqdZ=ei*9plda zVLyN)aB;NJ--MNlINN}Q%T^J9JaTJNYUaq!xPjloCXrtmMOkDTxV+Ce(hr{st5D*g zdK3Grq!!*NMev)t@eQs;TZ5_xhqtnv!NDLbeux*YlMS$oObYQ5J%IBfAiF!CqcS9mvGCO3Gj>Tp%vjV3Qtg#jyUNsjf6N z%|4I*>)DDE`hR9BA{i83jTNZd2R5^zs|2rk8Q5QRoLjeN8f@MJ2=wD@qjZ7JDM0HC zwGw+Tqou)AoE2!Id69`e##V=5`iQ9r`HMhXr;8KoQOm}V5>tgea}>cbxg~lHN_K;tuWQ7mj_zX+kSg~@ME195aW!?y0g|G zQ;~^+Xl;?!aDO+^I(6iwV9g0&a~fMcg7sum5!SKJ+vWRBIc~z3DF+xBOqQt=n>NoN zy!C9;blc$ELKSqAqgtYx+6Z$Z)2w0ZLug%KD#ALgO%M$#bYd3$Q(at0hh;%D^+}3p zrBj4oL^c!=CPo5=G@VtI>y)Ko4Y-kAT)H)2lZZ7Hx<9Avji*0}y>4hO_`8F-qRvQj zm8P8&8s~bp>ZG#tn~JbrS*GuUdJ$9|s521LBQy8O{)i}_#WqG4<%|McGY4&iL%Y;Q zL31LFT68;G6@uolsR-+67WTE8K{2S;eRN@t-AU92+Ws-b^_Oe|b#W~!c&di+c&T>4 zCsA;3WGh9$z1~zr7M#H@QL@p5>skX5i54x>>0F`(Zg)&ci|ePN1tj{t@#t=M&6RuC z&|}GQ?JBt43odF(!x(vbyp8okc2&u50>Z}3Hda_Ilg+E|v%f`Z_IIU-wwqVo-z%BF z18z#x;T9AG_bu1(z6lA%-0mUlWlp-hJJWMg#1jkPx>KYbT#rb!BSn8aTL)6~$C`>r zn)4r!Ubi{*|yDFEdLj-Pc6+M`W~@ZHz9X z8L$jiv>_~ZvA<1NTw^Lin}zWX{)u^m$VB{CEdC~2f8F9gsQ`Bp*Et!mY)XW}NLf50NWmu;PHk)8@8hZ|`@O7)fO?~+n|nW>1RHcyy} zNG5;Cc1n{!9J35WBwFC4#Xv+-7T+?RIteXc3i`B8Q_$|unoi#DA8rl=!9jJ^JW`J5 zonK?a&9BZ3O#de8< zpg`C~da@_j3KH~>n~KPyH|PMu*8B8Mt+#EBG9K>xgmaFwZv93l8v{a|4|ihi@Hh@{nRLVDd^ZO(~&*4hHf zeFEuJ*k!juboGJ|9m?+aJLf)*JUr}d^ z6YU;CN{_IO)1|Zk(g3Hlb7SoYqj$4)AdDU~6=9vx>09J{%fSFbY7@%*hD5%?Hbs}n zbRZ(;ej?HjcwW=S@mUSQn`H;{}p*`Wvj2-dOB=h_OU-oiv0>x5!Q=+ z=02!~GCfD$U6~2`GlCdq8>9G&i9dWdbN zE}%2wMv~Ig6?(d$CqecATM>fnK2s6ak)6J`4uNZKYn5U1H0xEJ`3sC4EbozO0HA!`Nj;RRi)uGS4 zI>7Clpw_IZwW161uyVYUU1YkI<4W_&A#Ndq#iYl02U}TEMgGcEg!L*iD@vj31g$1? zo7pv1&hLouvuu-e5zdAaIvk?iSSJGI)9lX^DF0$A!a9`G(oP?06I6df6u)2_qKo2m z@KH=skkF>_Q}&k$h5t4cVV%OZz8$M}?UbvN1~d$qD8ZH`-d2QQ!w{rl+!^)``OYxZ z){@gBZZM7w!(dtp#AVcRNQvy#Hf0Vcx+D|1FYL3mxY<(h%5JqHhf-m?T-2iNBG58y z-j2J%c30Xi9}}j#r9ilajYA$~FQ+4&$JUqBmf5Bvtk;%B2LyZA5XnxkHmMD`!*fXW zGPa4jt$9&FLV~S|?DUAX>`T~M5LOqNim=aW|M)0)sDOi47FLE;`{$6=t!xu@SuHL! zg^psMXmVILv(+H5o@Oe-I;@4;8Vxu#g+Ol(c-O{3q;~C8S+#!*QQgfpP#4vr0%Vm( z4c$mX$*n@0)m>~Y2&re8im*=V>^{gdpW5wRRV~+&tzQww0{E%a^j<-NZ)Y2>OYoe6 zS98;vyJ^iu+A^tmh$6X7`Bt_@gyx$~MOde~q7RbC!^w-N*^nm08--$kEi@5%Q7pG% zUW9wwDp2jWkm;w`=Ib);DR__}Cf47L^cU{za=RebpJ4rGwo(M^KbnfLj&)u%Pw||g zASgN20CKfu<|u8RL1aH+o2H9wUOYeXT%nsQb)%i=|6^-F`25IJgmpeEa``x0yc(QT zL(V{mZtpwgW`>ydTgY(kW?L(Vb8{I&D7P9MU_)9!p}t$raUYz;R*68JZYsh$RE>mw zier?<^9XVS+hpCwXp{i(Lbf^t;#yM?)*;T?JKh|IE%h)7B8f+n^E*PiiEWZDq}hd0 zsgs-1DJ;=smU1Ke^90KErXs9ES#TX5W`%4j<$*ec)6DK-wtWf#-N`mj7tq2&ctjO) zO7tU`?qDlHFg?>$gmp}iLIAeUDsZ82$l15j*>e8*aKM1g38H#j)2fs+`O0-(KzMIq z8?6iPEZF^ww07%m(M65jpze-HjS0gyv2`H~|H4#+b%tlRWw=rX=<*!DSyWd8daoeI zPp}Qw<><8GDB^f|u27nQ{5V?~0`g;~BCLbF62hsCjywKguR0oq9o|tD38=-@Jv2|a8B~%jcNCJcd*C>!LY}%ftN{PTE->8+&?kcMjgGsK#d5>C99b+} zk-=j5N3YuYuMi>TrMybq0Pnkrv8jL`s`k)oL;7-kY5qW4QzXKk<3gY&W@r!q@7&H{y5>W zPl`AyxAJ>N-g*K=8aSsP`s<1hv0!B?>?FlAZeW2=o0wXvO+xb>L^6&h?S^12y>}hC z<4DiQo5Xid1Fxck5RO&4Bpiv7HA|J$pOp2x`V)TOF4JOv2B+9M=LxP2pM6|yEf&9nMf?!Eh;=K`4d9XwzCxn*cop2;4~xhR zZFZv~atA~S!Gl;r!g&x&NKXH8Z)L~T|Cj>xtAo?9wMq+5AhkMug|jOhsgQa)!Q8izN6Q&Xx>BBwAPsq%)&0 zjGz<6Axsbc6XaK{DLq?lt@37yGuv{#(QF?V@f`NYNu^kBD#ALB%MT2XJ3DcPo66eV z;~n&zJ#`rBAz-Bgb38bX@4v0(MNxJJy=u8Kp7AuCqAWzclU-E0ox){sPB@-3=>t*Ewh}(x=y*MleYp-0*EIc*e zLCm9U({(YQ16P@cpq@4$U^f5^Z$qY3cctnfjO5I!%GQYR95EGPooA00PiMytb?&AA z8d5#NE&yGsJz7-Va+x;NSFn{LU|(t~!aCTKwuM{jD!Am&26Np=4!bB9tIOHes>_b4R2T58tP5W}ECSMFY>EaIX>B+9m2GTYN!{3ND&qf-b)&*A zEZw?sT%lZALuZL)_6G^zK~oXd0WaEvw^O41?NP7pRUxT%HnU)d=dj7XoNb~mmc@ne z9t!9v_qtO$lAih{Y&8h17nzE%4(q%b!I^Pv-8)K(An)X{r_A6}jb;+)1-%ux+Uwx6S z6QTM!QxVpwx)8d+uS1|b5gaS1;SxOQ(&VvXs!LNAXv}w!@bB0~p-cDza2r)@k&E%f zmPxzkC)lbH(2tvn_`e6**=}p?Ev7;@%8qLkQR730enQVF29hf zI^4C-oGUQi!}htAT?D%A^Spu#O%YzOpiaDL8$vS40Ye{KEduunQxVqTGCR_#cf!N$ zqR@pb+U7diHhuO73BCbS5!Ue)_Keja{8kBeJHh)t|KL}h@@l<-?Qw!_wl1o(3&B_o zf@qawj)*p=xD@3J*$NSq_n3;XjApDfzWs)23H&JX93FW&I6|S<@3C(IU!EB^^OjFqBZD{sqsk- zYM6?6(reH|U8+IvH!Xp@8uXm2d%_wNs>iEA_>!#}bTO?#511OC)S&xJMLg*>=m%Y@ zK|eMvfxH^@owdDT4GPuc)gXMyRt?%fYtZ*hjZbROw@pP@tU-8P^uq0-pBRMA+6MmP zVr3)ZefEnOzH(b-tGGc4aVzj99o(*lt$uYWXD9>LNlUM`wOf5rA@U7_m|76uPTD5o zP0IMhGTmTF*ycv(jIc8*Y$HplC2SSR+I*p@2OW=wVd09yjPLn zAiE%R3A%+wWJ!GMP{cWiH@)Nz7+BIKlT(qc8KHcusR-+oPu_OeuNTX3wODOnslOwi z7qLyy<#P%+yGJ^ZCiZ;xXG!7TZ7RZg;jfJf-&q5R*L?JdZjCyJAoN+#YJ~AY9KUv` z47q(|$Yhn0i2%g;AiGd>ajuPVx@*LKvT*Z;J!LmEDhw|I7r9eL5$yM~)g##7ZYsh$ z_Df^zYd6A~?Ll#P0MYp2nm?Qui96BqTmg>pbZ+ctPf5HxQ9%;h3g%7h1qc!%fG-u~8F(q@+UPz^T-m@o1o3q!Z&}T)Y=< zgvjGTHFfe$u0%r+@_psf5T-QS2_a74f5#V1m9cK*c_&3NURLes&YDb=%ET#NtvDRi zYv4e9WO#W9FFB`L$^I6pg}qWl+v4vT>3aFk+FS9!Wlwk=U{>S{m7<);`5ili-E3>~ zI|Nd)6Ai5m;pIwL;hO!=Sg8--MO&ami5T9Pj1sX?r!&k+!tCHrJ|0L6{5f7 zMzzG-KZXS#ur1du_=Rx82s5>3G^ESf3R?+M{AE)SNnbZ;DkAA|u@X$F$K58i=z4Y8 zKc&bJDQTLpUM zPFrk&94aCU)DR++>_^#J5wagP6=9w1eB1+VG*?xE29VA5@M-rDQu_hhI9+NB!u?Tb zbV9ohEp&QN+f;;gMn~OM_ta}FO@b$;d|%=uwrT|Q@unjF?}1*$E(+bI+ve)% zO7;f{zFt!i*6}g!Jt#YEjQ6m|?PnK(F19J%m)Ofzi@@DwD#AM4)5Jh|jaLi?%8<8I z;ivwDh{o84=ps5@4vHg@CSegKy9!PAmkEX2Ohs6yFn_CGFCT(s@FBmkGRjWitWkNi zdkD$=Iomj0GV==%PdCyoN+jUsT%dmqTLpsXUQ-d)5y9!63@_!ZRjH)@jvzk5HbEDJ zIQ5e{xH(t$KE(bkDf|zZia2_OzphQ;uRDT;|6R5T{KC(J$Q#{;?C^_;jl04ojHyaSmDe9V4 zIE?qO<($th0^OE#o*dbQ4PiXfQhcAP1o;pf5RNIfAtaLw`#o&62;6f_MOcSBe@}B5 zLe+;?k?Vd1H^Nnt?H)pGd)UV5Vp~uMgmw_J+8=CHV81ZZjxgHE)`2kEVJgBpqXlu2 zldDB6S7?afFbO%6R7h=~LP`y`dAgJqCP`0*QNJ*!6W#C|Wh+52RZT@$$8^*;lU~g( z3SFdaVlo_Ie~{pNg{cVZ_?AbrYv^YDLn0TOIEjV+2Npw-qnolg)p-Hi-rul|)&*6F z=i`yqaswW;hE-CeHR&zi&(?=m0Ri<0~Mw-awN7#x`4*q~ZPjZ?F|2D8Fhd z!a7REJ$wZy<2}Usl%2Mg4O6V1&t_{z zC@(V=VZ8~c56`uVoj2E?qp|jx4|c zE5ZT@2OZ{4lTNY1f)Goxa=eF?^qS2t9udaoeSfNi)g z(Q_bgrs~$5XpUa5!ug%jtgtmAG|Q$UtkZ<>?4?#w_^pc>ugJ|T64(vG<_;tffed!= zUkBm8l!B_7`{YpBA5$SuNfNSu6}y;p*8A6fNHa`95U5*P15FszoF1{f~ zTkRuk9SEa$n~Jc`=*;b*SCI#o55~nszka-R0%@x1nX}YMo<(9`XPc@^Y-u6#fReh3 zt9+f)ihhNy3IX>;QxVp|&E6&QASiWM?M3q*Ktz9F8>Nc~5=x8I1gch~)B7F!`-ICA zrXs9!S+>0nu8e-ISs535;w7h1gz5_2UsQQB7cMoPM{0##wpN(S3ou}XI*Xn160|F+ zbL`aDpuM8QR);`5(^Q0Yh-XDRc`#`am-8U(0OSU*$1v5FHtEv{@G7>sy3Njs_wZoy zA#T}0C;_Q&1d`(0%2tNp>oXN$9p8*yFgEP+4#QX`>#>T9{EB!Evdz)O13BG6pQ?Ab zJ&s}a#|aMKRD^XLm+XhDf6>BV7aXBB!t|FVXB)=VOq`p=GGU8c>>q~thzf2BauD&$ z*hQp^cw<4V0KrDNC=kcQjqEvb;vy}U2)G>}Z45~!i~b3=nxrzk&{Tx=%CLjZTOwaE z@EU851#YPfH{M0UNk|75`U=4hu%_Hz_i6_r`b(}Kd>7?nW%+A%5$aZ!t8->akxN>` z%@jfOgREGCvIOE`nRe?Bv6UuO=K)g@)~n9q{Q=a2a_yia^H8r0b00%Gg3R7urw0-4 zm)S<@!d)zK*-I^5%$AJ_k)@KPrGJ5~2Ep~1sR--1PM0lR76o*SYFD254Way&ZHg|G z>Dc08T?mL@vp-Eh{L)l}br940o8?Lcn+_q7{Si@|wcFNWV@3hS$w~#Ah|q?xID`Fd z!eWuB2oo0fPMdbjH1U5UZ-RUE$@Tiq7l^kX7={a-r2uwDi?CV*?=e^-_B2`pu>TE# zoWpHY=`?r9tF-(^FM7~HG_YYG{-X?2+sgPRwOMsbC{}_k>{8Tik6Yo^C*0c<*1NIw zkTgCvKAuKF_!wclD?RU2+iA_YlC3bQIhUJ?FsV7L3Nvqes}AVv;JQ^SkG3L5Hf1xl z%`=E|h;5oK&iSx2Cv}5GPFgq8v`cIi2q4c?gmpmE57fQUQPFZCj7v5lK=wyO@?y3z zx=3ae#zJktJ2f}7{|ngPCM=$3D#AL8)jLVZ5pi<7(vj({ivDQR8HOzq+?XrZ8<`0t z|8?Z~E_Q+F@?2d2U13WeTv*{a4GvU-Fja@laU~3LBZFKy4 zhT!|OsR--%=3kv+hO2!V{IlId2q``~Klpy;1VUS2}&Ip%w%tS(mx+r~evaT(Za3%A*IoHqZj;;Tl>1 zGflL>^`rqV7!XoPcH|bal_Fs0nToIu_Cf#~FDY<pY@E5P)9exqD!LCcog@#;{S{SlEB*~aK1 zn*shcs107QqK)xZ_O}U(n@vSnXK`wOS$H}+MX!+weXab06rRsELzlv7h0rxo>OuO$ zyV)Nm2<|c!VI2XCX+HRt)`nn>U5A*wu>Sx~Y~sKsXq0J+t;rupSogCH)`hi9P9`Ib zamNJQ(b5_df^TPQLkParRD^Yci|OibZ#@{O_|=T_MW+Xm+Gp5C>QY;hv!VlkG}Myt z`V?Ca!t0++MOf!Ge|!0GwBs37V{-c2?jhv#bGC81oEAX72BDqYl1yty82yB;17Y<4 zOhs5{G;g!lC>KSl;bAc;gjto-fBjZ?7Q zQxVpoEZH5v4KV3dAv!u|i&rV;pM!OL5<$IQfGg9uOPQMPqj5|Kc|q&5+p`6#OH$l+<*^z zwV~#O=1jImgy!j{BCONAF!J(%t$bJkx|DYXR&FH?dDH!WUE6UzTQ-Xb%+Zll!&(^wSj?%^u5S{j%#{NFxas*#nE{+V!v{&3a&a|b;9!6g4*v9I% zr?YZ+xiSFLC~6xPeB$o4nym|A=bDPJ&hDbl?BvKN_7OVXwlo!jtPijYN0;@*ldzT} zq1bDf^d{wgwvMC@Jk?Z$^*XS2pFaktg3+0KYE*<4u?pNfX&q6QpC$s3{q5{R(Ph65 zJjX(-@)j&XU0JiV>$eZH^&{L{rXs9!p9_vLGVQeNtVJs)XZZP#AiFoP4bx>ePdLNK zkZQ7H7A-XQ1pjqx4G5jrnu@SaXLfQW5N;5O8*iEGeR&TcnZIWnrAuaZ>Z%^xBobQD z$<9aFpC?#8Y%0PcmYxxr>-F?L*vT0z!sbwdY-ZT(Y zN{#U<{B!#acc}mC8T*e!d70%$Cwn-3?+@;r-Vaw#M}BNthCc#LM{a@tnApDRx`tnG ztf~%=KoADMwraoc72(eP(5hYXUth)r6aTvu6j$xUTL9u*wy{d2Bwcsm1?AE4+Q5+! z52RhQytQFkx=1*wS#>LDPXWd(xbr0OxJe1Sht>a)6J7IrrsegzlcSu}-!>ItvD#v- zU7Sj=-Phm0r(J^WiB1n9yv6;t)>2Cfb&&>KPRk&HYa>YAZ=>DJ0=6Eco0)4W!aA=W znLaC;l7;Eflcea*w%b~HXXW~@A;fw&UokVc4Wx_p&R;8I;EKl+5T<}|y^ z4zD4_``87bOR)#D5=LESb_8@gbeV5sD@DM*#Z*KVEN5C5YOz7gIOU|ZSLSv$5Rqtc zu4#H`p+#$8zg-8;1@3mk z7!K++uj(HeUQW82Z?V5cYUDSih_)ztM%uA3MKNn{MT8?1H=4!r1)!+QyPV&#)*idR zJ5yp(uoJTjqe3U?4T-}DU2~K*Fo91GdN<>6D>Br7cH)hx5-&%dmSp zoEIrOoSRR7N;r?jBH_$qbt~u;b~s;VT3*Qx=Y**Ui`5o)IL{TAwB+1P+y)YJ;~m0j zT+9r_^jZ3gK=KiFI-vU!_BtPD8?Os>1)Nlu;2au`CB+>fF(yctcNy6WF0sn6wVo7XbIc>4F!AVURF0`D!P5776~4ZK^K8rLa{ds+%t^2GtW? z+q%|$pREc3_gzyF*1>f;MNo$LP7flo)339&w&EQ(oWjfnd{YtDk!7|! z5nA_8h^}K7fG*6;b|=!*J0aS~R*Hb#V=BTr*tzmzGt64r=ibVH1Y6%Y+b~^V^YAJ& z#2W3KY3mSM145@^D#ALQIU*kk+{J1DAn7*+ou=AD=01UJUe7j5m(5(5Kt_6@J1caO zv`73iwgLprt4&2%M{^oZ{KZ|!a%P^d{)908j%|o8jMED^i4Qdii!eDP{af~z35CBg z6=9u%g#+$?XB(?aihscU9kwon-M^WNu+A?3^jev)=Rbli>g4NfP1SV|xKChfKMYs<{|I0xM4v6UiVSD1>h4t7r%<}-};E!JR=6b0fZ z*Wu`^O~l=m*=1VF)j^$)bX_`Dlc%zaQ@5JziNcMBI?$hyXNzr+F3(w^TW7MiqZ89Q`|E^AU@F2sk!)9;AwqseBCll| zq)#N<_fjH%%Kkbb@+wmi)``ry(Qm>TK>!D@_2|;C3MKam27RLQ1?EXu= zqHDes%?H^E5H#;I6=5CCY5T#&L+nJ-px5e82;%3??`C2x>QSC%4VvWdgM(C+J8wi*Oh!Bm9xhI0xI=CskIe?T0&*hc8$ zIJJP|dwyfNhW%Yq{#TibuwMSMZ<0B$AR=fZlQkjxBXYQnZHz7l?6@%JYd(t_``d)Y zK~oXdS@cHfD8vU3-DZt>DBN#<*8IGRAvI@LqNi=n_0HT8k$B8EAv-=%fv9 zWJ5?M+2?&FTP*_jWu_vm!<}~k0*O0h>7r~swRr}ieSmG6F0}atd2f93HO_n4DiA<_ zZ7RY#p!53F_03AB7L4JUmFJ8Gm2n8^EfaW^Gx-iVFCxlsvI{{M<#}+QHxR3|Xf@=5 z5qQAmxrq^Q<2UC<@7LIB5xieE6=5B3ui_V<&A{gLLlQ{8IsnVti!+_8{(A`bm>X=( z>(5ht-AN9%Mr4C~F`Y&Jk13hNnen%#BCNw*y(13t+LYIN;7$eGN8Uk%!)Lhp zBmNj>wp1DOUq{sESVO(Kki>RXEpn?t9h~NBuwfe-BvW5f;LF*{k=A^csR--9H|+OQ z>pHxGBvOJ8LlR*Ky%4(^kZpezytx>x06W+Pq}!2iC_q$*WL1b4nnc>~(8AbhA-j=J zE5dfRlB6PRF%@CGBJ{z178#TW20bU)F^A1c^d^V~@J8Fqf@+QEf;_AmRd$i-R*lVZ zxF4`Nb#4P2p=fh7-luHNWN)OEWQ46QsU$l^1a8?04MI(*Czi!)gby_EfRLgdA!BCHcxy6y0&aQYTV!YqN}3PKcIS8bD% zJ&d&8!!}lz)>)7vA=Wm`5Gbx3#M%;e53_Y4?A~Q6!Xmry!c(C$JUJSx1hw8kj9-;@ zlgm-F(*d7u8h{MDcc>ws@*YSpuA?wd-!?7R_!88}+ulaLnTAWeGj!@51O#8oUI{mw~j%}BpQXUS1lCurMe88PPF+-54mI-2w3u9!^xnuO75$WC>$H|{sSbLVSC zLuBfh^6En(o~N@nnKr1+F8>h(_7S#Wy1>9EJ=82cp`i`$Lu?HQoe!9buuf;; zmY`OGo#{XTYEP*BV@T<{Yy)*EErg3vv4)*NeT%IG0rgE&5!OM?jQhd;dHvvY`SS`V z`Vq05_%vG!gXxf^yJMer9Q)G*#xbTMtivemh{9@O3`r5+pfjIk?cT^DJD+W|ZcAF0 z1Or8_MWlmCDE6?mAr#Ls6=9v?*-_q8pm$xv8_lS^+iYEq z%i|2Gz^^6r)&RMatquXX!&HQIkh8Z2;v5yi>=#A8tYWh=u1+xW9>5;5!8S@4)0{#{ zXyrnf{Y0yBk-@#MT7U7E$#`{ce#N7$MX(yuTTVV(4h1gfN_Hb3$!vicjgIl8Q7rUKCqhZ5q+oL*9p^axt!ICpl=T`@ z5lI8P0C9CY((&bqXQnvugFdf`ai~Q<42h%tLs8OqSX;K0dNlo&`&P0l1egeD#Cgtp-x{4bNVwP{7be$x(IcA!rsXK zIwA6UQxVpQOy=gL@R{skr1ej1V|8iqeZu~MtqWoIccvmNvO5|+VgD)Zw&xS}bJKE- zeZr=k`tM>TF!t=%92@$Tq3N9UjcyI@j$he-m=;~)SN89wA}rQw^ea0rnPEbXlMZ)= z)~r{jlbjc^r&@ZGr4`u3`Kh@h#LMn*YY40eyPRaAxP+}2>9rP`im=X?=lrLPKfG6w z@n&{G=(gpl`VDSkYepzvW-7uuWv1_+f|>a)avo$Cg)ZkQ`VAJ@iV@7Wnu@TFS<4Gh zfvfcfB7G6tY+a;AeuK|vt3yEEZ7RY#$Xu^L1zheE2vY;X1S*8uKZcYR-)w7@!SEYgz*d5QnrkY;Iw&K*!7JG2=r*27{RS^(f11G9U@F2o z42yn)18k#pk(u}n-on;~P`t@hgmsEm{RZ!0o2|>y$ZznuY;_38J55Dc2bt#2;ppG8>ib=78J&Y$3@VuP&+r$E-c{W$mU|U z4usKqQxVn~%}zNrMkS!Mn!E>)%`@0W>9Uzq(BblQ_V)>w8%#x5=WMdwSx4IDv)MY5I`Ai^BCOYeh57xbvq?Q1Z~qu_{42JBx*U%yluK*q8TVhZKS-dw z(Nu(WD0BN$k?*1iaVn7fM-axpunp6NF|QEc+V?7P>^e&4pV%4@I{#oQ!aAM2(MoeT z`){^Ux@1H%SxZ6uC;Nj0#DAEIunywP)c6(7D>gctgPJG%JhJ~KY2WPM~A>2+g6=9v*BDm`4Y=JmXbqJ`ivs{Hsso~{Em05@9kk>_Q z6Lp)@VwsMmh&n=aAkeXWY?5_sH3+QLrXsAvnzbFmUWt{JxR4=XsgQDhM>tPoo1_b8 zc3}{8k_ieV9NP08V1J%K*>5VsB9zc|cltg*%tj-*s7SIuB9CWDYluVc2{)De3Pc|q zdGiU=rrmr5ohYL}riZmC7~?&rr4l>djvNDLwit|Y?Zm9mX*N{vt)Ruk$w_9NvzvQcb`_zU&1zCm+ZND zWaBNLxYMRHr5CYPB1oTaD#AL_LT99nrazjQIBC6sFyGBKTNh@bGfY&Qbixm^^&uqh zHx*%>G|z=uamkOm24Y(Zf()J~!r zjSD0_`Kk&Oep=p{cG98_Ccrw5VMnVzks$r8DFu4w7T zS`uE1*?JIO3rs~==hf5ajCtcuGk{!%UP-PtHw${#d-bv>b_@3B($jwpS@y9DK)2oX zLgan0z-a)$) z<=PWR$c?i;>o(W{wo(M^Ev6!@V_ke5BzdXJtram6j-?V*W;)mo4l*!FX<$myzUS z?BdWRxr*fCmifFIXir7h<2GONcjjlyHaO31aXPZ1me%w>JW%OHWgtV;-W1X zW`g5Dz3gX}5FMUFXp07HtsoW`vWx^b)RDlN&sKxLnqw-$BCOEU<6ODT5=}N?tHL4p z;26kJ+nw%9$nkP%J@E`V=Ah~n0{=TbmyP^Ewwab)oh{>RD|{VaDmv+g8Na)PBP>Jb!x#FCV|ful-lIEFC+KYunR+%`zpEdC9H|}mcbf0 zi66uC?!+3x`d+qfg!L;;MObIOba&8%`$f>^8;}52F0aeY;phk<)4nHr7+HRZZLBWK zvkEn#t!TTUw#YDQ)O4Nw0k$rL-Fr<%WZ7{Bx=@QGKLdv9*AQ{<<>u0wUd(GYoT#YAh*D5QriKa(zY zM&1>tX80u=V}7j^#!r@-;b-h`ky`g-DdNdY&9Fi3*GX!I4Pk1AxyA0RI7q?fq-NMa zTlg&Y=Sf*lHx-dIsZ*thk#47E*q8*))kw`SScXkfk*|FOa*3(*rXmP?^$qMo(riBy zFf;SOS-1?2adKm4lB5jMN|8}hS{cGj_IfU4>q+XvT2m3$>x0JLO?o*vq47M@y@_qI zE?uL&o*UWf5Qx{Cim(pxlB;1R4X2L{U-*d2^T+HYRGwYMxye?+27`=Yp|jYwNYkSNixxiklJ3O5zrp~4z`-4GCb2%g!RhMVM9-8 z$sL|Um~Ua5s0)*|@%JXS8U)r~n2N9n>*#I#eL`BF-S`{13g&~#b+9%&f1foiym;qt z$|)E&C@C1;e9tlA?qO(Iw{{OvoW_bMUI^({_^$6Be%usFvU~V3QxO&$1v9zB+BNF< zrJdXXUc^4`59~tFMXsOR0h9@QtYpslJGNe=(|f{Hgmu1ia#r0c$lNE8SfONVaX7b7 z33mhF=r`I8plBSn0tC&OrXsAPS+GS+naYFZqTKorOTU4NpS=m%_9;Yk727=BMg_5q z75&7b4fP`}Xe(O@f~n6`gmp|y)B96$!)mMVk3t?C@LYf$SG6%s_Ao*_$Tn6N+F6Al zwVNgnK}w)4nzSy z?(bB62;&HTc`bBK_aU~UBW^oq0!8S)gzV1pZB4OPsP}t>_QI>M<;$%*p}mXRllFB6 zTPMPFk*NslOy>#rh-mTQ47O^;CLBbn&8*EcNNfw+G~L!VUphNPx^)PRb0u2^0_bv6 z5!M0i-G&z+!L4D?sgw`;mGW>9lwwp3rzIjyfQMyNQV^{;T0+YCd9CG(IA}G$ITq9p zW@dlg7mw9qh+Uw%)#9nq#S(Cx7=*}aQHjJAq~VGZ5&oP}iKG_Qat(kb;>IOHntX|^ zJ*iQisR-*eYWn`Mz!~-6=A{oOm6`gG{Sj%tm~D(M%^3x#m2OHK!r}$&Zxa^JGZkT- z#q3?);c~TAO|@*b@6CGvnY@c_lrEDwaE2|lO0_OJ)p;lT`-ICoOhs7dvP2Av#Q;1I zq9GA_RS~YO>1PJVj!z<~&$G?cC3OZykpw;C-Vge^NKev~KFd~wAp5kb25_JbXsLtaY;ZLJ&@!wqE_Fh_)R2OUKy_ee(qYav?=0&AYB z29H;o0uPIDjYW?y_BYe+GT7_2(?R0 zMOddce@CrYX-R6>)WkVPcB`x1LrAK~Hcpq+fc7)NbY#j)rn@vSnXLQ;w z*$L*6QGY@n&u1H=%j0ysSt56ap^gv=ceB4tDBNW#!a9XH+rfnkqG|N|qfNg$;MbkC z>(pT=_X%WjKie!_CUXmeQZLvJ4)t*Uo&hkrHVYYb_btFStg`r ze#+GJ#AWE8O+{F&ndmZf>Q&GOm0vk7@ZO z2!3lS!a9Qa`{3eC0Bb+k2yIKF-9rfG9BW_}6zZ{daKzAo(Q>v9qys<8RD^X#^A407 z5GuL>8`WDxV5+*a)q|`6>7H_;%`-@72ir8=@pXP-EYeM6?*iRih&AES5q3LU1p;V` zsR-+U&bSWPgj**;z3x}g4GXTb)XRrePMse`TvfKAy133Pw1lR(b&_c6hMJPDZ-lK0 zp*CbH!aB9HAgFk;1%7im=wu~U8rY;yBfD3y&DCY+6iTta1YmxndnsEPg73wqBCO-P zY!7Tz)*-2=*J#0>k_>pGxEVqq99X*hjg9GE({a2ZubkP4o|-5G{~mTh>4Lws5C}^l zK`B})j^`rxBXszL@Hx`bbQkQRouo-W%+{0CiFcWbuwEzn(jJy8aW6Z}Wd-MCO>qwF z)yAD&;IaU2T#k%^C7Qoi84AFOsX3g9sM-a2SUbMTE;8NP(Wm-pLQQd_)L6n~anK7U zLk}-aj@>uil*y!ye2J|ssUx2^6=A)Otk~xtDnq<8!98ffjk=u6QXlI8@9ifuuaj0G+pgO=@!F_*q~Pp}Qrg)|GY&7nqaq!A(VIQ#2_$j?nhSSPYjdH}%8qcfTI zk0GHm%eJQfi_kMb%n~OhwV161A+^9%gmqFUi|GX9;`AzNqe=Z8S@f|@&}}WJ$Y})X zK$^)F?9Yp4bm-!XF`(5Nwpz+Vp6Q_Yj`XE&^S6 z=Sg^q4Pt`}Y=GlIw4r?;IKWnmz`ey(gmt(xAKu=#d)QwmM4oFZ!a9)|86s+rM}9>f53tSAo}GI zjuP~IaE>lEDX?<3Yc7*LjIbVK8>NqikIWyHA>mu+A=?xpk)2 z{xRhBOSXZ!ypjptCD0K9k}hj~#B((@ldLW@RhO~L1dQ33E0 zdaPMkw8<{Se6|LJ&Ky$_*6Ey?Ir_ptvBR*VB(Arr1JoqXBCpHYrs}q+rP*UH4EGxA zO2BPot3tqCY%0P!xP@0`X6R91c9mKC#}JptHc%JWB55; zUz&=r&LxUu17kY$K^X_0?2pLf(`;jOdBkCEB5g<;`4{%L35$O+6=9u4G5~GGy>TZD z!J+nc?H@xvKV=)J%jdX4xs(&Q^S{|2BvAg-RD?w+;r*ZGeUKZ&gC#GxCO1aK!V+9C z!l+Q8D~8HP=LIA+@1U5lkL*5W+O*!gj@)siXXH&MKwgZ~(n%TBOl9g%%F00f2|sYA z{D3#|P7o`^KM4OqAm4}ZpNH|ENAMpd&B-%BrIB02el9mD9pf4Y@T zXupLd1Gf3PBztluP^pXrNjxZuwZc}4U@e=9u#R=(UYt(FcdM+MOd#7=i?P8 zQUlQGv9S`OFjdRwij+BeV!esP-^VTnUE=457oZ|LqSM0Ad9wjwn-VifNB#&~FGBd; zrXs8pK4;6YSE=~5A>SDXzjBD5iig7xx<$+v$9(@F1Taw>x8^%Y_3LcYb*Y|PC`P)w zk?!FYDWSU?=}v%tg{=|+`bAR_S)iP`W~fDy77)|K8Hh-<_%G9BbzwHZTaSmicJpLq zApo=KH{;yAT}HH?k!QDiZA`HY!>FWYk8u$Q=4J?DCt#K}qe9Mm~HJ zD0)ArH8Qu-o#O^!`eeBPXR*IUs@ilZqHP)XbUp3d%)J%Z>k=csXhF`pOVrj+f5u{6 z$2K*;p_5{rm<5q&!TV5*(n2E_G$L(!HT&zNpj}fDNozU}S+%S7rnSBc7t)k@co*a$ z^8@T6(`9bsg4=$!wxo_c)l`J_I--45O{odmZz1p7+2-r=p27vU!)&Dp)|ROV>sZ^} zT~jEwdkCSufo+^FH2n*1uVd>#7`@h1gmp$o;ey-WvyInfXneu#qimH3(hr-8u#WU7 zUU2&XyAX8IPU(W%_topZ&9iP^9H3gy88;G%=ZMH5(!wYVE*$NSq zyG%t`M@et6DctDK2x*LMkS-*h3vNyJ*9no^Ohs5H5<50e?Sk8%vklZGl=weSe!=ZE zY%K_>drd`HCzZO$rZk$=-?6oPgl&Q@i;frEKE(bkDf|zZim+bzjEiat9L9SH@4M_G z(1kap3vSq`Gncz)+!EKbS1tC>66=9uJ{_QoTZRJ0LE$Y>5!*mJhUT{0Y)_~A?g{cVZ zbQbkD!4K1`mmv0QrywmIowbK2MLsArXsAjo>|+=HOQ%x*M9SZHM!dp+OA6xs!5K+K3P#4i6+NDJr zhQ*u=J{7hWgjCs7gmqGjwgk12){xgs1*6KF6?AwGS-pyFqAsh&A|?y!m|PKPH&b{y zTMYv1C8i?&cwoJcZK5tLF$ArpzM+q>KS;2=+f>9K50uGEG9s7d>%M+#|tYhhEJL1SY1Z4_UHz^I*(}o7~=Xe+dy4hoKS6FU~550J!UGxIw}2_ zYf5X=e+^0gmR$h4B&QOp?bmFr2-#nnim*;LFA|%=Fz*4Rb=GaR=IeT)+Rk8qpKw`Z zD#ALKY&157N%lwNv4w4nZtIymRNIy8Zxa@mn~Jc`A{l_D6sm2AZJ;h6v4yvR&iYF1 z4-zPzsR)Zu?1yT5v9#J^sJ2&`7Hb@;ZDRYX>l%K&v8p;e0(mO@+N%A&%v(CNDooiL zWo%tl3W}?C`o$)s{@ook{l+R04`AIT7nDcGYXe6{JP7=D%`0zM5C(b(ZEqj$4Ikjd z&(N*LQxEs{0@HF$!o5AuRD{JE-}P{BA7dM-%a9lD?IUbGNDuWPQxVpAX$Njo#&+$u zaM1rg+k9P;QwaC=UA9sL>$glrSjRe*C~XSqsR%;&r_^oDz`Gmn?L@Yoq&^&HD#Chw zUC%5gScN6db!*hYNibH}hR&{b%f=&}Dr=AqZ`8 zr7a@+RU@`V1N5uesu9pfOhs4+y>PSFEJC&i>7oFkEz9lz{y}Bh{xQV&w`>D-@hvKZ z3P~3PMMKgF{|#FULhAjdBCL~I)}aA9J^fd0?NyO!JdfJ@c z|Hf8^ApC}@2)W>-Z#MJE37~RdYrsY!um3*oqKj(@aHJN49WFP#tYy7;2Gv zDVo`4oblT~hOo|K8>rjH7J<`Ntf5G)lxRr$#}#ZX2&uD8MOY_wDs+MQC*#U5$YVF# z3|$_l6`)^>qQBF|axMGA1i{s&BCI2rB{DZe^-o-w994U@oZk^goo$jXj@dFBL!^_q zAUR5*1nkcfC>2u?)}hSl$K07wdLFUpQL*GcfnffWZI&*WxrGL1&J6XEi!qAkRcr+a znwOi3u#RTtfnmSqlmZBb4Xq^@-K27%KO>Y6vJKLOGP5uS8o8waf?kxB z!}3n{roPTrgdqEhsR--HX6!G+-c-pidgBiG*Jrvm@++b_wrOkbJhRXQeIN-4=;KO# z2#!CPmSuAK`a4q*)^S|0MeGuem7BwmA8vQ6I^fsEw0RfoEQITLXKc7!9Ci+Q^|GIt zMRQ+9nCDu9xeDgiutO-Uf%IxMX^og-i(QClS3+9jhSm_)1-5Ra={cq%th1iJ&xhm* zMMz0ohdtq@+CgT2L{`_ZjnVBBXFz&qsf`P%9E3K6#Z~NY6Bb)dMObGsYgc%<;tY5V zzvNuCRmG9>I})j}P0}SYyAYiZz@8%LXVS7>##V zX)P@@q^@C`iV~p5x)N|-W~)NLeZf?Ob#N!`+tu&Dnkut7l>8ZS{14jzT^uJD>eYrT zH6SJbTlQB;$^Y6^g!Pi2-nX@HmlKS_5~cjiY&Vwu5h*Nh*;*;hD0n5W>L%I{7H6@) zO<0^^D#AL8wSASLpbjgGDxSTHl}1BmM(ZniqGwp?KsynYR36R3A2WV4CIXP@c6OoY zwyd=UFSbga*Gj8ob~S)4ta73038Un%q5{x)`WCi&1pAeyBCKPdzPIib!G{7OJ2lIr zne}h>N5nP4HbxiM49Hd+YU4_6ND~}lf19ug=Jz zb4ci=Y!h_}EiQPGj>%SEs3U>(VzwFt)(cEUScf$o(*=v-5dDZsDElK~d6;dCE|wW# z(%)Dc!s1=*Zxa^pG!@nhjP`SC0`3+%h zW}Bkha;Iap13JS8KFJM}vBY>1ms15Y2;Z({$0yFSHWfk`aXtBlojaAb{R(D#ALT)xveKFtK`_lV6=59{|7N8!Kj*)WV6R{oh;HK(A$l&ML*J$B4-$wQOhs6SxPG&| zQwu{KILg6-xdEGLUQKSOfwKY5=y&^L&7k(3J73$#O`)<@Tf~Z30HPdV7mF^+bp^ax z3;x95GAHeF!7lLgu8x9T*ko(cF1OJ(@5(J~{RsJ+Ohs5HzivmZSZT@GO^2IdSOcQ2 zSnYw0Bp~^F*u|ntetn@F+12T$ZRl4SZRm&G61U~&vK1ug?=%%*9X-G6?MlymAG<(w zp&t)D_nOtT>wX*ii-h7^Ohs6ycqQDeDObF@(}NB^;0ap-hv#U|P((`T6$_RD*f3W^ zC%}3BRpc0J>f*3zKgupJUCNuptsP;p8+tTJgX2}J45Sd+s|HpGkN=Of?wv91m}%nw zMm~4~{72HCHbZR#_PP?l|G#rM`lHNonD#9YBsB!J6HRT4P z=yuhXa+>lJ5-Cbc5b;y4>AOLFL;fZGppB+A6K2z~%I=7FnD&RanwEERqwHo=5m{uM zA_yza1_-T+r8vDJ`Z5C%i590y5eB`C&;t5V?|4wAdGfSry>}fEz0{kaCmLQp@@DLp z#@qbRGxF>a$QX1Uh#OTE$+6tex+ zo6c^(Rfkjcn%^7?>IYR%n~_hR6qV?k*j)3w6j3Y_r+BsEa8R$oEr=t-%Sq4i7wm75 zp5xD@h_>b5Gtv%#Y5C9ETk&e>cPrxk0tvN==lqUU^`mTKH4AoPb^-3O)f#fjBy@5? zCsNiQW`CZP^#@HwB#rHTh^yOBw)D5ERj)pdo+1?pItDl7{evq*w-VvERTfvXGc9GM zQ-Q?^#%fU;#6(vlBKYsIi%l2&=0XGQcBMCoup92-Lj^#uqsZ)NUL5Y3HQcn-q@sMA ztuCo3|7t42dPQM|np3t=nC~L|lg7Jqq(QpVi7AJvJD#l?0e!5g2U!B)5K`xwim*;fBkY`lOyhZEx0h|QE<1xTb-UQg5QNv5im;BbWAHfz zUdJa9Ta#_3E;eSEy4%=_5M(t|5!R8lk3XmIYX2C*dJWq^U09qjb@#HhAf#StD#AJ` zB^aFoNBISLe28s^E{{pV)O~>cVS?bjrXs8($O%KIfXMkBaeRwyk}eLdFm>N#f1W`3 znyCouP;!INDOhr!KrqKW)7G?HGfdqvYy}9K|M_2whQ^^&xX_;wN)NkCbX$u?n7VV= zA16STn~JdBRyqcsQ`mHT5;5&$o2iS58K!OrTM>e6yQv84$VebM1rzxd(TuXq(M6*X zrmo8VIKeSuD#AJrZlpPd7WZX@d4ydUx-h36rtTGN-3aTKnu@T_Iva^jVVV6AS-qca zj4rFm!_>Wp{cXbHVN(&-S>%MFQ*h+`jzqq}Hc6L=R+zf4vOiCte92UVbtoEP=M+d9 z&m**Hx7(VQ8-=O+y(xj@nEW@UBCJEqi$bSR%XH zo>LG_@+{K2nr*6XPsk2aw~eg|0k_#ygmrL9JUWF@@@K?RVH==}qf?l=GW)Bf-{ zt4FXuXez=w_G~0N1!?w2#Pt=nF}k=W4^#I=_O}U(&zXv_&Z0y3IR#6H=aA6v*e2={ zVuh)Df~^LD^|+}B>#(ws=oCWP9}$c5C$?5elZUB0ll^VNVzH?R>n!x+%_)@hUqgOd z*#)56tfmsCu8*x1A$x_X2-$l7tH-_0os9QIzhN<(}YLm({U@F3TKK9h?%rvPgE6f$}N z+dN%Hj4*Z2V=F;0J;zjpbxcoEu%maf3q%*}nnDBaK+BZXYM7fiXUzfDD0NB<;s^9!G4Yt18~k*=XV_dNCo3B=i^BCJE4dJHq;b8? zRD?xLQR7m=)hRt{UL?E6q$L`W?C?PwO-mz^-J_=EowTe^nu@T942%7&h?vNYC~{tO zis3df>C-sm{f2F>ZcB6Gz=J|xkqM(FW6r@pVa&O(xg@b8f5ldYw76fGim;Avc3-_& z9xNBjGVETfPV!skJ%EswKHJt3WljNt0ft&hK0+(PWeNNHgv&xx5!SiPRhyC193S;F z;otHfK{lJ&hUqq-c?Gq>xTqPSvx%(%p>vt32IZ?AXvcJcqm&C><7un-9SaLf`Jd}95= zGEQcFpJ6LOFn!8Ygmp~wceN@_$apahtVaEM(I16i+}X_L?H)o%kF$-_g|whhjkR;r z+7U)SXX`*1{lrv+bw*1L439fWNu)V#QU|M!Pa>_wciNh(FDZ--kGqMUorx`A>p_Uk zH5Fl<*!CTjN~_U?yeDEQ485P{i0tweKgG_e1|`2DL!Ns`H&tNxqYAfMLa`oP!7e=A zR(n;UoU&f@t)7e4rwnwZ^{z;w>|vcDKhoLFrEHx^o!MY2!g`%qw(YQ29j*8cQD1J@ zvu~xdXP>MceY>|hLy$oyv*^=!9!U?dP1Ys7tl)<_3(ALsx(okLA_c6dGU=&rVQWJe z-efAmI>X+r0r1Polj4*h1*|jRH=8idUK0#t`fbL0$n+j|5$H1QEtJ3pHz$`0B>9E5 ziZ-|-!2oTa&t+>x*xqR>!aCdeeI=R7P+cr$8fCkOklKB0<8-MlD0ou4$rl}OW9vW| zy~R|7bw;yyc`&Q5!mwL}WxX6?)G;*g0c7(i+bCT&5GCgS?*3nAGQDiLiUAh zmpqmPatR3uO9UY+gsdcihzfZ7z1!XIQD zu?%9J*eFShSi?bFAig03vBp+}F$n7vRauV&ZH+3c06jCV7h5GEv6ho~lK6&<#1oW= z!&V5C2nyA>ioKTT}5sh?qmsZ%>h@EU0s`7K!m{Clwu z%=II-B9caMkmyZxMyfNi8F{oik%w%qY9&KwW_l4Ze3jUEQ-)`BVMsI4M0tkvm130` z(toxU;T-9#^=-@B37b=smFyyf>*Hd>OmWT51#QjRnUyo%j(kL{0i*LlTM^Fbtj?md zB3U_rMHKG}c+p?)tCfp+uU1X3{@4g0vOf_!#gr_>9m^n_EG6K|&|uprUm3+3<&VVb zG3?*B72zEF@q5B@co5P|hI&`p@ppoB^3z=nwx_@w%2)^H{1e5uWzIj|Rz%wQk}Z0X z7D=X68s%7sNVK5jj}{^lEhycmg@{Cpm)IsJjPkwq9o~GekKeDdjIN5eRK#yp)j$Ha zGQc~L7W5I2oH$6m!}s#=Iz(#~rLVQqyzUcMs_Z@sy)j;z*Q><$Vr^ij5^)&E*wZl0 zs|UM~R3cGt%__~2qx@^?Wg22r4c$6AT_t(#$nlzS&S*${cjoAdt%#(7m59|ukEj=H zhv`nM9(wx*TlGdE81Z(&^rsJ2|5vTn;q)v?oL($8)0ES~T$%Lrn~|P=jr8m2t)P)TM^EYjk_aRTNN0$G@*O1*j!U|7W@?SR-gQ)=e>mj}fWf<>dNkC-0Ec>GPh782#ZACnmLHtQecui2sfK%S-NXHL}LODPt%3Lh%h5iTO&zVcc8MZELdjT<%tgp3Rqu%{Hy^ z=KGf~5$nKQzs^=f(g-dfdK10d!gMRL#?160VptFxZ_3bm|8gK!i6On-R)lk;*_)F! zfZ0U|*Ii=6OmUg+U%o@E0i*MDTM^Fb*la)6*x3jmvJZ-#VoG*G_AfsmR*zwSjjagh z*gN(qYcxClPLMt)Ho+89&;84v5#N?M|C6>N($2To_M7Y+rcsWCh(rrV8yjImW7rvt zrZb|+vK`xZFV}ZBj$fQA%%nSA4Mi8{;7E9OSQ@`l9^#uE|6*GMk|3>rv=!kT-^E+% zwF;gm!2qq5pgQ8I*iVfW9(c)XRf`A1dIQeR2SY>k+D%0`9jAi14u-XQSkciQnkd44 znltPd=la1?JY<5QUC~mXEQOt}q2D&t*9^t)l%Y|#knDUtRjerMSr*%ha9$}kZ3^qf zgSaanD?wk7Ki~oVp#Va-Abs4KuQr!Qaf;H>!mFN*JaZ3}uhsEZa((^j# zVU#b$4)kpw-Q@$Qw}_Qt_}*kI!a2UR8|v_&#Aju(31g^%5FAop;q@2mz>qyU!y8-b z8LC6IltHM!Dt3)2>b1GP$Tq*&gi#aO<}1^D_H1mM#+vV!#2PaG|86V7A^#{b#k{2b zHazHXA);GF#q84=cP~a5|Ew%5eSONLNy~2=yJc)y>E6k3IPsX9Zzx^AeXMjJ{BqqG zC02<3);Z%ITuM@oex`KV6uJ6QxNqqO_-Ay>%BveN=3iMEEQQrZSY5d<4Dy3e!B_53 zpW*f}s8{j#LM^{CI@Y$c2Jr}24#Q#3HLK1k4vkd%#!3N5yYfTFPo30hpkxYbT2B{u zbV&`r2)P>&0d`I|`z623JET9@)}~}e_d8n=4l5+pj#*h9l3o|Hix8%j;u>U%X?A9J z!s)CKYrwjT<+dW6(^;~mh!N)X2Ln7j+P!CIs~#P8yRQc)YjP->d{TbyWQBB{A%t*WmDOn^M% z-VnRYl=}wgZeyF_%^SXcR1ZpJb2`Gkk2a^~t6(#0!b4(pStY61if~>@ARa^+139U8 zK|}Qrd$N4kXn2L78R-0b7bUbW78`1cc2O=*nyU9e9h&+|Q$}q}tO=v`0$UNzsmdL@u%_;sPp*ZSUuI3EK=G2rgBe3x#@jaQ(|MHmi`HcNxabU1XyAt|} z(4VFJpH+ZZoGJE;X|tG_8z!w(i-@#hZQ(TW{TY{2ZACb53)8hc#Y3>RqIX;w-xHN> zVv|g%%+NCuE1ejWE5x^FP&V6&a1JFpHALHKhak|mTI))Y=~jsF)WpV_;%Of(QW+gP zv}26QVjUQxqOAz$jFxU3tkoK@yQ*`KjvBMohML7n@#e6uwZsl?(VB6*TdWV`_*`2N&N(jJMYwRe92aXa~AP~ zDD}9~d%tdlh|S-`#+kC26DNVupH_Sw=+9ym7@|Meig1o-_SOol{HUG$kUIokqg8mW zi7sUbQ102T=0kIG#aK7oK;PDlwINTe0t2+jR)ljvxh<`7*{k)HVDSKw(%Vnz%}{ON(kFa({r*eg$Ua7#m1RJ!!TK>9i>s~(2g~|QLzq;(X(ttIA?Uy zHN{3NC}$1|Q{NGhw~0+LB{DU4P}7Bhcu0I}2I7sjBAkO*(8w1Lz*&JZZV~VK80%S* zAbmw_rYWR_xlTRDeQbSEtO!H)d0P?Ak)_&)w*5Hu9bx&C*c4MNxOwpc{&@Ml_=e2= zzqJ+N-2Lb5gK+__LDX8X$1OfsiwhD@*tKVcw`-4DT3WwzlLv=y(`)C_iwWS8=eQcv zpOeE;4z5#xHOYH=+#_`p9Gb;*v+(W^|0iQu=eSU;8bdwbR)llZvvFSylEfFhK-asR z6YWxlz-<(pX4>-RsGT)29Awo6&}Cv37@$jRMK}j^%AOE*Ai$9))gZAAZh|-P9_&+1 z4flE#Bvb=pBTZ2)fJLW7OSK?~`vm;#7x4wL9*kFDE5bRiML?$WFviZXRfn@RJHzI1 zt$skCXN^;qs69t)swuU_oqK?>Kct;n@Ikt=p71WQDh%8mwj!K^TYx>`Mts<{8u;wn zOQS}0uu#X=vm`-#v)D{iXbV-ZsJ5FaJ^jv6BOj+cC{~0ad%#vi8kyvnWu!$CY>3iT zT8K!r*k+sHDoRtDKL(DYHjmfN!onHX=oDJb3jO8UuvURfKRgZ$c>^5YE&WK$HoKmpYsSl2`hD@eSXKP4 z648~xvQjq)rKfenc6+xk?g#&{q@<~|nCYCQtH;Q#$Bs_SXqLH^=Pb>L>3g*J?#$6g z*osJ6+h2**L=)+eiS#0^mXG!WT)GTaE@%*p73BX z9F7Bt=*Ntqt4fY`Y7>3)%LwK!u>(wDE{EYQS`dd8VPPf`3nDB@Os?%>tr*#@wj!L9 z6`UZ}&SlhS`2Q*R)ll7hjxHb<9%qNs0zGT>?qSJFwtir$Hbbl zTJZu~5zcExuOp5c^Iips=zGORni7?rg?yJ-560{5wj!MKGCkIa>|Qv3(h-yJzjmY_ z)2j*Sx5QpB1!{dL@*8567~8Meig3<0`^2Nx3bTt4uA`poYL;SpC~}fm14idBk6Ahs zaEMVuIRWyB`JG?hayiCtII0MskS1VH{sqV9X0;FixS#xVna>QN)JU|A=ZRZ z+iWYsIkm3G9W`KGOA)J@*gR8KfU;)JYQ^#DVgyPMUIN^%~(9k zR)ljF@q_3P4n@9AY@8_@<3o`TiB({T-e@brIifBH9<^4}r3^KmuZT@E2V{6C@{3{> z7@*JFif|6d=!m0+%jgP%_b0L0rtmBeMgCr_5JUM}TM^Dt8Xs@ea2j7lNS8d{)$slh z4n-~$E5)$Rw-wjWH%+$c8Av>losio8s$17mcFtqA9gQir#+2A2Acn$dvR6jLJO z9*Qi8Z_Pjiwj!K^=y}vp!_u=PL3)nZOjAh0Ly>oh6=BHkuodAPS*m?#kW$|fmN$z{ zF~x$1B3JQUtPhHB$lU*ctqAAtm!50X_((4%fL{!?xcRgh3ExZBk@U3MsPo>&jYYqqTj z=e))_=%^tZrz}ysRBWng0}~&LyjZLX19y?F29(B~P^(;xy@?tYhp$QK~K1Hku zLw2352hFl2bUhi?w6KZ?hHQocNT4s(u2l^9!Q%2C)&Qlum#!8!-t! zGkBf&zRdsk+lp}R{}ZlO2gWlRllBb}_&2c`rUXvR(Sh(TP2khw8#4rt*ottDp!eQb z?LpPMC_(yfv7x4raORwGWcQci8!|XQvlZbS&KVe4VM9F(AY$D{jP+SpF-%r?Rd@`k zlj|8x$MhlsHunXtM)7B;cnf_>dq1zVS2;#}P@dBIbZKw1#40hQ(``jKM|u`y3=aKf z3sY{V#u>eX5=t&4w2u=z!L%)&jd_G)D^g>N@q-s$DAtSdU27}CIp346C>9D~)r-=D zXdP(kJEC-h*c4MrQ*(n#7s|t#k*eg$;#)Hi*V>A34&u!HgT?%y7eG*tgDUWDJNcd0 z7_7C*1#c_Fs|hdF2Y$v^5xi%J%{PU2W^Neu_Y?iwDe`>M-!J;0KOZsPD%Ocny~S39 zbE@mMHdK87?X`g-#HPz<@?EyKI8dn-3(Gx@Ua_8!8l7 zIkGal7Lbt?oKKm^>%yzWIS4K+^v98gjMPuXS};;SwiV%=)Ut7(ufrG+F5T~%Uq&Qn{)4Oe z$+GdEu)|^YBX*itDF*f=TM^E|p1q@1ht3qD3-O^-V+A}>n?tQ;=J-~0CE>k5>;}_@ zdUmb?c3`ag#Ey28ZNO6#&FDHbUL)3v5ng30!a3oY8-gYbjdx-Kk?b(*nI(wWlf-73 z5}TFlL%m>qpi?i_t3E-j07G-NtqA96j@?wR4ME-1A9wA)5`w3R)i*_OT&@t^pSk_- z#W!VcAF&nT-0jmZuLlK8*Wzs~7l$w#w+%D_veZ;H6?9Cev`x=mx7oSUd7|+yOIMa&=-^azqo8mh&7x<{XkJ|f@ z_V_f?Lj`B7%6vqu6Jz>8TM^EgE?*DvRfqgSZMf<|N}9$HWJ)UH+^vl@ilLmsD!7iw z{zU8oQ?h3P+1LimbrsuS1ouZ`wHVy*+lp`wckOn_m`Pc#8aNwow7@-(Km~GOsT3l( z=bBA83g_0dt6Nx&d-$-+ifB(3lWJH-%^2YgVKW#Fc<@;y$L?A8!J6TA8)0Phw0-T>Lc<+ z6jr)$c*9CxM`5MUTjy=U`m5rb1NL<$VWu%jM59(#x%&#m{{FCzc?lrAeRv}z8G}_S zy&05#+YU5+g_w4BM~2QCFVOU6@x55(+@M4p#z524cb9`|!-I^2Fh&Rucx%o}4c++n z)L9IOjWu-a=#1PD>g0n?@Z=8<_@GndsAL(hAih2GbzmzZX@b`iu8EE{y@WP)tZy}I z6{y~MucOZMHQ8}X6R_uq%{2w)MH@hZSYJP_FT;12SQ&=z4qFk<@tw0F$RF?^*XU3H znPV_0KK5U2@ARfAy_n#>S?ml`xGP~&5tf##V%LzT5ZLi|v$T{lz+LCDOOIsyrAgJeATEN9e_-r>X+vwTTm!VR|b{A*JnS zm{`$NNB&3bNYgrUWp0=}q28D(PoyT}l;bQ;dIpIP@c|BQh*O>Q$fWffvD&N({mNE^ z^D5Nk#Ew=Mx|AWP3&tj9UdG0-qsFIt=808cfM(l@a1N-~VI7T9uY!c?Qn8Vy?N4^9 z=VGxQjMqiBBAoNeb)-5g6d^Tu1IAeJDyCV42XEhqHweQm{b6f#1rf}P%{C=?T4&m` zwBCN-h_CdHI3zQjr-&6|D6g{>;T+{Shpx2NH%?i?_e`;=ruf7Mv~Cxx!ob~TE5bRr zp2w~_#$vUt2GrgTw^Q3Ih`4}y;$ErqO-{=KxA$e8)ZsnrrJ`h?+f8vZV}&~ak<%6 zgmW(QceKjzny4H!8lL*M*k8=6HxD|V9_5JAtHmaoQaUB4LY6D-U`G~cn&=pLIvG*i zD^`QSdbzELG%Sl(^vPR(8c$k?NVIVDit)64AshgL^=e$Fju)ua+lm_erJl83ZFUJ& zq%VryZ(5N~hx7hQbG5V_uPLiH6iRcSR@zye`n*^pR;NB|E5bR=?kR^?pRacTJxdb1 z-;2#OW!ED)G3d#V{Z_09L-uQ15zdiKKvp$vnPmdx5&nfQay1EYlBI3FSY1|0=GcmG zUP*e#jL`V^E=p)G6B}yUvZYztE)i?OsI9XV;hb96{A(JpuBC`oL2RBWD?ygFK&%AA zbiJ(z=a|OHyr#h#rz|16OKhqsGI5r+JH)Cma8I`t;T&9?kWC{L|B+BUC|2GSMfWUi z4~Xx{eEu3+5zc*{m4r?6e^vov@j0teCdrcKK(OWQ?aeHh2{ZACce*gN%_MzD8LV)qoWp{DGlS=z1>Yr?2K(N=_WYUxC5 z8mIJ^MCNv}F{Wh3&(e0A_}+}gQ*A{!XAwWG4k1h1>%_*HvN6umcE4B!hUh+95zY~H z$-t(ynl5Fi@qAirnmHiDENzd7RbYTVW-G!uAfudX8ZM(N2;MKnW}CvZ%+mHVu|f>x zqqZWPqcqO9rr|WcijdBFiL2rLA!KQrE>?Io1it(srTPIMa4$o~3QASO>;v zwXF!}j8fU8v<8;?j+)Vv#ip1N88=JYwc=Yd5ZBm>a1Nqp?llcd&yob`RMTrF0KA>Csu!Z}h&5)%!p?a=- z>%^$O-&TZks)v%aL<4;&f{6W(#7;70KXKVlzAx61)rIfcif~>ROcR-C+)Xbc#wY%x zt2u{#_LJkqIx(h`ZACa|+C8m_MzMP_;&!gsK-0D<$$sLCwP2*qvK8T+lzAExjhy*q zL~@_l0j4AmA^XWyVx<_^owg#JgB9g4(b$TvB)m6?-C&CM(6XPj#CkEpbz2e631{Xu z(MV>NAYv~Qn`KJOF#E|%#R@PqFR~Tk98EjViH4*7S3>ZwV)acC^vHhlFXEdrx4*|$ zgmbrNWH-?OWPDF3{!46TK0cjJ58>?g;F zbz)49v=!l;sUVAqhE;GKkzFBnfoa1$r0gfl#cDCQXV{8x4%aesi3ZwI20`B~c8w|Y z3Cn)6L#!gJ09V?Ia9#nH?2Qt9?Ao*$;-?pzgLWMwg6Nn()0uY_2)JTBL7h zvWl{wB$SDKpF|~kp;#G)?;mVMILD_VcQsWa1E|+6o@FGf06}`6*eFv-6xvH^<+rtB zT;46dKjZQaTM^E=%-T_`Lh7uWDUS$b;mC)LREWatBE;s~V#7??%+6IhG{gKLN;5|1 zn_>+Zo&T^E;hfG@5uG@Y7RGLDN0Nl}&G`2?52Xi>i9F`W6eNRjAfM{R(Jyl~ci9uy z3$R^<=+fd@LPBW#d+ZZG@`*I1%n@SsS*7~xW42PAviYWE7reGbol*Gd2Ayf-&izU5&&~A{enIjKW`RUHG!&Cru*d|7a`1 zIR$^cH&lZl)6jo;5TF2hF&IbFBpRMM>HH^p(-B@vt~kvZ$8#WKdTfiY+k#K4baoW} z*g93L8f$KgZACZ-J#}A?PB8r?p}InBjA{ROG6bjAx@6YqHjD4gSZuHr;he>sEwBPy zPCb^qt$OR~R*2Y?#m1SknVaiJ?NSdXzsTE5QLF=F)Nd=oIitDRj8c%gmLf`bi_J5o zG_MP#3{1}zE5R^5+g5~gO!K;6N^$C5j6gjsHqaE*{BEE!NWDd@1taw)TM^Dlb!jTs z=)GRoQpD-2V)INnb!$)udB681u@Vf^zuSs%j%ivtDZ9>xe@$TiEH=m#%ygDmofG+k z`0k9z?`%c5Cvtf`C=~IHNc0vUMTC7#M7)=~nlMezrQb_%B8$X#XGBi172%x7LR`wu z!+r*p!93dEpfbe3o(!E%@1jI%lh{zxwzEj(d_qlClJQ7WN;X~yIkoj-O&GPu+lp{b z?OLQ3ty$8(8F*>r6{|z7rdJL|!ukrYF%;$@-%?ocs;x>Nr1yb2@L;h}2&+`0v4T?n zz;(4&vwfkC+~Iwwz6^?8Y+7HQ5akGK4%g}jXs-_V$X7n{m5=jA zhTtml5dD=`wNPvXt7?6=BAi#Xqkk~j=OmjQaq2v3> zSUbk(jba@bqu1MtaLy>}g`>tNs{pb2qSz=?Huy$z4e#4NFTNoI@mX6D&Ow}lk5Q1hJN^;rv#t2jlf?TM^EAop!a_ zUIp(ghl6^-+l(oglkFGS-LXNd*(Jnq;VWECGfszG%(w|E(%cVG^JG&7c7-so<*jeN zSR+Prj;#piG}pE_J?)LQfg?d2$QFw5>ZVbw;mY#vTCvf9AxFGRS8te>GKlwOV%M0q z*|qJhQrbKPMv@(-!5bcBT6+UB=YNS;pKR&vmfcq+T#Oabr{6g*otrtab{`?h-+p#w#*U)>T_bVOhL^` zPyUo%49#c63NSREv=!kT&Enlby;+3DWO86?yut+RH)3N=fi1~FSAg0YAD8--SQp0b z=e8o8vpad;$Pf%q`?Hr+*tbMy-YZ>ADW>I`pbsutc3ni7ExtL!F~e4ba~!jxO~hUu z9^J*d+U%9udzW2=z+5ag%(U6e&P5CJzNQ)L=q?g#!04QBE5bP)ecPipir2p)8cz`$ zVoC#-wbt?h`E}wOGUq?hR)llsFKJJ#afVfZv$?SP&~*wuZfQbvyVzV)L`&L}WgLjN z)ol;SIlbG&x-fcAwH4u<-mFa_>{{!&A3wVYaeAHDFjG#mbA?E=-n;Pc7i+-i+-EDo zIi1r}gX{PutXkjmvR97{uOWV)7MpI$?~L>SJbq5m+GO`N#+PG$RY5*6uZb2{6%KqRjVHFff1>EgRHCR1%iIA?N!pndkY%H{Zdo=(nM3h}*A z>>ks$d4Zs9qIo#m!`GF(7OWNP$ZElATM_PSL3>Esx!61$91N2e2WrJ~XV|L4`bso8 zOic(cu$4l!;K^e5nAd_ZI$GcPz6i~0kAi7&v#QLCkE=F#Ex1;!BdZ11*otso3se~A zXt|@ud!p{eh~uqd15G(nwC6~}ao!2tBG!VDy4hBQb5dD5ShQ7utO7*m)ncPe>EK$x z`Mk;8E50EE@p4-c&Oyw@acclC(np%~7AG^(Q`b_2VS1D%OVa`jD*%=e!=*{rTprp=swBr{_!7Ly|EmJgc!&Ckw776ee7JtYJ?Lu-5s4O;DiML57OlQgcnm1h zgya6pZyQ4^?gdQ;mzM4$y+^uyv8?p8F5i@H@Ak$0Aac~-ABG3KHEULQ-o{$>VDxlS zBY15f?=9Q7bLVnxQdc?(BvT#TDyEm+QK9jpQ-W%KuvV`Iu-jp9DXVN-#P?#AZKD#= z)yvCD-P~;Jup6i zr#@%@V9@l64K+rOclYE|`>whbB6?pG8)r&yE-WGkO~2Ss3(5F~6~~aEUF6_oB=vc* z4vf)fZACa|G&i+4=pAf$Fseu`5_T;`lzuNZ&y>Yw zE5bRZjrbM@xa?JrM(R!AJZr60EqMLKatJ3^D`7#cX3&>jf4x@mHtvHhszJ5kh0T2G zz0HJ3B>W3sH8HaxHqsnjuio?^Z}mVW(_lRW%=VSpeq?pj!TM;mpKrn@SFqX#t9f&t zFV>dTlR35`oYxb7PdESvQtKWxVXsiDe)rawHn9po_^;s*UIam0R<&3XJ&&{*vG7`A zf0@`7rcM8Bm<-f=wz6|M3({GTJ#Zj9Hpfqy!y4j6V%-?+^KC^qr=8o}-(SqDIBgw-cl01^bOlj; zir8#Zs;A|`SZ@i+>%Y{I%{>Dac^rVtV6KzBKF&AC&6xbF$F%%ds}L1-@&piumPb6p;p?nhx988hxeg+ z^g6MNP3zJAE{}rPMOdR6oi0)v62N83MYvQ4TQlH8dB|_iV=@+P?-$#^YTA9aBAnN> znR`{3dgw(Ulw>qO(7Tb$5=8gYVzW%?!l84e7xV!TI5K+B^G@Iqu>uUu$81G7N3(c; zJs29o&K|Pw#7()QqH0TN;}s@gzZ4s53T#PkIMUXK%seK|>StnI7`sPpML1`N!M@wi z>5aAavo5s&+PxU@nsvXc$&rc)jvA`xZN5{($j!;i#pz-#7^$hYB8*8{?_@fa!nZ@X z(Sq8l7q_(Jp{e(W2IUFfg<_jc8{5(-pu5r;x8Rwyx3yw*7{%2}MA!XK6TbavY0M(& z_0&M8b6}|Tf+iOboNLA2Fol!LaT;pu(Wy0SW7mlFVRZJ|ib&enZd(z_R!FKNhqM*a z(blcG`-W?saooIJuxm2kOm)d!OHsXfme@n4^#-=o>-zb%NIzCt?i4G*D$6r$MI@EQ z5vF-6DHlv>HYL#nVU7bkleDJZy%>Rdqu4-GQ1dBSm)iNYr#mp)>edb zQj52=>ag%z*GY|ddtfcNejvqbyuw87^I~I7sV&L%leV2*K(RRjTi{4r#_qFXT^PGh z*@|$^Zf5-2O06y-Ce7d zVPvl3X#bTE%zurmnZa?nq3Hh1?Q_I8Wp1BoE5f%(i0uVIAsaZC1O)eTgjqawdSL)ex$39s`|02jN3Y~CXCw!wj!K!JLQRn(0Ual zVu9F5Q(~v&1h}pjtHE$R$yS7OTr;l-%KhH52AtAa9yc|;ab=buKzE4EG6ggvHwb$9 zs8-yl_;TaZ#kXf*o@Oh;IhYf-s3;uN`RPRTuL#8hVna+(oCG5^444sV!g{mUi0{lO zyvkODa|$z}hrb8We4B%n5cX8)EV2p^kH#8NU*{)wE{p z%^I)MK22O(*4)AlAHhboX4@@liR^%K3#(Z_7wgYz)=z9jIImeJ#etGwu-O{Y8++_o+d++BGzq#e5HrNLW*|-Dg#cCDp)(##Ts z=Q^=jrg-3uwbBdvybiq>nkR}CU}*N+ig1qR|0jVA5Og=pJ_R-W(h%q~J;?iU+o3TAe$(bf#s zUt`T!W4TYP0i*K@TM^FboV~jar+Fa;I_%&IVNdSHS{V=HtKs2LUFFz=9ZGOQ4xUAN zLlRv{EFTfO!Ib6MIZ!sS1G+zD2JN;=%utUk-u^x&){7DTu&oH^gconE4AmeL13awM zcweDSCIULt@d^{ipNWk%<+vmV8?H!OUk$?*!DM{S**z-Og|YjgtqAArX6$KIRWNTA zoiby(mQ{clO@E!M@%hYLowTB$l3iv?Q^ogZTu!hR;hf79+O2~bPW1NE`2}%UD>lNk zt(*|;zfoF5&P%pStrp*x`G2LY2){b8`n{?I_d?j5)Iz zyJAhU{2d5$=(xp* z#CkAdXWNP}CT4wBVg3e;(t=|MIJf52hO4;Bibq0I0qc5{BV1RDZ8XJoN=`*-!MA^) zqYpab%BwoZ#k<5kVl^18T}njPGYJzPlXd!bcmqQxajURA(rm0t4HEeG>7-I=S0Y(*puqe8SMIx6dwy^!R%&?-YfBOONP7ewJ7#YUJ? zI3b5=iz6)}=OwEGFBadI`G3q-gmeGTyt)CgL$OhGxIo*kpIL&4ykBgVDUn&Z7V4#r z0{1}kUaC^p^zWyJBNZft(D(FX*TeZCEq;miXR` z#W!q4IA<}p-AvF8-Jo=-qqlEUea8~!*rBb35IEstqA9sX03;|a!@U8c4L%X zgaDl-Hq5m7%+3XE&3ZMWGsPM(I;Yu+a874YyAdVM=!R*Wvczkr*i=(qi<1VG=-Lb1 zHnA!U+!eMWoP#@IV-kv7AEjyE5R|&u3{xm4b_NdNAC*4 zM%{>9F1|Y>vdLD2b0Tx_JRc9iTEQ~T7xyzG+_ zZxd_8h(2U1!a33D?KP$B_o*4*6Q}QF=3!8^sDSl$Y6xaE|iSPL$CKQXCPp zP^++`$p+;KV@YhXDaNH5#%R4Lj)xiP%peYk)nO0|wj$CHEdp02u`g*al7)yw3ks@e zAtKR&vQ%4$NVK@jHpwJv0m;bwk2$Q#$a9p8d@Up+-xKCraQ?d5ObyBPKCd*ry|(pc zam~qY3uy9qDaaob--}iB2b74zxZN$CV|=atq~~8#7xP)MsfKRlDahCI>F1}!cV~|N zgsq6A6@8RgP4s5BBBWb_(;6@;#uVhZ%eox&!C9Y10}??%lGS8@iaA3dvoVCUtA`D2 z6Zvugr65NPy_JB!LT;Fb+Ou5)L3JpIFRCFIXGX-;!+2k+L%$XyFs(yHJqbFF6~Tva z;)Q(ZCoaU~B#?d?BJGh2ecgpH1yC+j+sTy+p`hkM_O$zj*eX^xe`+hjVclF-x_>hC zfamTFgL-}tmw~Z%s`V{3e^Y5vqXUE9ZWxb3Y%9z^sdp#x%c-i&d82ynd>tM?%WoUI zWo%jLUexB;CzpdtUm+MP-3Py3H%28D=UK~JQq@3xi1WqOIGespW$}!5w4W4EY$KVx5Mge zs~+yGK@@>;-JWUdyyRWeG+Pl4>o!%J6E25HpdQt4z1C{q5Us6ZGfZinm>U2+ zpszw?{L!~Xd}G$VY_t{O9KoDDK^0~ZYQelKjc$bqOhs&*DVVuANQN3|=l5h(66?Si z4cLls&S>`jVj~X&5ty)U461ny56&W(bSXoGULZEjl+c{qaIBjT$=5-*E@4TYCsu(0 zdXB9K=YSSo4Q%KXa!0Hx50Yipi#O>VTkoQT>+NDgO>r%PC2-I*+H=y5s^v$TvZv2m z#hNf`Z?+ZToZ6C2P<2}{KFvVKLj;Xmn%I3!Y_2IgFIQ;m%K$2U8NM%zm0|e4U@O8o zzE!)_{7Oy8;FwG_n?RUBdR7Me#$c_sqPIkg>k08+#4a&KygEk{9yLRPvuBA-7;R0P zX~K786NCOov3d;p|JaIf4*d)`6x~;>s>!y>jI4VFg0iW}qfXlNBEoy>nJ!869tP^9pz*dBFrf2R}DK{bUDh&1@#4m2}gkPZYL*`Aj*Aov@ zrxOMkUqw_mi_JG}w96orGo}nZNGIT9{ju>z`umao4C@B5QVi>*wj!Kkoksohjjf>C z%vk&4UlXXJ*dS9-)1%(CLnB6{Uwn5)ByTIiA(3UJ^g7N_TW(mTui>b_WUb%aZEH|_ z{id`69w=(<<;tg@GIP zgfVpM@K4j$dku)v3>*2vn*#jQnewlRSVL@)DY5A}2otF^@?(t{k|FWk8Ip<;(RI_y zgy)?;8k>;rTly3Eb4+ZJsXvd&VLj)4*$c#XWIlYJt%#&rKgU)?vNw%LO6En8A&C~_ z?5eSDTqkY_8pS*w%B{6hVRQAbs1kfc>aolGh`24v%fbekB55EF=$%c?|lFdi4% zz#Bs?2+#`Gq*~|1izmq67rWXN@>RLv5FT=20rwU~9#QW}B9Hj7M_@1u9>L{T@Q5lA zovR0rK!iQ?h|2z%(QABHtUaqJ-?9~vwAXJ?U7P4#aHm6!f_J#>+ElE9C)Bj35#lhR ztTw;tow(sO#Qyk)T+Lw4K=z<}n>*=_6PZYNwd;(x{K;aK7|^3^MK}j~Mha*%s1JnW z5jDMtkoscdO`G$XX{3?%<1;-=tP^8;rmYC)Oc$o(U^EBowbsC(2d7?BgV)|giQiRX zLrwWDVzDkFO?{O_Q9TFjQuej)C-WK7m^Sa8y=)2hb?D% zhuX6wF>8son(#mgzbrqhF@&>k)8}$U91R0RDFa_+0D{HMZZGtBAO8%os;pw%YAeEd#h6K(Gxp*1 zM;*xBS0B-FXOqgfWA85x32 zGcafE);d#@RrAXT;%CJUFon20hKLs6EVWyk%XmZZDX~_J>?dqRq{&*0ijsj9g+;Is zk!bN6+e6i;1;o41)wv=i-vKu_+G5?9ic=V#`$zQ+{O8NFV4TF z)_;cB)a=&J+{&Y2oX`93ocQj{(Vne{q?yC++-`lIlyUZ--UYi1|E7O)uh;pG=!#I(F%@^KKScmy1 zMwGb{-qO~pE4+=`*)VT+))~eLluLEsAH*&+tpi(OV_W0{NbX9{S5*~gf&)JA+dlA1 z$_MF9$X$;-K3}Xgt2?8%BAnNqX_tppwfkaA7~o#rRQJojCX(+E8)QmydTxL;^7~_r zSZjWp`0k9zL$)HE6Pa~IZP+W+ykUsc3F)ninBn?Ty^qZcgAS#t_85!^L&I z@rkb{vRlONFl~-2afA}tU+7FuJlR2=(FgAy^&y8Z;812h!ML4H@(vIK&y*uSo ziqv;Rsw6hWl+;u>#Du!Qi_YxH#DMtL3`D_JgmVzncGqFUb`-RRv*2G7j^~LDGQ}|+ z-dre+)LW`-BF_=uoe{aqR)ljRb5%xQ2<`zdF5LF6((q378`2{ zZHdZ#uC(nKVPM#wNZZKq$(q&|#JVtcpR*O=oZam8=>?H}Y+b0Ao3=g(s--QI(wZW!gQ#O* zpgx>wNA+2Md8t?@M)hJ_5zeWec1^L-f}rC!#{)&|F4K$3`uN1`65`n}Hr$lwX}N=m z=IsGxs)OY)^J0Y<%%|9ja1L`xHcUJlu%iZnVReqzr8RM}Cz)p1e4VWb=O}0GuEYLA>{8*Juou9_GuS_?x4!Hm1nb|$hMB^e4O4K^3{Noo0VG&J z%~(VGH?anc&ZlifIH$90eR-f(hc~K~hDw#NH>5qits(ubYpS)GUq%#vCw71-#pSu6 zZGp-g055T{w!vE*{het>yZdjkR*dW~ZACaIdpbVqHm={Z4}us(h!tUd=&CnF!)u7? zDQ|Z***Jr;g9dN}r>(nUs}EawQ=KbTi2JuAfifKk}cyL5}SCi3M-XOj` z!}4TX5zeuk4l%MJatE!&;IuDFS_$KC?{Wx+;%%)K!cin8Y z2j=|Oif_xD|7u$i&YizBX-(LG4hHpNt<`8Zq+&ijc{90yaD7&6v?;D!M?1o%6KUOU zLP~4K@l#@b7{^c8ig39VGTM^D_uM*H!p>0#?wk@tF;&a~NY9g^pKs+*uF`p^cjxnERE5bSRrRzP& z#Ly_>L7hA-`A5T^z4_t+cnP2~1nSRElM9IIIcG>*t}?9ykIzMMe20{+)VSfDB-)BWI`A~VN^%?7I_@j3 zr-@Z%731%1ML4e*^E2A`7KqqcOT|a)QI3GVMr@)f&{I+mVAY8GNyo_3$!45aiPd1R zUYQ}{g-1_1ViNubnRmxepzEC4v}Cur!Jqv;UvJl-^}b^>H9 z{(M|~cZTL8wj!JpnY9HrU61e$*`9%Ld`zlxD2q z{6wq)qw^zM5zgr>gw2MO93JzzVsHfY_ICw__)E2&-bIPljCZ=4Y%GNLiM57$JfWr- z1VL$v`wugk)X8E+7_<{@ML36c666UD3J{#I84RQsds5#Kmh;7?m^PxRm;eOrd)FYt~4cgt14ZBaAFlV}(k4BY1TMQ($u;Y=YeCzh1guv3Tx@)_!Wu{o?F z?z0u)ydo}v&~BIv1~aB$C!VgCdLP#7na&LgylZ58KziHP;V*^Dm^%XSBUS+2)xWzgmVHX?ZbsS z*hZCy7-y-0PwG3O@G-F|rWB^;nxqSiM^Tr^i^)vx!{S>r5dUf`!a0aJdz;YJV^DHf zmw_;`uyLwbZ=_y+bSp$?9u*sBie_#OGIc2J{75^Wv}25ZDAs{7`Y&4%&Kc#RH8bk5 zyv?*K3S0DX(F|sI&7fG;pEyQW5WT7Iay5m>#p_?x!?jmJQEiO&t<+{DPY~ND?ICuMrJ0RL2WHQNU2>Mq9;N@aNOaYvfgQ)v3 zH|<8@pTu`&6kcL0!a0QvQ78t;W>@zx`Ub3QG#eOd9Nv`<2372()bhr5NZeIc%Z%{I zX$Qu^WfFbBFcAWY_=m(!GbO$u4*Gyr`(QOLOpw)nJ~CQ8vdU<*TCs$s3N6$ae|CL9 ztS+l2@3R%*yqZjnB9y|LR2HFhH2o#v`+?XPQ+y}q>hQFJWv5sh)^UDMd~e3$+qNQ{ zvzV(zi}l(kRrGe)wG`2r@@`jy^?5p-}!72zDyB^suN+IbQ{Sau53 zSX0|lqLpF~_AlT_eq)mRU59yyvIzM(Vpo|q$j9r*8)}OR+DZW#m96pmu3xLFt`$-& z=EJ($y1*;O*wL2LzG1o;{9S*nO2BPatwC7sRm3@TQ(YL@;c<=u$v0@DI zH*7^XM|=(gnGSQKaIY@}>T#`8mR?MtC%?zlJnWo|#vQM{=i%uUHSnMisAnBVeUw-= zhI*2%2Y?7a>MF#fF(Onw^AkhTs~&t4n*@Cf0z_xx!Y2b2=-42(>3=J+!BF zZAdF%qT7H-nO#<@WS0`ny4Vq>G|%qQ;$W5wcJx}&s)_YtjLWtnoHL$F822{AA+_N+ zyAgIRMdV&2HqVsYJW37YH&8!ZwC~;&?-47(Fx_n{!a1htF_(CMM`~A8#`lEgJz|qg z(agX`r8bAdKAF8S>gcK@9Mv=Y97<2tM8<2?FUOCJ}gkL)Uj_GPB9 z8$G@r_J{Ql7MI7UR{v6bOR83*)AP7an{VC#i?zW3yb&FYB>v1+;_>BTqj>|&vMQ0J zN0p?mIF^;320mDR+t@8*%S!i7o-}E2Y3V-r0FT|??Th>2`_Z#;OL0)oW9m?qXDxnl z8%CTU+}t3nav?1ZmF!A#@VxixQ3I=Uj)kuT22^lS0E*tQ+;E&@)7KxbB7BNGKIE*!CxVn-OZ zy3r+S<1y&#gTC z)l}XO-X}JQRmNA?if~>T&)Q9u5H@)>VBbsZM^zu%jimLRAm4qTLg5z8@3o#rS^MR)llDORsK({jG8p@*&3a3mk}-Mj*+JYJF6!599blTM^DVE?=)V#+Buu z57LpUESK~EDMS6|`CuE0=1DKG*<>OUVY+R@*i(xKqVyF}Nq#if|5h zDGo-5YppU(DdF^69VXR129zcj5YDw?qfHy>QZ*=4TC2xwq;>Cs-DKDI|WqIRv=MpJ61U}V>-k2*$gN)jDeqq|0| z2BWoCi8zdlGu!qL7W0r~y*<6hrAFM+TdZP;G4)a%7HxuRScZ)QLG@tJSm8m)k9@6O zSOEj?A{?NAQx@Q*dTJ0op^}O7&0+_ea=rqV0l*KqkqjrcunZ9S0b-H0{h$s~z~Kql z=L>G|A=n6d0fxjyI8XtHF3<^lyfiFUn$?P?t%#%z-$)f}qF2dR?8h`8Fc*tPNv$CW z+y=ivnh9^H96%JGu$hNYlQ=v{)eqUFQ~_Qtc7$mKSdqgeAh1L&yp~5GsRUX=dw!KA zK3D?bC(#lP`Jcp!F~~2m72zE6SqK>torOVT1Si%(9>O{kc3Ki`Pry@%B^MIl4~d;% z3ivDq7($(*6&TNjtWe0wiuPof2V`k|rB*99+N<_Z z?JtFBKoF}D&NozR%@AIE9)JhI<;CU|t-cki2Z&>TV`?4sHS`JIU;qO%$a!6>R6>YN z504D&58!`&cKpAi0#&&mh{2dvxf`R0O53xv{(_!`hX=i10MEh_Val-(iM%=3>Qi+y z4o=>7D|Apkx)rvyw%w}wCiH4l?UGsE_r%t*n)_{A5zcFFVQary>;q>)7Dh-p)oem7 zQ?)Uk8mSNv@O(-w&S>+&6`p$dLp_aK01CuaM6CCEO+7rfq?$S9UtG;C^SNTbnuTCB z1kd^8IaT3eRB@I34}3#Cz0+i{)Mn%Bi+#rCkec(knu=XG)GdWfn-N`)HD0>};{ltmZ7U6_Ktv$tIZbcLk6Z zqbKyW%H^5-n)IhlL2#qSaR_9^P#| zo8krh^YATY`aRGJcxemYZ6sk5efYR1hLz+(t2rV=I)?5NO=mQcNL!Q_0h}{ zgyBVEy9_am&dLp;UMfRf{0`+j{-C=@tN>$kH#xT1Wlz+^?{_` zte3+JQ=IQXWa5#V>6L#YEca{Ge^hcI@p-4%J*Irl&J`jn)KEqRkw+`ke2=V9>pRMd z$mdCudRVL%!}btef2 zk)EbMzU4x_VVzFB$mC7%t73&1%P$d#!`B3l-3?o(ykNObq5W6#^q<9s znR@zI=-e<5CwJx_#P?**{GF|cq+$Fw@#xktY&W=(fBQ1M4u2)Dd+(o^sTg~*k49ea z<6d7Rz9;kgDYhaGlh^Z^UWdPu*EfmP7uNNR1(WsSdor&--d4n6@_HfD>+o0d`k+{S zq1Ow%u7~1#GOzd9ia1PO4>P?Ee*`0miV5`>v!6UNPFFK21(ANN415B zLu8XvB>N3l@sSEo7DFCoMtP;b0x^`{!P>QJN_Hiv8V1F6^Gha`#o z^gb~y(@J)6u0eMCk)5yl;@tm5rusrZJhy)3a6;oRkOReQ-V_jdMrdUY*D?PIIhJkuU- zF13$5JZB8URm3Knk~@{i z!5d1AoC?JlsmwaJl2{wYaKKiCbB5HpjWdyWfmnT09@x39=AGN~#5ZIve~zt)w974~ z0Lj}h8ZlakNVFJd7Gb+awRCH>S+5mf(H3^c;*xx|Re=*vd6+9iE1;>lg2@Hcd_O35 zy=isH<%%6z;}U#Z>v-KZ<5lnb#rm+?^j=#L&N;5#qW08!u%*-saic}OR)r`s5T_7M z4%K1*KtF6k!Avu14;G-sv#2SwmNJO;_r?Sg9C z#(MDYidAG4;9IsLoL7KT_tyHG!?@c64>4B55cb5uR%KIKcak5w)2Jt9c5ow4P9eVOip!cvAA`&g=9l3>wXop0p*A9uU z=l!i;y;t^Aypt$>q?Q*!y$(+2^MhETP?;gqBy?^VNncg%4N>^rICG@usXy;+RVo2> zbQ|IQT|>{bP}UR&UTNg zagj^}@zX(TM)}v&dE~{G8#;S*dJgx_t7iggnuf#vhX!eRFb;3D%$~EJN3>TV@c?n(e_`-5qF8LFvY+U@+98BLwr-_ z{ioZCxD75O(;c~8&$^@eUjK@;cu;JJDS+&RJPCyd#CK*CUSli5IfaSHpQEvx2!TZW zb7H5N5}&|?JV`bAj96V(O+INW!g)1G=iJedr@th8zY!Z_imzKjo`l7(#P?<_er_wm zIg75Tb~GqmOA(!UAJpe06E=n$9XBCQf@!u`35IEgtqA9s4l#+22J;YQ5%P=0t}<_9d|MIDD~2$sj#d$b*An=rh+Sa{-Yy|e!udL}W{mR_ZACceJi!Th zZWkMBO3@@CPr~dru^x=sQ*A{!XJ(sAM{A_ELa4RAPV5|0&WD(gC#eGWi&bP*;67Us z&a1#7CehJq!Xe6{3h`;Nt4u4z#3bZN>ct~sO**D~b6p#cnWV zZk3QHLHskZVhr)4wj!J(mgdyaC`&IU(6c_|Y93~pkS9SsU91{IJ=Io(bJRW4>}Xtj zmL!N5ip?}_ttJV15@Kt`dN5+EZACaImYr=!LzP{G7(H2Rm?@*)33(Da*NQb@bgr=# z;hc^vtByuZb}7-kRqO~;nl=e}62`ZP^0YrC4AaYPML5Tlk#I)?l<_^G`GnXcQ#3si@+43`D!x5~@*!Ih&Y^6(ydD&aVYS&# z^}CMJlto#%AUH^W#wlZ%C%4+yGnClpEUFUtx22`^xA$zFXnPV!c@n`hl$o=QU_K#t6`p!Uh9D zv3jbPt~+}D5L`#}r+wJflw`Sz7oaDERW@J}HH|xGdy-fy#&(LW23)`J>yo+uHWVRTn)gdZi>hxLfqD1To zVna=dEzIa?6GbDBClBAN#fmU!du&BGhqgQeT9i;*r4mT;t?TVga2?_Nd$9{laW2om z8RgPeS<33+Korc4H^>pOR*daITM_>&Y&Vtzh{WFyXE4;6j0pAkY`a`XY+osM!J)8C zrOu8}bGH91){3$HM_Uoj*)Dy;<*Jum2am&MJ%m{FtRd@AO)ems9}ydEN^@!MrU8ht z+kj}sq;xWHRey$f103TA#p*DO@3$4<9OKDJ{|aI18~VQTQT8nX`jOZiQ$W*lNoNW1 z;z6Itm&w!c`{J839N)DS;T*>)PoVmVK^F1oJY){YLoCHj5LQlaO}z>dq!T~lYO1iH z-HIRu8)%7v{Xt6~!^Ux5$BXq~ye8X zC&wb4SR?Yqw`Wk!vK8SRijS!`FNG5{5H7f0AGy@qS@R%9BdpfoqZ*ElLDOodQ9V^} zSHf!v=0342Okti)X*MB?iZTUaPW#FdHN%6$WYGK|^+q?!SBdpvly};Sa8CJpm0%S( zVm}F?XAeL&)g~O4se0=nU=R#2F=!B+{|(FK;s7RrRtKrlk!#f-RVp1Q1BsH$-kuOn zTBTzMxxN|IqnpIeHmyfDP(6aWg8emm3sPk&Z}}KriM$2%De;y%v{<2hkL|2>>W?a^ zPvk8)no8bcJxoh%3#)r|TM^Fd-r1MeFf>(PkUxN@%CQFag#*Q^iUSLWk?{`=7!$+7 zOkM9^L|0O+c$wG@rnO>4ZUF6o3{Ck1c+MQ_M%#`!BVOAMhWMpo#Teoj*@|$Ec>YdE zjL@ig7-N12f{#Iht*QzmkUCc0qa5M;SFwqv_)f`T3W7$>S2{uvstz3)tbY-!!C<|| zR)lj{-aeH&pq)7-kICXO&nQ0UM<6+{-U!DpPU!wiY_KW1Q*%+E|2Qd0q%l3umBx(V zcf{H-g8ykN!Z|^IZxa@TpaNrT4iz}N0qF3se{HB)tQ2pia)zx4=S0@V*}OeS@eN_EqD)rUg$8xZMnB*M#Y&Xdw>@vtdsIsq z#CEsXHKuIO&&9ROk8PuNnAql{Z8X;DF_YRMR*_YJD{VzMuK-JShxNt~MAgAG+!@(D zbkyUPCa6uZxu#IP+)$#g4@*$vx8EDZ$}oIYTM^Fj&5wK3c01k^Hek$?AJoD1C`ZU% zA~w+!*(t1#g^6RNW8~>%f%k=CH5jaauodAP))_F)feAPCsVaX2L$^Ch%%BZ$OfMpg z?-Ltuit$Vw*(mKPi$uEN#o@{L1N7Zuofy-1*ott@bm7K9c&7yGOWuwegzZwJ*7aTX z9rP?p{Jt$V)Rf<%TwZDF2Yv-LRnNj68xOuI)`U^}4_gt=smg73Y+7HU2 z1q%0I%7O?>LUyZID@JyUtqA92r@%NhfGEn)1?wZ#&M%10kk|-QIw!!6gSHmT{}u6l zng2_+BAokw-7Z-0uR|nj3@8Zm`>J{ddW}5nh41#d3~~i~R~L8bybeVW@f{O8$&~N9 z93@tbti<^uK2iP1O4SV6I5uedtzwN2V_zUvlU0Z3*@|#p9Tu-I6pFYh4_08?b)p|$ zmqX_YZ?bgc;}s^X?-CnpigigYXlon2|5mFwZEaaoe!Ex~#_p}QBAm0Ek1xZ&d+ST- zZFqmH*@95Hm?SurhI=lSJ2Rsc@%o0?KvQ0G=>;^se%cgD*;a&e zPG|0eC%#%rP0##ct2)N84x6e8>W$6#Dxx^)5 zEw&ZmoYIVhP}KNRQ--Vp#O4aIQKtRk%$y0A&EoqrE*oq`IOlTqUU=u^HQ*(08J1(3 z#pwN0oCz!szxUT6O!lUoJ5#_!R}#sx*bSy6A$SYe;dk1h2A3Un_-Kb;s8%zYUQw(V zL)>pG!a3r(Nz;ovM{n7N9jVNYT}u(VyT#_2qMMV^2>reaAOAmBtOA4dY+Dh|Av1tu>^NLo!PcoQK6`nZlWsgUMQ?7eK*uZJ<}=*JP#SEn)>2nm5^s zaE`{?hZ_pxEZ&&z1a}zj0ZLISNS)L8#R=M1#Ri)~gZ)jgm$0pIyqB;J{9=t6!7qum zVFdr(R)lkcCm_MtbnWGy_6>3Qv)Bw%E+;B3u^tS;AH+9i2!3ZP!a0ItF0TdU)CeN_ z8@b*4gsXYeWY}nn_ht@XB)%nc_$js`oI8BRm9V?GsrJs+i+wFzTGIQetOA5$lh`QJ z7BDkcLao$p*|t`U%X;zs8JEY~ig3>5^qus!%-alESs|WDV}*L0;Q5Dv5wE{R`(>kf%4oJe=St!%3jb zZc*=GF&x%=#_2xjn9jBMe5Xglp|oj7n^7b?37$zq+`4i+df~%A6&l`tHEIX+E#>fSabG-#VVw~ z%&SLv7gF5{5vGNYxEiz1g^d9n+Vx;GU#tUTG{;tib4Jtm)q`rIANC2vTj}+Nl<_^0 zxlC-5X#<*(YeqWtfO3iW_6*88TM^Eo%vxW7XHo-}%i&#pHka%ogr*=i%oNRRcrD-7 ztOuPytO28Qy{!o6bWYmT>WU@x9r3tJY>Fw5sks8^(gVaD;#)HiPq!7}9K^y+aH3F6 z^5HCK^x~mQbLm}_Fg++X)D+XA93I|{G&L9%JRsJDQG1Q82nuFb%L67G18S$+dh)>#za1P=OT(jOd2r0J1>Hxfj-4f(+k)ij%+Vmnq_ZzYC zrs!a+3PvVsYw!0f?F|~&uf#erra!k8;hgEh%{M`2VF-rPR}RPP5_=XUe)B%*YWTe< z7bcn-P@65*gi)JeE5bRo1$%K%u8Pw#PV?(ol9*jAHq*4tEzGH1wMtI|WEY7QVaU$6 z72zD&ysKJ4wb`nS)5y9PBUn!n8)yn^e(pxn(16r+Vl5b{C)$c|PU>;pNF~988xZQJ z0b@wmA`hn(;A|~^753FrLHQ0z67jxW>?Tv*7kB0Dw~qieAQTYTiJRofPW(#Q8SzY3 z5pNSK%BsXuZACb*5{u(1p)CP*8Iz7zn83bHY^*8RC2g>pwmn9z_ltF5?C!G_;hf#< zm|X$F)^|bHr3{h!wAeILQghm*P`4g{9ucd+0Da6>gmXZ1_tsQwzTOk^uB8alFU97W zLYfErI8i@?$Kub#N-#{1+KO<7>4o=PHA($<-B{`V$&)6Ho{ZB#h}zx6aGHhmu6Fh< z@tO50R}+Ji)x-|&TM|`y1SGKFo*J!$5P>~Hsd^DZEVOuNKm(`Zlwj!L@mR%b#Z_#kEF$n87 z5UCQY2(0I*>eCzyss|bv?}h#F7d&o{G4$F&AhoTF6E2-< z(38dPG_66qbA8|spZtM`?6KN_KU7^Ie_%XC^oI}DQve3?hadTaBJ{QW5!HocTzsuq zc~+gSu@#Z7PGRXm=)i9oTUNU2_(_wX2iZ#>SJTIS`nXnokQSpS^tE8QuX#fm)}zM= z$Ho7OUAbIVDN*MlB_a^3Q@T~TqV$`iCrv6fLC@v4jiEXBf?0!0OZUMCST)k+i)E#! zb@`@rd$%vt6Ys3`LvSh`=6e_u#9JRl@KcSZ=i+B64`Rt_FG?{C;TuqOfIf=!aezK5 z>La@jqvfMhAinxwtzLyd2V;Xvqx$j;xQgy|kN94Zh^Mwi+)aM&=Hg{teQfLE6Sr2I z^;)5&LaOR-l=ZL3#J7u0G<4_aNjcaJnrOnD`&RLtnRDN4E8?a$p9hIgx0-HCVS2nd zrXBiEN0IS8@%Wn9BvT$Uc*wr^nVr=5FN<%_pnSnrgmWkhAuv%rys=em6r0gmI1JD{ zP_MPB1)WdtqJ-)%Vna<)Ey7SmiKgly+My|HN`Dkl3L7dytIM868pq#?5dve;A?;k;Xo0%n&XX zYr_yOP$IfM%_sg*BMc9$jc|q660!|qCz-Z5%h19}$9bt(HOB8^TM|l*0|C(_1iw!cx)jhOuLL@J~J0tQGTM=m@$ryk9UMA9_(H^2uyS5OKXfe(x$GU5t zy$2ts7!ZD6m>;ax%C!MFWv)L;yOg0S@*=T^O{>Tp*kww(`OQw$JRclz!Th;>$l5JIp@1=GrOjJAyL$=~l38*A$C8Mz^)6XZH+>%@Hhu=w`O*Ke^E zk+g<45w3~uCFfq<2>V-QFJeT|o1-j$WW1F=+q+|@o?itHmFNqh0#_!}uC&M@pMucN( z1!nYE92{a*xo&LP&e7u<`N6QzDu-itj=^uu5RwI96UX0UlFqis;kCv(x-GM zeQH$Xq#Zvz>apjg<6!UJ5QLsvMb#_%ZMF8>dD?Gl)NeDRlAS>}wPI`Gx2!6;6&<|| z|Ji~6?81Mp!hiO{KfP+`cXa1}=l_uN&(}P6K^M;*KrdCs@zPIpFa6~Ike4o0UYY`3 z947q2aHiQc><;wPGsp4MZ*@QY_WzKdE>eCvK5p3O>c3J$Z+}ZIz5OdT^{iI=3iRo{ z_|L2GpZoEj*TO$N8f@vfBXCi@W(9fv?)c&ae{hTU*T|z8@eohsjwm}l;=Trfz6jY$&=QUJ2^ulYXj;O-X}b zYp4MIoGL(%3@Xt1bBC|ibhu?rhX>YV8L0l4RWUz+HSvS^&xi4!kK#Wc$A2Ede?Eo( zd2|{Y6yoABzL3h-4b^T-)_^)S}hb8a)~29yh?~`-XU`fUj#WK4#LSZL>?4;K$<9MAGN+Eu1E%oEaX{7=DxU@8gAJa=k{FqrP;m2+@3)?oOH98f&+z9hD&1v8} z@zKs%1^hm^blVYkjFq1MIJoeLZAaWWR(ebH%b((3j)Gsji|LAO zN5e0h<6n+}UrO;Wli`==$G;p4zdRiOa@;e=TBGrNhO{^mw3vB5$UIVMaUuP9Bq($p z{dg4o__XLprQ1XF%hB-nFVT<3z>j~VA1A|)3olUOCS&Q=Xfjct8y*EWd?!@LZAYma zev^L08~!c&QQhS(J!cE zlYT@cUrIk73qQV}emo9-{2u*yJp6dviAu&4_|c~yPk z;|J--lke;>eKpnqAbvEM{@J-8_Go4Lf76d>`n-ASuV~;U^ds8TM?a$G&!itw^9Sii z)co`GBWnIT`Vlo>FkcBn%`c-LQS*>~M9rT~KcePurXNA`gw%PFy2pUJ$DIPQj#29R z^dqXfhkitLo6(QT@AuO$sQV}BN7Vfn^dss%Yk?Anx?e;;qV7+MepE7UjekM#|F5`f z53Zs*eAJFXf>^`DY6Z2`_2%A9a@X7k_W_9oMJTetb+CFx zWTp?sqNCL+zM!Q@N2V(3sBP7Xpr|uw#}}y8iYV>x_nouZyVu}fl4d6N`@Y?C&VG-x z-=6)Qv%70ufnEO@S76uQ?F#JrjiaR5@^*B6&yE&tM=9*+V+r&~9PQVNr5#%oOFRCh zSgIa4O3Fg@tTX8Cs)}YAnk_vMMa!hwaf)TLGc+sqT&n~g<4(o$7*8vf?)gx$bWiqFHIfR04gqOtZ56K3AZxURMHpK+!m9hdtl~#j*!XS1fzLT*a~ntW+%f?gq_D z+aD>x*O4b`kCwyqPI{?aOt&>F_3n2C>hy*Z=#=84r9AyGRs^5wJ){I4`z6gvp}nraLMM%pMyb_w z%}SxUuE0VoU4eabqbsm)exL+eQhkiHB)QN!%@tTZq6EhJ2F>yqp24SUgNMW5_gP}N z7+l*dEDfHhSQ

v!bT01loA7W@YZ zrYnKg%~dQ7TB%rSx>2#z^mWZjlSRi%D`jHl39i5(wj#bvX0>&!V4p*pv5U7#X=*$UG516Ti&1!~0Ak13W8-L6>LHmqI>(6-|gOWUStRy^LT z1UV}eOG7tnR*LLV0QSj#7^yT(v8)u;ELFOs0m=omH_J?uCvnQjljs;v;!KMt(N&(*?vpr6;O*md zfhTd^z>_$E;7N3_ClNOHB)Z&_miZ(G!P`g3)02pOdeT~-bhl4p#JrNkr#y*3l_&kx zCq3nph+%mppY=&ZwY+_Vw>*hBmnRYM@+2Z(ofD*h{H?l|I>RH0 z7~ahg!K!oiVds#rkjhjdkulPJv5rI!t_39kuS+jh(!dNa=PzeERq1F4CKJ0Rci=UE zz-3+eT(c)JA96_)6Q&t3l@T+HuPw-j2O*Y45@A_guBSttnrQkWGrvr~Q(@p+;5`vc z2V?rz2^gVxB0k02lI?KH5*-%4A}vX%4qCPkQz@M<4>2=hN*SVS=0%*5>D|>Zpk{u;bc-OEPMfQ-UuAdx)z+@A=YASnrSWJuTvq$&q~co z!s2Q?G=&#oWXucs{lGM~RJmIwr@A0pOQq@!@~h^Emx1rMZ2V#+|8gPO4(lO!KF^vG z#Lw)_H)UYfoaPYl41`b^2%#_#LSZ0;!axXxfe;Dl z41{_83SJhAEOv;omV{>AiY-C0 zB__6n#FmKI5)fPBVM{n{iH0q~uq76@gu<3c*b)d^;$TY{Y>9#`L9itTwuGQxB4A4Z zZ1KM>?zhGJwm9Dw-}j5_ZSj1+IKE%}Zj0M(@wzQex5ekSxZD+j>o$KCrhqg{OwRV0hcp8M!JumB8k^I5VHX zH&7O0)TM$}+7s$9@qTnvb;`R;yvvy9ko6Jvb~ihLbh0}d?;YQh2#2uR#HlmnorE}h z(F{JA-P?ziE@Q3TDDBi3J)vv*40%ByPjBpTN>zRI4K!_HJ$BA1`H>tUle<1=eTsV4 zzxneSe?G_0GE5zGEX!e4N+P0kf#!IC(3SA)(Z?t@wxF(4HA6bzm;<-IKd<#t{RMRE z&==)#ra_ymyjVWvKIXzumzf((-x5@I_4O%PsIt?bmwfq@#__rFVurwM&FG=T|N`1!Q zo%`tQwdY~k6)*3X#G`ZDqT!5M7`7sZOLnA3t;w?55kx1@mY5&!NrWP-kygc=`a~+) z#T811G;d^6QAQCZg&w$q@BMiN;z9*y(;Cs<@w zolU|-(_rgXs22rmG;3f0mBvha&Kg$)*Hz;Uexg^pFP=d`>o#1VoXTvf$KX1-7z%dJ zc53iwGBQdRMo)aAkK>LycT>72+hy?W``B2~or(1reEA&UWH!{$i7{Y20Zk;esgDF= z%s*Nth~Q)sfgG4mI_jbhfiI+6zlC#O+?yz4~US0Yw;fgfwl;k4CyoI1@3F zM$NFO<@OOZ_+g4KiDjaAlyTbRZF8!hNbdT9QTC==r^SEPIJEiJ7$vNjx zzTO($Eu9UAO^it+XurZtr4lIv>$r2ySjorCV;6kKh(aEfuD#tYgtI6Xw)XQTfZW&NB| z>*PmAG#tHQw6y?|wU9s8;-}xb4!_P%4~|-=XuX&zeR^$Qyyl-;uL}=(@zulDw+yLX zr)s^Jx_x@R^VauI)_R?H+se$^D<%!8UK6xlyq5U%+P!f8-EJJKJEk|bWrkF*)3jc^ zxcT(j^K$YUtyg1k{yl#mc~ya4Si;Inp|8^3iM#gcO073ef32~tt)PgV3mM=B}4>8-O~Dm;>Q zfO$}|W&RRi?F)_u^EIp)wsF;oTEj7i|KZUePJXZ;MDPX2j=oBV)bHM+eeucRr#v3` z@BncQeYa*6tnSk$aY*aeEvwHEs%el) z91Hs@Rc=}OxUMvL)djVey?5z1oyU>0uTs?|r{%PIdw;(n8wd_^B#yKFmA1Cc)|I~a zWPRD22lDuLoZ;MsW!lw5K748gZrV|;9Z;NjbIoN>4q^*$3w)KTXD2u5N~O-0A8)#A zQGwU=Npb0S+k4b9P;CisQhZ9)oV-ML>DJQC$>WQ*4q^#!Y5bLbd)8tdmCyEe&V1qi z!b%6xl1bVU-eCEZs_U$8)$ToF>%zL7>xa<2Zp!8Do=>TUADrqc_4>%s7wsK7rCQw4HE+y) zN*(?DzIS!_+NSJ3>h1>zxk~Uh-dE|w)RilBrKxqsjZLY-?0E3bjuv;^OHje5)P$Ex zUe-#Td;1;76fgbDkaffscc4g!!>82QO{q^^r7HHccef>nPN^2%5ec~Xl$!e0x(!;X zDYp)fto&r?PT3ZB7)toZr_}lHJp7_o>iBhIpPclYMFpP1wVm(~D&^m1zxw6EKR=a! zn|;!s9(&}l?X$k^HrocGboe)J>bRvsSAm#6`Be;e4Jpnrcgahy?nd`nM+cExs?Dn$G diff --git a/doc/LectureNotes/_build/.doctrees/exercisesweek34.doctree b/doc/LectureNotes/_build/.doctrees/exercisesweek34.doctree index f3a14d212ab73ef0228389bbde1e34c4d57a9af4..3ec0c40c4f28f53e092958a84e852333857a3471 100644 GIT binary patch delta 140 zcmcb!jA{2WCYA=)sRkQaLRq;DEp?5Ibrg&Yj7%n{uzI*4@uy_4$4=AM-O)o7j zQ9zbzozgg^c8W#@D>m89A6Qqq%Wh<3U~o>&$x)DwHn27}%Js~PHjLF#$jQu0RWRIq I-M7^h02os#n*aa+ delta 173 zcmdnJjOorYCYA=)sev0=LRq=AM-O)o7j zQ9zbzozgg^c8W#@D>m89A6Qqq+g)O0VDQWWXP8XM>+7#SFuOg3P#4HUu@pOV2I zJ0(M~2b)yul*TEwQ#3MIvC3wMWkgMGWYe3>&YH(znduoNFsBf&0pUR0dYBcA4K^3B HUAj2B#L3q~<227AY9&C>R+S8BbPc zu}zo8qhLw~d+d}9!5+M7TBkHlshy&c!HQSeAw6t7O6H{_B^HLQu zixu38GE)*O6_8vvxs25(h=3Y}#1e(v%#^&$^o$aiGYM#!EWjo%Pe9FP7q7~)`NfGh%q-iu85kxD3X4pBb4H$V%VeIja*SIiYoAqTIR=x+I;#kj=s9aD zy%{LfBUqkal#-lZnpdKmo0(Tyl3F|^>nQi+J7+c7LV)sF{*$@SWiW`k( G`Tzj)TvGD@ delta 683 zcmZ2Gm-*HrX4VGQss0x?vbGBI(Ha45mHpQ=p4T+7Wz#K^d zgpH=a0!aacji$g7p`hLviDO~_mOxc)Vu(-;WuqxDLQ()>qbV>(Qh>}hnbKws^Q(y| zk|LxqFu~?U6Z6TPhZGXCT)7z-vfM$0Cy4L{5xyY8A4CL#h+q&A3L?TmL?noa1`)9! zA|6B}f{0`gkqRQxK}05q$etWT#AQM_ZCJ1r_K$I6x$(jL_&1#35CdODgS@D$c84f%(Xf9@G&OF-J4C0ypcinb>(IFF0im6uNQBl;sQ1 zj>(CqM48xlCTpD5WSa`IbHe2C(;19YCm%R%$2ej0|I^)!j6RdQ&ziwpVLbW5Sy?7~ gkU3(L6U6ygq_b=w90xIu$)@MDn5=jvC!X^G02fU5&aq@U(k%J) zv+HZ?EF6wBP3+v3yWdn6QMOd-IwbwT<6@FXp5KgG8An!HhF4XV6fLT?NDrH%8Y~OS z%8Sb^3(DutwahHFRMpHbsw`hzT4E`xwG>$@$`@LyW?71g>&oYsTIQA()l`;O&bHK+ z*4CC+RRTt3iKV7=cKzI<8YnHUtFI}o&9ICuE3Kv2@_lBD)U|a*ooebVMPP*0mR(fA z*p&iH3Xy&`_vuEpSWpV8!L_z(?tCV^y0o}_R(Y|dx~6L8+|mkZo;kDa#KGvAYyQ8q zEm@ix{+#6O--cXlgQFX=rwl8voMWl00>2km)s#?=K!kkGwu~*vpO#csS65xzBQtYR zRefE3#>~>pWI21pMzN-JR%uOXWpU{yX;bp@P1kQqDr?nfxg1L+`7FZbqWXn>9_o**SDoZYl@JvCZ>q=vCm4hq%pzpKayUl6 z=nF>(rr`+5hgM5E78l`Yxj9L)SuMG($OmosWe5_(e2kAt5H?&x4*L6|~Z8l5FYm4iB&1iY0rLL?L+TYpbm9&A)P%0cl z&%Qjms*DJ8S$u0{yNJx z>6z3}{3^>cOIF{iii-Nm@?uuUYb{Bo6-DLH|3Jhls%lD;rM78Z8WJvpWSL)HWa-7V zg;z)bE!1hM7%J11C59OdvRFvKWf8_J7TKGOq(Hv(=N1505XTmThjOWZb${!B?P^bd?qf1bolv>2Fl4*|^P<2gwnI0r2GPR*g z3XMtzmANixmg2=QoiuN2cd5Eth?JKpB2lsxBudqpCj7oH5|DVRV|qa1Hyt@>DqU`7>f(%x31AJED$+7%l(fLv9naQDXFjq@$DBq~!W=$h zYlw++K@m9izW4*qoV5tO1^l6^P7%W9Yd$)zP)R9nBL?(?`%`!Zg*vkQOP%?^a<>Ty zKgiMgPGMwPs4-Fy&-KVc!X+8;PZe=-GeoJj*OOvc2n&B`2sF&ruq7PQfqA`SbmkaZ z?qBhxyZem9i6OL})8NJA7l!+MwNxXI36WOh_rP$W-uW)yh@(No_!JX|6Gz|5$<}Wip3f9B zvBc<38_Bw=9#Y$WmPoC}47t&zW@rWI0Ci>t2(k1xVowMewNl8EX7sn=jUi-th8QLN zqkj^<9nhY&hTWtQZj{Ue+7k|sRN+X9D(HGK` zAzk6`^+U#ET`N-bJW4a8RuICJA!{_DUmOS@YDU0=iJ3Iai2upNNbBKeV+hMY&QuQ+ zQXg#%kuD80qS;_pHz{NIdb6E!Zju})hF9R8t(4@LGa^Yzjz&$sy_MqhFbMFS&fTTLBk4@6+yRZf+lN%IOqf_Ncy@^F(qnLgLy>&2@j2`#%omx zgGZ|p)@u@0s1l^Tqm8J6*}#>{Hgp^_*Ssfyge_xA@Bvjq;@AYmhK-tpJ(`3yV~ywm zCV?ww5<10?DW6?mQ(~EuVHs2pV}DC+#+-~Y_$BS=8{W{iX{pw^G&V1T?%-r|Wx4*| ztT690YmwTo`&I%1l}WqD8KVLfz*2zcLuS95RoEzBg$=}?tG}Bx@0?V;(*_*_&p74m z?36eXrl6J~RWMF~nNgah3T`tza4T8*g-d(;hD>PF1cUQPvm(&)_n;1m6)KaR9pU)yZIz6o`xy<}npZP7~b3WLj`QUfO2O(h`^jDVUw@ftR*{nu~ajo8X z>G;GWqFvA0eyg5!{jW_j;&eTknt-g5esXwZjwPvRKD3`ju$o~RQ(9eDS~0V<#$uPQ zpByO-nH(Jq!5OSDvK9EVpPqI&rcKau_{IwP0D)>*I3*P2N++gvlNzRUh;Z;qj4ZCJ zqAIwg{HdL!7pFwGTpTHdO^t22I2upYlcLa2o3w6fD4s+mr-W_MbYTjl_bsfc^1vM1 zlGVe~ue4aU-)-Sl8c{W024_>9vgF0Eze`7z4gK5FqH!Jbq15(TBc8`hFx|$P0FbRI z(o!gdsO~F*aqnH%-m4o^Uny;y5p`ht^d87}bJ%x{rg2#ZxU{$0UX+S&0~XI(r9X>| zXx#x}W-`L-^t8t?ZPmo2>)A;1hT{F=^Kv>p%hD2E$WbVl4wh$| z?&XT~^5Ew1tRjTpm+hHUX2ehF<$n0~vZ44p1~%=|sJ;Qn_!Mb)xe}^<3Rdqq1F=)adRW8CVp!j*SY750#3N*^ zy&Bd~hIMqV!t3JPNqClwwO_+3W?0Wx81a{S*4J{Tf#GztC*@S#d|-QJJi^Om@<%oD zr#4pKE8b~fb@vVft-F@}|4^NM8x+7`Vw5sDo7fqqV$u)Qx8#Mw0;swoS6Nk8T5Exs znWboMZ53T(ttqXmDKDL`tg*r>D6Gdqk5brgfMr(s+)}CQyndm>hs~_2nv+poGE2H{ z-c7N)sTTeN0Ir)DCv{z8m-g0lljhgV#rqA=&?V7Dwb1BCsgmj<+K@*z^><6Q+E~2X zK+g0*aScuR!xXLHKeK{P8M&rDIJZHUbqZq#)uySU{`2F(K1Z0$n*WqppjsBqm8lCS zZ0dK6^W2G`o{J3iyi7wv6(Z-~#W7Oh_;3^F-rEeUDL^(Usy@#&x~R5zPFazqv@W!0 zuJrxf%KUI9viFbt5o)c1F~fuiQ!t5hr+3TVI1lJ3TTR$-v*h{bj^sUCPt|4 zZRC*5O^~Q;X;iJvWso=vb&8GhYN_5y`xkf9%cC*+vyG|( zOQs&unU!p5JG65z;KJ3ym)=$z5u2b4&`lgP1EA3Cj=au@Qw5mS#`T`q9vYW1r8A3a z>&l@ip)oI;Q`}H7nPNlScaF^c#7th&n>qkjUF~UIn5%qTi&su zaM9SR8rbQfcw>so=ako_52O1zeoH$G7A(l9E-Ic=SM8hK!yZdXeQ{l8MNx5Cd1Yz3 zvIUgB09F9fs~6Q#p6S3dy;kPQ5Hj64E}P40bJ^TkHhV6NkxLs&<@QfqMXFVdsgZ4A ziwQI5R?W_Y?Js*~#axv;YY5BgD&}f2oAb9_Vc>i*BbYC^l>hruI3YnDPE%`Qu+(at zrYyBwZAcn|#zd(_|FM`BrG(SaYtCddF6u+=_LLTyfGVo(jO^%6a&=4E4e_(mz)wvL3qgf*_7i+Xl`(z!ve`MUpk5Lqt&xb>3XdteUC{y2k+fvULlpq)+R^8wM8iWy2B} zkrWjd!;UTtNMN}arXMwynTyn)3ZQYizLsg=$1G<9Z# z=SeyeNIm(7+Uq_}>l`<9Z)}^AB1>W1Gsx-B#VGuWz*he9!uTRZvOiE2+2{`k;cv1w z4|YKW)7zQ`!27RrvJ7?f$Q3^>$g{Gg*WD$2CmZoE%7-p#n@(wLzG9655BY+Q7viO7 zmTbT?(1DTHCn9VRl|{mPmgXqyUhip4bg+N%Mx^K)&%zy@d2;2~h;%fA+lsH&xnUsAsT zFlZWBT3K2Hn}BfcrC(`jHJkyE55J_r05Wu0Lc?seJiP?U)sYb!`&ivBTb9F?t8 zOW~rrGB~k8$G&4rD{HH22F$Hm0FhJ%2HbvDAszk}*3X<G^}x8`uC?=F7&v8sBug7WBUV1ueN$(AdH7&T^Gj(*)TTG(pB+-Y*R;IVPB2lw7(3 z{+DB)0P$?*cg<5Q?e62!?g9U_`&3K2ZED(az}w}t;~@Bt9FGsp^ecO^XlhqVI6K$9T6(!dsBG;tmHh}Oy|x>q(`34kQ@(YOGBQ?mrlLJ4uiIZo%(yxNy=CH^I0Q4W|X7z z=|fKmU&%txL18cS8B?zN^JnX1#^i%TM)U{ZrWu=}mOipU=qRIh zkctk;M=Me^toG8Gw^GA6fGlCl-XbAGCQDPv(loMUM#ceTGP3Ud({9>$B{dAu6$%`3-IfU+M@s~Q#~(4sTR8%FFS_~Nm_ z!W%Nd5rshNbKHntVG??1q&|XUkEaX&lnKr#1Yx~2v`>J}>En)Wkz$`%7?V^C%LFyB zKmcn91162hcG%s?J(Z51p(F)H(H#4`Eb%u*qSX3bBl?A^7?!Ka-Xe{9H#Lm&%1Qvh z_z^Wl~8dvX9mG1AUYSq`H<((>2BrOEGx<}`Nj z8^)(A*`W303<36ae23s=1i3Fye=kG&_~{C zDv1t{I1RvL+S8Q1IA8klvkWQhrJKbkWre-6dqz7{_dE)?FCFmB@InvgOGjS50gf5$ z{M2{!tpJX`B}w-mj#ValV>Q~>O>Ckk_4vt%Uu6oJxYC!I2PDrct6@GY{rt))^kY-D z@vo_D$7^iAli8X$&^I!74&vi}?zNqCw!P*^G{PNP)7iFsVy{4|JeeuYJz|z#INVB6 zeWE6#U2A^k4R>^?#g(^i&1T*l#3%5pH~vY@dGqK++>4W!&)jtEW4)AeEK-p-S(E2# zEsa0+1cnP0#1&-Af;fmz&;!R$%Td{QvZu871HJUdiFvq$iNtUu&2w_3B4(;4W=3o2 z=*d$UE>sLxFijT2L40C*y?qGm+4#;{+^F(?;gc-sn|I90@xW^}{;ONdnGEBUc2dKs z$%~Tq;7>8k_Mm!mlyo9TewR`-^S4Qqyzfx3_WH( zkFI3i<{sC;jvV}x=EX-#YybVC@R&@0fYI-^0sUS^Pd=r;WkCnN`!yB`Z^)QO80HZN zl)fS>wwRa1TJC>bxB&_Ol<{G3bjfB~qTzfZQ*jWVImiDvAp9;9{l$CN z6n{|?+qGpLZPS)bZX(%Ty~gs(6`-gZQY*|H={bWUAgW z)r}fe51ERC$W)IFMh{{r?c!yhH%a}dC%sl&y&vJKg(Lu1J*7s@2X3sDrAvJj<- zOJp4uw}lK!Bx!CGiWju?zPJ$mj?rp@EGQnYZcF}o9U5z1O;P#o6SpEmmY{3#*0${Q zXSnb5=Z(A7PkGzQD6LZFqz*kM|B+kc6r8d za_0)Pm4h*}s&7COz=O0OAkXGQqAzI6_Nly`ZbaP>j%X*Z3&6E_CE5Y^tjD-jb0Ofv zF=2;y{!OT-4m;YhyxgFb+W-Q2$w4yO(Td|8vIh0Xc$iEeX#|610uCY*Jdkt?!nj1n z->l&m$@m-u@M&^!B0%lccNl(iY#gp6J^>DC-Hsf>BhJBR@{vSU_9F=@XdSC99+!=lBah7LnugHXXpm( zx(_WCCpf$VD%S}M5 zccYF}*v{RkH-5Rj+z!1+tw|a3sAdLWSoWZP=GnA_Z^B+`PZsP!-SK%Gy%E1NNNHKc>-;20y_Bw>Q6xnkS*+4EvJ1dmp_TVL*^IEO%i(sBA%zw zO8lBxn~Y_VGp#~nNbWNzN*VILqVapdOi-54QD{VIbnW~F*$DvM_YB&DaVt`K>FxQXhuNN#FtSGE(t=)CvaXkYu7D%nS%1LV%TA{3*jX` zE#VsVD%z{uqb0<)6ms~xwmOl7y$0>o62`*xil$vgI9o*bE_@9=hVY#}MsOYTI(kmI zM|Uzt-XU+GRw|MYNLC+3Hv=N;2w(SOOphCTi{C^&5PrqS7_KiKLu=rk;UD+Ir$@=X z+mEAPk@<8}Kf~a&^*g8s{xaNe@cEX;;B+`icnc+AxU!JJwe~G^T)9W5WoImT8#T1d zzIBHn?AN@5oK4wXcn56`$ZqE;G#IA_VaJE|wCoPfnv8JPao_na8bp>Kgj6-Z2OamQ z4lGqic90IPN+dCdVE8_)gLnUX=+zKBt%GbgTz7noUghuE&~)b~XkRnn+SAC}40zqA z=s+{z>@#RM1=0uC$ni7aXsH7mhrB&kO?4>FIg4U?O`~f1*AlL;8$)9&KhJ=MH`&2_ zz~?Yu|L4#9#936`Os~cNL=Q9rPW}u%(hOMeIU3juc<6KVY%|~!Uj*>Vu5;+gW|&*Q zL@xr6Rm`-*P%(#fkn7VUU!flmzT}GuTwneM9pdjT1J8NX=gHg42~e%e?bQ90R^75l9aPxJCw4eT#gl+ zC|$hPxRvL}Og}!|czZM8C%-~4Ir5?+qYLhtd)IvhB61^SCuCnh^$6eZ(;2SEe@74T z_e@4%iLrtLna;icgiih-Q`ht_%>huH|BV<2Xw2bUNp8gB7tsKO&&WRhL8JKuATSBz zARkgl_jV7!IFy6>v?YTpjMey0UXNBCNq#HQ7N+rp;@-dGBp+JT<~}$9cM5>THyc26 z{vphBQT#Kq%4kK{-cgPzT<2hHr}yBBDDor*=KVUd>ie^%0u*=A;Wa!NbK|EvoDV?e z9}XR4%?QEOVpT_$iWR^Qp1b-@L!CvU7Z@{08xe27Ps$oz)QBIKHRK=%Gz~eZ637{$ zI6*um+xxc6?Jtd6ZUn1(pM>Hf5_%r09z2JWBYrQVf7_7_FP=LOS^RZJ@25t*1K~e> zw!(GPV&g;nJ$OExG`7YYn*hyZLK{31fO0sVQfuA%5-5Z{UTxx_U{%pl<1&QC zk%R9*T^kokrkdfsE!r(>4ZdGy+{(dNhIQiM?@CpzH)7?KbjmJgu zl>qMOsykP%cw%@*JRMem$-^D-IDDV#2Wup@D}F#vtNz;=DK9N^pu1$tImjKF_l@in?0Etp&Y%U=l(0}E2h&ucV#@TLwIN>7Im&@ z5XgqshJ*A6eea7W8x!yN(XzXu$c_XY70>o^lV(qM7-_9 z87NN^k(q;CiW%)RvYt`ox*R+i!*yPXK8lRCV;iidgJw39ADXwwg)=bVQBBB>NQjjy ziX|e4=JRAyPdt;F+1L|1&~=&)-}c05iVkK?hXqk2y%%1H7s$Ljbq3ybGH(vc$2+$- zyikB0O(sQ?^w5#p^qJ@$O-6pM=E@G5jO|fmX)Zp5x67X7O18<8IEYWu`+0adwPI=? z+!wvBNqD0V?xtALQIqgW6bZ@4&)`>N30%obvIGv|lQ5|OZ=n*-7l5CB(j-i-(pEA$ zX%fDV@-FL(LlFL67Qq$$OBTUFWDz?1ltSX{k7LJ`mCr7lyNJD8t^%I*C@oqsdMYCpW-$qw=aE`YN7knMbqMEn2grW3<-fG@8>a z&6U#x1}p~Q3Xd}B%a4*x9P{vKmX;hu_62g2@%?dXM|xJcqNs9_g&pry-9YvXz&WTd zGl}k?lGX!payNKPo36Qb(R9z_b#FsY9+P8pLL=I;pB!V7k8!y4{YP;oj<}bs8wUa1 z=&Cu_ns@KSMpv1G@NjY_7P_WAgYYt3AI(bYaz`X+sd%8to z{YK)FfFy6WNMb33c7_wpcGgxG;%z*T=`(EdpgS%m3w&= zDW3#xU(;C`ZT~t677cyX#E+43u83T4K!Z+onT%`5l0lHsU8mri@PnOMM#ovzjNaAR z`_UBq8$wSp>G-M6AQ64+*G}_2R z6L2Wr)mdJ&C@8{@Vf-!J!HXJ*xdf-;f6J~&(X@f$>r3!V^sTH6+_oyko48vh_+%-J z=rxoLv+!KsZHI4F=c#)k(AYa?gZq-ZDDHb{HjY!==P&&C*?2O?nMu2)46ou~^Z+y& zQQlmuXbB}90h2IFAX-jBy(?d)?k zcqaL2GGyh5TD)02C8NJhZRlF&t9sU&Kvt7ujb%uDskPc+rmr_ zZ=z$eGpk`t_88TbzF&_#_$iK2lCW4K*cU_UZiW&1K3PGo1X$g&2J-lL40&-4jt{vB z@`_CDtIs#ECs;m=A?PTMBV*U%D3Mi?2+w;lWW!DzLpHAkS*NIuDMM<0Qk8p)njAqs zUW-%36S4(6V!Z7d@kAtCl<)sgQzUOilwKJq?4X5gg6BC2Kb5^$&;u5ylRWP>gL!W1 zLeAU*J!P9%s%3n{SAgRA8vf8M@o5_tOSO%~-^CEyQ`j8qQ+Q*(Dp!nE<$@Q!xfNPt zxVBq|8ynKC84icjVYlaGS>U(bn&os_-8TB$;m&fpZ2-4eGo0DZYFriE^* zzkX9A>AW5~ace9oTo3J@JC-c}2=@$6qWY!`;VejqWiJ0^+QR2?T3%Hq9oY8gmG9<}khaZjl+Pa$3qKZu(hwrWgUZ1_m`^xBz4o*wYa)06(`MgOP_bK&l0PagbT4T%Hh6H0 z0C>0dSe(|uXPE=nZQHOXAgfMy;_k>AjMefx zTOhqeN&7O=*nkEo?F^h*+IbgFBDdXz9RZa%eHXqKjSr?o!*=`z*uyfPbJA61{xdu9 zR$Omsxecwc__d+szRW-Qu^QJZi(;GSznS?Y<8GX0XX$?R+0LnXvn61*S6NzWELpZ+ zcMl$q%@6rZ;Z z$qt5x#L;^;)0p-k%rv3{k-hRDzLh6qn%?>lE||Cp+JCAaJUBpH3pFf_#frDm8@d1BXqiJ99qXksqii#uU_9XN|_0@ED9 zH+E%{BRod+1{8-Mzy&_EJbYUqj8g}28Z3csSOhG9An8%O$$Xv9jeNo%dlWnIV_p4* z2mZ1KK8EjARnk9>v+=8e1TKCYe?igCCx_Z{HD#|RXUGXJteAcoBxOGLPZ_2CYQI=@ z(%Jt_%KTT_FHX%r1EFRH14*>`BhWJ=k`}sx#?6PdA$GsT%WT}_F*h9pgIC;Cm za}bA;kq2=is-^BvCwsF(T7`YDx&rXl#~M12BL{I$i^t~|uHI>5Nl$Ssd2WL-3az4y zw1HBAAG76$@Do%xU2w?NO0Fu>dtSs(p!obXhI?Q`yk8?*qVWRK$6mwEfTV5H zLnBGV5m@bw3P!)|2p-0(!q$59uftjoFo#FOY`L1a&$McK<KSu4uN{^wq*TI$WPybS%tF9agC^?pNT5<-|x7g zX2x%M6UXP!wXZ8~-dkwh_iO4VcJr%-$`XgEn_masq#jm%jIYP$AwEmh3I;2#f1Sn+ zXbj2UgXKdJ{F3XTMAb<{x{;4Rg^e+|vJ(r7&cKODM`J;Vx2EPPo@>E`9a5WM3 z#{3hmQv zSzSTj-a_y>YqkXr{)!;M?@Suc;W5HNx#~SnLzYh83YK>k-fHG+fv+k!6TZao@bz0k zf^$4zaDIfBW%=YD{T~O%mI3{t@}GD5*Ek>jryU}v{kg!wI2tq<2mghC5yKK#I~bb4 z+Clu1>X54nM8-L`Y>xo;7P7PLZa09P4u{L-w9%b|9ES_G5v&gQ>9#rDZih1mb{*gb_Ai`Sb{j>> zwmI#t>>T)+Ww+a{E*Sj4o4x7uJ!??Iz_8eOlv&Wh3hMf~; zCcN#?ngiS^A^fmAtQ5oT&dSLFx4=)A8|bZ$9G{sEhudXkI9XXPcu_Q%49aGKP@jXc zv+QmsbCA>Sv^F?x%n`0^@TSux%LIPzoSZD`375kG23aW+tIOudhP@&92~MEj6?Mom z-A=2`?apR;!S+v%%Ss~)4!2uv4hjXfCnfJ zb-CRp%e3ZL9a#>li8Bkr=5pC&nNXhNuv-~=4rGcWOO^>zVe^X0bh~okhS`u~b33zh zsKc!;;O212(aZvy8$bzpf6AJjMc8!37&-t z$2{)NveJa246|+4Y>>$sfgE=hR0UsEft+=@vROFoZX5WQYMAYSI*`RY2zop1R%_NY ztuxNNX7$zg#$2OmPY5^^i%bYM6chgqPe;{he3K>f@c)=$lcv8 z*4;%G%;2!pUWX)*moC9k;K!S@9leSpkdG35{}&#LLfK9_ywTY_mW&##??OCC7l{ui z$gBQ$Azdmy1|s2f|ICL~4p1y$-A(4hs-sm8k)2p)$N%(qia%)woz4-EwBoVQ6#VaC zq_669Yp8N;>jbU~Lv+>jo-KCkTIsTJ`|bghUC>ImIH1H3z0QfdclXN#e`S~Gb-e8z0qNPY%vOUg2@eZGubf1S>h5y-sPh@9Ds0xj$X~4$f2s_syAy*+*9XIu1|lGf zr6%1FygnF<(AK(Plm(j#)wI^x@I5Sco%|#zxeXZ#BSoXG8)@H0=TJnWYI6Pv#G#>$ zZdyP!n3r#@6O-@@!E~9|R@bj7Pk1CZp2AperM1(!@JDiP`RPaQX{W1eN?O=nH(Vus zqP=b)z7U9X1~OOyO%#@u4gGWnN2K4pLtQ_drERGDD1G+63zR=E>FS6O7>vY3N z%#mfW*)wur*p}_ek@4S?q2YVcDRA%*uvNZc3IDMv7LKI}66w&=p#9Y@jKO zHZ9q3`Ul1bR_E2vOW^ zd|BE_XTfNEi}^ApV7}ZvM9r7Nzn3pb+Ch}do@|*%7h}Qe@_#hCq_MNERGD=);S>fR z(5;?Zv}k%sQC-odMgiV|Sj2t;9*OUwTO5-$-Ih^ZIeSxWt+t5N7^33rovV){A9vBk zp&z!y=!!yS*AMSYwr@9B^e$WN%n3DHW{1RhcgN_493HxE03^io3m6UNT2$+h6)L0UfiU9Qgj7=u zHYJpU_u)3W6Ld}PcDgPI%3xVp=-g|ds$hiMzo#Cvpr39=q9aCDW zGxP+uH$FB5Av_uUNY8HNSwb>#afHEI|6)VO*|9lr(5?#_G*a6wWS;mObwPyZnH07c(SEAxo2!Y5 zcWOe&XpD~s3ChvHL5aIT6@27B3QDWenwqMbO^vNeD~l>h;X7FQb?|-Ine}z0{pA9E z>HMO(^-z+Q*srKAsc1kA;3ZnBX0lHvm%(>$Dy!ftjy@twVo`N+=DToXOT+B3^uL2gY7={3OabhtBZun=m41$A3?M)e{nuCTyYHyN6< zB9C1i6-mjoAe7zNE7IX#uEojjY!wzVCm|%Ifg(gtu~FtQn}dHj6e9mr|1uIsMdC2{ zoTX(1wMHfbog5WC7=aIE3Re&}7QT!c#{s5sztiO34U7c`_x+?wb4s}=SXD><0U#4( zW}ykJq=@2ex|U5j`+1uwVu#18OIQ*8Lur*8nmzDYK)7x2*<-ILuT)Aas4#j1|ECel z@cpisE`M~es-~7JZT^$b1<=k$FDPW2)Aa41+o=aL%?vQw~XP;w9d z(k#DHiUt7caQG~BeN9s*H>h4#@=4Q8R*g?|pFT}gW87&=0ozSX7Bm*hzreEPrj2r= z?FnV4d35@0SaVPsyXn&@k`G7qUXxg{rhx^qiMucFRmi_hjRP5fTZPh;%Iz{0+`~d! zT;kK#VjI>iKn=;tbLI#-IrZ$(JG=-r+J zlNWMVv@Rjw+Usa?FalQFe5a?B=OYVFsFsaPm4}N>p3H-}6nir7<53~o#ae1*gl8VO z<$3F%(Z8w0SD~=BY2d9I8!`uxi^O2?R*wx?h|o%M;tO3YnUO5E3TVuVfX2*>H7Nts zhTz6@iPFz7?+g&K^-+2!-s2y#ngJ@?ovB2K)~Dc|a>Tfjt8f6hCtCjmdhIf%9u8>g z3i!l{ZzTtw%4JW=wGg+TWAuZ?b8_51hul66k5_L}iIruJEwTDRI{Z_ryyM1}S^kuB zf0Kp`#U=6j`4ny5S}`7_vUfVmME&7?JSV=<`M%rYPjr7beI+GQr@|<;McjK5;E79B z0I`jS$LCDl^?Us32en8)AW^2*WKC@mmw%m^CX!BNz0;EP$%xZ~&2OJi*8kNM_G^lM zf%&JVnFPo2mZ$1-&>AM&Aiv=yz}uYs{gjXfugI3&8ATRk>QmA77Il9;O+U+r+aDch z5zU*f|4l`ErA0Kl9^fze!9EOsNsR{d7|Ya02>svnN8Nr%9uzOP=_4pw!<(UrVOq)0Y2G*Jdx_w?aXU>RQDj|5l#9Ej)3%sAm!>!3 z$aErQ>Fl{xzEcu=}u>wLe)2uM%m=nE|Y zNVS$rdFlaA3C8Dcm%hXtfDh^9hPI?480kv4K0~pBURfUg%dPJpke{~EcylnOhkHOB z@wrB2n%Pr-y8`T>DXZ@4K!1jM>2vY!V4Rot(l1t+&?~$VbW=c0Pv2@x!!HM8MPK-= zDmOb_Da%OoxVeom7!sj-j#IgBpKnONFaUx@V?Y*g@w zmMj<3<@FG_vQYtC9sM8yxqBA5=>Gbl3aiKa>&;|Se|-*43B)gSfWBWd`c(t;spg9T zl9^@Fzzn}+_Serg5E|j8`n)$#e@n~!ii7d{Y>+;#8Na;2`U#4C`v&VXaYG=}Vu$Dl zH6z_IL|+?FmF`0!X4`_PvT>-sPcweTVfy%h{PKtC9r%f0{Jg{T9!mf(bM<}*RK?-? zDExXbK6efepjX5QegDfa_dQC5zX-xy*-eV%qWp83+{(d6OW+Vrr;(6A7c$t!5`VU5 z|5>#KR#N95tqeWHOmf|5{W1*Kd3s|!d_kt` z82u1>%er6MY{T14fjEsEZ>?)(@+Z}e)faH2Y_(V+-8EJ}1PyMH)HY5(E1`sjd?U!0(yiEarZdG?oaEM z%ET|3p3bdP&f1ofO5*B~f$c7WBd4fbbF-G3QAa>Ei0Z+hUr@8Qqpono-6sW%3d=o2Xr5_>4F zwXz<{pR7w7vX}!{K{86A`mYKm@%~c%)MgTU&Vt?G3v&25Nf3Va_NbGy^drRwt!%=$ z8}xbJn){X(RIaURzB}5&4EOfg`loal#(*upROczH-xiND%ROmTn=CK9LW90nq{(av zlxAxHAAYZ2gYo-Txf_S;+8_11_aZt zU-X-JAR}M@Z+(vCed;baysvHq`knSv9L;4dG{f+CFRB5@L9WyOrC$&qEB`n*pC~W$15ywyFDIAGw3xU_)o*Ao{kE zMNKe>TCF#XZcYiq{ZDs=TG20l;rFLxLv-LE=dZ!A2(+S|K_rLfp9^CI!wa~*y;&}_ zKdQ#i*L-;Ai-uOn9A|Hq5aiZSgA1qH{Tj%)pH&8Nb|M%JD==Ky!O%b~4jK(9xF8sd z^e{tZ%hJaMBTX_H?22@HWv^1%WHM~wfy`&ctqth_WF07Hftn4i4ap&RnQRBW+RTPM z{5`yDw3m5V02k4L0KUUt$wbXXz>19o0+G^@0Dd?a>6{LRYk4i0eYyy+k5iQ$CVDHv zu$~7pqqlW5tmJ_Vb4sK?X1h*?CwL@AiK7hbngNeQ8OBf`8_>CK>wM}7dlbgfdPB#3bDc(~lhQSoZ-Yi+b%V%SQ zajAxVf;Wqe4IZQ6Vh=Lr4(2iCiVt&{D;^&#O*72W;n%WS9v>VAjkuTYDdU6D<*J4+ zX0;L73#*PCxK)S25jnm3YcDv&Mn*}D;kC>^*z zJJt#WB4_h~L6;+^U-;v-VecBgd7WV!4`fyM+VzG-s0~>@3o0h3g0HbB$r}udajnlR zxW2Z*Fq7VE)5w*aOXg}Wsde!0xvXUZa=CJ@id=CTjgbsv#SWY2sAp`G%386PPTmU& zwe&j2osNK+RpV7deV3z!%<{s>GY#Vxn7L8p{TLwub_KKySn-L<18{oB3d77V1c*2b z*~iU8=1(4G5&HN@V%%uEIwFmAx}g zaN_7-q%1W92^|qHIB-TV(wE|ePgEP9?IsMt`PpnfK!T8j;G1$ZDI>WeE@xo) z`q~cTSv)1XS*yCSRa>rArLCIxVxlk);W^oI?S$*5WZ@zHo>hfKDZ(`Kob2XRmi8L> zCV#{3PE(}-zt)e1Mv%>^LL0IyRY(NRtOMb2l=l5Xs_-yU6So`m^jW#vsaugJYjY_o2NpCQy7a1{Mi3P3!K|YcHC>69FWqMBc#E@e!NNk zl-qLzM?gwCCWaS5v`m?Czj0|mO6JDvf>4fh3oiJ4zy@TnMRMBsRW$Djii9^go7J@a zW7ImJIBsrFVYm6-0FG0$1^vTMpF@jP9``!ghrH0evOZjipFSj_w{Rmq++3ZLJ5^Rn zb-UPG&|`FJv&|5XPdUBGeS|nG(wn2i6EDJYe#P}96 z;!0Iw1)qIWXVhRJi3}PnI4lY{=<*0j?qJAJhC6;d$#1{}7x+wv>*yiE9{wJhr*PsN zDs1F|>|OYHn9z+@NN|#g%-&^)P|}i`6Bff&(h~xg36Uc1~8ED_7VH z%^m<9LHyV=4tZa=57_mQ8OAS^d=+sM8xXRkC7#!WcY1$6*kJpX~J zM3T$*x#>cVB>+Ee)mZs9@w{NnPfmvxI{+WjX@<}p-w=#+`3zxfK+-QM>6Rd*-ohdQ zJ`Mo3!Rz#U;v|<`o6pV^c8mL{k0Lyexagv8D%h9h9Cz30n?P-N~&dGia&Gmy9S93dK^ zepFnt??_4^8Q~EM{hkp!+1{+^(9=!iU3fP+GgnxR;eH=Hs1c@N_`K$QxlX@svvBb6~K;F z%R%#m>E-~c5n9dRW5q3NlTjlK;*DfI!`>R98vt1Xa?1P1FQ!&lfuC<4zq4-D*-8TH z>V!wl$C`VN9H|ph$PrkbQ~I_aXQ;%-+{9Tglm(>QR}VwgZ~V;ir|dFc7>j`eiyd6a zd|?Z{r%!ft)MWTuv|s^rTc#e(k{z#Bl~OEPxKJoJcj?h2Az^{}=Y`N}cJJZWuC{+f zrSH;%+_*@{2uS+!A|Q1KBOSLGnvO0#*bIqds$}fZ#llSpjVAdiLOdSbgDhGC2|K#E zl3FGAD2;WAzu0h1W6I}xXf`#rY*QP+Y$2obQeim0z6YC%`cv&%Dl7#pSQ2q1{w}X> z5FW*(xy$2DsV-AozG|7U+w#B_S+m#Q8v8|+*#kYuL(7F4a{xZXwgQ$04h18LAjuwJ7MeI2N;uBI3tG2ER`$zH^_lcKyr|uz^(Vid7ob+>_g^mJ)7t14UI56N%xcG z)?{_->Alz})L{f~3@Z?9Ca$P!PbQ0lFj?^=biHuSJTic&kPSj1n&>C0rzUD-PqJl$ za0HE%C2=LgWJw&vXVq^Tg$c;KIDn{`n}lKL20u}~HBpOudVkm?JcrO?Sr%8cK$gWp zKoAdN!Ti=X$y9X-~~ zm7nm1;O{JI@4HtxuE(h$y``ncq+S7+9!C#V-H^~L;L_uXp7N&m?1$+3<3OK*4?hf< zUdS0Zvqoh!u$MRC5jrjeWV({wTPwO6+uqqL9LKmih;0>tZL7ImRml_FwzZE6u+!1l zOYYs^`sm}r3QJ?JW;MKdLyzvFPDqPWKAExN1y!g*&o-Ldq>(e#s1te5D}*bOP$TI& z6p}jO38Cv{q$vZKCz&+$3nPBg$e|}-Af!kQJpEP1Q?Cc(Gyh3wx4{eakzDjK7i52N z-JcQ)o0{^-Q^Gw>VQZfj)&h)mvK$9UEcWnx*)zg|5G?kV#kGfpWm?rPy1J z1)J;dJt(-y0|$kENF*C(!b8Cv;?-o>)I-AW0=D;Vx%OoC4p@6Oo>POJ);nnJF`X2? zMtDSTIm6)EzV)0#J02(1X zge$okhrIBvP^ZTmgE(YeV2A9_RyAr2?vPi16z;|NVV^_by73p7JiwJ%`2uIDAY;PUCJWGSEsACvSsX1J zw!yu+|AfuCY}n?n@pXR)4)idKi-{|N^k@44=uf&Lk)A7O23&_-6bdcrxmVEk;JjSF zVet{oQ@|(kk}&Kte0;469uBRk6z^Fsk(#b#GWXki)V1H9;LdD78f0i*^ z$yH>Gx0g{I1nYizEjRH=c>&Yq#}jI(6Y^S07xwI%$0XL{fqCSNNgRs{^H@uOFR0W| zQrBACL^0^OuHIV7RoFuowh{N>>LBJ+1U9F=B|_;kJi*No+KI2?#yt8~qds_Zp7KJY zjugf^tFrbYbXJXdEIe@oRlZkYj`u6G7-7JV1+iy;V0-M9s@z9fw1>TO>f2~>fQcLR z%X5Pp#82|rwBVyWd0Mbp<@bIb`Kz<|1^ybef-(J;7%>z7B!{)1h6SaSG2(s&i;euT zp%06`KiU(q;zo+b>Ns4hEn+U*gZpelG=A?>b>ufQU+Gx{t!7U=6GBqEigo0!u3{GK zxqp}-_A_LqS*&Rm2Z@Ojqm>(PpEz+KGS`&Otxrs|)K<-%Us}^U5ne`CLDt2K$B8LP z6voafuUlm4Z7Hd&%&4v@Eh#UqOPV;nuBNEGG8x|gD*qckraz!ml){7Bwe#wW0Bt&Z zAw$w688gj7xoG&r8ZJ89_!lOV)FjcO16E{uH}Qxiw7RCevMz~9q7S9l*Ax{mO7?v& z{r?LS6I(D*{UAF#Nn-8Oa%+{|Ctzze`WZESQ~CsKtstvebx24N%S{DZ-rb+bX3!6( zh`n|2`Ze}uwoa*HmRQt>)sN|YSpAs!PgTIwKHk--;=2e{kbSqq`dCFDvNB!V&)u>C z5`gKr3g0Bxi4u(gl+d>mQ9}0epRFxmM2329mz4la_NK1+nff&Rk3i`3KnP{X#$|}R*Ea_;`O|;x6g^Go zy|?6uc?f_^aSnZI9~RLVH$)V|#v*#NTU;mR=d+0B<rzD{?v?Ky+e7S!%)@CJ zza;=GurqE59R%NV1fA3sw7SraN;fh*pC7}(9eqa{SKcdM{=D+xUgD#uj#4V$1;Bo!^i)re&Y9{P{0DHFJKFy*J*5Y0D&b-4&oylJV0D7#>!+}WU}iuvM8C1 zgZTXK87Lk_*dY@%XaqKyfP?r5jt>?GBRotdSgsKamI*kBPqF<&#Ra&efY#S2(tntk zfGYqM-r;I!@(C-=@|dZ*X-UVpzPcQQHu zoO5z=lF1|)&il5cjd(~39Z3I>I{K|6k7z}s$i0s4%_;PI5?;JhA%QJ#u6iJ8W?Hr8GK$g!>^?oe2QpU38^8$ict4D%I>G`K>DlZSnXRiuzii@l8shoUNviDbtir?lRj@t z`q5}OXns-_?MC+bqaW>r6@^s?(|)!f#%d~Z${$FnY}%q|dOZ00xu%pQv2X;ZVbY{TISsIj!+R z>i~V9A82hft!XPxi_x^6_QijsoGXx(pC1h~J}-Ah<5lFIENetbff^D0m|{a--*Nm| z`nBeGU}Hr_+tnUhWO?1Jt_PjvHlQNOvFVoUV(ASm^zPrs(a{=tAZ1W)-Rp?m(g)Ae zVf?#f=#~=3(;-1Ex`4(*U9bSNE`<-SZ`EnZG^1~6(#3syJZ-CmcNV$SUfI%sJw{04 zt!yncfjW2L8(yTT|A6D2DI4eyXW|6flmH&~RS=(>KzIKGu9v?F{&3kunj>&=24+?l zV+N+YDZ8|IQ)nw+QrKB|XbNpdPI#09aie_N2(F>@`sH1ot%g>p<@qpA0+6Uqh*Mvt(Z0|i zuwlI9zCYHgzCttpfj+3K#d@v$l$=T>fQSEga$sf*!XN6-PTw8mHpQG2a6{+BL zP{0*`EG?Qt8~Kt#`#U!W2F~~Vl&X4#?b0i>A11v5J_P+dmr~6U9P8t5Ih{|VwNSpb z3pKywyvFnj!LcedT#1PR<$jYcTq}U3)W6K9BYEU_aQ`zF&|0*$C@Iv{G8X5XR^=J4 zzgevN<^o!vg~$5xqIB5a@kfG{vDGF}Y%H&{n70219Pbz~3vsG@-|t&+Ok?NaoYv(P zIDOh-!=7naFau)Imj#Zi`%{2R^nei8egh_$W2FKWf@ZPuF}2y`znW{%}UDqRYK3l{ckQ{X4!S?Bovw zzx8AiTRdQUlIn+4ZPOo1lT_pclf=o=pVrV<14wQ+sW^z2tfS2wx!npm5jcG1>N+}) zOz!5LL0P$;_VLc395ihQ5cCc3{ON-L!+;4Jgtc2)wvf7SZJfDX{_DGW7>g;8$^57-PIuipX)25zQ9=oO)xP}jHJ78Jbt zWXXF*tGU>1*A{5~j-Lzb4kSOhgNE^Mw!y>g11le=P5Pg^xyNs(UA3YB;IyIc7OS<; z^8B5&u`TImJ82tI#UH8oGMz2yOS@o_>M4JuCET=)EopBzw8xJANDJKbq%A2PCf8e% zdPgo6SrumZBD!DIqlXkvw4_!pUbGsL^Ys<5UcfxGEmF=@; z9p!d+fBX@R0TcBF;-&V2$kYAM%1;2=kSd*`*Rw41hf{4IRB3K^>^2ncE_y6ab{lK< z(Mx1Ucb{(KYUMER8v#&`7&-9k`=P~tY9mrg0X(T3v$Arhqe1^^cYeHpW)XhhB2 zor~S@fieF89TjluUIqU4OuYdQ|Afw$S+8$nk)IC8gx)VSXd1;lh<6uDQ+8&&>1AnmxJhU zRaC4L+*IO{(C|TTfabsc4x36!RPOc*=f$C<8CS%$pr$%q5^4 z<%e?bCHjUc0&LwW&*yzhYuLh}_n7GiuJvX548Wm3Rdl6$R4u*7?aMT}7+KTP$9r6z zrPP`*_X%g7_ZBz+*xQAMKSRmA#D-*g(&B^cLl`so*8l z6&;7W5+my>xg?Xam%}#R-WN7HK_Ng`_laL&U4SFOM#jWD&?3^UGIktq03^imD|cvu zEvb0rPM+~cdi*YhPeR$0ns*O|!+HKl@7{yAUr_oy*iKW@gsEhe@6jz~X>C zQ3t_Ffl#rx16Xzd)HQZHFBfCOX=*&Su9SE%gC|Qms(71VV!XRfaW+76WQh!FHv@g) zk`k;h84>S&0*nY`S>7kWS4@bkc+LY^iY>yUK$b=(BZ54@6SgT9XD#{uAXeNS>Z>5O zN`sl5O*AT4DI_sox{70z&7^NhVcv`vt|Dfd$x5O}2r$3@bcvq(1Y_e$lg;r(ujtws zZ@Z#vek((Z>*H-#bOF=2{TEC#bD|A}I&tW7&LD6&-E+fPJFR+6kwLW~^=WHXD8HQo+pJ4QvfA(xw!=4WYVU`#!%cV}P}7M{Nx^h@*peLx>M7l6=*i*vX8P5Kra=6Q z{nX(;RFf^x9K(Hu;=+?_V=SE9sae(AriMG+|E|r#?Md0kx~!G< zh9AmL>aqr8xKnQYHQBL3!?2(U&hGmE$y)3@JsR;+9!ir#9YSaN56{g&=FweU-Vf)K3YDZwH z5ByD9=sjbsVJ{!U>iB&jX5C|(vId%?tqpg0dSh2BcS)tIc`d7LFCN(p1hXT3wiyVP z?vM1VW~`ak76l7dKpjqO@0rcnGXba0$@czNb2f_R2?j%5lY~gMgR`0$Y)t6I-)+I# z(AhG>%w9NT%T_Z;#mg24747C*+>G+Dr`Y>^Wh+*eEb-OTnEqw~Tsuoc+##)5Kh3e; zMo)ME=r*gc`L7uC>wEEE+CZ-iG0qP|Ji9IXyJ)E6{-A=|u{PRzX%I>w6Fhv$vCix5 zSP6~X@D*$Rdj?w*gjf#ugZ3#o)?2-UXOr&g&K9eQh%vPXd$MRoU+~9h{hsUv?KiB?l8Sb*c0&05 zp6sS$UV^XZK&QXd3jCf~Ir9?uiM=exmh^HwbHa&MmU^|4!a}Yw+B{xxgW^$|Vai>r zoi*sij%ws!f{&Zo_J?679!dHpvJpY&g(RV_bE5F5umj=My~bpPt&qfi(s+&QFuUvN z4^PFKS+P0tZw|1hgC0n{dlK(zu9?Zw9DYh++cY=>)rZYHi%bd$d+;;%EGd_WK7@R1 z-c|AVz`krXADG6rlL!+t#KUU2YYG)Qv**&;iw@IcSssk$(U?TkNgII#6MTBOS0^nK z`SA?ap2o=xJtR{#)C|%tWSa-3QZPzfbxGV|61QWzl1stm zqrZU9l~0<&%J5^qPzTSO!bEk4m;19^^1N?(Ns|>MS>B3MEL>t-8Njj~(?rSE zp&5rYhJ(nQL`zqgwbnqImdO7c$g&8;Vy}1w^G-_-m~`*&4q~^+I$x&795KNSwX#KgG>pOHW|BqERykb5p|kQpl{eL+zB#Py zV$DcJ3F3Xqw1CL^#ie`N2-cVX?qWl|m?8$R8N!#0VDr^PIJ|j{dX0N_pBf3uQv^eQ zOLEyvk%-HD*X6Qsl8}VUd@W4yz)`S(#hWc_6qswaUAEGr**I?zMF@=6Inj^S)c2jc z6Y(in;lN=H#9&3J;2(NoNk;E@P&+a)c7iJm`jQaO@F(mmR374mB&LgbKO~|FJP+w@` zTn2sMHizOR%|rl4-}Ul~?A4$rl97c+d=O*NmQ3hz2Tx$n1^{FDxQN5Yijts0vf!DY zc%JDbB$>bee{8a&mbg{O8;LnN_}WZ|I?PzsySkGhXRTy@aw6+WY9-^-opL9{gC$+^ zph+wUj<*nH7J3YJ8Cbvtign~ARx2o7a@j`|EZ^lEn5X2Fd`d^xA&(sdxMr)^hp{S^RnZaJk+_sYjCC17BqeHOIxG7`|>{IK(8qn9S!+2bXO}iO-|I z`=OjV1H2L-psR-X<_vgJzKEt2qm*&P!xdEbe>{Ek>P*&D)53Y#rp(Wd_o^wjQ%I2$ z4b@aiv7JIXk}Ri?-k!~_kTxk|!(Ju6{B>4G>%tQof?45*nW9%4IFJXYLE5Bs!GoKY!!`ss46v;ep*L-&|%LxD*N5|KSv!OwIr6eC=$qPo$3JM<6&OqCf z;{JxSv6|zs$W_P(9$f|%ds=9~@PXq@(!(kI*b=s!K#aYx*vzPXC-wDfBU+-QC2PQ& zEJb8Rn}>MPn=HXXN&+Qe=xdxPtYhDZSC?lAs{?uxi`c2J!#EG=FU+ zOm^q^;d!t<&#QJA#SZ!hp5JC8Nj{VyPO@^YVl~K2S%=#$7!YuK%PQ7LWJ~-qD5|Y_ z=YNpN?Oe^uY2-aWLannG>Hw+fZ9wn%7pm(!tPedTE8<@u4ovBvs%sGcFHDELE3D^& zAEwXSGkrC|DEDlUOk=Bmyq1j#fM$)Ye#JW0f|67iTV=Umu!sl2>!~mVi7<|Xx-;HD zCaFB?x_BZ;72i#*9jx4X+}pi&J?lUmH36)!bHF*ThN+eYc+Z5bnaYQ51Xzf%$wTbk z$Tq3hIFMidKAWQ^;xx_BO)yQPP~vy4+HPhG)kGv`TUdP2?2Yut-nlI-$pdWEV`q zk>7;rSx3KQg<*bP&9>UZmN^3Z_}bY^!2vzAGW?5C%v?NP?w~;**oQy&0ZXza6_ujZ z@JE{PA?r*6`(Sk|ppSdwL&SG**I~AYLQg{2%wmCKrI{u4u{5*DpA9}^`^aVnF*Y;h zR_8u^=*R4eW4Mjw~->1&#(!~4itK0DHG`&gRz^tq}yE9upJ@DL9WZ@;BSMVO$S zJ$zs#D$fF=3fM#U@B#*hxhxlQTI)1Aq?Xsifjef z#Vl&pE&gl)YwzCt3B33wANdxRl%+t(!o<9tcGM^(ENi-wMJdHS*uhs_TXXoR7YT% z#g$sIS{#AbEH+qjzrczk&_XNuqo+qCAs*=(1OuY&sBQ(@}24rO6r6v490e_G}tX+b%R| z-fzRY&XdhrCAMlRjt}y0|r=gmUN!Po+Gih#VNT|Y?viIO5XB?Jup@w zkgzZry3p~yhqFTSI$?akX{eH2)+#x*)Bt%uP0oWtERN5vVBWFH3iF^%cE_1e|ikHEI#@a|e`?aucG7A=*IwN^46YwezzLDeif595YP={^-k$~@_!<8`mN$U16djISOd2N+`9NOMPBg16z0{GwDa)5=HmRD(7@o&WwVOu^?PA2pRb z7CsdBmBaI{!aA^>_uwxG$Bjk-o=W2Puds%6m#q68vhI^kE4h@qcaOaa zN6L@`Ca%|bv;H(Gr13^v1LHLf(9U?jfkGAI{Z7D|gW@p}b-ecUO}cbB5To%bx4us2 zbFZ@p;g5YaY^uiPUCSSoVX?TeW)Y9mIk^Gr5+2KHSMGf6LB{@euLi`*aymn3Ak_6*2D+7P zA1k?3(;9e-J+EnteQ^(5Qz&Hr*7{elEz=0>Y-=l&YTB0efy7lmmUl|8>$R_~8PdKW zM*C83ZOU+OxXmIoaymn9=)Ra?Z0HtgIQ$-bmqow@I*c?Tj$OUpTamrc_inDSNk zE-i{S_^=XezQ^WkC3xBO9#iuY+(|EjVA*~4E^O@dAs|zVAb9HmTdvjiB`CM92!h4G zv1M8_lfe6qHS&Z)AgzDV@9at1tuNMn*S=Wy(GQedO5O9|KiEkPW?l+Q+OcXqZxvZp z)8bEf&z)@&c=<@`tPsezibMZmYcw*huYB%>IO-u=sb0$m*GH_iW1Qf&P)8+3{A5mF zi`&Q=VUz-RM<0QgR`3yT$YVBJB;pq#&Fq^p7DegZ9HxC)O?S~IJuhgl)EP_=u4j=8 z_VePwW9A#>?dj_tuIUR2IqVS#;u^*D4eB*85W)kC>+{t_e2_m~Twmr*EPvRL)_9W$ zt2)<}(EpFz@qk0zJy351*I?RpJf9Wm#NU30Hsu!s^$_nO&2c7!z)!Ity^gmO5le*x z>4U`uPEP$h2)=w;5xzeHQ`9&&X`$~zkshA{734jA<)C68)t}QylYX*7A&JENM*&!! z52{Ox+nxt}qo3_u?)=L}qqx@3b}sjHKRK5>zoGttqeOpS1r2PZHz1|^TiW)j!1`X7 zQ=&gV)=2L`AjT?%xb0JVE4W6TDLJ7e9Pb`_O0TJrC{KQf9Z~uj^%_keJX)^`i3swJ zS={Mf9qA=O`nf;S9&PktDl52P;ioqGQZ*5^ zu&=G2C=yW%^<(r7 zofn+**CMJ6ux$|sdK<=3ae!@$$mlN*5j~uszYqYngpGT2qW)x1w*hEoT}8>V(>XQK zK_tLN#Ex-aNqFm4CNPaL2hpf2cOTk5Re>eclT}ea}JvmTc;*+>)kTnsu&9#6`LOB6YkRbtc z-^|oAG}2(8lmOzBe`*`mYb+!oTOTPBQG&LA!&LA7?|^aaDQ}yMLk@fg-C!V=1b1Xf z^r2RdA0MLsr48i;-^t|`!S_wN?15NGN=l|ksU5f$wmCtn$uFNiRR4?QdpN}LfcML4jd|2Cy|KmGETG<_*a9F`Ve9A! zeH7W_VJr0+I5GBs!q%TATaf42GvMs@NEN{y1*Q8)eKfhKs9C$Np!{v3KpwG|-;=k} zqV}Yg_D4}!)dq4=77I{jvF=`@^u`*0=C+Hi!*V+!Ll$oW-g2HKiN|RoY zhD=c}B)G}a{9$R*qnJ3^l&_qwwiXrajAe+3`@ag5mAoxD>t;zbEh0`jO zCrb*a{ZO8a0Gf!hdSyO36wJ1DCfZRMllM}Ys+Gc(@KkVLvV`i0uRsP8=p!~&Aic?e zOs_H;hmmNnGD1zjj7%OeRj(JUB=vz(!NQc36p>OJ#fMZwe8wA9B!|dkkMs~%twh#& zueHfi`bU+>oWf}bE0YLFL+-;Yh}T}zH)tD#4l42W)AeYwUFx8!$?}FwUTKEDg=|3j zVC9Z$0CvJvX6pI;LK2K0kIvMOkn@>1aJ+NaXhUZ+*B+gv6UU9rLcR`OPUB%4zh+uS z#P>|n8<`x>y0RmkF$bDgK$aiU5_9!W!)-`y=IKKH;dGs+r~LztXX87m;}56Oe0`;@ z7LLt_2f0>$NL4cgo#4{}#Pb*EGyX%ydiz1ga~uBw$2*}p)E`c(MS2Fgfri4rO40Rp zXFXN^Ukpjj%9+)XM=cDDnrDU7J}4f%mCy zZ5D5{RR5f;%@PeTSh=$%3!A=@@^%)E0^fQQn&lZ@HU^rd_(B}{26Dn#*C8hAnJoV8 zGJQWeBT!IW8h9153fZw>^W>XLNcB_4xpgQD3D?>>;4Ulbv

!=<=Pn*8w2WgTm)W7&qEG3h$CSI% zSRPwrlzN#3#j*otC=wrx+)x59*=7I-dMr_gZP)EG@!atTp{ke@r(6l6+xX>t%+C&W zRKa^z|1z7%WXJKFV}_h<%MsdG}W`*abkn&Xf93b8_=zCzGk1eKpsIdF%{ zd`$zgLzMfj)4%14=oXW}vzvWW zJgIAC;yH;0F2iL8j4jwhF&F#Wx#)@p%*~yJR1S+Sbp|adWF(+L)MWa(9X+4e-o3wvych-Zv$JhruZAhDq z&&dLf97M#d_sOz(-ke~M5?+jDZ-|4i7x>tF;yDJD zqvy?(@e2Hr&Sibzio>}bNfc-0tb7Dj)zMj0qH1L;O0=39{ zcjD7{s#21v&A9Q>2kqbGd^C2pQQbb-R6LeaT!{}=CrxXnGOA6Y%Hgye>!3*4 z05bqt2M;2Ep{+erw=?NhM_G4_blem~E7nPSr~CH0kg4NVw>+O>^SugzN_#HBNo z5}9qyc^^0>o)<5&ZwW;H{rS6L=F|H5Y=ZlW;PmRdHIoKgV_1)~yhxyvYgT)loE#9S z@`k#((D}a8%B`kniNpX{b z36DV0*X%Nt3Sl7|O5Z&>>-{maX4BRppEgfO9U3?J{&?dWCG;#|w9vXX(EYIH^IgzB z$eM4I5FbWOgY_BGEjZ}dCeE2vm%r|@(Uw#9k=&{s23UV!_Z;@p%ucF9kL%UJln6H9 zehl-3>{;aKm-KGtBAh+#S7Al!dzoR6Rr*k!Z~c99!VSvt=EBvp+Vrg48S+itXPf@S z;nF~uGnr~PO&QFh(3w{f5}btqygmS@+ML(u=EW>uH5h%6_`A6t>WshY#KL~j9bfr> zRtq4-TDg9p=U|W7@Hk*Qwc%=@$>ItV_n=Wa~3*lA}w=v4-c z)38&>Pv{!Lb&U=>!+E>a(*oNb`Rh)0I(O|f2CZ4caDj;_m433neRo41AD72*W#&xg z;}N2x(kko?Of{;uR5?mV_PEawy%4=LIDj384ArZEU|6a*=0-29AcUig9ImPF1-FFn zp5(YJfr$?m6-S!&`_uLOv=mz`@9DlG9J*YxhD_x4u>xwr0TUZjiH`RyTkGMh6o;w~ zOtcQ?wUNv%B6EFjo9CT#Ha_AwsTk+Z8W!koTBlEXsR%e*^3j&sPH~Qc`3ww@@L?iZ zpWct*N3CodGWeBN(wUvDjp{L+uU8g~oMnEjz-Hgo$UI0+y9z%w;o%_Z>O~V_N>w0y zEKQ{C#s@3hGfhhmU4r-M?E0Fw&_F{s1*c6Vb5tta#;GH)K~dQU$8*X{7R8*Ip`)%_ ztO@QJyA51crM;k1WO7Ve6J(-}DY0Od%sHs*!d_YWlcIVYl87i0mV+GF$+|#d?FdXa zVuJSvhII-)1Ij>bi>(lT!BXcD<8W2vxibjuf@7N70rv~1@w~ApYhFUH#=K}AD#JRw zbc0Epj+S&3!_J?BJ7OgQmr~}*0a;?;9z#YR@=J)@4dfT_UlWRk9`o7xNoa{h`^2n|raz%ab!Ra1i-~^_lak$X z*6bY6fn94)_DFxSwg9RZa90zK80!!_E7fxL!fbd(!eqagPFm+;7Yty*nI6fbwdcSm zG$oj^0LatzS*p*@1=|ACL8gPYvpzohWuV38W_5<&hWH5(&t#a!x6jkQY8ma!B6hA{YXdX@Kegi^R~>vH1ji35ZSUNIZM3-BMl*NK z=@Q%aYDgqIo?5MHd7Nzb^Rrf0Z7S*?grcm8h}VFB*Y7U&V!sZ8-jF2Kq(K1=-dz_8 zCNfYf6}fW6!An#z$vaiL$CVO}E0N@CSi48)t;HS*Q*JG31Tlw1h2eU@_@{Q`(5Z(D zn~qjIF0?8w5OUgZo9-7dk~p5LYal{X0f(HjQ-9wXF<`M;uZzK6_4d&SgjFRB3y1an zrnZZ8oUuD51X(b=FhaYV$Oo5?fb5=w28IY;dn`#jc+MNUyK`BAl96>2P}mWDxIfrj zb?jV{oq2lFXH>195nfNOwnOeuv(0;~A4BG-ef3t}R-{fg-h}5lC3mJu&|B{6IO{FH z!q}7BHbaGmo@y+i0Wj=BTsFc*xD1ievuNbA%A&q&*0}9~3xx57o4)7Hlyc6^=9_lU zj+#!!BmUGm8q9={z=Ybm*H6dpZO)=q-L8vKt=Lq0iP8?FqOy&`tc8SKp95}UIF(ew zFWv)Oc`|MwoeWfB<#gNIant6}6P7~5(uhtwLh{(frY{AN0(cKJVAKE<$A}=hz3GwZ z1>wqoo?l>ZE-tnb&!X21--vBZ1jpHpa*(6ODL3+;)%I-ZCn%{jw1?h|D3*`js;t zoq?uLRtw|21p1_qHf??n-PtuB`4rkgHm}v~ZroEC1lqZxS)P%(ShSp@zNg$3A2;Tk zPDtpcpf`-1E8m>!sOCBta$$wvi*WK8V&0##Gtt?vXTvt!uV&jWm}+0}5tq?bWzclA zxV7I#j_R@(yTMr|-E!SXZ6``!clOZ!{Tbn94`!|J+b#!Dyo?( z5|YhKp*-?FmQba$;adJWkv3Exkj=%2-ITZ2p5X_N>PK?=6OLuJjoJ=w(}v#$4pVA3=`Je*Mw<6y5EOQ+O*z6^1cM9(G~Z~G+i9e5GgEDg zZF{_>-|oixYk)Lk@-alJ9iCr+CY;5&mV zGVWMh3H-A@WGc*%KJzZGp2vN^5U>)dWh-usVOLCC1gkBV`0`XsiRWFgp!clVI@iHy z+8otX9mtFDtnU0oZa8)BfFw8;13?|~xueXidP@P@38Jjf$ zvOJrb0%Uo6-H(N6QA{s#7r?M1y!qgZ&YDY>9yZ)HxFt)`jzmkG!*=$Ulm4FAmTrHP znR6N(^Ue04n=9Ti^@U2WS=IojF2MB01OLun#Hu6fhp(WdFD8hJ@%JW zn`#&4SaW(MUJZOB^#jn2yn(?!ksp}*p!uq(}ufigu(-0t|o1savab8{FIgRjb?RoPU%v!2)yAN6E$&hbZg$t|=ZIkhJ zhCA+J^L4<3<*=30@CcYGqf~hTG+LoMJ2KPgWa<}P-dM_)+8JQSAwErw-BwX`Kv&F# zFrPT#q5;lPMM@~bNqiDH24aDXTgRQo^Qg7RYIJ}dFYbnOMIQtwqm%k`12%jQ&d@ zDh%!hQdMi20Ns2EcLD4!@RNB#&5|a8m{deVWQO|iz-=oYZ&JrukJu34VDKtyu>%+T zGKfyqEM=|b$X>}>hpT`wK$$z~KvUVR<@6wHr+WNHiL8~~& zoN20uwCB~Lf=V+u>Uc@h!ZAuA$VkSe=%Pcb>})1Rd7Z8$QppNSG&>~$3OI76<0HhJ z)&d{FAZZ1>F=^I{JXwM1n*|>rL6xo76UC_VZN#F1(kQWDy|3LPA^Y~}<+ zHX&va5I@-{gASgBi6T}Pr_|S!V7Y3uv*x*e;DkbfzX|@du78n@We+)PlAjL5l2cPd z>WDplR_WAR;Dxt9U_jQ4GYLn-4mtChqgiN8TL2S?z+}XyTxG^9@zhkKz94KaK2Yd_ z>e=+C&}CbKDIq^lFDmPN0-Y7e$cuiNcJKqv_j6fPS}x=-oTyYYp3DYvM_*J%t@(6N z11rN4by`+@9#6V;w?CasFYD1OG6QEntFkR&PK9UGY&5r7BENkBPSgX?p?r!P8IMI3F%=k3N(ICZ?atnV=J z&c{*vq_z&rXj&#x&j+$?pr&n8Dm|;?!RliU2Qio~s{JZp4V*K&j9aisL^)Uv<+&Zt zCxTn_41-<`DLGkesNJ+UGuGs&A)h2~REj-xF!nM>DiR3N-7HL&)I!xmBsL~iEJ7SM zJVfQr6XiSy1(nD29%TWP8>@@U-MF2UtS+u|u)jQ#l{buKP%tewvMT(g-e z1L9A=*cg^EJKHO#$k;_(AJL2y*ARI=fdcNajyCanCl)Ml;4+RJPpHC|LGW6EjGPgl zUxGULk}nRZ6TA0K%Q9B06f})z4gizgNngSz%jEqba!^pxW3dI=?M$aGh{0HZh zc9X;yz1ZuE6I4||;k8&WId?V+Wm@6u`q&59y+%U#%3{1DzazO+g10)9YXZnM>oOR@ z`_pmFJk%`*&?|VC+juxQkilbX&K|mLIqddTrV7$Nod?O+a2vsI-fc19g)n=O zskJr4w)YGQXNiM~Mz0$vWCgqx__;&iTemzbLVrSGERdES!>ZbAABFRI%PXXQ)R|Y3 z!<_S)lji2+WQjJS>B_mcmf8v2={1i9aM_V3HfB%;R-M%7lE_O zPK0MONI;LYb9$a4$D_F?^*?47^1+e+0#x&6KUlX2?<%2#JWn$iX9HwGZ9HFFw7H7s z+q<|WoT_tvU?W4|AQ-Hws(g^ZezhR8I#SgiM^`?O;i)n|G~>jxLs+FfBs?bI&su_+ z-aGG5Y=PRg2kz2>w}-Yn;1o?k*_5By3E>h2zy2=l#@qEEst*Xic@?}d8sXEQ3)x!b zr^N46*@B%1WmWcG+!8~k!4H}he*~gtE1}yUTt@jF8%LFHP5nmQEB5Eg)+xOr9D_B8 z@L9yCjcP4vfpGSVtFx5=t~lJo*Oaf3uR-}SQz^qLpKnp)B;3|aKd+KfDM4i|Z11rW zX+>^Q@`@LADn8AXcDr!A~FanKc6(uXC`+kE>Qp9aiy{ht@K95#9oNh#?a+ba&Md_tJRt+%s_G zrxDV$_k_0v!G?Cw?x9T4oFCKjXw<6BPE3N7j`<;u@>Q)W93~1_)R=XS8{913DijXe zI99{Pc}#M7P#&cMNQyb6E8wRBCM{b4gRUuvC24`XXGi-5(zcniS6E3`nN~&%p_&w1 zrBq^>*?6NiN_w5lfdd&oa%CE|qd-rl3lU9x3k&Ty-ptbZs1X9)oCrYajtw1oF-So|gN7Y?SlSA7Q%Nw_B<9{_xnp01llXpT-QQ1LW+Jny zCmjbJSKU)lD^(q3)*PBvTai6#dy?9-9b4ZpOA^c76YRrk)$5N3TU#O2K}w@KJB3Gp zbfkkTNoDiMRH+)Dhb0IiP!^L<)pY?sS~Ml`?Ny(rbL3Xm#|X$3@!~wMh^IB3d1Wcj z4rzRblVEBkDiRyu6Yqen20Z(Gx8roI7M*AQd3L77uI1EPb>pBTprjQEOyMMGXw+QI zV6P4u+cFcdnE1X&;z^J(M2ETfe)!cShNeJu=)<~=mzY(%Wvv~Z!FQ0Q=VL!UdzOPZ zGv8kj{U7n^C6dHx0gN1UK0goOgG{V$b*NeucA1M2wjXlYjVg6BlPKy-bB%!HBJ z%OS3f2I@(Q$R}{u{7N?`^#SUQMJT&+=xv)cdq7adSzN{xG%BcVFy8_T3Pl&iq%t<| zD$5;9kHW05*i(?Vmxnp(rhu;y=WxejBn2^BSaL*9C{hZ<0IhMh?y-kqa^j8dq2EQ; z{5naEy0f*bs7ukk?vus2xMW|OVcW~r zK$fiCVi&JjnBdR}oEg!d`TpEHRLvy_&FWjJwG{@32GguMhr`TTw+FG>Lb0v2SwjS> z1cr;-THW(}q4j9g|uK3)=I6wct3r zMQc)`%A6@Lz?{`m`n*``;Ec-awas=T%D|ya`j;4K+ObVv+&L)LUTMWlB-UnIW6Gs{%y2tnPL z3@T%ABu|<=65u2F%xQA{MaQiRZhTTc5;d`Yg1NXt^(u&Z7m&UWZ>O zE{j@&$q?L*vdJ+p`sz7emiKknwZ?Ar8-TD+ZuTQ*!GC+ zQhQN|A~96-$$o<Hn@9JS|-=1cr;t0)S-}Ks2 z4M0dftxIqe2-Azt4Ha9|Nlf`+CF}{5lTDb7OriLOlSuII?G$T(Z29SK(DirOg7};{ zKl{ z{~wKQdLs{!OkAJo$ik_hPT-)*QKQ<1!nw%vEIBVY_rxa^d*L6}MrA@B59>~)rgy-t zNApTCSvAK|J<1xbX#)w>X|2=;4h&Cm9rnA7K0juao-{~26jJKhiG;)pob|zIq{8>y zL()tmDEu~9fX?gy1y?ih+a!gx$hROjRl7$mX|xC1nyrr;9xET(z#vma3uo@4BSf81 zKz03Dv)Zu-%gquh35zHRFLXOqaAl?{wFA9eUf(pcc~qa9^@7{a+HMhT`q)dAItuOW z5~K*vat->F>(Lu(D6G0w#6gB59D}OZ_m1Z#1m@^s>++$VLo68UBYYGq%8o3dcOKL< zq0DAADITg(!$LYZ7{40le1?hvgUM`ZsOJ_(Wb~v#WbXE0E89u8*6`hxzHTo^%6P~Q zso{hlXCn;)yTX`OHei{G6CRyl@x&bn2hXfa&htxe_yw_64K26o%I0MC2gl9L(d*o~T)#p>9Is~qOm?Q&5m zxU?yYh6$ztaNZNF?P3hfjSCK-Mlh?7E9N=eW@aC;E-kWJ(cWiPwRmXMjfuombaeqNY)4G zgL9fBhGw3-TT}+S+Ro+lphLdEVu0+ML4M2?V>XZ0t_>$`s<%VkYpaYy z){W)?rKE;OSpdn#3g?bb>R(D*qHo~PO=-1`(hvP}cCdRWTet+6aNZcUP@XJcLD#vg zp<R6ONuw0B39Z&Ev3nwnlAMHQ1;N9U@N%^48s z4B}I-VfSaWXp{mC|D&b#kB&W~7h<;3BXOD-7Y-U=L{a0J?@m$QNk5+`+O1eyMiGtK zYNmHNMF0cAC}G!BOA{J9A3(%PWo;OO*B%A_QPwy?tL}H~S>FTjD2_{@O7cBu0=(_Y zEV0U#D7Z=LQK6nC=eorIeWDmkHlrjxyw^L|zH3xS)jG z;y38>0OF`~mPbn3S||iZR_(6B6>7J%ZDRB=^9{JZ`|OEIoAin&I9g(MjiTui(Z2dY zp=SE{AY_}cpax8&AwG5F_Yw+M4#n=O&~#2ZJ8R_hPO7Wgi3(8fu+LPjXazaF4K0>M z@yWu6Ylt1JTFIizZh3-H=KED{mz(RHCv`?UB)+U6HhEw<8|=9QN+^;=eyFNMu{RP0 zNkeh7=`SXBHD%U*r#@9AW#a5Ox(j|TaNbS{Ow~U(Hk>Kws1wZPt;)y|JUCQaufu zMyG1?5R$=kPpc8BZ_dwK+=%eu?tBVLEHZZD=yas*)A1Z}NTU>NtEi&j`A|HRK^OFN zL1%4j=91V_SJJ325wL{|EQr5yo0~|iscUmKYkLm6AA1<|N=IL@5f+#7s5nBz3{$KVJp+wQdzG+bTvu)<8B$O?QWe4dLA2vD|&8^PsyPJ z@+fOo7EE_M4~Bc*6L*GgHb6%fH2gU|h~UnFT`!NTr^ViyfIoHaz@pK69e&UTX1Jdo z+8veODW_JC_2!!zKo91*$&SYTplyu2YA`q)TfJ6yEKgSzX_YlO8L0}kSpa_JDP=d6 z>wap^fwat4s(y4d17%8h0YB1X5iprmiUNBog(8kiVECv4F!>}%J*4FU14XEx5pRTY zk!^zEF{LQ2Ce@HZz*K0VKG-k$HgA`#dZ3)XF@i|cs!_D5`!UiX>sh-kXvfJBB?$&Q zWvIwehm##(hfh&r%3#2eJ#*x1AW)(Po4V3LB@(gR6-TL0ES|C2l+{$wt0*BG4JP8r+tE2d z8BA_&FPLN4@opz3tbN;}906Cd3Zk5GbT3#JViVeaV7ErJ0$25Eselg& zg@xICq9`@WFCzGP5VgLXVTxf}k+G?`_Gh6Og>RQuHidNr|aSZR693xbW& zV7zwgu$enGxGPf*$#N(x03Ig+b;ZV0*OyUy7W0baScQ?sEvQE0ba>FGEDMxqHVc+p zx1IK#soaq}$TFWd25fd&e=}=En3@76)4c-=VuOQzt{#raYffq|IOF&efS@u{%UeCv zGe4qskCl`-Yl4}yrDn_Z_!`e4bG9)eR-j`2S z^^oPD9Ft`*8t&^u761Y=$E$g%cbh>8wk@#rS>V}#Z9sJE9ZKhs{I><--0UhaP&zPe zqQ2RDuw5T}Q--HLvtG36juFFjf3^@$hbgsQAS8ax*ID?kb-`jo=PY~X!}yXMaB_jf$IQXfzmUpGO3U}P*VS6o%T>?k_InnQh*Pf3XslJxYeVj zG{Gwm4@}D*RNLTx1OF7%-L#w#u9ae=TLYyA3eUx*K4ecrbPv$xTo==hI~FR848C8c zH3zG`2sQ}9L+GR6&Y0)jwxy#OD%Y&A%rOA>7wyb?yA9~~hDZ)*4`g6t=UBTkN~4X| zh&b0;D1r%81ZvWtU<$Yd!GfiQ!(fhzM!Y1UdgD_815twkZNQ#mbBq22UPBk&~<8m0*fte_gp2}G7EpwP*7?@emwGRTeP2ytk_eX*iJ zWTK71V~c!ri`2AU0GWJ58+&;hp{&-_PeP}S!hak#HqU`QPK1~cj3HN8n^6Xg4N7xE zHq`V(4YjLUqI+7)g7c;ZPS{D{63zy> zN%-gVlH^YZURV|ZGNs*yuw~lq_z2KXg%u(J943GkRBA`~&Yg&ha`3J8e8R~jny4Xz zR0YPG&F3srr&{2KEy3L2ug>+OK11o)s0T)lDIZKhm~FA(^S{&}G*IWw-kWMXER$gf zqK{d~qP_sKz)@?dE(6ECW>J0)JX{R{W%6`re5fTb?JLdY-ULwsH5WxhfH_BZDduFsq&@3RH`X-mZh| zrzCxEcO#M0CYg*BMX#Xb1E~||Zrn-U%1fV{bOlQ^+8Cq48KHy**=vEE^x=C!(T4_L zh3!jy1yaKSgqP)3gZ~`>n^ROcpxlOi)?b6FS7Hb=d^kkDGYUG10T;O*cr|Ck3^n2K zTD@*#)?W`!8`?ib?Koe|H%Am-a;h_@VKp*lP;Ze+I4Ew}KxDOD;$cUfLYcz}!M7vp z233mFMmhnt=7h~jZ6!u9!hVVPZ4K~oVaakQ=7=M-?|^@-H*A5!xK~f&1tsoOZd#F= zg#S4~9dT5hY*{rFU!ZYnVujAZy}`LmXHMHaF?Q~uT|`H9+uDFXPSg>FH4du{=w2RH}GAe&OwZ7OenwyE}(h^SM4AfRj0_Q^;wU-yC+^bbd zoS5*wp>9#W0wvFOJ0GmOyEcjnp9s{CEDZbs0C84HvP@uxCMI;bt zaMfykB1`sMFIP>%LtE1cpSrS_#G!z9m-q2X8B4A(LP7`lP7qZC-{%@OTSp2|`FrU? zU|U1rH7IH_wt&zbTWsqDURhKC&0?)$4TeKT22;1!qd}Sj?{JeFDI5w5vPk4OjORAw z`VlovB_I2^lt^B~Rz*Dn_CU_U6^QUbh6O@IUH6aC$XQ+52M68c(taSD$IuzUmo`k% zGaJbpZuH@aMh;v&a10#2iJ8WYsxV{uNEO{mp16rrY!UD(NeF%O6j z6+UR2A4Lq})fZiJc**g=&nv022OY`9u9*9STmEH^=^{*sSRUc|(24Jv=&0}F+VPR< zRwv;6L=`JH0Ffd7^nD&o&G{nWxF?_HfA06b^J8Ble}4F>_aFTH*S_|fsh&UlXnFr3 zKJ)$>`R6|(|NJ}n=ly@>)2H5lf*<~j_uKgQHy>T^{G{_!&QE{uQ|FKT@YAQx&*O(* zz~4WPzrTdP|J?UJef|fdJd5+}6C=vQ>{H?Ex$~a)m(hyzow5Gk{KD6qr_TG%H@tuR zK0f&|=f`thd!Z@sZ{kwzaf9Ukzd-K)hWB@FZ@RSc9pP)aZoPQ(zxGF8y7~D(ZCJkl zNmjSaEjarZ*WrIBI@w z-9+|HlqdL0-jvF;WM^ggDseU4x1JP^72asRf4RoCv@B1o^hQgp8vuf$8!a@i-yry( zxlwpyBvG2;3ex_!%Wr?Eo$#=yc9h&`H&JMPXu5$Frnpk`ZwxK9-hcKfnS!Uz&pv0r zY9~MajZg1h^sBdlA*8-@ok!=X=zK@ab@b`So;);;#q!E)e&ub(=%M-NZ`aN%`sRJ` z^~?IdtO4&|{U+XytaiLr`S94wTXkM~^B33g%PY8oX0Zd3zjwa_?ndr1X5V_9Nq?BK z*Sh=_Z};MMd8v=i{KXF5?GAMCepjsjHe|^>!M1S2-DSZ}rTzyug>{o!){X5ZX@*a= z>_(3==O(Z+CopS6Gg1Jd+Op_QbWEWrl6 zJp5rV2l(pJC+)^3dlx%7xk&?TS^P-4_av~i@cM?gH{(<6z3@i2Zjk1w`R*By)XPi5 z_c8&GeRBVlXE$O5u@M@6Zr%;n{g?Rsa;xoTA7GfYknH~Jqn_aPa&*f*YZvJN0TkT8 zLzCWw_w7MW{F)ACj!&xJes;s7^QMbp6^RuRDFgwPK7oY#_OJO`pqtvaKS0}%DCDhu zOEbx!Uau$JA}@Bm=Rv9ex{^Icb*1H^@r>}j&+;`&n>)-Q= zSN?K6=Fv>PN{@N2$r1DjxPNgRLRo;4fHG_3H7@GK%jYk&5*PXm`SyMblOy~y`Us9$ zqF6vrDDNiV_u)zRqw4*)WLm%B{nu|YyBEFhhYu_NVZ1#4CmxjH=ihyDt5Dqh8Wgqc z^3Tn$>5*@yWq|*FaM_qYeDv)n^YfBI+eQy%D6@~P!SFbH(nI~=0~r1zaP<}sJ*->p1u1;@v3Ls57T8){Qb9I6n{l~#h^V}6n~89>k}c zz<9j1o#A12cOeY341D|-zYviPSFaMXH7;(Y^n)ibGt*p0jvm}aw|5dH_||N@Sl?vr zpn;nx&fMV6a*UG*?x+9~$TgfNIGTt7`5Ei={y=+nBjf4!_Ta_bMSm_f@2zqCB!xYT zGcbcy4zn9JX@m-C_~-WE3^ey*Hba`hLx5z7^x4hGCT6&EHSce9SeCmdx@PQOmV>yc zaN#r~t~9&}>Bptx_>A#bu^yrn|QG;*%Mvt`Q z-n&@Xk6!8BwD&e|#J`(e_UN77Rf}))R=@gooBq+;ylqQw^A`LI;_@rYo=0!+Xlzi?1qO_$4X|>F>XQ z{{GHCydTZ|<(5Y}hy@+w6&<{Ja_M4)Fr?wEhYLO`u1dsx`xn_41n(93@5QNrrNwgyZ~;0#Ln=vTI1$6mUi_(8h-Ax!~JNhzv^3Tp?~q^!~752udko}6+OA3e)ZlI zy8r!ty?Y-3-y$dPx z_>JC4dvEhbO(NpHg2;PVkYBZhSM>Tp4Y)hgAD_=8K>cXxlJoBNh`tX{KmP?Hf$u;U z)Puk#XUg5q`oe4O-^=@-N&DaM{--zEUZjtI_hEZI>f?WUx83j5h`;{g2M-7L^KWs> z(e$I6Il|F~7Q4_Vj07N%8-R|jOVl|k!n>Dwt!wXJ>NT7GhWB^h_^tom!(0E}{mgv+ zNknAPe}Tbzblcy#zs>plu^Dbfj7$;{E1y6Bpsc`(cTEJpT>xZ!BI?h8&6pSDfFETz z*Wr4)sWa7T^(KXD0?Gx@qBsJt$c}f{;KL}tyEd@^fBb_t_3r)e4^#2A+nc}0-E}t= zk8XRdsXz^k-b#9THo_=`?hbE_f1?v63Q&z3%^(n{7}JnFTDo8P{)d77%1vNgf8mYC z_3uB7>mPlCaeZ{#YmKYG4LcZC&e0O0{Vt)s0^*SeL3yw4-aP&Irgr1nz_-9H2)Ioi z0%((vD}VW>dIR*0l@uG zMnsaKYurR9$Q$C5G$3^#lrK;uVme*dc&&O9z?F$l?}z`Z-u^JsU$q4cs_@2x`hPwQ z>hKK)_0eswHKd|elHB`Uc8T4P4v=F6M@?iu5irB?@mxnGEpq{%v-24d&mJoZl)~2g> zqxV*AJPhbtHG?t!!5fe9|MM`$r#BemN4LG!7`J;Ph+WlkcMdV_5jQ{_fj9;*jy7>2 z+ESCqx)~X!RS7^?X^bt*|O97 z=w=j})`@I#4S;@tICa-|GvFu@4b@Ddz&RLwU^nlF^i6Mj7{@og6NC3#Z#;Pa-^1Yj z)i)TtN4LG+;K>~vKYZ@{A6~sy2<}0hA|t1ru66;@u2xd71~vD7$3J_++a3+x8{Ub* z`m~O@czp;7`#Wfz1HBF-H&d*O~&PEcYpKYP4!u`@&2#Zfr|w;1IEC&yZdk7 z;rq$3J{T6?jjf2_ju{D*I9^?vs!}*%x)b^pZE3sJbD{4oZs+N{P$%mmBjk~ z!MFeT9o|sB-169Es3HdkkRkX2%3BN!2}Y6;xH{nh#<|n>ROipQe_kM+x%u(wj8AADJKhgYJj*a(0(rGV>%x=bbSW-Vg8( z{B)j&|FL9__mgoKuzT^?_x>eZ_nACOi`@L3@z*E!>nOc#=jG++y!`_t;infy|_)Kv4vSNu+_5N!&@t}0P$xRs2KX?BMx3R@{ z6`%V{FE#w)Og+XN-^J&CF1??iyIv9P%=xJoSI^ydcd*X~DfxNPlSd8T%~-C#Vn;sx z(k=OyFY}e|kx`a}&xim9o&X2l1$}p!>`$(e_sNs%|DW7m1BfVD3b)@regDamZ{5o1 z`zsKs*I<2LvSR@Yzy-dQ0ViNM7I1?FNt6Qw@eUIBQv1*LR+&D%cf9=*-_IAP^si&B zyu245uaM6b2>;prBD>pwFD|n$6bRq^3-{~ow{P3QviOV0x_(Je|6BJTdH*(kL=y5t z!uY?751#*2N)j%EPrcu|{S9dq$*11Ghu_x!+fRP&Yt$-*yMziH4=K¥$p|3q-=s zYETwf#;Bmge?S1C^g)T_(XjEXO#yOZeHa5W3bi$*ZkHUDXRe=8riBonanV;H|36|| z#7HIy*Xk9sLVmqXvwpPdi0yE9r)B=~&G#RD_x%^YBr06(S@i-zx!_Zg0eXjbxqMZB z_TV6KZ$;a!T0)#~#CvqN@CjZ98Y7ZoVM+S<_5#m+cC(4{3)nWXki!X2$fY@Q zaGL7%}+SCq|Ve*$6*^c4PL?1@T%ClRPD z<|+zz!2J+}EE3v@SwNmk;4imNyY%Jm1@aK#h)V-Eah?DRbbA?bg~K0y1=yrnZsLrF z#J9{GGXpdaq7&Jrp}SXi(-cXnWN1m#H|VNGaK+@N;1+ar={Gc(+cz5Bf_u`~GKiOm zA`RKdHO2@;E zN%f8Q3l4K0Q7GY1bh_D{ci zZT;CbtM|JfeS|wd`rZd{5|M}AeO$YKUjN?r9-6u(GWhtFm)5^`eff?Lhi8Z-34iF_ z3t}cO0I$pH;Q(;Q@(Nw;1xOr$n>}@(SUOqscU8eFA0+PSB@yYFG z`u_Wu+9Zi26KhRcepR860eAD#y3?gQ+^%-R7G`0)#J_kA#rJg|(sbV&S+b+U{+ zvpzvkIQO$pz5nj!fqCT7UH`+QkDouukl;_nKBU;E&zD3y_~dfZfA>8y$?tt|^WJs& zlAmtzAD@tyPssqJm zdGtEJucRrD&gTFA{%n5fZ2uzCl)D4{0hslon)psN{XZ<~y-k)pj{ObLfeg$hs zZ{82@FWm#h7tVusUH@*KAl3Vz>M@OahqvjX;G2#@v;}?6F*wy{Sz9eJ5=%~C~4Zkl(yo2NL_2{}lkm|LXYMf3R}@Uw(wY-wQwE z`oFBXU`a6)i9evCG)!$iwZvcD( zeJ`Q6Aix+P^gbXIkii__3k=abK%L`?$Nv2{fA=ro6Ml#2ziXjOTKf+d{PiVyL(MmI z4EwvXExvyVYX0TX((KN)@$NInFAOAM_r>o}{Kj7zq{#A9R{Z({^0tkj`P{IYT4;rcg0Qj#D zgT6Q-~N}+4$v|5_}uXS_&@)P|KjNjrv1TG>GA8iX*eDX zWPCvLP3{E$r$Jl)2>vOw-*Ld;8{Q19Jg6- z3@LHiVfgW)JD*1a?YlEsr=i*K{EvTE>$ol6&?qWZ?)dC;DBOZjhwr!w{?CHp3NMS! z2ly|Q?6sG>Z=ZT|=Zf%~Q6Wj93~F_Lm?j1bjq}h(jLgrOKSj!Rfg$!zHC%|ax(MnW z9ow9|isv$eS>kFlU#K`@BS(wvFv<-G5La+7s_g0AF@@?Hp|U6^=)e&;(U zT^K`Om+IxA-Z{@hXVn{dtOa}xf+$FzAK5 zme7rLbKD%<-hagXpOq8;=UJeU>_5Z1QAC${XiqkMK!;-6E{lvI@oO1U?6R)a^Jt`A z#xEv^QG7U=lQ4@$5WcAAYzPMvZD?c}r~LTZ8q~rOXO`Uodvqv1atPBB8$*v83_WfdcRu$<&$MbR`f}(8mb(VXJs~%W-<;N>$LL+*5 zTqlepNs=JtzJBl}$-(?=PBA-jMag+I-_TZ{hc5fQHLBh4%>UXiO7)$a6E2=gu~<|E zW^_#xbX-Tv2~WD}g`J^6ys8mgAHn?S?;g=i2@TKtWBA4Eg{1~D!Jt7uS;z!B)bFhZ zlQv@*kz9}qqp02X?ltf9T}$MaWbRlZREHw*7_Z`Qop`=DStPo`zzO$p8ev4$8oG@c zqt*a(Lt0{;@DZ=486nabx=U{ho|*Ew0dQ<7U?gXhRM35xteF<(>ChbVrpR^F*Rp7} z?Y(Lai~l(jyzmjH*fauY{7vZ%o~J?GkH|O?xb>J%)G<@3CU_jB~P2t-=1!c``dQn22qc^>y7}A@{hA{UR}u#9;j6 zc4=$8R~SoRaBfY^0>w`>bK>L|cYfvP7j-%nRx*?*I)%uTqcG>G!KD!foWq%+G{=83 z#|&-iVac}fkI&uTU-#4aAt~aEI72h_R>@;pL=jSfX4kJ!>Z^W%ABW<}m8}X>tHvi` zW(fJIb`)A=cl*(zy4{Kv@9WHKk#)ZT7w{<$5X1XG*|uLY~OZC?;O$ z>w1D$E>qQQTt{h&pw&H$o$;?#G+y(v48vwgX~bGc=uw@+Ui!otiMt+U!KzOlX?$3A z-aph1lW|@r7Uy8sW2P*=U^DYSx5V?}8kvhW=hKX%@PRY}jm7ae4&r{KmkGlzx-}+A zXSZ<9V;^Q~KHgl+O&VM*$dDi2ItoR9oDN2vEG%wn+sH#f3C|bhSn_#*OZaV&TNX*$J|JYBF zS8s6}#3_t~a?ZhdTc(i`7IwV_7rGyF&Eb2W6dAP;M(h3`-k0A-?TLC)zc5~TnFyD8 ziudEG1m1WW|4DW_V9~Ge5E_})KMl-`^oAGM%=1Uiz+@^srhB~*o$o_xcO94+rdJ%| zxDs=5Kf;4=s^AixA5l&83k*KEH2sYnVSEqfMMj!d@s+=ydGS*Ie%E*IiN8Obj*J*_ zFewWB-Q~Im1eYW7*;BfDNi2!q8ug zAn%mx5T#GY=jpWADLjk*=b0Xp7d*4btG9b!q(c#NVg&D8EY9&V@xOIE|MU3Re;R)r zpRM$|F5D~_%&Znv+$xC&=iz*}9>;qX^d>W^O|%W}4&&U1o7-tvF?_#D0^_21^{)M5 zo~za9$2({*c~Z2#DU4~}zn6jTTb3O>TK2x|1LN-k43FYQdzw+r>2 zz+oO=|6FS>NbK+P_^Wz5{bgVN|Ihw^;X4UF7P($eq4FluT&443!H%gyWazqXFf8f7 zd=Qu`lg>Cy=fFp3!r^$h=`s^ZhHKBEtqgM}7@9^WY}k?cywRt-xrX2mIyZiMHJiII zdhgF(xP7Yv6%a;~WzMi&7wLa7B!;o5mg%3|f`K{PI}=|V0~w7Wajt`nx4tL84uoJc z1~ZmAH01dYqLvLqkzj)t`~rCjA%Vsf*Fuu?W@Y8WQFCD07X%{1>e+eN9(L$J)eo}F9` zSM=MK1-18_QKGqDj_F7TEs7#@fhWf0iRNU9#+d%$L>K~P;IzR*{Pz4tZ2I@{V1N}Y zOjj!>Ru=9)PSc48F0N&*CtkvsB^b1F$}<#(@8mE6(r>8C^lIr?(X`=ONydnj>ARub z0!1PWLCuS`?Pt9SU>%Jo3}7bbWb4?=UpD*OLCt~;!65Z+V1^!%&+hKSSJL6L92#6f zu1qJbc{=4V7Gv^=c^n_nMd;mjw;TUzm(#SO)U=kaFV?KL3uGg6^A*)gK z+1(}=#%(g)EMwB=eAnFqQN7-GTBXUaSkNdu#FO^!E1?o&o#lud6&tNQ|=CB`=xdZe<<)aDl&{dNvX zk!k|N&}iRR9Sb3d>=CST{J52OtG}-(Z(lXvAU*~Rm0W#Xc}`{dDX|%5vKztaICSVZcf;Q(n3@MBC5GIr%OAdqd@|nH9h4DQ&$G`0dvzvy&-N<)jSI$kS?3*A2rl1~v!~9UUrt)sK;8}K( zX1xlQS6XmOr)AbQOm6R#{x4Fr-AmbkiNhRY^DY#$YQbH zIbNQR0uLt2(dndA->w!$Xs&ot5 zbvcvTyK*emZE$7kxWL$)YnpkrlO|txt^d6}_X35>_YET+2QRojUq0YUdErp&bb>ua zFg~#clhE#^Z@}y~$g-LwXLpiaAk?lyI2#g-!#11+Mkh&SP7C~}Y*@7QyjFF(>is7t zmiY7hh}W50W|~IO5MDE?2}NOEuCQ;>kU3)N`LMqj?)#x?C)${ryT@K1o}&J2w&6wu zJ*8;C;BKCzJDMqOH%))e@} z1X&PGGfe%8tMLj$$8b;F_s>HD6YT;1BTz@u;xES+mL>%U`+5x45+wl%a%>xQaTp4n zw{hSj>)u;53S+&f9rA_tcTZ;_By5_M@3hQJbuG^L_xr_btBuQ$W<}vc>%~a3>vaRC z0psjoweXR2mp+`D_SOG+F2Rk$6=GrGu`J5h*)kdo-YLGZPb{rB>%zd<-c@d|{2*5Q zu2)S83=5!Yf8wY%dR&d5Y8Z?zR0V8;o|$e!F6}wgR4#~8Y7)jb#KFStCPO?dDvrYz zP(5Z%v#Nf-+BFTQTznEmII8>Yh4C-7XJ6yvirP9kqu_sKT$oxM385vH|Coj+pbRp^ zhg7vd%&b37Hpbv|pECrEi1dcudJ+Ea?7=!W4-=5J3dX=Q5126OQVWeV8jVMkYt9}u zY94IV?Il61Po2jjwtu{k4~LKbEbOn=xvx`s9hn!*FHOAfsZ0S&`Ea?}=1fiI1CB_$ zIoHmM;9*SKd+E=i+gbH~yw~O(1{njmobq^YjEb>@*gFvATO;Q&uqTT-WQZnDB$xx#`~AMz{b*3oM*%>mPRAPd};DOtG0_XDQfNDj9JvSvD)|? z_ww*1w1^gmiD7(wD<9%rxFyK-=4xo1`(x0$517@~XIR&fMEY#J-k6@1Lk>bt_H)eN z6!qdfAYamB`M@6sEi@Kx^_Ua;B9YY_oOv4R-9i0Cii+pvyWYr=4J6VIR)(B>dA_dj z?2*hKx!#$W;g50l;#%&lnbPIqS9EwI+S&ZV4C;v(?N`!JYa|TAM}&9f-9p%7hT@Qf z5V<=?9(Ez=Bx-!GfXbb4=k;cTdSe3kdF~_fX@DF|Wx@Uk{O^9%APnnej>Kn2Pd7G% zIc1jQmlUgAui=ey0U@eL=MrWo0n$SCqQM$VUC$)n^2@Ds9FG#&8#bA^COw?SiCYFd zdOM$x>0hp{+JrtJIAG*wp8P9!gJzW9*`&mXF}LkZ48FJ63Xf*u!Omxo6)@cM-G2csGj@}Uyj&_pWm$#b6t`uDMVKn za?3o>=rO_)ZkF`)7A#ynpl|orY& zwxtnIHN37O#tV*QV0? z;sN}{DGvJ8(}eu6A4AupiB){!Pp$0Y_Kypw{h2l4oPGQ|n1~xcYx?T+ovCEZJEaC!rMwN5u~wrt zTUsLo=b(2=OzHUXH%8Hu+9Tr|!Aju0(ZqN0AZGP+t-LV3Ci(tSXf%j?eZCoHqZbxz zIreRQeu9mK;qd(;+tWM5t55?7HVJhSaun;1UdK`~`xouf>G%N~qIBw!H+S+yL|>Je zKVzv;N=sz|s_TtZKZAX{zGl1C0V%4%&YdH#lukot_66)Ohe$%=y6TGXlpwr?bc~V%s$E35#$KTZ zhw^!06d^tzcaR57`S?V}SzNMb+C`h)!QHy@hdE>Gt=1Lr|p z60VANCkiR84ScF;Rr!obuvb1m?BmAA7{Y?vzsKul4=k{m9sQEBBkLx8;r*UB&0U3V(1^-z)G*rQOx|a7lr2)Fgc;K)p#D)n2?8D zt~g$H(`KfIsq(qDP%k#FHj<=v2fI~v?av5#NTrP>Gm!{<6-`}y+0*)?pIsvGkN zaI1Y!T?#zQ+x?XDJH#Har)mR-^?zKxe{BEN4omESo2BF6Q@H07Eks)dPyuSQu+8Y! zQ@jrcu1Qw?&jx!mrWw=^!Z<&X zs4aVUzX6YkaBd&zYBk;n{{!o3-16hhH=;VnC;<4K1si)C$L;x9sI5^Q2HTW!_2zAx zHH0GmvMt>o+u~45J%mjUY}5FxMS>|dOq6m5bw58ld@{v9 zYb!d^Z*6%Pww{{IlMbT54Gq~)^an0x#M}AOIzBTdW5T=ag!=a`bBlWT65gW_iwJ2L z8|-mUTU9_5KvQ|E=NOQiXT3%atn^7!Q+heeLi_ZKD~!TTN36?{arpbahOC&qut#no z49_E0gugivgpw5Lo=gfkUl%95P%eAQh`OG+st*sm@lo=}dI^qrzXQ1cQJh)3NefgH z^tL%VK#ah7{@XqKdLbEYFllexU1xauJs4)f2A|;!Q?^>~0AgiH$bNhGddsaGo1Az^ zI~1V)_=b&)!XNQ37C+m4pn0-@HM;SbZGrDRy9SZd53^s+`qMS0j5baZmQ>4YJVPEl zoN~yi;g!gb>A*m5QcK9o<|)@8q@2}iP#_U+rSE^ixwJz}eU5V!3rC!z=!E$ycuxCd zgdZ-`@|rGBtBlD}IG^Ib&V_7?zu&$1OpCL#eAhQoY9YLra~K}`dO*_qe60C!2YR_s^G%zx5Z^{BNVef8-y>)dUA!L%?~LXAuE213W1|EJoapzm$NAvgETASPaCU!edJ?%m z+chtkd>NKei}Ab}EO$SL3gz0qUrya9!n*^~yeNQyqZj84lVseADDV`5s!RI-_S%%G0-ot14-bU zv1Sm*06a20A#BhYLMZao5AcV*(=Q%i zZxQk;#_CcaCi4=X*JU}@{g(fpTcFM-=UFVq3H(CWMM#gEg}uT3U0%erY#fX>hU@A= zcbv74+%jlZ#dcr@$$Q$2WO;tT_hBz;kW?@Szk96C$NuiMBCo!hy9-O`>#vWfER*B0 zI0VV>pRLp@e14Q`A#MxcxkQo^G~`0ZjAuyPo6c}E(j_Y{hne5$gmQTefB=9Lqt}yU z4-}xq*eNj;9K(=F0aLCMy$I3$dBqJ*g*g6l#JJZJnzf0O8<@FA5uCy=I{L_0eZly-JL4UKX-%GBx#u#ngHgujDlopKpbtPWK5~OOAjI;mBIOBFQSX z+l?63l*{*h$4F`&VW@RJZd5e?@Dd!RVXG3Jz>MV$N0IkHQB(y{43lfk1Gw{Zt-WUe zdDL2k0o1mQUv13WOBwjW!6xLrc{-5OdbijZs7l}5{CIz7UbrqIhcXySA zO6NrN2KcWJx!0BpLhgaNV>nXyi?o2<_}675Y! zjSut@$XK1hQ0%L-7LW4GPOm(ex<_faP)mNjRb7A6ODEEL^CjlS&FxnaI8^DD>y;TO z%4l73Vwim|;d6mSUN7#wVjRz;joSma7Q?LZ9;1X-kJm>i*YoG%f;iv-;()AcmJx}9 z^&>v+&g~OdTM*4b+jm*Z*5oR=RdsUAG=tm2!1EzL*A`8su32IUNq1Z^a;f_&2JZ}mqIKJ` zvyQ^a4q}{iTP50WP1^z$SM~|s@;~UJ&Op+7MgW=?_7?Z2P&nac+`oL`R)lSxa`nVH zuY=2>tm>|+E{n2G+IAeu4h?8C_?LG0afiwlybvERjUna)9q@Ku`%-=7`*#@=#4^GG z67F*ZDDQ?F8A!H11nL&dCNQwx+g1Q73Vh6n1Ry=AP8sLQz%gsWlUIfJ0Xh8MgK=Z{ zdvR_&PrL*@8J`--k25T&^hY2>AP2${>Z=#H*M!U-60mCw5f7)FQJC}izHSiiSKa)2?u+k7NdpS{=j|9$=nK@0M2m&8bB0x27l{86wzD1LQ0^4`anDX(%pqBZ;#lX*f?)mlQTVjPHhrF2y#QfwA(0hvQZD8 z6L5e7O@h{wET@aIQ`HH_&UY!DeWPj_S>kv(c#7{4>R>I z6X1N1yv&b$tyr@%K?8Uv;oh?%s<|)(_r^c&z}q}Qi1vr~?NS{ba&rs=%{r=cvp@U6Vfg&fZH{HbYjqf!Oc7|HAr z%Ncd#Z$kCU7iz#&wdn%~h=@p*XbyzRztdJBC;JXq(PQ{R_;(j;bG{%i4XD5rV)HiD zRme+w^?U!}muJ5J#ek-skZ+u&%J23k&tDa>4ce4uj?dzk$bx)>k8qZTKoHk;3@NtZ z#!B%`f}5uvxWsG+rX`w}11FJGb64my-~pGonr!-#U6{cCn%?GL<)+D0fDZ2G(~o2M z_SKwdHbWO5=UOCGs-C(9znfF3BX{)36NUZ{4z24GC=@bTYWLW0fJSkq%?*mX4mrsi zV8Ju*-J|ox#$R+SUyz0JB!T%d%S%(MgoMup>`4SE4q&O$8FmcF12wfF{NQ@qF81b| z9z$tq?7V`Rb90$dnS-bRHO-&T&TGTcJpDtQ^CL$#qxAPqE)jE?%`ytS-m#N?b%$O( zEmxfUX?BH;KXhH903pD2sT>1D1#h-%jXZ(%41jhlU{AEaTtU1Ee{!Ik9H8-@e}1w0 z=AZogW))~j-vBFr?fH>I3y0_#Y^ANR&{H#vGM5HyGsuzL>*(;#2GE2MBpkqiC<|9#Zy=QMUk-h@A|PgT9&#TBGPHQYDNh><5eVDC zZ!g=dUlRJ@e)Ni7HT}%%&rLHi)|5A0(twjaxfL)ACil4e0OS0@&(uG9XWDY&dl+J% zrpLPLNWJuZ$$I6SCD$W9sT??8CVaX-xiA6%%IT$<_ti)Wp=i0orw+Q>6A`Vh~4k&!3QX!7}hgp4^g`(%_xg) zDAmRkOZjg9Y;%o=MHt_0^@;QPmc#6G-5*r+O zpNV_)YTY1IdYEb|M25R$aPOeix&sjOun{=SZE6SCuRny{->^8S9dIJ`Np6mEqnE#I zv2oa95K&75)s?H{IFLI;p^h&Bep>pbm*|5NJo~?AzUjcR0w+i+!DY5|43jC0kEi1~ zc+GxD6lucr%f})u4s~B zC{+PQ%P;SNO>4ZY90|Pf87>bm9PaU%Wi#V`F}s3yV3^m$evI7aOKZHQNJsqebVWG0 zCSluE$%XL?q>Z}|NGb+KP??RD?(8TJ6kvnrV-HF9^tXqUM=pFpMU=clKdXn6p7X$L z6ckI`4!b}^IT;?9!?tVE6d)4P)lmoW4Q}R-({PFY!X6uF#sW5#qAnoI|KTM*(fO}0 z@GMKV@_`VxW|3p&5wE$^-6F1s&jjoB0{dk;cg8#JVeMLWt+TnxATCvP{_D5Tzc`Kg zkB@QA3E(ec(K(&)W?zDeeLQk9}+7(XVa>E+{fsAZ-B)E z`*v_$=W}}4;oBwCQ+f(?E%y+g4)@%DSh`*V7@wDGCwhNrDmM>)`32ga66XQ$DtC#2 zZZGSUB~#XZYuuU{>4#An-49zglQUz{c0Gjv0bdDh(KWCQyqOUoKJY=I`jGS#BIYNIez-EMvj1+~oIfUkjg)%m6#u0YPl$fpU@w79{DNbL@TX_WPaf zgI#X*@Od?v^F3AVWA6RRRl%vNJhRgGzwA(RU`=-=O^Z|j(bDQ1c({Kj=k7&f6o9P$ zm5bF|3pO7(8h$zOu4YLv*?ihc@*PL;J(mVJd;D1(2MDeoJq}6iwR-FJg8-+E zkdO0AZ!guq&P4=%%e;W*2(TMCpg&(IMF*E6#K}A(!_fBcwc9JOsehdt_P}@GY&!cF z(didiKZCwYsDt%0lFxp2*g9}=ux{dwJN3k)^u&A6a!_T!f;L*Oe%#1*Q9;AZ*@gr~ zboIB)7b7vS`w$yc zKWu+?iOvK5W>1Nj6AMaqGpR%D7wN;P{oMJWNbnB< z+N8|)Jt|q3W*~HyYtE-MC{jx}{7e^tvxoN^Lq-E!(C$#NuLNXm7*!1_=qHqzxbY`C z`04ql^Sylh!@j=X)k9ac+-5no8OFfR=S)nJX)(^VK5%k7y4~EIcd2 za8Q@}a0AFsXD8}0^8Gg1S0Qjce_*5HEjYLc{oxQF4pTcS?%LTM%*iRWRlCQUK5m_J zgLEqd-s(a86=Plv;IoeVytXM|>$DH?D9erqkCnX2fF{ki1aVsj=jnK7uV0>{&ld15 z!vpLAyj8>vl!yiS4&-ciDf)9H<|naYW-wfQ{Oi0{ZU)kDP~PacRbn1NxOMQa2R|Y- z4~Jwfu+|+{d785r@)=N?1_}Na*PB;_0PgE#sgwb_)`3h196&;P4rrQoBHVyVl|qK} z0SbOr6ekQ2SslVJrvyBaM%i*jPWUMmqmXQFU)1iyvgn{U9-j$BOuj_3S4a1hMDak+ z!1-xZc#ovVR{|CwowYXr|H7y5J{I|6IS!@;6w7O{%KGsjA(u?@R=R<|T-&b7teW9A zI?8luP92Qao4)59(Di~wxHLMe1S%6T3It?(42t@nNS8gl0fwqtXbz}QP;j*Bv%w@| zH@wFc&aB6%)5Qe6L~mxmNr}?i^-mRRR8}cpF3g1Ez_67o$YntmNP{LVgnuwiXRxt&!K7;v5ca9RfOF&M-@~b+qe-6k`s2 z*mYsiOZwyr1e8QyXxRdu>2tdN!J5zaEC5aB`YTa+oKzlkbFR}AISWNvfrcXsz}{p% zwFtogcRX%yTvxAW3|=API1X`-swsvVL1qiDdDtSbo*TpMIm*`FpgFj~T!0;UQ6}&> zP^9IYQ!N|JaQei*;uH;&9PzwY4KB|La0o){rvWvG({(N^_0gdolU%0~-X?W#L11Kn| zxr5>iC$fi46p3!z@46I46_j~V5s2kd`q5!nWkTuatfZl&Xyw0yiPizNVvwIXzOn}l zt9zsxEhWZ%h<}O~W`GwOWZzl)>)n!UYJLuQd(0edB}&&Yxox#2#p- zqv*wOlHEVFI<4Tfv;HlqQf`SBoTZ(!rxNNWfRx}4zu_|=8yxK7#VX$w)izRA>Ci|yk^brP9eAio;?(<;>=9s}C_96+^!}7vDk8WjK|{b!x`e*o9jm7h zcK~+*c+T>G{m-0E>}1L4(#0fJ@Z?J-TW3eJT-SoL|xN{3@OpL77fS zm>WTwklVg4hX(iUy2TjCd-58wiD}ab!B-!HzV|MAPP2Rxw)jl4X9^S9Pm}bR7_-1{ z+-gXb5nP}PV`gkDxj>a~qFV+E-%C)o7JYH9gffB}2oAR7{Le`S9kF|YGDUjD8wzFZ zn<+lf(Y4UdZ6a2FU@~Z%ucC#b)Q*O=jB?STbO%l5e?a@Y_9<#DU(hpupMekhlX|sK z1{`A|a_Kn=z0%hsyeUX1QvheNzWYzs2}D}%ho=ZlaZ z$|rp#cCUq(<_($KyKx{+knuh*0oKTO*}6WKi-Fgb17HAOOA3@4Bn%LB2q=PaR)=~% zdV9Mv2&u#A^@?)uSd{T_L(?^KL4F-NuTcddBh7^)o~%A$z=a8#aSw~bfG?U*h&os# z4A*&v+D3QUzuLJOBv{@R@YeI=rP{9>4SKFdc{Wjfc4jL<<*{(yu0TzPw(QUvuvKuH zgU>STW%FDhvGq967rne^*4Iw!Sw{@J1unx+7em^k7Zgj5eZMZA3!3yR=&rvMipmm2 z27rglt#fFf2XIuRS_4Qtn}CVGFfS|dyACzJe3~*}8|qTw$vJK=4m(XV=?985YF)pB zrrMSl3oLC||kBm@iy(b51DiOMch zIaeSSdR)NKh7UMTOb&o)zAUB*F*G}AG!j0b!dIyA5X=LRt20pp9zTHwJK&53i}=OS zo!ZIU7jyN_FCS|9q?bo27#+Qmj$Q><1WXt;rV@4vD>QjpU_Wf8IbR~>A@QPS?Vehm zoAfz4>kV6}2m~^k!D=YQ`Vc=J*x0!_@T+^|pNg)F5jvX2K{`nl`}vf3{OrrzKJr># z=)@y8krJD{sdw(nQqTk-+IIKT@5!tP=D}M-9{BE4@gV=yyLrTz`uhpw@7xBtb~Xnf z>QN}Hcw_`*QTv#@Fc+R@z2SfA@!paLRht8-son4nx&%Q%W;!t3L z=xSI&Fa+B0K}QkW;sC5cz30Po`uM;EzP?6Vs5ymu)GrpNfA$@zQz)4sC@@|Fa%kUyYT#oHIGWHRwJdXv&5f@)YBO{(in=Xao|Q7S{7~o^U+`LXKRZ>>X-D z0RN}AyP{yVWI=8QoE~Qtc(|v)5z`z;FU}tydWo)Q+3dryHK&p8 zT~Tz)*XawTJkl^;TK!?6_gJD{!ld*aLi zR4p6%qQ(9`$fxnO?70a?@@hs`%7|Vj9>E>}&Mj~cZomQElX$k(d$<+|!uemQt+?bq zR8e93vLYyiG@*~B%&}Ja+!TByzEr)0^ge$IS4z_OU!{KEMd`8sUOb4|ExNrAho*|wG zUSa0U-r0OMPY~D!V>|xI6$LZOEfHb*0v*37d*ZWAyg-wS;tBPBrzm6bk8Yt*myZCH z^#aVOylNigzBx8J>6m#p|GNuZ!jgy%xfSSns;T)fMGjpVpg0CL{JjjJDmYrg`lAlCk9OWq+^E05_%r6Lt>Pe|IA*< z?>g>r9ozFkegpCRW-E}{tSE>CRXlmUZf66k4hL&}y7IJP zKlO3+>qxp^4t`)zaz#Mc5;b`_n7E?~KyyfNr&0&n6O!%?P>>)5j?usn%SxaNyFagl z@@D3EIW3BGOQ5xYhcIp*41qb92M5554z4;P2P{1~woo&(f^Gww@fiNS@6F^xiU%h3 z5$!h|!-LlcY37a95}0N*y|Y1+Y{0u{ml(0-3wkN>TsZe~z2cx*fqI+Pu~5JsPX=q; zph#-B$eCd&`ru`k4(dEybqDXp@R$BMA*l%(z-o$4hdvtaD{;ge$8$2RQOo%xbud5~ zA>S&H9H{pXuMfQ#We?0PJ^3|grna9;`VPb5Z%rY^3h3&Y`(5OpPN~qnq_zeJj4Hsa zG}Q_RZcT+vhb9230$0l2 zcFH|I_#W}=p4*d!u5SP&rWJibIpO5?TnYyx|J9z7As{#DR8`fC5d=ZfF%(Bi!A5_e zy@4Un-w}npz+PIqq44N;M)Y^c102J)2j9~uNq5ygpk)|;wPsEZb*K#1V7rZfZ9jBC zLIV(mWWR3$Zr zjQhTy%|j36;VnqONKhPOAc27Rj`^rR?&6}@b9mQ*cL;C_c(u=G+lGC-gC6TnlE_nM zu)k^USDk=(B9|?6u+w}yc_B&2=%Eaf;=!iEotG#LD(Vr$a;EQcOqH)wplQgbo z2>7664Z-J5)1b`wwryZo?Hm6FrAq)Ua^7v>%#uw!Q%E(=`YbEMQZ6<&fgbeWD`skS zG7yDDMGZb~w>T+>`z`9eMsq?;w34xKH~{r6Fd_R0Q^@z^Q!*wi1N zni>GrpRXY>9+dP2TP8f9I_b)gDElQ*@A2@o+<^WfbVo1k*lhvo^TBzn2WIhesDS;| zF+dQ}B3Rz2S-vNJJ9j}`w0DQN z?b;<_bZG7IiRT|SKPcHC`k~d;J`@n^;+CAQV3W-lgkWoARHjWx)SG*HyRYvk|1$RF z$I*pHEMcKsI2^793r>V*70s1T?aoSvG;54kod>sck)~n;c z$5+|}qNv$FZe27EyOMGn&{$9xcM;5@T)G5GI*BVp_wV2wWMQ&uvtj?m0TM&yumVLK z*iD+#Y+z%#Tuyqt({(#U!GY_I+WDhjdz|;6=6HUGM{S0q#!!Cpahq#pt} zfggD1aXqJeL6LunssarfI>0BJc5EP?bRE#K-e_ETQ!%xC7e!e`LjSL7texEM@8u;v)b9@KYaROd7u3QXb$rbE zBnQEfUtSuz+!-KQ-Oz=wmt1-Ez<{-7oGxD(~ z*!7>jq7e?ezC%4WG`GSzHp@5b*Y6;-;AeQ?!Lv>2#DEQPCCaW=p)()Ab&}nA=AiEH zsB8J7IpBvhp@`E7YVDi3M26du?H33@l3UH|hfbL0{4nG^*WEYJ5FxD2!JcY_Kr$!~ zN*?@Id1JACfWpb@?xj?E@L9>SZZ!KG!jbH(gBzAU_z>pY;WJD6xlB($r~!v~qM*h? zDGhQ(hz0x*gmM`&gNS|1p~sTyIu7)K&=kRd;tDJ`V4o-PJ9#bvpyFi(fEM_;NP7<= zQ)VUfp+Mf1Y>hXluTO7u=!~NZeV6cJm8US49^%7wel;QHw+(?49s)aMa&XWZ#8@ld zaS$#KmPe2=pCaFD0$pIgcs&~p|E#y)f#BnIo;HL(-WT-U? zMOT=LJ0iRi3W2^<&#Z<%Y4lNltSArcePJMLnVvYxzItYBD8Ph38zrODy~1s~f!<6Y z9ESOncsegN=&(=-su@BL$yUWV0J|=Hb8BgVRYvB++#1dK^bP4Z@(6AfK()PYMa;+F zJ@6@~6!aPpAB)C{y=4f9k9Y0tJ&Nl&2RI8spHBA#_C3_#>t&slAT@)&T<8M73PQG{ z?ix&b)}Zzie7GyS6I6d3T7vKWk>_o?%eQk9SII@nU2-w=rT=XHpL!-p!Le1de(weu zA&-6<95d!>-P7!a>F{NL{HvP1fsk6t zq59c-LYf>{8}JfFav=UD4i$Mbhz4Ao&acCj_jn=+ni4Q+$D$oehlX`Bh&&$AS$#rc90tk&EwUhy8av;<^RZ%x%Ga!7{K~ySy9F`yCqvQ@>FyCW zcTkcIXNydLqZRml7%)~l3TA2fL_xo~3kk}2xRLvDBg(3)d+;U!Fabkz?2lasTv`m6 zcgs6Jtr`e0-k5jvJT!ar8MH=KE%muPuF0Na5(|nSAIsI<3MOei`g2|F2zXW#a7;-^ zZ12Jw&GS0t*jx4G!>_o&-#4%iz9m!+woupvI9w{a1Hkwm4t=OV%?~YAUg~+Wfy$Z& zAMP~>#PaPh)E&Q48{iey?U=Eui(eH&>8Jy$-;8KlP)5!MGrW;)4{FXB^yfB+U^ z5OG>9MS`v?Llond2ry@` zEu)V6I_DmEjIX{794$H4nnA3roa>+dgx8pE0$eI;4LpR}&|_Vp%GMHHwM@^~pDxIF z3J2x|!YvXsOiW+Zb2?OR((Cv`vm0&|O{xYRAqzSF2YTFG9>{@}Dc63IQuffkLH~d) z@sVX;zF+=Lzf~&qm@8jjb4_)zqohlzhJ(v@G_A^08v->blCdC6LEn@s8%+;=L7?Co z?4H=Mx6_?hZjiIUNq6+`Yke-Q>p|_D$tHo5b6Eew^mOB=NxR!nDZ^#sHkhE$HG<&E zRnSCDfZXc;q3z9fUDdWG-3Q`=y1KNDF{ZY`Hs+4f6<}%uPk(|j_y1?6bk0#qsnpim zTAE8^Oq-(j)?17Cf{Bl^aGU=8FWYhtr^iM&_ucE4f^lI7iZCut*gWh#d^4sl_{zne zo^a~s8?nOrV?F+TX5IYnx)bb{n{uay4M+fdaQ>40w#d(%#NVQOL zp5n7hAl!UoUfNNk-#CLpUpgw*9<9jZv#|s!6z_O%|J}#a#y@Pt>`AxxJMPCrU-e=U zWKmCH_{h^t8z?W_`QDHz4^88(I0q(r{jk&SAklLF=}9;IWA)D2_UD$y$DO0U=<5D{ zXIH+`;m?8fbIILu?T-lS=e_MBr|NdXld@*w^EH(V3r!gJ}zA;&wO7(BXGcFNHKzBT&CyXQyjbw|adaXZewhjynwsddW%8r4`<@}u|`N-Fpv*%tW#1Xg0xiz_K<1ZiPX(Ij0g(BEN$h0 zCM{|>2ppM%avm>W^t^N)HE@lyd}?CN8EJGC;GbWl&n3yID}FY*Xj=8$fd4eT*#PIu z95xH_Wr}C?$%JrtT{cc;o+txdLSdbcAC~6ac+i?0G%EHqK&Gtq-T*2AVMYv3Vt7A{ zKjr&>fg8F*Es(XCp^!KAngaZcuS5*kule%{3e})uX*w(k7g_}qT3-QvyGro)wq`vJ z=idrYs++fTqA#1@r#)-pfzE5uKYsaU&ehM2k|=2I9=iV?NW%U9_W%t;6h%~+jtm>a z>wLSS7XN)wo6H;`O+8=q>cOg6|1yM-=S zJCH4&%M!Ngyw0!&{pmKsUwORmxaj5d?x_J_QVeu1TD1WZdML)|387luU@0*9I%?Vk zBX~S7X?pPH<}8`e##jo!4%z;9SyqPt?JSMtPbArsBqO7Dct!7!zG9%&msKQ#)!JL6 zwG z4>|sCk3^oq1jN^KyYd~-;k{c;{{DISn^(8*os<%vJ0}9+QvowViyvi?fn!i=@$o*| zQ5w8F=;MQ%Gt9XqKvyCZPD;;2ndIN?>|EFan#9IP$~=XS$4(1?Kc){Wx*9iOg`5Gr z4S%$3m4k&<<}=5G!)HjXgH}-{`r^xNOHZf}10Z{OAy_k&f=6WUND?K9?G|4JscrDvdZ2vwmbY|9gVZZ$y1OAzjY8d zEDcUMSs_dLp>phda>3O2e%T%GSLGv2pbQRPCybvPYk%TX~;dzJWZq*WHqlnLt$SUegI(5OQ#aZ!ldF^AC zU);!rQHuUY%2~!h=J0a#{cGWN}rUBO_lSd?)4OnL^xVa8`brp=) zn3G)}U5z=5`NWVRsap9@_ytSkVZlHnPiuUXkw(LsCIMK?K;2`R8~PKv5Fh`TjQPJ_ zw|Q+SZ?}4qHX~@kCYj;9Dnkph@C`3eyLk(nz+}AH``EsuMAiW1)A!J00XAH__hE#8 z=`?@)xtsp=zLY+Gh{-2T|L=K|B#DAI$(;lpv%--4V+{Vy*o+<>mu5iCZyX58J1Oy3 zJH6`f(mhVHxg$#Gt$&BoOaYnf@yR=g80_Ku z2eY0ne9QdVuC1m%kY?SlLeoU~93Uxr$a~!js&ZHPwsqbb<4&l;Iu~U3d4ctsm8XB& zOQ3n77X2w>D?_V*A=v;POG!0hs{rhOJhQh?ea+!z`qgn3iufI|z&q!9t5TsM90uckA8n4vJ+p z(rG7i9NpZwFeyIT3FnG^r4BQ6xhH~ON?U{XP%HLaR>G+Uch=XgYSQYlbJywKB=<)ybq1UEoOqWtOXxF@07P##!P zS3G}02<*-j4iT8U7@hnvJdWE{907d$X_Zf=;uCy{9sMld<;+?wk0zSD`i)l&^cs zW~;?jX^Z#vZ@!=!fBJWhdB~icKCE5C&ZyNRoQY2icdvln=jCSzF5DKqdvX0$_wB6t zBg|KQeOVHmAp%|b@sqc5XeyuH_CYQ}KcImb*8SpM-)OIRotdxuua}xH;;DbqJoz5*?W87-m5l!yGhq$wzS135z!iu@(&CPQNi1v6rK&m9@6Ue ze2qE?^4Irq8O7DpE_mzNYa1)NoMS`3ec&GpUdB127A3>p#D9J)xJ!>i@CE*0q*_cck40Yya}aWey07(B_nXKBuF*>YmjNHK;zQ z0Ik%GwWW9@U8byaSNiLV7(V|v-ni6|^6Zp)N>j(5 z#T&|2m$3Ae>vVLDS6SICM4T6GeAw;)VM8thSClC10x)x_+?RjzA zQI%Gf19Y9szjsYt`Dq&{=$`RNK_+OuYnk`mRF;`>Y`6%9rx0kw(Mkb$Wm+jJr-xo5$-$qaNswky3*d9DUzLU z`)DYqYr8(vhpPWV9c2H|A8;}k{eg!rQk-qqGM60<^_+1yA0NB}(LOm7gg{6B*T;ZB zZLxL1X zE?ng9&HizUDm^+m#+i(W5D+13mox$yiL4R0(za$3J zrE9~>Ljc;qUG?vOUKVJ}R}I9x{fG*CZNRrZ|IN7OU)PJ+8yx4NY7G@?k**)AIB!#yG1 zj|-G-`~-Tthndw^pTXMagA}fb4ydvh^G^q|DgUlJ1oim{NFBHrMpv^!wDKC!Q)WDA zf~{laPAxZ9j^32`Z|&NB+|{yREG*Y=C-$VfZ^V{5#-|xLUffLTfV3SrXddesG1~?x4 zZWavGu@dO>?}<*PKQmQBJ#nTfHPOpy=-K+4`FgR#4DXEhDB%mYfV-6cxYEbWr=Q%v zdyF3K8^@%-`D2TH?hgJ(SPQi`~-0bLN}G8tqXfEerbst}TuJcBStN2;$=7zqOk=jJ!&V1mM8cfb$pJ!6DSOWM5r;i zt@{o<&hkF^ZDBvlM;9%bOYd>mljv*ki^Aq))XC832e@EQf6u4iD&=~1InLU;1__e? zE($Jk+EH}R$;>>^xM;{t3mu&P4q@e=*IN0gd=Q+J{WLAV}?(MIcPNO5SE2Gb@ zQ9`mNb0f36;5DZoxE=rF&BL`t^C-Fkp>vH9dz2Oz+KIj%u-l&p8QLygAm zR}a-TtfOvh?9A1Bk%MaC)QQ8k%(n0c*X$`XMe!c=`hS0S7vFt*4SEbN;gwyvSKq## zZTvN1SBqx-Eq=Vh*g>|;>+^X4oE_i8MlXi25b8B_Fzr6OQ65vhl78!)V6FdGJ|~`sNstrF zX&3+#HZ3?pfz9knJNfl=G#eX8ovj-S_Llm>dTL?*Q)B-7L)H6mZ*#Nl--dOZ&zDTj z<2O-bHXa6B)GkiB)-Dg6kdU==>bwM=PYC&Jn;eqwF6o1?cw?@rv{x4FqeJKY^K%_{ z6g-aVXFNOr{2_>{e&2{%Fol&RiTVg!Hop*QwG$-(&%f=o1>DB} z_%QMJq|Eg_f)y(BhXou4hN0KJN@4KL74R{}u|ngw^7(D-f*Oe9Y5(en*OWICu;RQ4 z>nXJo9tH9`+1s^ALuG8G#^})hb2D)ikJ__YX!`73$@?|5sz&ckp6zJ4?N@Y9AEeix|)< z%$tXLJGkRAWcbK|C^O#35}nDeI@rf?y_Z0ZaLleE#@`uxH4dTmd06*#)X_!mnzoq< zo&y=DCHHqOUEp&X);yG1eL=ZeVXi@?rSRQG3A92gv!spinQZ(=JZJnD&!xH1L>diW zC{8V`#SRrYkra+oFCJK6bgD%kDWOulkPZWmmkUyZA@o2!LgFo-C zvU{&NWK!@<&~@*rwx$K~ETAWou3D}LU`}A71QAphHh}Kr21tFOqqpj!DV=6S&Jvf5 zme7q8hhG@y4E z-JwTFJ|A~iZzq6kXU&60ki;CLxBP{ri!Con`#rc(zHdDy1?O3*lYkI1-vN4GzY|1- zW&makD0oq7m4DislO#!&a-2kjqeTeaB1t;Hn89SHtqY5;vO;8h%y7^YrT+9Yq($$j zEr@;m1K~6)Q z3`9A5;{*?r^LhH0k+%9Z24BN}nfVJnz`diP%QgTJeKA_-BCZ8VNOexbpX@e>VGBZ& zqE#CkSp=c^5jwu-_D|!$vmEv6l*U>HkpxQD@OozEls_U8&Zd)bO z+zWypYPSNv8hk+rq&MYFZ6#YEb5S~Mf6z!qH(ZRRl1OA&fW8{9oICVOSDzm$ucAJq zKv3Q@yF)*HXDXI?mI*diIaZZWV=r`=SynDE{)8W z!b$GO7we7J_9?K?dToy0zS;9)K4;4Eeq(ioC2azGE7yLFT}9%J0R?x}!AtWO+@YlJ z<=@<1Yn!6Ca7Ef3MXboQBE{MC;*d9(CbEQr+~C`xQ){y9rz&*fr%Bi0z(E$n$L}Jg z7BVxe|Jf^;EM!`n=Wx_x+@Agz=Nzl)p!Sz+h{S|3OJ0>+6|#M)`V4+dQ>x8V<>#`f z`(*wF9%XI=aaKV-gWk}sO!ZjbEG3tQJ7}W(SKL-;!co*Z01dYh(nj=>xPuV}5pLb>{MtR|w`Nu0r-b=@ z?bXL~uWr88@{IDddR_y2Tl>fkxjE2-if9NdH;?5P$UdjT^RoB17clz7OI7EvIS?A$ z?b8o46t@xLgJ-pk4{+#p-7jGcD$YzQKFC(*8&`NBk;OGgL3CgIr(68p1W^CPW(niD zp(}UA%O9zoOcP|MygqTQv2W0%IPw2<1|ooY*q6xTDf(eR;!Y6;!m3HJZ=paG{u<6F zckl|p>}m=0By$q%ROm&EVea2C-@N*lTDZXHki3i=_qCxrZ9%-7&HXsRYBY~mk1BJY zdG^imCRIFWKZ7B#qjLfg6YVg-b_e5J+r2`kGbW~qUmzo)h?;~E8Pf9$9wAIg9f24J zx$MVhnW)SgabIK5h2%G5bPIQR{~Z75;|cwYj8DY1pOQU5(w44*ol5^RCvujt`@v+5 zmiznRkN=%xBEv{b{)gQ*`oA9xphH}QptU)L=fP9lw9sfD5S5DA7cAnqLu)3-t>vZR z%!{I_)^GNtbhb2t6>&nQ$83PxH_aRib9|_F%PeH?+HKKyMtE;tsha~t*qdji!~f~* zJL{)zrbF+h;GF7urnqHN13A*j*7FMGOvQzOeIIkg(NKpt_L_|Z=V{Y` zh7$y-?tLf5UJ@4lM2P=I_Dz0;m5oOXmoZVSs_O06=E(U0N+BiTN3AtlK|ON zS4+dIsZlR7QCG<-iMFd}fV*f&@|yt9Y4b3=ne?*we{TlEzWYA7Gs?Tn9=p((uyDzV z=u@Q!(;c@AU=|rj$PIIg{&Gr{wclO#7R^b#)~r0fQmR;eT-WXN+wHbE0mt9>s->G- zBNaY1QaPcHePnPbJr4q(8J_|igH#9isGEt%K;3yX*B+he)4v|))*|bw*Dd&vG+3fD zbFT!R?T345BYEjave9dE>f#U1W;^e%|F&c3bTfTP4!)I3{1Tz^VKPWYXa*8yU0ONC zawd_CL|`bj_V~5+Tz;$iF*<%qAv;vpV&(dTTi)FXT0Dx!l_`6YJ12E&Hj~@Ve0*?C zPb&-Nhz>eL(9CR;hXVqvqOb?6{-5~lrNmwN(CB9ZbwN% zm+I5azJUufL)n-n@OS*|#}gBDsx6QqN_1=H2eNn02M!BS6$M*(9{cUuqVukRfiubX zbcc?86Tf#B99+ohQa*|P7RY^i!+!aubk&CsRVX<4EylRy1STht)Nsh-45!ph%($Y1 zUW24YBQz>OwGc1rWw?hry{tXN$M(E9n;G>?MVwUML+M@f0hs39Pdkj>=(3YyGC#6O zR}Cgs+Xc#JV|Y0S5?M{)2&{hiZzG$*3w*o?z0=EcDAv|qTexu)%RQ~VNl@uUp`Gc zB~f%+nPJPC9ck-3K`sEJ6+bQZ^5%W*nn(Qb&)~li1dqzfc?ufzq=MYFS!!f>e~L3Mw9cvOz;D_G9(B`6zyovHTK$n;Wz^W%+9U|Yc`#9U`o zr)?cOO}aOx?Bazw0k(%)BL)|}(<6MoEIRUsyU~MP*5puwl!mWG@%eRFe>albzab`!`7aAvYuf4@8G%yt_KVyWZeAa!yfz(=(Whw#cb@w>)A(sk0;|i7!xO&OC)Pe zlDxd>jCFS+XyoXTRo}+nSe1{X{Pw=(n7Ii#bhxjFzXwq%6w5wY+xM9rY{=LBH|hW| zh2ksq-al%|KA|zVMNSX#rQb%gL=}BQvA&Za6yA1 zA>Qjc)*^kc_zC%%(_mul(boqoMWu6)H|;IQY+^z#kv^~a2%p^z^FI81-Slhb(Kl~=$VwO9@a652fZ8G=wxL` zNjobm?Qf3`a2jDCj5yo%=WpxJkD?^gdGlIZ_^+kD0iOMJz*0H-HlX&Kex0rIj|qIp z-@8Sc;mx29l+s`p?Ax@MevkjzJDg=K$6$}^S|3V#IsfTf(eK314lC0XMz}r;c&s@N z*ayi*sW2&;WD(~ixy2*P8NePZ!`e@$V7Wo93m!3kc72}De?Lp;fkSaMbm@PYNj@a7m;Ot=orCtd zpS8>9yZcxnyrbOM&x1!ZN2Eb%Pf0vp|DRw<^?bi z*Jt-|n%1Saa8YwUBlXB0u7tSemrO^m?i`BVJT&`uE($>f)1mG$YJqoTXfMR!fT+x_ zpr`Kz&Ix$&0f9!*AqQ;vMn)egJ@!I=NKbhX7e}Rb^#^(w{MwYGUNsmm`-PF)&&r)O zPA?;J(|Ee+kZe1?B69=HNX#jmadN3C3sGYYJW8iPAU{2%a0~NcFpC~WG>IP2r=tR{ z6AjmX9&Ky?QB4=Eh_khw{NQ%m^8FnTFJ^v6@JIJno{xz{Mo0^vOXw23><(Ki!^r)W z1z1TyPMB`|^=89-*}il!Up4gOSf>epBp758&w(;guQmlX*t~*id&&B6oJ15(tRK9? z6f?OG_^|QG`bs^)d^U}?kK6=V6>EJ2t^FGd`v;+|EkxV!qpv~@`7T50dK|H)9lItX zGY>w^b#}X}o(dJytR3Tbq?*Zh<40BpWS9Z^vU@v=EPp&czC|E>W@WAZ#QJq6#|uaZ zFv{;X+P`@gz_P#b5@3$%!7Eclo#-2@F8;3S35tRN4!MvV-^K)HbCf$7l!}GRM&A^} z$P{1UfiuqE{N(6vUz&hnwHA@#`f-5D%BaIf`B=z}9qoh#*NR0#XZv%i8`WRnRYgC# z`C=A}vF?RJ4tKq!T$%K~0ID}FYNLXI%A|#EVf*k_p0Di4HmuJ9)@SJDlxz%HE}+Zsbp4cy$BY&L?Z%%is}?{YxR@T+_vB_wGb_g*O#KJ3MVO;gBZvE8 zeb!>**wloaf$N^^!S#5I*8!HR^_qB!fqF4JKaXHoFBU(?3-InhMv~2$kL$0O>4@23 zZ8oS0g8HaGW)`qF-ZdjnaV9##_=pVRZ{9up zgN7oaIdE*$Jn3-#R8JT`Ga{HIg1-SDO$&1}+63TZ0lH_oZjH=ib5d8Ht$i$?1W7g1 z&o(%JgZ&gZD9ul~wvT+ufd1*xx~!NWiW)kr$wTZA8u=`vZsE1-O%T zh?=v}dkLEAGnlU1o|v`}ggEg3{BY|zi5PHCuF)915_$mw+kDKtkW{Ee84)ZNV``Q^ zUvU__W_(-wjz=RxE?J%-bt0R;X(q0$YBUeos4B}Nd|p;HE>pW zBPb%aw7BpC`%6zO3`dDd|i*^Zr=E zScfg9UcHNiWQgHBTHKlwN25*w1F5z+8|M-T=yt2mNP+SnMK(P$Y4SSBu14?v^itdI zaz+0XnX5~2g*Q8Ydg^bCm7!i|@nAY7@{a=N^P!YRJd$~HM6Q~rrnd-AfbTjly6dvk zQe8eAJVxzAfS?StZ;2{zGtrOth{E7dd?Z*f5EO&B%OJq0*i4eTfo^qX{xlUGc&Yac z(Pv;N;Lp7$9OyMU{>`zZNA_>;GdJfSeoLXgZgnO(?;s-Az2XW7FgEZr7&#g|2NZM< zVOvbTi4GR6SJ_t+XRmbx;;Z9&+&A3@d0W!%5-a4X0Z|LHRSvlhzk$eCpEnp20O+4? zFgDQ1svY4^@TtnhF>)%_xizdr0 z8EL;cOkRP8DZ1zmfKcIx$V5*hqZ}%B_$k8ReBa!UK;U@bBWjJ|oxX=7VH2Vi1b$P> zj-c!i3^oKb(>_k+aA2b72}##(56pV|NQO$c$15*`!LIovn$+wV@qn<&dX?X#@2Ee( z9bS(j_vs1#1q6d{Xaf)ss(c0Oo4hSN;zSJZ{#{pjzr9nV&ce;-Mpt9 zN>-vGh3u|M0g%`)#27di;v4RqYSHM=&|<7}$9YLamqsbKyU*>JtgJNp;A#(;ga2`d zUo@%}mLJ@=8y%Ax%%ru~g1O~Q0NNo9j)G#+jBs2C@{JOv?XZ-mH9RAKLd(+hwx>PN zDRAil?PwazEqVjZ^mB{ore>WI5Wm|88F+69G>CDV%S5>{C;sZ6{o}dT6CN~V)V5MN zJ_0{UzXYp&8F@b+Q(JXmb@d!@h99z)5aA~j=W0Rmy1e4{fjPp;WaeL&PNcV*&!#%H z?pJ4H`^LE;*-=*=YkVfUfiWK(@3LmD2@`_{8M-JD8j>wCP;s-_hqh{`B1R)#&_E)O z@@lX8xV6vlaG+&JTdLnrY2#m<>*`y=Y_UZC1luOT-#+7AFwGx#2!Z<^Xge+nge3p* z?AICJetTPcon#>8L9}lVumX5_JHi`}z$uA1cEjp>wlRnNto0zIjOIk82dqOD=9|a2mYtjmYMO9JFJIZ-uo&0s*a}0@$w|B4kLF7VQ%JQyUEJ7 zKG@1y7<#pFKOnYSdFUn682lZ47P32wyj=G1KA5cm6j5*`C4PUyv5W#cmwp~Lc&FuB z9QVUH(#+cvxaAs_HG>8OO}dmg_u|O_P+@v2$QnRdl4;OEffI;u$FN37F7{5nhX>aG zw$N2vt7|xR0PW@8m6Tstm?&k1m||YM&SX6au)W6y_1xNXy3Z4IF~IyR%}27R)CEiY zKiA_r#LF53Y5!?xcHq8hG8vEqWooy-YxdYB+x5()9#)T0mc8~9Q?XC(@x3M*7E}8* z4AyQn0@Y_w5uqIY9qg+@inPCGr{Xy?!Q=lsGJeVBn@Ty(Zd>mht3fk`bB@4+`Z!{J z1KG(+f~G`9>fOX^BThn^Qxi-II9Ecm_S>y%|I3aR%r(^FiJm#Kr&S3$tK9{`Zn}=_ zK={%yPJt2W0^JX^KO`}5gXq8SQIH}~c+39GzJce{I|%UPk&cF0O+1v_=Wx9bhUp+d zPuV#34=fvayLL@~yEcf}T0EDP$zF_y2=r8Zp^bCKb-ld2KaP9_k9AVjmh0>COg;%< zT)l&he$eOd3=qUobFMU#Y7rRlQLuK6c&5N|LokB<1D|R^SnY4nkO8pnq0X8y#uEEA z3xi4U4uZv{%&cEbC=+y-W#sFf2{z8gUbRWhwh92wv9KN$XQXyH2U;S2YewqNg9jYK zmB2)tl-WR2Z?f~b?GOQoth@OEsqg~`Mn$W9ZfSI6Js=TMHju~4$C?=L_#@7&gug)# z6)6VGZnmWa?74v^e?SgkPk|ru|IGiG*%^cY?RE9kzre#kS)s{5ls0C$cul&vtmt2L z#5}*GR;}0%o@8hvSTiCq?kS5;bLz9Dze}i3qQqwqopir*Bt!*SMt#90Y+hBx^3lpF z1d$X7%15G&xv*lK8UwD@3-Vv06MT=&XU(J$xV@%5p9_nkaBRS(09fq0{4$@s^w3kF z?j3rkLe4ZJ1P#s(+7lYl%cg{WL|OH;^bs2NP#ev>6M9GDIPm(Y@1g(sn8zXzUFSux zAHc)|ijo$F)m!5N&~{|{HNtFK7LMWbA$KZ7n1w5iv!B1J*W>uaMt$DSg}COjK}I>S z{p)5?-yY%K)q?CBnxZHMD0z&iY{~m5nm`_)6QTds5R_Z|Moq3fw4Zx;7YEcV7YxRB z2AA(-IhL`#iX*iA4f<34W3BN<7#z00i;n2|p*kiAHuI$+Fy;K#UNJK_<(@$(2nKo$ zm!L-@$!XGkV1=2G5}J<1?DJ$G_NyQPj??K0Fb+Ak7cAnZZ!9jeWJSt8yasd$#~o3x z`cY&IdMlgj#fO*34p8ODJ+YuF#6xNcS&E5o-(FDls(tJbEx)q(dd&9UEe5*a6EEg< z=;`i{{Xvtxo}erXzYa0Kw@PT-Z#T6jc41f)NUpG!mjfvhiSB>DqJn*BGcjXc(teb(Pu`0hKd zjXi>=7b)doYamiVyu5OM)o%&6NdiBa1~q_IcYGEkBoF_E3|*h#>H42r?IB93rQfR-CB z6j7Y2KIv=LmE?BHuCf`|CKJZK8;U`B$Y0tA8rzRk8w-e70?S$h`R)-tz)sL|cx?j8 z&{EiZP$9CX(h(dM|K?CwVw651ouJ3bh~TuYM--`gCbyR5F!=X?>9;M8WntfcmYJ;8 zdp|E4?{yr%+5{skGz{=s<$-{h$(z&3q)mA0rcnzWXlKMo1_QyB0wBRFH(1D-EoGrc zS&lKeq!g(++J^Tr@5zYqyL)xPU9xz`CBczKeW9t_>2dAy5gB|#+i4R$y$^609@PEg zFPo$u8Mp#q!!yq%a?(1>d{P;M=cmL#`1-IkJuBx!_P;zU|KD?co^T|I&cO#so3r`8 zI%_}F0F}QHa?R@y?7Iwd*bvE8(2u%NqeVUM~7)k*W#*o<#5}90FDLFM^9T6ibQb zJ`?pJyMWxa4e!M99^!;a$H81BFu3^Z4=yCc5GooFayncd@bWV-swxxR=Z5}hGz5+T8xy;0MF2~l|^5Go92gmF0JzkzGRPRNe zu*mjASjC!EnFRE-o?9N^Y)Im0k(9!+tYQE0fD-Jj*|PIbf^k6TeMT;8V6CS7eck$kgjh69QqY0E^*H9Q08gBB5 z)`sb0Z8@b2F%K&NzBF#UzSg+CR!CWDpx~gS;Q? z=U_nn53X`G7X@|y$%i{2H0>8C;c(T>ZeJE~oKK5D?s*IK8c=rbvv{pa>#n{&4`xlB z<4fl)wbT@dyo%{-U8*3KF=sZqY)|%mwL^qDI0^5it)v>G)i(@-#^bjL!F4BfRep*} zhJgg}A+5RbkHay(wat7(WZ0j7#3U#IKxO#&F`^O==xHfOqn*WVt6$c6DonL{tV3y0 zBNq5w@hN)H@5AMel(M1eHHmrYVKMrzNXW0O9gZoDbGmxv^dFLm*DRtsXZ!u&fz>_$ zc)<_+n$s2H!M!6U>DFfc4f`Uy>z{G&1no_1G3GpUr}4P&ddGg$zcs_`%2jdAMK~m^ zUMcIlg-5cL9tAqTUg5F&G0TAwOF`Mf^{?0KUzF8|9{=WbhHo8Qy%N>@^0mPO`?9Jj zysgUs7xW;oAfiCd9s;g1W&6Ylb@V0;F&A&;>TzvMIqF^yBQ`MqgtpSRU5~)5mX68; z|Alk_y>7gW)H{byaMceyym=NcJ8jJ)U;C!F&blOUP^b#D4ojML)C}&}<-7l~Z3U#r z02_~hp)JlVfB7Hy+KHPoNMTO=}z{imXke!kwU+oV@m=q0CG0Xf`R)GV3~R3RWIO!2dU99tsK%pNecjCEGq6^yWT&5 zDehF`U|@9YQ2cd|0wG(6qXRFQeLsJVrvYY8Z?p&wWFU>2#|yMOc>t@HekhWxm5{v- z(goDaBi*VPTxDWQ3`#Ua-)@G)HJgR1$%17rFu_R5xkh*b7&k|_*T&<~Qcr~n|7j^B z+cJfRBwBNq)FXI@E5vB0(8pfoE`@-zhj zz>DUsg2aq_lfoYKsuc=@;8C4;?G<54vh@}MZIkQ<_`*6qyg8E_By{aI5FGyXGHd0A zOT7Efd_=DZ3U(7Ge=7)dEfu_IN;V>--|uoZ@d@6Z&|e$aKBbU$o3M&5Q2y6 ze*!!xRS?sPMlqW%V~&F;gOexp55}fnHBAtIr!2C!S4P9Cy#kB7r9UNXxc~G^+kM_PXki`G`((2~6&Znp9A$vApzMv^XH&W5U;#)UW11=Mb^uyG1pVqOz zN6l!en+^>S%!9>Ra6ZIeuf^`xZ$i;accPva$-a6$8%b4;!5+Q`HsXlDj5%nS;G?gA ze`HKCavJyfc*GFe#NQLI50br&T-byKMV3#jteo!w$+6#6FNO2G(#_~^!oRa? z!@xH6OF4?5BUzv$8|YC&lVWY030}V#cu|>1=|%KO|H!fC7e)*4C$AK8+Scpp-(l#W z-{(tHsrns(*pl2k!gF-R;zFry27Ko3o?TWS$L2RysDDUbVJE@YG5M3P|MAfM`G0ay zXlL{=cf$|z^cEjdaB^6!p`y}z@l6J{tXq0=HCGtvrM6+wd9 zH#rRmwQ_-Q8J?s8tx+JlyKfD#1jU4po4n3-m=ZJ0-3Kx6-*%pKWF~y!u)5l7y@eiA zv17uEaKt{_0t<{DGIzLXBio}7)$UlCdqfaNV}_&L$_{$vn+O@VoFQ}LhGVsyW6rQE zhoapI{`Mk{PE*4*8hT(r*6-e9gbCMw)xy;}1md!R5pgpRzgTIE2bTY6xc$4fir-gL zR_3B$F(c)J$>(Ql_8i-fU>61S%zB@`EWkoL^awBf(?~%(h>TUC_s-)%tSZP37$y+AyK{sP-5d5S>T*7?u419V4OL>-yqZ{S)PCA zdH{o^0sK2|zgW4Owa0w{;3C-EeqN?k*+&=ffzhWn*ear{@#Yf6v(I9|*e!TtU6`R> z=NvF8Mfq}-esKd6~7zhF`#hCUA| zy(egNnilmX`R?}gf$spXx#B+XCcYszz za&$8U^UyT3NIa0(I9GloA#T|6#ghwZHi^*ya#oC{MU$j`J^FIaoYI^PNGAAAS-w#V zb@2iW4ha24yGDW?PW4+Fp0`DS%^eXxsm@|Ie6ga49D4A^$vPiJ+2FB14N|Y{P>B#& z+BNuXvLK6B283>vr@!yu$k=ThB#;pxqHFaHk(vgGyi&wd2x8#?Q?pb zD4+zPZCJ+BK~7g)t?34D2H8X}^5V$R#bf*u6ZAdC4j%}qx$u#ZAqgJB8IZ>_Qk@AY z=KtjbeAJZ{{Za}EIu|izc~U)Jq3TB94jaA=bSEyRzB%ts-`(Ck?K?y5x3|and;!Z9 zp7yU9(HP{X2R1>fRD?b>mN**r`4$=wwfVd*M)@^OL)9+keRn&#$GjtEf^eY`wPkDY zX3t0YUU0$Ibw{9-lf}`>yh;*D;-`J0Nl{9QPWU}}fjgQ+$jmu=XSbe85t`1hD{FO< z=nbHxaoM@!an9noQ8x%V)V~<2{wK6nUAQHU%mK>;LL7Qn)Njhy*RGlpRJQv@1ng$4$M7A zM4?Q7R63rg&Pd-|2_H-*D&rY1%fL5%eV~Ws$O(NvgugEo8d26J=!xHd`R9=|Cp0Od zP-C+Cjc!rh-G9m6a*g-)N8ot#J(I^abNAzILLg_y*u|VeraALyl1XQO`OwzsLCO>L zJ~H7md{_^0DCJku3HCe^T69{lEbK#Vp zM1WbvQbp_o9q04}-6J}dx*v^e$?9R|W~XP{`w$f6I|e~-FT2ai>3j^3!UC}`=}e{m zp~g)X$anIIoJ#E$Tkndzin|_)O8p$?asy@B`RH@Ww+c^QJnh|Nv!&BJ+c|;Zy+ujb zS;~cq*{}MDZll}dcwecszldZRm2cS5p9giS z0)r8*PA)U7N;Al&1|auxmDL2rHz>w$%GvSyE8{PQc-wF7h7<4L zYi+s9EH17k!AhTL@Dq0T>e4yQ*g_F&< z=lpK0Q3gmXz5=XYh46&V>G$2*PwowG&<>GqfFN52GP%UFRtks#+SA(0%#JW&-)z(F ze{cAaKEmVYLgMp|n+N`a)+h3Id)}P)K6w0iKV(`WU*-jZtl~>w4)boVd3mI)_W8(G zo{~IF7bIia=>X8oJ-F`EPwKbvU=mR*1{GdM9%m)V?A|Ja5ZZ&nafNOv&F}P%i!Z4z z?)CkdUY=$L2|=<3d7zX0`q?2k0jXh5EzyXebEEg)eOZ5Z&!P9!7+i9e7?r}ap?f-Qd)A-W&H5QhmxYRZ?r_BG zf$+LPr87!bbS6@|5eT|tucSr1DK*@R@>n6;##W5xsNsS#UxTK14v06=4IPK~6)~!( z3(-ZI6ejTM?%9F&Ly=+2wj6~I63S@XeR`)1SvS9zczg3OCrP~rXz28cRhZZ;{$;+7 zPwqQI5d5r87)_4$lZ2z44K<5zZ$k}r<}rXzgVIGt*an?2LA-<^`Br>c6%+5Ok3(UW za&n(g^}|#R73=3R3oyqUaz-MJV{@f-VcS}W!I>a0e?^7J6H7RhH3%`X{c_Jtl&Zj3 z?Sp8($JXWvEaK_4iEy>|&#)Va_aQ%)c4rH%MwuUx z9hJ+o+Cl5M+tF9ftA50MiO?Jul}UOutmunMn`|mtNoDfPeH@ud_ud;-K$o1D`ytqr z{m91Oy=0yG6JN6NP6}_AK;lD$PVNN6IYLaFKkuWPy`K78lACV08_40qWx^#fc~$?ZzPVvkta;%o%VEh4j(`v98IbzF8K<1{*zh zRBCuX(L%}cuZMtob5J)>VmmyUftsGE%o&NjT>ETNje2cFFLOaqQ!ATv+vcjr+Sb&* z0_AjUt%58GvO_gCn$derktzZt}zgw4Iy5(|~7onO~yyI9va0c*$3 z**VYwa8Y^M%}bKq3D$8z2EOLXVUowGr$6vxw90%`)7M>cWVhW@SwSW7{CzzvK0Gf+ z|X3+$cYM1 zPPs%!u{dn22k$zMN5Q`IAvFvMacp@UWhMLJUwH2zEi7Nkvd4b8XVhoaU>_%$Z`z(; z@lOo79aMYAFP_cki(vUtDd^|#bz-RylzihGFfR|2aS7S0PC*T?Pv1J2{CYw7)Kgft z&Wqj(yWyK%PBuhBWx&b5&(j7yjy{I-9Tksz4kiGBH|^t({tkm;46`b6=FRH*}QPI3~jJI0^ z3FFFoTV##F`Y?-*O)0DaI!IUUMJ;l7(A z;XF57W9(j=g+4Cu-go;Yt$SuM4|5>J=1SdesIid{@#Rbzs=tQ1_vAt-;#y5r;QOk!u&2+L(1X!esAWF#VUAVZq{&k-CxJ- zXo5iye%bkTkiWQ28LWc`PQ4|m!GwJ}4^Rbmpqjp3tx;;#H#Ey>dV-HFxu={Xw*L=% zZ}Ka{-h8wCTFX zKFG?ji*u~)_$<(68@B^22|9b=jOMzeM3h%{!&G1UqK}$+0TXwD*uyCmWwPB`x*a$C z!Nhw~C~77H#s|IoF}_rAE%K^37gEmMO{KVc)ua~ftHs#WC7~Cc(=mN;Op{x{MDU4x z@zW;`%F6}@X8kjL9fj0>#dV#pKJ%kylJ;aOI zLK%|M72a&-ZS^PTqSZP$o{G$Izs^ay!Agl0Kh-dcCCQ;k+zX)P5gM@^(2l4Y8x-Q@ z`F<<)UfYSMW-FVhl4}L1v<0(UNO$z`p`c4GX?-WRRsFp9W+8~jBlGBx*Sm^_$ge)@ zaE%oMw?C6U^~K&R^J7om!lx@fAbO;)4KB+p&5-VsCFdUUUADirdcc{aXQ3v1SKQ8%-ct2t%D}!#f&=-cROU#YNBtxl&xChm}y4y z!o0ob)#IKSnjuW1HvzIHi}A3hf}}r%piJ2|&<}gC7Zd0GdMJW{Zh-8%CeZ@MnxM;& z$A^Y2`QGG`yU+z$L$+RR2*qvWg!p_U75_t%BEGcN2?A&D-NV>iCf>Hd7SiMMc)g@NjjHQ6;u9WLUU zB)S)uuW5{jdwaHvgz<*Udb#zk*sN?WvC#*!Ju{tvIqwGGq;&gCD>-^xcI&=j7N;wj zjV`*UBvObuG~!)_*xc0b9v~viOAc9bYcNeM!320Ar*Tb->%4t4FKS~ky=^Pj=V&LG zPtz*&L0o0sJ@IDV7SXjJ~col_- zmoqq&nn4A2P@4xoysu09(qfYoqF$)V(Ma*xb?3p@W_ja6>$6@*8FR9=XlA2T$G&6i zaiol8;Z~H?7e%a1;1uxDA5kgIKQ?$;aJJb6jeGmh)^O2XfA)Z%bv=A4pVt=wIr8vT zhyv%#^vd{hUoQ~z!jY0q5D$Ldqq^Oj>1j6$DVigO)zx&gbZbEZf9;;cfu!W4JRwvs z%02aBE&_pbT}oFHZiCzgEr~O?o3t%_LnK7&_)y;A^>j-Ml1$H|m@u~O*WdQt0@}7r z?+EiR=(gX|Si&A5QVKRrSvyt4MoI&HTOHYq(1W{nIBeS^quZaO>Xsl!K{LC#ZAY8| z2(W~%P|K*x?3c2BFvOr>q|cGrs2YUI#5!u!xW6$7e| z!&sw_+aWi`8l2e83bBepyrTO_A32zbBv^kQFZt}#Hj?{;ab~{7TLC0@?OnSS=-Yh-e+n>#qTSptMF4w+myAez zR3agtBM;-WLt_iBadicoiB1&KzT$T8=Sdl%7Flgfdb{wD?xJAC+eTjx2;1CjWe17A zkzX(jPY$mtcyX9*P<OY1EhYz zjMs=bm&lH~FGP+EzwtH4njW9rgTq(mzU((V!@bcpdO*&J@FpfKU!!@WpH0OMUk{#? zq$2yav!rm0O{t7?RTCXkN$L8H64q6thV&E?$78t=TshfR(&7_0CkKGi>ZhC5!zJXy zn(;QAx&kuq9qzS2wKv9gDR?IH_1fnO8a)^;-^HUGowyn)vxV_E4_5L_(rTnWISKW? z^ywC3OIeZA?qs!db*N$!oV(LDN}1^1LDS*aD`UxJ`~7y6aeqtQV2x$94CW|3zL&#m2zJ<8Q0vVA+=?<5OOj&nT6P() zHXXd&e7g!A>b3XQqFKt2g1X$$1@1zaW&6woT;2x)*r2eTSDR9;fj+-`F?x#PYbyZj zPGB(wm1Hp=7uFi%`hE|9*jd8s(&eWLy-yIV8y0k5wmB7K@`%h($r`<4dJ#rS-K@fD zS=iY#%#;mR-wZO$D{mTSy7_he8B}NCb$`8|^5PZg0OZ}o<@=R->|)u%DB5Fs!@b&P z?sk1oV?PBiG^<7J zz4YE^?7OXTK$FnjJdRvy>JHROA#B3}I;}3tx4T@vAfzf4gQrSes6mZ)UY~g@UTqK) zM_OS5H6m4_EhpVf0YPHi$m%L8Oicl9Q@z5JgazrhHS;hhb;(xo^mu4g@?zcYDbG73 zch{k%&D=%xwZghA^tYPiBk%HH0lCo9p!gzv#=w!1VwG)Vdk*O^E&Lg9+I-l*AN3}% zcE~5~OnJnvN`Bh()=J2$U0>J7sH3l~%08LA^C?(+SzSS@i@imRd-VCO9O_W4L^ETp z>j~B^_6hytKHShsAn803UQ^C7GWh&J2Qhy-sdDT(hkAmG&;4UvQ+`5%oGkatd{yVp zGDWT7`HqA6dXJKzPVX0|59fCh7OApl_3b_*ZlK%X{gKVJkc zc}(dw;;i!RqRg?S^4q(xU;vmA!RfFC0pfBzfBl_@W(f;T1axQve><*s3_tmsJG#}a zHwPLxMAq#>pTh?|11cuxuW^3V0Fwpffk_i%D=2Cchp+PCU3(BflefD~& zvlQx-Kfa!Bq_M`)mrx_YR2By^MMFn%n^J$oK9s&7BzalFOZjfp{DN(Q8dGu6-0Ray;%4}?FHe19muw>y=00(`)Re%MGhB^ z%dC=mB;0-o0>m3fvggG@R{@rL%_Bt6a6;-RWwZWREC|sJ2(@+oUfo=!n&DTF!k_j~ zSt!ce@(ld5Mv&B+E~WTlqf{c_8hzP-mEFczaw_Xq~ciO=|=QSF7 z@#3uG*Q=rA>l%B!Ttk~PSVR}8AED&uD{To&B!wU59!_G`C7O_YGiqj%*6C12($0*o zXCrx>^+Uc|lot1ZHTa

@F!>aM8~%1I7#8fG&2;?3F5Aj>HAg#>7pb}0&ayI>Zcbcg!b+er)DFVk@|UJ6CaWb3eTz)TAdK0tgg4Zt{tjr*y{JaT9;}KeS*kGr*W@O>g}c$r^$?nxuu^Z ziDgO;f+u}(@m8PCNnG-3Mn%)Y+py=;9{X6Eixhxsr56$vpLmqiXSzhkb*?v&Hi3 z1iEWBy0RVBTJNUxv)-!vHCN0aX+7+sI{M41Y;r%fm<9 z*lu2(=DwXLnnhs9AmAo@2KfWYse9HSQKJB1vYdQ-6=n=}riu0RHUbDG^p3e_O3IE4 zF3{jwX*7e*xv+Id>Fk)RO}p?WdlRJSW@w5FTEMUBx_k~dbK~U*t#3f$@MAms1!QN% z&O}5R9c!1m(v-Y9`!eolFrQGjy1w``l95jZ5-egIQcL9^B;e=1goHMoTOGHJ2RPIE z#s@SWC+X?wP2pBdFI2p5v3W&pRek&KoOEG&e_GEEI;Th{tZgc`Se9OW2rI%~1K+K< z$M%(4v(ux4hL5t=qHbK`11un~{fn}>Eqj)B~B`k>89=spC9MOHlZMM#clomU!@8GQveOu>H+z2yP8+SykRqVyltbD`* z_0-S=4~PIJ)xNkd9|7`p?O}d!a<(~>##M%=g9FL7OGWz3L4n_g$;cccIq}8z2R2ThtxU095+%P3iY-4CYuMZ`XC+ zv?`>n-#&C(H;PfF+~-oQXD)V@qFANdS0o<`9}4rzNe;OWpN+@)sIOnT-7tdXKpLyS zrRVkvv_nCPXl5JXNm+wG6nt2#%}q>ZfHn83_L);xD&|uk?z{+A0C+4_zyX4_-@BcS zp7)+*{EKJo@9<>$_Q5XN8bB~Il1irIfScGq;Dzhi7IY^kH*d!G!Ch8dK6QtKmX z{)`Y!SCxs|mM7iY@nr292$-_kZKXRH>eqtl&|+t_kB5Mb{R?DSsouEMLNqVZdUb)E zCz=8*Am)L*GF%2c@Yl;@?{c~n1k?ZiYRT+jD+ja3~*otn^Px)vt{q|Q7ObjEv zTplF2+<4n+6G)Gvtiqh*PPmVdMoOVMn2;d&@6^a%Ak$h49gI1lUf*6xD002HQ8&0o z@d4P{LP!*8hHz09nO>VwHK=K>*8rcAZoqvknE?z{*r7CJe#W>fRv-SI8?r)@s*9Mv zXrFzn^J7dy)Qbe`F$dr8?(o{`9I~klloAhNk9l|cEc1eZSZy{zh$j2v`3kebb4SI7 zlrMw#MeQ<`%!97SwM#t z!M3CidIxT)zP~sC#sYJfOpH7H=?>;Q5Q%LY8qkD$?a}5r;GGPRd7l#Z|QX z7Mh|K+u5d^u8$EjK+40%ka$tDZbXr)Y5bbxoWtF|w!75}k(dHMM{y4D^7@@J9s(QO zT>}a}kWt}#-n}2M>q^*SOcVN3k_!Z9)A6d-HgSDr+6lb%PDxT|A;kN1J$J{=x$I$H zB)|;XZykX2#->r$zJk@~c$MQ?5Eyi7Zy`d6*%Ra_Td}^v;xX(Q=;jD|Y)(my1R5^Q zV*bDutDKE<=qOt8DN9p_(QpB&l!e`K>xnua%gl!7+b7(z7K=L+NZS_VV}KgBi@m0a zLV4J1ZsxUwQsdK#O_q3pXUX)OpcnRgdb){&TtUJHPR!UeD8` zMWN`w49;}2M{64&SR4r|M{jYogJIP9y>(zQ^RW7??@|@y9=d6Re-X}2U z`>#+VS>z>K=!k|M?sq^F4#V(x0{YE`AD!ygc?h>c+O(fJjON;MlLjm^U}{-En8dg= zj$?Z8Y>UzmQbz5j%3FP_>kA}%(iZbBoK{cI=jO4&nC1Kvw-7$&zUehply*>u1;>T(! z(!0kFX2IK@R-PN`5DR=9jSuwSiEnIOu!{iKm2eD%dS&h?6J~8j!M3FsA=$lXJQXYv zH3|tDuygJLF=(5P^8z#3GXJarpYxd26gFQg+*|qf>FD(e^;vHgCUpj4naBL8J*cIw z_95KY`{x4h`oTr?BALN*V9f0(VLJ#01GUQF7nV>*$hZNXEwT)}(|M-UeSzMOkFPjU z<|#S>#F0b#b>27hCc zMo{Pmue7wi(7ooF-Iygx21MFJTPp8AdmlytsJAjeYFA9efyk-I#ry0d_QcIBPaX9L zJc~rLSdA|4jvmp?~wEpQi+U`8N%XQCgUmE91E zWlf7F^m6ty^u2oQwUl4Bv}n3ceI!rP_Oov`*{3H<246~OTEp4meCNRkgWx4Ex2{MF zgL(Y;2Rpz-c_jwg`SJ;y1yNgXXD^PQ^^yThC`lN>07Low!qUIPy*Xf4p76zI%~^|I z#14adi3A)juD0WPSQoeuzHT9eO){h;gO&VL}b{hacYIaUr3{_S^Gz#noiK z)_^__P;zs37k&t7O>L>5)9CwW4o6ukh5Z42qWD!~RUvU0V;v8ys<9=+1GBxa(RZF= zr=S6!T5|DJcH;Sl(<>#wfJ`Mj=- zm@IQX&X?|!aLL%g9S}Q+fqcZG*=u}8-KPi2x9Ycq8q09W(Z?Df-y!O0jT8!|*D#d9 zoeNyVTA(k$4hplb~WURN;brPwBH-9^x{qnRG(>CByx=<&XIrG}8H4 zn0~)_I>GQlC1tlhyUWuGju5i_VpIwJT0~Q1Bpqfigj6-+2YnBFTsewinLXo#ksLUe z3M0ag+h%)4S>C5La4YF_g~J70g<(Wf_{TDNEVKv_Iwqzm4)#>ZXN6wKVusjuYCU!_EvKluKIqL-+Xx;n%t)! z@nCY>olBzjv^ijbIF#`)`)7wuyjny0^MY%YjBJNg8uea+4^h4D91YF>JUH)KyuR-p zTVl@LTJ4{cMC#U`rG*O3ljD|!4hUHMd zL;5LtZ_vRTtl%oR6aAAOX?{orVk-*8y~edgYFB_R9@|s=4)jU7PAff^ImDhIo=4mp zMe_tAe5}`p{5X~HRm<}cW*5kV*{E0?QMjqWmMLIwy~doYZdR+arlVU>&KiCh0dg#1 zSaLves}8OwlH+eCsVp|y*omRm7pDH?0z}`9YUH!6LxP(J^MHQNH5&W(!)bFHi_aZ= zoRDYDeQXVAgv@uAH{fjw-zr?wPyPWg`FD5I(IB-k)jKu@@E`s(Cj=Vobav=I5B*Qw zGbs~zn4qU z#oz_QnaCq3xn$e&XUx4{35+EC=*oTW_yUAibBs>+$+$Ov6ofA&^>VjoH~CcV!nXsGq~ zbK)53_o{jyqWuo3%xZc3j1`8K5s5%op{m*y5T6wEhF527kxOdT27R#y#2}Wuu9hs9 zf9|nnrUdLkBAr?;2}PDEGy;oD+Mkt%g-Os3xyAJZ3T*YWMIA54iF((eD;b%A(`)~=q(<%{@We(`60G%xI~EswX`?YF=E<#)rs z_iz2xUwr-ZcfTwC%fIo9U;I6Y2mkQTr1-D!z2d+AeEDxaU;ZoNZ9^ot=(e*WZt^B?=8C;$GhMM+ituAiFZyWjtV5s;7H zeUA4p;c+;g{V#lb5q~&dcE-7X&g`%Jo;vhj^6pFhczqerZah?9`p1{*@hHCp{g*yV zzC@U2lPc)*NB!j<^k}>O?(3ELhyPza_22mJ`(IrAub;F0)8c>r@np5^&$K_jPJeWT zG6R?Q-~BIsyu3f0*$@^1&h>|r`u5)as!0FB_loi--}3(CFa6>de+wsg#~Yb^J=rG6 z+b=JmCVqC>>7)G;R29BgVY2VOeEH>1F3Rt|U6e1s{SrR9{!#zt^Rr+5`Zp~GM*J)4 z*T4K*p9}l-=vfl<_n`Tb4t4bPdZz8;{-sNT@X^+v>)uq4|GSHh!vuAWAOH4?-3~Y& z9^K~kw}+2GH6-1ayzcV&+pp@LL(nF_?CS0}-~ZNM#X%qZ_AkEhfBxHXfBQM=ufKn5 z|NkrV8RtL0GCz)7jIKW|{!a|s|EIy4{WIA=Tg(`2#lMU%pPRA3-+1Ex@#A>M1o8Fe z{-c@UU%})4!px9-p8RLW|M-9Uap?d3?~j9_{~uu5`1#N;{-YniRs1LT=bvMu`*Ftm z&+(1l|4H&rB8>XqwMjQr{ddLx@Z}G);veSC;(z?fw}1c3K6&>oOd|P^t;cP{Q2)L{{4QIepoKmSMiicpfMAKC=?bXd;(E*$bICW@h% z`lS8c_oqv|(8xivzoW?I@0P!5>f3kSPha;>&-Pb8Ki$9ix261sqkjQ=J^8X+^5k2f zc+3@j_J#WLxfFlryWjscSW7~&`8lrlzdZl)FLGzCn=kSt-{AEJrwZ$m?Ji)MtvGmV zu1;@AMe+9rSf?k2f2?%Rl-#{(ht!pfDG52+wdQ-~E0jetl&k!(zgAJLH6g{!3Jhpf z>vaqECK>HjPJuheQ>=GA6v}u#qiJa!{ER#1v`GVt9EC{ zWNICt4tmy>1hEp3^c^hCE>^GOt-sA1xiv`iio2~!wGOuXK`w$h$Sv1g1q*G7w@GVf zo_6MOi{4L;Wr%cNMCLN26tWqWCCY_+=F?R)@E?`C4!5m>uxpeOc0PLlcV~0;ZzU8a$KewX<+9O z>;c6AIF*t2Po5XxIDGc50!rPp^LDw3{b~t&ouc}q*N-BX3>Nbz|C1^f@B4^(uS~Kp zT=5wL4Gx=*P30>77(E-|{^Pa5b%JV4$sbKl7zIF64Y{#|5fEc~^pt8dV3$TAXVOxa zQ*}ArPKXo56LNX5LPEI$X^ju`^iHPg^QXtWgZjNyZIeVXK&NA?$Lj}}TZEo9&(57U z-f1ugRd^AKk@qdOSA; z_*JY*%I_|$kDtvZG!ZAyNYU+F(^q0wo-`*GeMnWR?7HA8HFP5R8FjA8VQ5LCPJ>I_CLI>#u^+8 z`AG6PQ-<~PahR;qYT0T}+j=_rXp^yGAa!|0>Hn!ML);T#86RHx=CJzy)0k^dTE*b;_)L!0u82XT2~cuZ<`cy-DK6&Ss?yZ!C3FbdIK zn13|JUw9#Ki4oFq@|T)5B?$=~9M_BViWK;eck*WKpkB4RCsnELem1uD)taCf5n*e;6Lfif*`3$BZ=V_J z9_!QM$7^(0WgFbA^7cIZ;d}adeSR~;eYA-($=E-hH-3IUoX(P9ZEVM{lIknwHZS#}+fL*z7|EM90G2W1-b3S`*h#NX&!Lh4MF!I58dt6Q^+P-c| zgH4`tevpxYvJVlmN8^DSdIMbcy?|ZdGczB{P2;RqofkeYXlvv033aL47WUWR4r@rW zi!wN6C?Y}T+#$=_QIUbF#Zn4Uhe!L~Fb76Jj3biLVpG$`%bF4mIJ6o>pkcm^S64>} z>(ce|G+Y5O<0Wh7@vTIFC=Ps3dk%Qk+jN&ky!&&Tc_+WxozUogIGWpN_RYwmNdsOH zBS5yWvgQx8I)b7BypdH5Bu<>z!zpK|s2%HX?)T=XlGm$OhSfRbfqFU*Pz%YZejq`2 z8?M{%`MkYBf05|tVomROiD3qM*sdGJld+rx0U%4e{Mx3e4|XHj93=0M7q|G8_AuGb zkAMC(a;Wyr_ z-1Dq=;)#zBV|)=m_Guy1K24Y<@M_UWsSw^Gd)cqNGq0mTef!cjUFg0Pz2D{>vd3Yy zx)xV8wim1%4NC2uZS-j3M#@oj<&*(Lpz9Sft0IEaBsecKOCy zyY_eo1U}usx7-8xdqV?A*^rh5?(Myy;fD&Rk=YUV*8O;b;G9}RK_1Jn+c~zE^Qm%? zmOa1v=M~oS+IZ}0I8XzWx+CgUd*>m%s?MNk=E^qLpSU^bOH6C)<7G<_ba!H9o+=}d<%ZECKizit1sm=98vQU!Y)1N%f7caOJ%$m-HC_&g51J!9F*RMWRSaF^4DOmlY+L(+rg=~02I z%ckGd0%@Zui>laVk#_D)TY}NOf>qZLmFSbW89QP$b+fsHA9!kx*E9ZfLFvP~a=EfEidxZQU|+sLnH-NK4=E)5}Gc!G0IJ zH-@KUvs|VH;mEoB3oVx!+YT04s(Gy~A4>=jB^0vWr)Gb+8fd+LfMwdD`%^~(eOVXT zg@T>8&@NMxAQle#rm}cL1~8$rsad0+eF1M1f|s6#YgMP`mi2FstHf|7=3XZn#Lqb_ z*I36zSY3{SbR+pk+hxa!JO}8FT?pn4n6D|Y(mQw_aqk^y=XLJy6ui|(mOYT6l|57r z_whSky6HjM!`4x1n0msra|fk@zA$ndZ=dXilq9^k6@B3e zVNIlj03pzVIQn%woz5rMCcRPBf-(-bIU$rpagaA~=_oz#8tLa#Vl$vXSwZcdfz>?F zX?|^vgpjf3^2Dya=K&U_^Wtok0Ec#LzVFA3<~9$$98VC&oXz+RmE_rpGp#P|b#~O+ z)`4v6<#l#&#%unHi=$@~k2w|BT@7r;!hLr(^K?&LOYR$e?z2&x=KNH_DT7XC2Ps*J zq}bP*3kCIRm@OLFPR3+9$(V`LM&8BU2)o&<#-P;8jOmTa7W%%lZ?8SKw5lGH=)2tH z3#vx5-t@R!oqXH%Z}#4yQadMTbgGKwBX!`R)=5Ipy_h|0BV9}HE=pvPQ+0FpH?*!` zWrk&@XY}Wwai{ww48@g1PwQSYLagBYgDcW)eztrL{>&F(ZeD9k6ND|^nb%dw4ztMJ z-F?+j@Nkmom&yD0-dgqS<5UnE^Q7&~YVVD^JDc@q=QJHi=5=ihe%>-AHc*>~x4!de zqdHrsOWB6lS&A7UoV_OuUh4?9=>1NDYK0QJWQ@^)r);2BW^eM1M+0>>VF(%C<6@rB zwVyt@L)Ou?hTgAn(45XX z+bWU7!?ot^F?o+x7EBMlF+yg0mi5t(LRSw8kXu9DBhwvy&OYXI+a6fedyM8fB^AQz zxkSedHgpBH&@gK_n@uA6`Dt0M?=O*;Re@j6385*XCXoCAh_Q7tjjN+X=gz9oCZ&FW z4s^Sw7vZ>igrA7`ywys%M0YLhRMRGA8E1(Q?^P6(I1t_fN?`-Q$N@sq^W}X+EtFm_ z=aBRFGjxIIkDQ_jKu{Gmy~pYSzq*q&G2O0SFrBMJ3mV8X#I0AY6{Kf#$sN=Vp|>z@ zuP`2{`O+BnZZ1EyKsXMXFX6H5-kj)l3q1v@=qo!Q!jiyU}{tmNpv~{kE^Cu|P9pF@e*D z*Zy27}CiTp_i^>R={lfp2%vg`*`xGSTVZv-ub{q8mu+>}p!=^}!+< zV)6ivvJyx`OQcsZ1}Cowm#=V{Zy<iK#K6P znRWUkjk{Y?Vv^Kv*b8U<{;@rw!bd6;dLEzBESvmI*h9P_4x~DV(2DoZn{sox*ExCU zYlzFY2use7>rsIV@gf68m|ho22V;!h@33om-Sf-RdyNM&k-Q5uy&?mtmq-ZuZOf25 z`8`S+AXNB?K-p*lE|U~ z<7=S_2NfLE^4X#-{>3g8s>ZZvN(tgidFf|{b$3eLxW@0N{dlVfMDJUEx;l|C(+k7j z+R%d>7k$3pU{Scz%p~6c?@N#5d?=i0HM%bkQ-Z229+PrpHxDf;6h~#)mYn3K7ku)@ z_9nKUG>WagMFps%Z{@|?5XLlhmHGw&YVce=u2xVA#xabgdu?tm79fYm2g%Oi3-(Lb z*THWd5BF8-(R=JR+$s{%-n27ye+%1VA~Q+CcuHWOemUIrFCvIysE1z3nK;WyyCwbxBZ)twEdn8t|KT7-7yHjh z+e&=gTi2}(vAIlOsaJPhd`~+~ceTu8@>3C6Y_dLV$oJaT!#R(n@U}psz_3<%mp&5Z zX0YI{BQ3->J4W#L^M$L}Fbb=!Qn3_LG{H9To0f?Vpuu&&ZOYB<;$H4k`SeW0eCQU~ zwP($hmzPSjI*_lB#pWW-CBkSuNo4Q(h;BYFFGT0pAI!fu!yya<}5vyeFJh3_pp*Qqc!OGI%fxjTs5l4 zoX+!9Ll+j&-N87qQI;Dl0!J$f4MS4snkwiZD6b8L>FkFc%r+G~+krt&1 znB^=Qa;jnR;Y2UEg<0}*><{FF=+7f@NLSCpxNBmy;}^B*GOMB3hR8{GPLiyj{A=5~ zhM@ANN&vNYe`CJpVu1vi6NNW@bb?=?Y3s65eT-wkJ3)~#;`Cr*oqTf_+OUQi>-K5C zofk9uL?YA(=2sE5ghvAz7%7RdL|a;)ub?KL7MFWQmhN##qXU6FyQ<0A#k9$(DA6@j z4Dc8r=(}z?{Z^^0WA$;dBaqA}YGl;=o0dlh8L+{1VetU3!VkJ`%e$1~@YsZ%%zoyi zTHjLI+mJ*nt$GF9K>t)A{WOX6rBngv$g=Qy7}kSy7VZ%xoZdY^1@WY4B#>7Rel-T+ z>kvN?_ZT<642z4>CHn;znud3Fz#ZrxgS6Hm{3BVN{T9@tg7zB<9v-g(MsAU_RKV}tc#}LbINzg z%p7*ui;z8|B8gX)yQd}P&uz1KIhKREhe#y`{8!m33eNY#7S3$ii)uIf73?{DG~}SE zPO8ycOEhn$GW?ROxQiS2J8+e5?BFIo&p)P98f{*W?fK-GNaQ6>_|$lq^+k+y<N1r7yDfa$#qmyKxAZ8|BgB>XR!& zGu-~l)R8rzl*g}jvc{cBH4WalE3GAXH-QQliF${0)b!-j$C{@Oi|1Nc?&11JSiIh; zEm9=b>Tx+c93u9@u{2CAW84%2uRE7a>&KiW*ifC%)Uh~IT%;NB5lUA`%9(ChtlP&z zJ<5CY(5k|8^EFjA%g3rSOm^YtU@n>Ib+cyBA$5b%G;WEWpLjKiO{z2UF;h+XA@h#F z@407!eP@a0Y*&TVgOgMq+{4bssuQH^)7zUul6A4}uP^fO_UUE3sqQ0g4f1gsETj*h z>$Hivm`4eVB;P_(f+ee{8z2;F;xa_u6)}~z1{i7IX)E9r&Ed76nUK55cDaU~6vRTU z-p9dJ6yCw7Mk3O-!bDp3@~-@}ifNNfPcUJ|e(LS-wrk`X?Gk&4n2zfZfR-8S>IqSH zjU;^vH;b)#Ju{$C4F@J#_$tX=@vhz;+{t6x; zbRo3rw7X3O zoOdj&<9Cl7CVZ4ghdlo=NmCuNDE!>e)0ft2~D}?4YAI5Q`v> zIh-Rwqe<}xVc^&3e}2Q{R@;nceR;FErzDn@f+pcU4Lk(R2Kw{qdOo$H?($wTzH7-i zPS==PtzGfrl|$J#RWAsq1%e+yHOA}MTxls7c*A~eYFQG&>aiASeg7JzjsD}6`9VQAq+hHk}?c-*+PO!E}dzIAm|Ls?eNNJoz_1vr;7 z6K{&XdEeu(qLa#eOxC&#_kd$#riJI>elT$x%M~L z0bk$E#YMd#qWGshTC;Ltwra`p_QEYF66*46m!BH+iJs`NbI(bjF2t)yko$Ss#O)cX zKE2+pg9ktm&?7XSwraN6*sy#!;vId{OK9q5wxyS)Xr$epHun9SDnjC|FT8?t=_w_q zUVjAg11-I^ZFl7Qa)LkNMqF-(1nx}}HMzT>L_4=OgDArSjlM>PHPn+bzFk|IazgJ} zZ1}#Z4eiM?#l$Sx$Jo5_e?6%0fjci-aOQoJu4-1Tvt?X_iRJ?f=TQ}piX}iJ&{8Zk z?@8=oNtJ$OB*c)&%+iD0Y)heu;dpw_UKAZ7Z+3h6+U2?QHHn3z!iqnq>h?t={N=ay_Teo^y#zbcMoDk%PGXnE#1>8I>CR5t{CPU=_4DoNOe}jI9Bw;+ z)=A#P@l2m-ec(^x>DHt0ZRW$}VQmtG*4e3nZ5P`IySL~1g}L<3x4;mkS{i8*k(huj z!R2_7V_tuDyLNtG-HEG2aeGI;oiI@o3$lVImvOV_U=YGS$Lj-W;6)HOx<{lkOeb3M zR!Xh7Jv7oSQGx%5PEL!_RpLMMDqQ*oy~-l+D^DD?Ag(|gwRTP&1b*1>U(A3!@+N{& zFl>c42KZ_K0CEC=NTeRaqi|Y1oP#S*k?lRe(3w>f-yb}-0w>2x;OvcdOd43Wc_lpV zJe6t{LDP=ChGMzY-?Mx)4+;!Lh<(CD2`OHY0l&WU@4HaucABV{PnP` zdB^R1<*^O7<7F|uNA3X%RU&0tZP_df8ma9QHH7Pn)}i@; zsv1_|*w+CS(w)DJC$csW0tWjJERgc$*H_Iw6cu9(6_^RKEh7+WI~<}~WNW=xV-i`)+s#!|$qW3T## z+&%IaA;P4iNB95*gAlJcAACSsN{WQ^+UE_}0dF0&!-2%4dox5M8s{f$o0c3UXHsT4 z!mKW`8DgWX8;J*|H1d8u&icX%OODO~-ip&Ca$0w>cUX12En~wjKP8=dUrpKNE0d!m z;_aE#uX=rX`a%>O=`f`F#u}C4Z9h4$dM8l+@FW^q_V>#yvpU|PuF%$RQF!U7(32>@ z$@WKQ?}9eSq&`qAq*9dT5_f_EH#q%P5mj`}1}*Q;J7LM)rTNb2sd1h9-9_9Vt4Z8c z^!7cmfx{B{a@&oP-aDn?-2>w}?WI(P;;qC+aMv6tzJvjWQp#X_8}q_^mCOXwZUNL# zxPpg9n+C{)8PQU{>rA`yM*R}xWrhuoQ#t{mjUITKTB5UN2%SQM=oDsoX~_@>{OowGk^AMC_2Ylf8>OOJS}ct*G)*!od~&&D$eL66NGFy-m4ln{-kf;e&fj3S@N{}!ojKN zaWq~qZ5f|4qc5r+b6pv&=9M>J`q$FRk=2FFYVY5tO?2&T;$C!G3N%Zzo)-e^kGDOu zMl$-{Ru6>;UdLw?W^l?lMdS!T^_)S=B+6Yk%{!~KSmZHCC>Nb-i1$Xph9MetxqUU!DBKrahD%A^4<`}XJ}QmPBwLBA+UR@2Rt3>bMS$ql6~q;quYlhz{J7h-s8l9VI6^olEIj zRYY&W@aTvHH^jAxeCCpO8E18vQ(0Y5HySy-mye1pVcKY5F*lfNAu8=ku==oBfP%6W z6BF`tHcCu~y%R<$x9|57ehb!i()*%h1!Ba9`QWA46)H%t_>egS>gMR6OJ-&1I~^B!ROzzaL* z9x^mGh1pRk5YS5qZZagZT$=r8xj<}uA3#2t`S|3e95L{Aw%JC;eaXBkdLWL^ONfRa zaOD3l+Ww_MS#-_TMt=|uPI79hoD>D*EImL_0gY1|^C?-<8H;1eb;@ruRYWX;BblnzJP`{r0a!7|t0 zxthMPu!#>PfBxKf7nK$~w$mccce`GOZUo{edA`yxMm zl8rIKh5zBicP$V{5agR(`pN0YR`218p9Py|U$VIU8v%#}UnUn0V4Bd_Fj z_Ys#xUKezaiz$^~*DE-dP98%jwW53lHTFDW34WPK`HMk`yalY0KhD?-WZyuB(!LD! zX~AkZ38hcH>lZ=>VT8?-9EbAkvfe3=kOQ{5{eJufnw)RB6}uYA5nvBc&isZB*D66# z1<`V{+4K}&0*ejV5`4FI=bleL#5C{(J0aHeBrs{h3=z-O^4)ttvYJQjN&ooNge|xj zi8R5>SQA1hCu+bLNsGw1-xj6>ilB}7Mie36sQwm*gK@mgSP?wq{Wm$Q`2ooEaBuy0~?I9YHfHL^f`Lw!E<;;ld5y)=em@@2|r-{@~ljATju&q?*vo+zSZJjDG|r= zhrLbt_FBRNvX{-(iBW$=rn9x4Ia{U@`jGZD!KnZEx#OeO6qL|l39BJ5 zLQ`I~oz`B%lNhR9=ryir3q-+>+Lz;ov)H?RvSXP-KqA@iLY+Vl7NFGw&vG zhj3Sh0_QE}y1*XH$exx43*r9fGlWBsZ+}AXKS8G}Kchb01?V=j5L@K-?R4C~o@7xX zn!#{2(>rZE0Fm<$upYR!__Qc!&a=8-%~N`{Pv_#2Jhb-#k>5*lM)swRZ(ObxAj$de z&)x&`G%JR6;Ez;5Tb*Cv5RKPRPWArfLtwJ6U37EJ_*9+reIh@>0r2d`-q*!`I?2}! zkFI3Av2Kw1DMFCOO@HWx$tB7Mdw|m}zL#egQCS5i0?#oTSpoTnOh}`o_C|ov)&=-3 z!lM!Y*qd|Qv4;@_*Q9@3uv77O93XxuS$n^Hf3(zIC$=rBoOj*@= z$=wM@742awBk4=GS4n;xD|zxou?hpF99U|QO{g%-;*hOsPh-yPRG)zZ`epB zAwGK=$Ya8JQK!e_{3)-9ikzb>&KvUYGJX1GYJRVMoRA01EU~{F6`YN+^GdHcERcsg ze)!vX9bfMq)+sK$u#D-4eQg=&&!-UByx& z4tGX+b)7j(57sK5f^R_S5MP70N>bwez{uw(cQC*yCEb2_JZ?*uWq0oZIpOo3y+j+I zuR&K>i~)nbK4u)wZi+$1mSOp8A!BzR{d#J0u>6)y*II+@jb{TEVDR9)O7;7?V>5W; z5a(YtyHbWa&{g*K?wqTIM5!^%9|PDT=NY^7(j7iNf{sPN9q~LZdSS%LQ!3Rn1`+Mk zRp?{HV)u8&O>sEllQNeBDz!MAh7SP1P3-KITm_Wk`u_NHuighxXpWA?AZx|V<#Vc9 z&VC6ya(%_~ud5Q1I%XAiL9*C1x4wZg+d?v0aJVb0dM)==@i!e%z-tKagJ!w^qiYxWOs&&#&Ugbn_$;tPl zAMuH6YJ{@-LsYyl+S3@9`_lWIphU28-bdkM%~}gemC$|o!h_^n``<3;w$oom8xRqC^TNOIclGzY zkt~F)ag0&7GdNssR7@FIB-@_Ds6xaY`3E4+ZvZE&C=e$7VwiI&hAnaRvw7Mr`sm(i zo0|;&MmMQi+^6@jXx_(tiW#@^B1BW}JV3Fw7yw&zh4yVq7K2u5d1W~#9h~Gwbd&UW z5w=s9)#+0;(%S}5Tus%MJ~z;0ig)4be$DG#!1*hZ3$PV05>OyNatA`)Pope~t~@zJ zetdh2)ZF6Bi#@c^*0^`fFRbb7QIq9O5CZ2E-+cvKFkgd8#mIrD{dPHrWU8Rd5?VXk zyzVyBYnW9~4kzCOplP@Ne)()?|DGINu8A*XU&dt&S*WeWZ&riGQLYhpLD*As(md&} zGjN(6?T>$XWW2Y7eLRJYUxFNMaMJsuk+p)6I8Y+%pxX4fy8*D&DAqYTX&p`Hw@{{E7wfYj$+92(P3+Z^;Yk(Mu8jC=Igb(>j8*kMUUN6bSH!Hbdlo z(OgU9Pp9bqd0HA`nV0b|FSoqCTjB#rKN%jOj}NK&Q8FXhoE)#Wr)7dZLV^TwcwO-M z3wtiy^Aocp!S)3EXX~E+d&XNv(e`>Ojo+)*Y|fh+;ufz)=9RljtaWTx&C>X!V>_f& z3qPG^Es~zvwTBP3*j)Jtm{+>qZ1N>&!`vM89WdM9;Bs=6?XtTHo`dJBDZly}a4&AZ z5P&(UxDx&RWBbLQ#vsM(J!mQ9^=DcsUwx^YaV}*Y09{ZS;Mr2+DPSvczY)dchw*Pt zs6O_#?~FWSLd-bsNxj}TKT&aH5wctKt`z{wcDD1n zJzf<5+_c-bCZ^{pK8F1XMymR>l?7!aV)}lf>~osT6C4jCtKVzsmR~oN+l%j$Jxv6L z%{&K)oQ|C5V-Y`&D@~m0Czbo@@Yg|ioowl3BFudDyJt}V4M6{}mNnpffl?UwP%Wd-5FaJkQC!A3PJ$h_)(aNdOYFpk6XRe zi*?)`A-uDlYj#o?sWAD?z=qwEb%PV`qzDLMS@^(G+}W?UT36C zUn6q*2+_5Zb;p3xE*s?^2`x*l<4*Z9&M*6LF@c?WI5g1JZgEA3Rr?a2!zi#gVu5u8 zVQGQ%h&J!@D7yJ{=R2Xda*JL|4R`T@&})14Z&Em^xHibY-{K**F??-&FT^8eEY4#@ zsFD~lvYr<9XQ9B8`%974hk*WlE+kRjGhf(VUrcJ(IQ(TMcr1N6<%0CspW5ihU(e>H z;xOd}UcR0vRzBspvma9fnDF;#?g;MMyOoq_()}1QTKO&Xz3|-S9)+}>v5l?LsR2?! zx2m=zN9MxC77Rv@RCcEliXOeV`)JQk>7Lmu@HaQ<^EuEb{I{(5Z)u=fE81e2^jK_+ z;Hol`zCyXMpQ+|2$ve3svb*{WJ($uJAwkB7<#Ir2=@!mu@jf6X7l~2cGF_}H9AjS& zprQDQ)?|TrnlPxH$BQrKAy@F}*zTXccq}cFY!21&)f7>HBe1}&9I?unS1Ll59k`}#Yh!h)kx{zI+w_Ng)-0mhVk_vW3iwjrw%_T%u%-pu**KH4LpsklFK z69)9fk3vFBDiVE=!(SZd3OTww$tEtsJx?HV?snwEv%Wi%2u~pz%{v}rTrW4`X|2>7 zaa_u1b^+C*JaKu_oV`2OJq}-N{VZ(x7O-H+_?}oWU-bfB&%5#`6h}Sfq&2-A`+}R zN$bS}4XKYWOyF(pjvfqXtd3^W$xn|2(^^;U-3G4WEerNtQa5p(*wh+E<`{|fg=+$c zFvf@OM-Q|5-#rf{>d7COxMC_rQ|lb+sG$;XjCReGPw6|@;tq0D62nm5dYw}Tzi%bF z6+mMnWUm3o^4;(RO;3^XeI1on2Dlkl7Mlc{siy_)1qo`@!>Njv=753TLHIOh;oEpr zi9IA+Z5e7Sv^Hu34E19am6d9aN4Xay*ccTT@si>PC9#TO0*01 zLLAP`Zqf8T-aQO)6ncrcq|^9xIpSO(u`~a8chl*Hd)$KaJX^FvZ3dpbF9qIcCa;5p zi(Z)^PlOgsc!5Etjx1fl=-C7FQ8%W~k4^?cGf}BH=i9VRI=$-D=Xx|R) zuTCMmzH5s4k~WH&b^f_-TSAV*akIcdw#bvkgy5XV`C=LZ`N-!{CzXSSO_oj?O(`MC z*XLL4mdnQuQEJRvOS6}DRgN(ji>Bj-exk{irtrW2+CN{1HNpvBxBbW0z43L~zkVGv zJGRWnBTpkv{UCh*@~{12fnP+6c>GH@*n1Tcgg;v8GONQ!|Gj@qy8l#}|D%74z95iP z`H3VYOS=5u^p}6B`uwln^SU43KR4->lKCIK=6~-m%ImWhs9EhiUawG!{;v+DSW?cs zMRs zsLTKQ{me70T`uf+>KD(kkIBNM{>OeZZ{`r}R>{nzQ5}qqucPUIb$H$Pc^9Jp8+M66 z)dE9>zpkVL9h2x&{R*CNUj6ldgC!jX$FIAQXmv-Md8Uef)x3yEa z4@h$A+!rbU^$t!g|A*e{$GpVds}hr2XNGcmq;cS&e@KpcG}QDl(!jv2Ovtue9s`zj zGx->?Il+d#eOxxa}v8Ze{o5UYDGrg@LE+($IGpNn|-I zq*3jtIYyAiH#QsPhl+0inRT^nPXLDg}KSjy^Z=k(44{!r6v20>J1Cb!VNm%-McbDT9rJI9;0Dx)(`0PC%ocd z+!F1gzJzBI#XB?uP4hvB4PR_Ggg@d5q;PKA&l3#;lf5`*OOtM?lUKSQfu}DfG$#R6 z^uB>2;*G;g3s+V9LwTbfMY`=E#*C3+gEIPKvFN9Bi+Mn}G<)%O^7_Q}doy5ijeK+b zG`oJZmAa(1&7WQX|6ib+*wLSppHXOn>U+BDakqA$eY4XDij2rp*vEHp@_eDj27gO!iBNbHT%CkXrA{zimM=1QM^yIqeYIF~Mm&Tk zfn;~s#qUO*KQjJeipKpJ_)xKu9lT*bF({5RifA}6t00h;KFl$u;6Z~;maW@#lRfN) z&CUw;8+}V1uzAeOXPo-~{`ZNHh&3;f`jy-#b%MlH8HMi`c_}9KqV9|aCr+5LAGmPH z03JP!)&i4^311%>n~8M!y6R&nbX<3b>eW9V4o0OSlb$HGlVohp7`|`qf`fz#sV@ZN zG@z*or#ME^i9tes^ke)B);suy*InOI=5Q%Zhoy+N!o>aw6_oTy94{+-0tI9kN8_`g zQdyx_4fj0rHJN5l?zyAfM_lBF^`&ol|9l;H)a&e-ouuP~$g!;wUcUKmQItqcUN0)_ zy{PA)v#1KncT_HT6)zS}p92o9pt3cgXK!z$Sqhz&jK9+<__)I4B5%t-vnj#|SAt?M zG5`37it__b|EC>_`5G%(JM2o9*`~Z1xM3O8UG4H*_aL*X-9$?urIU4K)c1Mg&h1Lo z1|lb9z|!~m<2#Kr(p`x#qS;pWSOuHQH)VVkmmwZ8T{mCsR|AW>(2 zAtzo)d8%J-b4!5R&7t$m+TCWtYqtc;TRMJjK><{uxos*80%azQ1p40Mm-HSNSr~uv&dAi6v~>+d-;Bi&@2bvMq5kou z;mEv!<}g8G{2R}ce--HBch}zKvHqP4v0J}V;b`Dz%qb*z%PPQVf3ih#^>Y+6@u9A~ z(caZHkATOrhRqeustZIbyIAjL+m9E-D?ejGpF5~@Wig+wZ0Q+kN+qbsol>*2gB^9h zRwuW^5D=n3nx{rk-oJ+rOqjUBhe6e{2m#cO$4;r7%*M9vK=8`qq2UiX| zgHF3fY^CMKF%rfR+94BXsv*$boPHu&S+wFlJlFX+dSeKx*qoOd`VzQR=?@PE|K_C^kB|f-(_&K*m%O$Usju#ZyXE~IG~WM)U*y% z4pn+K_r*;V&E5}W7)pigSJO7y@!pPqp_x;Y7TZxqmX4@Wb%j27 zsRNXlU_$X}g9$f)Kcn4(m<$tfc1V6t((b8X_Altdg4!Z=*7hlR?s6$LF^@Wnf z^EoVU51?T%B$+O32FScl1_$ZliLmbx_w#+YemZu-Bpa9=@FNuP;lc6bo|ae&^= zZJHv1u)OY3Vvh~q(ZtBkkb>lLqtFi~fVTB6b_eH+RMRv3N7vh<xA%IJ8YS5;2y2Ke z+&!5702R&%x@;rS<(S#~QVptF{7yWD>^SZJo`#q`m{-LnoQWd zuM1?Ev{%@T0RTk#{RlKaU&i_HT816?XrBMh60*^J-wrx*veZ;@+DTUOYn)*U&8 zndzs+?Hp10VQ+!37@ZkU4_R40?str4?SAhC?Q}x9;>xM%y~;ZyKxY2)hF-u zBjoIeuFfu-?R^v#Bek<~)j%)T=RbjZB-=HVE#nveVt*4R_BH*Y=m>0!?l^(UU8T%H-O^SWU6=?H?QX8Q|vu$9(#hd7k{l~oDV--HR6-GOnj0xd_SYvUvZEbWPIS-SG&w`X(?Gu}| zPMm)BA^U&^>+hk?MhIbakKAunF|2f9pP!hwoW8HK`m1Y$P2yWP^KVW<4!El11B`>W zw5JNXT#bcb?wVMi>p{4CFSS^_H+eswZIocpXTLT*kA&BD9@rAdfN%tviW2vK%q_^3 z%=iK3R7h~kISCNjQ_-UEZ(k17rtM7KK1$P1hX-eMRvrt8z#LkHR*;3*?LThSzOIGl zGl$)qq617|cE#5TC;b0#=!-p9M-|!h)M3P)=ii|zyUkX#a6?V9$ ztl6vkoy@Yd7*8;xBqmcUAs*ulE<&qQvG7cOtezv>8ZL zcv(K+m_5I zli=pGuFr-Vtwt-*FxP&9^n1umpuO-B74>bhyPZFBkjHrf-AWxcd1!;Shm;o|Oq zX~Rn!<3!F(Cik9_Oa@1|Se)DQ&h7_RBrRj%Yuo>vyzFV`{T3p3bJwFf3G>V*>5OCxMMW3&>v#bxzq163N41T>gs>aI{S?;Az;P>k8m2k5{D7WL~=^vLj7TK@BxQ1x@X-2+GY1}AZUEojE%VPl) zJGn0dhvUaNN z=yDBsRJm?)A~EH~?xnHWf2HLpk(VR@rT!c^g$J>HbL>vij%${LacbE;bLKCv#66%d5qr#RWd#7;x=%fvkZOnl`kC=IL8XW2y4W^Ut3D<{p{TcZ!gNL#w!S<+-nZPolZ1LtM-r3P)?-f7>(R1h{8G|)wCSu;h3MG+ zVoMX986w9Q*Xp(8UYK5*^&L>K76yQ&85w9C`U^Uuzh^4lBzr4M!DZCl`uNR_9#Y!W z9-gkO<&X8BuI?nFtE;kwE5BOdj{10X*6{~ZN&N&l1iQ}yg54*%c}TB?>8QrnJqsaf z)Hhy2H4`sda&3XEg@0!EG2Y-fQC)Or;yTawa8#cUz+T{O0zU&aqjjrK!E<+~P*_)S z*Qmd}gM9L299wvm94KXRuKlH-;J`1jV~jtH3iQ!0U*O(cBeN2i)~xO*@Mj;SW12h1 zV(AYHM~hFoCUgCjII7;D>IrNu;S%4bNNfi}40_;O7V+42Fl)VD^oJB}XJG-E85$jh zK>amxq4PO?MbI$9GP!E${mdbR{yu^)4k`S|{yO1ag}dw6tkI#yOCtXfTru87d-n@K z{LwHqufPzR@mVr2wM!)TR0RHFtwZW-1@8KTCX(}%dM?H6bBhlhrJW6vBp$Ap@1#@Q zP7SRhMR2DC4`_#GUuXqKU^~~1m~oP12DQ{L6Hx2F?#Uw{2Of$W_T&k*(fS8;qd~1j z(CYrfPfDw)ZxVzoQF*7xjd4RNdhyU^hHKVGj3 z$*Y_>2pYTN2WhL1ef7IsEP+%xlyF7P!ADwUHFVCun?{A?V&l8!_;DYO3%p*zJKGsw zf#4|uhdH#0MDDB0x6hG$iWQgKpJPAKdD2~kZMA4(Y<7wjd{qw>u{#K2@OFBS*`XuZ@X9v$0)RH^*p4_YD9|3bBFbn7B0dOcv8`Ehpa&4+ zM}?vUa~~YLJ_4I3?l|Nzitd!5iu`O=9#~3MwP6R@pIbs$M;m6-Gv*5Cz!54cv{$#5kt=6&aIKvbUwuuCiu-xIGr)G-`)e^@r0y2G7- zFyhB@kE2jqlyjRey(tYX&hi^nkWX1n+uqno)Oy^0PSR$G)D#ltiM9WkEN;OJm57(= z6KvXc5j-#@>cT9WI|kpMjHTGx+CARM{*PJudDN`-H5(acr>`UKCml@O*Zk=jdq1M{ z)F$}n(}G<-D{fO%vPPY9(ISAI-gGKzo{pSsfhr@Uj{WN%OL)y0D5~|?mT2?^SzBb( zSG!8K0u|0j*kbVf3GCyzUiM+0j)vq;-fTEhgpk|K?o=N|`A7-E?!9$e&p7HENuK_; zgg^x0*|8ww{P^GrF@2x9b=?RBo$JdV4~#2lzEukHPBO)W^F<3ku9$$?Hk|+@ZJaNa z6hLJ^mK&70Sc!Z^+(Oeozb!N~0gez3*w7t<(3us`kLV3FTvv$TWlu%3kZ{J6&7TXi z^`WdP>nT9dIlSSRJp8arS@!P*5@bv(FWW64pC9af?mzc7XW5QFM$_F)dDE$iuK@&= z{6S8mcNX*SoIE~p(t!Ump!vkv$wWj3pP!i*V0b(jU_+N%7t0*&FnoLVt}pJ9<7lYM zV9YJTv|LJs)JWwl2RstrGiz(7G>N>LJp3M7KEF}TpAuaTV}Ma4y-h%HD^6cZBEvag z8}C$baeGO-=44u?T~@Sw|48ImOH=2bB&a}7v!!u7b9SNj`Y{j%{&c!q(K(>74RJ2X?K)ia zx=C@@kTjH45oAlAIFT4Zi3#!o6Utvtc1u7!uJlfMNz~>l)5)8n%ggw{k81L#2Pk__ zjgYkWnvs)58ag`(YNQaZiuHZ^7WNLzI$+l=vy4*uhwVj}E_C!W$CdVIFncT-xs@cit)7jSi*3n_kpTk9B$ zU-Rq2Q)&A%?td>3{kOCvCn`B1C58931suex2Uhi!Fk7g!qNR$!64ufHZzYwtD_nI!$lxz*-Pzh)N(Txz-?Q*{oooQ$R3ldLG|YojSFJewG?vr> zQX^ln`Q)f5uiwQb-&nzBGTuVW^Co?Jnnb1BJqeHFvR(n5eImPD8WVQ-=TZ;ZzJtR} zk*6T;fdS{7+)9!Cm#RNr2#_N5ae>7UzFENj;nZW}Ihxqz7GPAm%g}*s?nGeh#5cl{ z*5|5uCk4*ofe=dNL2^48_vh~&Zne0QZ#D7xx}UzIcDE-h zbAwhBQQlKc`>Mn1gVb_{)E<9*!$0=*MnG|ha-XyXWtEIWXg>N&ry?f}M$|(>STh~D z>+MDD{8|H~`gUfu`4f-3pgEqTqM84EoI6ws05Q2Z``2_1AiyzmQXJrHttM# z`BKEgq)^!x1#|?@OraLCBU)jUD=#$c$v(j@pgV`ewL6#0XODn1KzzcdFlS>`s^=3w zoAzBZ+~c=P>f(6l+2_mc{J1@ueqYk*=LOJM;PfbH4<#emw}&?(G$00JGzJCF#<)C^ zp5-6Sa0~&gG?N&;By_>P56A?_^A@QeCRIR1*w7nip2eOX`OwL+6~5G(H6gtISHBUw$qi_b2A6Du7gVMT9is2v6-Ddx$<}wqRZylwsmbN(y{^A1IuU&K z&`_S6{t-K}=-eXUSp8)Ldx$Y9L*X!t^oJOSA`^98d%9?EQiO%9ru=bbW z1jlq~Ug$S%l^}%{Fnc>d2cXDNC3<&>7<6<&Oerv!%mw2|uQ|3AbnY|mj>G%h69m?{ zTqylS8vBjCmY;dg9L&F2nf%%9e%DBD-&a)Kh}lcQV#`?MKGGw|w5dc3;`_MLpLufC zGpR`E<=@hb!LkcC=Qmcw3CDdStUa~5C_@X!b>AU$w0!(7Oe^Z>A>4Km$Q48hmh!au z_PmBKiouvb&d%7Bx5G6_8y`%+brjDy7M|Uxezx{Zhnm^ltusnT2#d`3kF1gLCZ=*b zBrj&&T0bRTB|4WXi-FztnP{YlaA9&v#@=4?c_3NKl@ezJGR23MtFW^^P;@*K|N4#e zm8E7ZqfB&j|n9GaZA3xOiG=|8-g}C>w`zvuLN*EZxh)>V+4! zxqrOw4Z;WFA3yKkIbxq4;6XpZVp8r|IQziJEQ-&2EuuxV4@gzu)+$bc-)V^P~+9y6Ie#gh0Fto$REG;K z5IxWf-`3=J+DF)|IE9xpOYQMaY^RMwJ?u1%WZKeqei^6)*D4|i+i+KyU;ApnH~}%~ z1;dF;R_t!rXkYZdx0v-PjWNQznw5(+ke%t}QE&;0FEQdkU->9x0w%lOj>$5M7a?YD z^KqV!3y1w4Kw2V5_<8@e@@+_y2IH1F0HZ{0l9G;^z_L^Pr`|!mnuL9OsY@RwTC)o9 znX(__?;CmTpk35JG+vkGbm~q7r-wZae?WkUlb`{vRuhSCynucD?$LQY#8I{Z>}lS= z!L4I%gNy%Ld-7089RX)L*4XML+ExX2HY}LWzxW$z3gpO|wBBmoSF|;X{q%Bnm)^(y zw7Zih!?rXVfOmQE)3`&V%ksus+uYS^2?UVhR#JRW4Hy)il$~xGGk;^p*6_=M1t08@ zp_Gu}Id{NfydK7iE6B_fseg){xQ&i6BM-l8@b|hPg;!CwWDpPgMus1mF>Zv`3}zg$ zhSH?ibl9gM*?W=rOPwy{K>~-|wjZ3+6_v^td$k@2p!qRXny0zhBQTSEI(QJ~KYe)c zJ9a@)2>NH$LdC{|h>p7InYF^oaC5OlcE zRsB(6{T>+B=I1nkaIl2baNzC&d@RPV!5K^;O;OohM=SKg%UQA_Wyx;K9eu^~^;Qo} zWJ=vO&ezWWU1RMQ;mx+uL?|4M)osL{1&*DnwTNbnkQB7F)V^x^CQ&X%}?^lXNy>|mk-?JlGS2RDs`R` z7uPS2hcByT@mXw9!s_Zu(?ZSO|wn}R`jvw60GK8{BCz%erx5#*@gOhf9OXe zgBBZP_Y3-P$FDZy$kfzFI{mFE@?X?1_u5hYI34c4lk$qlthtoQq4tQ$BtO=53ND<~ zU6PfRcrGY+r^G9fQb6LjQ-=cV0hnhb?wy;K(H(B90tnh+qlMVjG@? zS*A((mW0nRs9EwLDFb=AdQgo7coK%IzsGef`kEwPu>fc+HBZAmLGd?AeTnDxau)VZ z%W=YT?8_*#8Up$bJK`^oucedNxsGmnJQXGJQry4Bs}$EZE1diEre|GPF3axItY${T&2F)SjBk+LT>k-fE~lb>iFe5Cho?9Zht5b~`Ep*tU2UYDxzM?9KJ1QU^G3(%;I4TNquF;jW0J6D=R?9B> zpJjqok2#WS(Lrc>)9VRsFA|aYY4aj~5q)=NE8#GsmwNrnS#*crg}NLr+pgY;N_j7f zd1StisPUxYxIeT!xzbSXh9140F$6hAhJu`aavt}$4#udR z8hjq+QUBh=({bAg&Wbgo1Q-s@vdmRT%5&?GcQDn4GpsXHYy38Fac>C+#;F3x@$DcN zhb`er4kL&~qZo15r7^=FcsofZP*dI3gpK?4tcXl!DSMSY|%+erX#9nTqEhs|k2rT)Qj~5A40otQU{cpSx zKvaT9dv5>UYiIwA_% zA3q`;(Qx364Ftfcq;V9I*-!v~GMgJ4H&2dNr3u%XQM2K7m%fsYB#oVL%Wyfb&|!>6 zfy@?lYC4|kB#JfwgueSMU*?O-7pJ;Jyh4zdOG^?y4Yf;3k4MS-ayB`Kv_L!k6eV}E zIbZtE+C8#819^IdHO#jmd8A$+1*fmApz8tdbf8rhmle&yH)eRR@4UTnj)?nd4&*T1 zxzrtFugbw!jkUVg7#`NEawGb;JE(NQy~L#(JJi={z(|+u;vhqGbD%_dDERrU5Pbz4 z3jc|IZp;MdFuv-HEWL!I1VCsw^2&_s4h=N9O5q!oSG$Lu<;TvS&al%ZU*WP5$K;qw z%STdV&xx0O$wJNxxSm*Tgs^IY+$S&UUim{%K!y~b^AR9Iv;Y(v--2nhuajTu64WdX zzfLAamY1kW8)XI{@c4Lt`QRuW8lkN{E7=hvO|HFB()d|j_epT867Txquc>-JAEfBw z{B}|*z1UtNk?+ucZDA{@tMuV*Iy(wR0jPp}E=khKgFOf-*4JirZ15{sZ<3%u+}G35 z`%dT&(b#U!>UwzEhZwa@v&rPj)xwmMnU6>K5Xg5Q9h3IqJxdW#CFnR*{oNYTHDnIZ z*+GIJ?5^nC$~ApJSLlpkQTIvXT2{Wlx6FSE&^o0I8VzvX3c1^zqC?N*36mW|`7xuh znroXdhS&GmZfza_&cnmKxurQ@L*G<7y9RQ6{1`Rhncwr{Eqr~VKM4TCNtAMzPEjhQ z=v0tM9>B&~|2gDtqIW-Jp7h9`Lr+|rEz(kP@n0xkcw%;-EZsUpA9~^E`{DSMqQ{AN zyLg&?vg{J{(yG|ol`*|&mX6FLb!$O%2wLY!Olr@s1Jr(`EYPaNiRzYmSh1;;MY(`8tq#*VeiaaI0XW<^96|K( zis3D-jCpcbw7(T7^xhK52OB=r(LJAC>?h6z(0CG=0J26E9z7NO+(pkvmRmY-=hxjG z`!xQ3I7{X7-Ck5;>OBJ7D=zeZyQFUwUM3wMuNhuR-)bm9{hLDojAh3YMvhEi=H!=V zt)?_({uf|C9Fb6G5VeF?$ey;@$=k`{Uy}a`3mpGnf6XUziT(R)LIoBsp%G$I9Fs_( zC-K}Dv)}waEg_}zF=?QIl`>q9aDPBN85t>gzyI^H?qE;cL|nbnvOHlgLUE|^^p_gf zc_tEAVWh7g&rl0e;LhuKD?x7mQXlX9{1tY)X@~9y|6xk&#s#iz; zin*O$cKmt7KUa8hc~Db>-NA%$s<|uz^!63Jne^ZLe&};nI{Cow@fSenY(&Wposh^* z-f5vP2>6i&(y3-RC23B6xGKJfhgS=WVd>IPK=mLNvb?qJ0?GgHF5Ug{_vfk1afIK_ zSP+SpE-zPKy?Uq01-d#4YX=;wzix^S&XK2eU3SAw1*63M;m`l+z&NDFj5NcSdL)Wy z>g$U7cXuY7o;^zl{gzRw`TSW>MXsmYSs}`>cZT(I{{;q(wG3m*a91i4;#x5w{bBHu zKMwyrvoslEvP1J{B?%$ErEkW;8Q2T{<-cO%IFi)x+Xx)XfAt}qqeB02V4bIwmo6H? zxEEp}{R6Hlao5^y5$^($d!5bojqCG&_9)TEJUvA3zx5(H#APDSIStD8|K7d*_0ru` zs^6LYpZ(eY3x6pH7=KDqtPuWt5A(nMyK`R|7|jX3)4z6-ox}gpq0C(F!|}g7$G3WS z!{B>#pYEK83w82QyoI+{MHW#|+2-!_M_5UA+W+e1HkSnXBkU%>Oo?dw zKV9BB*`AX0_s{tdf1Ta)e*Skq^zC)oy>u>k2Os<2y~dnAK--M6@_+Ve<<<7^tvvjP z)Aj$kU;F>#e(XQ}4Cjis&A;@8D~tH|o-`~VDEtn?yZ^uH2IF1$f9z!ckKd{J5x$-@ zDT)-(+9lkx0T_J-8fW5h|Ff|l8ql8;rt>(A|IIb~pMKhg42kH-H@A~=qzyW)IVe)# zc`3-95cST;Z0SGyp-eygf)UIJoT9`mE1-VlP(N#p^es%1wZ{IS$*=Vvo#R-Dm+XzT z?S8CbWj?W|v2;&QEWTe8HOE77iLUKRyHQ@qvL{o&f?jB7>Uv5yfUU(sh8^!0SbMmalVNvabu-# zyz$Tz`2TQrCQFX0S(kkv2K3!fEl4y%0z@+d1Om~BUcl4W_M7)ls~VJ*Sq;-Ou1B~_ zf{%0dUh67>Hn(+9v0CUp^HueNGARU58&N@7^5hW2{iG(&m%9f4;5yUsl#z-?<{ob% z7M3X;cY1bU%{4N=6hGu>+Jjw(3i}a3@ZZR@jMmr%PnZUV)cwy}127x0drJrZD?6`+ zT#&+vS+$PtI|VT`d~%W35<&ZBh$!UN^8@rY0rr*bdOLiF?i?!5R59&BXNGv~yg4n? zX_(nN&Qqt%>shJ#yZ1TQarwLnqJN)XO~f?lgVuOEwhLO8$62*@s{etVe!Bc=Y_7+j zP}xIx4vFr#pC2Cq4Ac%xsP7nSP#>FcZ8dqk%h`Yj^J$##gLi#co&2!Ogh9O)&l;q~ z5?Vr$~5xD%MeB5NOa(>ISyZ@9NkV6jw-_H%4vO|M>k#j4s%+Q!_-ueT#le&&}Revgk<(u5M zWr*;MUi#4oY2#4bKfV*RIQ$@d!V`DXPWoXz(+tyrF!nM`B*ptnwu0RM&pB}c>;!L% zck~+A_eqE`zJ4%K&&lST(#qBr5(JeIt>2?H9KIKIB*dofh$Q~G!iN+LF83th0kNoC zQ;J!`SyIbs7yq~bI8bY%t_eToK3MwzP6CLNi<>V>{Z+fpf{$Y9Zj6}d@-S4$t>qM) zW%|5|Ky6kf%e}>O9B8bJ)mc0nzE#0oMw7daG)O)a0`9CLqTA;(U5}yCK2MMA=mq=> zu7zj#-iFL1*$Ui+{gV#{zW>YRxu|Vk)C?POxrM_J;LZpqFLlQsys8X2z*%+Z?MoY@ zA#Bdq{qyD1az>EV-^m7-wjaEt*~58!f5AIqfCM`4@5vgO_mRw45}BK3V~}cSYj{@w zAFkL&d#{>94*9tDy7_%)+&tUNHd1#Kl6vPZkP{XYgCTDwh~VjN&viq%dH& z6U<*$d#h4>y57>DccEfK5*plcJc}X=^21TrVK_()T$0pJyT(PiP)7>`$5*E(9*CA! z41EzyNt6dt){pBA>*IXgz3Z#(5u$bolBmV=XWK273I9YtA?tPyrey&Q9*rymABKO7 zs*RL9u%XSS10j;r6^TWadqxC(Wq#hC>e5nT>P{lgH{px|Xg`%@zQG$g9nUsWQK`y0 zpQy#s{Bb~E|LYo| z33TaB2|=l_xUjl%Ku10;pJ6okg;Lba8~KvUPg&V>KUPoDu)k0Mge~Yr8RYa4>Nxg) zEx8V{{t{@9ud;;@`ZG4~VIGtY-|p^>^k&%~57wke6K43e-Nk4Obc0zp&P`nbpU)h{ zz#1^H<*ek%4;kbqFi6&xH*SlhT;1lC6jz_R4;M1#BvD`wl+{hJE(RGTry-k!|>znog=+$HEFl$QDNI3j^NrA zx^KmiX2-)FFO=WFMECm&p-}4>Tn;S*HFS0TGq`J5AFoo{CX2#}D8z?h-pAAh7QGx^ zcZ%u2%J6&=sr^SUsMR!4mk#f z{6dEO;h5u#RA0CyoH~d)_erw50NDPfC~TnZBnvVZo%#2GEtB@e^5z)bcx8>sI;C%3 zsPob7TfxMQHKbS4z(n+8&c15$615+NBR<+4r{(#qAwj*pTEN;yzH+@IUmbT#SmQl5 zzx|;*qNntC&t-);l_S${?qV>2DS07RrZY1o-^BY~IBJw?HXIZs-hmWYna73@1&7@P z7Ov;>pR;^*$^zr!1S;bPZ+(~;b@78n!R$itf5+kbmo03th5<;OEj}Abd{0QF_0`nTTKm_@OH4eW=3M$j z7`zB1g805M?+t!0LQH5w!eE^J9g65Uj9w672>K4O_5?{DC*uYY)lnM8X1&p~~K z{{m|fNHde27`wU+Z)UZ}9X@4u4S#q@oJaoOJ+KcxHX=&n#NTn>jtR^9g#^P=UeW>Xrk1Nx?*1k&%1bIWz%&gZ_)W$g zl;+BMw9A{kkSK|+-KYekOoymA-Dj;NF(9@iDa7-8P=XY{I)Hc5wD_z{IVKEtcV@rdaTgpVj!#;;3{4?o%y$6cud9C@1MrM@TV3xM zSyuDo1m@I4qTh)*TF`y-v)xzDz|K7+fG@q4@n3^7V<^gqA3R@2ZK2tB67zYspVaCuyy9-ZXs;^l?pg$fv*OBK z_BykdkFC_*3HHNRl2>`9Sj#PeJwD^^-UE;PEoSo!WDbiTS2&g#F9`#)@15LiFum~z z*UZy&jK2hf_m~g#?Z6)o&ERo?NvKeFOtQp*jYRIum$j#l_x`beDiuCoobDr*FYkqY z@ws;rjeX$1dS4&!wPC_ zu!j)7xKU1eD-r+PNZw*@I(9&mx>Edc-UsR@zWPPOUvQ4y@Z8=#P^W;V+_|awPlBH& zMB!`{nf`@QrE=U;m6ee+EYa2J_chcbMv9aOf074!{j`O{FPU{|WY=!F_2oVt-+g2Y zF%DRlsew2iHkH}Mrf^0szi#*s0??G|BNE}A*r*yPpIucGl1ctXkb|%96FOp%)4AG7 zomlWPKMxIqd72M))#i_ea7*J&uSo57`7Oo`g5O55iD92~te8pfo?1#P8-yN#fbgyk_Et<1FU(fk1Ca1#|$zf7fQ*T440B z;lh@auGYCLYi@V8gtv)i+NZvQE55suO~SeC^WD6?NqCe3?(~8K4OWW`OHC&r4_%{u z`#So~pN>S!7NkbDQERgT#GHN3Y>aQ!zjtA)8 zAvHyfd38Je!-);iS3QBMOX=MR*|$8yvd}V!_JU}VmOQZ5sTIro5SM$8vvL#CrM`;V zSfvLQ;@jtiCOS^pqwut8^>;(1h&_F7uBC!50hL32P^IT)twI=oxXLjvWJjoH@qIS8 z1F{eKDq|)aUp=b#9>T3&Qp|?sOHf~IpdVf<{%&k7B9P@Riqz$$gNPc@nar(mX%YsJex>;^BGP8 z$xsDD2xces$78bl+4;q(vBojZ5Qs;E0HM?ba>UE-@4XHFcnH%?a8)qU$K#$}FsxV%nS1DpVt7M`I1-q9}V+_FWj z6qiuXJMCHP`*n)pe z2#;vW$7x~FLcJ(QCY0n!EY*n|Qo7E^P{Z#0^<%&`5aAkd-F+d3R_b4rOu`qQ;#ZpJ z((1&LwR-ki*cct+pG=JyqU0vT3MZAmZQ6fahO+5ru?EB5|sDU*BoVm^Tt^k#eaZ6?>i zisn7X(krOwo^cLvA^+Ln*?YD|I1YvhD9}PgJFAz`9#&qfQEvo?YWuWN- zm;3ud0jy20hYP!7?Ya3`Rm-2P!y7VoSE<~mR{2#TEAo2$`O4l)8w5_FEB!oieyjRK zQEcI?-WEG&rv)z$BSbsE>)e&xL?77N#OmG;Dcs!;HBMnZREm#ux=4zRsvaTlXsWmC zg}-b-^1>Jg-y%KwtM3wZ>^-&Tq*3Pn2T@YoApHW|xg32GsaV{89rk+*D`DZB9exzc zE)NgU`^OHZSM3egc{83kE@cU z5545N`i>`$ND6pF{gVT^#ouZubx)J@aj({A&KIuo>n!HsbP(@h2mbnE0yuIi?oaJ^ zxOM5BSA^+m645yW=MW1xO7FbfsU9?QkCgRM*@87RPu1vzWC;)MOG;Q-zND6Z{rQ&x zQgR1161?%Lh5F~U~=(_b)Mz@TY)dU_}^WH^unp7SUp z+NNe-q&1LVNyJkf%hvUzCd*~``&_Yi>rGD9V1L3J#~yab)enb@l9+)sQkJEn6H{BO zGwxq{zLJld^swN{@_twG%1%o5NiG$_Sf#)GSUZ+t%nI;4C(jP+v?Ul-Xp;dsMhUUM z-L`k&P`~RTlF8ozK!qcO0niILyhJR9bCQf<#?Je1HrCMs38xX`<%D1DgGNb@XP_yX zoV$h{d7PS?aQd%@HcXxgqymU}9A0#zS@B-jUgDjd5{q$=Ni_P90itrK0N7LB2Mlr> z?j9PU#oV>OUUP=~IRK%^omV4*u%mwrQor;~;v-7NZSWgB!&}S;7@prtR8ONje=0@f z&PkblNRgd#*PWV~8V3<2&U2LJ`)ot;zow!i+~K?7_Qx7f#GAh-sN#0OXIPtpciqJq zKJRuo$8Y#swfjEMP}+84u5WB zHswW-^6?pvE)HP>tWvh|k*tGCdB0*e*G-)b?Gg_rjL4!pPCm0~3TNdMY1Ke?LOQRf zFJ!`00G@f;^QpDGtoVeng??vaGrG1d5$rV6_oh^_;aMA$_$&tw*6l+a)chfcKLVv6 z5Cl8(Xv)i{&b>1FZM+xK-vB#;{%%)`1M+e_f$*y0lFuY`JIMg34o`|c-5{ij9S&N- zlV4vCr#ZR(%^M(j5HOqba70SMJS6c(FV#MH!gPvSJn}WM7YL}`hxO`JH7(y4;U3A{ z^Fau_-F3T{y%EzoCAjAwWui1{HNM~=ZOm82zJZ#JW*I)53h5yz`g9 z$45-^#J|Od{aAIm65g4q9Owh#m?DcmKYwDWz6Z@W&HU(fIjfBYt|^m+c)MYi6JP0v ztXX3D5?Pz}O6^3K8eOyHAkdzAim=|)PuxP7k7u}S@Y z>>gzduD{5i5KT(TcbHBIyYIK}kn1fDX6Vc<>Gz|_Z)dvVWAYld7wNFRK69*`(UxFg zZ^HW6!etwf3~j9*^Tzp77lj8}%Z3jSY1m%Wm4Y6{MEx9whrpU&L#KftUH*h9{&~ri zPtNL$e*P3eap6qVx0x*%F3R<^W(7B04__*-HEJI7Uoj&tcE+>mit2Vs9-;pz zYlcMIY45>jS?L_s?DcU^9(Sm2_vdwWz>k+Mk zfEOi7fHj`Mts+&&l-8QSGc9`@o!ya*Id=mfg4z#Kv`*I}<}<*OlW8y@x_4g#^9zFK zZ8p?|?&@WY?#eg!!;!}ttP_*&@_^>EVFncc?wC_dxBX_6xAtUjO$;iD_PWeLH%;m9 zfV{1D>=-Z*zsia>uZ9jr(LKwYlTrHu_Ao30()_NsGB)P@kcqnCR$~nZy=@+~yh)^|UnRBI3Q~k`9zWiv5Q?zhdBA~V^(gCQ3V&E#E5&_t%m=UOx2?*-+rm=k>7 zu0W|_U&jsVu}}}>WD3jz_$$4;XRkwc)CPmgJU*o_`ApETk|(?EZ0@Hr`ghvj|wFpq+iz>O`OM}MMFmPa?lYc;KeW0NJF4y*7FVfWnL zGw@(wHGk0HUFk@cx}>nyITvOBjy_MJ+xRXJZg9$|p2)q63xlA}X(5)AFX1%x{iEiN zHcCFf37)k2F(8}eVMP0;MzD6VpFV#`s`*9bn_&kJMR)?^5Fcu{zG$Aw?inP+5#X{klC#&B z3;15jpL|$HREHufBQd-nUrz{rzhbT+UzfsQPUzvM53_`|mnjdnOd0TeBf5v3!884l zV5cHpdY~an!ex_VHRe1zJ#}3$kd@Bpu#4tXdruMxwnPQ-$A+o{dd>|@<}B5KHQ+6| z0+3;m0VC>lNu|Na?t;;9p&SK74lY{5e2Vsm?N39 zUDxFtG}js@kXN2HZ9Ob$@e8VgFUlF@3gd*&&tgd+U5JKTCI_{@5V=TGj{&K6pnu>6 z07Tb%989oMesLX%q-nEOy`W9Zl>&NHU%8yhmpq<{PkatWp0_MbP$=q6A7guXJB zNW^sv11THPxJ{x4m628;2!hJd5|uuTUa38s`#UGfxybe!$pEozMYPsMcezjg9LF-H ze>V)c5AS!S_o-M1`t8Wh_ws%61xkK*wEaV9o$b=^Kr*DR`nRP2PN@~K7pGyL=|%%S z^_AX=_Kkerj{(=ze!djmzhPoE6`&GNVVwiQUOaoZF|$0R6xR zILNw&hJ=Ln1bOU&5CJ%G6`4mE&=D;e1N&&jSTMUWZIq1|BI#@$DB~!HC}cZTV$$BK zyLX@B(%)NlkSAyC`wuZlyWP~>)Y|8@#E1#6nt+|d{65_~#IdG;D=a{|@EWy?^29KR zif@V$EtdVlgsUND0_Rvv-cc}qNfsDF>JbYsc!A+v$@}tep}S<+$awv0`ncD8-XHK# zU#@7`!VZILz=C*#xi9gF_jOw1lQ}LP0d{u5o}~ZlSob>iHgCQGT8>%NU;U3kgk#E1CH%dtd4I zfRdfy)5uK)x?Tmhq)jOqI3wwxiOt2R9kK)N|mnjTtD&SScUNGV*oe=zjQn&nKDzjWKL;du3y|UcB%t(Xa#bc0dQt3U0|j7dSV1o)vQd#Ic-_Nzc`O9`MV?`g zBZezp%R_KQOW_CY3>}#SU;_S_Opoika;{OyVJ{5@?7b-x;dQ))2*$jQ5m{OxW$r>p za1e9Cz{-{yhk5awuI3QmJ)4YwNx@T;Btb9AcX2DUP$Wa#jk8S1ojthewRT3JbCKkj zo3vp3!D)~eZo!P=2{KIKF>7a)bEMVKwGmhAuBDwkS;uEDLjem9a1RCV0Pg=A;ePwgH7Hbi+)-I-ItFw zdzk2$-IQv2|3;b950bUR3=NaD3%&bWXFjD5^8LbPI&PbHWgc)FzC#i<)0TM&B>EHM zJ}kw%(x-jS2u1zZdzbx7V_v{HFu`8gnSamWgy$Thc!>#e|+GZ zigxM&gcdg>H;XW_$~d_ka@;vDjl|p+BA(kzHlc-#7WesmYZ=kNK!FJSP^jC^SqKso zi4XWM((Qb7fZDP%k{}&`*)G4pu&@0Djzmp^8NDkJ3xR(U4Am6v?cEbW+!{#d8~8Gf z2kwiZgdPPE#pB|%60w0q^b@NecL$f?v%P;`SN{NgRChpZT@zv+UKn#UfRFuo=Wc`@ zYek6BzkP4MVq46hoKxvRySiKy%&MK6vVu&+V_EY9l>yWsP4@Hur}GWfIJdhzU+DVN z&jQc)PJ|#rM}iM(AdF}0B|_#*)|p*nmO{}W){A_BNJWnZ3|M;qy~`#hvjcfPy$ql> z?HDX+1hpy?w#oAH(Xw?B5NG-2q<_sC<}T}#MJa$Fw@5&}w5FerkVm{vpDT#a|6yNb z;avlLv??0?WJyjLs`EwMVkRoQXECJ`VPdEv1?N_1!9`SEO+n{z=w3gPXKjOo82xDN zgVX`LZ2#fBbN}MqO*6mu_Z2?5P5O{i{^ynLpDL43)IarKSI4GiKpVuW3-fIdL3%WP z=mgG#%K2uB%Cmc&7zAhi6Q=%mU*bYkl|k@#*5+4oi0CO$y$U4@`(LBW=%FOGbTt zKNIXKAz3aBV+E1zbwK|nbd7T3Isemt-S|OYv4>Sp+&p07poJ6cy3YXjwwM1tl7^J* z-1p^Yq8LqRUKcvu!=@GC3|`BgWiX}I3bx4W_#N%>^|r4&?<*aN`EbV!Qu$hFt0veK zwfv=jvJZ<4ZUY&Au(?SGCt0&O5Ej~Zh}JD4Lia!HAiy%1`raOt^YL7uMsOK*ymz`!KtW@Y zPGM5p*MBm6XI#7ZJY-%fLic8EoVysY>eah4*Ez{G81&-WW<7z<=X| z3K9K{v3M=_mk4CUx~Kf$-7&7WY3}FtJ~g?(*@nvEOkaxraFQ$HF2@xc*20^C0q|)y zKOHtfaj@%QZ&X*7S4ho+sG>rm`OzFR4PBiNCucPcOV#p7FWkcEREPHs@qg53ikLC~#oZcJqj=5bV`2AmI$6 zZ(kY|!;FN%{qMSveA!ppR&?c%zijD`0*vK~xpt~uoZui~jyFnjB>!l0+Vc4J%EJ&I zsS?9V@;1~qxYprwTQcBS*9NETTkGtm%y>Y(acjT$U%xb%uvV+z`9+WLSPR~*g&3sI z$3u9yo|wQ%wxllm~!d+B*xPl zP}{GI>>&9Vzj#v4&r7d!$ub{VySv#dl^ZlBEw^`RJvRS_u_k3U7lq)%@)uR{P5YF% zeT91q+P-u6I(BA!c8P?JON$o0nuNjHXpZL{@TalTVLtWn#VvxZD{fit=)GwOU=&d7(s9O|RKi-Tm3YVu1h1np+fKmXq@G_SB;5}ZJkmv`h5lEWdN z_0L}y8h2pg8=pTHg+)5)4b-@h(7!Nwocqh(^N`AZXAl00tH_V4L>Jf(xPq?b4xtC^ zbHXs93d4?$@D_08VuPZomwe}XvK1aQN#?HJ1%u9_#Y93 zW4q$$H^I?x-VplN5WbLdDX=!7I+g$)TTzL!4CnE8#ji_pVmX2?BA`*9p7Y>=O4ujJ z8&Vp+u7}IVCS7E{KTpCta=7ch#RK@U7DH%wjCOq~a{fwvayiX)`<~_pbGbjsoYy+u zl4Pi&$+XRd_N5EFp+CLq1NpqLG|{Fs0I zR;Hg&TTMQqJZxgc-}Dh$B(Hq;a&uH1T07r7J^sDy+2x;@y$^@Gz^y5v)9kTZwVA$w zxxON@cdtT*oUc!71_?ly<|eq!AF|pAScS1uUJw_8&)asrDsb3TVB51e!M_ zV@r{G7W$u#G;DjI^j%f}ha8=QbX-JJdTjQ-eTw&|e!#e5UZ3&_@nhj--Vp4qrFnw& zlzn2|2B@f6k?-($g+JxiCiGQwJVgFTsZcR@Bh%MqyLWkUy}cULim!F*1oXzQWHOZ` z+4|DLquw%V^vfz{>toRBExlyF33L$Ol6+kfF)@y_AjIlM`Np?9be^jXPx(Ktd-4bt zsb6ed2Dc3IxAp7ovt-s^0RKDyxBTXx&J&e849US03IXakJwEHj=thau1bUtAmQqK~ z?0;>lSPucdv1?#5(g*?*q^TvVEB6yi)pGQV-b8!3?hEuhZc2g2m}NbOLn9Q#YlD_= z<&~sa-7SIss4j{tW9#D+2nNW%;OS%4QA5<~W^_;b{6dGiT zzYcY!G;&wrxTR0?<~lw{WcP`r9s~g#+Rnd(a|ZE~Q*t-JRps|xBBSrw)h0h-+)*;v zAQ~CDVreHC80okKtq9f|`q^^uO)lr@VG8eudc5NCpm=fBk!*e@SA*%Gn+q zd5Rc^r9hU*KoO*k9d8K=%Ga3VV>7#pH%Qk%x1Z;@$|w{mN6wZl&wz6dism79Bm+o8 zUs#899`N5HjXk!h7$824tA0FQ3o1{ocBVMK&iYsMj-W5eJ%s$Q%lS4SYGja&!OhD; z@ugxj@w&f;x_|Dy;f_PZk5X^|EazU0mptV#M7dL(h}Nha1F($h0SrWbhS!|I$Vlqa zmgKCrXuGNKMGA8*T2bU^FzLMA@r>?=a@P-M>A63b#pQTCKd<+8J?~5HY%tZ1uC@iZ z``1ARFj%|@F6AWOuNDCo(~(fk8`Kqtf??6q-=2BZ=q77wiGwjYl^x{k_~w}$ zn3jzvb*p$$;%Lp)G0O73AxE8GBjHV|!H%6p0YkfORH1&(3LlV9cY2>RoGGeDdJ6ZNZtR2tI1-fvaV@@3nNwepSi3!1Hy)T^k%w0QWt~; z;i|~^2OhuhDO%pKbY->6Qjh8iZ(QXizoUZEnYNkDGU>LKf@ZYtqz3>tN0ZZ&Jbe-t z2(?YP)CfYfvl3B&BuilrjLZ6Yr3d|!nlz^y=L_p&!NLCXHK3?y?lPDhzBc^azpq{Y z`I_EY^2qs_hp8=+bDJ=Sva=Ux_*liCb_wqH`}>{e`+aDq=JRk+PN&o5a&hhbliB$= zzaRedHSL1DX!!Lin*yK-fBrvT*Yq8%fRM2K`+bbJt~8bVDXQxx4FB`J55?|^f};HI z_rmwTe?b=xhW~ya^q`^IjVlX&*5coPLx4Y|In5J;_5b`i74F_p@JsrdR>Jw8f9K!d zn?E?JdE<}$`{&N;dyV(`|MqV>dS8l}dFzMaUkc>fe||>%xBF0}=H2(-?|(k|?Ougj z#r<>n{`bE>V54&4?1pddwi7jb{)Gbl&wJdSk1k`W z@=kJcV(OMAuIP9ub62CiZ_#xNDMDGFk!>4T%@N^4vlbj7>vLyp+u!$oCI)lq2`4yS ztC-jfadk?2&{j8VFg^>9=gH}1Od*eZV2c0!xeNXG-dL0=9wnn+{^xZ)6u-Y;{qpbY zb<)dy0M#K)@J#eqzZvLO2>2Nshuy?oy30R2%W^%!$c0y!^AwS~>B6HAH z)Kn-gj|eEw*zGY}1bHz)sqsQ1_Tt9Z(#CGPxzy+Uj!<<)t7#-CzkLSOlOpB81_oniKD#>}T;-(6c1Cku zpLys#0MKXn$*DoIv8)D5>>#kHj3=@IxvJmTR-^>}tOdL^SM5y$e3bc7-N}D1lT`s~NwgoA`H)(HiZ`TDV4CNGh4?yqxX;?ei_D zxa>3qC&8|Q{-6IQkLI+uR@bH)^Y5DW#K_k|&^$O_K%2Gxxh}e7tZdT@UG^OW$S6W# zQbx2!CXv4AxU}GZ-T&Sf{w~$1W$la}ifhKSk6g#}UnT6rR{a~KM)S4%))J8^fuzY8 zTU+aTB?MCwE|iI8V0o09t02{e{jg(kUf)34!9Y+m`db8F*xh9A$W-b!1q$#6E z$B)QL`t{@dSmS30i{*_EDlo=OXT`32WD|(6yAHx zCYq8(?JjH1jW@qpUjb!WpHObn`n2f}_trS9>YPS1XYSS4?YmVwu&t__n8J|altO*S z?7(es#1-H@<_%9RL5QoUlb-dT+E)^!cyM;OH~M7~%3Q}5>4?^w#yE`}rpQY<*$M3B zGi^98`&V3f7^L4vQG{bL7%iK?o*UZCn*Y5vFQWxW2VM3$ zdq#8lb%VVu9I2cItS8;Rk|(P z-&^>Z2887&57$7K%p93KPyVi=FOLa`qsQ+xR=D1<+sgd$awChorB)%>Uk!$Ckn zb9jN>w}$H?b6}%>pHc^qqq2B`YG6#;dHff9_hgAmmi!m(yLfrR)3uE{E-m3XT`fG_H zQoNDSAaR02UUtEm*v$RYcfbS-^Mg-F5_IN9Ud+V2r=DPdeV0!;i&OhRu5rD*Q5lzS zC-$+&W5~6db3%_MPp!=s%c}};;+)(0pyZg9=AJBjpt>5?xZH7nK9K_PAaj@MF z6_Ss7fmxhu9)bMY9L+`Ipg1_`aXN}`5U&|ELg9Bu{#4WDmo3LdqX)xtcXIDwXoL7? zQg?8lP%wUwA6Ba#{3o7v@?1>JjypI>mY`&2%4;_K6htJb@9eJwe}jJGDWt6g#98>j zRP=^PQu@nydqPtfxlLneXcdu_^Iby{?TN7Hs5KzaUAxYVR?aV|J^|M{9RLPh;Jaku z=XTmeS~Hi9eQ-b99KR884NvEA6JI+V6?m-GVf#~T1`U^ihUd#|nmYWr%l!9L|F}&C zwy7Mw%z*)CF+GUPjLWi&2|I!(%~H5(zkdY$c&$u>au>E zE;vJ!x4#eDj8xLzHRUE!tZ%*~qn>4Nt>p~_B)_q@FAhQ~ke`H&(mXWXmm zi1qzgOKK9Fz>j)EScMc|+dXUK`~KHGAVo(+s}S+LiYWNS^gSqM$-HZ6$&4yAb zdSMaz%pEd+~yg1<4VQRj|9V_nBt*<1Ml)S85F8AeP!Z%PQBgj*~C)G+lDXA`p zU)`WN2DobFSHswfzHD!<-h*>fA?)<=u*3#=K`l2jgH!=$Eic|gv7dNmMxM?YA)42V zKc<9;Q*bVZBSW-uHe0ph_pCTja5QW{qbncqwHEG$D~<$yL@@kuCw>5WcP9cE5U26A z%hNBIeh@ZB{aTd2+kNPX5}FffwAi+v$u|am7#>mrcl+c|i7{I&F-{>qdmsIs*+EA7 zXJoc3aYXM;??qQb;lIV-p>-RaXe9#Rg9V3IXF@D3AdL;IijQl}y|=2-j`W;~(klRpcvi zAb4jtm{xVjhkroWNIa;7l@BGagV};4Z(MZd>sc>QDXf@ecLMrnaIn=Y{;nbJ-!;Vj z(C%DNoe|%x27+RNnC9I;Ac~qU1nRf0q;CaB`Au-VU1PePRBG;X_is%Q%zAInx+4l? zUa)xg=i5l!nH=S@qhx+&^xiW6gz*PGu4Furp9GYFGojvdPamQTxfE>{q`ngjpn{I? zpCS;q7xc^C^W}M4AG<7ncyc`(13U6i))W*D#36|yW{C6qR!7+!djOQ_qcp6PO2yoUf5?qpk zS(B+_fR7i!YPE;}o>vpAk`T+^>*9 zN^6_FjgyInIqn-@XWG4X6ONI2YO)Y31pWQCo^Q)K8~tZzo`3szT!mG%`GRPI_Kjzc zFRSBm@#{W|0At*Fm#ZN;W;p{~$KPMrmmL4z3ePX_ERCV1cF6l~GpC_wA6BgE=K0V+JT(kVRwRX5ANE8@vj6Npp)^YqzA>^cmA`wPbv=yGsSfec%#rgGw7i|Gcl*v4n>+K>%r)m*SbJvLI=2m+ls+Hg>Gst@GwIrTA6ZL$o!uXxG>)W^EOiY0 zn{}+OuE!%CP?8UCE*Yyhoe^)wix1$qej>~Hu0PTfZ91O+S-v!d?g$Fi3A!uD9zFUq zL_Ttk8EH0EGK(Bb{X>R!JiPCBD+S?u{L9v@DH{__I-hsnGdkE%Ddo$3B`|lRQT;BK zH=&;k5hg~F)AlqZop1d}X>rd&Z!$k{!*ao7a~@DI%XpT%2f2|bxpMXI^NV}|k9e2X z*Xh!`nhRHikUcbF@89N1eh?+G!RuDs0f}ry%(p7g^bW8g=(9knM&lihlD6Y zJbM=lb_+-lIvRgv^veC&RqK@3k@Ufdc2YWH$le7I8}&nZc28LB;~vK^EXK#L#5aEM zG7}v6YaDNfCZkVbQlmfcoFE--3cH~Jp;@sOCehq}22b3`L+;O#C&7frS>K8sawglE z=#X{YiOUp(u&DF>tTDG!6>=S9JeqlRTx%4gj{PM4e*ZC4k28NRTLTbe)ZnJ_hq)5K zMzIEcMcnLj<{qHiCFtoUV39UubVB%pXI$jj9f%|q37H1S9jJ|}#ReLdq>L|uSaTN~ zHIUbsHe6yrH)0Pzp209H`-W`p2rbtfCY)hPSIy5l+$e}njH=E6UZPAVzBv!pr`qbD zC3|3DwA&NP1sbTW+hF+xn|sbWKG@rI5^viYolY)z~g4dIaB{xnB>1KYM04&3jR`CNJ7_qE_nI1&_BwkzVGGAL@`H)x|lbE6OOh zn?i3CxEGE3p}F37C?n=tfCCh$!+$DzDMS*2J%~b(o)E~o2S2&vukGkrImaD~w?TbH zMSeV2RA>+>yWZHH?f4Gi7@)7v)cHG~@estz-%cw!aDBT`wS341u@?sSv3p8cS#RRC z#RPij@zDJj>BW7B`WgD+{kM0*$-QR4rl`+TTnY$qv0tFwpYoc|S7wcvGEM zVehh~Esp6BPw{Grj|Qz7)p=;8pb9MQChbUVq_XZb#q0v!uSYYRL`D7W~vM*SU6-sTl0kMFdfnls@_s#R6B(|q~2*C4hf*ZHY2hw~SP zKm7c`Gt>9fYt?H~p(gp-n;SYbfA{Fr>!mu&=uRzhF6J={vfY*OnUyx2&M=y;!q`(LV@$C1Ep zX2Kg00@4$h6VVy7oh}q*%ce#Em>(ma>f-YX{KM(^XsIuDL(r&UC>?Ca9jMDBK>$sO zM?)HZ+L6I+9AM@U&3#^;W9G95OSuDYLF8e-yJ7!xypZpo*xt3zhc;0r5Mk0&&hGc* zU6#}HYoI9dbfE$+UgEI?OLCsbh>GLQCPT#KbM5=J!kK=J}T%iXk9G7G-uW!QjXQhN-r}7q>Yay2QU&1 z^OK(061|#bVcN^KYW*J*)dC?6*4*h@@C0eiOm3P!Phn)L!0Dpq|2m zg!^M6)|qXbYqaTYjz*qC-c@soll-KU9krvpjEc3Jif~XXGzqFO?yQ1?u119Tx1;HC z&pqyckJ-toW)PYy%C@| z=Xgkv{Cj))+^gc=e*5`qzY^z)5Vjv6vedu!49WZqMnO4;;m5dd0R6+l^!zMLTy(dA1{*$g$bZez-R4+z5G;anNSYx6JJf(!BfbRODH7|Bh5Ri zC(W{%Bd=K8t@*GSMtNi0Vr#aI-|^I9^BWLX>UOEZ_5|C(pXc+&`=lV_Dok4GloD4N|wJgy6#@@15ziE$$f)#!VDoku8fL0GU~AHmrR-(P#nWMAO$oqSAMKDetuQw zTa*@K_rmgM`7w%4$Ss?lYHWre!~70kkC1xdhN zOU++q!X6ylgE<^^as8_2TTP|FM|!?gP?lGIALBK}o&}~?$o4=JcsHjr?E#TC*B2(X zJSe0T9(=Y6uE7JItxbOtyU{oI-(Sq^%>oUy| ztdy&>-44+)X7P>Vh5fC0;oOKt_ZoqfMOuU8wT0+$iFjo2J%`IHE-@9}Mblxd9r1Uj zBAK&G_KI~~q%S?;5v#5w=-K(G2dw@5;kWi+OPsc6B+#ET02ab#nqU|HEi!LZ1Hv$ z_K|aKW|0bzOZKU9`(LI%cCXMuPHpgLgA0=ROkm~lnROdsA88ru@n>!sR~wJB6^4!4 zzCp$F)^hS|419A12Z7zmxVJ)(8v<0zL*C&b2oz{>i_A88Up*N{zSSg7BYTx>=Sf_? znu*}P+uf9m)gnYfrf!JmP-=V-P-puK!s0(AoMX1_9J+h zjL5%F56t4wCZ~xSr9kS0AvU!p_E=?i9tY6Obr|VjDC*ir^}CXkmykWKZ}Z0x7gWzg zgOHs&7cqUZ3NzyDyRo+V#2NzS=&WJ!ed!c-(-AiwaE@j=DZ&KRd}SLS zMC6y9e(Aja6g{t4SP0C9bBgO)_>j;&=JqcZI=uPhZxi#VuiFdOylHkvGaW8WWq+#y zQbs^KYVA7m_4}837UzFvds6+acLrBoBT%Q~vg`5Dju#6IPJTux4sBvN*87O9_mRwn)qD)Wv# z4$M&j$2iM|orGk?{6e+d!p@c7PuoDg!-rk?7>x2iFjW zuiJ1sua~n&vwbNm!5$1Vt~rv-oQbeuaxy;$L_HS37w%Vt?M~DwW9F2B-EO4HXqu3u z0CVvPbRj~LAWKuXo9(fu;-eNE!_r`gkhY-HMUllpqq>W;iLF*rDnoR-jvzveUB4$V)L28-xt~@7?a`u z(;EQQV=U_x<>5#?BDp^tp>^bwYVQ$M>4#1loVGDNQkV2cT~x^ebr>Akzu#`wXLf4k zCCpxQREcp4&K$^6$ioHb31zMxok$HtPb{o@8^tIO^E$k<*${~qTK{l>*t?BzLd67} zff83m4ec**S6#3_l6m)jx=rAR94ZgQIVN4^PlI&gUHal{n!Nu@z8LT69z+pR{WJ6T zxk{NSNrI0cX>wUjXx%}wRV8TT0)X>5$e}1604Q`FG;Lw63QItnnRv#~@N%W=WIR+Y zfCNIOFg;QCS&X|T*cS0a#=~Z-PpJ{UZYC|s#M&zk`kB&W7hRF~?);SL5#hw*Qkab)-O*DwE8Ll)Qz>MC&Jjb`$ z<89BxWa0B#jJOK_q1}YH6kOj)0io^>yP+1@vmUfuNENuqCQ_DVxymktI2?(Htj+56 zo7V|Akpa*Z7f)edO~wmchQ&G->;q^x?izM2Yd$m&AsYoYZ&ra^`!4(xsqT&s=(1T4 z=0_h;h+Sv%zKKvf`-pLT&!yS80r%^$0-_jxlX*{9;lRem4i?pKl-HkB%{h zI4i32#HDV0I)uE1e1qBI%Rb@6s?OVWF^`6}(Y%6PsR_^^m#1ek{Te8!OiNF{RFOHw z)6pEEg7_-RgK_@mjF0nzkKZdY*_$B2O-Gvy_uN0u%=yByub`FRbd=EV8Ux9BU?UN` zb3w=j|Aufl%c^AHknco!ay=(g9Dd$T)VBbm$hZwzP5ascM| z5#qP_$VV4a@C2RL`0@$Vua6EfL0(xd96uJG=fmqc*o{+kbi>6A{G^Y~KHgZw)*^@g z5*4GQa*hQ#hQ5$g?*hjEYPkq#>Vcebvqy*$lQ_h)E;06WU%Xc1UZSETsth%0@!1QY zcmO{HVk#(FoR(35ytt`l_5|~4)<|i254z2&<{bmF7c*b32i|n4Soil!xv+oo(=M6l z+P$GEBfjg$ui3C*Gz6rVi*jH4-&@$*llO=fB>Pg;5WfI9{`q?gqF~9FFypv*l=jD& z7+?_!6sH*ozAV(q!J*9(1P=4Ph#JdxBw}Qiv-*rz%uV8vr0Gz!n1MX)b}&+gC^Wt!H| zOpR51{9VtnKwQZO%;C+qymGPdK#GbOKSNsx=Q9cG=s3B?t1=>D+meV2&$huYm@%`p z4_~E_lZ0wpo0Hkm_ZF2=LX@mJ*-wg*doJk?n|TES=V!>)ONI5B??%$UZ)zM5G~VB3 zU11Ngyr;MPn0?$wht{4j_&N}fr}|G~IJnAM=Zj1-{$&8t6wXO0<>`IK8RR#m_=0{r zsLXKE(Xuc7c98q80wkDI<}dx*ce8tZoFVPW%Tn-nzdI5nr{KMx0*yRS-rpUx$W8lq zd^Pp~jxSk57p#%?{BDWO^(*OEo%fWn;OpxP(g9}FJt8PrMjjVA58UzsL$9MA7w!s= z42(Z7IT2%(l5ObP38I>g|72zITce+gKM%}vt^vA4WTvo#<}-Uq?DBUIx9=HeCp1q>9z)yQ8$a<~4Egxm5n`$9MG1 z-%7?RGY6Gt2)y1%i+mNlTay0RV$k!=sWo|2mD}(u`#u`QlyRlNED+l;w0l_l4EaJX zyE|;f$QC7?Q!i2m2A8AG!bVTRno3!<)Vl9)vuDGD+m}p{gm{fOt0n28XR<_M8){UcM=uM! z)skFDY{_wX|JO#6XrlZ*J(jneusRn0s~#Ie7BS=~cOBwn^oN^}f3&8NET{ z^#mtg4KP`aiZV#)U+7#e;iDDaw?w|iq%<|rN;JXY7Z#pDNNj=U^0OAX?+f=?;^3yq zsbh6d14k!V+6sFDbTEt$?&l~|;E(R$0)sE`t)m@OywR}|%?nYSP(LrNFijZpreKAU zIH`DgPjc-^$?L&ZyzqKYp$pZkX|qFAHDGt(GSA3{?KH)cAowf%jko)Zat$c@Tm0$H z=_p&y9`BJo)Z)TW2Il8tJK>bZL@qNgr^xWOmCDTFQ%UFD$TYT=;H_mNP@mlP& zjG!Oxxm#ePk@MLu52TReAV15fx4l^pF=k<(?L?{a_Y+bx0TSnK=2UMEPondg3Wv zhvi{Q4xr#CjEx~F!arPaCzxX-+^GPAiDoQ*?p8rPIZAY$-g=wp9f$b|H>@yazjD{0Cf(81pbw6 zKclLGVhVoQ|NOcf0EP1AhEHV1|1F9aYKFt}9hv`nt-rT~x>nn} z{f}-Epl*NHN$UT+kMcV_KQ$dZzWl%SLhk3kH&^tp*ZZ_{lmG5@fKUKpA1TxT@%+_D zAZS-Nl#Zb$qbGS=eXBlYx7Ypvw3(!yk0{&Ra72I*W?lS=6$SIrxjDGVkJy^s0w5t= z*_9iBr4VD*2*zx<45=u^qn z%xgG(lJL2mKZL|IFWT5JdgM>-PdHo!`3^f4HjNOnp@PHJy!aikZlK8S$2!jJ+$*NQ z{Kr>GV5$*241tLAiw#2oud#GaV{vXrgzbiH6#yn*ko)LM^seShOl$onf7Yj5Py4I; za8F3*vt8MlBqjA~x=l4)yrswivt-7ecb}gPFhsk{Ecd;}tg3tXRVJDQcLP+dk_h&D z4fewR_VrEij0O2Gp<(>Xqx4_#l^+zW$}8Agi&3i#u>H{NI+!B#p6i*kPYQq zyJp4sN-x?95ckuUS8xRs_b}h>Q4%yBV41cN`@C z32yUWNDoMV?4{w6{pB z=AP-UNM&IFh>r%lqFlptba8iOo1AV;$99bo&>Y%V0r^|yN0fjVL~a_6WGx8jWR@Tw zmwvj(>3$Yx>lzA^JDxX1x0pM?C*1Xt21PRN0vGRMJh(_xXe;uh9r+OYg?myycd0FC z&PkX$(<~02NiO@gCB;kRjSBa;yk+bx&dTq3f^MkGB~12b9o`!$`3|oP63FG70QB}c zfi%d@7hL);uBqIvghm}>r^Y*__bU89d*d>#g^khfllN(t_DktYJ{kW&|L~?KkM>bZ zaWU|A{tt5{U0Qu)xjf_sKaO0HFXQILmK#8zE&Fme@6M+`@2woi>6K*#dB3uc*JyAA zW=j%mESTTI=% za?TUW?+tk!?zuH&6!Lw^p83vvl*c-8g6E46&Vl@67mD-uZq+3GEw2ooz7j6*(Z{>2 zA`>LtHi17`ZrCme0;R$!yE+wPNmSOza2_rQ3Yfl3RM zc>u&uaSC>f3`#J{4*f1PXZ6O_`1j{Pz!Y z8zVedJkfd)wU#zbpBoaJs6b{QVRytKx<6uKhivif2Awa*7PQVK^JmoH5`P}Me{$0W zBfeTQkqdZ*!F&+%fLXaCvlx<#B6qlrDo}+^rA@(^1lj$sr-gOujLv3$o2T^kLqvc7 z1}oOgIRYKw_4j#C+KE{Z_kBwk{eQtZ3yw&XMWG}kBkDH4?ELI4OylRnfJ;Zx7@*kk ztD$GnTE3Qx#$M*BRjx_prum7X>8*)y^FA)~0wtF>VlC~n2^Jx8-(*-JcfUZXQ zkn_QQd^PXF!`d&u5{#!NarFYpu1?EsxJR%v#>g!$${p@I`Vz`B;*>!AZ=)Tl&`88q z{Dodr+sy7qE0{j+F$WwROM^e;jd?+E6IpzrUYEY+PY; z#{G(sChOu-S-iWl#-OI$&pW0LMH@&aHo?phei6Os%eU1FPI{Vc_I&5%@z?h-j{mfg z!V;s&)4E^^mo=_~x476tW?`Axj^4yn0@w%cSQ;LFOkr)pM`sA6#j?b0-}4q-u_CxO z)=s~A1>yjTL%N&NUT)jy|!DG;iwxjVBN8&ttJ^b4KX9>qayBA@l*NsnoKZ0ihk zv$;NmSW@{ft$RVoE!|(2J+sb*c?A9l7ea^Xd_EcDgvl4OqMb1toREFxVg&BanICcf zp_X2bk}SN|dJMMx^JW7U{I<{9!+CWZhI#sFIzI^YNC7P?gm?c~eaMTHW?$b)&&8x} zSvH+qxqM$;dpw%PlPb}cbg^Qh4eZj-+OVa_Bq%burkBqboD*N}XRQ?z(Zu1<2TKH< zNl^F-RoFrk`J48~|M>UllE+1gzQD9s>*dewEckyed5N@bJGGzSdLVpcYnpbXh4KWZ zvHt)gwgD2Q2QOVIBn&Pw_{Z{GDm_Ymj}xKrGe3UIurbg%FnEm3Zcvqu^qC2-{;M?C zLZ2zUQOb(on`SthvW)Kp;p>sFEEwnm>#aMPKMD*ELu#*GVrmd8_Bt;*$i&_0cr53a z&nDv&Arf{+93+j)?Dn~xzEPF_h$LRzH4Yl&TVyS#SCs29JNVB-8l_7SZZFYW#;17G!N zHEW&Z!FXv~ePu5f-Fb`cH=RTISr7xxWYQHDg&yU(UAm_R%m$>42J%wYWnWJ&1FM~A z9?<>^X+aJR!byGquRh6ww#1$5GdHHr_D_67*c4to_@j^fcIy2zc5JF3EZz9XF>(|a zETE1*)^0mbeUKAZF`WiM<&CgmDkOyJfL_b}`(M2lLvT)Ve0hbXaJ=71G;H;K^gBj~ z1DNVN@gyb0*>Hg~&S@~CI5OGQgQjL}QuF+zSmS8RKe0IIrM>&eXTDV_Sj@sBtKshv zHnltXpmu8eT+Uyn;QW|0WL=D2-ivt%024F#Mtqtw>Jw2@iSJk)H1loUk^3H%W}Hc! z7M;M!H@nkfNCh?+sy;V3<}?{29iFZ85%C!H&;QtHjK@8YC?hGR`Y$2 z0AiwDbDnvsG6YXMb@7)Ag=+>5kr8lLFw&7yoA zvG=&~#&_jnM-@(h>8f{d>4;aOg#UA}<3fNrlEP>-UE z=B3qMdk>eQI>u;0mp-TS#QUa4oM{jRO?e57QQ3r``=P#J$hHwjG&}F?4o1vquO2k2xe5z9} zg%`eJf!jNeI2Y}s8JyV2>bB+i$Xovy5k&V$t-BM~ogdWkd<>oh1#zH3)Vnal=UOK< zn}I`|4FILMW0`h1w!>0rw_;8clPSEzAVM9-5B4@~$}#-l6iI3bFy1Gm5$9)EQ)ndH zHX2Fdp}k?xLF=PeP>A7WC(mbd?GDz%P=%&C@}jsgayAW5AE2KWzO@1mv-#ed%eX@T zA4X|d`SNq8zh_i=A4@#7H?Tv*AO5z}x2t48Kk@*GS4G!SzGK+h_=2RB-qf=fK#D!L z_g}ut8(f=N?JFAOb9-dW8`0qG@%5giA#^GbdWt=kmN2ygLJi?7MXm9Wo-V|mlIr`{ zRqmR}Bv-F92`R*tFTH}|3a?g_*lT}Z(F~W3_jQJy{2caQGMd?I`dr8-qRqI1T=_J; z?zdoi(Yrq`$?J89Dr|pQnZ)j6*|fzl%jGji;0Zuw|BQFBC{744U{>9^8_u-5^47Qj z@KPkm*OBSGT~)n_lzz81iuw&U7UEGEP^=4qx~EBVy}-MAs6&|t#y69mVmpObh{$&y=ho(i z9!7|3&tbJaStXmjTN65T9HZr#?l0W$u*z9A2KmI#!?tzcUgwtw6H{Vx3>;yp6rMw> zNO`=n3!iN97vJ_As|>sEOjr@x?NR&af~@!F{IPSTZR%J8>YJ_fbv##g((JhXWq2w} zXoB#o)`Itoen>oBm|~Ng$)?+yBJNp)J=Ob~bem?x0P=ALI|0<%|IH+JSkwa}5y8^( zVvoWt!bfm!yDUwb_SPSQx~+GU4pQqzI;Y{toF9V2EBG$m_B48g6MM|suSv_r*SUt{ zeA=T^dmaR*Fk7p(9xq7fy6C9kBiU=B&jh-p{Jv0fud*zCKHKa9jKiOn(JIDTzCNz)%XQ99jN@*`Oz5IH;%B!pNd%wY&X7wnCP{FU8{vcTz__lj>!nH2!?hX5$qpR@X_D z+S^UR?MzkXE5D*;fwiLLzn{2PrgM4BedXaYg7O7dT?-v|d;d4{7S3l> z3<%2y52R(}wNgwrEb8(b6OP+?s63-O`lC96S3gB1e|O7a833Z4j!PF+Pc!Xu>l~M&|*i`ADKKf)P{EAgh4h=?_bU<6F700#} zdf%J&rMv0#PHE~Qa4#p0HH^wOMo;0mEhmwJFz=db?dkC* zE_WW7)Ugdo%-(o(uc|i++FnLPUc5mxt=42o@uvh18Zc)DAkkJ5Wk;Z8-Qpo9kpzyD zimo5G6-m~7&pCLC%<;E30+1|K`kAvYS&U43epD!{*7%vbSrlCWQEB$|@Bmm#$U7pT z#e+q1HKiFB%Z;OQZIByiUZ33l)qXQNU4G&XpR1EtbmN%{Xd;Qt>eu9}?=gI|r8l7W z5CR*fxffOVpE1U;3lQ!y(uW2jjrgrn9DRS6$n@nQFu)ZDI*j{eoqAIQzk1hw1LL_W z{p{`MJz8_WLvcK(o~IGBe)$eqCE5s+r7`r^4SBW5RAWEtfQ(wUHk)%F#L`Uzcwb&) z(aG`eoMt<}-{w@aSnAgdE|5jf=s_NkVqiz?5O&C7IOpY^ayMZR!&`9W-FX&kWQ&Ob zKLk}%NKr57Z4Ob67ip`u}k=j^|;WQxUeen>Z4kkv{h z{QYUMY_oWo5%tGmEZdNqbvE-iV~d`Abhx2BHQ&(heXkhPg&z;RG9t!=(z25Y``d4) zW3;WdK)Q)V0%wK@=n-MC{m1!9=|yDktOp&*{r(TjFg2AF7#QPN;SzYmgZas9Ir7J* zq6!~bp})^IYj7tgm)y8!2}UZuw-3YiDK#OY+!$Hdiil%G#`Ka;dldIGYz zO^u*kadv&+GGAoHywFCheJEgR>+P29q$K3G9~JIrEO68(TE_}p#=0`fGU1|{6)E?Z zvOB=%np)RXcy8<8@jVMhHLDUGBgyA^_Vw{k4TDnx7|?j#9EN^;W=>NR$#KTeZ+?f5 zp}d2f_T$`^D{(iYljaHu9$fzY*nXbzWnyog%$3Bk7)6)R;mM7!`DxxQgB_> z?;m)NTL<$P8kU})0N$0#URE*E^ya=L?HJM-w{nUfy`4JD4A%|`qBEF6E~ZJ=`Rax) zp29ogHxy49^9W~7c(PuEex@@!`TBxmR;u;0-t%i0J>4^&tWvxL^gj(sc1-+b${n2@{~WYT(CY=xYv$*UXN;Y1Mh&)O(%ReiwI3%+z@H zhDTJ6u=eC{HqiO_Wl!H#L*prhA_~t((Bjvdmsn|UES5@j3CKWU^_}eZ@`b(?v$b0- zQFM*@+@S-IqtQEzja{8jDARHsbqb~nB}x-@efDfVqPxM=+26fPYVmoxUqvX!b@PD} z-Io;?m6exIclrIz(@+a=kRj#n2m-ve6gz@~=+kl@i-mDb2Jx!BMz=PFPW~79o zXX|5;rSuj{CJ$xTDZf-U8s~BN#yGs6`|BI(y51gfuz@XuIKEJ?IXYi1#u>h9@U?FW z|B#*iAluix^~mD=e5;(laEJD>(UPo}Q(^9F@(gpYDDL`Nv{oVU3xwSps4;G>-X@9C zVNO9JHkyLPjo{p{avuVvwZEElfv-53m9w@Lr3lA3I_hzJMKM%}V62~W> z6pxos@WzTtUPBi4<8(ReE{RIsnqAE0>*i2ZD>vX0E!9=^H*3fAt)bK|oqu{seK+OX zC}~6MZD59I-uW|m?i5WDzssz_)xm@=C0lR|kuh?}0?Ua&kU#%#$(1 z6G}gM)ZjVV_ddOu;nFLfsdTctMz&Pi758{-THS65obT|X8Mvu78^PSmN=tstf^2#S?aErPv;3U^`I=2HO3z`nJD)7xiw5 zAi96+1;FpZ*MPqG^49ZVHXuvV!22|u=b9#dgJcJ9g#^zFJO-!SvEAw-N6v zd-^_FonaQPPn(vA+vFh(`c^3MSz41C){WM7<*T%cCRi?jfSTd4W-^f$*!P|am5TUy z$k`T`Mm~IEZO`(lRGs_4CNUzy#R%&PvbRinMV9DK_5l`23cT3@I}3PdR$VL?P>{yr z8qye0AD8H*7y^OkY5*4*GztzZLk1LjpiiD|zr?=edK|q0wD#eyQ-Chy{I;IT>Jzk3X5WXdxH!X}6I7Rmq83tKVJ`!L2K24mafcYk zkq3jQ>U*vzU;}O|4t3bqbsTe9yadE|0xRion(f280_eofbx)R70&59T|BdPq`*gFV z!xQ>T!SE)kL1V2nzi)3peR6>6_3syZ7LZ{A%S3!mMIwnw>)d}VX zU+Ae**z~v!-9z|ESDs1yTZwO)j_>4*ccI+Hm;`-Dj7o%96*$JJe2R6u(kvTsJk~s9 ze-MU!ug`IKO}xc?m9oU0-;`|hVcyTnDcRm%>v(jq>EPd(nbA#3H)NEQC{8aLJVDuD z9SxVonxx_Vv23XkUvK4yEr`B*c?7}Q)QBnRRO$dIi_?|5;gBDfq$M`VRl)Z&mpsMU zB_A6Cz}!`-jmsK`$36X0ys&(C!dKVAEm$$grki!}c`5iB()*Xh7mU01W+g(~!ZaLS z19fTpMzGL-a7lkCG)4wa3JFW@Tn@XU5tJmEMxx#rBKk!mTRL&}mA_*ty8G+Ojzdu0 zZMnT93|4~PobFV6;0CLP8;+B6bV-+>P4CSD)0h7C>h`#>V|ae-!@jV8lr+9ly`0Dv zv{{)Z^Q6jO9$MF;{L&bGHUsC=iCpMH(3Nz=9B;^Wbp7)_$LR?!0JdJt@s{bC$1WOk zT}rHExi5lsdGTJ zEJNod<>Eogtqn8KWt2ke~DpM_`pAVDkz^Lc(O?-?z5w00hTDdKe?j)QJd$bcm(ZVVSc zOWWq@WwCVCnj`Vy+YY-k>lA0?X$Xst#9VtdpFa_XEm-dr3*|?t6kAlyWdityfF}a> zUoubZW%csZmA@C@nrlqUk*IJ>vc%z`B&1@3dxcru12<&2;{RnOgi3l3=mM}wD#Gc1=;lAt%EI$94#LInjeHXu9-1qI8y^tQ=Wk%D zAV#b`&Js9t#0=gGU+>k^5F)qU8rOz|PxLQ?1q;t?LD;9=qfFz3Vt$Zj-8XljZc`0M z2=kbKKLQ%cOv5gydfDCZq;{2wU~1`-k((WG3wmQu6|7gxNm2=5Re$k8d6>}NP6zKZ zHD66*f6ou!YJYa|bC)NNVx+U{z7U*r;3zDo{9YNat}>>(LgHc-y=V7n9b+nj;b0W9 zJ<`I_5G2!=&5q+DZx?nL{&J<|rYDwa+Z{%w_N8gDjL|;>3ioic`-H;f7}&Nzm&;F-{SCr!8;T>RVXn^) z0=hiTRH5=(JDT-id}#h~>jf zr$$f<=Q!W`COkl~U_fw-9TbpC>M|#v)>kSAyQ>U|QhsC5wzVy275np(?8pPXO|rr@#vf zK)ZKOlT~Ul&**if*Xu zP1v6g6kSC7eg~ion*dC^iMoMk8k`I>g%F86?2W&GuTzMO~#&}678SS#A0C06K~GKiW$~Jjg?@9AdM&9bNhB$g_w{r zr0S6tBFO;ly7zUr!wcQrbr7;~W{PuW|9PKI5H*7pLI=bgjt?FvspmQUE>}m1y!YT* z?O%6r_XEDz#8Tu8$1{%c?-4us$L-78qJ=8U<*`B~S;!TApPRiud%^jJ1x83sTzEu@ z6=)%UA_{mZFgkk1=VQ2>+4P>ZXsP!bGq|J!??NF786@+I1< zISsOq9{!Km0BK06FI1y-vOa&}O{=ERPY7|lWOPCaVyw`ELqkX26X z8T-!Z#iv&gy{&<}wV%M{)xTZ2XvjZTkbW#X6ZjCiW%;D8A@|!!hcXfSL=0M0EMT~z zv5W|A8nKGe`QaJO`jq-nsxcKo^~%}2e#;#pkJxI#=xHTUekUM(s)J^DjGfVqy|hI#Rmd=ZG}0%Lj>q!OGVs90p<{ zNZ-ycH*Fu}yc@m`|{zO6Sn|)AT)~MEC~*tgT%2sf^=U zdM~(tN;v-q)wni~Zff5kP!ZiC7CNvA{56KpJDLu>C}-j|aU+C95|kpb^WniK4CszE zNb-8cg5k97sqdo1k$e#0>uYNndp$tznNqz!BZx>ow7qK!KM?bJnT0bJr~vbwD(ABI z!}yT+VZx)R@uIbO;cFRA4oYIN{P6rPTARRn$e3egpTA!Z%Y<+Yk|Vv4orDF+3DJoB zQAY)r7hNAep&tAma0k>sRZZf;-FkBTHYeeXInnUA$El&Ux8aQzgb=PN=1J`a2h3{X7=>4e47oO~BwVLRWEP1({qF*Q;t zRG@E#&LOa;PfH3I2>eF5M{F)ckLYcj^=6?@)yj`tL^5>(FKh({Jh-l*%`%@E&S@n7 z4w<|8LxY^i7Og1>mF!<;0|%&LKd?m(RzP<=S9ZEGZjyfe!|iwZ@e%o~Or`YQr-GjI z-?Nakiv4%{%M>k$Tt7(Nik;jh?p^(jS8x&IO6UbA-NgP!cpUJbZ)%v;w|JA{cA3IRUY4xRnI)LsVF5dX{dB2%j5FXnayra zG$WbONNr5rOOq-(`WR+lF^`!cT+gdcW494R*i(fl%mx_^G|f!-F!hid=JcKsCCYR- z%xuj#uk05zSmvAo!ONb1-t&R865Or8%)Bnr<(h?w!M$Fe-?d=md(K4=W29tm*aKot zcOhKQ7_gRT;sNgfuT+c~5bVv#<SuL9O!SCXMBoJYKNHAHZ~q}Zr`MMM34FE%4!ey+J)StEF@4EM7jTZ)g^Uz^Sv7kf z0^(kK)h~b=OJ<&s5=3i6-jr@^<&0AicN~t6TD7?043Q)s%G|AA`R7w>@ zsl4uXN4(ehoYtFJwKv(_2@~^%Ub5-fOcb=%cY~P-LbBZFCpSVWUfZ+UCa)1oQ2_Jgs^=6~C)i^gwVw&J|fnDtE_Y@xoDMmp3XRzGVG$ zWY#ECL#0M@FV4tpb-_Jyfnf&B9CDY$*I`v$WVg4TKZ9y+DxLTH?~$}nZc7!Se6#J< z_&Mre@9kZ;3yAJYzp!(J@-NDdxrBb;IvU}DxvFMU`xhx8ZmQh+6?XOI+IXKpdxfIU4zjV>!ENcL%;{9=S7$wwH zY8b-z@9){77kensyrF+A*meZR1DPI)#Cyk20V1$gtAN|SRf6ijR|c%YV?{^#TteEk zN*fHT(-q$oBIU=(gjl<+hgXWz$LqI+w|Kxb!70tV_zUjZT<17&KD(L3Z-0AFiutPc1TTQQ&z0A{nRTH2rn zUFBntFInK4O6o z=EF%JAuaEChXVAs9Un)QHsuZo=rVzN@Ugx|oJ4~?u*2HG7}WuQm-pWtJWrQvsv!z* zQ{VTT%%cF}51=>XIevF$o<}TTO$|Ep` zh#Y%>idKOMVGzGRnA=Ty885depI7|zwyqn*VM=dy$M85HYfzpZ1ocX=b+iXh_XcJs z>^kpWg_38}*~hH?jh9iKEhMyvCmS#xoQu%d|KJQC- zTQU>juoE&zzxSVC_e1)jmeinRnk=JDViY1{*Vb9-POJjDvIvr4xn8jQ9WOsFxm-|P zj_zuA4@-RQ8n+1t;Y9zXak zR*Mb$>{E+r9P{9gkIQW&8dIytyI8eb8X|cv9C!e?5a5eW#SIYajNdsx-Tfq|hlG{y z2>Ayd)jKC&@fBg@oPh(zEAXePVs5*AE9Onm^NpRK1iq}D05gdWX`yy2-YmQ^I#wkL z!bfZRX)W)-ORRQz`%do@_qa2YjF_dty9GTG{jA{IxK7`tVq^gaNyFqr&sTP>3|I;d z1j{n+2bc8e*uN<(Ypk@Ps26*I?i|f_c!kw_M^mUD*)>)9;O-YttWg1sFB~ui`)%lYU`z7%8iyl*Ti>7g<2_klK=^t+at{Y& z8cD$%T+(c@STwEizU3wxp!@pqq>~}Wr21SG%{i0oN-9pb6Jj5uc{fv{?JW=C z5A?{3hUm%Uh*JV49u;>yC%|jc-eVL20|Ik-XW7)}^HstPp@{qKg)zG%sMWJC9~hVX zSWKaA2cr+%SnoggkO&rREb|#htyab2gIkzuV!VzYv;bfdu$SmS7~+SH&Id$c=t$7R z!ZEO|Ofa7il>1R_%sCYgf`F^Y zEb?UmxrEjt%Zp3~Z#&TR$c9;9R(Wd4>xQV`h_X~DRC-1;+#iiOPMNM{F7IxFAoqjF zRKYidystI*8Yd){*M(KZq!e!-%$NnnaPX|RZd#j(%0r{y_v}6s)F)_I9CGe8@h}$N zm0i%?LVP$MJGGGUqdAgG4sWE20wS5n*WczkaboWsQR1Fb;wAQ3*_=~ljNV(T707em z@)PYYk~^)(2(MA~36WUQY1_}|BI_ z5mK9c)nw!~e&D|&Ul3#)xsB%j_y9hfDfWqHUu)HuN(=}5WdEI|Geh*7^0YV z9U6Z_Mi=+bv~~T93LQeG^vX`|HJ3l{CtjalKvczQm_8p zjg#?nH$GoUk4|8R#V<)3>tEgReRVOE_lWxLx1tSuumA)eJ8-3JA3L2FW-d^Koaga| zTIEDz5sfU#MJ$xVuc*u^(ce4s`?$tE<~w5?%)uh!z7T+0wl9AR(9-q>Je1SkpRg?>2QwyrURu0f{f?w8~|G`Y17<`thy1`81g znsldq3oLol{N;D_>|%39UXugJgXiGmWr3mUsP@a!$@wq$o;u}n2zVNmNuhYF}`W53ytWIg@Y5n`9GPxxvgh>G3s(v;(8Wo`QZkbT&#YF{zibOjVmaA^9kb-e3-H>@lyZM zKi{@DK0Kfydihp%1T5gII05BJW9fJh+eG z4!xf~aOQrTND@6Cv59Gwxu9HPv-;9Gv~TX!gX2f3{X0lHmPVV zXMu~qpFxACf!)f#(tJz3m-x3;;?v-NIwi3oxxSZ|SmHstu%8VflG>O3y&u;0+~YOB zK6J8N!tZ;x`miqyFJ8 za4$~zs!+*qzsJa}f4@$BzIzMA z^?&(RKixo?dpvml|11sbdr^!I<_7H~lR?Nz@t`-) z4wI38J0gGHSp}H>fB%}ja+F6yTNBXY{^$4j@2|a|U-k~W$iMxYfG=F5Om7tTZ-3VR z;y>K}i~o@RFaE>NNjUU7djo0t;rj^RpgkeShGKlHNbd&mm21x{?SdYcumLC65I#`v z?eG5X@GLp72qgeaWo64DR_4yhMm9jO28AH<8LVn^=DI#aa9zZa6F=Av>xq<}yHVV( zmsfCI^xQ5qdfwb20ZrSzk_5B`0}tV+F8bJ~y*925Q~9K%@)H!9k30-cqf1;ee^E)I zMirjqZX%f_uQXY4`esTlH@}#d z9ytU346m;TQJk}a%g|4@TX#RaZ@ucBt$o=MDlPZY1VfFaQfkZ{;7OS{d^84o$1?81 z^Ai^7Mor)$d=l*tI`)%kSEh4Eq#LP2{7yT9`xKH}eq|PNFpO!%{d&9G(J7xnDvEAS0KWc z_U&U;u1xfMEfy=rU4mTgiXj7komn@QI88K+nQMh_hQ)lOXmhr1rntN@XE!qI>~}9d zbz_0<7__vL`#|L)YMrL#g`YbI6NLDk=W7&xtaASjukg-g$Z{T9(hLU-t(a^bnd8d? zd$%Qnrc}(giu~Yq5OQ>^IR4X!*7XN6(jPm?R zLsoC1r7%L(ZSAn0frCWa)*2ZJBhEz62khg6=_^k|DeQeCakcy4682zL+c-Z~-S!H8 zs{C%a)9h z3SuS<4yAa$zKE><79?Lg7})tLclN)FJtHN9q7*s`1|6!kaT0voik<MI!ifspKqMKK3Sommf4D~u?Y_E9QLOkzIeL8#gJIUG;VKavW$5DwxP|; z26qf_me1GKduNUG25C_-0&pUjB4kN5<~SifzWvtF)AB>(y*pbeQv>7FtStxx~0STA5dm=)iVF7qG@ZdNy6NlSUPvRC2_18UYB>rhR(H=G@I6cgI$VB+<5 zGQ}&T+I`HS#`O`I&&oBA0P^KCnR+Ouk>rNdR2nD1GdCiG>F-YrkxWs>V@dc_4(Bux zaJlULKH;neNw(%Z^pdHVr{-v6GEyy32l{tg-gYe_D^PsOZ+|0|yTZJf{jEqKT4dAL z3oXzepP)Sq)OTD_h})&*F4Gl4ZnivY5SLWQ))XQOPwAk2GD6^V2X}jikRF#kvlN%& z`;{K2Ms8D`h!{aQ68BdA3gce)65KPjVe6F-KfOFHX(kHZ=n{PC5WU(;(4YiOWKC?;^bBgFC}(kOd#^dc&1shK9%fC z$1uW?ObBm@U`-5~K8I$bq3X7927HbfI-$zKo(>ml$XM{DoRdAE_=?X-n4P8zDofvhNTvK7fEcn-#!kW zO6~^pUfS_R{fj!qxDvot1?=z;wk-omj+MVSkACV74ox3C0_OJiD7d$+#{^N2mn7UfI=T zD{y-U+;nL(ZVr+^8`X*VXkH8MabL9uLMx&`eIF*#A>KH@Au2!G{mrC5Pp2CC<2PXL z_%hp9oIH|wK^+bQJ{qNKpaLkaDF}uFlMMYu=Qp?H}?(+-U_r(rOz`%=yBE(Q_xT=xgHx zbR$o7{1^*3U30s;T;&%cV>5Ck^SAoVT!NW|=Y~94L`-|~F2L|_;^23T#o{#dP2eRA zmX25#vQg;q60MTa1cK0w5sczYskZ0Ot^g$v!ZhKa&!RBB9(?Ift5FzPsVYT}^GOXh zR`s>ymrDWGk;sEZ8e0cbkMr}R^Va94a>ri!>c*pnsxhAL3=@t|S0}mV6|QN=&K0mz zyH402_8c#5kIU1z$)Q_39%T9j$Wj6``$2a(P)l#7JafHPoI~IkLLlLrSXk!slBH_9 zLMQB&SEXH}+DCF~|)#)aQpT zLQZ^h1(-c%g17nI&;_!91E&RP8tdbWUgO~q59Ep7e9se+-)#D_kEA<-s|*lf8xMt4 zb)eY8E8wc?Qs&=uSoqC(UN+l1M4^!S(o0BX?rJMvFJ%J4eZWFAnWA>+scd(Y%gv<& z2TVS66qjC=3_CVHcKRT$8`Mmf%VD~#)kpf?w%vxv(3OjY(tVRFr_E68!ZmA#d3T-s zjx!%_4`XsajVHexklnPb>+b%dpz?^h$D!GRS$I|d?FDkII^=B;Inj) zR=0_H=&$~puWQi^`Ixy0>T8fFJ=1KPrK<;Z8^P22B>6&~23fhPEWYvbJx;0BQrTV7 zXX$Bi!j&tm$5kW>D`?9ZaZNa&E(``vt&8Ex{EdFuQeH>hh6H8pdfe4}sU%ykm9Kan zb-wa=qE9fL+Y|Xzj_L7;(>xs7=G)9-;PQt1oguSl_}p#deNrEl4S0U0^=7w<4%Bq3 zfdlb9^XME3_;}(W1IZPvHN-;9>cDv{tFzy*1O^@T=!Q_4EQ0p{TwuX&YL9dd4K%ps zCnI{cDq4d&t9wR|7SP%l)E3*>QUK||tck0S039Oj=vA$Eun18WIWAa#0se>lMRGwe zH=&C;!gVnTU'O5LP5iFf=H)GxS(0^=$n%qoY8aHOJ4jI9Y0I#Y*sbr}C+@g0; z!gs?;P&KA1jkBg@UM~3Ye8vDvdhprX{pG^>Sy*~X{#kNH-p<-KKjP+tH6}*PI)EH9 zwozQXp=}_=WOQM(yXx|a%4TzXNl$iW|0Z23sQ1CT%E0gwLtLJ>LHG&_`q@ojz-imQ zuu>7v7WRv?PG$CS_emCoB`<=B6Y|#qR|5TCinu%?+(vUQ_^z0bd>Vj8iieC$j%FnJ z5aVex;xY*b<*u7aDX{={#7kr0yC5z!h9AjSB}wa9MLDBDFXKvAAkz(1SxY-o#yUx& zy_>T6P^B^FpYPaPJE&P>9^O1>3)VX8juIh!4gv-@Jwa&-&}Q?od*AT==Aesr@mXxt z+!{4?SNR%e=x}LQFi@Wm11E6<`A%F$ju%WQnBfJm4Gyc)6XPJAgcBVvyf{6@c?-_(nCzHs>^CZIMre+_BxD8=LX6cm zvrfAx=n!?qJx_W$EX-bPOkaDQ+u{$1! z<$~mTlJMus?J(jk;P}4GcJbEF%l^toISRr}UjDVnX{NZFzKIQt((?Z zjNki)z-kY}quZNX@67JLeCkQozSq*tng|Kx`|$H!+FLZE+;^F8=Fhmwz($+rdiQd_ zIBz|?t%Yz@8ja`o&Ts)AtiRFHltXTz&?gGb(-vVJz4CfNB@#6+yp-!D{dlkb7oxB?%VmFAIhuyu;!VF7L7&S~otk~&t4e%JvcX+_7 zY@YFlY~bN{$gz~Yz?-n&7oh3cNKV}^_DWK(8(<8Y`bb``RxWe;c<1YL1-4$yB5ekt zY7nlyP9ONtPcwR$4lgWhUNC|_i*)-TA z)1;o|^pS&0)!8zRk=Pz00&E@-N`$h3bwVwly>hzBd3>Q|htH=%N1sgbhY7Vg#KsZJ zhF}gZQR>s=!WLW0ly?nqPY1VGC=&2pO2P#@?I&up+4OilPE0whob?+g9PHk?KKLat3Je0SYH<;$26Mh~G#lsK55=dNjf1Y5?App+08UvHQ;RW9ae9NFP zy#dmSN$#LYt=AQT1cFSks}ukkiL0mwMB@P>^K<$7RZ`B?6)|VZjzJ76JW9QKh_)so zt(?)dnyV16wGWGZ5;9#CxI2m7)0(^N;fSGcaP@Rc}zzYxQxhK>6Ii1JP0e-x0^RN|vdHNyHGjQ4`MV9lOuwB<^j`o@BC~AZR zi|sH-6@365(LurkfAvz-7DpVE-h<&csH+rWi0L!*C7R;Jb8P9wjAhVtsM~7v%8!+h zD$AY3OQmeh&nQ|3lrrR#Jn2b0_D@hd@=kj^Yo15L8SBinZJgMFog^InS?n z@QHl$ZC4S^P z#yX2`V{_$AoaYU=xnnlyINFch?dqu8PAOR-(kDQQa4XbnHS!Js2n5>Na~yr#@b>Gh z+4N!J#n7J-dpG;&Dfjb?k4)RahR8xM);`g$t{^H0uV?^G;WbfGX#4v{p+2uKjBF^TsD>UXs0_&NjR9KD%lJj zNO#zh2^lM$XOm+~-VS3rAM6u7Me|(2oVp@7&!dTO_o_pb2a<{>EWZ1NC+y}dxo&VS z=+R|*+22!4Oc^7${%zOU_n0acs?zz$qLT+z2>VfIFuUMjM_8WZrQ#K!H0O;*nMr}% zqjhPXg@%|V##d=K(rfbelPMrD+kV@c+dZkr=d#^B;H9;AXUdB?xL*o6{;>Iso%C*i zE6KIH&E!zsDZnsd=c%O+ER44w9!@jRJTwb3QKG)6lD(+k1q-iy4B4;F>!m*)XMus! zyz~&5qL(F`x}c|{n4j-j{UqD{eTH%4{4Uyvd`4n%A)4zk1HUUW8dkjuZrnYm)FCgl zcCytD(XsW7JmT!1b*c9&uxVUfcFz`nr%X-=35~bWEo@W?;~jC5o3go@4Qzyu^@aaN z;qto7%p(mp20&&%nG^~h1~G>bJt#HHM|zC5S$a)#mhjYtkQ(~0$N=<#f&nk{43 zSnNaZIw=S6t}mt?9QEP64oThYCQ!XsZN5z82APh4Po;>-&cjXsO1OyQ4uhql52ODZ*-S5vw3I$j>-)vbSl9>;pFdc-n-p|Pjnrd zhm+?SbV5?k-P49PW|VkHDJs8fYQr~k=j!M}*oz*Xbzr;!sMkb(zQ$);zm-QSQe4O` z$3`S-=%?JzHKo7GlT1tYsh`(mM2Zq387KLdJ63*d&bLjd0pIL5Yg}XR(b53gA~qV= zMBSldsNQiI$8g)yE&QG!20N)ukz24YS|#P{oqu$&vTtObCZ}I=_d(zYR84wQ-(TN| z;{XqgZ^HDLA^LD?Q-RwEo47kg7Nssd&MT6XjDLY<2rQ=T*)vg$=E_mcRn$*Wp<%znimeirum7A6*k84vrrVzTJSmd2Ij7{lZQEC!)>u|46YcoA?Q18+R{a< zgIV;C%yt6QHDRwnh}P#xjj!r7u<3UQ@^bu$!bNhV(kTSRIA5*gUcY}Q-jp%LNAcm` zo8LHvsf_-4fhHxy_=Gzgy(Lr5?h$HcGS9eU*x+YiYsMhqMlXjfI|nLQeFG_f{*d^WY^!zW+e0|MFa3mPy;Z zCA-{zj1c7e-r)3r!(k?ftJ#zgfAUK1N&cj4pkHDJD_JbQ+qB?|sw3FK>{FqP4O6WW zaU&5e%8I_I#>44MNgVUpK9-g|zK^2JvsmzHZ<(#U{E#Np*rVH1rO-1U3GF4P2EhWN z{%uZ7irs36H1h)aqeH-=j29|;?lu1Ejj9SgJrX0hk29WZ&q8`O{MS+N!v8%F!B;^O z(RzHu?JvuYAAWL|T^ zm69zcmSkhUxr>CYOvQcZFyP`}->1&V-&G1<=yj?=3c#xW=FCm{C7xCd{)Yvt`|bFs zqoMB^>$aL4HLaE80%PY-Ops$}KPmlg2#+&22vV@N)*Ya;*CR!~{gjzyv)ROE&^*y? zze1}W`pEmin~Tfsuz$N4>cn?m1PT3*1Ea0{}wSesYIvy{igAOv* zdlbO~yOhV+8uMraa&NGF*Vxh8MjDqd45fp2O{Vrz#dHUkASUdsv(`a%v=rw1CSaTb zOfG5dxnF`|c|Y{gZvDm|bZ}BRSnSm7n)lM5F8kv+zp)1 zhunQyiQyJ8Nq_fcL7AJoL--M;mYynkfHV9a*H?i8=!cIchY5M#*Roek6tsXIk}Y;C za+qka_In?XoBP=876t+w^yy9lY3=1F4|nlCelj>j&FCb4{Jz2q;))xDwmV|1LR{9= z8Ui$b26Eom8_h>~NOoRyf1aGyIUE^zT-5@+RLKTO=u#=1)GHlR|5(Q8+xgpBUZ~iw zFW19P?d%Jl?FRUawzD3T;OT9sVOG%Oz=HKK1$6PsorQ#lz-_JlAffr1stZV3RZ1|j z?`)s?_e1IEQsL~39O{R0v>lpYBjTSqNOH~Sd|h8pjATS-YQg>bzVe$CDKBB$0`eQ| zI=WV>xS>6QdYn;lo|Bh9ht9$x+uzDGyI2IVc=dmm_@#16@lEayb{#B)q= zZwv*-`zLP^H+=i$4D+ZoqWS`z_jFRyFIeDJR9*1!s1i^+-g>^}CFh&uNM?gOAkqdZ2Q z?Mr;h43zFhq5r()6)dUP6GCMpd2hjHM%5?U%f0yaTQ$ZU4o_t8^wksgkXn$BiTC#T zGeEEW9mY2Adp@sA6PrlpzLcGIu{$ccxMlhv4rR)!X?S_-(EYNOZORCqbWHktFRK?q z$N;Zpou9>S8ys1~ncC+$TTbInIm0Tx3%d>50TDXCF;*iyclzDgDv7w4kJk;d&JMfA4qzmnC-+8*SQhY2F)o_ia{O!pD(O74jnIR^nYWLN4om{WR6dtSm ztnDvtdn?gG%nR#d=Qd4su8HqNY#JSS6fBoMzHPXhHpIi+1Qn&38`4gM+kQc5WatkP z_kpVhgc7{C&{4xNqcV&dm~*G(x2wQJACkyAU@N8OGIoem+Tm+tKa~=*5SLc}h_9)iMf%vR$vNF=-Eh zvWsVRduyC3kSToiB}ORTT5C)Ig7%T%%zOCx{kIL7ASec+v**m(A0c(Z6!+)8|3ur^ zN?59y=6O}7-{-?#TfP)=&uD4Aq6z144466%8B*6_h9v-mh10Sq#E;vdbHsiU(8FcJ8aZvX1grL|PBOF#AZ`CTqMfhzmhgjm_s_1+o6WT=RHrrGhhRs z(q|$^dtTVN0d=sy-&V#b_?zDEf#kFi58^Y)u?)OWescoUq(9C0Q4xp>X^6Un;Q|6+ z4ro*xVnj8y1-}|S<*v)y9I8gx=4jmUbnGKyQ zeunj05xq7=>7%GMA({@zzT+e9B_!*o$2BG@YGsI?;&k_qt;>&i%R*<5c{RM6<_TL? z_8{2z*Eq$&2Xt_A5Xe(GD&BJz;>t&op|0@UVc3@8w*ant)R??}GD7mPy`$p86w9{+N7n{#N)Cai#|e;-2-4V?q}23$9T=Q( zFZ*ND)>Kaph#?JgcxHgqBT%m&DT+z&H!C&*mzF{Fu;Q_Z=N^PazO_RVpTM=d`}rF(h~0HF zD3to?i&hX7<`W*AXwsEHV^n)dsZ8af5AcOdgQ~{CGWq6HKC}}i-ZJun;IKHu-6${X zV~NHKf>q2Dz~CxsFlNTi0Ib?rG}zu4s0dA6U!EixbhMkh@<$5nZiNHA5qlX;2Rr$2 z+W|PI7>`p=?IM$u#d&9>2nbRAB8>-T&}>JPa&hzF7ql@dVW@lNz!8ltl!u^fdpSJX zV(4V(ejm}-G*eVb9i0!408ce>hrWa!Nv8$$64XMgkC_fR$b$ifLYFIbIX=W#06 zVZL`JU`g_dkB3-tr%yQv`yuGKJ(<3)dWny!KYi2huWuUHhAVu6TLtvV%VQP%nh9zZ zJn_=OjQl#DzghKTLf^!23^5U+py1Ytca9f{bXSA?xkT=|kD z>OyuEb)PG=-H8@vhUeC6 zgDjOJ%`mQXX^;>wl5LX58gR}O#PPi2IvNY!>kl`OpviW!X2SbkXh9F48K|?JK*}Gg z={Ep}zch!sPE7B5-EDt<+M1A7<0I+-Kdb|0o6>QxL1P0;_GKI9pToEwB?q_fJGnOq zjwhc~{=twfcJCh!_ERl>>;x!fP{z67Oj+Mh(WrtFom{%q>#ED;?WpZh8 znw)*Zxj7K`j1DS@jMA&9!FLtBDN?IgcKl_Kc4j9J zW|7yL0eX&B-1;`)$XG@xiex+ojL)FxRa!h4*P^w-)jS&aC4__-$w53-ghGYkh-sP+ zF2Et!zx@8GFCY5$`b(BIg->$03Q6sBqKHp2dT)MoI()bQeEP5|h6a@C{w|ieXmSTf zE9wmw?Q4(x@Qp*~az;TKZ4%>V1?A>+*Osy|?%&fdk6KeXfv*2Fn*KXL0HDlZ3DGe~ws_XNYq=>O)A5RJC^*PfT_Jmjq-Zq}*+lGBrb7R(_AN^bp+c~ON^}90e`hRz7ua=XdK@aPABXCtW zJx;Url3)X67q??<)wA)K228cBw4|(R|<9$c(VoE_UgB34C>6O{=d-;J$zf z$p#+-4`0^bJHJ{@9lUk&_&&uh%*3p9!#aCxKCV=_2oAH=&H z07xwRT2Qz0m+4xWQ+}Pv6L#Y@+I+H1NKd95@Fc>W(}}lj&!r275MiLK+M2SFnEt4ow%+ z5VVOis9zie0H%-@u~qKgVBNu`_e(ji^GM*PP_Fb5*}cyjy?_0Hhym64-v^3N$U|Ce zoW=w~sWP;hXO@oq4lu1Aq0{+F1Ev%_;%VSjXvov<%Pkm?`u9Cd4l6*C8_Zo7q`blp zM3g!JaPJLHk_O_#rw!~9p;k`^G3DNC9mNR`Oq$ak@j4sj&+Md;nZMlJM7I6AvTbe( z?uxQxVU!v41y^F?Cz*7%;!nfvobNLpPoA(Z$16badpdpkV#!H6cAsf*UOb8OEn2|w z6s?**DJ9l?mzt-p31;GL`=%CQ)X!h=zPcl{UnL+3HWCIPVeX3P7)xHwg7vLQgFss{ zH-ddpni&fJkPwrfNtYSN`dtuOL>&qy;KDmsNc(5e&$@od!7qf`qOy_MFSmenWjZ6Y zjoWe%v=;^=xI#SQ(EM;;DsEYw&~8SB3D*}%!+M={xLE|p6?$oD8P+w;f}uOVrrO~9EmO*T1z^6R-wOQB79@75 ztPO#MKX~UMk;RMXQU9yk${ZjU71Z$OZ;sV}Ih}hRq?NvZcJm3aN+2$U;0BrVukVU~ zxknS?2cACCwSJ#;r6BQM~&v z=dOA&xXb3RE-d!q^6i_RZvX9k7GJyIB|c_FTkQYTCyVuCv*Faj|Eu?Q-No#G{PWRR zgew@7qvHOqi zDBRX9==%HW{I8DdpI_In=Et8;|JzxOaV_ARU+?wD^ZcUFQ}F+Io~6qt`O_0z(Ux`h ze|mz;T;G6}hPL}} z-fio>{QGCFJ-2W^8xEx1_TPQkJB9t*_xtBl{;8`jB?6X#Z3s^uLLj>*z&!WTbMt_D>zJD&q0}{ly zn}RyCpfs!9qZkZI`|*0jzXv|6yM1HvYbce2CKLHMc)78a{BfCC=7)^j@9=l^90WVi zl7(*ozWUD@#>?qmMQlZ2_v;vM(U`K!sf#12fD8`42Gvthq%k!H*yx+Jm(Fx{qTyqQ>^B!V1vxTdWf;$X+18dR=%OHXyF9>V8 zsdge`Zf63%T`OB6{ZccNP-=R}Yv=n$Deni6x)CRs9=Q%R@;spRc)F#|oN2e?R%TnMutgTG6m4cs(5T1MBi3JaVih#Y~lm;@IcLWy%Cshcw%JBc5t z?o{pkpq_EJf9y{URq?wMicaQM`QX7E_x3&;D&g%MLHvH1P|^0WN%DLS0Zj8F;@`A) zbpF=&r@JPFvXvQ{+BcBP)lz%sEl<|0wuLtsCWd-=;f)9s8G3eo%v*Ade#JQ?Il|O) z32ZM)x2ZRAQxP;5u^_}NuDXe*KHrb6GlpDbftSs4?U6Zo1KQrGByJ#fd4%LcpoK>x z;OKv20R`DOMel)f@VLq+M*eV*+h>E5vy8G|JepgS8{OT_+9lrVUjIgl!p{rvm3mi$BC33J;b9~|_M^zr@Ksrvc(CuZT;WK_jZ*ovzd48%b?$_Xb-R zv!d!TPU|YJyAM7bpG+Vn?z^HytI)>U`NzM+J=*J@E@3H+=v^u>}Z^Jh2UW zjFE3pKZzp(VYm*VH2N@JSct`YAc=^{tE)Fp8v8tX()~-Y;j_!ttvR)%j<+dGmS+_R zabMY-4G-8V1;D)wsUYEIrm0157Nigj0s zu8>B})NS*%Z@QFxiHEOtJI!80iX_h8A5tU$4BLNL7wQav->IS+NU=kSz`dd%G2$XA z5>YR5niU@9y&cj`Q177t9buKm$29`|A?f-()$d*#=feNG2%9%nafojz5BOfrD1gCZ z9Bs;=Kh=jde&OKC&w+NV9DITs<(-7GJ_a|X4~lE;G#15v76(wkHYtsSQ$zJN_1T%f zI=H+|#vMNF@gA*+j$N=~O&-d=edF)mVbkZD3c}s{9MbXa@ji%O+2A&ZJ>3M)9SQxM zQ6A4>HV_loYaO6QFcSxOl0b2R-0&*SkFw7zqV;oX#Hs}RHqSS7q87aJFayX18r>#IVInH?&xQ{y}ePi26_(}le?6kd<4!DyYD zdA(?MQCM;-YLUwroU$GUw&+pqeX(^G@IQd~i1d>5b47Va;?A3h7*EHk0-qa;( zV8*q+Bh zS!pchb^y%l+8MC&9?H;4=ucjMATSC)_5su&{0Z6dMav@}me@Gz3Hgy6xIK2T;!Nv+ z(sX`o=NArLvz|Qcw^4@tcy_n_@B|OOF_G3p-4LOKTrcYgp^el6Pn$p8$J4yXj|%6Z z7IV^(?j7)Oy|-@ia?4iQBPc~;cg)P*If!>JIo>@0A$BHGw2~f5qg(HdbBFjHlOYHm zw+vyyeM}fLBjQjp8Jouwql_;!Uiw}0KYO&+l>ch)!97R1TzBnG;fcWb34YzyM_22PJ-LSkMYQ7sa-RWF@gB@ zM_Y!(UR&2GF`cbZ5#i-myTq8^FPR#l7rZd?%d>v|Q2c&~V1(cMPkA2jGiP)aKl8&C6_>Lcp`od#u&#*cGJym7 zy$eQ~?+SNF9qKht2$_Ec_DF7qPX$FyQ}bWhJ{-uGgLo8SBeC&$gjZgP%j$SJ*c}gl z+Mw%#0*f^#3}RZsq_{mA{i!$+@mAB;TV~g>dtT3R?J5G&#Z+l_YQ;s z``iwS<7t0)Zh$wccs9XYO%kP?j^8(nwF)GFh5M9F@+yKhgrKfc$a^%oJaQYLg-iQi zAG8NVi@{I?aVL0p&gO_*%i9^`%T5i+dHX#`OC3IyY`P&O>id)L3-4eIu^X}2ke>p8 zI8Ks3KVPwh@WUNab{k4j{_x!P^F4!aK`Y3Hwy81D{AJb^&grtl;mZP$->f(E;L_bo z;>aIt8hq$+ynsOn*1LL-z;(!~WAf00uJF-Nb{LRY815Zh&s+KxT5w<_447MByWcpcUUApbL& z?+?U6lh@8?5z|cg5r}Vf32DE7k9TSYo>18pI7{zZdN;?O`tZ^NF`0z1r^4oZE)yaj z{Jj)BFQpYpH9?K!v-V5I8N3&b2{kYDI7c0h`E^@_+wLZq&zdq<2VPU{pb-~}zz(H% zpN8=}$O3xP#_TG1L4GNm4l z+iv$|?Ta&A*B(s`EYM=N=Pn)Y+vfq}#s#v&E4emu4r(kf!pvSgW!QTues4a8bCcrw zu=fBXwmwobEcct)TGw`;84I&M2VX%xC_SH#L)!%^@Ze}+#8k`rB!@{Vf4Xd+8+PtI zKJ4bN`(fy@e34BD-Z0X4a(cR~0zESDT~*>(n<$34D!)?*kGcgzN&)(^jEfj zDevA2ki~3h!X@3}uOtwD8(HSx_{%V$i#)*zD9B1|G=gApPi?4p);`|Yu9PChDFW#E? zhmRU((n`Ti1W-uFQ(b?m75lz$a5g29J^K4uE)2e|sDnl;k2)oyKKzbNk7DID&+FH>+Hz;sSM)E> z;$eKH}z;E}E)87knGfm;Sr=$ANJCXE^|6&jU_3 z-jkf{g`O;FaWRN%fGIa)%FnjBW5N6MdBwP`zrpjkvkQN6!s%Yl^G zGYzg|?ma-cBF6D}u-S0<%5&w;=CQqeLx_r39W#KpD_s=E0VXZW%?qr6*VAc73e+}f zYUR@j5@>&X?|sT7%Ej+(>|Om#L`-6=c~HWYp?h?Z;jSTKl!T@H3O=g*wuo;}l@rX3gUTrVA%ZG>m&4 zow{aZ-JQ0y#>>gk*b5b`n#pb~3cHw3d)#x-|BDoj9kFs61nN<=C6y-(v%ysxyE5-- zf(*`3RyYipvC`IpkkP|?nORGm&~TTkc#t||)54l00?e0O{b7Z3mo-Zhgto7U|Btov z*mfMclI#az0PlwMAV>lr0m97)M-bk-ukUzLm87bk_3A;cS|w%bWzybzPQ>0PVE@nz ztorTT8ug3Bz7GdC%#Al(SF%-CGBo~9yWJJC)A`|^QxopX=J3ixFmEJTwP05rFvsp; zav;goI++@r(DX<1F|go8IP|U_!heQc@HjZO=hQ>|9`pH{1*^091*NDB4jD+9G~#;| zA821DfA^X{++%i;VH+(Uh0N1e(CZ){e^i`Mjnz)2*ZpJX@7~&`YBy^&uyftzs;8d5 zgY~+2L;QuW=zMtc{Te#Y^M|{s9jD)r`|J^@rj#{EB#f`6>I(8vAcN2979uYD>3h4b z(V3)_`AyD|aW}lkV}8nUr!!zNillo(-W{X(SuQtPNdMzQ{ClF2 z-2u^-N@YVuf%z{Vh3@Ed&$%xbBsnJ(q9uOCPfA=ee#;RTk(=dn>C7A8kD1d|dwihc zeYV19HM@{^9G@R(A1y|ISnKuD$z+;z_WiPX&;6Fa@24cM6~(!Th+CbW@-f8e`U=c@ zcu}^~TNsUYXYobm?NJN0rRxF0yy;YzCwVdij-BQm7Rp3gvl8l9yH`|^!@3j$u*yXD z7(#$2n`gb&m}Qa{iuLFH{Cal$WaA!xoWqOzocCPs7&}DF_`)UyX$qKmxSL;`%x{E- znC$y5?SN4=PE}>0;Z%OZUF$vWr>^wDVYNtm5v%tY9mcmui_3Y>AMa*D-xK23E=P_$ zeS3g_>zgLV4sqIy=)?PH$mr&x!ZU&N*7DG!axYknxGq9&{SBAGId#Ex145A3(id z@%V^-Tp8de#F<@M*>5j5@$FgUSfQksTr5gm%@ov23$6&3=g!1YrhUR5b+u3iIXN`H zY9tH!)cSni?$x~)+U_poL_3dV_oU$Fk)L+3+kZ;>{K``=`oSgF?$KW|1!*7#YaI33S#=HMufvS%dbqED`$gliLi0Zc-i?IZy0Qk=f|U|&u>W3?CPLq7(B@+Zu;cP$-LY`A=n4JI`5QY`I|PR(fHy}St+KGe1fC+K>lUjzci%@zaLjOUHi*}LVWM)B|Q5Ld}d+J9<7TZ18Dy{QxRGl)O zpO0!n0IV{$`?h=-fx>^D{d#4a{jV%9K%fL@dmvjR%n*R;bB_>-vAVYySSI_>anm4k zqJdRJHC$~unA}`Zfc4=3;xKsFddmUpJ0(IuX2ySXY{<^x{0rOF5NefgflC9FqfL*{ zY-+L!^B4UxHxlKfe!J=ydmN`pgR7-TiO%V{2Rp!}uuXRwi=$bRpiX}AkuL?v%jK2e zuJJ}CNP!SHGkRRNM;h7r8G#Pz<4zRn_~0fG{9jnrzq-Ht0Cm>Oa>V^_}~ z!*i%Xc?uEJDI;L=50F#-T(knpD>z`Zn;z*>IVC-BJ$OzuB_nzW1^19Re=yNCw99Z` zt6^>r?L|E~omgUj109mYGzFNm_n`Pb$`AI8d?(1*TeEz0!nKw9s46YexV4VHg3?Gl z2=C#It{}ayX;f$X=ZoETP2oD>)(*Mf3e@q|^(*~2URUZq&*EFXbg&ZnzHfXHE>pvZ@F@ z0a`w;REdp(t4evnb0OF=W;?JI3+zBh|9AIeH-d;G z-}7aXghcSTkR|uH9EZyUg$9mk>B&BS-VndDqMU&TnOe`S&LhpK-=E56RuF$5CFa!( z5wjCawtG9v*~~}7!@_}@g+M!urc>Cv9GipH2zT)@VoZJOUm9JBDIUlN!am5fdBAEM z!@pgN4@}zk!S=lQ1p$Bj+{tOmf8(VpaJa5#9z*vX`S z^9;j~?o+LclE@}u(kU8&PwHU=J2anv6`BmX_VgJ)i{!ms;5*tVCJNYKmDs(FCywRRU&#tUd&I!>4)eE)Gae zQz)s~iLUsKehc@ZQi|VY2rcC46X}TnY(CQKiqOxuy}~-6R7w?M?1o)nx0LFK&L?g1 zgXd|zM)gn3!7wW;HmP#zcy6wUqDjA-^W35fVVUjwA~K9Q$XnnR*S3IAfc&vtBGYfj0os0o@v-C>< z@g&Ch=s=Q$7rnKYgfvMnM;^hrN1Hvr0PqkgvVedN^{C=q3bZZC$Lhh^PqqV=qd=ZxBwn}8J@)cbz47~efAROv zm$&+OUcf=N^^jggrOs_M2fcVTE}xb6N)b{?fZ}|r6p*TKX_6PfW zi3yC-@ zbChm+PyQqzvo0;$<`apdf{K$)IyYp+Rt@n?Qrw+Hv?}xC2Tf&HjAVihK7%tTJp2Ho z`%;Hh%|6T+Xtu@ifZcX9o_jZiXXp$1tbECZL)4Ika0Kuaw|O4bTbE|u(zKK7n-H|A z^6S%@-@EPgAv^*6-;r;eW8X@(yCWtV;%<4)Q~;prt%p$lmAKa7IMK`b8vck}x9;XV z{I1hox5)j|ldi|A%}c8evp z>a2i9u2)Q$#+ImRqg~g{wvg`E)^GNh?W+z%dxw98Zvznq@?vQ*{jIn1IR|j~s+{Cc z8Y=G}@18iJeZHkCs$Y-gNJ+327Jhr-zb5?hsrBAKJ4k~Y1n)b=&H1m^o_}LLa7U}< zm*MVS7}^#BKVqWK(XQYc9`|Vjkzsm-qRmNv!I2@#6Kkd1&P1cix#)+y$H?P6p{(*b zcZZ4>>qS>uzE`T*E4hS{_%zSI#h^;$cR!Fsb!6oellS9#E8kCS^YDfFrI2Qldo&HQ z@`&O(&&+Jl8{B32#`i-}`~}S%DS0E?0hv%A+%O%?X%e{6S=vYbk2=Ugiv#v>H`*`MQR*6M1$55>cKka62?Q-*}uxUcd!4_LxVeTlwni)F;v}nB@q9vNFi7K}`ex zlaKWr{^C(Epw3d zvs#@AtH88akZM>in;i~a))5dHeapYG!U$p^y4*n0U-M_-y?k?sFNMxeQW(mH!9nq*t|P}=;^9}_b=nj1paW5^~z!rC?e1B zV%^RTNVOE+&bPTnByfK`h)|hrdnpYK;8u9qs&RT)>hvpJ3)|Hhp4^gJifoCqlT^w$OuM!xhm?L%4wiJI9am)QS zq8-;=+uXr^^EU?K$SzTJ&av~H{=}H#TksbkjS8<@gy63jXRP$QwZhDLoNn=?&}ZgJ z6ghfD`~`psC}yJD)E1We7W*GOld~Q6Eyw898HKzylbXj;Nc#=vZ%yfoMb!|!`xU3Y zwuhVU<(r$>!+j7V5?rINtS!RUyoW(No8=|AjV6p7a(yL_jqLIul!yl<11sRI9x0)k zQp|O&pSp{cJe|W||8O-g=fX3Gwc|~0gr`K=oJe4*wU}#y#285)kcE%hknK7=J4}@QPEJHBGa(FYkfzY3-@!3ajh+^5L9R$I+{Am#2ZYG8A*Ri&J!ftaV8m+Sliu-=hJh1YQBqp&Ynmb?g zw?LO*@nv;YD)BMk4utfSb^1IF__DNj&i98iz-VZuZL^tr?c=)F2dzOQdg{`^F^jg* zFvOJccr4TrDHZASO9YJ!R4rg`=uxAIMNzF3Z*%JwLU{%d`XyV2r2(a%%TMaviXhh8 ze)U;~VBYnY!9OamL1{Y_%e^bJV~31R_>Sv>5oE~41Vl%B0}Xc;$ls^gyN>E~J<~FW zwzW?$0Hy9{^VVw@v7O2f@_E)LKbme^5D^2?7+;`Qb%uZQR}s!d=E}YJlsgO*$oC#! z*jSR7;S2QKTbIY@I)4J8b!>$&8opK*qn!!*SNzVj`ar#O~Yi?1T2HMl6&Fk*<*FT z@rX&Px$xpmr7240xZhQjXG1Shf&xAmy$>EPyCknnPn!pOi9Wv@vgvxF;G-L?A1SbB zyQyNpp{P^#;Blx>j8}rcUx_0nY1bV6!lc+2O7siQ2Sb@(vqUHz0W!KOI=0s}i**5I zDLfvI-Spx>XCeP~DxO)7TK(we$P7-ZtHAc5*%JoUc4ulVf#2EsZC) z(7cvCAaygJA6ef2NDZ2-(Rv=xwNn~5^Qjy2KweT;l%KL62sdmwh2?&a-|col&f&V% zLNVB#R$^@+s;39K+95DG?#DK7rhPkK;N2Z0t*RzlsM){si#oZJ^I+i!-ruZz%#vvv z3v-Dp(>CP%jdkIO(aGm~vEB(3R*_EP@6-c^kaG9J!K@m3J>K?m`1BNPzynoOAO9Yvw2)661YJ6z}}$ z51JnV0BmFTks~=b-vwPX?BnOlMfEAYsfd&ylY*%+IFIUd#>!c1tClYtI9Ho>0TfK+fz~0h+}^cT_zV{7j-Pf8VKiVm`?2~ zA6O{tb=>yv5fR?jq0F+Ry0KON(NhTOi6QaeJ@?58U;E0DzJ{39yx&c+ToSA?Vx7Ren1%)ypeE=dSo2O{)iZl?^i>PklG-gJZ;C&MW9CH5} zd)iC(eoKx9;iTBVA4^iN+GGUQMjO!wM`Pv9PNK}IZH0g$=E>jT zO%mfJMrqX4spt)BbgnG5u~y(pyp2J{74ZJ5vyaLnfQZBD@wE8+RrsYUBLmkbxl^kP zXPK5|>H+EJaJJGxpI;WT9ly%G5BwK0zO!CIjYP=)6I_8^W)5gsIL?C>=+}4d(?l0KuOroNFp-X+RQo>;Q%RX{F?K zQ-Vy)g$M4wJ<-_ZjH&{!Xu+v5DG-bsAl{tg<3e;4*--CZFY$Ch<1-;Z2o0aLe;r`$3 zk*hw5V3^=LF?4?~vN}EiLB~c5Rx7r`@`x6WX>}Z1XKQU=O(?L%#ZzzVF+in0>uc*FS?CfjGxBt*WBix1d zqoD<(N=$+JYRjC5AOsynYm7WPFXpzBYQRG{&;|3O^G`S8L$6&y3cGSLaHj8|7C;g~+VEghLx z@mcZut#!+OdY?EURD-#3$#N4_>`w1RC@&ks0wh6t7981S6%5r-&H`Ja@_}-UynU_-F%y}DozuOhRbwZs`2W)ZS8 zhxo=6XQ$xh6BQ>Qd?Vqns*V~MRWXWNB7I7Mlex3XTyw!WXzd%~a(!KZmY0QlFyXJ= zF?8cmC3^^%nrSg1LSE^67+D5>LnS0fAAm;$jT-%qx0I0TQIE=X)D^@9-46EW-0I~5 zN6$na7-oaClcK}V>5G!l=bn`Z0k^u``PtSDUuy;ff!cBTgDdt=k*AOwXMZ(PSd)~A zlO*|XoU^`SC6LP)wDFZG_B{;YyhpjY07FeliVW-Io%_K$Y(RBE45Gs|D zmHX%KmjwpD|DC)mn3gsn|M%~gw%7Qk?_~L0%OS=`>M&^{=7lP(=F*C?h%{r>l#JtoIA6(xLv3$6hJp%Mr-X|9&p6>UUS(_v-jCjSumkkLLmLoB#Pb zI4wKO?C{uk|8GABT~n(^{`!vr^1uF00#=j%|Q{%eEslm+geh0${{?Mmj z{(3tSxKpo)xBIs81o_jXzg__4C~u!#?z(*rOC*(MBKF8p+Dr={O|U@lEK1pYHe$>2 zbl&e9UgH`EE+PQ_Gvtn$Dj5AAgA0xGjig}8Gq=Yrikc7~ggVUQ>U~Sy4ZWmaXMLkt zWb?=HL-ZCsC$a`@32( z)b=BY`&G4zk3$$~=!a|FKCwK0^vjlGOv9$!xbM(3%eY5u-*ADsiyQI1aQa2QseS7< z7n2-CAU@x3`0S7AYqV1UPgWa|T6qP*sjM;Gj)`c~&XkzJUU&7z+ z>V(JNo7`QyhgB1azzt&}KC?fYw;(sjag4P)obHEe&`V+7IUB!Rhj&+mSuK@_q2v=xi`(=Jy z&P`~oBOgwf3<7s4S9D*_IE<$`6`G*lM!|)GL+8@i)1wrBr#%}V*d?8ozEd@WX>(iT zjwDr~l26q0?j0(2DqNp?`&L8;>#^xR&T6IG$g0doa4K#PZOt;K$#F;`Jo={Ay1uK( zCnz^}M?aWTB~DusN4xedeU3q!EYFtb?DuU{n(diLNWY7JGXr$UmymUG_!9M4d-rLy zJgi~QgRmYC9?+ZAO~cd$)3aj>Fd(1KNh@5wCJ>Rwbc?BxX&x7AH&-VuqDr3I?=H7m;A8-zYEpDLA zlZm_1LRC=Re$xrv3;KCyx8L`Yha|3mt$zz%@F3i}K#tcVE9JZB{5GU&Vo&I#4g8$0 zdi22o{j&PDhD10}p$a%!gRJ}#nl34kKN}0Kq*o;t+1lbq0FSAc@3s9wC2C9PR;Jsh zPo5(-TwY;rMi(=y&4+$DzOWwNfgL+yC8A?WVJ$Mzyfh3J!Oll_2&hD~LA8pP66|#v zxTr*la9kI6sn<+Cwg*0}ia+Nrty0PT%zzKL z4vBg3il2+L9T5OTz%3Iu7ds5r+w%uzIP{?39!$B-la<~)R!gwdAoF>Lg9Bm{VIrxE z2$)zPX~sjTGV1=IfJViUyU#((L*Z$zHv|E^;_X)0K(0Lbj2La-9L>r)TnG)|1{D~7 z;b3zJ{9@xE`)3oy)H|rH$V<1-3qfn0c_V6}&^8%!9Z9t#a{D(BK>HE709m@HL2*!p z<&q%|3k)EJ3nPV*d*c6=pBy)u-X}mO;uIeBt<`WS+Zl>T3rn)Zw?q4``^&saE|I9p zUELR^Z36Q-90%~ZO=Q>RA7}lLefS_QbD%%pz8MHmG|$dE+3CXdK-Qa~s|VK6i>UE9 zQSA{zJ-gTSBW4K}hB*&2wzthpEy{f{^JJegKxs*D2tjRTgswqCWPYTjSyJjBg5z(l-{?ky~cmPafLa) zn4$SGpFd2kdj7#NIy+gDEQDoqYh_>GFe9c7=o8BiDgW*Vi+M8`&Fsl+^_9=&5EXZs zRTvNpM6yedGT~|4<^4AP=ADNy;iwa`G*>;SWdG;hIRoF%+&6z6p#9t(pQ7;EiRYT} zE&QtnAlJy#qsO7#;a?Z_wAP-Do03bLEs_Rvrh!$&&iYcJs4< zPgr%MMfv+glpmaUHUYCR8QlX9kGP4e;P}`5G=Hoyvd2pJ+o4mp^RcvE&FQa9kMcka zQx?3gEB81Z{ay$OTiLiX)95NR1`bFy0({FX2Ra{?2EQ2wl(uy3arTKqN5`2EH3oOc z)Z?c(vE1epm6KZ=)$yjM_7Bj_ioSir(;4rHNn3|AasWawd|iGU>|KHn=G=uZy~82z zH3(58TJ7-IpC3T?QpC`rv(36m$nVQx6xgU~pT=!UP&a{AYrp87yZ_ZY2TYcquScSavIPaa{isC~AylwY)5FUS zw3hthxy?3}0bk=N0?oUko-+Q(a;yUBd3hCD!3f|9e<_%e?xeTZ8wlFr-3Y-(?S*(j zreIQOp_dLXHuCN*zt0(Rm&C&?GIvjo^A2!hN{U{FM8h1$tj;EsxU5PsN*h zZyxCPD`&S72|Bkf9ehWWe;HyD=iUIr@$it~!x{BH$1S@9qWLt-(k2mX{^*2YfnTLH znAU4IDPW!yc#o?{e+UFvx{t)X{og%(q$}LI2(nAPwU3$uB_G7lhf%3nKL)ze1ug51 zN_Ka!@?^a=gLqUY0fO0BrP4Pr%lAAvdx`6*Lr^2A46G~i(EgJO44P- zCFeVna`k|cDlCljn8bm98olnk^}CwJzLeUfunfjEWl z{jvSYj3?|%1J`)OIgJ13r#3!TZ9_~!7GY!-rvh7eA+dA|He{sQn4Ca^&c8x`8)R|IczTFw#g!IT#U;x zR9=)X;C}s=7njJ-Z>L>kfP*2RBMsMmJCA}88ICq(oDQyQMv)OpLHDfQGRAxF*!}nh zz&T9oNx1UoE29nVqt7P;Q$vWqAwwt)i@*m7I$tw@6F=R0xA+G6+)(>J^q~H6A+ER9 zj?york3cUD?t!$po!!sj@IsaB_NdM%e$y{|<c9JPn&Anc z`5w@tBtOBZ3ry&ywtt`Bu|F60x-S8_KvPaZ%vnf!%O0e(TBK)=1_}*vIPoRi@x6Hx zdF&JH6VB<(ijM;r9;*6m-t#@Va9(#2t6}RX#R9QB)8Nj{v~8Z?t9T)#G61e$s)tj9 zl1tBli6A`YBtG0XNWCk$1LgtsO08wXwy*GSx57i#9>?V!oc(hYBNC7A(x^mA<*?F@ z{6@?TJHn3!=gR5ctWvRmJIYJZKpP_HOXFSPL|@*u^E5wJ7={xsDE$jpw&oGKr0ZN1 z0mO=@0-juo-SuZu4!H^p02FKwkS9)ShVtgHR&jm0=~8$*R@GV9-j`^>&51w1e$Q23 zWOjGqG$4@Z%J-YQF6sJ%R+H(N2ak-;eLj67+=R8yiJu`ewIGA<9|xi`xFv>vT17#b z{PSm2C!SkUZMciS-aB1#oW#-rN@jxy(x+_Us-3oU_KKB(f5}N>Bg%f|##_gVqz;d$XNrzN$`VKACcn^0(h;JjiUp8_56P4{e45xmxfBbM^e!XWg^eT zjvQG_DXaU7=C8!e*L*>pB4-OpX}q<}UaIJ=pna4Po|D;}a_g94YHjSd-}`m&F1v62 zxd`Dldgmz1f>cDJmrn8iC>9Hmb=WQU*o26qqZJ>@wIxeh>_d;`0ncV*M7lZgJyF>m zoZYOO8k6%SUQJ$RW8ee^GHGxVo^!q_IS3-}O4N<<3)zJ}KJP1-KUv;wP!0UvvRVs= zVQ(1(`fGCfjB5>`N!(#Yi%K8$!0}lKUGV;L_~Ps>MRizC6Z>5Yym)saj9St3!r{7# ziuHpnH|RYyDXgj26_@T#W|W56pMhxO;N)7Wa88O-n0VgTQ3|HPH>J}*gfcLN0z+}% ze^4E}EyPyy>VcLn(T6dKsgrR#2M>U|aJii&+{USPmuz@-KEkKay$)(hw;R5L7Cu85 z`Z$SQbSL%gL7jg=j#8{llO#dCaN(E=&uC8GhRYD)_W1$a2^)xS zYdFx;laGkUtzMpxodBN&f%xP8Dl+TgS>KY5STE7`B-wNAly_i(NPEAgJjo;O|aN%^@v)flHZuD;V_k3NvKNh~^mys^}7g69pS14ud zk%DquzqYu4T=K?O7UHP1gz}{@tGc?1Sv^lbOeG&oAB@)JGGvmc|Rtxg!a<%=oU`bYN~vXefCMwW5GI z|IG7EPEPOPWV6z<$hr#P${;q!+P2y`y?FsjN@2irJvDYhNK5&ud`b&DMFjnl!#QpY;I5M| z$3wke!6w1yc5kCtAr44t_UNI8%gvd4glF#fYB#KRb|4Qd&OvKCV3O|h1Jc~j$}@DG zw=@deUh`e3em_{Vxnp)1sMpUvHy8iAP^hb6$9#vF7gw#8Cb*sO1l|*z8(`-`0H zg&v^N3z&vvSFr0Fc`@QZY>LOATzCNxVOx9RJ_*sv1pm?9F5stnPWDpoA~tegH51P` zFGd8Sb1�V9~*>4}-r6#6hs225i5NQvnS|ylUO$_kA8=IJZvAZAl)W<3?t9O43M* zlc)H5TreMz_%&;@-CA~jdu>Ea*t3tL8KrQ7y&{LH1(i8!Ss5i^>|6D2v4kj*3XBCh!Tt04*%o}TxM~&T+igEmqnFJXR z-p7n~Ed_bQKs)o3yh?hEH{LB5uOItiCZrTu?ku63gJdoq+CnC?Ks_JUmt*%?$lgH` zJzqrcyc@NB>NEE5<>}bMWT#Ys*WeBIB{LG8wT! zJt!w0plYxfpEu1dLB-->d%EB#xa1nYi1_QR`Vw>y=z$z_F^}tHH6AYxTwxgb&OBHa z5FY{nBQdap@$?$9{PwQES@>Kbj+T;o8qlQ&>SIC&0=M+T9=LF%fb^{LN$~Er2L?LW zW5K3^6tL=_ulWf#E($ux8c&}4Fn>>r*5@@Wq@vjLnpXTGT*gqIN)#v?l%|iIJ&};S z!^2+0h3KaSp6VEdanNj#9 z(LGTMMuJNH7&)B8s*P@2Ni;bL(Ir^Y=}M{FEhNt4{iOTIc+Mv-F}}IgbGoJ0Tn?ut z+Z{|Hk&n!z@?y}s=9ebeNMzVcg`uNyv!RElF-1oVyd)qaUMerykVRodr5TNnc+q#k zs@AYc72{GI%oG10{{RNfS(ym*s3}Y%um}$50jCScBJtCr)#tJ}QK)nBi5V&|Je%d} zM9vY!b?*kKYww-`%;7%P=wI-SbgVwTE8Ik&jTHWoJQJ&|Ncgoy)=zARsf7C-;PO8J z^HwI`Q9VSL>9d!Ez7DM$>A%`Cw;AvRzk(wl&B)>JP+PbI@4T^jj*{4mD4_3HfiXnx z%9O;^n-c`wa1=*h1f@%So3&^4x_B}eO#Wp~EZEMTH{{V+{2}V$zGV|_jcfanz zw0~R4z&T&t3k!zfK7@y*LpZ3pFu zPvjkKu50S73*9uY^598!t1cYe+TAyaULl6cQ)Th%O|WCV`^^2(@Y?Car?uFDew?8; z>tz#|*Cy@2OvIp#-__~v4R)X6yj_y$d3cw~gArT=|DkZF(;7c$*olUu-vQ1*J3@$Z z7IXc%g-Bpd{r*b9g&CP(7%gs77I<`iEtR)XQ@;-jA#w3#r#D#rq6tMnFg8nHqtUYMk@0esZ%gX?lmH zcm*_}>T9H5)n{6P9ahbeI6PxVZe3AX>(};HP<&LojAo^;nUc|wSp>yLKxdi6d)mze z3v{JOhH@0%bo9*hQ80+d*|Zz4;}qk1l#a(5XY*rpis7im_yDJ1A9FYHHjV_7;Rkbk zG*f}Y40vylw`H^g+4H)IBQCStJ>z>e=0+UsS$dW=HMvAv_|6ew)TU|0x1*@zG09Bb z{h>x4tf%kAaF2Uz_)n!6MT(4{@=Jy(K={ z?uTBHyn@p=eb7_KH!;+Ebcj5>>R&NeiuYy_^BQr!Ir7WJE@Z#*z9bly3zVQ=;xs}9 zH~k6o*x&EBVHxO%@Aj0R9DCT5Z^q$MkpZ4MAxh$;kcFZ8iW15s9kSg(@Y9tq zaOCOlubU)9xXCpFZ|jt)pI8xmw|74o7Z#DmTu0A`dExUwD=zN+RUotd5xBtJq?8hK$S$8AgGNmLgv2Ryvp@}rS1mg3SN+Nx$oQ3 z+$%=3w!sDhB|jlXOwaWDh%?Z?JI6i!E!>;`x5rGX@#@+n9g)GYx{jtUgi8gyvaAi5 zG0Bfk8Ssu#5F+o+?exGpldhNGac!0ZYqGa9Ug8UvVy4l!!o%9W4(jwb_B4^b{=Q#1 zVx`q!!yM{io$-RsS%OugU%WvPOVrue-V`vk;$kTiTQ=?)KUTt0(Q%3O?CZ3=kFW$p zDvk`Ta}ZA1APXs#`d4IXjC56i<_5`%p0%2I1I~hDJ}J8xNDV=@sI#pkws=-?YdrLB zQOe{o<@iG)u?-N4!S5a33?=O@I26-9%TUY_vQGH-ItQUg!k#hhuAZ+okyelT-a2Ra zagIFLm&=g}rI-T~VAlNleHAzpjZv2HB$m}cS$f{_w!bEo_i*6q8BDR`age&^<-Hat zM@+7V9fyL7TBWjuhz0C5Bu_H~nP)4d=t`1LC*Fe!nQkxQ9RE7%@A0^Zc8e0&`>sM> zEC@QOckD)6X2tvxomE{HBkfS?`)UsPMxI7OI(vW%b?}2EST~sgmSVY``k2Ok@4u1_ z#xa?xMPJh4qCd;SHIXL1TQ6ztud)tG;gv%I#x@2FrhKEcDUGS| zug|{X+&m|C+?4XBQVJ=gZ-3=lHlA~g-dp>XF}@$jImqLkyRA1;946U^#C<*8fb5`O zV}D>5a8VC$F+1-3mnZL@e$ep3fq}_^-s}|}67Fl}tf}$++uF{dpQu=y5T{?ewisd` zTF)*q2Ggy%ihhImDQ{2I8uR{Ra-GgTcmPqtM;~4YWePWB`MBihujdF;k4=ot7kjWN zq}=#(1inIed`JeC&rI_hNb7^;;Sir2K>7qPNqB$@U>fIuZ2%~Oi++HacHZlpA29vh za*nkho5s(;&%%-S#HM7`SFB`bS-d(*o&R+?SL;<|tyD!d93$w~F2MPbA9BAC`Tp{E zPKflJ8ie0lwb*|>bN8H$F#nGayQaroRGUb{VO83oFJSnYcsku}?1gSNWbeQF+TpP_ zO(*XcbvA|L$)RF*3xWnKneF7!=z}&JuG1nid1VidJD%MiDv>(wU`LDM-vOiRl$>i_ z!(no|mQ1*iAqEcTGWsAeOKLY5&JyB(ac^;r%h3yT`fntUGX%sC3Ws~{LWxF6_|Ff}pewa*jn0P8h1bfsQ5XAOpyJWb z2)X13o^4n-P~eVlXcxlkA(*|vLHHZNgGE{{zlW;y4p*8R!@;>yeqbr5d497D5A~{( z|NdM?_`8ajl_60Py*!g06u%mA?CPL%svtdYbA@0uZ*Tr61pIXc%uBc=unW6U7{r2( z%o5t30T?Dv^A+j%j4^kg(`TcTcKzNO+$oCkOT%>Kj?rBHK2r%l(z^$rBI}>PdZO7; za^f>Bx(Yc8h4}qlC%?<-2rl5jh|X~gdq*O2x-7FsVNTW__vsI!h4)++zOxv~uKl*! zYU10SyhDwf?)o`gM0`0pek$Mg*nGmi!voB#aI&UKoa%IU$9{#E-T!yjxg$X!RE9n2 zV|#%)o0!(hdLo~CGPj~dNgpbFS70EpzUhe)<9t!Pz75TPM#V@5!fY=qrnc(dw&=)7-dWdO*k3~)$i#^ zEx77WhXm_9Y8;U6wDjD>M`f1K)j*GKN8sH(gA}d-q;Yuv(pJMUQExVE#Uq-w0j_PA#lAdHp@n!;`<%QFkiZVVPugB8_p(Zl=w>EuJ zSX^REIDge6iyVGPM%S!hKr11&RJ4&8IU02^zIx`*MEr)Wvyl1VhfCtxemS~$->mAc z6*y@+T3DFG;NB+;U=bSd4b|UFjTn4b9HiK|l$W((F9_IOnroO+GmsQ7rI0P<;vf8T zO1c6fyt7(ZX@LYPmKBe3#a6#F;PBBb_5yYeQ>{z-wakcEE#ijO@Lij@a>srvgWpYAsa9mu)?`G7N$urR`I@72&O45>AKa{Niw*;1ik zZu65xAzb~zGJnYG0)x0`L`;C!d@9R=vkgec(?Z0R@YzYA`q|BuobfId zJE*!oxXh5>UZrfnho)rqlN2XqHOX(S9H6i59)G-=78gS2$y8@@m=2f=>P1bQq&XaH ziZvuQF*eZc))#SaS{8LSr#;RA&j4r57J>7MKL6goa{(gm=9K2=P6TaZSE0BkUYQC( z2r))$iUHV3ixT^2Pn%Z;xl=&rrj6=b)hXI5oQnt zU_C>u2G*~Hj`Fb%^)hok20~dOZ4|J{^n-_a%+i^8u3g!nzPan|puXm&q8|`E1nt!sg5HueBR6JzRnA||Gk)X8X+H=sM!M$5sU>DosQAt zwC}D9_rmZ3yq4BpB*W^Az&5lAuZCD(h<*Xr4hwHjqQ356{E{YkjGpvbq!_v6Khk%5 zq}ij>XgRZ2p2T=9g0K8#{gZ_BriBkC)Z^}~5H1+c&&=PKoHeTyvj(m%;VQvDK*X2B zixVVK6fO%PIt|EQ-tbNb|Fk3D9ng&NMwzwxdO1kH zOPwZyFHgI7^RZ4rnU9MWvdZsLe2_!Tm*)4WMS%P18#Ps0XFRdAX%wJ6iaTT=dY8a5 zS3Ek3_+`|6fW2W!{PP?9ErdY32X~N&>Ghe zi8tSHE&P2wWA}4AL3m>EYTiZ9o_U`MriqT-_~fnvab4iO=N3K~Z{tC1E6Z>30#{@6 z#&3f0*&J!Z{q7Bt7R#Sk{rIjRF)B%9G)W{+3$c}D%h8DRo9@zi+gE(2NM8i1xP(bywhu{= zBO-r5&J@j!b4w>&4}bHW0;#&6YraYvEM=VYScJ=m?H}tOveXyZJ+r;TLToZ}54*YO zWP@+9q0>yK#n&mL&mJL=(h0eU$oS=~EUe0?cPl%VlTElWF4vTktB_^VWS&S zjzCTEh2n)rJX~s#QGzz@?a%;RTcpiPwZ1*>uEt}U+tVzTrlB#a9p|5$7#xYh;qVWV z-)}`K{PYs%+iPwS4@yhAY%@y&p{v1^=;$(OA7dnDSjfBKtiRUSYehfIePq!vpolP^ ze|vcI1d1KSe)zwv4v`bb>qkGr1i{6Abdidip-r%F9^jchF8^#M1)0(n}+w>OFXxX+Ids^!I|rHCvRf_{GI1s|31USJ+23ssI;?~ zi1rn*gfScW6E=Kk@;2!$r5#9trOa@Qy%3Jv;Pf)#5Lg{Qf3k)5bF6y!ExzD)X8oJ?7k$Ky94I*u(Qb&y>!R2xfy!_E!1D-u5K$Q zSK7o^IUJ8p1GI}+#B$dTZlfH=*X$t|*em$lASt#6V=&OY(c{FncrQe&{dKJ#U#w71 zppW`+Hr%TH$+MucnR$b9S;8RoiJH7Ac?7LD)&aO+_G22bRFfE~?ZUekoqh<_cE6W{ zxd);J0gEEt8EZHCUam@dgMRoRy3rzGtxdny{OP`bI2D&N+CQm01N!|PPuP==3G5^x zW*Bexq*}VheU%aoYeI3@8xF_lQ)k9JgI#UB7jg!4btd!c{YM?qB%-#|%@Rg4`{&lw znH*zigTT?hy0!>8-y&Ls|HMb7w>#dxGS3A6)z>X)mnYp9(V4f%W$6$9^l*YX{{4J< z?(p;Pd{CzuPFhsovu&7*{zgx{vVyzrjUw%`??A($#S8e8W@(FuM#(87F5rk#WgADFIP08V!eJ1s4)Ly1omX|5drENhZ}jc=+@CKX z>C2TPc^N}bFTPd>FE?A9k?KR0w;u@DFv|U(PH%D8o%Y|T=>J}$<#ye@Y2-56^-|mY ze&HPLunZUM8jFRUagnRp66Ol+cU|~OhC&Adw6J2}++zVXWW~d7(C$nh{j+=f-0yYk zg7b6xSa1NlLSb-%ce3>Gh`{IuFVOGX_O+VDaa`Q^*_0{P@e9uye`d{}718AAqni0w=H6N#F+Y{=+E+J^xI72Y#n|k-7#D^|F}pxjnMRQVU;yW zPar1xij|Q8ty{P$86{RqcX*?{-Yy)zcT+{{TntyWY{IeZ-7;yPZCpL#wEk_zqAK<&AmQ9`TyvbKX=e3 zJ&$tT>yVCyrE)H(Tq@^ zwY4kqW0H^qNC{6s%?>ly@7-pE=5{w?D*|!$Fic!Yv1+f@QMosR^|}sjY|Wnw(m$Or z&u3}<9v0Ws^dpV>i}rvsc&HzMwhk(L%W$YM{kojbnrqJ*EwA))gX)IL@|R(uwA0+0mKF`e zi}U7&I0JEmjcbi-HAw|L^_S*hpxLS)Dj6rw4fpX4kni-G#HU{XJYU|Oi96tH)W;B< z-w*DwOX>M1U)-*}SnB*GIX6D6?>Bs`pDB_^l5g4H6}`fC<+mL85QVbrxZMHkHuT$X z>t^yJJjOG0n+2gkvx;$kML&g30F) z{{_gC^nY{RzRN-|j^K9H#5Z>xr>O~rm7fv$Q(9HbrhPY*xBW7}RxiZ;OUGE`UeNXz zybZPrk2QG9v8GRCNlvIqYX;4Cb0cT1JGPA>bDA?AEiWEt^JU!$>z*r)SUe6gLqt`t z{jh#Fj~s!DFS7{2#_3oDr_86u3v34r63vk}r}EHZ9j$?`b?vs`(n}6MslR^NHzms_ z5MlHNXq&rVPFE*|8f=J^2D+HU?qA#OQ<@@pHzGaweW`f&*1zP&RH)7GSQUsT?yB{A zWjG5X96%a9#_kl|-+6z0QNTZoC-QFgz%I8ni=cnhnzHzyTAF<{2Vs<5>zxn2@wUBh z|B))4{g&QXj@R27QvEK%@(>wK5&f4y+-%zEt-!Tf^E4u;iGj1(9C`VLqL_}C^u~Hw z_Uk4CDRB!o=l-PLa6s?_C!^yZw-D0RA<669 zwIuRsZ)ySHx)c06H<91rhTmsexzl4OY+{pxjEzQRW$ZolHFHxuFvw_}oQO(ds}W-O zmPa?>SN7D2C}yJ~@aGYE@xh)Kd1kA(cSZ}ETy$VieDOkEP*X@t*HzjpWumdmJyN)o zZfvLs8ul!hTKl!aT_MVFxb^pHRm9_olad$XJ07N|CV_b--qB;Cj3AqS&}q%wP3Q^p zS{$@!+yo&X{k z0ZG@`>z-+QZGrhcdUU92g@HIC*28p$_BI%dM;`r}VGe)49jR7ihSnc@NH25fY4Ai< z7VlzhawOOKi9BwvTGO+=gMlk>7Wy<`DgHhYY`^y#Sl5}CGwBRA>ZPtf93$(PB5!@% z-e7ivEicgEA(zc}2UeXC#@s6bGg(qk zZY-FTisJ`y@$02S(!_kXC*;SoK_sN0zsJ$QmxB-%{oZE<@Px>lT?ccqbYgGVxs=spn{%uK=Ed1UtvV?(eg0Df#@qZ@eZ`(O9T(*J{k z`8(tU3iQ<~N(kOuqW+y>Idnx{)P~t2EsQ>L-9_j3pG^g38`Z+?l@erT-(Yz1qYy{f zAFw*U!o)g0cB%AeKd%(o{B^)L!^wFHxTqPVlX8ynCixv+M@O61(^U6I;)AirjZe;o z+s_W9)24s%WM+BoY~g*6OxFso(X`Hs}^tJ^CC< zV8HTt_8^1KE;9d;%GnLkivne6P@{#5CQFS3XWH;Aad+~Z7{!R3cM-#2eAbT2?0$U-o% zyWrUu`RDPLE;Scb))mlUB^Gg-m8(~WFq(pl645Ogu+DqrM}3rBIlA2-}^poT0rf;(#|{f0j0hxz-RG~E{a1W zXD`DgNBOc3WIaN@GDUKG7EwN2cztPp72Oa0GTBmiMYtZ#Y2vn}8V&GY(s(Uv~QzSETWziPQ~5Uvuse z$cIBg>%RetcJj<3Ext73{j8s~*AeHm?vPc9=LMEaoaJ7W!Y z7p>i_(C(N^bOLs-vUT;Vpcsjpp$=S3wdFG%nh`p@Yzt}Y0*xk3F%Pe0I>AD@`F*`E z!sWkw-!6T5-scxnn=($luk5gz!CT|U@2!2dr3zYW$dc2qNAHyPm>w((p0(>{mN9-_SAYU2jRfkDD(AL={9?+w#O>sfyu>X-QB8WGag)}PPs-dBnK zu=p9$AF{c39md)>L`aQ!9Ni)*2Lfg4+z?P$nr)KIN||dJAlBIzsCu%}G3h)lM+jHoGt^?=RSKGWqj~nN!Iy(HAlMf2=q^Fkcj7H)o@eWxZd`(><}vyb zx(}!X0ZF9C)p^&f`jD1Brj5eUo30$D702+_ycqPF;f=IanMUT6Gwqn?PapTsn=V1t z1>gE-rXCasCzh!vP>@$Hl7QOncb!x^ywb~)d|7(F+u$`soA~7(p-$^<72Wh+!0F9X zP&z;3+EQAAb2c2JW`0-kgz@5YG{6CaFG`wO9o_c(va`7r(5|Y1i~BNOEgwbY@ceVq z>@)nY+!L+vPdwsz$-bUIAseyB?r}qYTN0OCjt;HZk>30bO*=PHA$G(PWyIBKc5NwB zAs`3Dro8gagBMTN>)HDxaKpFRr9j|Gx-+Vi!xgunzlf1sbsEBHMx@({$!AR0*!1+@ zz0@@kWB+xNv?b{e2UD&*+;lj`l3(W@;@|)Hkq52C zL(^NG-4S_VIlI8Gm@{z!R154tGbQMVi-D09R0GAGL+p1}#!CCc?s}BKrc(k!dXR_V zcv)r;iTpw>L@xillY~6ny|1lC60uIERFS&KmKfCdsM36QSMhu`LR*m$7oi@})LP&W z+F+Z{z-P)P=7uTp5Zlo2)epTVTK~xI#(rM!dP}r-Ui27x5!YN@V#zo>lGiPNYs(&T z0nl&Q$IZls=M@6Xg2)=NN1}{O3%InU17unKkJ9ogc=tT+y9`=f_v|G+^w7v^c(Wf@#OIshewp*^n%Sw#vZ5ik3+qPeF5<&{Pxzr`MwTU;j-cO%KW8CP|G)Ot z{`d$5r`+aebaxx)dV`}7Jsg^Q7te@3vCC_dM$S3EX{g5T_#V7Aom0-cw8w?L!e9t2 zV*&NLJIN9G->hu8S`5m+-Ydx1rF?`AXVn`!aH~S5{Q513Gtk3$-$023_)XcS>R!w*1tK&B|fd5xrb0KDne)6T{`3( zYA(BE)e#6gPj8@+hQ6=DmG!vq?>9S&n*u6s$~`>dCM$yGde->5o#XGZDk1m<3|>tw z;r#%?Gvm3ORSiGRM`?+%LQ*Q!DnIi>L21;zm?rZ}j^lwiPf6>oAa6DBN7LlAuC@!u zL+W8sL{^U9h~)VSx`_AXpUgV?@Nm`r_|=_8F`DK8mIg0CD}To;@Pai^eSF{9JHNLW zFa)%izU7?x*QPdViZmH?#}6mi&L=-Q|5g!uyI~Ky%CA%}^zkUoGa<@~El&He353PJ%o8ym2WYt4}sZFI!g;&7z?!aI`h?+&}t z^KiR~XpZqxuL?F8r}&#zKW09nf6JSBo-^2Amozx{k1Jeme?nRC*|2a$wxxRo=RHO@ zJOwXz!E783=uCL~;|>x8!LTXWk$xRUJ{=ZMhbgIyJJqR~M4x8=lr{XwOD`rDhH}bw zRhRv!xKPeEAdV|3ejX2X55N?=?!9I9#v5srsKlOl!hU{pJ>=@k{mvcj0)hLhdqu{* zIu-TjXsipmrPwyD^8KR!Id(<_HCbj+Tg32it@H*ZcYXzI+4uve5HwlXhwpR%7${ zJ14%q@Ah{6jP3lPInEF;e};+PZSm# za)w}Ew+tW;id1M)^~Iyyvr#fdMmFs2WBAxv21TC<{_MQ;_Z6Y+yyo#mMEr*B4EFRM zpPzdGIuZT&eZPBDtKC~P_8L4dBrQnjAUkxtpZl(^Q0&(EMSNNl&A$-%|1O!n*(xX+ zGB(B|t)$-55&+-34YhIwMd}Sr@E(9ranu*IS%!CarTCZGUuSDITNHVeto1R>`WWk> z-@<7*A0t?*v;B8Z=6B{>z6NyzScAX^?8wfM{X77o`~@4^coB6zurIz4k}awu<`bV^ zADr|&oKMmUW(Nv)2(ZfU{Y-ecW4CcUun$yxKsWA3 zJCC#c^qbGvT~JYg#i>`)=)Tj45n|SF<}dU3Ts{1{Yr&HEW*{5A9Od6Ul7HjTP#UCz z`6h$+aQt-$24E68+}W8=ie;8?_^1Ua(cAZ!F8G4Iq(VA*(&qQP{o#iPXvL|U?s84b z_nhbF6>(sdYd4&725eH02_NUIiEBL7>?el$!Q}ufrW*=ow9I`4$_6lJs;6$~11INa zH~H|Id`R(oWTs;P&1a@8Y<}bMl2-SNSqF^JAyNWC?3Lf*XlJ@CAdT^U(Cg_t;u8@_-E#J!EqS+~G9b&CCfC2d zt^O5^lj_7JT>>_S=(J0D22@b{lYy=@HeiVqZt&)E{NU?-lrEQ$Pm zkoi;-J`D0_u&9XpU*=&K)?N77S77bNy{zhk$OoP>KOlW4bCVNdvD~}weI|v(Fl)l} zmu2{S&%Q*rr|}UTAnOHQ6nYA*_;ro;*qCSGAX+5yUb(1%1MtPya6D5&sIzRDY3{^u zM%-8*%*C7yTcYj1y~Fb_^rcqC(1@D%B*p6m*)F1hO5#=EU-aV=W>$6WjV;{36l^!}PzL<=XS<^Aj~81-*`<9+`tsax6}-yUiOMh3*&{fn1o1Kd_2 z&%ydPU^j6pv`-4IkszC52LP{CBz<~|%qI-?Sk0dag(sW@@4=0l`B71|=P?Mm!Kjd> zlE$XCm(23F9Hw71v84{EfddX)VkH{9h2LPY#i8Q`4h~vBK&N2t$C?&=*NX6(8&+nN z^!nqa^2;fC28I8HzfbX#{^|nkFxbnXax%wP?6rxbg=iZqUd?3YkZyj)_dR$d&nliI zwpjunryQ)L?aS%u1m{x)gh8>PR~*;&p83uU@tRNYr0qn02%#+%nNW_vyVt)`Wj^~* z24{^wVuJr9kt-QWds^nNM2>IR3HCU1x-BSs|K0ID|5wL1<&hoyXUCU{VV4d+>u)`% zpWL3Splx@9;0W$?&BYM4r3Y5YM@fWC_kVSKPqH}&`IuvNSiDcmmv`}6&^=%MI1+X* zmsj2%HoNImNLT9zR{aD#80$$j2=;K#MOX#gVE7bb;X)@vl7ft*8iJyW5q-sL<&9zK zp?61YZ0|lPO@Ed11k^(ppS%H;yx2J7ftEoAY)forcIIPc&iA-P+yEcaDA3x6u#+f+ zyPK1EG~{cSoq+e5)-$s=Q&Eakr^-&Bp}jne{*P5Pk_X z?SEgs5p9znZ&~e^#l6Q=QFmV2_r0Jj&ttb&+}6}N%Cg2=)JtAM11rU2^Zm26jaYl% zTmsK7KyB5R$K4ybHSs-2Z`}FStPYSG*jaktV-Y}aL@P| zhazu;c~Eji=Fl_PU8{J-xh*eKiuCfW$5`-peoAV7xD%DPT}kw3cNmU#?xX+i(m%J* zEl4N$-n&P&ej1QV*Tdi4wXAe)10Kpec+|=%NA*2bAXf;3Gwy$O4Ft``BB&z_=8YZV z`G$ncK-O>USNC2S@zgYkXC|Q9wQ{Qorv}7&I}iP*p+oprbMEgNQ~J*;pI?dAdFfr6 zdSSoBep}Nd0bC3J={9CIFlN*EU&^t0fxg3-#chC*vAlsedA+2Hz&)?-uDg|H5s^Fg zcJjmfw4o*w+|kQ)wNrOI{<%^)JDs^P0{tY;-a#RLX!^41U-1M9&f$GS2ZHE^ZdYQp zckY~97`p29A`XMtc-}iWlM&$^h^MBZp(6NS!dY|14?UF~!i)J(R!&#dH}!%i}X6B#gD#@dm3or|k5==ib>-iS0i72;}eH z-xVwfZI-H+b1QF$67;>xb{Sru7t|cCR3APH8-#Q>Vvv@f_`aq1QN&@}-*CcTqoBp- zgJ!5G+%zg2u?NCGkW?N^CB-!v=t(A02b6V3z^(@YxBzW_l{`@{J0ayEd` zJG9?+z8AV3vnnj#m*I{EW#~EImy_;)(JSfc8*B1!GZtfSoNcj+!n9#%EIgZcVi3Or z$GiBqoUe89yCUAS!-17Kkh~vT7fS)^;E1l+3!RljdV|j}Gg`4G9{C*hu7-PX@90*R?(mk;+ZonUX#+==Uh z6001M`L2C|D7br#KjQ(u6XrhKV?QY8fYOZUAd2@--cx~f$!<8P#F3GI(;Ix+;YX82 zZl2j(n)S?TIQnzP-$)d4v`0_0;fl-in`vB1KIrSPgAP`e zI04g3%OxH#nv*g@=iG39z$%g%9ZBA*5MigCd_!t<+_#&KF8))pJ7R6!LQi(w6zWA6@k9WoQy&AB{v$Ju+Gu0;$5_v*?7- zG+ts0**SMkM;%UT8eD!K2h@7JQkbu}`F@!?wb4=TB$kh;X7|YA;}*fci>tT&Wk)@^)v4v&Ar%S}(YpM7#)Z0BF~bmQgQtz_^T;`pgmyQg|O3eQw0Pzys(R71K9 zJ<&I-Zt!%R_ILLo5f&R1CZK67xc0wtz7PE841h|_k{M^6S67R#cq1#a%L8uuufniJ zF1yQdcV;u}Tu;q~NsK`9DcVC%Sl+kKleB?}7tGY2#b?PLwM<6KDlxIu{71Kn%h5fz zj!R2}n~4-s-_Q>Lp{`GADFpR&i3=Wp!!f$>`ZYq=>W+I}^03PZE+^qLB&9 z+a=$#0=1vEBtQ55Z)0)~vvdh1Yid*_|%pK~wCM1?(K8@HJk zjl)j=SQh>?jSk~Xz8O@)uHEmF(~i{`h?yKa+E1@!?gy57iQ`+ZMXCB2ENwEAS8lK$ z!RI^c5xSSDHc3(UxFjrIDxX5xUkfKlB0*_UqTgT1rzO&g7BPYG$tv1*13QGjwU~oR^!#&1m!7ijS6xS(;le7m>fQY=*xJ3#8xNP6II=9 z0mCG^cfKiYKG7W`XK(fgWtR)bI!$5SKzC4S=xFq_$erT9ZVP6IRJ1#skNfse9h4)O z>qIV0$Viz#O!Nz$)mZ}I8W$#4Ww*^fcLRkB>f%K^1VoD~z5HxCuXMer9;m_9n9YGK zT_7(9dE~{{-?lavXe1opDCbQQ>3!TqQtZVM^Eb2Mrn2eOXKC1%6S(&zey1Bos?#JM zGlU%sfyx9d&|ly|-ljdeJJji72gvk}tsSxNL3Otrne^&};T@|@%Z8M?nmY!`r^Fj> zh>MA0sU{gPh<FV;vTP?EOMz4c_ZFbz{QXwr z>=8DadVkLr9Vfz75y(*Px9=1xr39x4zI9iur?sz^)OW#Y($}?ct;2eAMBmuNxAynf zy>)j)N0f#))Z6#VrsJaxd!xxo{iAOb_SFf3G`jb~tc#Jigt#=bN3&)Zeq%)3BD%?1 zgwCau*@F=i->f?8)^~biD-;}dQeE<5UmohjtD`#k39NUjl5`?lV&ZT~Epnim>xw6G#E z=pEnADuhoSm@_ZVxTtDp?5#XK`EIms5xsxfG0kBt1*q0L)$Z{H%xk&WZjb$6R$bw0 zXBlYh4*_bUz1AYm;@Q#H1YztvKsbr@C&_1;`x!@A4fmDD?P}d`G^&sMkSEpBNnt3J zSii0qhFpd-f=CMNBY|1qYx5ErQ%PkpqzLLGGE>J;2VE#b)a7m}Ol0tPQzh2^pr3Z` z#nZ_4bX3}vEZ-rw(@1U~EQcB8=fT)~lDMl_-78H>kQW=*%4}IjTORQq#4-DA% zm(3xm5a6~D`wISRqlB1#Qk7EDR3 z{U(KVZ{IAt9as6Muf$!1b#C#FQC>Otf{8t-_k{yC{xRxS-6`2tgvG8{&K{A4FcA)H zfg5IaB(EhDk(B@*_zQ>GmN8PWRoCx|oXjMB=WjrFvR94g`3b76c_$O8FXv|3GWb0& ztY9VLPc#M1sdEgL@nec7&Y|qZaytQh2;Pr9UU+RpJyV%#7|8Ti> z$F@Lz_VM4|(A^0@P)&a~{{Kmb>NDl;^#AmGCjabbRz`LW664>zp^(Vl;T6Zr7&VQ5 zbUFWi?ti#ppU!FAjK#~9|6eZH5w$LA#HTy!YzOI;fG8XPb^Cyi=#Z%TXqJ6m|5gE4 z>+N3um!q{BG3IUIcSUfQH1J}_ZUneP_+m%pqNaZi+4g{hpDj>i&(1+{**3OGU*aUso^t-DQ8# zShe}<5x)>iQ1AnPKXw@&%7)`$0j05n|L|}B&5-0rTe*kbGa`73hkb^i z3=8%Bw4n5xs-dTrPF@J@Ogb>^MZmhC=axIs#I^O+c5o`YaL?GJ3Dt%#|Tll%C7A17A*oSIzi?IRSTMoc_?g7F&Qra~XtW`)lrHsqX- zs?BS)myCUD_KEfT(~(h!5Hqn?>dl&xfZtV5^X^n?m zoSH_UR56cm-97R~hX3ofYtTZL&^0@ps>_|*3%v-99+CU|2{o3KWrJkdE@Qa4Yc6y*;lFLzrRKSi5y!37A=F1Qr<#^fe95W$e^;#7t*>hlY%{ z56(xFVw{h1`3zMCs=12Fgcg8Eq<$m!W@3Gdw(DCd9eIB#PkqzJx6DWmm$QG=z)+@S zT{jx~4D*tboO=R5tezAuE6a`p4OJs--p_GYAdU@Z@pDyBA(Za5@uknHbYLD83u`G|);$=$`-UOm zHvvx3_BLd+pM`aFr>%6dS~{Lz!KO8fy^lxpV_M3@Ij;TNh0yt4A259gSumMo8AGT!m2O7@HUC$ zZ`llL5vbqo3q1oW`6Zlik=656$8?idu3u1kuj);&Mm;Av%$TD5E|{_7=K~FtTU0tV zTrP^8Ib7cA3+36dO8BFB)->XLp>O>83L*L}naJ#9J(8)Br#39laR|}lfysmS1hskj zF(1U&#q;fH?2&E7(q>hF^t*lUxXj;_CkqRo3z@R4ldlFD?+Ky(>%DDKX>N9xe|>-M z)7|}>Gm+*>9f6d6PTBUa?~m0_c=PfmjA`cg%I+pWAv>%1ox4&;teH~Xl&*1PWLQ=q-27HAcr zQ=8l8Tjo0(ptegolmw_D;sUG%5%1J4U0;Swm){?QRZ2(yU!wV`OL%ED>9fMJN?A}nmT>D&=vL!JAj>TU=E} zEu9mw2G2a}(hKxc3LA_g(Hg3QEa(Z(tzG$|h5N-hrtqlH+>`C=!-KK8V{gKX+`b(5 z`}-WgKT0B1rV4!C&DZr+*VK|f`sJfMBygo zrRn_q3Q-BQ!o1^j^<_G~heeUjv1W>$1CXvkY`W{*we+Uz#5#zim}=bI!+KGK=q0#FF3y_~M>CiNgR! z4-nDl<)aujCr^Oc)@-pq)*|deq{IHwpVwd59MJS|w`gK22M{-1>M~q#Vy9MPRdI2|j-77$s z$q%tl)4Y+G7pE%SVI%Qv!u0HC|D$TVv*@0V*j+sgkw+>ZX#{Fpuaffxq z-yx4J?8-35+wMy#!P5>YOlwjLN>s9b#@Ms4J@tc|z70Jf8NsI1mGRit1PKJkDdNs` zR>ZP_-P{kj+Q;6=j$~am2l42vbn@BF%Ynx4A14v%gE;+*Q}ePWY6l+T{&4@j$+f9= zbu|B^`@$6ad3jJ6r7!X+be|NNUzDb`c_`<%VGnKhU}EQx@3cjK7MYXaMbMpVefBi% z2!Urpg0s5(g(DPuv@wkm8ra;QTeqjzxAi0^~0Almq zVnZFJl^$epd&ed0_??X~iX#y=KJ3(;t!NY8qMI8hvdlBtf{Z+dJq*!%LOvQa^#g@R zPUhF?XMW~qi&oS$ZOlw$u|imP`#T)(t|3l0`g7=bFdk%7+EEF6p5QE@RHNiS-_Fnh z+NQ{3a^yZ2M73fknR-)j48ZwxmOi7U zOxF@nmu(yP@mU*NMJ@NzTnX2o{5qa*OnSJES$DT*>VWMSq{%mgmaS)W>yje-ao7TK58-vbYI}^=-p(1=q|%oa z!PTUxY^pUax1*`2JTIXX0B0)|qm;I7Jw%7gQy zh_O2b0k+l8(R|jz_l4KafnU-;`uW#9m_Ps+;>=E!rjDkj~BU%XaNtd*9W{we&} zie4*@)`(#E=zV;97SSJn%C_A-_vGM=AcwwV++EU_HQDejI;$KJsn?edwG}8ILS^21 zy!y(JOFsrIJv>Q7vCeaFow;+S4ew)dU`d2EXwiaK0ypO#Rs1)3%cuE3(NfK3*L%MK zOz`)?ek7jM?z(>@`WWJ+N-$v>a7MX$A8ITaW|)opqKQvL zBLL}4Z!gkZ2U$a#U#SS%Rq5P&Aa_`wyyoHnnVPy40f6;T2$xFpZ&UDn@Z5d$ZkMZd zMfg)>A@YM?$)qyV&5L;c3b@zpw&O28#h~7$+RV9UVir>ML1nAvGF+l&@uraCtvS{6vLAK6M#p!j<6Sgs!HxY zBnD1&@cs52mN^KKycShUFLWo8Mdg64^n4ZYf_p{NV>5AAr~WKPDy`oQj(-jxcjm4> zy&mBInem)w9?*adFS$l=wKd&yr0+odpSO@#Uf_s+PhE@@?k+-jyqfmScoxT*ih_6} z%$Vu$YilfgbO)nrzxZ`K7j(s9Hki2Y|Q4&L$MYBU!Z$dUj3w42?b zl;DeRPqURzi!lra2jnsFq5q`@`j)*AN#h1%9g zJ|-L{`0%#+WiV{|{8FgbSF1=t+&eB_1vm%oi<{x!NK${vXRct6zUhp(w=TQO!P2Vu zo#GewP*)z|%N*Vc#$j3Me4^yPprSB2AO0Fj{*6+tDx!B+*irQZaCfk6z4#a0fg9h9 zC+BDolKSQM-?KQ|>qr4%^k^|XNKrstav&PPI(XOKE2K6BOBDZt7y{>@SXXP;;GIYL zvRCB20a(6Y(k{Cn>MMqt7iwLmlXQF>ZJa$Awxq`*C$2Mqw)J-hWl%Td#?LrhdiA!b zLc-e7>8qn|+b`@Jw5X;j=9c))%G_|HQ0)^re=;v>G7K$=s-7!P>VU}>M>L>$F1>q( zUEm@GX1Vb5k3`G0C9%W@b?b!HEpK3rzEhI#wf>MIibVQdpf-Nv6hD*R0&Qt}9VD=p zts3{!#J+9H+wa87s4X*9cg>%10>Wv1KBS2gg!$j+#rIum>~8!b)6QjgAw~j35`S0w z>C1?7UmFm@y$c6+%I#f#GPD@3rCvIfB^#av?}q#dKnnzQ$3z{fnx4q$G<<&oqxceg%_wWXZu^+Ym#K8Ky* zR(NS@*r{WQHg>-Z{UOsl>h8yh(utT)-~5GMb3?1_IZUdCOUnXPe)i)3PJzmPU=mb- zWp_vPpJ(qN>SeKp`;PQ6lz(S$!Cu`8yZT)ATl12!Dpv6?x?y{V{fb(MqY@2o`utx)v$R! z!p-ez9fS_CjvzUPaS5#SJSH_)Jfj4Kk^UniQElLozX65Q<(-)6*W+t=1>QlG{jkOR-aq4HwVjcGw_9?jLgq11_iy+z z`z`+MyK;iWFdO?WP~GahmMg|x_ww4;bRv*j$+9<54>ro|kQ)B>&0}a^R=j(Xv>L$i za&H@n`QdfBwvztY{O7$;+&H2i*(qY~oAuoA^uJF|G4ta(u|bx7F?r?~+cU-LmCJW1EBuI)LV4hGzp{x9?42VlA1 z{Y|mW6g!)}@$s~KN*ZhSGKYXZo}O}*f@Lt8i?=`Y829-P$$34e zk>ATjr<$gH@y~Vn7&}dT7Y26s#>_=K^JmhA2mdEWO1GT2K*i=;E-8R1Ui8@Tih5QUpQQ?ZdD_Rgw8Q_{1gA%l$Bg;l=tZRp#V1T)Tb3m2&Na*ns0~3t$ znC2Bn8|ak8?)cd6N)1b8xi9@$EM@qQx<6lUc*<|M7l8~GN`hj$Jk`lQFP=|W#Y z9^N<+#djX~<$VKzgHH|_iPkBqKzuJQx-hcmXODJ~#(&Z$8BmmsY!8D?~G{m86MZ~`DJ(QHfm2db<7M{kh z9enW22hpBq&pl;dQ%a3=>Mq%a`PP>c%-F|_4TVBDpd26!7) z0x*yc=QkMgXI8^}{58G<>nN6$Uc_|sQM_w!9k{Q!C9{s4T9$t&&qWZ~iT1eszBcAH zp&+}fo1-9iwEWPog`R>8_1?XLBr9xrL6H9b$6JUeH$a18GU2){2xu(B=!A-^Zgh*f zt545mYH!^ca;0?GyV9*>293h_i%RQzinQrp+rnz-VD@>t-G8T0jmY6z24~K?0+%3R zgp`{cFPiRUoU?qk9F+?1-;Ke$qchw9)@R2jR&sy*1V)biEle2RQb$yqVESe0GjX!w zZF_YzSPd-s#3kB*abGtytxt}6?0 ztmwiQkFS+)4-s(aaRT<1Wqf`+?sVx+ui77G$@|pO(whjNetruwJ8^$lkZezu4shz= zLtjr@EH^}rT3vcpsAYxVARsbgn@O!Mt}ROKXV(y}MkQK#F|7%>$#aTe6~H67H~N!g z-%M9D&Zo}~Du7NTcJuwPivpwdP0>WXUQ#p<`$6cY8L3jrzkC2Wpo!Ly2je|qfur3c63VrUAsv-u7RO3!)iP#p7JPMAZ z8hwZ~8>HKj<|87{AlMuMW5Ed8V7nzc-|;TJ)^{w7RLlHROfzJ%jrD2IOkYGiakbjy&SO`{H@|xna5Z6M(DW4o%T_t zK)?JmQ$dF&UzYpQ$L-8i%TUD94|tI0$2fS$Wo65NKxS{3hjowjf~tS7&F&`pCzisY z^{(a+UYROkgsZjE2Np4MTr~rVlgLcT829p^Kh}UHSlW{&g+7F6Nxs=2-QUifZEAN2 zXt+xmvAGL!#iX+`b{qID5hLOIbVg^O$mt1`&t2w4ld@r#fX^D0^@_sBFgHGcq=$Ya z3zZX*l%xqNIVnB5(^jNO2qSuhUAs3A8eK#kl7h-39=PtUfP023=y@nlwHksZp$h%? z2<7R?K6i{F;D8Xm)#8Uw&WAUWM<2!XTSV)fPdotaiOv0$kDia>4R;^tXed}5AMkNk zLZF@RT`u4U_uj%BATyDuCf%tW2t-Qfos3ZMNcmOMNW#8LTP+<78zmkEscF_#3Nc?Wx zcAD=iFUhk$;qJP~3ZjP}%c_9=UGsf@>j|k~Gq^so{K308KRq#$Y(_SOWv2N!*oEb6 z+--;?;gQqx_B%kvTrMO8A$nrl+P(NI!K)}cQr=R=Z!1$6=bLKy@%(ED$Qi7t>a^YK zPQAMMBc^?rAI63i>! z{mp4nr2QZW_0ZI^-T{(0Va)MN^=5xYsX#|WgQZ(BgCP$c^%c0kpJ6a6ZJk`*bk6dsHXm&$J!+e0tCv6w9C6m%AsW=(@VEyktb4pI;C5str_X=i@_b z<#ni5szWO}o>+lN{M($*UAZQg2_6ZjZ19-Q2wq{uBkrE*Nsgn_F#lkU1`t-m13X(o zZV{mGLYjFD>!b|dO|r5O9%Si1nfckkO59$t0<_MARtigre~iY*H*Crfoi(xXJ>*+o zYtOaW-*%kk6;jtpoFfy_%Z;4*NjohBh`{3zr~;8Pd-dYo%S=AO6^`^r5pm9o8|#F@P6{H{TYi1-Og7DmcA7e8+?Xt+ldTw4QQ2=7C@XO=FSTQ&ToA~r~a z%-8YtnA{%eGnoL@j^0EN%r6+`y9ba1205Glm&;U5s9N)p+wA@uTE(ZW@hqMzwj?Up zEVUR$PO5th6x9h~c13E?u7Ie)#h@bh6q2h#3Ct4^ODSAtulsdK5oAXUsDZ4=+7m{B z%S>fjjLSLwjm!-DM^RkSzHQ^3lM|7m;YkYbpCW(_S zaTqjzYxYY*j=}E?nlL=sNXswp7-nGHEB9A1$<#h1==>rBeS#^tl9Y25zW`~&DpOb9 zsT`$zlcm!R^A4TSeh??&-8{U^c6Mpk3bKH(m-A;P7E9gC(U?P4`BWPwrPD8ksm4zC z05QHi+V1==*e0=#r0+&7i$n{-%NPK6^;gb=3zIB=QuC0u4TA72Ey(13PV4!qd&f6@ z8OI~urwsS^cx>n5_g(bd z30#yc+xubPmQUuIB&9}I_#IxZZcIe}j8Z$z9E9;&OvadiCkNP?Z@Tl3mTwUbgD3hn zb)S~|a;SiBWGEPTp<_qQ1u~tUL2vLc0>R2Eo=W)u%2~NwBFPt`TLu}-Y(LP8!m^8G z!3i;T^|xO!fy8*3=^_a(*Dy;>MoOty*#LJF4VI6(Gz>0SbdcFAZY~$M{C?nafzYfx z;2eaTimWow)&qveSjaT7UazP!kHGj)GXi{Wswy>PzTx-@_faHk-#>TEemj8M?N&*N z71hYR?QnejJrj!phcFZCtk^!3q)McZyRw&55G_XuLy{fTKc0PAt(YGD3Ljf5UmqfB zJzHV?D$VH{oxDD*Is*_2?!eoQdkSStw-o&nrQ7=*Z}$uq4&NQly7x8;)!o&SWZd7I z*Gvc-y=XksfL_)PqA2gKT3RMI|1E$yO3YUrOO0&HyGrN5o``+=m>PBi6 zTVE|bA$#u=dWND!>_Ae#(a1pA!7wnv${u{vKmBTw8oZy7L%Vl`x0}1NRV5v`5=-(T zKJ0R?eGDZrX@gcQPJ69n>{Wo%?DPSpEQoQxAT~Umi`g8lCoYA;u4d@-5nDbubcatN z*J9~{7Bd&Y1u{iSyvI1Xe(LxV5Jx;u!STCvBz_Pf{g|m#a-ps0F&qp8C*d$)^~Eh! zZc$=4$3!J4J;(RZ@4}5a#*Nh@Ac0%L=)?KLk;-w1j$agfq-T+vjK1em*-K`K^%4)E zQtkH0fT+tA!N64PVl&4D|J{hbcJC=c>j_ze;8=$)#cLGz(c=yPu$@wV7vfKd#GE9x&eHUi}w$8&}mo*UQiA zyft!?7d|Edp4e{URcJ;AJqr&~O z{dxdM$|jmTv3#`U?ebu1^l9hl8Xa8Q{cd5(t={1pe!d#-azvSpjl#1M-sAhNX(LML z5;R|Tyc&V7Qm~)NqTZe5cErZ=qaTh3SdwnK2fmb>U?;uWT=VQJG{v&~%{~0#rJs85 zxk5FP$>`5gQGDMKQFeX)Eu} zM_Xyb@{8ox$Enroqkl%T%I5dBJ3dC$q5(`tcM4h&G(nfaLOStI+?P! z3lzInY9k1{9u>wVdS$|3+uObf%x@G8%t3 zf+WWQJcpbU;ykB%2BlJ~jTRT`%oY2@nC7M2{qty%yqnG7EZmGyUx~(D{&ts?gU$8+&ihJ$vWVJ0>6I>k87mcKJy@(EKmUk->6A zURo%96){gerJ!0wY*hdU2Q^3XmcenRP-Geg_Y;?Q#zVa1)Hin?SA9P+uuNj8*eP<4 zHW98{N7%&tWX76dJ+C=_{IWuQiCsOE2(lngLF zRAi|Da)NA;Vrs|MOMq|xVd+l|A4R)3csC~VWXpRsVx28{@gl-Ry&IhHIAWF|;5&2U zZR0ELcNjeQ!{(ri?T40?!kD{rZp6A_t*@NgYAkNOhTI^p(pjD zR=)iAtJV8Q(lNDNnIw^7IPjvUdqnydty-~*j&G&O?YFBhum+M9di}au{abp32xM!O zCoC5GiT`@*HYBZu-K;#C)wRfKMNqh!iZq^BQat11Bvs!`Mbc+%+)+ zs_#$0SG^n7=hDfzpg<8SAFZI9M{;fxrLeWKTHz*KllLH9P6*@;>*YCcDv;jzHV7++ z3qD*RRX^TB;A`woL#L9wqEz?t;4Q`&27tDm2KVT(M+>|bIZ>PwmTq=ZJ2hIg+=@wL z5OOT+P6Qn*`IE;Yoli@ANY)PqnSHz6d{$65)*!B1g?b)|6oPVo@tw%9#CwH3STM}_ zh6v!6Jx~CN*Jo(;!5$k{C=t`rgz0m4qHudzx=xp^qk7yr>LeKN%wlD?|mO_R=Z7qvZjdN7Rl`kD#5HsJ@66v z>>tvMuJ>C%;vEqF*6Fj8lCRFN;}UA8Aq6kU*ddHfP#idJ;&!SNtJWDI!~@L^#O`N) zQfPO6)Y+R=joi~KO55Y&MTx6?4WoV>6K4nT$mk66uQLVjyz|^whprJYMek=u911l2 znMqFw{KCl$f=^1m$b-Vr`Q7&X^CMuHbbeX+r|m09&zO}yT8wh1UNZ8uAEt2AW%0Y` z7Si5ZBFmGQ19#1sbg~wg;3eUmDoQUX7|vp-v=!7kZx)<(ue%^WW=Ch+*NfyEJnX7e zWrDk&t4-4(OH#C4^gCS=AK z1G_g7+}Gr3SUAqhQx@g`{6~IwAr6;slsBp|^9rt$7j!9c-_aY6Qim5-{rKJITR5p&PCr(%F8odUSRRTb;>6w>eG%yG8E zW+zhDJ<|61##pqU$|$!|_jlLTokoZ4@W6QhIZf;^7tQ)LWn-dJP z+e;>@F2y;M6=Mr@lTDFIqTe7>U5&%y)B|>RIu3QMO55_0l%Y*txutmcU7peR9>o#1 z&7ep&MXu=Cun;n#XcXgy#HC-=TWd=v3P0(EYeTRj7nR zjfEC748ZG1^}aLFcOVXA!y*50Skp3I%e^ilnm zsTPFY3GsnK`_{&8kT>(2A$U~ll?KCKUtkSs#_Erg@kG*Qqvq$E#`MAGl+w;R4fynl zuBl{j=}Ry`1GokZ33^934EHDNHWEp$zwjtrH}a9o4Ic5#&v+#-Pp<}F2Q8CU&(AbF zLNSoZO_~;$7myk-PsT~ad8V~9=E@Jqo5cbdC#=>E2}%8;-P7eNVuQ@ zXS*FwE(2uo`*gpr5k|S4uiq4k%Xi(354cVgpu43dQ-z`8R%edCSr;6>;pd)BY;zBw zkpSl4CiVyHq~8v~Y?o~8LN2!XS%9r>_j-6dd=NH3h+=IO25zkZTPmF|GdUzX-9(M_ z$3HdwoC1&~6HjP{!gm&nRn8mHgx4ylO(w5>j7+{{Yjzj zXpps`YAr!eCVHq;gR?e>4o(+8O{7IX*AN7Vyps)&fT2{c)n6690g#k;DCF?dJ9YZV zedTaq5u-;zy)~FC9#iAKT`xFw#$5{uZ+2*m@QDAmrXM^1{Wlg$i+4-FBrZLrliKtq zh7-c?GXv+0f~H0(qKG$M3@{-gx#6HFk7swGrxKHL5_FLnEi=C>+cP+zmjwrsCnD>q>o69VG=S=g^;C(+gvUq3LF@TDyegN)Mo(E?khkItMmbxRX@;>2v{KAg53U)`) z$AJ!41j9J&ThTadzR`+NFp$4s`wMdkf&B^gWuT?tT{bY-U|B%8?k_#F^xf_QINzqf z?~Ton#qs^UG|;&Pet!7eztPDu=bkv+(HxyffPQv>YRbbN`#Y2T^?A-g&xa)CC)jac z@+Oco<6>DR1#B~6V0)d1X}jJ&yR@-x_;>beCx^!ns>*89aQO)6oU53Jpb_&hkkv@T z4?|>pKwMl1?U#Pxat>fQG7~MsfE4kK&wR4Owf{O2>@3`IP3mqT%y>_d+%|bVg8AVC zGxhpnxj)`L<&c^z(l_4V*GDdCJajL*(?fZOTaZAPt^aTj(R%7%z1@HMzDLo)M*qeu z=MSU8{afqJ<0|0ijNe0th4_aCfp)v*>2%ts?tkg=dQi{4^>IMG_kVYLz2p55|6=C| zZ0e}}ZpB}v_&@*LIUVfBxS6c(>#AlL{LFZBbok|Mu_W zYu7eF1!vqK|J5h{>mi>Zw3&teadB(k`M3W+{s={jV`h8*_I2E08kw!+Fh2h2Bmb+% z{Ca=)tY!T_{tfmBPxOEEm;d$mAK`I#8?*2K^|kEFEZe#N!}l%}#(Vv5|HffGx8b;= zsPtcY*8l2d!`|^Gg@G8L@bzw2J)Q~v_}bOj#*%{Yxyf(;Rxd{Ci%P*>Y2-WTV125m zM)|u6eoPJ~B1TQqLzw?6R|{sIKSF^;nC6uFl=3=AkKF+i{o@M>*iJ%_$nz1NX4Zvf zgFCD{Z#*u8wtXL?Rnz}}exK3n^ghSxrC+fP{bFM`Q99j@Y>WTi5)f zz7{X}{MXmq{)KaZ9gq6|>7?WJRqegdPWDX!Cf)z^_y7Cr>bJk0*!1!L`TN{o7}E|5 z)A#@B(*N(*zPnh-fB*T}(F;rxpV-Sg;o;E;pYevbD<{S~ciK0GsyMZQI=B0kTb}C~1I=qJKjT;N<8ZtWW`hZn%WVu`du&Q34Z4 z>u4U_<)F7OmG>h@20HEW7wVxt2Qf0VfPZ5G5mvdNhw^cS%?Kt=GTU@iuQ(O+t^4@6 z%74+gjR%C}0^q#f(yTupu*JLJTspot^v*(R)t!Kp?DY0D@=*Jk{s-q+nT=mx{Vgu? zMaeZsVsS6EH=We|r6r_xkKgvon`W=A5d&?3P&%pA4#iWmT9iZQ&XdE)_18R_SLul%Y0~gIBaS|P9Bav^dFm);){i12d+vrDxf?EeY7&qIh z${?csQ3XvhF+T5xzaG=*KFvRE+jidfS_~7)d6>OX2thNcvW;dDo0#@VggtO)E>M1+ zt$ratGhL;;QUoy9}M zi%{O<2Pd{KLkK(fm9F8ZF|Q900r;C22YoY+m3DU4+}oJ>7H9-y5va**_QIF?wjtJhgWi9ugZ{@CghZWwTMC=nVei zX5rBO4QrbxIvr94eh{sYtMXwGQkRerziLx1cYl#fm^29Kwe7l8#{WH@-dk8G!sd31 zEI!-Ov1cM&P-R&r1^Lz_V?AYL)iRQ~>2oEmr7d0<- zJ4~m|+LSYDRw_bF@9o9)WU)(6+0Ed8d#Y}g7W*cw)xL*N0&V7v>@Eqb*ZoN$&(`HS zcGKN1F)Jn)rNm~7^`U;Ua<@+m3sEhy8I&rUE7jU;`GC`CiTfiOCe$4bO=Vx77~x_C zM&VQiV)M9=mMo6&^jcrKra6NHRJ*7F?$!y)!SMLA?^1>6>H+*3!Y+>xQIH4a@Q4on zwGwaYRs2OKTjm=a`j!UxS@r529RaE3x_ogr)a&NAshqh_i;7Jvv}OzHcNSbEQ4luk z#su)u(cm#o!H@YmN{W7)iqYW?bJ7vY!S4FK1+jpDW-*p8bGLi!F+*g${$rB%N$K`# zNUu6G(PR~0Xp}bKA)#4#b^A+2$I8!M0xYY@W3}%To|v&Q*&5+X?@gq;x^LH8%6O8? z;T*sI*a>(JoXA`8ST0ERjVS8NCrEe&TP7D6+MJ!3y+_I#(=@E+9Z*FiMC`pnb`|tnub4 za8E;m)w*+JG|Urgom&@Qz+?e9;qSj&!?Sg1{_%q^0U~t!Q2y?AX^1S*GyBIEg?wRB zR$`q=B1wJU#jVy4C0}D@U#zb%t$rw?-gfB?U4~m%>$cxBzXt|_yOa7T?YA=qmx?eB zHV0()E;R{r(=&BORcx;u*%&|N&*@yL^7lfTn&KF23dWwjXYn!eybPIEr@z&ONUV*m)<|ET_u)kvzLy^HF4L~X zIlo||fGF2mImc%m`_c#=9t5`4BYMAaDX`meCC458=uhIV?5?LZD=?V8;w$c83qQNz zl}*s;xuFg4{swvNBE+E3k^?N)>X~(N!VfMqR&5&d4`)4g31fBjZKa1FOxX5ttH}4{ zgx}MqIXz-q73?0Mt0-~v6JuG?`TA%thL6f4kNrT~DNo3E_CyIab_LD`e04 z=#qKpsw0P`8Sy*=)NkJQON;j5J-Xz#@G>8c0#V(s0Oem9qBWgUqZ@-O=HYVkl$i4NE!$yM+rn&u z;V?mkSBSb<;_ZMrShL62*X!|^3cYGUp22#y0eyblLO))(-K(-SawZr&0F-fm?Hf6S zH`)%Km9qEj`%=>VI3zXRVIXM8p{z6O3_n2jT39pZHN~x*w~vE_px#8hea|b34;R|) z^g}&~Qv<6fsu_TNoWZ{>E4~6_{~^&WKESX#!xRh$*X+lU&t?OOeb1-O z2N(}%&c6htS%2W>yRCX1*$Lr)HU!44mE-Ch?R?Pchesvhf4^DNr!#1F`L#}d@@?E- zG;&&Pugyjqu`2V#8T0ONdbKh80~NLf%FvFUt!@oNjquDB z+!*!Oi7N~7Q=qDTtZBui>>YVWb}35UT3u;Cha%!zwNb1t28RZ|a_JFjE}n~xs5-92 zdr!LZzaG^;&i z54QEu<=kaK14u^9NT9%?{^j-cLj(DorT&}Ns02o~E`7jr5cg_yE=wMrT9IZM;?`mXhx>O0)n%r#{-i?pu zr0V-Q4*VP&j{p7@H<#u`8vXa3vRV&K+ZFj-*lsSbI4$G-yr7tA>kS%Ieh^RRaz;Dc z;c|6mBAu?@sEh6|HL?)gsbd`=zds;1@qBV@;xAaH9Sb)U$m*Z$r`m&(XuDo}H-^6) z+Ab|Rzox8I7IBHF$OEDJW5nd1N)BM6a%2b^l zbP}5KCr`Qn4`9gq=x^5b5?y0Y1S%lMw0E_-Z`U9m1D++?UyzhEaHd;&P?PUmu1JqOCL(0?cSlO)ob z_kDbGB8;u%D==`-CjM9Y5-g+ahJ~aEc85C~l3p?DWpy&gn=r#Ln14y~2;DUa=kkv{ z+_Jo^K0!Pucg_zcnoBXG7k;UJu00KUfu1g zl-U>WDYW43npsq$cWSj?D_+%S4WDiuMT9T;EyPbv$t0UGsGEyL%yt@v1MK1%yFztm8iC`-KyiSj9*bw4FWc_0zn{k-ny<4|4I#pGc*ypOL&wvA5&_a()44#P z*#4kD;otDtPX3G~4ZUM0Tx-V#yXbh~xO881hmYa*kBNnoZ5wwLNqRw_WY&Yf$3i!; z^8+0}48bDLf)?bNav*?}^67g+=0A=1uX6;ouvh%TQfp-<8Aa24@7C89=cyN)Uzs1z zWOI1!T8dyi1z4k)gz`$+-*wbv_59TR=6PFR=3H&|arD=;HJJ8zzz$e@N9i%08YnC9 zb%MWVh`siRAEpjIt~jx*txj`XJzl?83WmTZP_W$ZZV&lJT$yOsm^Nxt_g;pUC$5K@ zg0@iC()HW8q1RECd1~(>4#yy!M>arFxD{XKv&9w01=7YA=HD1KuNqwjS4q?MYXHHC z;!MftC+B3oz1wm2ul>o2pzTX8q|KcWmOKQvbF-m2KE2x)+OMwXg0X5@Q_vImbUENU ztbE~5mOHNhNe~!I>2aNbn&;ftD@Ml1uRHe?9d~fN5E6d#TebO});Pe~4DT7Y5 zkN11V+0L?VEcrK&IHSn8i7FB_>`g1S-Cu1z&ywB6Mg#An)HwRX?~plCA)Waij=uEC z3)CB!sWw?IjJI-8SugxdJm1(*Ci&j{@CN>DDvdO`2lv9?mGEXVk7vKz7Y?)-g9jS! ztO`xoc44R{Uaw2cp*Gk4SHEt2cT@uzXyn2S(ukm=@Rh?{=Gkz zD1TwFQKgUm02c$?R0DRecV2TY$LYSdTm+A_52DsbW>}ff%O~p_NZ#~(#e!t!Qv01i z#Sn>1b^ExnpQPCsK(>--x{mnqULXYomR;)c^0t|nyGeE1rnBYd%N51nWXnHjA?Nxm z;>W8ir@lF{o0wu)WMp3Upi9Zwp@w7g_ollYEc&UM+49tj6>anbe`YKLD@pMYC0+~3kCDh!CpyY5KM)dJ8#RO8DC(Ym z4j4t^=`xEMx>weUT?(e_50q_j!NFCE5i;wqr@PPP@ApeUy(?vZp7w;!{uye5LW+K`fQCTdJ~(G)8bN}SS(nwViNyT$PFmSY#%*_b!bKhZ0H++^U5R@_l`d&wzh|?->cP3P(^6PRr*f;}!&+nDpA1}uX(3W_1 z&cx%bR?+vm-Sz#|KigT`N7;+|yq3c~Q9C|RQ9&;fLy2yEgKwByiP>h_%L)75X#Z*D z!}($D9_3X^lk_W@hZg!M8+!m-KI4(M%OTXI-Jlf1W(L1eDte1zE2 zq@8$%*dlgz{{7Zv_QdYEPru`*O2mSxdZ%F9%CV84KeRL>Ihpf=CjCj91IKuf$YaNJ zr8;4(G=Neq-kSKhU0CINKcMbctCyNw@B8e}-BvwLmWXLiEMP;b>mT9s zcy92M8x9(%ZwYF)b2{4>uf6hF$G$*j=M_(|F>{D!G;D6??;PdKdX?P|oAfVT?6xMs zgq{{O10ilBb^SL^Wm(w~RX-d$=Kyk)qz3mk*fE< zw99B-NUC`io$|h%`4i~f`2v+AWoVPM*c08V*XyW}nV!`;VW@ScY*HSx&p8m|%Nnqw z+SNQw+&|6LY>oK|SpES|oZJByi8v2@s641fOiFVBr1$ zAwpH?Slo2VSM}RDBC^tM{!Wq=gVo)_tOo+8QOd*#ybo^sV&DI8oCp*`r}Cq;$Zq|@ zKtaj%%S1qpK-wKVf%3cq0(}IA#XYCEF5U@~X2WNo!4NbE#8ZKi0dN51dFI3Z^?)Qo z%t#2^6xsyaC_`Kms7{0{|CU-9Lwcb#P`n+tL7Xml`Ga?eq3$o-8)ximZ@yLw*N*zd z2>r0a{J!j?j~8D4y2Wa|S?UNI6>SL9k7J1f9fz!Yvvoj$S{z-K*(u}Ya{5pM^He

>-$Z-?0F_Pf_tf5s{! zX|P*y7U?3?9G#WkvA?``e|%IMy39tMzWm$H2vGk0ouWx5?gJ1*z3{M{_DhUAt%AUd zlfm%POmTEUR{0iI_^5DFCwj1ruetp@oOOQM(?IV#B zP`Eu6shRjLEr4z3hB{+SRgZHYs_uryj9Er?pNLLU=6f`Au=MyXV5hOG{t{$+T@%*F zrZ-I~X~6>zt(+Tu z@3rQPz%eMzP-8X1?7)PL&^^UN#T&o zoJ37JcLz}vCVj68o;c{mzS%8-JW-Jz9c|dW%|Jlcw9_4OvxEvAQkTFeddhbooQ@x$ zjKlPghZb*KDNG0*(@)m?sBLoR5$b|QjPJ78AkGi&(G zI^-xRH<8hMny8_!@>UsXCf&vxgBjIbh7}Oy0Ftt^CxE@N*SPDm@<{I&O*d7X9n*&{!dwhJ27(3d1T^Jwv&oP~BQhVW#dLlP(wZ2eWV`}oH z1H1WVpjR=%IoiaA5LuChBH!=u=MobB_NSkLtcvfwxv|F=CSRalCwa30q9g0sE#e4y zZ>;3WzatE<(&p{4?5p<7uB z2+Tv6cpi$HrLVDU^Rua9OGm-ZN~ZZQPNddgrgV(Y6~?INJa{pL$3;)vYOWD|(W!J` zF7>Iqy6w+oz)Pme3KIj6j!K;jGG-J0{_dAVCd*T5<5iDp<{CNabXn3%T9_2i@I~+^ zX(Tq&Az}RWBr>$_X}c3&YcpG#)fs6-XAe4wHHm9RdsDc#%mw*QzU`CORJJxCd>Du1 zQ0|>U$P{-TAHbsOLcLTH_0w;S)Z8gw{jWy&a z^jC-#S>@50?@1NU@a2hVu|E?`VTXJk+JCrjmtS95Bg@mFP;X>%M4Sy2#an#&THu$& zqxDzrM|k|WNjZA>=uL#^Yt-Fve|(XgZ!EFc~x#`e7H|t6gU2!5bxH zN*IaBJvz|{dP&swX~@HX)ZiN5unwI9%817R}rn0~cx5P8ey^}^@l`yae- zv4`D0V+YWCG#WE2d|aAr$LA7Jht^@`#;LdlhU|fRrQ?0--%sNFx>GOhjvT-t`&<_K z*P+F7*~=e`kbb3Dlu*LGAE_#X-V9TwKhL7UTf4J0)%~r_gRfpMQ0j6 zA1nX_4$xF+@lSsE@z3#iEs2Ax<6YTpM2!o*AKpl#G-3BD#QdAk(&_$SghE-FVS}${ zsSB=$2e{Vk1FyY6{^*(0uOlDq-2xlE?g%6QmXL3+2tx0I+0lm=aFH?=+rm>v&VW3d zJR|r3>)Tbaq9j{5r_jU>emonS)^F^R9MzY(URncv-YVMe$t@&NOR-+4_iVLZxur7P zG6IxwgYh?1)x_7}#MC@vDfxysucmwe?wjd|v=o8!wR|@n1Pjh%lf&7aqE9OYZ+X7> z`2QAthaSsq5-h>WDi|u#@v-VftqK2J48Y9rC4z)IwL2DFplPBLf3H_>Dwp~Bmv$aeV zYw=F4LOqZ;u?~m7Ah$i}5BI2{s`A{w7EZILru%@CCw?B|ZAP=7Nk*VPHmw1HS=xe& zl=I{JawOKuN9?kK)`d{|(@Q%lprQ~N=8~5O?#SuX;;rw9zqf{UnSAb7f(w!Y@ioV0 zi)o~Lxr^OEmx{QZ*nT^Mk`~mndYX23a25IMFV}A>N0Q2N+BeH)BmhMOk)QOzgAxBi zli5vm;%jpa^NC5=A0B-$F)H^#g&VZSzWXUY{Sbc*3JX^ytx@~%-@Ok;WQj~2krIC9Bi;CdRewE-6qiNf3O}I1U2+#(p{n4 ztb6?juS+XWTCNGyTiF8`_&yC4uh{Bow<2akWJnvWimQw1t@v%!xlqjni3r>3is?$02xHq(^Vh zL(_Fj9=%Ux<;||;`Vr7k<4eUUueyg-7UT65%*+Wxfb^rnoT?z2gCFzbuaI{l#I}Y& zOTd!tF>pDmhhw{*iZU=H@RySTwhiko{v-u(2J@%i+0XSg=05Ns4;=Sam*%?(fcO@= z)caz7&Q-c9ABq(=INhPSV7I;CkFBkO0bUaa+h8_Y#HaXSnFAAp1tnfx6GX+ zpF1a!cVRWHfNUSPJxPz$ZJ_6Xlg9mI03Vj=Ir@KAtDfUGAz=A7X+6G3pskgYp0hko z=-Bs9H)gW^etGThy{|VRAV)lwc`xchUN`oE-Ic7oi7fs2CsCpssu?LcA8;x3^k~QY z75voZ94Ch#0_*b$gMO{+2ei4i^A-^(eUazTjN}*7)nYrVdpW@Ypo){>jZ^AAE28F$ zk+no}WuEz|e9NuKy(EA}jpIeW)=e0$?edZ4bx!eHRWt&E0TL==AbJ_W!1L^ohj__$ z7qO}d70->-HmR#iXKBlxSYg*IO^roNX8G~=(3;XIQUhKL<0Hd_?_%lu9kXQo>g~6m z{%8w8Ndzc9+qc|(%NKlZO!uK{2H3^Ghu`{HKF}6k5zq6!!G|7qVT};al#rqSc`gsS zJP*k#;Jt!_nbUj{A5xcenTp7sWqhEB`~@k|W-5i}#NT=Ggu45w{^vQ-we=Pn z$cmMQIe8Sk^1a=*`|Ig)Yu^GoWqG464+&}q0>d7h!P|#Q1PLpmo7K~+bC6`kJ40B| z(h1cTi9)?<)s^jcGN~6JwWqVCJgz<^llGI-QRvs9`Fk_gi%-vH4BxZ*Vk^@V+21!i zw(Mtbqntv+Lyp<((mn5QLRGVDyv#sW%6n%2`D%5(_Bwj)o;r!?f((DZcL3=2??RUv z-((P%0bwjBK19v^`d-C+oL?xk!V;rwKCcUzYTGk>hU9 z+dik76U;jy+jT=gItiJ{rXD!d7)0DWx;{sir4w-u3To$B};m!Oda^7e0ev) znr}_UYCc&<^^c5ZLSzdDO~_WK;@4Gc`LC5KdV2Rh!B(E(-bU*`dgjjR@IlZ=RHq~3dd{KP&hx4|HK{okuNJfIx)8NT5Rm(3ryhj_q8Jg!jTfNN;mm_x4$A`RiC_#K@pp8!g9i9R#$;&? z7%^x(Bl16Ej?*R(6E7i~F-+r#Jb7lY?6gM!)Q7Pm6nVE-m({otCSQ0lStt{y?k`J?_MED@p`_5NY<_fMWA0vCDHSg~Hf z-n*f~5@Pd15FZfD%u*sP!hD|UWYSC&&WS4#-3<-Tol;jSsL|4!2FlT{{)`w6s>l{e zaWkqIm;-zk+JzNiw!FUsCzRWknkLXWSmp2P(HFJzh%AJ@ zCpmJV-)M3@Z593R1h@xWk(d|!7!vLDfu4mHnn1^mdNNbH6JDEqpM&FhG=B>;3&^Zp z69k;K7dwtw7a&A(VEPo5ELCFe63!-KrRCGk#r^_^tv2cMd*=6^8eBPl!Aw3M+TdpWTOi>+yu#Hcl8QSuKhkHB`fh#E zF;_rIbUp^MV^>;uyr#QoZmT?-Zq@JhyuB6S_l66&C%~R?fs|vvt)Z-@u;DF^F~g_x zquIj*+Wln^WL5DqxBBlS?Jb|=mA>&^srWVq*NWKdb>8z~%`fH>^q-u?9PZ(W(Pg&1 z!xiX;xAG+GW8fFZzN>sE66H)Al1Jq^Tt8JKRj9Y=epo- z?6L~6cN#2%=O4=;s*O&4{ym>Etg?WgUN4wmy8TsSLF!4H!VnbsK7D)5cf@1saL8F> z54>>bt$pU&?Sl_F%@?_3qurczXfuJFgvS%T_WMZ^biWmRE)+qa_U=f%eETy^yl!Hp z1~>-ZWdCauV=?o+VuJ7cZI;=sey@M(-4_Aqf*_m5G#1rpo@uZ?|N4UOzMpNw6~X>q zWOsMAb`Wodr1rC?>sj1M=cQ-CoprKOKPj^%4sb;Toeo&qeoGD`c1#xz_Zg(ns}%c` zGUYEW$_kr{5kK@_@$iO>`Xe@sej$OZw7TZ~E;}1r3reo&>_s2v;Mp~6;&@XelIOg5 zo;>8}Op`>P`3JKL)ZE*{Q=9u9$b01X6#Uv4Ml7GH^GVm2r+@s9-^u9(DaD>X(qt5_ zch2!DpraY2-%>QVKdn!yL~=m*qGsOD##rX#kw)*`9tuZ*FjBkT!Hx0(YjCUi60V$X zd+Ci?r-+np;0s9Dqb=N0Xkbk}=<&A_vEBpCS)v9WlfEU8va8aI8g9#`E)puTsoJgX{C@ zg}`57?F7_de?@Ukv8{v9edG$ha2Pklq6QT5c=krXu5j#X;a`!3z7 zx!h+rk~T2O=hPX7mKmQe)o8s8jT2aN_({S%xqo5OSAl6B9tU?FI&EH%5R|NUd|ib# zd@A|zR^iw}$+qD;vhsD#GvHUmc@3T=f4$fAASV!JY@`RM2_%IM#1x~BmI52G=W*p0 z{=usVUdYlgt|Q3<7&&`%AnqHi8HMwu`prjfO)JtmwTA#WGcS#UT{15rRtj&&?VvNk z?5VvmoQ$NG3<~4?Lb-!(*MJsk?|?Bmv0vNM09a_;>R>D#~fuNI}g76fN|Ker1BvP!CEJ~$Jay%U7%}-$&(Lf=FNpZq&tuL zc}xl3(4K;ihFG89@P5?zDeEM8Oywpoa1!ETa4xjjFkzsGz9l%*h@IeDj-Jl{=~u7k z_-Q9Ua#MK!b`54-@p>um;1b~rbN4A~imRyao^JEo?bFZeN0vqR^2Z-Hmlk4@gSp{A zNAfQu(V*fX`UYg^HXFs~Ik%MKJ2^2d9_hkyn_6Q#$X_A|bO1;ok6?ZLRQ-v*?a>7} z;K{)5%N3zVa%N_b)FsD~@$AZlUVnKz{G87NQV98Upbdhp`aYZ0#8pn|mFyqv7|k2+D8`Q1EHDygZn=m3ErM|(XPF|m z&$ZmbTgex`%u|dyR>%4_Bfl7j5Wqz}m1_Am2ksY8x`FD z?Rx&}ZG%GyXCS`x|I#DBJ`aoH@$bry{-?iFt^5xiZXUzmL-~ST7_Dip zoseT4fznuc8<&^k-u8TT4$tDk4W5T6MTL{83uxHZ9OP*dS%|bsFY$Uj^U!_951WMw z+LzRqjN~WVqVIf-BCNr|+tZF}zzV~~s5h>s3RI-iL;05AQ4lZ?uaEJAzWsHjFL0T3 zn8;4kv%1Eh`mg`_-%g9U{O7;J_~%J@Ow(_cMeDo8EPv5XYy9JfU#ygTT54bv0I2w8 zic57+hoBF?UEs}Ozg<36V1)A^zVd(V5IeK0BG0K{p45cb=J>~zIqd)D)mNstolinx z4eVd1Y%}7?tFI1vz&BLG&IjBrXYb!T*1yKvW?7Mg6s`>Q4h;o*0mwA|Uk-lJQC$;Y z6He<~sw+vRmP;@~!v1f*?>`k_D_`SSdl2c`9+Mc&wC4eKD?G6^fDcfHplw&kNaa_ z078;wj7+XmAV%z0i|v2=e7KFx=#Qux5@h_M*%P#%SWOxtSo`uMET|`XtVx&NBb@Ik*Gk z48{gW8FuGM$yLQbD9HdzlmqzYh#W2RulIX_z8}$dwjp zL9XWd7uufx@W}t?vvJ-h(8m!C+LPbo{>N1s3WPk6Lo62s&9`t^bvS0%e_Qix|)hHSJ>o@oh{ESF8(_b-pZ!R{>l zgzzWU4SK#;G5Uh>!(FNHB!!P0f#Uzt`ECU4{TOx5cJhC8zWu%b_nG7N?)=0T#&Zrq zWW=Y75%kCK+SLIN>(Gq@(>Q7G0}N8i7NYgztkHB?&-DsaQp10`K&KcUF5?R>0GaN+ zwf&6~wiIE=QjGQhrM3IQ6V1{Q!=I4jiFdU`a*nQq9{N@3kcj}U^e+pi^nly>JL)n2 z`pT@*{LBoHp)cK6YVqrY_eN;PmD|;9AulR%L;j$}yj1zZw>2NX(`w_s1ve5;e|B#0 z)iyudx5#*ZOdSO;FSJJYP?B!3A%DamEe)sEF)6QX0~b|V>v08rfv_PbN^pE{))7Xw zFD)9kMTZ9CfsF$=LEZe?h471LaR~3L#s}dHK zK|?%T>wE0 z1hq>eNx-aQ8weMdYM=J39vYwhNuSP87LP+CHYx!I$nNZ<wu>;Fb33X0erQ)-JpTS&}RJ`Dbg^1I!*S;cCpZyU(^a{G*zzb!{raIQx zNp8t~#g5>&PSA9=UXl05(QSnt?^m0y5MwAm4&Ez_+1pF}K5q)Tz7QvoQdj9!wfPpGr)N#gzd?qdKC{+np78O&a@xiYY$E(3Wy?usrNNKTVbto+|xs3OE}fI*9FV zI73nD(P-uU!w$Kp(FsSi&x%f>#-RE5_3w^XfyymoR9J zO&YTYjopWC{M9s9EEY#vg0zfB_7OA7gYuN#{VTKCCq5JS^2_k2j*$z0xJpH+r|{|Kox+nr;%rVTp1qj=c)coSSu zBS1F5g{^0kYp>q&iOcho5a)wRHRgK${RFF+L$Osq=NsoAYS7iaX9*%v_5@j3?}R+Fx+n)~+fVJGWhh#~;0fB?G^ z_StnjkM^(0$KTg4(*oi7U82?3mja5#_+5pd{^>|Bg>k`Z)T3Ib#Fy?wer>pqfSzJK zM4^5o?6nK3usX65=U*a-?GO;arUp`2l)1-C=@F%r?HCj{#d@l+;lgcmR2nr!-|xBP z7SAKlt0D~Rohn%YtA~d?-Z{z?%dx@5lG41t3?uHzn^^J`$(}wYC8($UHRq9w zR}SDQ92HtGfknV<=&^5f6nB0?<{71L>o_3#<}h(bT(+kAgyc~&ftZq%{c^wf;5i^N z2X1`|@W<|pbNGVJ;6=II&ZSLAfnJHo-~Y`7=hJQ<4LJgh&nxzt4doyMcVMA>zXg@; z6tI@P+PLH&?@kuxw6>;4U1SBg^&ut{xr{mKk4epc`e3%^ZM=7LdHJS5us&B%lVRl# zNAUiiJiTB*(TU>q`{085B=fK8{^d~h3mt5C4;KJPP(mB|MsRo1fqZR9N(x+gE4+y@ z;?|BWJ}DY@If{sC>Qy$QqJMO(&rPLF=|08lTn=g{QR4Tne}1f9rHf_#+nlz*Q2}R% zo}9TuR!7*_D{eyYR`|vpOYzef(bQ-WBQi@qTvYi>5{!N;2I#haXDYp;e6@PHdShb; zbBSq>5nq>FBxGG%c)rmd5zZa+oHYMrtPo?r8)?471MBsa>xk5_yhiy974_0jxAsI9 z=GAid%1;3o4_$UFES(I!fdRW*;qvibi`kPrly6_hlwX9%40efP^;Ud z#@k0irS`J`QU*Rcx^&{{r3(kDw1=O1vCbFO0sB7#ljsoQ24 z-Z@hK?!CQ9@nqA~V_<`qn108cwYt)8%v)LGUk#M6XL23R;*`6W{Q28hjn z>mB2Bj?F$nUtA8$vcul`?e0asJDmFFYF&V^u<};45#v|lS^_?zt%}F9e-e*Rz;D-+ zp&L41on;Km+?vK1HGJ-JaeHB<#^O5nn?Edi)G2ynQc0ml4KqN@-m#^Xu9n@ofDnCL z^T1Gjk;0KZ7jj(pR15nOK%DapFJSUe2f%+A_9|At3%ccaCgA}BGs*hIT~Q#9Ks^2+ zT$g+{+2zii;kTH0O4y!Tt#>Oc2w@O9!fQf=WR|e?n~kF%p|f<3B5?xo#yYzs8CWLG z)YdNMG4;KjBM69iaz1~k4V4fxke?T?_l}IM$xCxOAK`?$Vr>(FfYR-f(EhGDe;$vq zm00%o?a1mnUbE|nlnw;%*(|N6h?_o4LM?!gkoM?iKwC{VbaR4OSGQBOl*uohhWE>; z@z;KQUo)#7C$)8V<{`f!VWd?SI@>o*-I5*MYon$M(^nfeZg}q=JCs+GAA&q{yjnmXhRa1yfNaKR9nVbAyi~>U9=(|6m%bP_e3`nTt=FG zkZ=BTGIr)q%wlhE6PZ0vT@Bo<)Svi@3y=KW2SSjbI|}*gw9)X0@!T4Cn<= z;|DZF37`+;a|%B5&Lk{6N);ke4|2rE3wQ%a0@wT7GfwC29CD2QAbR`+f-SocXYRW* z@Qp!WoloA6?4a=_8AjS1(l*`nXHY)3gF<8M-CW^p;A&_O(FAOH{oeKKmtms{@n0xt z_~P(662BUCvAcOU1DN|L4JEo~aC#g;%e*H?AL-}z#pf^!bse|cX*d>nHqcY2-d{O_ z$nXDToR)8Fk^=p>i@1(DIApardmAk^8tBBF^n>v-qfy+l^b4wPb4+;tIx66Uku~}1 zcDv_C-Ax>fkJJL^`0tL>a{PG(mm9M&0e(k5dWUW5oGrMiaRtYfIQu>O`iN9S6Ed%G zIh&>S1;{RUvD-wBqC0V54_94u-J*5VP77E+Ub&}zpowtH{DjFc=ur#Z)`HCnHCpfQ z4Xv0xc-Iv$BUX3~kU!2a7(f1fs&e`r!3r9yo$PP;NJD-LI|M6Qi2D^cf2UVR820>R zyj^5AFnSvLzx-t`%G)cDyNPSxz^}qV{6OZN8N3S|&%J3^@=Kn%-K0IP<;pdjD~AX; z==7mG!`luwJ+y@H!yc8Z$arJ|Uws>fsKm4^w)2R2cX#(%-pRopf2lt6RmN<1JO%$w zT&e}&KPNCqt7+_WZ@q6vyzf!`D92&o=>!@h{&*uXbnzaCP9SiE%T$`f6v0YF@TyQc z%N?zj1Mgu6s(*34-&0QCC)sdMLi-x`7aKkr2{(_ld~o@Od&DGg&+pTbPmZ)5^z*rv z9$M6S;KWeSwhuwL9y)M&nytwLh;}+SG0PDCan;~8`v{ZE*95e3Y~!{*K1FA z?uhMX4>ap&6ly;=S7V70TL{-fxa@W{>6=pt zV8-E11%dfrFCKLS1cWvJYJl5=OOe;4bZExGC|mCo!q84ls>_A&qf}_P>8PEbTR$?~ zmb-Duylo)U+=Ufs7j<~ddAAK9B0M9w@m#e78}6B|>YJkF6>aW!p8yYn@`s@%kQU;h z99opXyKUGbzg+F@2^2(d)JI9E&qr`t66N3xd+`A_dVbn&)e%q^2r;Jybsh|Q^y9uQ z7mfm9DKCuO+{<>%@1Yd89jrEBI>HnLKa*&`zuzwN9=PfN0Ehj~Rz3@8VKFlc-&BqW^nJDD_IH?}&M}y@LZ_q1MKZ#IW>_}%Y_TKUyr(4P$ zX80rAb*0?Ij_%~L64^Y`8}(Z;qJh@vSXQ)Nb%8;#B7DaD>E&RCEwuTOgFYP?BITlW zjescg=b`d7`PfzF?VaJoxqYo8f2r?Z=TXH`cfbd5B7e!V=YrT@jK-d@*E2MOzArt_ z7_+mKu`9^l_zg+IWO}?BSVKE$%io2SHoVJXOOvf1ra$aWyypyPCxSEl>B#5k8Y;yC`umbe9O;JpLCx9phjf6rP_HypPIyFq*RV33ah#dSYVTKreUo^yz0C24 zt&5av$_O{Wl3~w6lD23f0}nE36o8WiY?(cYE5;kFM5+h^J^cl9;{j)fC1n>5T+u{U zMa{?4O3J5G%QgC2j}N$kd5Jvib^z&LU%F?67J}c#*kJlzfPvII?S<4eMLxPSvMt*gBEtkH@0K z^9Ba#XPCbA zw1H<9BX46yOZb=<#2&WJkxKR^a0<+iM4Wh-n^aOS;kMZ%wH!x;Vw&C~g zc|G{%mFOQR11@@NL_el*?vTF}spA5m?_{@&R3a#oKDP-Y!@3gDrg729WePcbWsiq* zvz=*05$xnMO#J`ccSTVpGjA@aPn(>|`!xmnO#e!blRw7iO2^o-ctYa^v8SsB&SM|+ z=F-=5clFelc6sETWH3%q(tR2r%gON*Gl`T)1W@WbQ{O>Bp1&+`kso@|NI zfUTc@vShP_iU1gRtbSY*&|(^>JMPC36w;`-lGCR;RYdFmYH-gomm=q?2jExVM4d>v zQX5Qh_(BGGD)QrlwMGVZlJ7hkdD=#D*^M8F8dMTm8p>xmRIhQPYdSbgo4c790S6ZA zE;jF-o4$241EZJcd|nG+&R6+010Z-K3ytq6^|9{|T+%MYvFPK?zTK_0z>d(a(~juO zSE!GKf2>gSZ`%1%TILeCOPB(j z^KpnrHw2HG;r1ZTr#CwH(WOL1!1bbUl7!6P4|TyT`SIC(%%VTs2O}ax?0o-V(2Ch?j~9P)E9oW=rf@%sQ6|To z!W7qZAytNJzEAwd<%zzdg&mA9?XGxoBP;+IL6&B8gb;;)S{t^no~_8lvvys&|csRX|;D6UuLxpb~Lgv20d=QJCprjgx|;2SfB zVT_S~c=;We3OiDEudU*OZDHdaJV!%8-=(zcd~B`ZK7PVuh+^3qeiRH0_mT92c*ZK_ z1if_nEuBD)W2q`TRh?1;#48scvV1M!i%GCVcdp5N|6X4}sIKFMR+zrZH1d3VAfHiR zxi8}M_@u*$vu1L!FdBZN$l@h&Epe1%fnAg1f}}}F?@jE%Tih;sl*IV2588|IT`^j| zR+}z-WUx~n+^ElI8N55-1h2oC!gtnoudN2%Rbm%wY2*A<9CuQ&dqUTYc>n1Hap_qL zP}^`Ti@AyV0sno{jz@6iXXkq@sT4$syzQL_xfDKP?soPk&qdA+q(HpH9o2(E zywS-z+h)SJ$lqIPg_q##ptYiDo?dz1ivIEe$keq^G=Q*q>iGEU03(icNFR@PsBibL zH|eAC(C0f5;MRy6n!a`B#j3`mzeA?wS?gS)R^;SPCB8^RVDQsPj!b0*bP@a|r_ZOW zwaxwWoyVDo@iRusd(l}uh0iSIhq$=sB_L8@eDXY;RxLsGRaw{JRIw1&CK2&KbNqZY zc4ziyd#iSMJOS?yB$ym2e>1A<$v=N0sDZcs+jEbnRG7dcG70mcD`S6*?qxY|#CZ}c z?DqGK0bYl4n2vw{`;VT%74whF^4?1ebh~PCJCY>&jSMdHwH>D@dvsY-rDcS_#7ea1 z83RbX`hki+!IFNsygJUn!}=~*AxLr3%h!+T?pC0Rk3fEKN1Zh--}%zox8fG+)f+^B zXFjvLg4gg3Tc*7ekURa6*I?Uu3;ScV&2w?{hrugX?8B!fg7soQdWLwhl*^d5(mMEE zwEyS6Xam&v+^r-R%e1iV_AhjissXDgTb=LJ-`98)7l`}L>y1~HXpi=o0w3nP>R|Aeumpy$2IVXin5Q~LgQO86LP?qJVeLHjH(2#$aaXCuqVDP~<9H$tN#OgW` zo=Xp5cm+JGI9!Joc)r-e-?BZXHX>mtY8>EGqYf4XX4|7XbI229>`&Nq=S)jpeAhJ8 zuEKF&_sW@~rRAI?cFw*I4YK-c2HZ%`93T)Xfz~9{i27b^zCYg3wmgN~PuHWo>=vb$=)rtBKLV`qJKfF5^$m!&)s6tW@kRA z<9MkmJ?CERAbljJgS_mFz&5p&Z*=O!x4i$hNx5Fu+(KSaJE+H^dLwvmYWv`xXdYoP zbR@7(_W`7fMt`gX_ZsGw@()>~oTf;!xTT22VMLWC2n2G#nTyQ_PyV2N=@{%N!IYbn zxloj{F5bGs+51b%8{RI$YM`=r-us0A`@JO9>wNzK>|++ra=^_2Tv~LAlH)UjXxp&` z>35!x@PFt1x5-ZDipdsOAzQH9y>oe8xw8cah3HG*9h_1u??2L4xi|J0O5en>RncIC; z^p#&v5D!FMiDxA|_pCjFLKjsJvpfDcPGTgcOiT)v!CO zNVtyA?$jxF(30QWRq8`yAjrK$zrXCrWE3`9X_&l#`GwGy*SK=;-m^!yN75kPy{^9q z7bn!b=TH+n$MN!?uXGE zH%U0gIhDI?9Hwu*HU_hbn97aNYaXFKboe>R{%4j%f?!yAC2Wm0#C_Jd`0Jq=zLeZ?kkRo_<~|B5Z@)1ijc!S4cU5OQk)@1fg{^r1`6}o{-54v6#Zv!lm0Kg&F%|@ncA_+$&d*hhQZCD zL$sl=PZ0UcrdLKNfLlK?=FOqbj!Cu5B9QY!6XvWzToF(J<9Fr z>fQe=(ih1j8!{Ot7cnP}7=Ne-wtLXYUnl`BrE^Bu(8PK2;?+nB|u3t_} zQFeWX=&|xq(2kM>oK&>L_)2DYO-fn#lHOzbBpF_`4&Gfb7#2bCFj(0c7=K)VDBNzb zf*_dg3fjsEn1?FZZN;~6F7Cu?0_>SyOhx%^C30T&qRT}|-uMW8{YP4(xF0swWR*+j zfBfYmZcv7hG`xJr3_!EkR?*>ok`z!i`AMBpxqzC@Oc0cLz)0_Zo?#g8V=Us3oxhuMLPOp%A z9NVpbKLe{nLHp*x+y6gAn9zs=v>K3m`thfZcv@{$9 zb}Qk8%hj?@Gi=ZwGmqbU3%t!T9gGyvh-hL=8g$LCHCQie4bH~wA6_qw(s25e{_$&Q zMcwV*0Wk2F8V&;RdxGMO;Me6(uCmkvi?AIw3V?ZsT0Mpx-ci)DJY*;6q-*6pe7M0% zrpNEtPmh*I-WDK$9sCh>^AGvn2QIk2vqtk8lfQO*`&Q02kEiY5XE49T;;W>9 zluBM=0$#BnbEkmyJ^fQ+1>Ty6=s|=*NjR!Vp8||jUCUp*wEXi^{%V1^!9RoEDYcO| zu23BRd;#j5zmvG{Rwo8(w6zd?@#fq9?eDG@ZjOz?!%~jKKRwU_0t9Kt4)AkXaeE;N z{r4ARcb&CuX2S-KwCjH{w!U*-e>LIjL*R3l{~T(6e^>lAmB6Y04I-rJ5!?Dc!1h+p zRg7AZQ_tS_lofjg3?n!P3i`WqO`(HTeG1lD!>rsC!C!rbk`q#}K+r|TTC7Ii;s_F| z#c9ac1(Af6s%U0jGRD}`c7JB1YG6Kq*JnqwR;{YS^@(o~siyxn83lFXp7Ff?okxzT<03jeJCGd*pTQlUu zi8H9i*8eO#pJ|;4?OOt-!FVW!NIzv~$Y`2`)bkMMb+}gF^0m`V5|3HEyigwQF^{O}Z7t zZ;h4gvo%qLcI_;Z7eW{9%F`m@R3XW9@Z8;1nqtK1c3vdJymm*dNUjqbrJoy=%`af@}|$ zh6pUmwPYU_^m56;mk_r^#MTMp`=!^e_42z;_0`oCO2mP2vCJG}Us;^iBft8GdE6>b z1~SE5@95D;9bJK!3W zCHJXsg}rhmxBKN3=Ts>3;TTMnZ$)qqy3O|8cfgId>zm-SQA^*=w`j2iX4h5zb%?hb zJO5{f@WiK@cqAKux41=aL*IDY!L-`GMRf16_ipg!q=STFMen;ut8*f%&82r_WlD6%YHE|!str|6F?62{xMQ2mG18|JJeE z8!tMp#OLn#{?Ffu-&DDezmMnd_nn_G5=TC0*Mz&*)`vc2 zgKxZj0mz%Q<@TSi8$N*l{$6u$_)WzJ&)V(w?~i*A!3@5&)_;8;$+wFx6T;~+{?GS} ze4Gx5)GEWL3;lopw-1NT?|TL$mEH}e`WM1qh#!tOzaukqzgO2?jv2gw9S8&zpI-<` zxRilIpBid;fJA17>jF~pVP-9nDC0>0CYeBu5}P-4iz$@$tj|-2_}wl+oNA648~ z4QE8lfKnw8Z7Q6upv66WUt1=~25?c$dX`k&z8=$9;Z%+ol5jK1H!{va-a&Yb5oTj4 zRkRCMWw2NT`Y}1n@z7aq4nWWw`cyh-mWTY7)AFGV4W&ljYX{5TYH$2*v#$gu5z}ug ztCk06Cc*w<5Zk z)C2O6%F&>4);jeyqtD<*j%)P_x^BLqCgt|MWQTLh9>W~(MW>d;vt|e>>?B({mjK5R z8j_P2;nV5PEjEi110#cRTc#wL(0oZPP{HYeYLvY&*1pt7m^k zd18yJ$o(L(XS0J{=d=k3wqT(2f#65)e!)D%$p+2#mCvph28k@7qRUc9f^)zilf^4(1hKn%0$n%iTj7HHu9$GCP?E`&z12!n(drgFTmW#eG9NSY@p#8(* zfQSZuS8dMaz7P?6wyn&#`(+;*AG$;Km1OF%JYdKBybYDo&%cb(WAR+OwM|;Zk~|ak zGedSwU*E#&wBL_(iY|y}l$d^ksnojzq9Pv5CJF`-r~P!!3>jI#fI-%XIr!SvY!#KH z0ps0HdS$IUh$Z9Q!@Gi~R4f?MEAgqM>RR>&KyRB%k>}z*SVh2OCA$)^IP4MVraJ0T zBUgjk-uFEYrz1@-vaX6#fz*iaA7$@1QR)x(P_L@rMao_Z35o5?$tPYj#OZs*s|W3c zR_OGSZp8_eDFW0(dSoE8VhZ!iE9ni^6Z)`Y=Jr=ex5jUzSohtL)jCqcTiO4e1{S@w-mH$3 zYyLfJces4udFoKP)$6j4csp3)5Yq$!I^Q`iBM8Q+=0LyDv^gzPKF15^0e;!9@AFqI zJ^{+-WL|Qj;XFgL_KvI+1+-C({o0py9Oora_sIVd42yZ0S3Z%c>GoLjw|~9g{ogYu z0vo_g;k9_`G2B*($%=`hXlR4x>q}RE(z4-xp zyUz|Q7YOv{y8Be~wpYaYR`~-rO1Jt^P!r^v3zt83cx?CX=7B-p$?CAacLd->=cG_b zs>5bz_gLrEmX`PZt(Hgf?=R=v5zc#`&c3Df~{etvl zJ!225yNPaP^a}%zQ%(V5P@T8%IQ5{6D&o+WlrrixZ3vf&lOdG52^iek##NnPpv9Jg z!}wP;i(l**=cerAEx8Tse0vT01Bw=tU%sB+pa3s$|4RgJA{4S-vlG6Ptzo4JZnE>iXD}BPXcw--7 zNLqr65%v{+YL(sY1NBEFBr0d$z+AUMBfDct#=5XSzj;QS@IGWBAN5Y#wQDJ zMmk&8EE+ybS;lpOzkBkFYaS^^ucF|^&xr}^M|<7N9O2-740sS3{j$9BKIFbRtyg07 z+UePYN~I?Fz~k*0X)H?Y?g$#Cl=gdk-`!h>xq^A_M;GyS--uNbgs7;}@B7S_L;aeY z&Dx}OhrZdi00njn(+%hHi+bO&9HtbRohALOVAreNKbA!QqMc6I^~z%Vpq;tB zb=!iI-kMDd)m#|iN+IuSQA3S~XP%G-yoo&(pET>b?5xp;8wuLYAeVr<-1l!p>Z$sY ztWeiF5dT@^yI-?%*T96_t^nx?$8Xwf9i`DL%2Nb7_T4O^iZc1n5x5yt8b; z!~D6s<^alm``o%b5o^8fZ!Djfp$gt`YgL~ke^D~ahlAlB2E)4TeuOx8-TnJ)%J{^5 zjSN5eotPwtQEjs9C5-om26F-t!`tzUE($@sySW)8gYp4R&F?-rKN9`gKb-q)GP=#6 zBLf|XQ6J#Uu%9w#TrI0zqAlDZ(uq%ryp|kY-;x;C%~!~zgHvI4b*pd=DmD4*4ca9L zCFKpRtnjT~(2Cti4Lev2eG$Iay`J#}$!PFnegZu+N5PK4jKCif0(DEkT?Vv|5yHAB z){>~_W9J^j0*NDd%5t2h(r{Gv2QnY%fP@Rvwq~~2;FD-<1q6@OcmAO4$mjIv_FP$$c1LHR!O;kGYSbpM-Oy$>>9hul*%#!pfPJ*S?CWt<@pW$=MykGVTw3(9)}h z&sms5B3cc}Ha>i_rjPdI+_}=Ud#Ncs!shA=>|&$lyuv4uR2fYprRl{>jvdkCjQ3mM z*@<|+_(&gAKPkgbFFSpr>Y1XUA~AFUor?5Tmd4-HPP$9ISL8#Lv;$xCm>lp7rcu7( zXKh-wUA(n7b~}s6DYtVHd5wi>hj4hdo*-V+R$I3{3VX-?bhEEw&km9-%^oo1OM4bx zT`uQyYfOrGUcaaGxy#`#Urse+Jif1tMRk+hAGm6(jNwW2)Zo%49_@E?t9c4DZWIxk z*dBJJqrpc*D>v!7k*y;EZNkyrR9e1!-+=ca@ptrtHz@o2#_v}Z`yi=5(*+U8hu5?6 zPTWYi1OofW{tWF>Ws}33GjsWsw6uQqIlf@wXm+%1;};+JmJ1UKP}pgAFI_BIe`ivk z9%GmOxN6m6Lnq1|h7xpKaIlXiv(j;*9*%Yb^IzmSU$yp_Mu%(^`96H@AtZF3%x}nB zsD0l_;odp+FanLw*~JG|_}w*lOB@e=uY306ApWjT<2@Bsrj33!FDukp-K`8>7`5bA zR9;GRxN_}d65bgP*bGlj7R?}C@j5NE%!S&489!`Gq9iZMrnqX~`{L}y$onBe-HX65 zUwo~}+81Nm;tlGQ!0iz%ylSCk?0&8u(e5U_9AV$4vlq1k%^%{&x?;*67m%RFBM63W zFAsp!GuIirs3P36{1Yd$6bwn*pr{W%1;3ZRa0Fr{h?-d%Wk_i=24dZKiT<@81tIUY zQ4|7OAq~RT52D);8}G-eNb*1OK#+?`VnU;Hk2TQY`fJbE-2p(mCV71WyH87o-l_Ge zAt&0>ah!$2gt#4EbdQ_e)goi~0c^og)i*qFbJHK7d*|;p5&n_W=K&c83Qq?F;Raw$ zM2R}rzkE2y=9rmjXSeb`6PR>Q8d=5I%KXPN8nylM>lQv(Z<)cS-}DQvYk(ajvg$HiK!eaj|l2QvQfZ{P}F%SI3gT7^Ap%5PBz$5PqK8C zp(z)lS*Y0?7AA->ilycH$c5Nn?x_o5@jkoBUL^YJy?<+*p;^aWv~ZWhYv>r_+0_vy z;kqwiZ0~fAb8p@@H3;zR9zN?a)x;j~EUg5vu znu?q6ukrV0{WjmwOFLqFB4O4SSNHNzqGM+^b79b5og1IBm0ek0r4Lu&FpF!}#E>t1 zDH|VJi|7bw1iR>VqfQInP`f!d0F_YJ^L|K<&F7Jse#t()=}~*9dovNiSIYE#ZOr~X zDS=xp|{Eo4H~%JSW*C?FHUT|YU7)59lWlf@bQb?2jlJ+tEVFbc>WF3WR75=)bMNhx5vC8vED|!YNyC6*8-W?ynh% zyV}n}T~$5ggc^;JwUgqTTu|;Jjirc8!U3;&KGl04A*S1P#jOf1bLjheR0KrgS3e`C zt6p2jqD$!8{3u5PkvwXpd4%5JpixsjhjIQ^>hA)j@tFwCCIQ}@YeB(5rByYq=O4Ly zHv*+)?Xim(uL$qGvOY4)c}rc~NxL{B?m%O$%UP5EK3DEhBChLa5RcO+u!3yn?d(e@ zJ-e4yA79?y)ojfB6%_;NAUnz{9gkhd>XIjAj=zjoURHnef(z1INJT)%g?VrD?;dS& zqJ6i%^GUk-d3{#)?^<5Q7di~AM9hx`@>?Ikowqw&n>8D*HGvgCdhII52f2-`Bp}AB zyz{WkNjLutMkiNk#}{poRc(1sqrrAte&)ngR=fslw7}0sb1DM{?Ih&0Pnh^f zzrVA|delj4Z10|{2K}At8?p0?K~Xn+NHVt$9#nIqCKm)qC__=-q;vJaM5s8DCsq8; zSR(fV7BFEA#xHSza{v(^Kaa6vQAuvi+u#En?c4%adY2}0QaKr;E)hz z?GD`M{!Q`A@F*v)e0JX@xXV)l4Tep8Ulq}m>XmpF=1$-tYoYwHl+H|C6wn*({nPcc zI`M(UG=1c?mbw23Gq#eVO>0WQ(XjHrrQj}ar#u!TO^iqX`c;IBd}lqygCa97Z|FO; z5OoK7+AG(dfSQ3Kact#1aLx54l3Z+i6}|jnZ7d#sd-kQApHwvP=mun16>wu+hP$vh z`7#*Z((zX=yxgw-S9u-ciNNhC%VN9O7#Ku#NDygz&Y6)X%@*tD_--a>M!yzg*AA|BCsYvY#0KK@F2R*)6t^emsD9ZL`6et})g z5uSAZAqj7JGrx;X&Qu|(XYkY^8+m#nR$H<8c__-fK#l4hHbtZEzvLwLbx&h~*gdUl zJ={*{?i5El5S8N5mB;E_Z>@WZ+h+Pg*o2h+^-dl^Zzu<3}x#_)sLCkeMujASp zvwN;nFYS>F{ldY~1O0rhcg3X<@`kvUL~J%vaw5lA3cuOu{P^KL?hIVMpSWERt6;n$ z$4w<7*b!eF#~Rdg*RC2?=zMS1Ve^B_#NYjc5_si}`y&N_YS)@J=NrvK31&w*mK|C%U0?OLB7XP zKP=D^B{C=YCMP4p+2A!Fb0M`ue9_Cq2c(Erd_eldm?`woQ}hB!g5w?cBJt(#8}LFB=7#T? z0wUtk=eQvEB+0jwK?Lr}&`pB$2TO#O2-X<>g|H(p;SJr=%WiQ zo;zcEh?&m(oEaj`yX{-8s(;2+ul4LcxkD?d>-inK;Y0PL4NSPmJ$Kdo4-F!;{>7X3rYAvJ(jxvQiC@ypZ4aLb^fqz1LgoxLeoNKf(Ti8X^TL&d`bC{*sBEmg?*YacVQ0G zH)7X=6dz_m-w`VrT_obW-%mk4<7`R)Y4cGA9$^b>#Eg;RaMQFdW)>DW=r za1c}r#Uj0vhHm4U`!OpFzbPl}ok5;?gZ8m?{fwQk{px6>n}58~-oTYl*$u{d++USb zAX@ zB&7*;1#dmr_k{;pNQm`MtIvV@-f%^IzGzBrT_AjKA2X{k>wosn_O$ayWyHWwI<2Pn z6#Z0pK2Ucb0YIb7=Z4w?t53AWK5`Sr-t*E!iU*WgV)>Y9>f!f%5uH|DncE$)z|%Fh zMZ4jc(oAK~t8nhwKUF9+MzW2Qby8p_JDn8L#{gbcp3$C=49H;PD`0$~bgh!NPXjJ! zA9?AlC?KW;>-VdikyazmLGaRFK`Kk%`jwFL{^r)0ck}Xj1X1Vmexh==Z@IA$&IvnE zizn?Bj@CaIel>JArxQ;+*b%dXEW6f>HS_Z1dOJ$+f9e+|$t z7bqmIXe3)t#w1|lB@xF`ff6_o-Jag$6uDS}Z9ei(`gK1ob`9lq8KvV>&T?pK6Fj2w zNV6Z5aajhEUaFWtOmo_QMA(iw)l}z;GsbTWk}r3hD9i7x&I|tc-5>VpGqsh%!M%tJ zHXruUJ#_ZhS4Y?B(2Bi(FXY22*zOR--p~H+$w)CDrhUwbO=ZNl*Ww?0(@vk4?}g*B zN?suF1u0v(^PTuT<^~R8aC2XHiC|*j*zZ6s2*`Wc^_Y_wx-!DLkdJ-Z#+3wDe5M82 z`tJ81?>grm(bj3)+Py$2hqu=8MuvZIfA{uovq-(>UKs;-;N9EXBzN>!yf$~ZJRY_@ zQ?TO!Z!>+>``a#+>ewaK4=YZmX9sdGZ@9)MD9;{vXg`+mUnV0u{YAN}AmIZ%W_K0) z*$^<|#BbSd`pj-&#zm{$t?gGE1!OX3_j=wsEIH#CK4NTeu!sf`2)m#>KZg6x#r`C8 zy+@%@^{=AS+^-1yjM6}!!J-lCT;mAm2WOP+^Ag;j;atR!Du@Yww6())d7!AFzDVn{ zHIxLq$(nmZ#l+#e2UaX4iWzkchgJFG>j#t89lqSbNzqlaAI|Ii}~|0^ljlzif^< z*T^KOYY?BU`VL4_YH}W4O6Qw^m+M+L&n&Q2#F1F1{A2}z0R&ONkR0XCBlzMZS>^~y zY5hC7GkdYZ0g50{w~>I-;QaURnw}?f*PV>}nt~5HphcQqn+NaxWW66?Q_sP>o)38J zo^K4SM~t?xdHp08uEe@o!64rdwU)pkBFLNvVTbgHmQs`8&cOvd<)?<=e> zM~8U1VrO{C4W7Vam1dL((pR7b(rk{GvLTuPUIcnRt6_ga^@6c?Z16I*Gb7X>*PQrX z2D4^&@IiJj@3;*&TZX7+lP28B8XPWBPAk1}fj+#^)$VL;O}l52&jozEgF_J>yh(r0 zkrN8r;A-tq9$ckdAYGF3`GvaKUIpF}O+~t@o)9>!kH1kgN(4QL2@FKshtjWvi!hu1 zlR?1$n*q`X(F5oLPy1{)i_WAk6SKqEPOdjg|)`d=t6(?1eKmf*O*v1{7 z)#DR=LEvqawV#*D(Tnb_A$ye8%AQMdovTv3EWuSnL%$S*0=y8ZaZs5PRx7x7x>>ed0=VEwd>cp#C@FRy_=eLK1FHxXx# z&;E5D1()jm8@B9|{T-`6A#E%%qFW-Jx&yzK)-fbxD5&fLZl^`ka2{hrQHC=M;Mr8W%!Vm*>H1Aqz-o$*s=asyF7gr@q`RrlIdTjCzx;KFZH zubAQZb%tkvI|EzRFtk^1wU&;2Io`U5=jdl*fDf^vZWW6$Xa-B5i)U0|O*pgQ?mT1X z2#FSmCaelc*a`A5SMmFgFH@!3F0|1e8SAd=Z9GqJZ=hmFnh~g6tLRCY54Obl;@$qj zow3pj*|vglF>(P)r_0xS2+)e2X-VCo z?{i^&e&%}XfrfS3>Z=aRoo793Lq`& ztLY!7kB`|;(z+Dv5q$RsCl7*Ft6OVLLl(-hD}A#IUT%~Ew$2~%L~I|NX%Qi4 zQ~^6cm{zn;yRUs*d%z4 z?B>;YD*Mau$Y4FidlC^lb|Wy&YfO2aa8w|^>@)e?F3-nBH;yljIkj+OjqGe@D(sKj zCVkMg-M;bXD^Nb+sgPQ?4u(f~q0YqDJYM#p4@VwRUP>$4NM?Tr+eD9SpE0hlh%)A6 zs6)5~3~de=`rfAi6!ar#slqN*IQdkaq(&s2~wI5*;;aqT4& z3_vYO%ZmNw*vpp!4(b;|2tNAz)N{YVJoku_g_}jEoIGAmlnO_Cw4MaSbAUMR4fZkT z>gifbpx1WNBYz%rYagNmvZ*E=Q^b@uJNQ17j67_$cjitP`#CLWeQWDZMee&3kz1GO zF`C})o8JC8^9P5@NsZJLO?+KR%b(MVe-CH&)Ee#Ka@fGyK{BH2Uo2#zku17^`FD-T zA(7Rl1#>=)6qj^$i+GYiDchUqjTjX&0Nt6l=R$WP3odmtBOYfkvwF3H24+7}aT zZ#!J?B%Ne-CG4_msc`_MkC6NN$~#d3sQkWSRw-Zf&sN6+e=OTIzROvYUCZA@kjGUm zyY)kW=T#nB8iewBUwott<&H-pk6x}3SNC^#&Gj;hciKx~Z*{Hbs2no7-?5G42-i1` zN+*XYk%r2-TTWU~)FKA_22-Csl?G&gCYm+oG+-8gpv3AWpAN%e3t{4o%^BaK8QyK= zvdh&2lLC#1bS)(SX(EO*%W!z-j?cmtfZYBO)MpaGb_-cgci{naL_W zo_~ruy^b#|Gw%h-+ozN{{8n7?&!mkw)Lyo^(nf**`{>>h?Wpcq%BSoG>c2g_iB2RF^O+p>7YXSHRHCp1MLrHr2$ z@`huRl9(RFr|=n~((DY@ar7+u=5jyXP%Ep`dJ!Z@BKODr$|*&shFieT@1}VyP!@D~ zoKVzJh(&f!=)k3(e=Ui+5BL>ixbvzN=iTEwv)h%`-^{Z~U{I+pmCkhDMRSeQXJv6_ z_6`p6`y707I{IC&Du*i$z00#F<8_|XF>bb%%w=`>@yG_)k9)%Ex()S}IHLLbeskEE z5T*Njk!j&s2(H|jU)gNvF3J&maW!rqy;BiX8u&j+s*E8-+GZ;~`Qin~f-~*%&;ItM z_Qm=8{=)UpYho>$}7YH8tSLeoZU(+ zQo0oOhIr)+QLKLNVS2O5g6f*kW3~#BP6&z3i7`b-q?zz^bT$Qb#teI;crxGU?_}x5eY(ufguj%Nn}j6C%=l^R8e6=cXM|P$#|ZEwUka7bdxgGs^ya5Y7&`ybv>Bd{fN% z`X$|mc#31U?(e;G=+B>Z7M3f9wmNf?zFKk6q>~>}{4{xy{EIq2)}Cj?9(e_ zm`Vn1@cQ+m%k;rTY1ZOYWv8a{i6wPIdH5?!zu7SPTZ}fJNCY$c>;L)-@E#tw`xA4*7lwiU4c~{fx&tit=%$%jJVGKYt{);; zqV$%)H!jXwL3ZV>BW4Dp;F`rx;b|6k$kGf>pet|7eGcx6+5gQJcZTQt2pD1ohr7+% zoxkWz+4?`7slU0u6CL-#LomK9j{4Z)r+o1Bo#D$~8gtnUmtJiQs(gPkRvVqduC~!X zV47=3TNx!F(1MO+7)nuwg4S?8W8Lr_UBA+A{5AgTO`5&G)g8VAzYYzzn6uSWBn{}k z@g#Ec_-}0JT&hA;0pf`{7*6=-Q_-9{>g|uB&f#GO8(-;16N8Z+z#qR%`^zK&)R>v@ z6^rOvHXno)z6*uq^W&eM;HpYi^dSQmO*Ao(aEUp-cr2seh&!Xnl;R#zpWST#L)VNW z(#8ZSX@S+^M5>q#YP2wUqlXy*XCSHCCEs80vOqI^UL63js^tIb?Uh%&?DN5Te~JD6 zVJwpk2**w{eyz~n?zkQVnNl?PKuYJhU+$sFB7&j3bs$WNy#znzFB^{M@m;yezdCe^ z{M`R(kyN`AqY;IZXOS|Z%nJbcysZm`7{W%d3T&eAGMA&ZKha7{JMP(nqj1@uQ-9go z1J0FZ$KXCS|0GEwoxi>vfj>|r!eSqQ za`$^z;1doxG0-(L^IBj?cC}gz*RCpqWX*qdUEj90UOqNdQtPE*Ma04Jhs4jXV`98Q zYQ-kdUzFc&)Hz)C_t`%M4AL1nJ{(qO)4waQOt6r^>VMyJ*rkgJ_qEIl7mEM%Gyl52 zy`-TL{!uP}eIon_f1db9>f>DC2Ch|K%oVFo6?FK;`h<_+os!-Ezq|XtdYU?ZB>vN@ z-8YZUP?{%6<t}h#!)NS<;}`2bYyiI+gSGepxfRss!0Nw|icYpL(G6GauSaWxS+|es^l0oKe!Fb*T+%tpT7f*zP?j~ z=WrZAc~lXOzdYQx_g`IDe6HOB*8&fg&A=le!TU&0>sn@gItJbOEsq* zaOZC|pU-!{$C#8CSUllz&$ziC1Jk3_@hhQyjK-xI=Jb7I2bqJagG%cvN}V(K9jSIM z)3+*dML;fj^kh&yguCv?DRu6Uj^*_4Qu5xjFNE*Y&V&Du9oaVHru$#VQ~IalS^3Jp zJDz#|*YSi3+y3M(65qwu&O7Ns!mfjY)r|&Pv>t`C`ZfeWlDsTiQc^$?!>5-tC=D|~{kwYodUyXep;-yLFi}B#G%PLW6ejyw-u;-E3dw=wZOP+&JfdRnL z6#xjc=V6&y)0!TkgAM1*hIsl~^8=sRXbH$LGfw#W9#R5bAjQo(|AD492RE&-+a+I^ z`O=kYGK+BLTY2r6$3w|WN@i)p-&-#x+t9n6_4BJaN04%AxwwjL>2QWJw1yD)bWDt| z*075=YF*`7EcZK8W*f#ff0adm59>J|aEJb3&yR#Oj^y?G#ejoZe+hL%u{o+6@}qSW z#$i!P`BiP{X>vHid5~b^cXpRT9YyufQfm`OEohK=d@!GyrycWpR%(8^iJ2?C*eLk) z{qHNdBoB~AcjL`azlArIxNeDh1$)YR>Po{LaMwo|i@=oO{YcQAtNkM{OwlB>a4NaO z4vXE>io6b#I3s(%mkQ1iA};XZhFaLjzy#b+OG1+8gc2n{J9}G#;@nvSZm?b$AtQ`b*z~6VjNeXQPOrIGNUHxJCPm5 zC!84{!zb90fAJgh^gOyRJ-WknbKS>|;Fv8#AGO2>I4fZSG_<)~-~2`tVry=D9I!}l(-2SzFJgMQww>~bf!Mhag+Gj!yk>}eI}2|JFO>T!O)j}&>j zTG!pqx<8{Xg?zgWrJ505?g4JE$UhqwUMd6>_X2TogV`c%_B4G0Aml>hilEd(dmy#q zT&w`zHJM}{c|IP!^Y6+jlNNUKm$*>jJ3hRA(+PMY7rX5%b3vvP_0m1OLjLEibj$nBSfNzL(=={BUNuaoe?Lj zKwWnysH@i6s`lGGNj+Kpk(6YL?Jo5rqW8)fr2N>IQVAD;ba7WsD+KjX)5MWgT3*I& zJi1>PpK&Ur=mI)7v3;9@(h_i@()2h(Kq zOw9{3*9eu3zdXtr9aCIG>4RBmw=wMkz6C~+TB#F;XCw%8iV!qeN|I|2ist%WgjY$w zzY##@)YDgg)Mx&vIhJIt|AplQm)?zeG`1wtr#p1uGYt*~Qw+yexd9MPk(P9BH%dt^ z*qeL;!gtK&Wg_rC>>~=Y^!EKCV17i3ccVY34VpQdruB?x;bgJiD_i*yR$joO%Jc)? z0H90iOY-a)J#TZjujjB|@`85OBFdLNu7YnY$IkJ5+GANmeR5MO*jWT^HmKfs=k&|i zo-g(;o}0?o+G6(4EwKl16=}~rr@RRnZ4O^_tQ2AMeJA?iz7O+`LO1YpWlzkbzs>$B zyAI2Eo9Z^x%z9R@J1$rw>|;*X{Toc+!(6o4nNszq0YPVtZJ0L+fH6u;g0B12o*VAn zN&eWd6>!1RN^*iS0aCzXGX#S9SRdZYc*$>IIKp9WBfaX$pV(h48hujPz^uD{ng?~) z8T0cjVrBJ)x9ZE*EfN^{$%*wzz%}VX?(%HLSCD~q`LH|I&Ou35YAJ~6RV;Y_tx>pu z^em*Zfz82j{WUip_LWznKfzbVlkB7jJP@)yK+!*VPvmla%X&8yMRH4DOvLF{b3b66 zQ=FNd_3QTl9|}5%b1|d5P0y2o&7T7PK2y&{Dp||mJj-?M@=y@xx#{(fA*J|H}7@nY52|a zPSQ=2P+y#UM1YXm5W9D)!ztc6Q_v z<3)mzX8MHTbMhdL)CCFVE{xX#p+!ntYUWVqr$iSY$>f`KeM%lu%0?N>N?5g%{pard zj++6^@)7)k1S%Xn53-cfnnyAY=q+I|4?Oo%jO7A;I#(6QoUX1hVXowhj6jc0ohgR82B=6$umNQp6?AeDp ze5C#$6W;Z%{(#TQW(G_0iBvs?@Su_$zk+rpen3g_8`deOP=)~J&eG?@aw;cAZ9V-x zKcx8$m(a$xEo|Zk>}Ftx%RvPt;tHYZ$KjX#o z;H#i=DOu(Hw8#LrPvkM~UqGvQ+kV=k^;@nQk5^rnK4xB9mkh~jm8)ZaNgKYD(p4tm&hGNQ1O>ez+cPN-N*aP4d~V7)4}f6y8fL8H$ZSL zXY}!(NZ)Y!>fCB$f^y(+n%kI#09wsc!x{WO0`q1G=MV(z82>MC@A_b8ve|{%8xUKg z9|d?7x=^!>)3;VV=>Z&=_??zwy40y|)%)56eJ?H1q(S?=eNAV)N?_w&adOkZO8C9; zg#TG56*7)5OoML(Q@S?WVRqNg4EXPo0{iTS){8NTd(UNH?u>N@-n)9{cc`>bw>@Kr z9Tg(K_gIdJp#nDZOHE4Cn}ZPQJ5dgPQqI=6g#Jd}7|yS?L5$?|1Jr)5HMZa+@Yr9E zgE)l5AqPgbEK{YO~PK<#D{eJxN(P#PR55?;Qm1629{XaVfdXT@iCv#|FnM= zF(d(fI~%nA=c9xatIjY!#r$^(XKjZA8w}nO-S7k;H28Mk44(}*~awF7d_K?pOFHc#Icd7!yygHY&vj%Ww2+>nJ zUWQ_kE|*n1y`KJeJFLxm=!Y6afoRBAw-70W3g70%Zq5@CSrF66}%C{TtXI zvEc3BbLPIfH<5ZtAN4cTQ@3@{X_!0c}GU8Ow^ zMm>)p9f$d}rxzDMqD78z(9oKTOKCq}#RZR{pEyWp$!g_TZgyg;BeURU->_G-`ZPt1 z*YkDWZY^msdu`|PX{{@Ce_j5uBY07DVrBR({^HS@$-bsr9o;K%LqF;Dt?2mNE>imHzLao2^>ZWp$H-%OjUB+gz zADxTTu?3{uY)nbRY9`-BX1$mFdxNQ` zKhFrbEiZM`gil+zV)fJ~Gump_mBYImWSm;Qx~r7=>#{g$=D{6v`sC!R+%1S$xw_8b zT<@WBM5{))gXuWKHSGE8W?V|(h0`!yZ_v5i653S+5EfgI-ROnzRWjT%4I7gpHc1fl zh+xch=-qD`5;C3at^*0jNCc-4kbI?7wPg53gGRg$s@wBGb_gN?-WF?vl-?3ApSdpG zHzH}=WpUHUB5*mSo;88PD>y9s*1@``KI~RET3cKX;*$0sflT-ID@S)xr8l!cVcb<- zaw0nF6KLnUov1M( z_PW2kA#}rlbgcx&Vxv>*8%H5i&w-;a!Oor7bTzz#z?`dv-<#cNrOA6sSkzr^Q+4)^ zj3e3Zbfoi*ZuzodR>`i3M{e^|Y@d&u8}!bSpb#Lm4GJZeo{!7A@@BWXCiw`-y8hd{ z6QM!+;{f1R?2pi&UPDoX0U7Zh25F-aC(BZ>Zm>UJvoE&p1n1bE*f0Z2@b2JR!Ip!{ z_1H$>T!Sp;t%5?sk%Yxd6JYy&9B-)U?O@-kfu1=X zkbnRq+d{l$$Rn_H_0eFWf5FdV<&YX|oyvpX6mokA&TH$w0`*xI&>LK#FQ|sbXv^xe zg6Yq$o<~e$UhNnpv7;Te9??7ELCphoT1pKB9VSo#i=lBq@o_wz!lSih5Nfp-5a=1K zuwGfrrasfHy^3qBf2UpyC%O6tj1RQQb=N7%LQVPgz-t=o14u*b@Bhl9w%F#q%kvj+%xkIM7% zO}B4uc~{uYAwfEodq8oWf#sdqLYt1&ZLr|TtZJ^}SjVbyrp^^4u2zNYknQE>UoBlKNd@&W-9 z{$V~>L(Cp8n3+X}#LnoFI{`zLYFV+o8{Vt3;MGQLt%9Bj8=4OV*n}PN1$i~`o*Vmz zY!L`uxKO0lXKXt#4}XNNSS87sGk8V36cr?}-brFOz6x@T!5xkk>J^OO(+W!_MIum+ z>m{rn$xN)sbfvT#-5P~(ZdKMrMMRwAk+m|;u0txOFts#;=we6mERXkt2n@~fts@Qc zMedg8bM8b9B_bIy>!>;=feX1xB1+$>W{M2@QwU7!KRmT2hDaaSO=~O?uIYVop36Ch zmM?*PODAX>)v}`lzjd*g@Q5r}dOprWlbMO&!=kyU!c@MB5C{$XBc}=R2F$%gT=^@e zkceQOnW;$y*r(shqq|d|!s z*^DaDpGA7P9V+DbuIa{mbLn`SN-YpG6*;_M?-rP8D#cn~oL{zp(4nUZ+Be~7%`G`; zC=!1#9QSLi(!mFTaSJZzx4%HKRDSXZ*aUqI`7PBr_4>gj)fv{E+DZ;-uq;brhykZu zMF|g(`%Pl)vPG5wc)AAZXyFEL@MMo~HFAyX02I^qrsUia*q1BvX8D!l9v(I_>rEZB z{mT<`tU=TBTL|#>0@-+`VBYBEC`Gr~a>n{Kdt1U9ZBoxD4KAn6@exws+(ZAcM$miC z$`3LkFcm)Ma^+;#ZMuIMAc0D6w74Guu{-pHIBWLGqRS-^@_VwByTNjg4dTCDOE4(W zD7~`S1XxGR98tc%vQ??xuDcfs04cM@2{`%SGl4%--bBTF=vSHZRlQ@DqJ-6AVn(MS z-XW>M%La1`jKj{{Awo_QlfkypNVyE@`C#_yq2f;IGe8^{;n1N+-z>pv4Rfs@gZebV94 z)gQMyP;jCy2vheT=pjHmlTqEd$-QDBmtBZ+CSfQuNG0c4(_GxqUtlL#Epn~T^l7!; zgP)FiGD)R32t;#Gs7zrPfb*Z5@BZaLjt0`7k^wql?|ZwmkDl<}#8`MVLb$>}ld4*4 z2k8x3u$Xh`MNp^Ew0jYe16%qwxQD?L!9#wnMYV~KrNtkc+Nx5)YXAu@7r9%rjfGt4 zX6GsVHfC;yTNm@Lu@?r?m+AB9Ay`&i=1a&9AIaK~{I-Jo_nbf@r$xwaf%$eWwqR1N z@|F}%dqj~S&hz1A!p5nkc>oZ*eH?7YSwwOFu2QCI;ev`u(~jO0-ne?*-LV7>h{Q%%=X#4nzYPfkvC7z$WlF)q}Pf!wXtL;wm1Xu z4GqmrUBd}Z$w24^281vzFT9&p-Eg8C?9y{_>_nu<(>p-4HusmAiY?2znaLCIhg?h4 znni%YDR(uW9cS}x(gSBFMZ<1em&6mY0{W#BwVjHGbF&g-Pk_EmWah1Op@&EX5^g&f z)=|An`8q-dePjYhXR!vIZE%+z5Hp5Lw=iLBInqJAmI%p>ZZzjP&&y#^>WBK$%MG(4 zrFG`QMQ04*MWK?OxX++BR|U;jNVk3*=a;$ta&bh7F|FR$1S8hXkrmq3SRw&Jeaj{ad{UZ zxKsE|D=Vu}?>t8{g|b6YGY_F>#!nz%`Mkhu?y!<8j3so-TYn>~#5NZQoin$nw8K>4 zZQ^myTSS9$VrM<8RF`tFwTLFSaBOGq4<1RiBO=b*81Ts6+Z*^800nM$$Y^&J$ftXm z?5Vj2yZUCT&wvbz{6A&ijHQ0*Q5iJSO>%wj_TaAz+^s^dR&9aeVs1?79+Dk{L}}#c zmSA;l9zevrQLvRSNW#o6lg6=1v6^L58uDDdFaAxTW;8L+g#UL8{-#<%ZZ9W*eg#ZuI;{TmXu4Ew6_|b(nQ! zA~^55wbI&We@L3E^?~!RxfomE)WXh zymka*zN@e^9B`szzT2XvwlAXV+wo-pT>HU6WzJvG!1-JR3VucLuv8>DJHV(ONavBJ z*wr-GGx7CxrX9mmJL15By?vpRMk*|(Ag(8dU2eEliJ$ts@OW)xJ~9@C!ZM`D@&h6EW|`F>xWLcP_{Q@sj#qM{K8kY#i8ZL; z+kM|?D?0b6vU$V)SB-bjlI?n~QIx9C%j<_<+=Qhf_p@l1$WvOV4dkjUT8+m%5M{}i zq3+*=CEGj$%FWQ?;X3trmyL)1G8gs%rRCywpAo2H^0KQQ_2Nn-LtWly+iOE6q=tU_ za|`Y8EsuAWc&lBM)MEkIA^N1Xm;EKM{ly(&nDAmrW8=!mBp}96L$hVCAv}VHdRUze zYMl9@fn8m4fID0wPPh|$-&@MM@Pri->5I%!Qr=M8kZkWE1x`}gEurenA)WN7>vYf# zx?7!t=(ZtD@uFA9%?*L85-Q~eqF_Y?LflOaK_Tc{xeBE9Xt_nMFW#TcaAh!kf_CJ? zR!L@Y*5pWyHg2SU227pgkhdb*^n-sQgoJVLoLyZ*?Ktr7V&g`!Pj14aDr;Btn^wa%@_6&n~GRgp5Zy?^_CP5H#-<==rAr{w^aD&Tm1eCLO zIq4K#%4@5O!2TgMl%}8qRQY3O~ztlz(sz z=I)M7)Mb}#B_AvUavf!GR{~pZL6Md8FPaPU_gO)OqUcN%4J8sqVWL=Xk`q>Mldf}T zv0yTyW4c?w3J{_6nvM^eG0QXCImg9ZI=kB{Fl@;}{9N$WOJcY1s)fmzUJX3d`J=fycY6#=A47lB!`U2RdL@Yi#3!?>Gd zO9NK4ODJ9704SC8vvMPkj(a4w23Rk}dj7(o)xdP`iSIzoa*@&7cAFqb)+u7cpX@eN8T1BN>{_&K$hZR7C~f$ZIw=wvJ0J&;QFwbvjlNw zU)RUle)nD}X1tkTLkLFyUIM<%%v8s&C7jT4fLBbxu@V z_U6OqYhlffXL(sFF5B$Ki%`8l^8&j-B40NnJ64V&&UioMh7p^IwPEhkjS;;sk}f3Y zn{0rCsAw&#U!jXPn$4=d$<6IFSVKEdQSE|ZuKSm~?TR^v0Z%H91rTktEJjbckWHz$ zV{ilOO5j(w{hHZHn4^ww_VVh^GhzOCs2Q?E#lzbVQcv3+*Yy2{i-Ogq7`WJx5BwWk z+sgd9>7K3&{~OoeYXMuloiV}}0H^F#wxCjywX_gn#%hT5t6q=<&GE*uh2`O{;<#Qn zn~L)_mAmUeI6f9<0o>)1+*`=o*=T3Dgl*&Q7+Wc+Z0o>>HBY&Y4i4-U`sOYpE227# zEd_x9+p6v{m$)T^ecma{z@2TGW`D(aSwGH>omZ>waNIQq6B=~oY(#W}{>uzfF4@&^ z6M4z@s_NN`W^Lq8T(I>u_XtLQoth|@tLK%u2B>K;ytkhR>0o>2eS@v3uvd&$A(rYy zR;mXel*E^A#QI?da)cP3cwoL^k$UId`hv0qfIZ#F6pmyVBZfRfUgl43gG$W-`K9__m=dDL}JyY~?7S;WqaB8nL-!ZnsagB~J-bhFFgbqI=mng{wR1WV*l2;!5l zjMBIs*2J1P6=1i-M^w41R(;5*RRBl?7W}G)2uOZ_3sQhj=&p}@4Vrw{aL~{$Thu#3 z-kG#@$gs>z@DoQku%qIto~H4Oej_l2qdc9z^FHHAtR(^6EQg%*E{1LdkOrf}gUglW zVs*VANCn>7M1|*AkTSv98Y|3@&pTqz)^wr6FP$ZmKXFTC1pJB7xBkSSxjXD8FR$Zr zMwTHBKv4sCJ9)NQgjpA4kAAPSWduZ6B0Ax=lwpUr#+8@#^9!Fi1hCoj9_$!$Q>62g zsJtmqUb0=KyI%a-UgsQ7fy8<2u?K5t+G6&Nr7dEnn?1G;GR-4y1^!Zq0FA;7&V(2~ z!p*fj?4|%>)MPBB2VWoAK;s)Rs`;rtG;_IiXuIMa|2BAYkI&0|8S@D6BzEIHlK{q@ z@eV%F&z0GB<7` zBBDp8T->Vz!X;-Q&6YO+0yzkHh^OyDKj%FfxHzy`z)}u`+jL3BM* z=hO#GAM_W)uoF3%73-UCcZVf5@X5Y^3Y(`_EEBnhnn`qU^1O?oRlL6{1Hy#lj6h8x zF9}7YAYYd_ckr~=a7VArHJg|E*^e3msLg>9ExJU6+_Ppi-{E5}x*4{_3Is81j>?bDQ`c2kjgN~gEYiQe!I$l3HjuFaO0&+WQC%CH~_UM}rchP8Er;thbi zk&F6v2pf%Qsq={Wb1P@!01>gAAT*h#<4z+$ z7248EpgE6ZEZD$<-z&pzNmUNR&1vj4@77n48|(hMpK44Igbtb`RTY3xtbdmrMbpBjKR2|>z*NTzTOpLBoSkfJc$!L#~sAFihq3v`*f3IzqUaSa|k#Fgay@!=kYrw zSEZ9IMQ^4OViOY&t&!hPpey z*kMyK35J&Ac3$g+zpbHDgR7$29_Ows9l)A>mzgM@#QE{OTJ>UOxjK)JN4C(4%^Ofl zIO2#sRK2Z7qRyydu*_n70)?n1N<%*H5b=pChC^=5ygffA+xV?_s(|4vpO>sUao-?w z(dN8?T+lc8r${`)CuzDTD015FdviSW8?<5kYpQLuix@1p~o4 z$wj#DfWh=uq#(Xfc%_yPpu0EbO_f<5_K&tQIjdUqbT_-8Mzk_=Mr+DDLNss*kbIzp=1KMwH%UKlUE(1BYxCggu5qki+moy`>%%;~&TehJ?z#<6#@R2fI zEKiz_c0m#eh7-}l)K-3s#gjD&TCGWg!t)M-SGP&Gn{y$Iv4}};Z;1{y&Jc1cU3)k9 zmKqc1wGTg;}XDq{|3g zaq9E%8eqJ(ZWTpG{M2NOo zgI+wGV(V(J9p9LjxL%sA9&m-rd295e|FF+y8-VLT% zG>|qbVS*bMLYppmPO*i5tf}|qnQnH(d3~umbipc!V|)a&m?B+Y3`6H2hUIjzD?{kmMg#Y9*G8ONWQ-sTzDd{q{%Em8LmjNFB;K}RbHOO$S_E?1R$P>$f-Kmkx1ZP>x)}&K}UsC?6PtYGLHEE7kgn;(Y3W85*Y0=_W`|n2pbpxagk(0;xm&?$l?r8sjM^*UD!U78~fNxJOai0cEoo5A2K?H%3CQw!MLx(k*I9NP5Jm(a4pN9nP7{?N~p^ z=M=F+Z3Q8F5UO3@^8SIc@k1ni{>F2?3&|GxX-J=E%weS7z2q{w-Q2*8HTSO_3w7$n z%_-JEx;?4o z3pWv%xbwLVjo$qfkpjMc&%dPGh$O9Jd7$PK+ZbJfTr*Ga>kO${6|&?AAKS^}A|OOx zX9V=KB>~G9X}`u&Az4*ZK8Uf+hSWoAj0B&NO0g2He&W5RBB?!1OY!0D^QbrvR#fSz zhaG@hwlo@9-1FSp6bnkubQ^f3hw(thGpufALm5bY)7Ym&v%Jj-ETi9{KjY4QyF#l z+5e3^-Qoy7#ElPs&%^pd|MTUwpc?x9`#Gq_?mc-VKWF8t`h|!y1bKYtokYIw;r170 z;v$0eyYD*X_Wsbzj6BplJN@un{2AWQpZZaMFVpoWe$MP1p7566WCf?8^CPeKNqOM~ zzxVl0o>UV^hU0F2L%kL?@oUA1F4QVgXm4snKW!Irn4eyqk1edddTrs?nlf5s8wtJd zTFH&)sKc7*RPm8>?j9o<_Z?t@G$0U%ZQGL4#x@eP&o77rTFsM}FeliBxz}8E1pkn|X=7 zcBu#q912_1V;v2WoZD&(zXUTC`(4!QnjSuE_I4HtRc>KFp3*{=4U__Jq?zqrK!cfk zg(TK&zwrwX{&NfY8QtsZH`~ShvAgdkA2$*1Rh3AbY6uQkV=6-?pGVQa_F99T^-U!t zM{K*74puX4=ddDO76Lew{`yM{k=<}au0H55ke8i$8<|o)DbX~!Pkx^x{7Wp zLg&giy5r{}1Pkue;=O&=!|?7=EjmyLRRkN&SrusqVq|%JNg?TJgc?jN0n}6xP?_CS z6jO!t%tJq_0~;-o{e%ht?XJHLBD^;BHEmFHL!oAWKjl;D@=c@i`v8jP?DJg%t8<7h z&SW7J<>v$I++t!}V|Tg)v9f~2UPetD2ero~@^qE;L*9!4Lqd%YHU!!(qT0=1GK3~v z57q9SM0xl)MT3J?&w{? zfGAxH8#=kiv0@N8@>Ev~#psYtK%)uuSk5US+aX$+FV|D5{SuT~;!!0hPJsO|JRno=t}gJw7+3BSJ^^RWUN7g-8214z{g5k7*AaniAm4-)6cO*E^d#W> zubr2vP}~u~B~TiYsI?lFK5@{PJ#Xr%g+4%H5yFHuv}B?)efMexduy4<;eWWTTn+S9 zeBr8IKRGfMfeT!@2HdM)R8(g+@|Je5L9cYfdtlMS_y=5As1?E6dIPjCu^i}!@-c>j z1)LJRP(7gscRK+h)j@)4uDA%%17NNAf8hdw;ZGpw2r7v% zx}d%oZfh7~A@F8JoPKhAmnfYVmKBy zq!M2m=Z%8W0+{oCjJ7&IF=yw9?b(h>K30Re9%Oq8mz>5z+kc)F-?h}^a$?QmW`&1; z!Lhm+UdCMk69o_L32xJFaY`L%dBI(TXzD3x5=n~l=XiRn=t+W{2aqs^wi8Jb09uQ| z1O7MXh4}tr^c%@HGBONR6wXfzM_* zSi)`yfR;nt@Yj8UAys=|u0pu0TU;+g*G?P|8;aDO?~-r&Ty#LA?wI`e+HH}nm}j>1 zzU;BCM6@(mEaBj2>6sHRsL67^2>sT;+x3lCskGTHCF;=9y>?k^2t4qRW%#B%jFr_3 zJP*2Z>YM0PXG9t=?a`YFCnJ|dj_f7EK%$k+LhA~n6__9K8DrNL*VAkUJP2Xr2*<(o z*RbgW=e2gh_^r=jM0Ws5vm)c+;HFRegpvy2L4G5|bi5=PgonyEcmwtIOP`nU1<_>| zk{njiB$7d)f8$luB(67ANf+TX_8Zf6^ugbpFg19J2T}hp)vyN{6j?EX+GVaKsQMwa z2Zim*xp@EUQ*VJVP>9=z% zP&>hxGb7Atpm_Qw3w^-@OrUalz97JFAYi^>Rm|5E$~7RwfYkyP19+v-46`m0$FAya z%&<(#F8flGSheTV9)0|FnPoJI9k;fP?^0yeSg%+)CoRxgm1IQhEay4o`x5vVVXi*< z8RlQ8`7sUFMp@J_MJHUio>Q3bi13Zzg}WS%HblrLvnpj$B2dx?Bk0cHYAK%S5P&xQ z#7W8V`dA)&@~g(|%4gXCX$14Y-SZ}l7A;E;-wp!Zr8P?C283!H9d$7eTkEY{?;Qz6 zjWuQ@iISqukedMqWTSAo*^3Boska~3ya!LQw>mPo20aQ)9u1Xg60(}<+VR5AYZeHZ z@`Ath_D-bY#bxR}SE!4-hv+j&tUonL1MSOcqT%&KP@rB9;{tz8@pkZp!wTwAM;g$0NkE9k3~!zWea0ElcMzYwtA^m9xSqLf- zy4E?EpUx1I%Tr$kK-+qguIEP^UN{Z|4H8am1n8Vj^W0%VKX+KYYt&p7*OH?>j)+1v zk-t4Ul#Fu?JQvQzVOrO%8cTg5Yjm5T7f|o-!^)U zM|Obc$uY6tIuhdorbd#=nh}GdC)!hy_Q89aJ9!DKm7(_=Wr@>U<6h{TDQmd_;{EiB0cyvD1_v{gbEn)I# zbB?=mZfEI^({T)F%z?^kz39Co%yeYXkf8}V+<4rYS^sFtx45ZRgiO-6DG~@Hy9n@6 zke9O=G>yExx#Pvgqnr2;?7W5M9KD;R7^&bnji{UE%G21OLx-Bp)F3N9a)oXsmg_#W z`iM~w;uH2a$Nu5TKl1PyLl$wRZ1m;ud=(FSGesh=;FWw(bzOD(X1SO_MJ%fRihXUt z;W&)i;to{~q!KO!XX6#e_;xu*%@XXd*JZz3#-Fa33)hjQ|_q) z)wGYtJUC9UcParBMS3hWR|TTIuSsdB29)x&NEjtbXjqqdq6B&(=2Q$?U@2c7$LMi` z?{T@p-p)x!<=)3Tck|4dh9G#w2S2#%zrK**xvV zEsoJ`x8BBFxHvic9$&kcF|>@b<+su`z!q-ukqy({X`qQRo4uyBJr?~TxCn|T@6!eD zWzkfM$0gGxA3jUy&hQ0ivrvN+0X%3Qc{rDLAV22(1UE7=LJ!$_@jfzwvv(&kh+AXx z01XB92MVm;`38Xf!v;4be2%Ipa#vZ3uIz?Im3D=5bLjTn8qUz?7-C%GN$l8KjL+No zq)#Pli;c9GtS_upi5i&#Ron3z+nY@Uo%>1|d06j2oE2SV0m-kz)a0~m?0st!Pirq| z&rLp)qKbnStLzXdA~x$ny5bvKHS+?12lEu6HsVu|wk&${yv8Elff4mMuAp`dmS@a| z#PeiVw`*I&BP}Hv&`a{cR94)6agTR?%0tV+xX{ZJp>6mc%9-l4m&Sz!$U|1TDSFj{ z+=|PW?@W2$H@il3y*VhWM2aF7dfRO;^reMroAGg-%#zb<5xHdMzfEwkn!}cC z1T3A24liK%u#n764lB-wb3HZ@+$NOxu!RHvsz4~8V;lyouo$ptM9yLUB>kIKV{Cvd z`GVYFfP9iQA`+J$8LHHNwVb$pdYG+|Q!9}X1Mb~sApxPO^PCj=d+ZDKE?|AubyHjn z<%7dAbjojCax>&A79FR}=F^^p^z%q|bM~@4$F$=`Ba8!G{nA3x$xry1|I`nhrv7pK352(lDSj;m5@)m z^_lss3oG*7ANO+;o-OQF#-Q0~x?7|2L$)lA&7kQ!8++fup5AM^=bYMV*Q8V<#Y;ck z$f&(vcm8u-^&A&W`=AX8Ru%1Hg{0*a<|%qO(YD(oXLfg3-X{-Sa>U{rn_C8vfvk}8 zf)X+CnKgiBc#Q=|<}+Q$7)}ghYA8RK*aD;cVPJ1&uIs%IgQwpfYmE-KkQ)P(>-@T0-*b<`CQljdja z)In<(POmNE>O09NaRJned|9(&qw++v;=1~H4oKP);N$|HM9&_yhYRBoN2`z)u$5&XwHEPC*xq> z6;QvVN}aJKXd0`>ZFa3+c2E%*y zuh(@?^{zl@Z=T&6GOou>zcW|Jxip>TEL#*DI1x*&NSeFJR*hk~1$W0CI~hsE8&&Xc zSYfjI6KffrASQlL0M%PtV2=_N@GUAC3THOt;4+etg=~%MJI+V6UOw_l<#Tv7oc(*c z&Zc=9stIw0`eM4kwDf8*dZRwVh`p6#OS)gB=*y0kXeg~W$57&6IpBMWD6JS!RQGsQ zdX>L<1{;8uyIj6c$xt4#}xwqo?WTXVdF4g9w9*x13;|^5)OJc ztQmM1FNie(jtUGDKc+DJ1-s0t1Vl$-!*m0cXS-Rzh7L{T$M&E{Y3F=Bz&n8(OTWIs z<6L9i4|0c-6Y4H4U)tr0hIr-8RoHQX;`fJx&0|u+F2$QC*z>UobW=-H;Up%wpF?Oi z)AKpwu7-goFv+C=IpeXFqit0zp~Pt|DC)R(g_0i*Xf_3nhlqM#A5-HbmAV#O<)u{R zU_~5WHs*XVbM&kaa_+NRfCH8R&qYI)L0c33Gg`V81o(!&FCTeFF7QvvUaU!TAFdgMfvB4dS6$3b6{- z@`%C}pBDDg)7~4owR6-LlEXW~>S}z;Sh?`M7`*7T55wgN0ky!0>Q&kzH4Gqr#B;Vf zZp{v*@FZCd1>#!H(EnCk7%6F03T*(Rd=KaT#K)cPMPOz`B+{L+x8)!=NB#YT;bqEd z7Z2TTwFJ#L^6EGBu%~+E4*NK6#*wHNqHUNGnD5w^L7G0Ie;H&1wHpwMkzFbo1%+wy zo!@ptMO^8?nzRek*m{8e9C%#RK(OAx+55=+oVGJVz#G#>8_qJ|?vV7(`tSP%L*URs z>Z5I5ubXPW^FoM}irAN>C=AVkNzaZ}vCkH;hE=YhKm0;#pun;cYx{~7xj<6^NuM%4 z7PMElgVmf=G5|Z%yxgX}E7r4*6KdA&tsPO7LE;3i(f<0_p{qEg2E#^YSUayZSFwx zZGvfEGDm&pCU?w!k?bHNp!!$m0A)-MZOl##5(G333VsIJBPI5VO4*)dAqS$JCK2h4 z%{wD)UeN23@icrSSQi5A#2_MetyiVhrPqrZ#3CcL+T*f!5K#G;VKIp{1?m(I_P&b+ zAGQj{@Ae4>_955uEv7m!5&ULi7Xvoo!nG&TEGQK-(ref$XBizZAa<5hE8v55jBq;= znoTUduQcEbx4b+d2)*^lwM1I8MOvRwz<)sj<7uwt)l=dm>@3F&@?mxvav?m*nMJkh-v32mqPseg9SH%Ns!Nn0+~jlt`JXP+zq*47c?Wc1;SoEmz*4KI$&h zMamjr=F$myM?Ik$v8V}PK*fDg*{_}?8&iC4$+(Kh+`(KAC=k9tGDnf9#%_FwMCGFF zr@Gj~&-`7CW4*`h#CgC+`cZ~(*Qy1A|RSSc2L7!xl5B3I-8Ei$s zAr@qV5cVR=fr5dtzBuo(hs5dtHz4#0xS~DM<2{j-d(@#a=>eriyCx6-d)?1bXA*Ec zkthj%w$h~Ho<6_sd-!xd_w7(MGd2=(8Xq()nNw}yf;IbcjirjxgaZ zG3NGOSDja}eM8h+eG{;j^Z0SmqEHO|7ANgyEY_&DXOUPZKfx)b!J6(1-$}z8^h^`q zaSZI#)E=baOV#3t^FA@I$5V@csZd12UYtQG@3ya;`FpwtPN<(UQ69%VX+y7&OkBxX zH<(WgNbubT`+a1fNr+z^?|5%Mg$}Bo>eYRcpum8y4R#sSJqp&2#0*f$JW}t3y#CI{`}N)Cz1p zsHmX!gI(g=6fH`@eehmm49p*I^icUF9LK0F1FA!SH9{SV)Mkt&Hss@CM(HMEJxAoJ zQYd*HFzu8yLF!p{a}KDJ04RsbPHR1xb30Ds5c zhDbY1Cr@)KPbk3%8PtWq?hOU!Xn9b4ABQTfyEv{#+xPhb2M2`W&{ug!L z<9;F!(_Zc3wpZ{3>7g;lc*DEUnOt65tjI8LNPxfX`1CgQVMh~%26EV2&r@0~SFHxR zIDi^t&Rx{?v@iUaALc!@1ZX3yP|M>5xq<5(dnzeX2M(WEXHd2)DC|!KyWFPu^0PZu zgeZz5O_fQkGG?*E$A*y<{ArIr?HjXqr|d~s8&6&|jUUtoOJ39*#}MJhGL6#I8ucvi zhK}PB0wuFl-UbiA3rvn^B*E8!T_d8#xT)Wc1F>HR_lhiV;7=U$i^of0 zsGXM-b_~bP(LS#iPE#+EV+9OVBo@VbPE64#QwGm)p=(J10}T>}v-N#@uTqC;Q_4Dh5T}0bGh3hSwq9oXxNwYOtO)4fNZ6mhrJ{B6jd~m_;V|`tslB6bMD(~W<-|hx=+R96 zCI>vW7RIb#hvgdOKivpxk0-mBda#Ea%KvA{`_b5}OBTBT z^iEgkS!`A}vPSzG-m7Jea=o*nUE0N3yWNOWd%=4NV2`?p*~0O_A(Nu1U5JZ$2aE@Q zfd3@S=di;R59*X5gX8th^@JWFK9~(PcBk!yro_VX^19Kk3`yvsJ4>LcR3!F8GOuBn zysD}YqcRNcF_y{=QVi@C>y5zEPo$#X^0T67023gUAkRn04WNfX`VHz=`7#@)mLsph z){IP6k{533wQ{o#+BdW}rhUs)>+OW|eT%GE5bvNZM*ai5SiNrKYp?;50cehPd&!?* zT!(==t?#ACLtO(}9V8eXiW4qV)aMVU)wKWl=y%+46qbwPu_mNYUst(52M)tUInBf0B0U^!2ywsq3?qrkU}sn`J~s{)3sZjTP68(-?pbTvdrsb%vo;k0 z?^9iSI!`1(w;XlAbtoS$0J|WY0Xw#A6m-Bt=oE#)rfmriyBUBIkN`3DEz<=3Rcw8t z9U8ras82QajVTkx40GB8!4=Ep98l*;?ts-B?LnhXfHS7j?rA?JD4`{SR2QecGL?IP zy%T~d%VcVy3m7^L%!|6R5cPEMr!fPquFYyW&B2a#-a&n~nK$Z7SV4#MykbM|qF9{1 zxT)!Ueq*g8AF6|j6$j;E`Q>yq#(El=4H&>2>4KiyI8fmVc3iZc`?x{%r=(&7)d~~= z^%37w+hQJt?|Hs9CG7vNPYR^_saZGVzWVeH@ix48@ZoetbW`CU%MJ*JYO_=|EUhIjQtEgoJ_{!aI{3wF}m>-OJf z!9e3U7C+JRrFhHL>YHo~WH?|bp7B}>!E7@0*A#QZ426^H;k4%$_HOr^pa19o{=fRO zkN}UU|@_z8gF!>+xSn|)NU;d}*m;WBW{OUjX`ita$#vlH1^1tBM zfAoXr$A29E)%aie?bq?&{D)tE5&tdx;cw&r{|5g5ck%y!^S57r_19lbT{QLY{8y9L zU+@1?6aO;#ukkAJm&$+pfBc=F#b3m~ihq&(zkh;9{wV&-jpzR8rIP;@Pj!Fzg456c zm($PxBKgyAe(2*hzTE$;@xmYf@PGEN|Kx|i`fGleWxuP3BK-QRzv91w@ayUI{sTM@ zuV?=K&mZFZ*Ncz%?$bB>%H3WlmB{w&V~}?EB{nvuliGm$K3o= z6^3}0TYviUOOO<YDh>Yoa_&-~{< z|Fi#P+(qAh_>Vt-|LH&f(=U?d5BBl@_~QWo-~)g2z+dnYadUt75vM=@;3Izg(=U>L z{0IAp@xQ`y2|JA?q^H2ES^uAT&O_S0W^shf)3Y7Jh-(`2Hbm*1a(M@ngg1 z$3B0ZUww0x|NlqoFFsP=-95Paev$lB-2XpaCjIbYj{mLr-%dtcjLCn9U#8_vg5U9j z|J`>32bNqP%cURBiOGM2=l$MVE1Z7#OXZ(``n%t*)&9vhuY+6TzrsT7$G1lE-+cE_ z@=x%`-+ul567rwo?_d4(;87KsJNzziYxnEqfBW?PA~X5F{@%}ihGprW;Qncq<4??|Sszya-q&CKwZ{{91af*^>;Dw~=x2}X{BT0O0mQdy6|SEz z@#=D)&F0w=f89C=tHkfiE|zV`VP~_0bz0xHCleb~Dqz--Z_ahwI(6Pgro2t|K!q~% zbG`5wZd8*?qn*3Ei&7@o%z`?|^$(w`A{fCLNWfV4^7PsZ3x;<~!=L0BzZmv$^D=~> z!27?_Rkk`_Ph5Tgz~1UFyhEWHCc`PNVJm8Cs2ZZ@%D_<^_5AlL1I^A6mkLTj{ zWCPW`N=y|sbzRnV&0a-DV3874i&ZqdXfL3z_PiO2)7##y-U9;;?RpjK{e5?|kN4+k z;Z=z|9ta~msG6g3JdM`NSarN6peiYDj1pa$acLo`WZ=s-5}UWc?)uqozM4-WoFDvm z9&%_XXFquuRLcH!QGW0|{LKEmSe!18-H-pfn*00l$4}f8_G-WW@zdhn{G`2q_|DUx z_eFf%oqzm_u7t28vP>-9D8XUFA7T#8t- ztd&CM7Bg)ddG3G`a2p-Zh!tIKg*#X%QwwwsiJy7pxNpAoM$N>sh2V{I;D}k#8IYnfE_(aR9Q2zJfZ;-UZ6NPjrJw)i* z0mDTJ2&FppKoAnVI?Fqmcr7FsQ*C*T!dPx4vK&Nx9?H^uB)RS=ccRF$Hd=PisW21< zTckvvPCYsG3L*C(C21r{4aO~$BL-R6KVAj;kdy66*r&zpJn7LP@rRQi@;*rS0SYL~ zBQKVv7lmDmx+S?OEt1-!z|Zd>n1-gPlLX5Ad=|IGCF8>cp$!@E#zaWOuQLJ&a>_MF z5&<=0yd}B0S0ZJX=0#WsW`botrdBm!n5M~YPk=M8jg@Se9T|pAQ$u$f;7BhtR3=ZW zvx_>8u%0BZ%MIi&3}S2!&m=-Et9-ew$H?Jf=zDgF6X{R7N-v{nhVdVyOj`8p6dztQ zle7ZWf#Vv@^C&ruq_A>$2MYN@)ePi)fcj*wwO(}F-fBstvm_|P`*T*y4(4!@#kdYIAr$zs_pn8xVDSOjW$N6p^MF*s|3iwLgi*hX5Sjk-y;4-oqwDBhwp z4nG5O6Q7VTY&m$ClX&hPJd^r760Em}`Ej;@`btYkjHEOdA#lc%gq2So^8mIHQR3l6 z1jY&%LKNewf(ICqY04w$+PVUYA%p#6gWyt>N^Rg;h-{RrVcnzl$k*=AGKpkAyfG)q zb&OD?^<#eXjQj;%Z&|g4vXIs(jh0!`fm7Wx48!8S-vH%lyahp6l(-#3DJfsa_}gQd zPI5p7;Sx#;L~nrBa#um3X-^-Y*hAa?kgA(HyYof@NdxSZlB;!?w{K7s)f2Wf$EB2= zu2&%I2((w_W%@C;omI{A%KIGA@btRias6Zx8P-ux;_HfQ^r=K>r(tRE#1Z%Q%Y5xI zHtf_vEB762IlhdE%?2g>&Y{J-TdDZ|jG947n78-W=W%JjbRcgX6xc7g*_n`}nTpn8 zvrUWL`D6U>$mw|ZQ`GMTwsB{3Lg9M1-UT%pk}D&U=D5D7RV-OEZ zq1fLt&MC^WTHzMxma`2Yp8gHP8Dg>#HSJkA9$wU4S&&^Q)zHQntaU*M>^c;_3@5zb za2v8>0ax%T6PBMpak5KFjF9aD!V5~78J~a8oZFQ!pg`w_HX_-QfyF`-`%n~;EgFbP za(%!uME`%py~mc~+P1a(Kome8iWoU0KnRel2^r+QfBM_WT$vgB{(s@t?upj+S!?gi z2tsDgF~{ir>sZg?1FjCDq}iQFVKPH)Et>iDxkt!|aZiCUYapu`md^oB>0KBcKOe*> zVSFx*rw@w>4fyTQ-h&nJeW@%wC--n7@mO8^=Q@iSKTg)Gtqr9KvhD0(Q~dXwC>@6^ z4FEv2^>%pz2begxwntA-xPm0}A@ZAkdi&o&$!aBi<)0fz&|l`o+*G`N5$)HJkL7fO z4tvdi?LK8~W{wZ1!LuVzdnm8*c0<00w)ZFg<~Fx5Hyks#`1Dt_rb0~%{SVN&G87K$ zHQCuKI{)vZEy#ZE`tbx?hYS@9_x=oF7>H|YfTW@_Ran=21U!x8_Pfsa7!bf$bARB5 z99z2^u*bRQCmzam!n#2y4HiBdK8r?$>xBve_{k^-S1GqM1fyCKMe76` z4g-eG0M%}S>(C2U4X=-GU@N+X81VQ$lt$8-N+6a4QUl`&8Z*9cd>>l(E^~aO5u8f% z<@e*!D3@?u7r;++-EKaHP#T2WUk*G8<7YgpBxX3BHLkJ^oqFq4#(QRp;^M#S3obVH z!~1isJqitJ@;hjH0YLo93&iiJ84L>u2Q{<$ z#g4HW;L<<{*EhLSAczg`;u=h>B;YlBfq5q%_Q=L*_1`P#zyCB^+f~wk|NiTrj`i>7 z=)a%(>jB8r!>>Bx=O1-=1@pn*&&S{Yj9$O@*Pnmzk$yhu|5=K?=JNktTGlV1iAF7! z^}URmdAm-J9;|V8!PC;hiRVD#t`j_^TE!&ZTH5ANwG-61owm*d$jo>+zFPG6_OF?x!w$0+H*d{Oac@LGzcKyLN`nIj_R`!|4> zT@sUK1bH-l60^eH_-ijZFBcT)dtX@BdcHD_50mc;o|RVBl@C;Ak=_(Nv&Hh+YqG@j zXPAv07;-B(X)KMaxC08WeQpX;rC+!9yq)^vM2vOgW=ePTdtRR=oObN4@q~}Jhl!HgO7t$qYk3Ss_>K>-P^Ggg37zQnO7OS%uC*#(mGzT*TO1u@ZT zGO?#;Eh0LBQp2r_xT(8pi&%khWB85G- zYTL>ouN}W$R-fCvcB##(0l4_>NuN?!Q!Gi@6rf$hwc@VlK@RAeOpGd&C#UfMBKWl^mrJ67?5d&DkFrgHqIQ7r(MZiii z*BsPDUu_T4;vEET1h+jvAn9_bQOkZB7=RH?jafGmf8b1Df=UUBXjw$Y!mbIKeWy^j zM;fTL}Sg}uG5#;cuzi2evg$Px*!1}ZouYaP)Gn@?qh4!b1fe$#=_V#@Su*%GsC zl~7eyNbfwoPKk_LKa1{)@;!cTuqJ>UMtK9=a8G@-_jnsnFQb-OORv{v8_DzKgmYuG zw;<3t!FGR0{AO+qK+evy|J+H6jD+iaqs{Nn=Mp>}KUrMMTsiPN?K}c@Y>RSFZ+$oE zkQkY(sH4d#kdePN{n<)(v^lJNiTYS||TJ8=Qy)+PAPWW_jpvZ|!TmOaZRjTi;rH{J(5Haho!9@3%0` z&PNNYQrH)>A5KjF zAvmq3L@cMbL1i37gKZ?FV6Q4Rc3sURb_X`(YlUA@CVxuI>F6azhVwXTi+J^;w#WdW zj-6sU276Opy|H=iZ%Ns+QrYUBgR3UrrT2N%c|1YSbb;N`fzS2y;Is4nwZELc%?X@I$_;aa2i;=)T0iMHb*&vl zm|r$?cstlZx9RBI(JanWH?eum0MZ~CCpAvXi47)F?Rj%c2K)9r0SR0moxWdf zNMAAt+V)V_i$DO7N=7j3(SvGqoJ{zT{e^TIy128gQnMyp`8~XP`w@4VHbUuQY9#JG9kJ^)}8*>QaYd6hwV>1l5=93gLT-Fg^Apn&Kccy zf^xT7y@Ye>x4SGm@Ukl6v zQ=OI_?nS6_eJ+|S78Q5visa*IFAQaJEzruMU}gs!r1bgeh;B|ZD7wH9nKc#r%1atE z%cG-w8(TzrUwOB_3n?z4Sn&i<(tT0b66+y1u0E~%@;RT_%@<-W-8<3=?*p`hV0ym5 zg4?(y<{nkjL|Z^gcc+{8l%mz*`OEu=_4xO*rZKz7w(_mnttVx#^1*f7TvxtiI^DW^ zu(SMYjRpv%2TM*d!J>-lp|f9(aNj~P)%r1q7xY?0+RJ{@ocu%rC|ITmX!NNNAX0x87idO+%Z*kj&dd%U9eYW&Rn&5 z3TuNtnDh`p0!Fm zQ-9m3PeBlyRR+7yXmqinpFWO^2HU70o*utvIHa} zOAVZyv})W=%>rt-lfJJv7?jJ&2!PaZ6TW+VcKDappfBa`dg}B>*Z4AZm|+~=g*n^H z^XEBT6QatG^5JyM#iIA>%0)inl&ua7Ikfbuxpp9g49&8AY&82@12lwvMZK~+*_()c zAAZhC9K_gqFOr=qm)_mycet$fxB4C8WU&=d=&py)jvU@kxts_;Nsbk)*=L1WYnCdF z0_4ez^HvoGVra#p=5CsP%wY@(2zK2NUv3NQ@8uf0^gVu^WAoncN8uB`sJ3l##(XfR zMHfm_JiKO`xg#--p&$Y~Il**5dGaJa=09x%pIEFB{LCYyDc~#Zje}DIP?Hzf3 zwleJCu83RbWz$=yVrU>Kl$rz&VM_0|GrW`&NIW$ za`2cUaO+7?IG$gbk?GE7c`MH9drxNZ(;kRW!##P{-pN5|$i*VA|GtYHw;#VUJS?^~ zxS;Rb7N|B1ntUh;OtHJ1Mb~c!?I}1@rX%(#H_j)wc%QI@;A}#kZtus>zQv_DH+4HB z3h{XEQrsssWvaU|!b0;t(mxv<8J7BfZcfXw!XKpX3i)*Z_j`#tp8CS&@%|q!#}#Re zKYn{TzLDn(QLyMwVK8tPa*X)?{aTmLCgFvLoF9&7uQ0Cf$BnE9ji#JP2*X;Q|NT+< za~Th5ejcM@IAo_SflMlZ^78x4Qnr>L`nn7fXq%)82a4{t0Lv zyjyImC6+(Mgb7AejttQMhsUxs&9R2HL@8ur7^$ zy5`8b+aH>Y2>0}eV{h*hJ$E1j+lr6TpWf;3?;F43?Intm6weu@sVde4cnx20_L4}@ ziBKkljv%kwi-Ees{j^Kxdmq~T@u4DFj+6ms`E1JupHK$F^%c)}p01^=XI~opP;`PZj@-}V+Tj6CDv)Fwvxk4ZgK(bxf{DC6Lit) z%hYVywNKDz>N_qE-#6|0a~+S*kLuwE^~>HAU14u(j_F-AAW)MHT_NSlB79rWi(wi< zeVh?sL5t^W>ABJMJ<-t^^pPx5ew6&1z zbbXf&c1)Z*;lBpsuj^96s(A*BW9p}Px8?zt_0AI$w^vJ2oB5u+qDeUoUVQ%XBTMAl zwYz9Hs7No;HY36tQ(dl3^DF0vd;H_uC$iR#wV!W=*^t9?#pBN^JcB?T zSg!a<)|F2kHSWdywXUB{Ip{`^lFBZ-aL>c!N?Y_INzNp6OFZWUw~^x?{a$vD6qhnH zZSjHUp~pewGM@7`q%^tN`*)%fRi8<3u)W8tC1F8#!^j7H!aaHz=fS#a&BU!v&pM|z z!2XPn;IaF073ElrZTG?5<0_1E>B;Brvhzywj7HCPj}QFDd*_(fmJjFS{`u^0N{+0D z_eLH$?P)dWvCkw-5I;U}e9p>7;^+Rnokwfp-gT{ihy*H$V)YKZGkxCENAml5 zn>Em(*HzX?SEMaDJSF!(HtJZO#M?P}P+itl?t`cder6uw^>!1_H{t{X+Z#zQCW0uH zqr7FAsSGCm@$ZI;dT^YkaCdd)?Oo#DGd{~8IydrgHS|_ZLRAQjc<=U$mY29 zp51E0*j42!S@t3j8;Hsg2IjfA=q5wnI&`q=D=WoU6Zae3+4X0er2oE4TC!)`WVUML z*PwpwuUNn7=Vd488>k;7L`COf<6o-blTY_8mVtNSpQ;fUs^{yiErIYv7L^WPSSJ&= zv+?5@<=txfT_bIRR!4Lzu|xh646zptO;fv$V$Vj1o4I;~lAyk~4@6T@PvN2MxLUew z=kqg0D51k1GP<%%^X14t*0j{fv9I(a5@^!JUa7`7UCqo)&O#CAlfM4G(;qQjnz?V{ z>AITdL8mig70w4y{W*3jYwi0CQ1EKjviLogafzwQ-E_#{c;_ln%2w1|}+xb)l-!-cd8Bgh{}dK}Z@U9(^*R1!eTJx4oEczmhKrhFri zD4KfaXaIXiJs?nOvUnT+*!S^{&)e5s|K7Wsv$sJH)~#rmA`4Oh#gf4No2HH?r! z7m{;Ar>`%VWk2SGhwOG!QTGLOTo3)ILx;jKyF;}cX`H!^1}k)a{FstX8m9j#=xZ`H z^cA9=1H%PvyG8i57Eij(uf1*D9v+wvN2Ui86alFPH$>ONa=ze0QmQJdL@%r{AN{c+ zeHy$N+1W#~a(-vAZpy?tUy(8r7TWmHz1}>NHVY})+-E;vB0=_L&D)*z@15s$@s*}g z?6`aOG2hOssT(7^Y>z<>xY$A*Jekc)AtF$?Wr;m+E=QcGfp`E2GLp|7*5m@o(J6aut<^xC;nbDoLw>_!xvqEng zn^%Rhe(nz2>v=UI5qUBdt`;oQnb8F7mE3!!|2~TnXwZ(Z#Amn(nM=}voR_3hEKD^D$w~t!SxAup2 zP;@W>>TMWf)hcgIB@}}uI!?BV9`~y3IzR^0cnjvy-!Hxt&D$ZUE=!A;p2`0EnZdg~ zO_d?fugCxVmHNyhvF&C&`JK9PyEgF_no-X?fn{GLA_l%~tznK=OkQG|UU%>H?Klj)p zw9+~GW*l9L8_V3=XH+4~3YgyO{o1~sc)QQ=-2VCTID zSsap>x=Ps;=)ap3uW%Zd?==wb-qavi^*E?!0d~aCdmMt@?u0h8bx4?eyDk8TU+og( zWe{Of+Fmf0Ky9v1aFuV7&*52sWRm7Iy&<(t8PoWEWe;~wLO?S9#Yrf>mpk=%`Q*kl zG2BUj(&r(79Y+lzz25B5=w989=vWib4q%40lRQdB)m%UVGXhw6-G;O{LVJs^M&2aV z_e}XI#V2&dgp&@V77WAeu#{iXl>v>)^L{QL0%4wjLO>5cis z%a;xlbTxbFm%eRGUzVjm=l7T3y>M;tMpVBS0s*7q?{;lQs(+A{fQ<<30c`uxwD}A%!`&~ENnuVt1S3@CLeQ3A5;w7EO1}}YS zf}8tN@~ZYk;IoDiS*C+NEL0+omz@?;(R#Xy(c_D)6L+hY)!J1F3v$X9^o`H8%v&$f z29iOdPPenTH0!!i#$zTqg9y_(snz&!bN=YIKNJe zmVvcb9g5-YBF$rRI0d-k<1^fnTmaj?@>5hl?xzUuTMKbDk0Zyqa27V3Ko#`Utr3BUgq`7D}cH(0O!ZzWNxiKM=`h z(@eLFZk(%BiEVewS;gI`+2-YiI&f<5Z4$m4Xfuli{p9rlT1y|)=q-I;gV&Iv3+syM zS$XU~zctZcjh>L<6@48(D-A@3Fr99f&k!*;hRMFUm9&J47un|z~$A!;@bSnP;97|-<1_3u7!YRMCd_O`)?h3 zi2w5r8H645#M%OZ7f$>6p^u0z0Fq{2qX*0ZyS9wu{%Q{eTIuIbMDM2Z#e?C$rTFqd zojVg&dS-tuMUM-ruXEb#T+RTS}-AAiu1}>$jaG z1(X+h%}u;)k7vKT)k=)OpB_lH-+GQa{lHj@HVwivOC=^{d-Y!}%DhWNF6Kj zFX{a}zosn3DgT6(1N}4%Xc_9rwvTq7-U;+SAGNxrvggmbDvmGB)aMW7#VF`lAc#_` z#SF2jNb7xB&{O``TQk*uEB8V#;Emjq##4i*;AdYN*L?vcu@{3IdfUt6YJh|@pf`QO zIvS_w*^1=RV%9Q>vR@bM&qi66-IS&kn2Ilmk#VFOr>qDBm+)j)j;0pYPdpQE^7R?0tiz2l37L=WT&~Llj=+&-yx+9U-pPLc80u zwSRe@Sx{Nf=ZqeoYLP98GtS=9J4DFvo7(Kk$$q;PLKiiYwz#bF;;8Qn(ILG*y36l} zI8Il!V96S7n}fIMo?`E1XZiG2?jR)fs%P4qKXdou%Sa~! zw%&Y{)-vdcZSr4zRgl_!XHLz%S4OY<1B?lqB`93 zkA=KIlXN_?Q2u1myBPb6(eL7U)_*()MvvY$aSFMMCX%fScq5R-!CHXq%_9yNjh1Uc z56;ACwT-dbo>_@5G&6$ev8JSmO6W~K>L#~|)Q?3#gD7E!uuWIlB&oz1{iz9T zp>lQ$&o`14RkCFmO5EvsdL{4*-Mj`5@V6Ge#88kr^oIs^_|K-DzVlB?d7td+RZ2a(#vgka~R@`^N@MG9B^IR=Hx+O z!fe(jf1nEEfc~XgE$&wr845do=D=Wmrr~Duone-55DVGrcEa4^?|blgY12oFpX6PL zP2GFPFfBwu(&n*ObpiHkYM(Z_K&mbUQZJ~3$KajCEIh58)U z>e;QneI82cFatn1fO#e>2nCZeeQ^w2Q z)dlyip39y1)>N>2h04)%FQku$Pq@o7Hu;`6%yqC~MZ_?}Au==rXzLU4aEsQV<)*Ns zI0lU}pZF?2zARc^3m1t0uHGV&vAa2%80i>^&p$XfN%Pc^NATvrK5t&f=YY|2YnN?dS2@XuU!z&$xMCoP*px?S1L zjO3Qmpdi9W(6L-0G}pZr0MLH=&;4J2!%tOuJekl=^=hnIW;u-beh4#_1V~*z?NsQa zN(Fm$r+@Y7UPr|5=YC$fx6GcfK5WNBLk)C9*xGG={<);kbbjmvHDJm;nweYX<9AO= zgw%IVIUh5<_1)MN63+MZ;}qQ1_lnCVuO4D=^Kf8rqW5gofs-7Lu79Ui#D3!jbGgNR zX!1*(mlI+^UoSkpGheRSTwfEtV?#gJph)}e#rxKTcy`89ezieo=dHYY zll4Yc%{=5gPqKG<2-;B_kp&?16w)Af{Uh}WbpH@Pg%HCGxb!;EkZsXd; z8;6B$b-=Dvs1{k>{G>-Oi~bxrCf2Y0Zn)JwEz<-LkDDhTY`f|~Shuziw%L2~Hd}Hm zbu4`b2MC&i9EBr@(Q(1SlXK&r)R(8kA=!0Zn$oo2&$UCpBzIavcYPVd9N z=6wMmAA0MO@Lx-eves=5*MGa~;l57x7ki}9KYb+^meWWnnyOtaeNJS&vhdl>qUm-$ zhoF_fn8M6PWaoysjoWI7kgH4Vfb5+^VN&;f90{P;Bk|x~zX#-s=jWsIqFbXAjeZrx zD{OSBH8D574b~@)dMg~J%ADY&OndWXWz8fz{P|!|w#a5-gA4tLP4maIif51#_bia# zs}K(U)wU-Uy=|7D8r;2>#Yj=%a_c!k4hj*n*jw|ufB0&jS zUA)wdd1-F3BEAU+$ptP|Z#UlNa78rE`pR$qE_+!1)C=+etrZ$kip`7#-)+JOG(CWy z8*!ld;_k=$$GpC=5$82BC$s3+#ES?4gU=fmW@GJ+uYwY_MQ~({LWCQx`&v@%(56<~3G;Wa6o_p=D6bbNJQi)NF0o zRNB;Z+ZpR#`1K5l>czz~w7E~LpSc)l)^|_yTIH!_@Sg9={c)le?Dl_uYI1R?$KERL zRK~}fNj2wod(WlZFRDO7c%D{XrO$h9#ee$(kYbSpIs7KKuhF$NY9Z^2nEfl=1q2MT@KS9w4fQe^H7 zmO6fCdCN;+c`NoU!1PsUadq^4W|%LP9y*TWcOCejK1NCiUj91&Ub7%29qE;s$$~`= zjygAYuDElKU+-*luTu`rbj$m&%_E-){9;_at84K7$}*a(i?j0Qguu7IpYEO{6DbzMX620g#_iG;&Av*(tG zUQ5|;ZfkM{`RU3;Dd~UrhXk6*T?28|!AhJ%`}aqKm4Nr`s0r!{0}-UY;P`opcIf}q z{TWL$JFPc1wSJn$-DGCJ<>WzLvgmZS*;HJ^C;myxe5HIZ3g1|*&E_PP23zWdv=!p{ zpO%Teu2c!Smak7mhmaSAy@;8BssZ5MOWp&w92Wgm*4|rp z72oEYLg?*M$6e{pvz@x?ciyV19ji3x>d;b8wW2<3{e)faus&`MZzbwp$&`QhpRcaX z-u)Q0*U*QBp5)zhwB6m?%E8Vip4dqh#pzPk@%lEEZ@W65Y2%&4PckviWw*Y+!v`}x zC*&YPlJXRjj&|l7;D5pLApLdl74Phj;%L(6Zi@h}jSRu-PP-@9Z7(bpSOM2kUv=zq z$*_7!b_8K{2vuVE+2YL88dSfggx)KxzxCVBt;d^$3cgw(Xd zrJ@GiXKaCVJnm|47X&V?5ct=#n*+?bCz)C&5dHFGB1U$mJ%|h`YYG|3Ic1zf*x#Pp z*SN`*+4!&_Q^h#hZ%1OYTHK-PUY1+dF6U2s0u!0&RRGOtZDq`a1*%5l_kTX0DigZT zvD@7z^a!b3)4|gpyBr2E=ldKz=ZOiAdNF@}NZ);YX5+QEHc+noT2skN zG#cgWA!|~8v5qjF#U!`%hk)F+F%>O|^W1LL$~Psd`StD}hYkL6$Ga9W*gfn#s*D%i zTBW?3z`*q9iFCIFemsu_c|M#^d`Wfh>yEk)Z$LYty*NV8$*ZI6(AJ?_JAo3yn)(xv$x&+8qBS}0L zI6Jvfzv*}w4?uSw+c7IzK{*y$ z*QNCdVoUOO3-DuYx}JF(+acKaYW+4GOr59RWVL>`frxm)Jx{OVd)#Dcebm2o&2>=L z9`r1i=czQ7Wz|1D*Sn=z@Zc%mH7bT~PNB2{!-U(W1YwUT@2cYN2lJRe200Th9XBRcW8|`!QB{*G5>c>iEQ^Fo_&E?SLoPRshzilJeLK%E4jCD zDR2}vg#WY@G&PvE`ghrfW!}z&^|hLHl%D0|$zqA&Hk=yI-(F+_g1$7#CpV{>qo4YE zg>yL0RZQ;%P-t`vNIuYa$9JlxqDtj#{d(T;-*u+VG9|YlAvtpqUrlV(we}L2=|-(~ z+97=W@w&$Hd~o8IwIyHKqRx2MI)0>2hYdQG=ND^&B=|3Nmv52L*ZDgo?Nh1hECQ?*fSHyEXcS&}PQAE_r#7=jzck z!a6ZT)!d1H`>3K$>5(G{?Cq6J&38RBPYU{XApE2CirS{&87Up{hFb@ITKOk1p${-8 zSRY+pOcH(132C?wzv!3K)9cKx-44{j) zZ)s4f8~(+%ju=26vFXkhvi4+Jt(j08%jMYWA8&UX6k_ik$HPXAtK+k~LfJ-GM zYp-nWB+SKzWne6plWP_HI}<1JyPbOtnPCLg6dN(yZW-4JG*;6$m**kZ9v5Y|)l?a$ z?GtsNpYfGa&k-duxe+;*y(ncNCQ_!slh6=XzoNo>9#+TJy>UZ@R)>Ch8ro|$t2-od zCYKu@w`BDW%xq_eS1@uu+24LQFSHN#^F7Pr3>tbslGo>MUOn#vXgn}?T#5a33fo2S zzP}(-;rpHzah5i$j#nMOKK^UQh&SbhB-noo{Uz!bgP6 zhSkS-H%#6ulXMIkf}e_$*pG;t;vNrqz}+V)$mGL&jW*Qt-JEec4L<_FH6Q&yoiGA^ zq`_}s6&_1P%O-i@^MaUf%OeCS`}M$bK*=}c%KHth#8qHis_0Lj0M5wdHY?JY;$CzO zYKsO3Ok}RF*HGc_7-Da1cYEA{Cebg##AW$Yd&T<0J(Nhyd|3Of8jgfPyews*$-E*S z|407MB8gqhaD;Ac0b=*+ovWvFy;N4TY^`poI&u%2^i=mG`O~m)LwkCt-B)|!5X-}5+&PYyd0Hin8W0cJp28bVL3YjTH@vg zaR2}t!dteC*c@JM+wz_PUBcKjfvrn+! zym-B9@>%WccTBCz2`$aDmUz^JXZoMJ7@RSqA>Vt(d1Oeuj;qAx-Z{K+ z!#;lu_az|t+O3&GcNf&G#^Z*7;sS?HQ~zF&Pu7v_ma28>dKM8UhamR&0BX^Co)vha zk`>=5z=|B0@fML)e#@5e`TjMdYTVt!GJ&{PP<6nd(@UMe*$BAK;pSRDn(k4j!RfEZ zO4N1rK{kx^4fT8$@2Gf~NJ#)a0E#VMu~BD=)8Vs@HE_eb|(mbaF(i3QfV^8L(}Je z{<497eJQc6sL0gOByybn{#XcO_1&+zCAtZt-k~D3+r&jEt3`KmtB*VL*xQc-Ao7^m zvUv8IClW3%<3>}9>~e)Z8R3C&edGD@`M8*wiAD6QC&z($LCRls+>?2@Sn!Nr!)5Cicn7xK6hMh6OH+J{dp=G@{0BgvtOcl*i*%=D2X%e z^T(avJj_O(EOlcm#7E8{s^`=F_dSlU3;&@k;>16not$i%1C4pL+SYWZ@(VYhIn!EvH>5B{vdilgzq6{_}Tt^ePoFjA=10p+N)0>mXP{J z1P-KQZNe6G=72y)77Zj6KQui`%UA`(CsOfpwtt{+7@+PA40lDRiJQ-luo6NfT`Pn?I$15(noa zcz~&%zvC*qB)|6g4YW`YXrYgLTF_A-O{$`H&QU$-sj=C~k8;d3@(35akjJKYg}*JY zC=cP!z$0w0-llG2!>|YBREuLz{xDLEl}M8G0MXF3IaaCEp4$2H2k zA#`Z1eG^dVP?^(eOHV_H@aF_}KE$6Qj*0`ftm#J5G%Y&BKW_aeWMIa$vvZ+ObFJQO z_iddA{JC#Mo8Q3B!dx&XX5o3W{r|i);N~^!V?&Owgc0P+93De5&dx5T@-7Ly#syfF zK2Q?A=1rTJ-y<7+wS>1>qQAPn2Av%(daU%vun})B8bZVPK4;Fp+=Hc6>3TA+IH_gx zJfS1z>(MXkne9CLYEQPq+e?O;=jg~Qx&eo@HSf0qKrG0kKF42tI%|zUp>_0SVNM7K zBzF>!sr?WFa#AC*WJ)g@0H~+K$bG)L&U+5GY|e7r+o7)u8Lqf>~S0mN5IgQUAg2dWX*ZzD>P(7Uxd`0jV^uq;I@Q zIU;Js{q*X`20yNQQycIbxjEZOFG7A|?&={u9Er&bN6XMFz7_!yY!GHGVG=)rfJOqK z13#89-u4E3{Q2p#I*|Eoj|@KP&@VZMr1+{wZyV@Y3PP`yZDNX`#^o!JiR!c5Sb=)I zlyaAM*K(B87aM>{H5n@p+7|TMtkW-%uMv6Pl}q|f*&X?)iS{3OYQ0T#6RlWviB5Yd zgJ}RUJH6C6g%+AKyTkJ05_-dODWW2;G~*viDJfX-+uz~o3Xx5l!)kvyeAzx_(@`(Y zrd=aILm&_nbZVcQr#qd@h#myQwZYRbs_C$-Iqr1X?tJ~3BZzfhqP;wvY#V*6r5YKu zH+E$Owqr}3Xc~cPg;wBQg&J=gEN_g*U&6!&?=7V{Vkd>fkz3uqJ?WEm8FX+!uV`1j zKjZDY&kS*`llQ}W#~}~2y?e_seXHxy?(~$8-v>k{ov($FSW%f7+Z5eOD}m?TBtfS{ z87b;(3p^c&>iWYO7S3DR!%Jz56}u|I{y0HJ%S%X-+ahG9c5#B-q}J7dwi>v<)gDQg z!>gDsh{*;qQFmCQY2Qn&`pcFrIkeScr8~%2Z!d8v4?bVX#CXr)OpZ)?9lqb*7v4!~ zi1if3>*^_KYa02lYmS<+BI-~Xvug>FpU@pO8`pWj{CoEdVn2qL3-@)=aiw^m;iGt@ z6%NFMJYC?oN58Q{zwvFtX|rG=*7C>CvCE(7iG>S<~}}>%sP>` zPd8FMR1z*^9E`4g;0@%Z>hi4@wS*z0#5x$@*6ISe&wuc5DGdo2tX_jj2HiU>;Q5d3?&zaA`#eO34p+pn#G)78b;upC0-+0 zF8I?mkS3wy=_S;U3Cl_Q*8yOloowyn`!KnBe?ch{A|iSt2%9&+4m`g_W_PMx*)=k$ z0(U08msBu}wQ3|{HSW0R`wUnfi^qZ?*R|L9u*v=b%YiF(Oo;**lvOS{p^EqQ!x5UnwGn--{MU2 z)9jO{*Xjea@&0r4!eqA{au$()v5s`Fb5dgDtPMKa9+&=b=+5JD6G~-}t}k<>ub#{& z*&_oR!Q=k7kMats396SMq1U58hb}rx?Aj?vuw|#=wHjqC%LVr&XpX)-apX}FOY*BLlZUAEcNRU zPvfK0ZU0KKHwSc?_7`M=VaaSphnTd7GfFXU;VL6eHLwI{NJ&>0* z{Rp|;mraWZMMSvcoFG=p{i5!!%dH}9FrZoJ5<|}B2P9iN8F!YlcQ<9r(y!w{H?0Lu zkrsV5cw~>c%}!L;kn%jwTiR$gWAFC@t80={Fec_(qN3ZUdLCV8i%rg3G>~0x?F)|z zc&Q_uXrK)~Xr0#I%L1(6ml*fhTTy-p|^Pllcg4#^hNj2NFK!V$wBtvz}%!F@4Fg3{mrW2ef(bp zXmby5yk$@{Y#pl)6mDUZfiml_v61!t=eN&i4eaasy+XRD=AywdghRm1@G6arVS$OV zhk?gNj`9gw)6aPSrt5m}yf}~)LY0oU$PUAvau7?Wm#Q+Ba~UV*cP=Apit2>ba%tAK zo1Y+rJuJ{7yb{7|RthWNbM7tdPc7yxLmSg*CA@V`=-y*z8hX$Ou@joc=3=YKsU)7M zvJ;h0VC4OM+&$r&jGNz{r`)EJuOT~b^_#sqK(p%Y-qEi){e{w3ejLbs)u z_P1GDoCw1B&%e|#yDw*jloP<8)*SeeC3IpGRSsY^!)k62{^|xUG94#6y^bpf9PI?_ zkgR?4>4B4+Q*eXtgTh3;8rg4d$09y-AKYp}hEGvEvoNE41_rV-OM3odNLWG4=-yZ< z+vB6RjpMYb1>z3%M<^>O9FetsYW!U4w#Z2MHB(rLdJ+y3+?Y3-K`HY8u=QrkilS>5 z?geo`E6t$|iU^{BbZ2xbAkrgn^?NXLt+oFhu_GhupenP{iSY3@V?2XZz`3PzVKMxF zJMQ~!o%i0a#UtlwQkT0+4De&Y9(LbgS4{_Xb6*)CyE`)IaP0#{28-}@u@H1Uw1?Fv zEZMFCVc+l0WwGk%THwW9V?o(AP~5LLH;3xUbHH%7)Xsg6nkc4wIll(WS7m~Cma@t* z)Md-DB6Q(qZ_xM5^VdjG@r*g^_5{;e)$qgE>TA3q=&*Prx@m(~YPEDB7esS`&WhPV zKT8;y<#s0Az2<3_o8VY%2FqnSUZtF>h^a6AuXi?x{a=rx9(@E9Je4!Fe|hqV;Xurm zUrd_u13SY^0BCDpt(sd0yOHz6gL}J;uB`nU5aXJG9klv05cx_2v%s=(7TkK^mxrFy z(~EcRUq!0wk7}xz#Iqm9;kvmX&h}-0fzRDDO~q`}yn$$YjdcI>SNQ{CKp*d`4Yyum zJHv?VgTnG4D)Om~oLt~bBp}YWgme5|EJW6C;zx5L87^4wF_2GksC><_wBu8WNwSlR ztYL34n0{V3&v`i#qJBdeye#w}w6SS_As%SHVL1Qfe8L-}K0RS8AcDXWoI}UuA>l`4 zrq?}hx<*FS&11vej>SaWCnYR~!mcpz=WpK_us2r~o`LTC|1!NYlqp%jD)!@gc(w?Q zMB=2StFRa$*!>!*=S|&4;bV#~=JaHL1EJgf$b{D?d20IyL+@qQr~l%!12Uu z5P{u4wm%YGkjK@iO;u@{=b8Qu63er{Qvjad`?SkvU-~)^QgL67{=QM~=KefZ(olCi z@v^PP-&R<<6iz@k`-hJjj8|ZXwjmUV2ss;*KmD(By0_K`Q@$gH`NS;WZotkjD7hJ9 zs3F)PzLI9K$5#>kc@}dWIx6HfoYYRQe0R^CV8to+*{)Z}(5$=ISNy>Qv3%Xb>E!~? zj@Vt+OpBK(N@Fo{hHFe661pcp`P~N>yz32+NYI9S)mg-mgz{h~M9=5SbJz1581JXM zMeQm~ReV99c%0=lDBi<-_eAu{9<9GH0=ul)l#H7|Ud7#!5bA4vOjXnfOh$>F{W=4M z!Yi*a-;>{uQGagJHsB#vry(15Gi(BZ%7nhSJWL?6FxmHr7y$1qSMd)cg7pmIaFj<> zf@i?9DA6fN=PF(<^sl*oHrPaY&hLf2k2jo|lIlCDZFnd|55&^nm0RSBI>664`FO)g zmbT+7xg~ikzU~La&n_XPG`ha0NUpiG{<|VX_egkca3=_Wn7U#;4iWiq{juv#yMZJK;B6KN$@FdYbt^7cS=zQ>(^_u3jt=7t(ijnbUIGKcK`De&mZ!p6$^j#z1n;gyn#FQ77TmFkk1ov{)+Z-ohI@sAAsu z$T2WMq!Zws)%C+`^DT3I))DH0o+01FjkC_EFdT*4M5u&zN?sp1+fM4U1fcKCk~gxg8=PMgq9-N3`YW0mEni&*Si_fUL)jbf_>KX{DcGAi-EZd`MW}VY9o)b&9N4L9Ljcp7}2-UjXqW%3r_q+5$ z);0&$KnLQD#u6lOuq<_J1(reP5p*mEZ)Fa=!iykefX=Nz@Cj(sz(XjF>yaQ56dk!P+%zOTf*2qeJMd&a!q)|vdV+_Z-A zQS|XAZBACn@koq$Z7(fPJo23kuU#6lS2e`$6e~4_@`tWJnr<&c2eZyv=EHhTR13(+ z9HF^=bx}?{8@;*2@wg#Z#Z5Cf0I&@Nd`ahjERM$kGcht&I)#2_(r)3Mg4Ub36B{#E z-AX8@y-D6*Uk7V@25eF#$Y20Ys*QN+)PTO|i;|h{FkM%+5*PxLhqE$}=lm_@+NRCKRSUT} zg?w+uThY=>`SpJ|AsAX-rpiM8INr<_*e^{K4O>jY!44x>|1~SwMa!LoR4{Tkj{Y67 z#?fn?#o{G~Aguj5t3{x~&-Tdg#aT7cNF_lqfCaG5eN@$|BW_lEj(%9d06TebX?B)Z zUKi$R?GK49-xot`I7@X}RgiGqCKdZQg03_`>q1pTLDvuQk*lRQuE|#Hw7(%qq-6@7 z%tZJ6jW?7MqGUC?J*Tfn6{rfY0sc~JCxEqh0=VEU_6PZ_3+aaWHb zBCpXeH_#bfoXSv;kNf(Cod?q55y@2SZSc{O(N#P^I#xy{S;=plYKPUTY0lW3bj72g zWXrxMTdUk0v4TBqcQ7-)%EkKir{}P=C8~O1_t|m}C&wPzmJ??&sgV--Jq@GZ=Tqbw z0WKQ$iq1r_CT9m*^IU2ikOT6AqBM=3_gPc|v^SH|17lKvKX(l&aDuP|ej37D%54l@`tmBr`Wz_%@H`%;9fZnZ0!71^d+#>F>|E6e~6* zovtZ{SVx~QiSNyaKgqc&1Gt#)ZaP_4>oi+^?fL?Qw{XGJ6dAo#I`0P4@kz z{giMO1}gnVkp4ehc6_}B$n%k8=*(TV)EvDyu{&O`s(F)4#L2h7rT~EsQ^L_)>kh!) z76G~LLBeYZeYPw(>U17+$L#p4)b7qo(XV}8R9=(SX!$tv_I{UZ%#3bqRxxWb3;i};x0E;go=4Z1ESB}! z&oc+%c>9)(O}}k$1b-@)NM|d#fm<{4TEw-#&K*WK3{3cLBXGiTE~h^}-PeX@pgL^wj#PWaXP62%BuhIjVc$)!Cs$Q_P3v#1il{rc7&V}i)GHQ0-n7LQnSI{ z`vC(g>cC@ke(Hjj{|ayHBuop6A{|eh$GpvQ_s*x+%&;kfMFczs7I~V=w5a1lw%xN( z_`1{__pX9B=?(9cO9ziBZ3ny7d|yX3IPO_7wXZ+nld6Zv?u;UZnnRex{aGSH_&#iF z&1<`8+=6>mFLxa3oB*`26G+-z>V@9APas&qZeGNjg`ovePEJB$TPypwY-1S`=(aVs zO|A$^Zu!21%FLbh+d1z9*m-<>8}Jm=GM$C<^9nD~`o4Hc)^{t!L-cy&0{wg3B0ro7 zX;y)seN-vHim*;6;7XVzI#P8m@?(V&cjwu}Rlkz9;X>6QpiJ=;0^BsmCsbNcD=HST zDg(s^Iv+!}T#+UJk5_nVgD(!5^E=B2y^NyQRX!eP?99v(@aH$%*jgF%2cC4JhV@Vq zsUqLf&i1n7(%b$yK_pucdofCn+3kL}8%P;!UHRR%R+2d|?jb?I>zM=w%NcmzhB+E; zdIw$UdtHVrM{w7hofMv%b~Bd>={>O#OR!OiI2tPcE6*2C7oC?I0ef*2&S?lHT6|UE zki=QY@0(se*iyBM<}CGX=p`a~{`dL6!;8B}P*767XHQArZ=zNKM(R}ySR(R_tRCI9 zmPNeLkT4?>JCLeK`8sSWt2HS=M`~Ts-X!Bi_vV zvD^B}>i6D;wyefa5i5XGox?O?26&ZShA3wFAWn7nXcYkfT#3e)Hi>5};;3ZYY(| z+1QuAo~ME+?+rWcmE*a4knV%PX3EB*$AIVvo6k13DLB>>tzO=i^4+N_20P=)TO zJQR-C%hLT3eE>m&%y|GDNarUr5Mz1|pRdCv4>3hBfeV_Y{GlHgyd?OqtvB7f%>7d* zUgq#}Er&Ee0?J)N5l6X$wU7~tf$CuM|H+GyU#(&%^>muInN@}v3?nZWFteZ#je{vI zfRfVtoW}JdOh3;f353FIEYIMgQ{Fq@7QASX>;|=W^cK3uy8i|2%+T=w(YmwY_!;_h zSV942*j-p+C=Z_<59H3}P@GlzZYXvm@4*wwZwpIZw|C`>$}|FJ<2Cq(XOs|m=KKaw zcfshppGZDke;kpirXBBYj@IiQ>=0wx@HYR9yAL?>!UkkWWV+DWl5g)4vH3QUrEgQ^ z8pA?+M|54rK2mo&y|I#GsP;A*_=5c#(`8R>GoZh@nDQM8+8lCi2nPVt`*~q%-;31-ze5`?0(9L)Lg>xjZxqF9#U69|O#K-9Ctow8cWv zJ6?AZL+)j-D)?$0NvyU>D&CWBP8~yAx^ki0R&R0h`TKk@M*&3fEN5E9w2f(827)N# zL^bAb*wa;-0*!NIl=XUD>%Upb>x1H(E%O!>`_9p#L{=V{aL z=zf;{?BjJStM(lvv)v@g$r$_)D_VEP-3F#wC+oA@PCO}e!E}I2`dp+`F_`Vg8n-H&DVVv2=Z?7^K!HJ?-qkjH-LY< z5KQq|*a(U=2UG};+$ZqJSrCz!ZKETN>zCjdE!OxqL_A^|OMnxuz9!_YYVfR_5hJ@7 z5bI&P-4DlNcdNyXhFrsM{@uSkvByV3xBkc;y>yH$$vSVi+=H!R3qDMcb4V{ORpe_} z`3rvY;bLB&*Pxma1cU2~PY)k#6<@(Hf`eizVQEWZ8oDCE#0N*O12e#0V9SHmxlXui z=lR^eeO$vwX;Oz~W2I(g$uQeqVuYDs2a;Dgn=EprJ(b@(h(B!srn_9 z>*T6;0o6x# zKoqL4MiVv>trXrH`7C}YZ?jj!#=v6)RcNLpCH`ZFnOf^&9bIx3L;ht2;}HN9`Nv%` znoEddK0k#$Eg_rLQEt-ZCN2<;mRIM!lVmOKkG;LiFcHl`kGy=Xtc6ztkl*#3Zj2H$ z+m8YS&8I0!n12Mba%Aq~jr*NTQ@?`!-fqQ5J22uotk8$Nz1==|BKyiiMDp%MKJz)Y z2M6+vZg}Kaev?>H_F!;s!vFDrXP!^9ae)^i6De@C+k?q<%k{pV^L^a4;>~WQ^aY6C zW4k?qGR4ka@A*uqg&X%X)sNmwxJyQ31xc?(3M~~L-tlIJ zdFW{tP1~$$IxvwMvh`i_Q=eg^>zPSpch~8=GqsO0%kUe6h4{+ZZ`*258=70?bb`!t zu`!>%G|gq5Prp8U{*f+S{(Al~jd#+sgSfxZByh7fu^wJu&f$FAYG9@a$3dKBh-!zk z#PL)(Y`W|woKFNxj?eAx@cv0xq8-OI&*37ff&(xn_@Cn!&;Hvot|2A;o%fe}g3J%> z;!H#9Hor+!VV7#&%I>-$0)$F>gk2zfq<5cmk7CsGvOwnS}Q`uCU5ev@`64GdidKhX}6^`u+P9x3!o``=1FEay`+)XO@<6pghz2}j?RAL z9I>b#ZS=t3`df0)E*wQ-9K8SLvMlc7TuSEd#jgBt@&D}3!2@Y0oLlFsYwp5rC_-tn z2%yw3N=;r$kP*N+&iFCYUieG)2*uc)WWJlu0KM~et6bQPj2*pXuwUr6{LA)a7J;!Z zfved6G43!oMw0Jyd^6z1`Qi5~@Zn=lZ@UjTZ^H5K_sH0(KkO&s*6hhv7h%Ls<8r9A z+eQH6=7_NFFO#qW6I(6R*9+&s>LCCrO4(y&Mxh!5o-_9-~GF1dPYxjgtmSM6q!>mTpPwnH{wpb(*) zwY#oGGPZ}z@eDGy_tFa~3$`64ATtSZ;tP+|&MgHZq1&UFNit8C@Rl4iclaodwF^+a`RS`5Mr}w7;3WZ2L0R|(d&tJnNJ+QW?y%z z2N6QFIP~>&zCVi=$cOuL&(~&Abmp}hu#fw0jlR8g$RjY3?^vnXlG3$6w6J_f2z>Q` zg?bpp!OVcp$JVEE+m@d>d21V>su2nAZE982AEOysq5UBmul%D!rX^7`}Q00_#hfqzil zf0#_$)wdI?i>`X&(LoF?bahHOVm8|W5;Z5jqy_K!aYuj;couEG;{p-k>tyRq5j9f|(^e&zbJLK$r{S{=CWD9a~|7mZ4)}kJ@0~w3E zr$4!!ZWOlYvDMg^o#Z}J5PRj1J{`u54;!oe4vp1JLp^`e^XE=pb55OHDGe{0*8 zxwUjdp~>AM67(0mke}NKKZb0Li?3#|9ZNEImmt9B$dt~V*BmV8?ekHBV>Ufn zZGN8+{TsjTyTzjJ$KPxFyz8zOX?+3I(r2>E-*9CbGo%lk;FLQ`p(HR}i+_8=zbwTH zI;iTPZDJLB2nOp4Y$aB44#Dwosq6ixPTGU^oumCDj=eqCyxpKP8%r?Hh>IEzI2i?> zx#YhdS06;aii^)o>Sp`kyXk&@E0oFK*|0re4PeU2+rI9u@|7VPb3+MA9Xtzo*DuNK zVfdXM*->L%fYOaGnk>Lfy@Q8KTDhhe(Pfj9U+}boPfh>d?YGjR~4lkW7-2(jjCV#sNLe)Cx0vW@U&V&ks;6-0+=6M*ZHroKX8T zBq6cma{4J{yy%ODB%)rv9k!33zB8qW(uZ(Q%-1B^J`_{Y_e>W-N$^1?nq)GAqyg*d3{J>fiuj7b9`D8!k#9Rte z|79CxZBp>Nn~I>%s+dfq(M%j6ZtG;UA~&_n-j=|nxA z16tJ-`B(G^+OdBFBe)-R*xqy5{lbCje63<$|qwr|^Wv zR1yTxcY(E5e~upZ%D~iaXuI8KottL{zRJncIfTB0t^KVpZ+o_91#-9sm`!cG-wyll z=?o&3Rs&?AACnBYv9Sn<@$yxaI}nemk=$}^O_r8F>{k7_c%avyK<-_0K z;eT8+zz;#bKsq)>>Ic#hXFm&R)(~kt>cl>U|Q7H;$eSN&e(<(G#2D0K>ITTr4O){~;o%O67)UR?EIJT2oc?Oxi}!Ko%<9667e zY89;*p>O@;_@!!&>t%pN&6dQ$uyy?!&wfNhla>JNhhgmvn8w7P2Z-o2AN;G^P6kVJ zghy(4aHR$L!})OuO-)O)4?O?xy_8OSL#2#S8R4p%(g(%<4m|p}^0aK+aMNiiktCMu z3CP2aa-yq>N<4F_8^K=Q(a6F2!}@x+;y5j|Vh;I^H?n9e8c9F%8>BVG4;U=qDr=DK zx{Kiu)?onXfoNAS_bCGZH-x9eGvDdeJ_l046@^>Y;Pf6%u_#YmKglocBf(D!RJ1`P zyxKpB=RHIV4Qu$8IbKO5Km{6BicY0GqlUQ|m}~SbcqwFxNO}DH1R8#6|9MLLn~88o z9qF9%<_wZFp9rjOWrQ^fva0)=W$2&@AFwgTn zeCWWFSEq9WAmc#R2l++*PwTWYZPyv@IbR5|NJFpa`If4My!TmRxl5lZ%owq%wN!GL zQDRr$&g!|zzt*YecN-*Y{H7S8vl1&8y`ts}g2Fc7{uo%6bwK9hNdjNhwy`WOua7S^ zR+2tmg_`&J5&G(fp8xy4!iEMT5G>FLsfelJ-gZU()4{g4CN;b9d~(#y%*{6XxgV*_ z?wd_2`5^H@OQf5~$7)Yg|2~qE^fn@h`4P^RI@}jCM+j`RQx%cndxMPV%=t>?X$v=H z@TPt^5n&8megG|i9rMR?Wu%nCu|LNf{SKI@(7j2E9gIJ3zILv^wNktj`~5J^5dViv z``KJwDySJJFrsfcTGw+sVx+9z7lv-*OOM2|jm|sLQD_j@HQaeLkI%HO1)6>trpvtpq4AIht2!+7G`82nYxD6i6p02{kekexR`ZM!8ijO-x2k&JT$txwYcW=l^Q&d(~JEq4i`(Jjgv~`>Va(;)%xabE~ zk%;Txf7?Wf|MJRiQE_qv!Q0y_+VegALYr3xK~IjLtX-%j&`^(k4#?Z9ts8OsiMAiZ zM8P2I@noITTolh+FvjWqP6&n_iFZBmVP1;ck<}MT^!M->*tchL+Hyfx9JaqRS(=Ai zSIRK<4?)^v@>fdmqndIl7t{|v(r==Yny`i968+cF=Pn3ORXC)FC5L{V9t!!peQM9~ z7X@S?8yYy?8Stw3$-nUcM)2T;7$0PLi-x`r>xv}fYswk16F~}L_e&_u1HWNU4g)+#km7xV`nIyB0H1I(=w|Q+{GLf3 zkV4cwfD}SR!4*m{nL^jtM828XN*o67wgKsVdmsCa&ntT^im7tR-YYK_go<%K6QHJA zKCZwUP~-^BV8s#2P0)pT&D<;x?o{_pZJOAL`2nuF&2KEbH{83Q()O zf}>PnO_ewO;F_Lz^V_4u^WYhS5rCY8TjHOE>Bqm8^NEw6)ZsoKqy5+)eii~Cg6{oe z00a8&n2j*PPu8CF@%``mS@OO?^n0njn4%kh-$7aU!>?+OTw>79s;#XeMmQ{=oEkBa zBj-2w)`IKLvJS06v7r=a{YASybAl5(`nLFJWjwMI9z-qQD#ZN^$MIOygu(C6Ua@9? zibx_hTO5mdU&0_-0{69a;e~247rv?B_ZHW@`}B$--NTszb$T{?UYJn6(rtCz3}%s0 zGlNvgZOZ)l3W!*RdzGp0j~VhJXeXqACA>e$z~0USF%9#ce3Jg%?SdtE=!e41L#k%#&X zRRw>6*ZBH36HBj4DfPxDib<{hzVDAZ)AGo3<9T;*5gD0&C9Ec+FAxu!N%(Lu z-E78XZclpH@5SRqsi3h?h3Q(-7|T2XKADZyYwst1a7yS?`U{i=2nny!`d1tw<~3u< z38n7HYIwkD)cWxGd=|$(*SBHKn)x8kZ1ye7gM+H-z%m<-uVK7P*%$~%$gz&qgz#jb ztS^=-g3eH{T4%oJJ3Er6cpP%OyaeY8{De>c2BkVe>TCdv#f z(Upy(bN(9gP$c4+Y;^5$Jo@~?5pz#I=>nVTdVF>^Cazz`{B1~-x%eTY1_qsp7yT`;1T$LKt>Gj z>Th7*(c>QkUH{b>4L)oc>=CCx{ds#u`W7v_ zd8_Nb{(a^(=z@Uhw_g@yVDZU2{$*i-(Xz5vh&?nx)$AvcJN4yAOmJJ!aR#0Wz1Jv(Jxrl>H60RTD@mVwPQq9e{D^(J)KDQ$7W`M%|Er z<`S_!QtFF-c~A>Cr|-9~%`2=rhTpa!c%}EhYXKFl7SjM-w|!aFjGAwUMVE|Ua^tB& zBkQ$Dj6Qm*g$2kbAi(rmT)HJ!eScy&j72C4={oNxNk;j>AK_To&E&PKS@q5-!muqz zyo-h(chl6Bw{0djh5{VrMJ}lfq|Z0vkynu2FA!N+7mHUu2vh;|`~)|d&H8+n0Ty$Q zpFMvZ?;7T(2i(6;Vj?gPx_O_}p|s<=kH?O7!yI9yh>n*ZDz0@el`6NV6)K8T{GM<4 zzozmR9q)LJ{7)zT<2NVY6VenY+U_Qb)i>O>)hs=_0b|2$!U+%$LdZ)CuCQ;0_Y1t0 z+f!8WF4{K!oZN-rekU(^~mhz$bGn`pcP}-Hk9& zzwy!^2qm3b5V~6}-5C?o3oKCWQk!OT!12}|m9Scis!hjfw(zDe0XWg%ebxMVv};Vc z93axE@ncs@g_Z9BUvk?xH&)+WB$S2*d)UGSG^$ zzk*bA;|sjk%`1qee%K~3vcEEM=AD~;XkEPAV{HRAmAV8Z4Dm0BqM-qx-@2sQoU%o9 z275XR8s41$)va>^f$PeH7Jtd&#e>zy9R%^e%wtQmNaT`ZQ98 zr*lmNiat4Zf7OiLy8mqd)#ot9AA765NwB<&!P@aQ72YNNguw~GyZWWua>vt zSg3fGnU_~j9Cz71`)41nnd_B+&}pD{p~szq_#v;o!Y>tXmwmu_B;dPHME3rhQs9-= zV&i!y?@LAcNq(?hIJo?Cet9ZLC|vJZ{o({zpOEpsDlO(Gq`wF;o52a7&Q>5ew5{${ z#*9nbahrVINdy?MNDRl#`5G4gg8Az+%k^z~@?|Gw1g5_7`8!DDS;h3>vkR?Ep0Z!wzq&RNr{TI&Hc%rVi@e?&ue@A@R^JDF#;+3SxV|*AjP<-^O z0T|w+FMcD`iD#W%$P=Pv`zN-?UXw6Ih_#}{d~v2@`w|QwfXsYg7uj zj#s|^mbkT7eY5w9Ntrqx9((iDyA$m2Jwl=O=lM%BWJ%3cu@B}>xMpSey0;E=#A@}C zQ}(hCS)4=P>Ts$@r|=s9-+_lvB zZX3SM_TJ#w<4#eE2Xf6madP;@+l}EA7lkX4m%gM!<4$esURJMB+Oq|+1oXn{F$n0ybK{8u_4L^Nt$UYX zA7hFOenn;4Nz!udt6S$Go}CIcek0dV2NhgT@$4WF)9B6ULh{y}GK$L4ik9I`YW%SQ zqsvVuzCMyNbhI;DM)A)=^fJRiNO4toMu6veJ3>H>d6(nJU2#9p%$h69c*kBdYS>lEYk-c= zS~XfDJ)rN{zw5Jg49nUcEM0+8knCSjT4Md9U|9-Im!e}N^+?a2L4=pe?-b+vrodw$!UEmU4 zGEB%Eo>4dAnogMrX(J@&4wrm}!={5N-q;z*^Ye)TS8)I{$BFy7BlMjQa(bsJA#Q>u31STh%4G?<2*pVw)S#!9R=!v z8LKp&pp_#AmSan2`=M(v!w_Xevz$~->;Kp)3j`F zuUi&A+qvOEJ2c?NdTI5#3pu8GckYQBcckTYmTVG~E9bvA1!)y^>;B%;9^TW-_k{=- zE&6I2M8MlLVP0E`=$ZU(GbnXVGDS&HT9F39?5e%6OL!BmgC<8d`;ctF!`Xa{9!2Zeu&TYwhaFCUXgU_&mv$6 zw?IT(GUCLFVccfo^=#R%J!YA~(YyMAH(X^Q|F$>yl*YbTGgB-p0+Tq;?{O$U*F75h zd^Ej2Z|BGR_5)xQ5;n1UKerIU-)ou}X>txJbKh6iMRjD%3x0=m^)P<#fGe;y(1i>h zxTWc4b6%2Z1=N9ydjb!?M7z&B#*$9UMQxuJBOu#W|9sG2|1n6h2aL08Ot24HvKAxT zrIAw#<4Jpr?3ifXoILyk?s@3Qzt9owljhrxX`_9vAzT)(!^17jENdej%vsDYXj8jd z_^#anKf|H(E23P42-nXjgaI-pN__OA79&N_H3W-DcPFGS9`Ho@H1-EzgPeKwB7bBCb!qVCv;CTvQGKL^Y+g@(dU7 zNMudcQDsQd#z$xbI@sZZbNkH3(z&2c^mqEpr`nqRTBbnd@#v+m+Mb{evteP_wmP=7d5FCbovLF(d>lyMwv0W*O|& zf(dSxJi0?I$sgRRC@oOyw|Owwi|JJKc~)I;rm+)w9Kj1bt@EX9kMNi;1U|v-l#jLG zxW$gn<|uO@16L8A@eIJaBTX`?%SYcKQ2S zpJr&*Od9ij9#W#cl{@5>BmJFTz#_+dL;k&VS^#LRM1Db*IKshNUjI2~J{8da?!oCR z^Y+$9)jnV=82O&^8tzjut-Dvh3%6YTzF9@jH$3C>+$@cQ<< zkYYlc(To6{?M|^b{4G5QE7$rmoA)iR!GeHy6Xt&u!;q4Qi+LAvc4{veU?B3)Mr11- z#l4p!G>NH7l~+b>>Ih{?aDut_`{}pbgo9Jp(|=->W%{jM`D%A=$S^-S*DCaJ7mEG$ zy&LSpuA82_7S(jus6+MElJ<6wG?%ojY}y@IAjySv=?NgrpBw-Aih}CIH9>C zj=~lD8h@)CKJ)HCZjkl-jZJ!2m4RQ@k76MpQ9jqNP%tL7l}C;jU9RDsxept zK%61iu2D;VqHi2F1;YjI8sJjNm$K&X9$J9cEb@hhbn;`6IhE)0>E$)_G5B}w)Q8BZ z1}%s7@~ZNaAE$43x0`*xi#Z~xk>D*+E>wT^;s0|TCMkhjl)v57?_FFz()BV2>%nR} zLiE)k^kepGf77MRUM`ydWpHYj#Zz&AA0y;dAs@}uh_psMeBa&+ZVUR00i&3H`uy=$ zE=K9+XG=xE4RpDchWGC?Z?>9oVa`M6=(%CZ9wyz!+zNE*-rZUMXwycG4&_HA8HmO< z`E!ovy|9a(ss!z6b~!sVXI^4fUs%u`6?Z}W?+F>#+-7U+!KnMa$vpWh&$1J&TKZSlM*_0LVrglg18V zI;by%M-0mjG$k);Sh|QKL)r4!d~xbm28{e~s22%{vo3!gWtt z7_Cc(Cb>u4;CS_18Vbgc6C0%&!L8dlZgoHo;yg(E7>N5%3w}Hzg}3ZT7S~HwH74XM z@!_@VDt_cRZInYz;i{F3d~Epl^ZJF$Sb1*{oe0Pq*rBU-R&-yC87ox~(5IU!!Lm|P zkUV%`1qL+Uglmnl`j8&uHAm*Vm*`n?5P<8#9QSkR6|>AozI#Gg+U8?X9~bwD#D<*1 zqSL3~b~J0x+&*FTs6>X%`h$BRkPn&bQ@-*#5Ut8a-v7H7Uo`~Rrw7tD9RG-D_M1OG zXqX47vrOV+F0*4fJ#L-r*2>AHTI#vwDY`@*RWVyjC(egWCCVriGz6D#X6kP#@8N-Q~?*0B;o({lqN;&SRrouTDgi-{8QIinV29i zwY?vcO)z^}zPvx0eo3HsIVO zj6B>)ZhI}K(K-CfK3X-f&NGor->xLahXv=LfWn8+Bm0+#oBwk8%2P(WJ|awYw6R`X zZY3cq{K#peXXpa~oOQ9r=GKus8yffY5N*}Jmz9&LNhSSsxKY|Z+2trF3|HzsQkDsG z@$^jPbQ{!1f^C6)$IN}Lc>RF zWKqw>WQ7X?4;3JV^w%OTuBU(hOMpa?suD9r5#AfVm|ftzOZMEnV!!VR;fm*RkL|B zg@W+U=3)8%{3$+}b`J*42Rpt$f5Ly+imDH8U;X{ZR&2EKE9u@J2lEq3bcwG%g2oM& zw&0R8sjqRs@7rk@w$Q*t#{OrV`sEWKL1zQ;`FCSw#udH4yE*=S z#~D&r@g0lncPyu$)qERiDpdMNK?;B}{gOX9n|z>+jN2`*<{#7U-&?$^AC>%`w|pH98L{;r*hADL6f~J_;Nr_ zHSz@`ObZ@YB1#{Ha@a73UjOExpYTWkdhRBhjdk|aNqs1;{?>bdYR3i1VAbVHh5;$y z?QmQB>s5HDyF|o(2SBc#O-I66O-Q?QFGj1D@{iltMu+wYh6e5tW>Ri{EJlntWTQj> zup>xJ)lzz#yK6&Vzc=iUTF9UVq_EKsQF%xFC|#cJy?k)+9rPy!v(WHp46bnL#}81F zs#9mO5)^$ZQY9J~oLC&*dfI#1F20Odx<|Xs(;shz%nzTO*Vp|~ z1F1}NByB!l{_xsy_-*2lBnb0O5W|Al0aDWXJN>+#VD%afHt3UV@j`6Cj(GkK^kVa3 z3J=NZ&mHonT5GDmKa$hT|I6R7a+W-MPqA5!nznlw#qwRIv= zW05W|vHgiN>AdpOvS!W)TQSyA=*j-i7a8aC2J}LT>g4<=?y84u`yJXLiqsfq<->^N z`3fOi2|uqmJZZ?j9Qbe&O0z}gyHR#qlX2+S;a{k;e7wMfk>oZ=3x}>bZ5=}an^Mon zz%>i3?jks3z+~rcn%+Ftrzv^4&kw#~`RHW<>=!r&5D zdd*er@i%1WLskJSa_9~b7)$jYr}qibKYO(LBJ+V3wnkNcdt8Gf*6D_LV`_C$!=hQ;fNEQ zh2h`z{G#Mm>5PEoc@|0Vfx&(Sv~}Ki$40jvJmtc1qE6KrJC1z_kM8zE2&eL?KYJ&k zF~XGBfV!&D9=o+i4qd64T3&Y6dYD3R6YN}!nYF_Z9lMQMp9L0s>hj9@3?d1~dmT{* zvud?_dV|(?4p04MLq3@Zq!PYnkW3n%(6#O_4CSiHxkawPbc&@hv*MoJ=UASZiU|L} z3>a`Yfjm|X_CbeF5)WI%$|g6{-Ph<*A|c5Lg(G( z#K<;1Y zJDzXYi2?ZqxF@)}9WrCq=QpD>^^%0zmLm?idA~G|r}Bkvucjoi^7M${&btwQO0r3R zx~Uw5wElh>805c9%Bdg!N2vnrS#no>2|tk%fxT`hr>&kA-Iq#R3X23liO?@YYm2rH zk(QvAh=k5Ak1ZS(A_haR?l42=k&*AX!2D*Hs4U+m(TO%&4wIKlc>Knff`)lm21iEm zkx8HzSB|A!YJ~c=a!58rw9Qg9zxSQ5k^h?F2d(PTzO34S&R7}?991gg5#0Qp5u5t@ z%W&B{2aKQCgB4(i$^_7KXV~cAO;p|R5Uu-;)lKC<79?9`1xMBS6P!n+vVRaq zhoD2sfQfkEdXi>ZO~~la$*uZ0l=x;jYlBN8BWWme=|_59Z3f(%x1$lJjspb9UlAZ< zLpk&C3eL{^jT`bQBd7m-)OFrPyh24Ztd<|1m#iq%+v9^|l=aso zpF(s1`Gt_cv0Hb!{&svgB4}Q2z-QyO7y-L@2+N+~Qk1IKRkPL()tP)=)BlIBGg(@d zO{44uF`yHWAvS=hG=iYaXho#&1g^fe-^t8~im0f_Q8w}CIjFqNv-euqsfXU(>Equ_ zW*>S}pTmcwQNS;G32cppCY3S0}}u?dQo9jJD}BO1#`hUvstn@>(+?peGSGykB^OwgO~}t?Wd*z%P#T zoM}L`&CwH;ifX^3t2wZb`f+DJJD5!IzW=e{66JEkZ^nP{e1G|bzI+l}PjJrmX)uZF zn4Q?Cm1_U<>*A0&|8m5C+z9j_;S}_81iQbUdJV|wD$pD2a~J&qK={@g{N}G;TKyC*Y9)op_1c)KYQ(NPr|=v%hR9 z_Hg?@hLf-G88@U*Pl4AIp}4E+H^@z96MC6HciZO9ho2TC?{8TYl!!^X|NTzWSoP{X zG*`pmQY_JL7%RGHIZ6DyyM9gVSBhpyX~MvArxmIDG6Row0M zFg7+Bu70*J11^)(r-9)0Wu>r-K>Y)g1!PLp;}JQ#h2hm-Sm(o!xn)oH&kG>j|DQ`z zI8)?{OpHJ!a8ndpnsmH54nRdYGQkJ658!h23HTC~t)TtXms{R8 zzvq<0`*M<`h`z{TDLRR>5<+d3bJVTA5;h)<{SLSjBglMUYERq1ez0n&0yFb(-iO=L zQlti1nksXWdGqIdpkP2Lnt20sO-<8TiY#KTC)Rf1srNm+%v%z%z}`C~$=$ij=jVHi zWvkg~A0DP=ooYuat69Jz@s7In=oC{)LTQI~zh}8laIK(ESPQO;GfZ7@tb#UencZWW zEtyHanm=?2$DJ$;+Ko&st+%ZYy)#l?2z1JDzaOLxLN${;EDhVyzuXA>E#Dcfj z;4Ij(ysibu;oebqzQb}QkhFfhU(PbJwTc~FXSAz=@m&_4el?+>si07j_luvbm}xXy zsJB{sbC9EES2w@@QBUDhYRGN1c{qp_8o!Q-wP`}2_Ys#zXE(!F6d7ZRGiyqRNAwa} z1P8dbo6*qWEHemx^_Cnd@*aJ6>7(3}j*33)U>i!+QT7(BfEhkGE(JXjPBuQTDr;|#e>u}!2yhS&A_WyEhN?*w! ziF?FUH>TH@ltw!+KTi!r7?fomw>N#@)}Dh9j$(_?J+e+8A|`k9Z%zFLalFF~cu=2= zkN%_oL_=w7z7Dr5o=v2OGqY9{oDjR;d<&+=|ID{;_(gv8r+JRQv{~A_Pnvmxpg}5- z#fy6dmkibXuD1}ELyE1yOy{OKArXIUZ?976xS<9S_vYwPiT}+k5@nE5k}U`;0g=S5 zZ@s%~+ZIp<2gU-9Q}T-m|2zJdQCD_&%eeSKa8RsD}_7$%VcA*6yFr-I7st6T&gLRkW}< zN2lJX_6{cYrd4RO0f~@pMugr6y4ZdPRjvvt%bl%%?1&xJM1gw5cG*Cmm6E<_>^vpZ z_a>@Vmh+AEzM6iTMIno~$PF+k11J}H4IpOMfP{QMERjq%(lFA)J7^t`km8z|q}D4h zy1)v>O~Eng=n?bIm!i*bs(;*?j5H|!Qe1db*Ojr~A1+tCH-DeW!TcPop&x8<`D4V^ zQidCQ6SLgrQ04glcS_$-JzkvfD4HVbgfTndp9XJ(sr4!Ns zMvnRZs25TI?&>mWk5|{Y?{SenNr`h3fu}HeyXClin<=|w>_`5%_oY4_AFue(SZ2>$ zelDu}cLpZV%s&X?ZLWgcJn}w!>iZdoxx)gu6AqFDX8+x}0Vo>e%g=?q_YrHVW#Qk- zmNnY<&ryi3JARKLF8*;c%+7@`>)!;5hRNkthQA%zM!;psMcsY3o59);f}=ehbb?-S zd1Vhhu91@PbqgU{t>e>gZjKQL-l0G+rhW_J91j}jDYGc&P~ zg)0lJVHV<#Z4AZ)dYLq$?Vo|0Z(_xty5MtrSig%|Vy_s_2ZCO*36jm{HNF>knD<9I_gB9Gu5TVQML4~z z^>;_n{5%2=n~1Mhg_z`oT5bnp-u~V(#_t^?+coX9n$8#EFGKB0Ff}Y}rDNds1}6va zp7i?$FIfh9yYCm;z@0B#F$aQZ{T6<_WdHOqL1sKKTP4;&l;ZVh?y=-7uQUf&{2`2ZUZGF>@?#IYq$toU) zKNVIPnOTU`i4u#Bg6Kr0D|Qn&VYa*9os(9umXQQY`ge$Ni7pjIc-3CkXHS zJk~Zxb@F+^gq3Atu&9V(wkNB%Ru|*$?jby(gTSOu={$>V($jN$RV%qkobB*(!7|9$ z)N791{J0xvj_dWwuj{+s^Cw+y7-x9AU3kJc!8CDMuWLCA0!)SHHIs|=20QnNk+T(# zf^a)r6GFVI4MHs8VZlvA3{Kmp$>yE(Jp?HO&n^8K4ZLaG>m7b_hc zZNun1?z}tEN7K(gP8R#5FmgJHhWqZ$7xB(YgMNOVvg#@R_A=^kFC+OEnU}$ZUnfd_2brn0F<;(tP~Pe$PX{_k-JF^O)dW+>nFdUpI$6 zMsKLjr-wn0&-(d9<5U5DtFsj>e5n=;Xs(aj%?;e_v|YIi3buLhdenudJEQq@HG;-5 z2>O^l)k!;Qz^b-RU$JYtDtbNa$FI{T#PNRj3781H#C@0BrTx00w0^&NGwu{V;8J>S zuAiq~FGY2x;%4lkyE!CX{SG$cn_ko_S|sns2+Sek04R%BhGKqjQi#*Y`1@XZYf5i4 zAzZ$p=$3}dr_XacF5Q){5yN&@HtMB?xd|f?F?aWOhcf$!@ZUv8rYui=>8H(?nCBYO znlqCfX9^W!tY;>ejE+L9Nqeve zai_+H=&Xc7B_woz6$tU~{wTd(x|jZ*yV{8e0QKKEl|62NgdHg3caP>B&PX5X!am^K zK)Y-9!1Wv2_d}6&>i0)M4+eRSx8z`Ylsg#;;^#$bIqQU9`lK|c8*-Epz>0o2W%KN! z_c3rDn!{gVY@6%e@`DU*T)e3HusLM;<>C+zqnYjR#{tR=7qXr{AiIj%vGNK}jVg*f zy$P+W*`G*6Odgj0I|68Vcr$~#ST)~wUGL$)W~`~pqs5EqMruE2K-r(w*>D|FS4c1| zSd*0kLj?g68>3&=;}k#Q_1>8yXR7Sd2L7DQIhw@(arqo}Wy)3@9@<}rpWRqE%v?C0 zboUME`4hDOW%1rN>j_L1ie-m_c%LQ@tj6d474EmsG~1NVSIssVp3PaJt+u;`V{{js z^-`sg>|D>kv&0*~ZGdm2O%84HR&3~lcE2(ywQ4>0C{oK+21_3_28c5f__jqP5Z#QB zBl^7cQG)rRs1=n^Qr~8F@t}M@@0Z8i^y+pw(F#JYbRysm53`~@y)c_Ig!KRTcXY}` zw<+*D&~;NorwkeE;O~~T{|@kACCOB|`{?K-ooz@Q} z$~sS&cOs9lDV<_x-~0Uv$NWi<8-LWfa2IRRDxne`soRghA7f4Yx`e^TMNGXMyT)pWiWLD@awtl)4_<(XEa1a?beusqKhj` z0>#a{RRgSlclAC4cX7LzTdx!?dfb|uOEu&{YclhpFk*`*5G?WB=VicmhJpr0EKlf@ zaJW!k(_f}*kzem8pQ4qJOFxEHkhFlYPpx-0c_*9p?o@P&6)6Lyj43~YaP=OHrGjeu zNZXqws?QcHd1dB=%7x0V{z+EOXwfn3fVk$yv7%pIuTGtf zySp}@T(#>5pUb$`uO)g}I@qcXwwpWj>29fq9UYUlDr?ygGQ%IciZ^89&e8i1rawnM zy!P?4tBSiQF}`CFZ$9Gv?WTU0R)DZ{TNewGd04=-eE(!(qjOja_k#W!yiGdB8GAy> z(ykfe(g{aX#Qf$aqR-M8N;qtRXRsnn7Kx820MAX4Gs9E*8(Alj#lVdMa3jRgQK=rW z!_%5^*gt5IBF{*p<(oxYA#m_%%wgJ_bUPQ`MXwuSp{FRdI1yWhea8At_f{bl{FWom zg{n{S1g|Y$>Bj^)1Dz1wz=l}^=;n7p3ZHblcoExgQSC1^>;v~LRHCa!s^cG&LJ;RCxhPz62HYRWL;M(qvEvJ2hW#S5OK7wx_+5N3)77kL7E;XhP2aVs9 z?^ke6wx>hv5N7o@YzYTkv>ffcDq1(dsZ!ryan1!vL=q7b+RAbAO9;@L0)3M zZY)@E72?lAlAQq}D+3qu4M9KPUg73u!j^omYSacK>-swek_HZhc59z*uE0G%30(&S zGkJ2PVEoRQx9ZZVicz?!igsbj&;z*}d*+N8X9q+)1`|9X>;~cc`SC;R-~k;NDcsS2 z(zW!^zNPCk!fuDWEob_b#bg|<$e93^x@^)N=36p!(SPSZ2)Pc=eup*iSqB)J<)?F( z?XxJu%?;^Y4t3{Wk@onx7&p^b&@kF`;Nx`{lm(u<-RVGI<{{-N_v6rLe6Yht^pR@^ zA(xrLPJlD~*XPkC=_!KADIR_&@4q`^ip-sjw3R~SEG%Z-9wl_(m1tk8_w;w)Pwo6& zuEWBSxBW}l?*j=T9tgEzdleGKF{CfNo6q)Cy|y17v$VIizb`R>l+MXa)y*MQXPgOW z{4IkSbZVrH19l@ueX7LF_Km)F_3P82Yq+ECYuF5r=!O!u_Y4l1*c~^UgQDJ{n`ZqJ zegf+!mq}&;oDEO{Ig%&mX#HmN+b;iQLwgMSLGxLwUtj!#uO$u(mR8uO1J1(ealWfG zy}M@+wjO!~#y3@uCmOtn;i364#5B1r4Bze+4KyA9dyebCZ}WA0$kyAH^Bawup-VU# z8v-5t+S@jr1Lxt_pXBAw|K~o!@WPZ#fy-$k)~@6RGcE50IEm4_2Wu%S--#vHKJwnC zt!|`4(GbX)+N&oY>(e^_x&WUHBn+_n51{sQI9XQM9g3)8$nuM+A?lk{E$x*3_82&G zafH4M(8AT9a%)0XF?ns$t@@1u4Qoms?6lS5gp56&-rxN@+oWfYKJZ&=pKw(`gkjvA zT8sj5Z)%@Hr8}wH{cXcg8?3Wkum^6&)RW(D>CYRP##c6Mt6hvd(68`?^+eiSzNJ0B z1=fOtRYzdS|~Ua?1Y zrh@--@(MjVP{8zwEC>P6ccU&?8Vnk!ZS(s<9=*QQBM8SzbajT9GJh^d*=dX}C#v}S zIMra{z!qo)*tX&Xj=V05yz2SGUtZXX3+7YqR0el7)`~1n@=C?sNW8z->U%3xL45mA zt{gI{y&V!1(zc!=JgH4Aa4e^YN?3kA6cV+>SBLvIU#b?n7<&|@jaCoL*2eD{1%3~{mhZGJfOglY)nX^v0q(Ug>PkW8B+%UqQ^mc~t87dOMwIQW_4I!oOpgr;s^zskLHV+o=1w&=?%eA8su;FuS z$#&%Fw8MQA4V57Rr^`41$nivgRqX;^gNX?Jt#gQqM}O!Z#>fe;A%5;&t~%ke-ais- z(z6=;XvVGZ!MUIUS6llyWN~bt%zTjE#I2}R12J%|Mi#HSy4j_C6HoprrhpdVU$_Ua zsIO9e8TBmpng^z^bzcnZYQ&>6lMxtGS)gmr)C9oNuhac^eUKS`*8u0azq_0;%b(71 z8;)2l<cKug`gG7fhOh6`ZR#x(QT74` zxnTP;_eUzqHuDL1hxW3PEBifg*T_X0NC4-<8zbn;K}Gh;eCTF33&g>J5`sayQNypm z$_olm)?>d{Q1d{yWZt;&7yAzJXLv@8gXe8>HQx_fq5bgeqRfH4{m) zK?vG`es(R3NZ*)u`HSVExmhORz+A3*zm zZ~^}~+@oR(0K!eVp?*wQZ_N}kd59Qyp2mfIr;e*ds%VL_djyYNw3Zi{T~k0-RZ8=3 zRC;@eBG4u?It!DFnGfI?cOE#1Y>S?*mwil?$sEwMn~tI^+r%&7$$kq0+_Is`F5J*Q z-MYTuecJuKPp{}ra6E3zXNa?B^gi>rs%N5OYMB!57M~!*jXwbigh2Cr$K;P|1Uml7 zM%~DAhX;bsAqiy6Zl8Vwjn?nVC*W2@`V?Fw+3;6sb5<=(<3ev{f%r8HdQE{xq`U3x zdWYGA>iKY)B%i$s90QiqY&M$sW5B0ZO&7iu!Ty|4dD@D=_tADo z+_y{Z6!2HZyZdI!KCnLg^F=eXvToNLcSbv>JJ(=Wwf#;u+ni_z$JSLP8_oi1rdi|x zyFXHSD;@{hcNmmo%G*`>e?6ytAzTi3?pQ2AxOIhM--hVm_4hY~!M~Z!lNPv4mPs1B zT$?9wY&e34Uf(1`)4HRFtLPqx;UV7qV4$S>+qrMgeK zy+F}$ThBv^aF2LI_L20eMuTEKC%}oj9JZNs=I}D?Pu0=JsL4E?AT8Cc{(8A{Y*nWRlOq@y(s_Ezi-5LF-WldDqojZmJ!v+4( zMME8ZwIN-KvQG*g$L%MWF`?8#t^+>QvG&&YGZ_>417(;VEE7wgC-KKXwVub~WeWU= z`wLn^Cru73%zs{8jntyNXy@Apb1J<&$+!=CzkL)7*o9NGiRD54mRFH` zoHpv|U^@jAB|qOyu=W!*#^6wmp}UL4>AGuI z8LQ1^axZk?u0UOa(_m-V*1d*p`b8V1I1PmdjhRE-*knuG+zIU7_b`iw!?h+TI0YI1 za?qqmCRG%xZcGX)OPZQuW!nC>E3mgwj<5axaFZYM-jeFZZHu#L&aQkn>iuIHERRhl z+8qaW@Y_q^)$R4+?EpMGgEA0Y++>F&?ColOFn@h3dv7Q0PNy=hM9WTfczP?`idU;v z72*TUmcvX%Wmp;_Y}`(nu4FL+=bk9j;~8j_Sv^k65T*NO?1#~jpYzxVAnX(_9lAWO zcEW?c4Tp)rUd=t&H)tdK5HQo`#C0b2Vg7>H_~~oye`N53j#+DEz1b|!rww;HJl`*b}LG0dpeO&ie3~(cszgi)wZhM`RR~eXjPGuxX{v=VeeD0 zOP|9qVbF33$nc?HT=XIE8%KO=+LnUKM}8SXOX)t57O-~oT5nmaTMrK!ocp=m8J$w( zalf@SCCWh|5#NHdJ2f1x+Q4c{PQ4-9l6J7ksp(Wzj8%MZm`qLYy6pqc6H=U!GJP#h zK;oL%E_3k~vWv9j(3p0=o+#Y)MhDK7zV%h!_-{HH^Qv`H^XgoPvXY`PSU|y^}EO6gpA{@ zjrYRq`#G=8{k6BrQN2K@RXy2p+7rg@(?bKe_7 zQ_L{xM5fx`D4Wgo8ecmtKYySo((pMG&YG`HtNJ7^>sNdo^CIKo>9`S~BtH>2K_FBU z#ME~}EhP?+Qmg#8>?aR)J+`XlTreuVBCMP6h~vTpQA?&~oC0>MNS~u9x{XUK2E;pz zc**G;TW{bsbb-V*3i{HPkS>=}!)xr-F+Y`-_Vk^hK3|-QrIHtRp5IX=j zA36|L_L>U{H@wr4w+mOSzcr2-(Uf3S;IkmPmn}-B1dCN}>3`qPh6C9VH{T2!x={y` zT}uf=2r8H$aW_a6_piuG+1~@)-BH05JxqCFFfXS5+^`{??)wH7?kZvM1)icjxE2gO zl5w|3+gcb%SU7ofOfH6j021Hft@G`+4mJ6;C8yTJGvm1UNOu2JNJB5K>{lvGq;k zqas#HFZc6P1+ub$Y5;M7-GDX&(p&4!lE`VBti;W~pxq$QW698LoX6iB+539*d@Pv* z?k1x{)l6&}oVMg7OpFkrq-xEQuN;AA4vY3aFexO8=?mJwKuyN~Wp}XPj@Zfar zSFoEP&y+J8l3Ti12>6j84U|4Ae#a7k0G~J{u(YgWC8Uz8BR9KW!s(*+8aIsl>Q!4j z>NvvCxCyq*EGyExYI#>G92YXlBRMDlT3l!ipHqTgruApIsz@*$5jEq__O`l{B=^}K z`8qg1_$n3~G9np|1+b0Jlotr*0%h*drE;IeC9@?|KHQ!lB7}MGvR4%7TV(4bB6*70nck@ywgnwon%k|YDUwDO-bSu z+ya9Q#e^+u_p*+P=sA_eMpf{}PO>V6iqXp{Rzyjb@L%i?_5|OZQm~$uaPMz$7Dcuf zN``s75H~205@=dSj}Hsr7zGk3x&6sO&y}7ZMcvnEzwfgyrCY9b*<{?lzHkK`UwwDs zgWZa1Qei&8*GB>aMWiX=1_;*``l?Y46wfX339H=sP_H%vN}6pX)!e@if^KhEdFj`> zX+I?PDX&_n>kUm_Qn~Qw{?e*%X6~kA^xj;ei)@0qJbXry%i{x7PnV!`T@4T&s3nfn zzLHy`Ifslv15U@kV|zG$z)_p0(<8ndaG|TRtDE&Wg6*9V{O38S>e| z+{wihC3Y_&nTY%%*!lE^ZJDH>MY-3T)I78r_hwvihKCiQy`33_{W1$}k1+u(<*o~@ zk}J`*0n2*Lu8-1b4_ly!c;bQu?N`&so_9`f0p;c*{Pf|I_m>Fpy7BdW^yFQryDJmw zlN;oLNxQ`p)B=w;4L|V(|8a<;(UM+ng?GpiHY&UcT%6C;$HVWqCp!dYteq%IkE`=p zYrgqDI1Svl47~?M4H%sq=Zjl$8Q?{BbSm{CRyVFYwU<4eACsv@V&manMsnzKtq}QD z;P+!mdZXAmwY9JM;`~rvUtIqDe$0iq*Iu%5ImS2@I>;ECtUcTe4T6&fajCr^_i{Bn zpMh}B^M&%OV6g!@6Q$!vt~l5?Wl%}dO?vCV-Fc}_1kHBc(0e!NDojY2hIN?>wK3s~ z%-8jdEk@{0v8f+=>3oQUD}l){b_R?9hMzmIMlOW(h*lAV!&Oc&6^UCTu3N{_gr9yo zh%s5ub@Ippnmr4~)P***E!(NUY0W+pe$YXSp}ujMcb5V z!5mmVG9ptf#(XVX{eyP?H=6sQpA4huh;&PT0JYYp)022zoximVOp`>g*Bzof>vy|W z!`uo7Pzs9!L9M$n@?_t;=3A*%wY7rOYM|{qOXBa|9q$;BGBQt%n8fgn?&diA?}ipp zLu!*gz0Uh+E+3c`C+L3K=!GFE(&M+rQ`hjjEiw0x8ffL$s4SkV8!bk7kRe2U3)bej zT-jxK4bGcX7G0TY@y?r64yLiZ8acl`X~Q}@%a%WsLpOb!U=2Mjr%!Sg=Qu8MqS|MK zHE@i6WCYOhEVneXNncBT%a+mT+EtD3TJzgT_3G6xdRUTJ8}_R!@S!x-OQy9g9oZ z**}GM^Oe%YT*1X*{4Eoxnd*=ovDS4UeWA3t21B{YP$xz7ZnIA4j#ldg1`pMXbD?}0^GfPm zmAL(AMN5RdyR^%nQWgj7y$&qFK-zyDbNL$&HnP zS1N>T@Dt*^!nf?YuJw)MA|EN6?E;9bz}#D=ZR?6RO1K0LsZf?-K)2R+e4as5d*7lZ zl9uNdaf#j6+ke?KjTlw8dw4Eew72z0Jl`sD+EHbH=NNpaj{3&K4L|t^`MpkmttU3Z z`XR(w%jHTp1PdXdT8-7Sk0Q3plHJDzHxkKxBQ(%VCm(c{bGt%)%H)`BI~&P~p!ZNZ zNjG;43q!zz?)pxTt#X|xtLIkr=$y36{bflK6qLuWj)2N-JwdZh`@u{QE)YJJF4MP~ zsqJ0X4`(H%MDBvc8e82rc26S`f_Ij{#A5{fn^E|6Z3}(aH8UHYkyja@Pm`7MuRL4ub-B<)A&W|&wzM#G= z*Zfi3i2K~FZqJcM8Ub-nfEugedu$YrqRe6D{-B0^L5a^V5@hJ|I_d?CM^XQCg z%nPUI5_a?XD@ia8eL*zq-Wpx3^^9j1UMvA8if)=S@tkQsMsLmdR*_|X@J7Q0(OY;< zd8T*#avWY6;*n8>WCtK__8p6JX&C0g$=k$6Wx*FjY|6n;88Mt6X6J%$*S}{6Tned` z72aiM%NsLGvi2$yqX191!Jw5$Z%|xkuPsl{+p_!Ur+~q)!C9H{-}B+OsGC(gc!;ZW z0b5?!q9fJY-*Lfz9D$;B6z36oPK0Niw6KzE^f~4CtUIsPJ4BJ~#o4fOcyU4^`9mp2 zK2GqF1`B%rEq{Tk#qkN8G9-Hs?l>NW58R=1xgHAs`+XN+3x7^uaHq4ozI}H=hh&0; zT8=E774a#mL>gd`T5%V^5$>mKHqDWzuD_qDMD||59MVml74HT*@R-VHiZ_%G-@iEe zz1|*s(&$&FaOtwTom*5-)m!NJq_nqh zM@a(fquS!$XP2kkI#T!u|IVaH$za4wX6kk7_u+L7D(*?e`aRpU@YynVoy(iMRuCe9 zICUAA+=Meafp6ub2ag^$I~+FCtf6)N$GS;D_v}xIP?4YR8Qb-TVfK}G$Z83od)zba zuQyrrcH0vBWM^b-qStQ>H2|!~UOKEFK8@@50DE@MbLA$qZ{dXO1z|%ew~{@WYL>9g zre-77E&&S1rQ|N-!d(y7_a)BCC3(iUxDaia=}yl16u?H z6z1E8qgsd(an5U}s_YIfHcdNIXfIgTaHEbFnRISa6q7A+= z;g;1yif6L{hizs%#paf#Z0u}Fg2dGzxfxztX?x$R z`vJ8^?3B=z_PVLC4=cgmy1Sv>#j>Fj)&2%sXSClMT&suiUAnkJ%F{f;eo7yEksa{D ziS*X+P5qrIdunA#aFzv~-~y^r3Iw;7;_ebFmk_5CYMZ#hds`SyC+so~ubb1Zv?}&h zF`j{uT^fNdo#+{~VGs%8{h;oE5aArWh@SYzOLx-!XPY>jQdjhRx&`+k@4Fw}t z?>E?O9#+G?vPE<{!Us0Ae}B7|-g>g^KY;;)B~yT#Sn{mebKkgPF}zNn+u+Rxw`29G z-*;ZS<7My$j1t}HtNFn62yb#ELp--&x(D{!NtJ$LEy)6ZL|k2%EnHX>{CeG9;Zl>= z{cCSsu9-P$$8&!_fgmRwl~TkXCtyRH%Y7^%7cSoA6*LL{=8#omH=CW9YnGb*{zBVg zL|U~DZ(E5y27jN?aUR7}_`yG(SC)}v`3U>861uhnuUL=qtv$}SV?#eb-1L5BvxBP` zY<(yc2L_PipI?F;zgWHpsaIYtJ_khzhrWAIWrN~WTb@e#D!r83E*;N0a`SFy@Z8f* zlf3f$=XvCEc@PA*;8;IY@uM0?zN$Qv#-#d#gYH$}fe9yF?;Z+t4)wtJF|tAZ9wKf^ zc$`_^k=N$>Vo$%jF$bUkP{``zK?I?PI4R`d+X*_1W4I27$G3$^6EJ+Vogl1*R5INH zWSRshuSebSAkE=Q8LPP=kaK6e@cJn4pc4~9%nIw(l9kW^fXh|Atw^}qZus{e+2cJD z@(6|R_JMxW^z(5;8JyI4-8VkFNCg11R=RHvSCSMo4j51+bv>U4H%_zaiir6kL#a5lwV?jpcNx8$eAIb1-V8gd+)dDDhQbS=Ixzuz>`Q>%*Es0{6{ zz7@B?tXCJ&Yul_*O-c`)w^d)@>-i3d8`qFXZX%Zhsw~!MT%MxEyz{2`-Omx@ zMhfGRkT>R2y6!H*`M4i;$MZ$G`2KFx*63TlQSQAB3WgfZV_V+JXp2^?JE!W`w%cf_*q^VaT`}`q16ua`G-j`n!W03 zS20|f{luLD)hv09QF2P0r=;y#UY2&>I-@@flqsDNUQWKEM0A7=z&qI9yX4*$H^kY7 z6ZKjj7W#LN(TEBVHz2HBpKtLnF1*H?zd3^6Pv!vJ?hvep^|+AN;{1BRtNWk#z&_11 zvb|XyQk}do+@wo8T<$8q>q35$;H_VbBg8hE#N%|&Obt=u^+*5d>xdo#4*%byxOu0set4&* z=XA)E0DZYDHn_{R&b@^%%8Awh2QQz6@b^Adqtz*HWit&SRE(V=${W^_Uvcf5-;IKD zYuS1HnI_$A5fo%Ru?@spcdM<_i;Fyd2`)aj|0FthB_F1!x6JL;J3)neb<|$qVr+4- z57u&fUT@&CVnk(_zdtjat?4!tw9kFM?AaGxW>4uQI~o1BlSLq8F8-Y3sxRvm4nI!x z<1JG%6X}BaywlwOF-j}&U_ch3 zVfC5TXM?n9+fCC{3?0pL?$c8;?L#D;QaMe9K)~yu%{Up#uszIM?B6b!?_K<7Axc0u zZAiV(s?VZ!;i#oe+w9u-*Ftub)jAmCw(u> zwMjIEhN{PSz@U0h%Z)0;!Xr@g{>l)&OFz|#i3h5uB4(Lx(;L?qP$xFR+#izMWdIS7 z?k`GsZ7)})8re(5e`k`QjCLN8N_Zf_pe3EtY_=Zc^YxFn>AkiDahCA!*ZOXMcG}s5 zIY_TpWmy>cS#Oj^c&*F5J}+(C$pNi~SFJhk&=O*j<$k#m$@&q~^Ze zZ}!m*;tnEl>Pz0i_e`csc8f=<|5d)A9cRAMEA@};k0u+%=yZGIreKTX+2F;^^K^bZ zgwp!EKX8dFOCJGDB1)0DXuI$9WcS#BB$v5Ke4`4@>EoN|=7vV-KUQ^4xo-LDExUxT z{Vj=kwC}<7gfPz}ndXl}n?4ZQ?|4=xA;ydm1AhS3K8^Qdp}nIG$IY{jPuz`&@Cup= z98?+x9u21}Psa1U&Er*^`(c)HIDa_SJm;8^(vh7Xo;p-k->6AKI6IxOlsC=iF>fd* za8R$^8K2{BJb7rFd`fmmMcjES2}i>w6Y%PRfGe*NCC}YCYvJ zgW`6b$$Yg4a>~JyR`c74UZ8CzH_Nl;qvovQlz=>DtQ!t|ByFSFxdw%Wj}jr?<#+$& zA2%kx-vAPtzuDu`({xgjaa>@JksI+xt!|j>XJ9T&A-$1oEG5qU#o{+Tj>yL6>%;5c zW4zsDPlmGJv2@rXk|OG0nOKm8EV%@#94HIpCt|3voEA|ybXj!7Z|`efMfVz9mEbx* zx51H&Ct$?}*DH|lgnfgx1QEOm4&2a|YP}0j+z+2a*N5HZdGEfqe2y>-aRTpP9#^vh zl%HyO&2qQkTmF8tM_@0DaT$&YCv%h!UbbB0u)S4_^10^GBwgMJsv&PYu@91dV^IPY!W*vNAdTkh1CWgzdRNRYb!wa22I@F?$Qzd#CZIDJ*nC1< zFs`&Mqx(+BYf;t#R&TdJN`78?a2xgpo3c2=ZdOa{Eno3DlR6fD9kxY2&^xfu*Z5db z<+mxp)4Etsz7dJW{+vyW!*i3`?uq$tAM3+VZZ9XfKM=F89?+0?^{@sb3kNS$rye|W z$>y{fu|IfQI%GasP3nzUEOJDs8#t?cW%u#k#8nYt+>v5TKLXb<$SAri3KrjcoOrJT zbqP%G4xFv-Oz*w}Smc(Z32%WIcX)?S|Gk-%f~m?^e!r3MMH<$qLGd&bC4GwBwUU%6 zTAB&5jFUGptT(3yFA#Vo?GXpy-EMl#VcZ!r{07PFwc5AMhXK9QBut*^WJaXSv4Rf- zT>i$U_5M17@2&G|`8htJCO)lO7WYYq-9sV=<{t0r6Sev1f#C9yX^a?y9U3pHcHh|0 z;Uq4o8tPOWyv%DyOaeNQXX~lpc&xu~Gb6mo2EJE^HxYQeu`Y)b0wXBxDY?#B7Jm4! z%uJLOulKXCLEAjuZte4eJ0atUHz9gtI5M1YMLh@;gLw~VNevk9dqYtbzJq-0Sby=O zb7KN~k3~dsbYJNxVioGlyCcR|o0ys&>A3*@f{ogCjt!_?w%t{oY1^~SM<`2q%i9n4 z?vuib(UYDA8?#Wuj$;@l7#xRqcTQFLLV`%i81))5Y4c>TryKpPEb|)K`m~(}@r<%> zkJr#}ji-{W@IToIiA7KQmqRb-vsup^CeA4QZieT@m5)J=(#=i@p@R_Pw=wFPK51%g z@V6irwgU#N%<%0o=%DWJ@v$Fp?wBi-uP|6@D3lhV*=apgyoiY$ajmYBmu~lzC8DB8 z8hE8Uy|cgWJvbH!)47zqyHt<p zLOC2tl;XG4_i{&@*n-n6T$|b%@4F9?Uh;DFM|iBB2;f^$*#|ilxNtvfsQur9YVYX4U zPC!g>!3eU4UBRDkK+ETn>S<=I8RQ!XG8NHHSF`T$j*=b z#T7OJ&tr$N5XKc7lRk{E4XAvcK8Y-B?!J5}hz(hVAEVu@FSQ)CJG)J30Ez#eD@^FW z=lVvdF-A!UP?%*iJq7m&RP-%mrTy>#y&cLn%ib25iUj99v4|v1uKfkaSgsT(icSx#M)Pa zWId}17@T;9yOUgT*}zl6!Ey9oR_GzdL7cy>(J4h6X@sGv^ zNZkP3`SsQ=x8J)&W_q$vxa7%0u>M%`&xf5O>6V>&i+8al-5scISA zP=sBc?LJIo=xSHLWT~etebg2rNO&3PjyllKPHRLh+t8?L|FQvgsybeC?l*8Y5vM99 zr#n-k?)_vQxcddV@*^Ppw#U|hHFgwENLK;tI__k=_C8hBIfvp}?q-+3eCK|fUO=Gp zPGepn-KDyZx;sg%=3A=Wu`FaY<2F&yUj{@JnQB@Jq+>QN55Y-g-FH+gNr%c%K}_4@0s?nt zMK_F~_3BB5AX?LG;$vNGX^u)?xQCgc4S}~^j0RmU&4#X@xD3WE5ch($5TtbZUp93r zd~{*`{WCwT4<{S%5*Z2z42*iyPlcL{OV&gbPQJT{cO?m}zLLY|MHO#j8Z!qyqufyK zYa)^k?tTn{&aptyP$y&bj_a5)-yha?f^`xlw<_$kPhYPO2saO5UjPBwNN4*JUl?Wd z+zr;=ld?Tm$Z^7=%Zo0$6SS;f+V+}kw`<3*?$$DsC%YI)<;UK(rjJMh52tJ+A0-hF zXeYfVotL)0bUNqqFE{&}FAVq=JVByT-ny-ev{D0Vclb_l3G)*XrrVI6CEdfJRlO`n8V>19br4%lrEmb4$o6WxK%<(G&Crew>KaGQZEofNYDs&y&s9+EI&$!2gRuuAOf)p)W zB8YJ&+3|9Wjzxe9C{xAz7 z+?+Rac_(ul3KO<%QG_4W)Iyj=kNFLK@{87E9CedY@hqaw5HLzPF@;z!qxEa=jFet& zYT(Vtwk2Ue-#CA8fVA!Qy02$z!(CNdhwy_|=vRfZ_JJTj%cHl=T_ zN@=o)yaiXEp>i|lH!F3gEjCA$pIGX4J8$cu0vIWaythn!b_p6JPaH37o~D94+%zq= z8@iu00Ef#Da6Vo(BkmFE`_4M)neBEvPn@^riY8YNJn~{#|FR6Z587Bzf*6%(o=_cS zz2Wv!dy))7TFe#(2p+~P*7NfuYdyqcA9g^P*8>{T+^vrHCDi;H0=Yxidg>S8gP+g3TttS@U%C|X zQSKrxMm6XARoM`E!d0dCihb~ zlj+i&ZryujM$&#XN9^Vjm-{+{HZOE%>uOKuhht!D!G{XE=(G}dEK#uDE+n`29aAyg z#$P`kYse?fwB;n6%B}%bG6jA+k4bu3yn50m&erMe=f>yA!>Z206jfkTgfy#?*QR7d z!-S)Q=DfXLsq)q}4YPPG(|N0Lum|#DeOfQ)mpZ(mld+)AJY{bsxQ0(6zkx=i5%L{c zpj5{GY#uetqXBLg0fa=B|Cm@lc?1#oq#i5Y`omhPGesChNoo5g3dzC6oYjWkNBhgF zHg8E`LlUOBDV2|)lK~w)a(v4Es_unZJm>P2n@~;EuR9QhHfssuk}~#2s@@o1pv0S1 zKdfO}MS+iMzSlq#o1KxE)AT47-aVSR<90JMr^rYfR@jFpxXhMzjuAV#2r<9?SL;J0N~<@jX%{LG^sx*aj_qZiAw3BHmcfbPHADk zY1;WqSpn0e7Xh!P5riJCiS%u4J;-~?$RW1D)NQzs2#4Q&>H3RUKW zQV6*dTF)GXTG^<2$z|EF;P%_-t98dPMel=dOBWuAG^cmg1sp_3BNnL3K8!-GIftPj zeWE8v6Uo)C@eDqSk7B>-*%1j0B*zELgPi+kK?j6(w~_9Eu6^=zmDGm89J@2-w)Vke z3yKzE?uF?yx(c;)w-3il;iIOuILKJ$Q|1zBe(G4MRh}YXu?bTZwUJXIy}8mq->0ha%=d=KiP@S;t%XK~8x>L& z3W~holGm!rZTu>g>K`O@p*KM zz;JY?DI|bd)VRTYYYa89{CRdzioXnPI0jHX%p70sgRpQJRUH_dPVzMa$jFw?S}udXBm;a72>qBgC*{8G zT;4}Bd%7tgGX{I+K9cmWNwd1KGvdB~#FH&1=9rQ_E*3AmIkB)KG z?xu#DLSGlRr8QqQ1dAcjFq;t_H;qY98f7XQ7zrE50#3RK7L8cx_n7DdpPB?a=-ZW8MwEgH96d$2;q}WLo`4ProZ=oR3F_Y= zcsj3W6Er)zW*K8O3@8Lj^hL}83^+YO1bpa|K)Zydug@9iN6rSXLBieVtnsRicE_%O zd$j2_F>onw!9q<00!LxbpJd29DXWuvhS-zfT`pAuqjGNAvC$3C0SH9_b4?{3@J`t^ z@v}xaHE_Lr=%8PgUJ)W*z!E_$P%zs^PY`TkhV;A9QCqmj|b%`V10DXZnHcygJ zLL>lvgGl}?=?1Jm8B#~b8lM(y|vl1XeV^W(`#MWv$DZMoGWS~h ztA#y2%*Xpq;0PWkW2cV%@GRd?k^aoUxk~Xzq=7fSD=s)Pf*92JCgZFxU2Sb>oPU|$ z$06uV1{X23k_!XKUwRiyp0`WoD7X%*M{b5L5C!QdY17&mH`EN*Lajd`vW|tm*w@3^ z5z0(4&|yM4hq?sqy-xX(-%5JMG9!&cGfH1^VU&-$C5V?tYzry~d4S}p%*sLB(a$&C zT+FIszTZsb^*TP>&j@>>M7%k*RhrJVg@`RBPKm2lm6Pipa)^Q#jKkIL@n~cUII{7& zTU{G=30w+5?qV~VCk0_T@vM_4@)Mg9^+S14I^40PlbYEgtbBhDn#!!5jdkI#)KElOPH95caZ!AS2#Ut zA441+UH52UlC7t5<~ zjBqKQHTeS1x>9sFsWr~T)p!Qr8P?Hs7C|&&c1RlVZ_C9P7rb`S`Y@JPr7|6`jtePT zEv@BY3s?3qsUEB9a?L{EKE|an=zo3snU3Y*Jp1&slE<%m`1FFjp@4(<_SbP3%J3&X z{~7wyKKog$fqTO}eEh*JzV^|_-(}euu#n&WI-Q1-yFESFqB=9k4|!r~dqVvw8mZbQ zRz(^hj1u}tXNPQ|kAAJu4Vl*gd;jTY9D>n(h^0RL{K=o?{}1E&{d<^DVdllc3QSyz0qs;gYQL>n15iA`iy{@abMJ z=}9bcvP)9(*)-P^eNDRzIieV6B|#f_y%2!ryl{Toks}BJlA>srdAXgUWJI*nBTUPl z@V4o54}Mtf8lo7NQ_hwzqx`1s_kr)CwP8FFqa`J_(ectyM4M(dISucpDvqan>KU~i zqzrDmT@Q_0h?R~g6au;vqt4?FMtiwEU6^%IJ_j;%o0f+?K<6MqP{(7l zV}-`(P|m0_vwuF}$U4e3?Um@N>Mdg|%Pl&0)=4#eKYkvxwVVpM;_lp;4NC?#+eskR zpqUgZ#3n|)dJ`Kb=c`M_ZelhD}XTE31hTn?%uONY2V@+j!Laf+RNQPC~mf z%O>7jjb;Iexw`!n0@zgo$T`JvfZungoYG6tR~IelsCdbT7SiLa&vnk6-T{DuiQN$> zgb?5|YzxS(2%{00_@7aYCpKNQXE6>`KHK>eV}v!(nI#CH`%xP`pHBhF69R!URv+7V zKxF4>+CrsJ*At%?MbI<(z6L4QhOHu=EO!|Utc5~0=qjRiRV5BM9a+87YqsKAZH9n{K=Y;FqR?D{ zsv)Qb>8;XXNr91wGr$hXj^H_{6IiL17i({c`c4hi4$gI2&6=-)sYDD8nY!t?W-goa z7SH3*B?wQQ04=vr-DOSO;dH;}u?LCO?8bX&&XGVWCV&9?wHDnBJ=itsJ`&kNuP*W$ zW{pEOu4rMKoG9Mg>m-oCny#Sh5UIW-%WRY8C9lFJNHDKXyen90Js!X2*f6msvh@>4 zf%ba6&w}Lchv6awr}h2d(w3W_Pu2}teTAZR-Q+Ku{l1w#M{ZY~XSXYGvsUG+hevHK zSaZKe)`O1-qn>tl;{)3E|Mi(9IpSk|_;4Eq(zfx})1pnb?T?k7VpAf@Iy8i8>??edu*2#fus&H`N^NuMh0#%=1W&S673>80dADrPJ@_on)z<7e7ixB7 z1rW(Tj$UAfyr1uyBu49?Xmaw2Ze6BUsx#DLi7jmdNHB$3(hb^TNHHYpW~o z`~IzfsJ5Yl1#o1QgevDQjHXleCv1l?DpKo33Zhhqj!SqK7`kHk5?c?dbyz{oJqHdi zO&5>@BKHEREOB;HrYKD}Vrt7qDOd^;`5aK9A zIvzjxaO#08T_unc4kT1IB%R!E?vSdr_y$uUh|{>vO|-xc=UCKLJkn2_wjew7bCAq%gH$S?3|XT0S6jg_myp zk@0y5T``_h#@fsyrm_qzCREu3sqK$j&vVg%0ZAlnI=+K(*z%wfXR1k-c%5-G2%_MogS1nzP+8yK7bDct=w ztMXa~Y=dRe!^;*_==gc9?LC<(C-xM_C%;5V>;3p*?@tq5(Jl!@wtx&OTTJ76EZ>p; zAVxSaP(|#EJM@AJno6sMmXCI)RD;9@p9h2i3401nvqM_@veuvr1{9uNJ`PAVrsADR zb510T0r2nzzwTqX=OQHG(m0cYKVV>m`AMvq5K6 zCX>;8qw^wgt+u<_O%k8%KnY$k*;H0kKSv{E16g^LePN>;e||r=P;%LUNuBo;`F65u z=5*Wux(8tz6iW|ac7?uk05hNUnXxviV}3hx;0`%~r1=v2MvsNbzRubaApDGQKhwME zI216Cci5UKbOm8X#R?g9aFQSnr)=p`13!H_9djHChv%l>(0+H!GqY=3y%fBm3jUgd z5)nCo5hu{MltfYL3lPFF;(D&Gky?3NgznguFdzYZBVLpM<0*M$;EqznsIv@X8KCDA zx{iL(Z#{B0x!)S$xV87!X}aHMx0`^^l{Ekp2Naj)U?hi)kXrpu_%q65@KSxInBqB{2Ksd;-@WklMkAmIi#oe(|_naN#F}0Jd;( zMvd97pt`k%1B@1MmLQTy3aVkRry0(X%xyNxQ;rThE~<*aZ!h-@)?39PK7R&kusk zGm;+JKHvpFC!i%GIq>_h@MG+vSVPM&eV#tX7$M~ST1tfZcs|jYYSVkDwxjK$;|LTUY?$ z$V&!z8+}7ZuCp6ikG_vH8?v-}r($Ux04TWjuUIR~;%K7NkH=B>=TM6~DcH9@A_sny z_9Gq?r7goNFzajd{P<_%WQF(KGZ*^hT63bkB|5}VJbgOF$$YrX)r37>&vDKr3l}#ocNr7dapcJ#u7k!v;!aj z?U2ek!I*J8mxu9w!g<;3KxEU=)6GH8 zq7T{7%L0zxsGg6&b{pQU9KEu;^93O_H&hPg{_~eZZF{8Gp_x>Es!vD4X#Wlp9 z>_=`RNkoeUBkZtHpxKFTibenieqXVe&$g_f_iijW-Os&5VTu@m7BDL;h^zsd@&X$3 z)UxIV;Zt4|O?&Q!_`-bbn5X%159Y{CY#JI}@GSp4L$MZk4{kaI$u(Seh}s!vVBu{I z*yy54EbYwi%BqrVcttx=y;`ojaRCoQmAoh6hGk&&=GK7JSM*cBneUS{-JsZ|<38-7 zQIBWn>mZ2)8m?rFi~!rVZQTy*`Lx8K_9R-mB{*voTdEPq?2kyUGT8Z_(nrV_>P6!p z%x_;A%PNSuKF=|2X6T{({4?_GRloZ7GySV}`04k>1oBeIYk&JQ{a%9Y^4x1Y@}Kf! zs*KR5q)-VqdgJ4$J%Oz$yg}|m; z!h`FuT*PoAljwAN)yg2CK6MaFh7B$5keV?a%X;-mNMH!TQAdwP#}ndbSE3Nevo=wk z%VSR23XWW;MT1uYabhyVehtWh=?mTN;r+6;GhQ?WiRc4D8qQb{i5X>8@FwT-7jS7v4@Nr%(^{e45P-u!(aRt(b+j43kAX51@m`xX(uiM=M)UD~LLFA_ zTHb(=j)r?=4ZdLF2Z62+IM0RzS*X7UDe~fq20nbx>GrhtdZ}+fRZa>l1C41C5BfZN z{B4Y^e!K#wA#4GZq#Cq(Ga&v2b<+sW6fJ@BA%VQ=4vW6E;yp=o~k}*q)2QbJnZnf_@aJ(F5 zvf~VUV=CWL9N)UFAtG2XB-=z0j^fqb+OVhaE-xXF(4Zp*6rT`<$Ew%;cy45qSfi7f;+k|Z-7+jc7mMBFJ9rN_g5 z3n%9oecxv*g*%4P%VUxdFOrQE61@ONrE*S?kL%GMn4J=(g^WQ$&*4;*W8{6xD+ZT? zeSP-x19&mtcK=5(xI2?h4L#=Zzh#0f-; zxJ}R!S|SjgUa}Z_Y(E5x9e`}vLyb9^o0G2`yD?XAR$X3s%v(Kjx(6F$3r5kCH#T2uhA+kAP>lK;1*#dl9*?g6cOL>bGtpx6{ro-t-jon z+y(s{>Vp&gYRIchdjUBxm=kYb5=j3ZU-o5$)R1nb52(^YelElVBs;*<9k=% z*AVI*X`as{VpfI(kjDjK4$h#m1cM54ZB7AuJQAQv2A@l^gz#w9i^+KKv%KB&@!(6M zO9bG{&xoB*r)FtZdNnu@bsHSsmnfo@G{$jV+%Hh0uaJK*FwUUkq`=C=d)wu-@4=GD z3F!Y|9z<{(4WzQu1&H=oq(w;JI&qG-*%SIk4`?Nz(s?#a81o1CK9Tyfcjo$b%sF=r zhQHFzj;0B6NXRq$6y0@!VFaiaAw9!quCq8+EXKBjUk6li+&>=RSSnjqJfnZ~*^Ll4yBcg?U6Hd1X zbhj#6v>q^4+xbI9eJr1xU*}!|6{g2{{#q}MiFFBmSVp)$@~4I~`E-_cbz`d611c3X z_#Cm81FYq?r5&+2^LAd^iPHCiP%ZX&UW_E_X6~*m3Z}X}mATz5qsMTzk)}oVB0}i~ z?j8xe4vFNY&?8mMAw7HFYvE0{SGQM9Pk?4um(cx495o;`8g?ipI3{vYNLNcfl8AhT zIEpaFNCppi4P;`FDx?Wes6fCtKf{*Wg;q#BA~_F91f*17^%T69A%n;Cf!yZ=&;b*^ zy5Z76fTntgKr%qrz1D&v-%&b9<^>Kivqq(brhnQ0NKAD9Wlz0JI_|~Vb&6tDYQe>{Ie>Y49v$}`fkzj zPwo@tubS{{H1P*4*$dbG@pt_C9<%W2g+C3yjM$T*Se%-}bgyu)CmbtBaFJIxB@Dx# z{p{V}Wqj?|1Rvzx4ax{QS4_ zwkg`?Yd42G@y+@-+Ut+v{}@-f{#g0%-+uQ8*DtPLUVkV42P9tkjq6{+vG$!y#s34| zYJYyg;q(8&@cG|~|K5iWy{_@&^$%Ld|L%wXoxl3M5C8nHxPFp+-8>8bo1g!aZtnTt z4A=WN@IGAc^wak@@$L1l2R!@mWPkbRzq`%vZ+HK#ZtSXgYbra+qAYyN+v+XFb&_vh z!|>aG{QLg)Hyh6d!N* z{j9{nFTQm9?4_T(=G)KS3h%3_-PiyMrv4XM@s<1a-*oc2$+N%tBUL-eryu?PPu@Ph zaNPXp_wlQnC#ZPV`0&T~{NzW&KYjV`g4aI2c{7{pKf*E?*2i!E*?iZh!NmalPW=C3 zWPjOsUVrcUH{u=x68|myF|33b|HlXapHEYQ)%jXk-&>adCf@f8%hDe{{A1-GW}jx~ z|Nd~D@83lHk8@@I)WE7Nk_fBv>c4rI%C`uN!QZY?JM-Qezi!@Yu*83yjz8h2J`HUA z&r`1<`m4kLuw$=Z{Hm+=|N6V1#^sl;+AsdNWow>b!yrnQzJb!f2P@}SuO0Yx?I*t5 zM0xfWrA7X6mwr7w`q!@kdiU;f;CvHB3O`zhQ*!?D^K&N$Y=gx<>VzpVcj>pRqf#I;tD6~Zb=3QK3-uNAlka@}&qiOqgMeDreDUE6 zzN)Ww;eYlbuKnHDK78>ny!h=KKdg z=5%}twQ&5j6yAOJNc0=@J=P!Joceb5bzQc0 z<$GWINV!)yPnfT3H?RD6?{N7K*Z$et_b>a!m*4*LS3&gY!1;8NeK{Pf@9)eXPDA^3 z1P6Kbtp|c5_1(MY`-AW60=IyUOq^<;zV@pRuYEkszI<1uSn)r58~o9_teP)=@&3Q~ zbdY}U!e4%gk2Co2$LIT_-}&yt8TvzPj1P}c0LYV9shzq0+xMU0haZpEAO7@L`uX&J zILF%T4KBjp`hy>R^}2lX#qfl<)Axt?kB-dSYc9V3Cg#&ye)z9vxZWQ*)Hub5c;w?q zM7{EA=8IsbP*IV8V^bN<7B`t4&%?BD)yoqz1kx%tl^eE!uAym!CSG56DV zACI@uS3GbKjKs1dN`My3=-ub%8ijua4?l;Z58gow6#eeqyI*o6->!&1`F+r=z~Q?@ zPM{cxroVq5JR?e|dkG_2^E2|~ z+wK+q7`b`<-+u+8!|z`1k}48)$dzq#OeguZ(?*F$#%=M$9DnUUe79|U@(!pmJNge)IFc5~X(Nlf!k*za9SI2a!JB9q-h75xy#7TkU+EffrVmg`vi`t|n;M zL|I20af??ma%Udr#`1V_7>n|l`O`X#w-@txcR<(SERvx=E&-Kt;V@jU#^-jU-N8S9 zq+E2u1Gv|G{$4eeo{+)0T)=@c)Q2YKcx9Mquau=L{@7m*i+s;}1&T=9=`EQZfJ(}C ztQW8o&th*GIqR19Y!!`W*JpK%R_^50Q;sLiI?0ZnCqWJsV7bQ~G;MY++g`7F5} zs#Rh|z>*LgZs*oMW0wYyZZP60+qTtm?4MxzCjSWTUN6h!N^XpPH$ zMec1#BpoSfV-*xhZZ|x*5j+7@e}@so>!CDwviu8ac$c*(5D+cg0%DpI;LcwgqvaIsmlJ1LKa<<7mQ~!pybi&^g`Z-s>R}MfqT>!!mHw{X10wU3T%XX6 zM`E3(48I=AuxcaRuW>LN;BCfeJ4T-_N}onKse0h_wwrF}N&<)H>a=XmkG3a@T<#>a zQB;7amR(G(=Tp~jn?{7lW@kTk%Ts>dP>acMTRXi3XWVJuEudR{%q+s6*fd}#g%<<6 zth+AYY}8Tk!O4N%IpE+qaWS-KQ6vy=yY2Rfr@~LN?xOp?Lt6p4Oay@{%s31WK{Pca z?#`Ljk>gyDtO(vs7YJb+0PGF)^1|xbdkTy=KlcH{wj1KMg9JewfVk2ajRRr<-Eb0B z`96Ez0ftMT+YL)bq1y2P5OPERLSFBK9r!^nE3*US1??v!xnEw|%&fw+0eXNs&VuFT z!hzhty!I_V!TX6z-Yzy|L+$4%m&S|G7Ds4Y>;eUY8K|>vO0LCR+=ArwK|cWgHXnND zi^U~b_Dw&!J?jC?a(9efob#(li2`VD^5H%aS765@0pHlt3P3wf^7;-!r2rLcUwbaHDFd~wr z!nB*`%MKK#zDe}Zj|;4N(~viHT7a0G%npVPJcFjUXTnGW>1G@&{4X6#5+F(JvZU9y z`G~#5s|?-FEY}I>)?%~xI-x~S^Y2cReq@k)1F%LlQIzbQ=+n@k9b_37P}Va|CQish^KC^iv%U!h9qWXdAN8#trD8 zT^v31Yof)6*bK0IH3+j+sseOoKJu$CtrtLmxE41+{W%hI4anAVa33o`E2@; z3RpE=IKUmbxl-!sAfs8(q65e^G#s;OcpQ*>qMPi4SV2o4Xf4M%n5A{>MeHLqya@GP zFxQyMdjn+D+8jvVr1iOjQ2Ou|Sf3Wn5x2qk%PJT;{wVvTCmJ=tEW`b2HM)0?=ibji z?u+fX5JBTp`~FP7xh=gln~Q$ja>G4G%JTRG!fZblPBjT?fKI18_vGIL;j;6l=0ln5 z{m4p(@ruW_m0f!2%8Bhnt&cNr*NeiE6t}a>!lG-cz8c4Nu#MAI4LdlK{l$aoe3u<_ z`@K3kab(O_tY z*Vc6l^Imjr61jsdn;b4^DfDh=)gx|qM(Xt0@H=Q+4%72Z9NNGa$BWvy#_&KIWcw^( zLMlP`m{f!Dk*$W^g(`X3Iy&*B8n6K$m%_Dz1jU&2rS!5N-W2W}XXnZ0j;zcF%#QzD z`)lVk7o~h%`;hzv+UJ?_$M^PjJj=F_6Wp#VpWkH#)JO^TWOcJ#5n z#sPdO@9z`T1N}fUfb;bxismJKfM*{4qvZ}%=TC@RUVsPJp05wh#;14%j+lIT6|Kn6 z9O+&`n|4KBc2ecli^o%YSg$z?Igsxw%$@}JRlTR9*<*jIgWa7BrpLuG@}2Ee)sDN@ zd1kL6`S(~2*Hqc%`0mFn&a$<9yy=(M*Lv1+KPOb~iDfl{oH9qo3Q*efiHNx?>{^&` z%odlwJT@SYhw_4d#+S-6$X05l1RITV-nApsACJ7~dIS}lQarcC9!iTIL+=k@qtwQr z^O4gGL`STGi3~BZOmb%)pf!RSai9bf;pm#0u`_X?5@^DPN?{a4bGgvrPb{h(bAIOP!Mv8y9)#my;t-8Kb*Jm~;c71R_jDPv z8@M}n`RaAHV}w@o2mSI#RuzEI zcmAlEW8w)g1Oe0zM%SWW4WQWJaVPgmNk>$=fFWqZ*~{k|hlU3ox04}FAI13ftPr5^ zj4dlIHGK*p0MqxJ`3#~=!vfq)o^Ayx*J*b#$u$Hx_Y%=9n0ByHD+zjh6#-;Ddm@)B ziTCU-jI8}&A7*3A3*ov$(HP)_8y;*bYmF z-S?D7kAiF4ClC_WTc|S4qsN0>6S+?{3p1Y&zGXgHgDMk#jRei>#r&`$Ovcy>$4(HE zWqJof53Y?e27?z^QuZ&~a5I#T-;1SVIq9r^u5oR>T)TzYaJV)g{VcN z9kr`E$Y#mYhqEFRp=X)n^l`FRUDh1+=y`8Ddz0#{w#I&h{ab}Nq}dS^BH80j+FR6P z--{+N;7K}VlDV_EEe13B$shi-&i({G^sn=om*0&TWjDdj=MID2*aBeV-nVgYR{~bw@s2IqaX^slOiV?PMZLukl$#(Qw2mS}R28;_mC#)2N!b1D{PIid?P5AUp3M}YAXXm zO%gol!}wAd;Qs;1k1!^S=tz?MLTN9Nm5v|@Dvh=qb&}|w7VB9kFP?|t%m-nMx#k+Q z)t1pE?nyHxp}07ETGqVN+01wx#_n>#Y~_ut%;k~AfDT;m_otB^JhHN*qt4 zpkAIYtJ$yyC!m-O;ky8bO>9&qoMO_=8C%bZhdsj_9-1E1GNYW?oN9--Q@$wyah<^} zAus;^QN!4w=Wbk&*MmJdter&U&K$&c;FI&X=I+=(Tuk;#wr}R(pFJJp5m}(s5>jRG zt6&$FrxXU|Jl)_DlY@QQ_JzA`i@+VB2+K&Dpkt771?@T+dq zMBx}`1?-|SE{5|*7_+s?X8R1!LgK59Vv6-RzOgkw?wXKomaL+saEz#6I0xJ5Q<5X5 z=w5NJqJ$%A90fQ5l0Z`N-gBu3h2H+pA{jjK1Dw|A9Xjl3dac-yx^bh?boM{&gJ zSdGs!gv+pjpzs;asY!Sb)KS>&p+^C3qT%e{PSJUOfc@u@KFCHB$s3GNBrp>)YR89* zF!)0VDY@r|v3JeumRUtRgo54`M@qDbXB=Z2+Tj$wjz8)!MZ7HUry!#5cBfEWc8Qpu zXK~maPJ^GAgQyggi3apf+iiRv7X4|%QPyms$(tdUGEPHnuJ*nA#97hmZ0LSiPvPij zt+m`~`evbh-YQRt8{t%vL@1oE@7JytMTbOt3g$e+SqYyP zZG?B0w)%3i7>;TENw}&T^fzzW_skBXjF#oDe@qWiq$Sh)YoD>w6l_lIFj-!0NO}8Y z)AM4#6J>Oi)ZF5bt%_T5-0bcFf4K#ue=}#$x*pbdsmFJxoyQLcthkdjY=`GqkGv{k z7{@PiX*vs~VK0@dvJWBog8LmCT5y*W8G=Ai(!d?Q&O)&o31d6a#_NOUU~V8fy;a0* zzjM`oAZXw0mkP0$Ly*t$`3=%8+$fW1KDrs&ydY?#B+6(?6UlA59`X+Q#AvMhM(0k| zp70;kSvx4tN#Ug7BG<0fetZRRx?ML+Z5+1!d*5MeIX&YiXH{8Kgp_Yu@@udH>{s|M@D=NwF`)?LoE9!OCIjbpl#H zv@K0E#D{b@oMOQaeYF~BG!U1yJKMIOtB5Pm(wg7U#(VGMD<>@)))>odI>?lb)J|f>tkcZ_z}pW!vK# z`ZD8aB7g_zD)<=~Fow{$nJ{}6Gy$9@Nh85w&W=7-|jjt$` za6=2_3^Y2K9XC%-H$v|Y zU(IGnu~ROdXxL-Vb42sb$Xgs%N783W%p*s20hy_<1PW49MK5|on-L}j@ckWnPC8=@ zHV?^S$t9tn4T&<)D&3R}e-MlUn!atRLt+puK?BiLwH_g6+AI_J?xa92FOs*ac!7_I zHTdQ(v0FmEfHT^76Bw?zMY~yqet;HSCaT_ypl!g06y5LA|hh zD7PNb3(YrY6=6!gTZ#*N$rEj~3WoDTLaI@Zn~k0J*n_RTKOFN#wA8_Vo7Gon%YFtkEQE&Nt<3ukJ>N=D}^y zUEjIx5@*2cxj;x_mTVn>zB!GV8I*I;YIsVlyFP~kWA>C*capE6P-v9>7%e}mAR5}U zJS=E9SNpBe8ILV;Q34y{5{E7TH5K3RnF$-V_An7A`=YPnUzYzu57lhnOGhcA&C2Lp zl8rhe3#_Z>3gr3NkTFTU@+ZyVWKk8Ix}8-JD#Sh(0n}qnNpfym-Hmt?u{E4MjSk|r zuc8Y49;u{rHOMo?2U(WK!4WFyWMt5CLZg+JrupO`O55>Nw2`xN2q-Hy#t}IxweZ!~ zKHQyd)?(N%vs8Kb{vPoOQRfvn>S6vt8rIvE!>)|%)S42x32U)Ok9))m%OpX+QYnxG zGMeU8$o8Ekscc$nBNP3^oi`kYSdUSM1S)??Z&^gHyoKiO#frI}z~l|NuwGz&V%L$R z&LVB?@r4bJXsXfMjjL|D5DEovG#^UmJ4+D3_(d3?1d zT|jTAThok|8@CmwE0wh;xjxCeK***o2pxX020%&MUUi85@`+~o*xL zuoIuHXCEHqir<}F1L5^%R$7K+9*Mgp%%pQWBTE(%qHbIf;%>qw725R&dYT5^6CtF< zr^hwlJ)sdBfrgiK7&;U3!C`Oy#$U**Cj6(H?kQ~8?l-6sR3Re7qy(HWOYiUL-4L6$eaf!nVpcWBI?9-{=E zH)=cIBPIaPolD&9a5wmiQv<$vfZD(q?qa>0=HxQ&1p0ZmOwQo1Mm&PXpj^9`3)qWu zl=nY_i#STubWl(v2^VU6pCMYMbu(p6xUU_MKnfbAD`Smxs(i zpRp5GUsJw<+`xRuM{SWRWrC#`yA70f?hSotmJvGS=NIHirbrstTlU=8k4bMpO^P74 zS~6LBD(x$9jK{YGxz59kMJ&raJmfD&Q(Ay?uR?f6gCKqRxNK(fCM<^%R@&TNF8#H- zbQ2@OLZB1thHty!S7Ovf%l# zGi6=f77?E9y)G%Tj!uf`1J%GDR=;lwLt5{027F`EGP6iHI3XLylMP7`i9UDt==NzO)U|BI}NG1&1KZ0(AzJtifgX)U8)M7RwU z(cCAYhCH=BM`~cAbE1`*%YcQvC%<+i#n=J-*21>W)-8u7`$I{aJ{Lk*Mza z)`JFwdNPe&y2nM+sZ{9XEno|p#TNfi6uFHVs@o*OjP)K z^n|A7HK^l~iztq&GwnT9Sgg`|vJNR7d1sIwx+7?wFtv_Ug=F8MUSh913OrHTlOg$Z zo*lL*vZ8T#`B0Y9sMI-XoR4p>?}U&U2!l$rHe1h8r9+B@@$2fuw?^ZbLjTb9UT8GFU=|t{aa&udlr{nIiKuSb> ztpPe!G-jek(5SQp$b8j0s*$a(bg9@AQ}?9m2^k4qyC?8n1ZSzF7mYmT z@?p7o?Tw3!90p>+ zpo$+k>npKX+jC!d<>U7-`ydWreDK)qj&!A>EJC+_V=WuDwIqjsvNy0@#3k~M)Ou~$ zPn{|Qo-a;^n4L4FmZ@3V*_R!=htwx&GOP(^9ole>hARUvEpTE0s$$;d?r^V*LeUR- zvIMB+kzK1KOnhhll)DmTIZnsOHBQKo%&s%}7&H_+`-!|uSX_#$+d4`iwtOcouT^n} zM&J{9F@h?{Y^y$o}5J5Q7ACQ_rlG`gP-NGb@k0`up};Qk80+90SS z<^a~5b1fJyn3yFm28;W6GP*cQ<4OVa>-E#z(B#XQpRw3%(BHnC)`3cCD22qkt$k(} zC8+P@NqwELTX~Y6N6JN*GtJbSq@{u!>6%&0=g-MJifC3#lSMjt7;(b2!n(xgrswdg z`=LD4d270QD6XTXy+1W*LpQ7^e{)$UP4|WXi5;u~9d4se$>2#H7D$ScnZb^bhHI`) zNKfnn-#yZ`T^0jPlC4MEbY=o1qQIXBqf6lgW8e9h3#HSepGvgcfR2U4`(%j18;+oz)P+;qKCJG~G zh9ILmN6k{cPYWf$MxNb_h7650<%0Aw)2|@tE@f|Ca+5_#xoVbJXLhGJHcEAiD&Q2* z?PE|64*W7|KBb+_@?^tr4JIJ`a?<>!H{yc4g)7J{t|<*d%Nq)BiyPL?YI{E4)GT_mp1~UP zMBJ~Cd*04>$smqYsb**&b&J2BH}XP5dbFmFW6Kd$2-H16e?LY3ao40M4w9Zk%WICV17g0Xgup4Mge=5oiW6&=Y{jz(ju-m&4(* zD0%z+bxzBN?re6FPd!F$+aWd;3}ic>;y6^CbUGmqv+A@5mv0nxStPM0l&}+yTNC6` zLd451PDjwxpU0?MNwU^#h@vtTvqvf!Hq1`p>o)SKahXbuV)#$;`P2JUtwRc3HYVyr zhJaSGME)toUSTwl%tTDgKnGqt7bxQU%j9;@+t!-v)XCY@B9eF2j=j4wwJs^;u+oOJ zT;0V;_Pa=B!{JlU@cn+jhV+%LhnyL5$l;J24xcv%2#ge{lWjCMZd%j^?Ak5R6bRzl30k*- zfz$|6Bx&H*MG*vQk-`bu0IpNSMo<(*(tc~md2!F)oBM2D#kB=V`*0p>*811K{`If_ z@%^LOcor-dtCAoVBPb#it#0?7N_9(Rn!c#IU~@U>D>y3<9kgDUGs)1F%n2JESJ=#q z_M>9ps5?ht_7$B6j0^Uc8Q<;&hONdzOGTGuZXNHmdllfn^D(bB?q`ab0%+$eLXVLW z^}<*lcUHm0AhCogbH4KRgDqOnP#CA19aGyT1x%rSq^<93*%2I*2?p3#-Qfffon2bZ zbL%9WSCwMHmq3B@OmMpN&g)VIcu5iXj+Q(n@a#a1(A26Nh?Is@kyB8OXd~0qEFa4Z z>6qlLHS(Q7NrahiA6bN8XkyW$yd3j~=G)DnyY_eCJ6A|toPW>z;|wEK+ufbG>?lF_ z7E{AeC%A~$6RI+r_%g@SnB|^m8Z| zwh62&^ueYt*1i0E5nHjXP_xt)eIYtDYIz%5w(pw{Sd4Q#tn;}so9_&Fl|>@hfIW?G zQAr@3Ps9LQ2zT3yjv9os6>4gamEvt_ftozVxx2mb&C=~qa6FI#+JaScYXKdPO&O z5>ta>!L%!ZMFqaHf`6!{V+%Uu*XnUp3l4V53vLnaZ6Z=6y6z2#U2(f^`q=y?I>puw zkd|q2)D0E4-5EgX5T_Lik3*5bC>>gC{o(q6=9>*@J~$-l>tnPLCr_ z)IjXn`Vb$NSsiQ@=yqH3Q(b<7am0K2I1urnl~J&r$rbo{M`G$Q)Mp?=g7G>pN$7pD6Lhs2aDK3Q31k~E;qcP*_2y%I@9p11;TCM6HK-{LIM@kRYoo^ zeJgE|4;KazEt_r^gWN8#ABX8?albBYs5W2d1er{}4^&<{j$?J&@6Q)fOI1$vsyW10 z@bjJ;XKUMSyNe2kV+uOQS_&~Sda{(my<#q|Q2vP@v3<1CNx+WF6niOcTu&mDBv}tt z7^cvxS2%yHh?;LIJBQD^na)P{k&tdboFEop8K{;+wc>!4H3ZbI;s4?ipx>@hi=@;2 zV851F%}0fV50Q9~w7xp*LVeg`+f@{pDHLbQ0uX_|2Fk;Ly--kYF|M!MY7=1AZ77QU zXuGke`ulpZ3nMVfJ7o}~S}V|9Ko6%<>wX&Xf_izn%rc(gP7B-#kCKYSM z7xDBqpYs-^C^^FsADuUt%O-SN2yA`X^%9kbIRCy6uGk5x(nMje;^-o8{xBp!0y`Ou3JfVrW;CSu&x@T zReMG;sHHOOAQq;P1TCl@{QMl(R=E|;D=fF{wQ-1^YHSGcYYC3Tf;EaG$y**p!(D_P zYTE`IVFuy?wLh_zIq>=>Hlst{of?=TE~vovd_bp;MVPKA2M45jn71+n@K|;L-7{Ar z=ZqB4PZ-v`#y;Zo}HE{t%l$rn=@lzXj>y2YH@Nlg1nBgZif zZ*U<`RMguLCBaAKyoi&Yj0f>zKy4>-J=EP<7l~t;144gk+pp{;_|W#SfBHwEwV+Ki z2_Otdntmm~`cl{nq+yRw6?Q_YoLu{~Np7eH1x*k1fa)I1_6N)Y1*joD>Q7d? z3QY3h1gS zcGM2*KJ7ZS4hxH1wI&O}dVs`XWC35A>WG6?a>>%(Jc<$OW0rO#wt8RMB8Ueu!KiX2 zQm~B)jb<~_k8Mz1(u)e&Ktfxu_W>!Vmo~@*B1o|ccmXCE&GJm0UJKE6KQL$3Vut7A zlW+*-MrzGyE-7&S)+$6tNIZ)?RB8I*|Z6|(ULV6p`Xeurwf}K@YRiQ2qEB?MH_-BGLFnv#ITJl=GH0w@DGRtl_1oU#`_PDYLJfE^yQ zfUBM~7Xa8Cj{#MeKz>0~8}EW$Z9t$(`(xnCEmH)7Fq+DF8#QX8^^%>ouq|XKxj@CY zk~@oR7iOMGotM)<4i5>d!d{{1WxotW%|U@is+7MFuN5ML8s@1%O7BPr-R6CK*xS$b zQGrBb0Jyi!p$JDsX8WyPDc@*Nlhy|QtbRSzMcCF9 z96>Vv_Igkt*twigWx%1-&@ZEeLz~JZneb-Fj5Q7s*IA00)%{hKUigYtEzI&%U@gs% zWhYC^PFPrZCmDZX*XR2MtrM*GBP%*BMEkk&q`gAWTQt&dHc-ELo$LAO?7GU9W8t*g zVXDbp%1@Qz3DH|ZeEVA2Ry!zBtiel_n|7hm&kf(~pcO5ub#B!OucqOu#)W`!r}a>r z6%jn$NCtJow@kk!MtrN4zn%!QwAu_dy;?9>)sWNSFF*`pzMvV&t7=i)?p1C%X4bRf zUX1R;eWfI#s4$g)8DZR{2>gFFncJm+EezQ2@wgKOQs;KF*)Ur`_EHs~0J8G93#;3h zN~i@YyQdd>;?r6CqS<qW7#OE8?&rrZVR)ym}06S(s5$#cP6k-?nsIM3ZtdoHaO1{9;-4yqkBKTxo z>B~j`J~K$H{R?Ti8Z&JQaLn;&IN9AZbuqn&hPLfa-kX(MfLj$sMUHrjAymC$wzHm? zMLd3$WfEFOtcdg)RgDEj?gth*FMt8HR51X90^&Gw0Gm{(Ak8y*AzV#lVSh|ksa-$k z+gH8Nxv5Pgn~1=9x0c!h6wfvmGtJa}&D3<R-t2?cEqd{>bVHH1cK2jt3irT{oVob-fo zH7I$P`CQl=Eh8SkiUJuCISM?*z+|hBGZ5{G0y~x3O1j_|S5uTZMFlr8oB{xIq0AS{ zbN~+NZ~^@a3f_dA33+oNVH%WD;|x_8(A7dz3-YT*m8k|Q`|M_>cJlrhErpTWL2`!Z zp$c?gi?dB8Vj*esoess1!x6%ou_eFrFxV-R2{eOtP5@R{F{iaXD)O7r8^( zlin<|?**&D{8X&3*mAHMh!#Ud@1n9RR;rQ_mLVZFcw#{1wAgVyV0o_S@t5!B5F+d{pH|pJ_%R1;Z(B~ zm@MKMadpsXr=8JS7F$9LP{r|>SQ#a=fd#V`Xe}Zllx82@tvZ8dlmj)qg(6FBB?WaQ ziZUGRBRJUMc8{jxOGe!W>jKXJgn0r`+bw``liaYJD%Ly2aNCcVmJ(#1ua?Epq0LWG zbIOa)Ww6dx6iUj5e8EHB$5^f?&1DB=s`g`V6>&w|-F_J^Z%LV+?HoGsXo^iN7_L?U zZ~^dW3a)E_Nb+d{C7CT@wR-cDXup8kP{S1xqmuAp`KV%A^Ur(3c9-tp?7g35y#A!% z6I+uu(uG&!HAEyG|)J9y*rHn{Ni5g7_2dx6ABt*OXnA5k27Amw(Y)&};syO} zt-*z5I*^+b`m9`O$)ofp*_c&k-gPM@KvN-9p%>Wzsaj@_7V?gspwZvF_R)whuH<2sgUGXRJfB21j<<;V z=WGZyh!+Brg2y_B^O^=fP#d<-C!_U(fHtilHe`;yE?)+)zxk*Jm^!8gQh5sT2>O9D?9c;v$tvk}yr z#*~H90db9}xNcu%g~qZytM4$uaXGM=1;hK*R;>G#TBI;ft%AWY&qPt;DizO(RXNBv zG9h1ksK}TLdOjVtr>HYrYFF#!6^C-})o6R!ZY=WqU@N(!Shlue14HP?eqXRMn9K$e z4v>hWFGU(cX_{&*DTEvM=zNBw$J$Kg_o(9$4vr~ixR^_`(yr^DM#e+v;{|^?U&;r2 z;Uon$j~O*tsCp_w8Vf-YduJ6zE&MF+jc$V_h7C2-Q_%;YX2H2_dE)fsi-rbn~H4}3m37Uz2bnLAl$@^ zyA6c5D-pqbqvi-PF9iK}k9^bM4%>U5YeZ4}pxuD~Hp|i8T~S$t8#A%j8x4YmJ-=M+ zHx=0B(ud7 z63Wd3(HvjhCWUI15Bo;Dk-r3!ZZ)-rqjt99_)daj{Cd zDT4ES2QCZ&b<&C`G{CC`mDF;`ty3|c&S+`A(J3HZ5b;hcW`X(@F&QD1{3ue1^7Jh^6ZC29 zY>v_+D2falO>RBy6j>OCNMu_EO9Jw3qGl`&4^Woch)y zft@XKJNP>MiT-v{Q<=&j(TmSJsnuSf(sP9G7UqI98v{U7Y$2k^opcY_`o(-YkZ3g}P4hPVjErLErCzk4X66HIxhfRl+V1dN zF$w>{uFJKRN_r(PloagcelI^E!D011>PKXSHtbBrd;;z57h@(l9UzWr8QP-;K`oBB z^T`g!-b!XUFU+?EzrW4*P?9&7@THh>UP-CdL4gY{)a)LP{@6UP#1fHpZXmbEQ^`A* z2axIMMI658;x0RHcZ0z9@3C>@Cp4N`YSGEzTd;{P=vpSeiR<>P-6F9lA*_76RIyr; zteB#Pd9k#pG$Q#i7t`PE!&lMEhxZeyQQxgFpu|ey z;+Hv{k$-R7fAVrRC_bu)=KcQ z#Af42qF<{ng00yso5R>!@en-gStOXXT1g*>SBOPo(?}vD@P$G>gyigaOn}Qfo|-qS zG#?#h*45Y+dR;=QYLi-?7DiqK?GF2`AdYQb`GEoUeFCgSSSt2Mtbw)n8H3xbhJ63$q2{|GSwbt|amp zN}}8>5m!NWv>dQnRe|AhfjaWls5Az>%JB`!87w1~-H;_dtxTK@-smWTw6n^1f=Y@R zux*EgF-fbAGmbc#t;*4vk1#sP-R#VVeMAc*(RkIBfs3$DAshi=wJ7mZgCMQN7%TrB zJ=FA=g>{GF<+_i8Zc>PK;_2XU+wVa}BFPMaYnm#mVs1&!Ni!0X*eRw5s>Hx&#{p|Z ztagh?W5)2y`DQE;ZKh0H!9Xq`k&?uKqtJGsO7ifMyeNdBP=xyF{VWkh?LDs!xnRbT zM`3~%kbF-PG^J>*b@0Xa=`tPz4TdC63IEYI1GHC5s7Q<0Bv2+M-f4k1bBPqrfa)RL z54aEha)@7t6IzeN84bh!LWC=#om#Be^~t+596))07O|DN!X~plz!H#r@-f*58eExR z*$fkfxaKPc#YC!ta8xAwiAeSvPmp_=8P`B}q_83;9N%=yA1A#{1PZwfQyW{kmV|e+ zyJcaWr(nborG6(G_6PDR%Eay(<*m=>JL0X>fwz+5P=_-ZZtt71c?CkfFxK|~#B*oq zZWj6Cl&|Tnjv)X7z(j#{0~UV;uZ2)@W;N6Ex0o!dmcR%zW_(MO<_u{S6g^zBoiRKW zKDrg!BVSGFMC;@bTC0{@Ouj#>@2OCW-=Zd;4` zUi2%1e2xt~tgvVMTF4_t{zpXYpnN#XR@N#a{=HdcyL z8{MK-x1Sc{&@rJ4wI{x0n3Qey=HVmK2D;y8hMH`vLQ{d;3$+Ge6hf)Tbh9YKR)T$8 z*6OXos8!g<>1<)eR)a{r;5e$gDJ{GRBS9z$0UT&DY-A|1vo`F3v@F|g+i)%--FdUv zbBx%4y$JtV={f2D)-VYw!zjsTs7w86ZrWRk$}GIvdBD)vC(Pml6}#XtpI!ma^)iu4=~Y;4}re4I)Wowbu{ z4(E;8et;aZ{(@!5_i2PwH|S2NvWL@tMEuDK4QJC;JXjPdCMbjTHmuDfDQM(dMBL^ zFE?VWh8%u?1|AdJLWIwxP^7;i7(dgoj~H)aGVpQoDDUo$CxBSY_N0hF|^tu_Wu2dffiio&MW zi!2t9jtkRT6q#Pk8}FI9TO*t78Sjufs1%C$RISoVF|%ggj^{wW5#(XN_>;s}-z)w- z<2x;7wTGPv_FLzfeYvanbq+6tH2aMV za8&E-SRy2L8t@(P^AHReEN_C>mMSF48kQJ3=?@A^9m`?Rfc@ei`)fHrU1pYu3Gd@f zKrlXffTRhaSm?Ui_xZj43{IcKUs}#k>%}$5{$qj4)>vl#)x^6$eTLq;S_V*I7u6#ilWg&MG(OM)@>F>Sb zII!JE1RZN}>s0}>efhihp zXOW6(ltjzgddv$5Dd}wcuz7ncBg8SyP+B=t4WJ%+Hna!IV7A%kneLivDB)=VSX*L0 zIV8Fq&H5toFoi0KQO^0#7OlQQMm&%o90c5%37GqnO%V?jCj#o zp3j;|zcNgN!DhigD7ehRGvJ@IbbxCz4*gMH^n+})ilb1y+4KRGqoTGKTYvy~$1^E` zGVz7NLJcYi=Wkb=UZJq{^)xjN8&1EHog_zVam`MFLyBr9NB`I)BuadU#y-T!pkVQoNRjJ@U;HA9b6}4iLS`>XA2*55tcDi?^sopkGN#nKFgk}YRtg<5? z;tlFeCJRtgWDxteOT<2AiUF`#C>NDBfi5sTyUd!Kc8Z%0oZ`UxDH=;1Csbe{Dd`4@ zjfRtR#tDg%#H>3jp5T%B#c^y)1#0%@k8Evsl8gpTL9&TdrXp76T2+vdZS^sX2dDzkO5w#Zmh}&*!1(nY1mhmDy&BaIq$@-ZF zj<|#DEE=h5*=hj$GY7@G7zHj8u*?$S?v{=0f!P3Tq`}75BN`_XgGk;GUD^&p{dhmb z!ndD|&0|QGZk3Oicv#y-f3+uQ`CJIv+z&*i$0z_yM8qX<64Nk@ zFXD6E4pD>+G^*%kop}eKeHiP5FqU5hAMV2M_~*;$FwMaZ$V>eUIoKhYEWFz1!o+45 z9HF?OKkcQSJ8FRuO@SU6S936%oZArXJEPkXT&=O*6VoN{3ERe07tnX@nTEHd`{vbx&)y9sIh%v_E zn-syNLOjtw&!aoid834(mFg#4Ux8r-Cp_|^o1i$m0?ZCG{ z3>hZ}5blgKcaqB?nk0>)-01SI?w zyH=n$A(WS0OS^n(oZbglz@bJ$dx)0+g#?T2R-i;67^TN`YM<#-+l(GVw?*;h6~agw z0N>6H`3lodA*N0QOgHCkc{vJ7A)@u;!!EQSY6o>HMdhR%kIb}TkSltlfQK$85&PJU ztXIh{Y)c3oEDgee)k0MRL6kQ~z;7S+t`QaXmk>1t+;Zr8GF?WTH3bkYAb()u)2faD)V?7uVbIIN+^reW_A)Dr%FBG{79d zCRW)F1|>!mTN0Av;W8+0g9EBbM;i=crw}^X6AIprH!W{~i2_sgcGPCsc$$h%c?vPZ zfo)^i0e)K!U}9S?Dy%pVDmqs3x{W$QN`MoraXFLRwvj9-D0!4j_YbH{6b9`gy+zde zs#sg3YR&zAJF3c6L_-30zsVCwp`3tV=>#w$P(^&*9QcV%l}5hAxGz`p<9!4b#kX@H zn-#?HFi8c68x)CG!nJ<3?k|&4^ua|=Y(&l6;Y`I#0ulV)>gilB5CY&GXWMl>KiZGDY*9x;GW!35EMu`dp zhb|Nd!&MTHkiRilHO4^&B0+&EJi;@`7L0nU`8>P|47JdhfLayT9L5VAG=vF<0C*Lm zvbEaAD}!^x8y_M=$y)P85Odo|a1m^KYekm#NYqcq*iEFGjPwvMoZy8>cg}9hG=t-F z9U6SERo-`^KrRy-l9v+b_0~JUkmS8W*TaEaDhpt*dXCBh2OzAZDSv>-9kmTCy-^VO zacP33N2M|V0|Cw-Lm?H#TLhjSK%B%Kvze@W<>|hg$^+mFG4g2^+G(#1H2ZR{g?M#9 z?JI}{NB#!Gu7w~y7$9Cb0%urfDQ(spWsOOyjKBw2e}U*OIM@n+(?yVX82@}UqD?sjRK+L1OV^OY#WZLT$+QqhlU?k1QRVlST zrgM90(-wAWPo+ZvK<3K5NM4Xe+hC}W>>$%_*L^h{3=mvOU z-ojZHdrAOvGtL5_G|W+;fLF!|-A~rVQi}A!R}Gwk_5r?+#36r# z#@Lu!YYgmgMxf#IW$J2_5`8SS-cw{3NyEn#$%$hf_invYD5@d0#y}p~80V8jPh26R zNaBH?RuZ>(A`CpV4VJH18H9mS&+`#(+l}xNlruWgSwU`U#KFmw*-Q)Y2GpTu!WjNW z#I$!K05fCK^?i7kB6${ozf!s=Ktg2JDmx1FB>ZMnH5~Ek-(B&E#SZcXKw6o&luH69 z2ciGVt zAx^oZHVg1%adaTcVmq$mHpdzXxW}RHAhG*U9{|r1jAI7|?Y-|vGPU)_+WBoD$j3zh z_7iI5}vhTr&xqYT%|D)#d|Ef8$0ob+9@auPTC%*%J5j(!A{>_7MIckiso zWt3Zb?<#Uxm1wU&jpA8L6jgdbsx!SnrL7l(885uckzSG#wb!p7AMlU|P*WVWxQ@Uc5=Cl6;Ts&!45o~MX_KMY^ihkq4!a?9n+V--Sv z_9j@7+&X>)-|2Hp^aka!QRY^f&S$E|DVoRpjz?0A(%QHt^wr~1SBKYgUMUhf7&U5^5hY+ydX}ED&o$K#I1^W z)49Tqve;T>Y)A0u#S&3Caic(@lQpM!PS(kx-ttlx_()KOfY`WURvDFOwPd zn(oz;2JW1Vu@|jF;$hz)>+S>OdMYPu^a64NG`E<()a#DCc*TH{qEx@_E!@w zEm#&uny95bv8%V%(C%kTIdA{i}^^Evhz{FkUs`gU_TNW&b!!Fn(o!=gm=r9%(iygKp~p2qRru#o6G zm!WqZHm@h{TLR8GFaZcS!heJ7; z!Li@iCeaER#$YBR&)owD3bOWf%ZB51mJA!_9lh5Bm?I9h5%T73bOwF!E#2N@P{NZF zJ(6x?;XFeDRmsq46<_3z)`??NhGt4e*O#RQEEYGZsxMEXcYdsCb;73GIWA)t|EM3E zx$P+HRPa9T6r1MSKe_B==GRV|yi+wb6uaO3O_P0%F6r9o7w%?v(f0`@4Ao-{PlfTR-?KMGp5Zjir|^2=Pq%psRz8{(l00X zzV0qKj2XP`wsYcQmz=opE6OYzeO|eVd&%Wk?7No+nNBY|$>Td?lEeL}gHPc-+#Ai#U%&U?av}Kr z=X~2PXdPv&*RF$51x$y_3sY&*?NBdf;tRuG3~w0RN-vJ~Vw(fZ(SW6OnT9N*0nfoP zV>NK%4YNE(=Xk?DUKf@Uzk*tmLRhzIN|uw$=JbsJBf?j&kADe&?mD&_Uc%q|C#Lf7 zi~1{;-h2He>_NI^-7tU<)`3G<~S&lKn3b@%dx`!4ql-SqL3c5NnyXD@3V(QVD&wl``&ME(D^|K{}S zip_t04;P+cq5i`UebF#c5C%O=wv9=Di74w%ro=G;ZX7Tx@dnv7{hOx{^AJNGv>kkO zZ>9pDtzn{m)gz9+V9BAv_t1V?`^77~3kmS|Pu7)F!8=t=^niv>U7ucdPUru4(&U{> z)i|Df|C{Cn8eP(lC#8eNav{RosCD6nA4bY^wVnU%lBE2;H?851zeT)sH>cm)3U70< z*(S#^{6n zDE^$Y+r8E@dGSN~D>gwQ!jwRm(arh*V}-6^IgBF+#qg{YNh7f+a5(EW3>Zm>=#Ygi z;y4f(v3z!H@44X}GX=uOo!_%&@cQ%)X7e*-oVHE!j>UW~2YODLJZmxkuth+lOZsBY zUW`2E++JU)ikp^Eb7&bi9m)}u8nJ8YE917MMGUBY5fayj?BRzGR-cG3~|`Y}|({~wzqGPNxMUeHGl=Nq2E&nxGb4-QEv zy@=dWJp4=%JV+HLPB=3TxY&B`snyXNPhtf0%jIN;Hf$_nMRTQ^_}rtX%BBHas6hzY zzkRYg-F!4I&%Ab%ZEW3hyX*2Tr)u)!c7^b!LTN0x`yMlwn=V;@_hfiysV;xPT6o6L zb=4*JrsqPOZ==-(8+9S^-P1XGHhQCg(<7crU1TlV#&w|vA2X)(Wh8@bP?u`)F{47V zq+LY5lAy8;=_1WNW;`E15t`-#zCOL<@)b)fxa}-!Tg+q^y>V3ggP6W~ZX{Vg=tWC` zYz_Jjf#O2Yi;m$E&plWAk#5TEt`Kf7kcePqcGx-lhdq|OXM|!9r5L*f!ZCPGm;Z>3hLJ*82Rn)dLr*-7g3JlC`P3%7Om^I@%#Y&EOKwv%y-!G8;(hU^PW%3|Z`0 zN)QNrS(xexXXGe#HH20P#c)al2W0a|!_lfgTODMByK~e77#?-T4Ms>GRQM}Y#)3Fm zj#NpRaL8ptZq8^1C0Ujx!j1GcRT#n^O_c59IgJ>OzWVC@w=wl&TEVnL&sg#<&%_>0 zK-&;5(Aa}VViPjaSD#92Wj&%1m%iV>IR5h8i-Y~Fe%u7>Uitx+^WFg9EhXk2o*<#n$ z@G)l_7&RwD7%Y!py0U%T+EPEQn^;aMWaG?R9>9$CPS=f<)$?O_5!g5s-TjcoS9d>$ zjtovZa_4zTPY`<7VjW`?`hnt8H>Tc3374C0RB(wGG`?Yr7ffA*rEI;sP=gO1kxh!k z9?jsk@m!#>$BgCck6CKAVLYy#$Bf_y9P8a$PR{EtU$|fL+Ln)-TEhNaNZuT=hYdy$ zk3{oVbpsY`Yjc@MB+fH{Vxk9s!w5wr94~MXr9+$rAm9LUaCJNjIBaVJ7zB0ENX`>D zzUZRYI8P9pmhta5uhJ_-#S1D5c?nQftkV)XW)Pj}03~5Oe{}v5+ahUK7077XMgC_}e z#&Kv@s=%)X*i?>I25dr_wA7&+uq9y#!kPdJhyq6tF>IRJw;nm4wk7fCrogkmaw78G zj%hB>eDiT!WgEm}TYB&qY;rbv3FfwqfsHleuMQbyC@T)HUynny_1xsDE_FL<S<>`643<sb!+K&H-$oSXC{}O-B zi52_#pEW&?|3ZJo=6U=BC?pkVA_uRTN88PHu%e?)MAr@kWiVTj)VzZVay-{rR*UCE zO9282_DbEodWFsQuqEFXfcBI)rY+B#!vg+{97<0&Y8Y#Yf+aSnP0R3efg zbx!)8=jy079ma8*GU zuw36hUORr@F#7)S>zFyW`r;d6@!h3uo)KsLtAEp>h@Lv{*`Gaz!5sh>Zss_VyMN zlU*HKIfl=@>B&OtKAPh652N8H7N_bt90E*ai1j>#%fX}xRJ1ERW)eq&0(;bAt&zZ3 zrIW~}ub&3B6A%#nn|{j~@`)yhbtDHFhfToUxP_IwIT6$s*iHZZNt0)(QNQtBli`dm z>7p|DN^E2s^eZ;tLK-(!%IK@jE7E>%IM_C%_v#A|9kUB!t zu>HXqPnM`N_S!IboS-D#h&=Z^CGQ@sBP5U=;QC}gGlG#35jT_9haLQ|tHBRr#LDQr zqK`}?05IfE8?ZHmC>pa>wQTn{Hd9FTQcM9!7{+4db?&|aRvia&!rWc&6z zH2sqN@%vwTUg*E^5AqwAzu}<`{o&~g`Wfy!e}BW{132RGFzeJI;6X7G@(w-_gd>s- z9EWjeiYpvmb*$ny4=$C1@+iTBr^oF=HQ;uK%&(&ga@?v>O)k6N$BLj&B%@Opf9Jg=v!MXI*Pn5+?N?8Re3nY_yU$EU zHAtqb6dyG?#YS!0#d}F?*A4Df7fP4x`Wu92&*Nv?*dFqh%i!Hq4uhaJmE(nO-#&K% z*}C_@7hQVjTmi4-K9epxO~kl$o;WZW{rU|Ze)PPzT!?W0#%Nm*mgKfxyZ+I`>F0%Y z`gviv!fo*j$EWOPB->LbkqcH#z&Vi%ucxK0k!NdgIUL@G%(?BhNy72JM`rQ$@z3JV zUAvr-EB$*_Q$qYj{S|8)yRPDBM|_};r~xOSFR>FJa*eTBkfJE$oO$yEd8CecV*9jf z%eDn^%L5qLFP?De1sMN7Icf4N(fZFU!WmuCMXUEA^f0IG`a!R`kip{N+dMY54wIQa zx&$oGp!e%vc=5uMf~i}Fjg~nizF`H!H(*weLXOSS^Wuf&J$%qR=3sR-?6-7oyPedo ze#NK6+?4;r4S4qTvFj*4`*l>{^+^0TzW6q`(q{A*zxj0vSFA4I{(!T8|J|$i?~hLV z=hVD^(a^k!jgHV7o-v#5eW*XdyN2BD@OvTSTs zsGb6W1eK`>UivfA9*P&eE#V{pWgf|_<~`jFGgIKJ+X%9Z$h<>&5(#~9;W9fv8cg;C z!A_C}7oB-b&^>e{(GIO*jL1%c6Aa?-o|rV~N2gI|up%D4Wx9*(5T#|cY{kXF!YFA+ z33Z4x*FA&Qc73xz7pP&-4-;~vh`?K?klMwk*0zzo2aSVEfBz`JZMx@;m;{$+-tY7$ z>OWmtb8e~k*{oj4wDqq~25|d6U_-|G{$DnisWCWx%k}A@eGgbBw)uJZyY~|8!^cHv z$WrsSQ*M1S{0i2++eqMs=4jC9JSMR@a-N+vgwprb{oKa^RKDl$lEsxlE4!m)kmQ#JY6L zF2p>0%72s`q1-n#TaWL0%H`|MsWc_hQFfcZohxK;$;tb)`zCCD@%okrTn2OhS;rWRiqmdBUFApzqhY~kd+S@TE z=x7o(J*p(L4^|8`MRuhTD$5)|X$juIN6l~Brqgy21O9U-gdczHOSYPoA3Ai|5P!x` zi;~6_wDj+sv~>4A`&E1f=c|uc`>fFueV+x2*AaW+JtLAei0{G2Tqu1%YuSinv6l0I zCppe@K;*i4ZaW4jB3cnhZcc66PLu${nzkiKIl*g`T~7jBWttL5Cbbu1C`GE5xdx_! zO{(fa2Uwp#yF+XrITn!xi??td_N?X}(G_XwY9g@tezWMH7dEfhRmc)OEKW`GOZotS3dYt)|3lVIETR*5ztRV=G zzs&Jo8@FE{|AU8&T1RKNZOG}%Fp-TMmuk_4R8D^R@R4y1dYQjXis?)GpFD(CMi$L& z-4NYuB%fx?TPS_}0vFBzAcVMfLcE&e?X${f$&c z%jABJL*UbKlB`Cg8$eeMX!8JcG3M}=yCwz4AB;fOygq(E{@f*}4R?V5hreW4!rrI9 zVhLjQ|Agd9tFx(v&2}{O8^AM=o)c1&RM&k@W5FEqo45^*I0uGOCG8QC26Gg#cDv zY+lYS_bsGVzH^BA?!Qxii49vhhUzIVpIl*Bdg$8eOE#M=LEUs9S>J@=MBzh~jPJA+ z`==8ppC16z=YZj- zvzZQ(_39IE6LnvGL@Qw8PZ3_eY(aw`J!$f+?J!_15~EA{cKGG|o$HeuXg+i{p~rcA_}cq`wf!!! z5k~PA&Mvpj%?~=(zl{(lH{2-k9Mw@wO1$A*OLvJ5gG>*3#iXIW7Z=W^n$1jl8wqY$ zh%I)pS)4v%$Q&DutZVm@=R^uRiFL1#G${7SR-8oaUy_I)K8kT0b<9im66Y>PIFbDZ zB_8sMbJ(j(4*R3#R%9Ev?c%*dFF85E`ODgBmvzF^w#>j zJ+st$#ceJ2U4DZ*Wk^GZMW9H!d1pgg;^Jjg3FWDZ!L)c^MJliL3om*LwcRkkg~6V={4 z;%rn&BgGJ)>ca>$)w698A8S=(pp24W$Zk=VhkSa1;^t_u_40|%3`8COnC+`Jf$X@9 z+5Sf-v+cA8IP6E~Vr=}cCrzHEFsuK$NkpSdy21=gIOqVc{3}z)HuwuP_ArvQ+)Zw{ z?Bv2fx){ms7sNJ7TQbPGT2ohc>5E8zXGO8rOZ)A&4r|bUsg1L)C5kW9nv-H5jy_r# z|MWjHSVl$x11BBL`03n}k+=t)y4m;?a73VKY zK|CS2G5lA2+errIl4Nkx1PwYF2lx9Ix{b)L{9P*}UW_;`?e)D0b}3Of3>`z-llU}X zSsj%P1h@e;ov0|JY|qhu0<#?a7;Cet=6lexN$qioQ2O<8;UNUq)s%NFrnBhb6nqIc z!KbG{^$#|}m!2#7%N_zeLO@3d0tx==0g}c8CTz|{+A@c&D=S@$`H>pvuYT#vcWR*j z6vlWGN9de?pvvj4YP+TAClMeB+zsHvo@s1N8qXW{Rvk?i-vdI3?npmChQP;0*b8WB zJZf*CnukN2-Yj?NSk-Pu)#Hc&gD#>Fi9M|E+1Z1&$)pFo1U8jU*wkq=`{XGN4ViTF zhRF%nH}By)>dAL*7sChR*_(G8&ravcZa@2tqRB$W=nl5c^XAh=$}gY!h6^3tY@0@J z3=!$nWl#9TzDb;6n>Qxrk*%1ssITY0boQj#YikE3v#l1F%u8Yur+UUf*l?pGQ;#%E%gUJ|Lu22U-&lRw9!{#rnUS` z=lH;WoE&%H^#Y2vCkwdKsv7APNg&@aRroKFbAT%ll%YinQi{Q>K0_Yg8D)=vi>VPPqZ4^( zo*@k=RpKPGA0tg!ZfxN&GF%ZvC708s{s|qd(?baQlMN#)v`xxRdy>Z*e7amdl%K#D z5XUgR&(mf!^tPVu`L@wlUBW-RBKY1qWCMghFvkT&AfW3{riP2{iP81j#%`SsudMU) zje$GfKAu~kv5R=ngdvB=*8bru-6CTWi{O+SG;&S^&fdCX((#S<%O{BU*Rd(cTpvKM z;7z-_@j)YTcY0`rJS~HVZ}iOcI>JNOIlBJvu%a_KIrk?nz-cxSeUav{j(+Pz)VaxT zmuEhFH{59--h?^e%@VY^9FyQ+2@U*7QZ8C>hYi+$Z)EZYWp+Y@ec?QoHP z)D-Q;&TPA4Zo;~f^n+h@T09=LAU|SkB(_0V*Y551D@hd3B?s`DAyKRy&o&gdyDo!r z<8N0E_}m?vsqM3OKIZa$r$Y|T)ZSPKB#MFwgDY4Jgn<&cY{7IJLhqC z$*zCeRfn{`czw$QE<-ze<$vNtL$!VF#x0lcI9K@9)KqVcg>Ap&B;8-RB z)3!m~^WeQh{HUpz8zZz`aSrgWUUGnLreaH!-ySqzJ!4b;e!y{}FnfLNyzWAa+tnFz zKCa??Y|})@`Pj|m-7Pba(F) zpj{B1pZqqpJd%Ef(!HcO5%!-a(l_R?Tw?dRvbTP-2gFtE1nm3pvGdl%Uz?Xet-uKb zxXq8tGxUQ=Vf+3oy!_yv8d{WdIe+%H*)Ueh?GKo&r_09t3E9pvf_%_g>IO;mrT$Tq z6>LPZU33||V_4(nXCQcxok%86vf9vl`t3{h)N>!BS|7i@|JnP-b^U&@y)iTTznzmX zyX4S5s4p*D|Bn}3I(hdRF*pxTedXN6YL4stS6upazofHqpqr#)e-WOs9D(&ggzM4i zL(qMU^X?hQawIj$6k=CTj8oWAdKuO}-Pg9llSluRZiYuHJ`r`sE6S5A%OPgG=!0_M9tjiQ+71hwKx0Lh*dlGl!mpNhFhH%bq?0v*W|qX2=99s{yI73@_$# zNrH@wNM{304*k*X&3O3W9VI1GFj3@PgDE5w;X`}+AaaBv$69Ic4vMfP(iLdGF^uN`)@a|3dJ z;iSp4HjgW7^Dw%kZyp~8N#N>nIx4%a_ndS5*-H}RLx&>2wqY4p?jMGW z5@9gt54qiQ4#RuNVVpOopFGuYY{R~J?_L6Y+^Xk$>lsv+&7N71sLL_04-O z{XUznA9w1;w(p$YarugaI@cf6^=f0i9)CGmb$3Z3J%5M>ZyVUd-g6oD*~Cp;;Mid6 z_(hs~%y>Ra7NOe_#@5N(pKY;MTb&(u4@1HPMSRH%=&5T%xZK= zKeK-A5j3y9Hs z)ZV;d(d_0u(CB^NxI3u8NHBOUZ2Il~H6|T=ZDE!EQBE(gsOukO0xip&ZpAp*=G+XA zBxv1X&Vfbm$_%8ui;YvbLW*G>H3i8Gd--ier ztblQdlrFtG&!HOhPUpGlO4cM&;SW&u5^^Chc~=LsC0=%X$}p8$vg);)gSV|&x4WSF zCqVVv(`e67zdn1?z*+L?hpjm@I-tv^*KSUeeF!dh?;XM`30?0c2la^)&a#c@#;tpY zb7irmvC{09%r&N;AHI3XVSLQC3T#7gT)wya@5k~n`mO)l+2PtHJNyIoWoqlO^ZLDA zekBItFFBA;0QSKyQ*2|oam!^mZknR8>I_>mo{2qLQrY@-fyN#@65GlCqo&NX^~rY8 zrERCG=4#+N-}v=2mz;jL=#JC*vowR#Gzuf`&?a)pws{(G$Nn5J;hIntz-iWgZny~# zaTmyLLvB0bEVjU2@c@l^Nl*%Gd!bJCE0N${60O5@z8!a5;@EOVZajD2)1a%!Gx)TO zEztPJ6*fTu+ajVf9D5 z@aPer+2KKAUo}QZ09XKau7U`7Qy8qs7VaT+s&(I{D)1}p@sN<&lR{i&q8>_`u|!C-|*za30ax--u~acgf+H7_wWw#9Iv2CX@9{wIkjf2@qQ4dgQIJ!V9&kqzWz!!Y&fYqz^DU%Ov(un8+y&EaREIpFAd41v+h zx=jROen6%sT|8ualOP&nCxs^9*sNW1#*Gv1$??e+b%afueE1OSVjK=h-8S1-mD|5+ z7y`+rjDmA;q=G{n{kp9SR;bhg9{P!bFi}0WhM*bD`fF*n0zxCAaa7cpgVv&VXa$HN zgiw=SD`uD%x#Q5eNRTxN%|VpT4F5n;hIFw~ZRni?mIK;=hPD(`LsijBj)JdERl?F5 z-Vf^7I9C4&7I^)ek392#{-lAk_B@ZZ=NTQ)_q-pum1AsOzvH3%26U%~&40;}I1iTA zN_1YoufNXFrgP22$x9C8gF3U>$bYD8f9sONyRrPODU!~cB3lfiAr4HHz@n7SS^w~oJ-=HV7%SLKrMCov z?Wqqmp?p~Vy*~WDcP`%#ZO1a=;@>9y^b!B_OOE*2*;odD_`+6xd}-b z0BG9($KIQONp@Xjg0`fRRADWaETt{klEYF-$}DAOMMSP8TWd+evbC71k}B<5(vg`_ znGqEkk&dM*Q`HGrY&QMCjY$>*J%DT$f0z$YWAhE&KqJ;+`RLXd8m3u=p@*jF`4BzK ze9#Q@pL4f!U)+fIA|pzYg#@mQc=7IX&OPVcbI*2bII_T{t2)pI*85p+!;z!ifNK#w zp=}mr=x{iIq0+a#`Ul4>SMZtSad;M(QG31AC{w(}7Lp6#4@Xi0Dxi|3LY-&qOr1Bm znI-Eeu9;iOE^TpV8bBPZn#<*ltx2R_z)MY;6?E`frtAtF2A4`?cWqYTGi|6z09bDS zVf=8bm%ifoLGCP6)-52{|Og2+pJ$1BKUr!yS&M?mj`p54Mzj^&VDLX$R zzu?Ub!|GWnEI2Yt0PnzKJEY9Wew@OXK=eDdxi$IBYqzc4UU?eZSmiwa z!G>6=;4c)1+i45so5qZ0>6?QpUyb*QYd0ZF)|5#jq z9^XD*`2zm^n0S9}k5YZs-nxy8T5rHgza9S*D;`~e)qujXxLj}7T08H5Bhk~lIO&7<-Sar%q)E|;J>v~UgWPISpK6h|%<_+drQ zq}ciN>;lXdZbhCh9hyQhWOPv@#gG{zH+!EckPtc#@;#wOt&}!!WiA}TDwKxp;u-b2 zse%iy`oy_1+|S4^HE9WT?1M-hMeSAHwQ7!i{|voSH1%*tX}{Fn(T`)MQ=1n|uQxY} zq$(&s42oWzUz^5O?RXT`CZ65Hsfc0t(UJie>u z0knip=4PJ48v4NCEF~sCjNbZ&#cZX3_8?^`M;r=!ok zKuqxd!8;oSmdXBhB{A`STLxz7QB8Dn?;X$B%aUHRyBL$(FAbC2E~jiv+H?gP+_M0H zsYz;jSG%|cHQHVKz>Iy}G`02?jb^}xW2cuu+|1b6C* zw2KwQY%aH|TTX}T>LvN7814J)_Qod-dhp32ftlv=`^*tTse7q(v!f0jW?UPB6r0)+JGCRRsl9!eQ@d2Hj2j{{Pm-tjl%3*Ju03OKa+p(mhdSDXX~qp4 z^?ok^&f16UHQ0NY@(euso27`z{5(>*zaPlfK8V9}H=;lhGfm|J2JtX7Vbn0oxVIVA zaWaCuy*Ytv99&6n2Ikywn#@pI7HUT z9YZHX&Va+2*q)a`RGF2!x{3(bhSBpz8xdV}aMnt_5j@MB4ra=I(VO;+tMS|y3Uw{Dvh58>ycidev|XVqH?@%CqTm@_ zWRLe)s#ACWz!MWV971Qn{%2z{E+j<)?>saV1PN${)M4Kc2`O@!SuUq6*hhhWlj-!N z+X@_=x@OVaq34$-_z=TM^D+fnM5XX+`m6(;4I917)b0#Wap#jX=cqd#D}u(cWtW#( z0U&~>^AsIj5DZd9qy=Y$8#OWY`xb|l|3nlvQu!VHNprqh`g?o6dV!mW^Ht+fVn66L zh&KTbE>{sR(a2Wo^)n`P1CVqBhd?`9Y)}lm2b#9VFR#HLLLu%Aw(U1t?Uiz=sdN)C z#Vawi!{MJR9R3;oVW(z_6B;X~D?T>kifQzfPoOL)d=(A$9BkAn90K}eips9g7M%mf zR%zXEH{6e=?OI5I^ld;mfIryY*Xlvv}tiZp76BLQaomqcJ} zWT%aA6i+Of@Zspn`}?2~<6#Mc;3QSIV~=P?ysD_nyF_B)qd57*?vcQK4Bj0Ona#!X zx$)d~_Vz4)%G*zc?c1{_R_e%9HGlbqjfwm=?sdlJyls{rH_h_n!Djh!*Q{Wh6>PIY zxLLt8^XFmaWB&TTs>#(R+&J{vOprbYr$|4zN!BJDboALZ?*bvcq?>zpZcLh6S6*KX zMPje;V)*>}F7RuweKEzYHH~+TnmZ#L8;Wi77Pz*_>_8j4Nz6lN8zeurOS-bw-At3_ zRXhL66v>*AO1>YF!`sp`?+wh@6C6?ee)d6baT!Wq7Hk%?_YS^npR5OvAeQZ~)y=eC z>K~;fVt>YBc9xg*b{o4R*IW+qK(u{oN1$Iy#CBweb&7TcwH0#bV-Mru9w{Iof03$ZR!?fK7s zhg~}}CEoLIPq#V(xU?-2fwvk#%_!^QiBG&|h6(c3G5Qj)b^MeF#N$4-`QQ2{PJ@YI zck83`tA>fr%QQa;G}=dr=zFt77%`ziK<5uW2;VwP5Z;x@`2x5UFDHVXsaZi{0G5w@ zP(L$FP(!ItMj#lYYqB0Kq)BiCf9Xhhy^IThs#~$rG?XizZac7fp*^>Qr?w>lJr&;$ z=z;%2d^@1aCU(6YY?xIiofW&mjDN!vrCPthb{_DPB$lJL5!(S#kNu4#uEf^S~}FC*Alxv@yil zGm*?pMj zb+;***g$@5DiyMf2y}{F zuG3TUhU1`8R`;dSCUCidQ|til8OUHPwsyV*95Bth5bHeEM({&!BQTTWjo@bT>33fh z0btUbiC|xD?pQFi?;iM+|Ijc2d`B;G65#cIFA+Fn*I|VRv<*J@v(`}Iz!pZP+wO<7)?#_7v{k2CQvgcU zq9;jCa@%R+*LJ=x$UgKd7HcO)sJ?K%7{eI>#h-l~{OefbRKoZ9FIlL~;MyfaTaN?F z4i#Nx>0blfIqhT`6T>=WyJpcH!aX@rKW!pqC$O~i zbmvG-;|RX$q0J)vy`}79Y!WsL5`SzFR{2F*myyaZB#3jF#oD|WRD&26(jsn8H;y3a zv@L*$-;U9#Pvm>;+zn>M6N^-4`rnInl#1ZL=+J8>!UX@eZkQ54c7G=ktN|6PzZx2- zj>!z?h_qgIIS3390S0`P(c_+@Qftw7f&mZ`S=XNt*x1o3I zlgmE=m;v{Q7YiP5b_5ADNQaMWJ0wVr;-8D(&Yr(Jk5k1X97}*YhU-+2xQ_7mbB!{> z_DP2IVp!vkBA$I)x3MJwcYOy0eDxv!ROj=h-SO`(7{-*3d{nSIbeCdN0xn?TN znR{4-3n=u1)KdnI<5Q+b{*><==9F(swWMwaQOX91AP*>J?inT$E+*=mbY2TD3X_n(=J)~5+UJ)P18$F7G4=8cW--Tm-7&1pfWqsd zk6Qk6XcWrD9(E@hPSM}&EGlK9jgiV~KP1BY$+bTc7}q~f#P$<^Wm4=b-ge>^YS`Uc zWbl%-2Vas~emj5~u_Pa`7Ld9riyPZraNl)SWq4Ja_3S7qyQo@wj>^nZk^`sjFO{Gd zj~y*r`%R7 z#dZocCQp#4)tB98(x2&h7lM76NA=h5mj@@|r89Ol9b$zP{BcFR=3qEwiC5Xo`Cc#7 zU12p*7bxKKKbrAxY6C|e7F&~5U30QsG`0PerR7=?w}PmuestFtovb zAuJ44{ixhH8||U1YdZt%^5xZVSi*qv-=AdZ<1iK?rqENu;6&4r&S++8ytjDgp`om*0ANTR_6?Cpuedc0 zjaeFqQoSCSPqM@lMB*6JHH)s&#-$0xVImX5{GzF;Gx@?9 zOhsejq>Ri@uF!zQPs1tcUbgtFj6BGS?REImOT#wyxo7@Y%Q@F@6CtUdrt`Hz2CG~6 zY|>42vZ)d#lvqK2#ie?6rMb0^Kj#A_j3%>BlD5YXQ$#8hI|@#9#sT!92h(w>w1rRf zH3vcYeKrI|-9nfXSr)z!ODaU6oi<6Y*@a?_>CV`Ysf69vxg|4GW??tcABOErqCOi2 zQ02I&n;A|_n&>QKhWiFj-RPtsFXqS(1+j{Vq(O>m^}ow+x`}*5VNUM2^=g@pT_>iP z2boE`(@Bc3@lXDV$MPLI_5*b6YFl1)0mtPQT@1zytQpngd5Td6QWD* z?Ne}N*+XcyGpksufgBmr#Z;1Qexwas{0iG%l^7NG5b5KwjH=8yKm@V~Y}tQ5!|^DwmFHxXp3ApNR+>>8~Bu`)6W{T>EB2ZAn_I%)^U6)Yt_W}2e*g;UbwW*{ z$-eL}tiX2Y7Tfl_o%X2>UN#R>-60HZ*4xjiX!5z33VUmcP6TtNdL6{|-(n2n^Q5P= zrY*Ajf5*B^#d9xy+TzemDV@@4-cB!=#ZYd!eD3(8bll;mFKQ)3G5}|+bTAMOjoKL} zc*W{u=L_2&yKx^~7;G2EPsxL?bufKSzv`iZIsK(yw^Zs#M{xRAC~bNbq32DUUB`EG zennE%xIMVe?yf^22zJ{8WW&usSa(a5CmYfxHQf>GGL>w&=p~DFGbNS{Zya}UR_=W( z8yw9G>BWKQ-L0uF4nDpcaS*rrY++|b{rbi8<-2p+r#N(1ii-C3V%h(G>Zt!ja_*~W zMn03>J2;bFd&9V~U$_NvOt$bp--xSqk2&-fN4L zy3!##3g;He+N_pZW2W$)x5IB?hhO3=c{94~x9OmZNox|dS~(=a0t{NxLnELDj_B6@ z{TYs(w)rdFAUgs3fh09dhD%!0X{5CVGddN3Re=trjBj^ql&bD@K?vIv#M}cp1U&==PxQo6A~*Bi0ja=Ak7(eoATFPX$+nQQE%442 zk`~33{O5uGeN}BluBfA8W8diZv(LT77znAv^DXyTel_5+c)qze0|`)*-V6ZW8@a;o zm+O~L#k~4&8I498Ya>%n)K>P<6B_TqPp=r6J)hn_r&)sAw-F*6rzZ1u>DdEdsOh7t52MX(hzp3={F!>$oRho>uTLL`_HVOU=VD5>L zrq3G}#B=c#u_04&!?Z)DnKG;5*N3rU7cJ`YLI89}{oP`0#3X1%LoqhLHRPaxxUD6X zVb*hWq_CuRvG2ObgVz{TmO5Ai{4g_TcPdQbCwbsoJXY_B_^F~kIjjTZ5VaNpdrt*h zz>$N|TJuE!)u0;f5hmnW74Y&H4FS6hZ&ei9cSp)mg_ua)1pKoR<6~cRczR1(BkESH z%kGOJqJj>8-Xh;jiABRrJ+UW%PI&RcfEo=G)XVMKThfl)vj70evQA*No2+YQ`f#C2 zE$b=Y6`Ni{If?X&jBSz2a^nXFmm5oeU`f{@S*QuWtLg`7doaqZs|#CwIdK;D^?k<3 z>JBPF118B7N-!oBtyEqu;S!wXR=r_M)Q60o0aYZ!(n@upiXM?;sHW{N9VyK^lFFW3 zt%Q1O7x)Boc6|j@{rMOV`4Y&hz(q(hI(+93{=)uTtlLylsB!UxvF)2_u@t(o`^pF? zd%cwi=&nTVe;g)|sfbE|o9_KYz%Ph;`lVqarXwfC(1tKK-7_FFS>lZb?J0op5F+pl{A;vn(g+6^any18Nm2RLEo?-=1TVSGV!hKGDi?CWW@9Kni`9qYx#a`LHD zcGYE1N*=-DnaSjfAd_A$#}uc|7q6Q%_9=%jC;b=L?M zK}2n9t&ULAY8m%i2IFaA0c~Utmsc=WqqK_H*d{_>$zVxUVG!l1!eoOsRbFH7q%Cq! zn~2G+^3=(3T|#6m^3}>zg0+rB?%E0p!?Gg?mu{j?OuNM~s70#tPB%s(^!9AIbPi5# z;rg{#g=bG!>v$g}AN1S6D7SBp*`hM>aHlWD1dfR8y2@XCvw_7QTgr^$zks9vD%O3^ z-HgMuUV68sOEWj#%J!upJts}0bnjz|W|S1$TiU#!f9eNn6X4Yi@V!JDs8dp`3FySb z00^P5n%-dcQRIE(y}og#=aMD?H?KLUZ#f`vvHLy(sPnbB%e1sHv~Ry#qGxeDHcXV< z*j=&-pnJWQ2-c-aLK>*dS0AYN3=^m`FQYIPSbAB9O+40D;D zaf$b@*hXc+i(U=02`p-|`9g^DplL51a}i z(N{Cj!&;2vLc49?o%;t~MKR|gbk;W{BGu&nf$2%YGI(c$!1B;gC|kfYqz(sx>F5RF zGbfoZO#cChlV$DSx$}aPwXRt-by~#;Pq-Lix&lOb|QiR(v;O_Y?Dhi9}rN2UZc zYp!v@RZ%h3$bX$(T3o^yO0+}1z9M5gEPg>@@u%pIs8`tYtEX7TQvEs&C5hE8h8aR&d5IfCF;{5kANr_6yh%^uF0d8Ct9n?tUqsg^7TcQ`MPU zhAk#@x?NkQ_iccdv90ilfxLUSr<=HtifLPbTAz>M**}vdsmEcvYlpIJSC>z4zY!a< z=hB)(?WJyY&6L?xafMtDfdc<|0ML*oVR|;^3B2>b;7crKHH_Z+hDGQSH*}{qyGBuu zmjYuu@!!o{ES8Q0onlPiT>Od5iPMeZ^7#|UT5gq#)l-G+AwThLsnjZNk8RsGyi{{s zW`kc%sR73!oX0c?!SRbBPy@!uAkYWjZi)afCpHDAMg9F+CzfjMQ;b*9U)9vV@zlG6RO9 zbWs_&2u+0S2i%Q}9Jh){$Ob@T#^@8a37Z8+KL>6&(W!7NrL(xog!2)JLK~~?buxj# z-pXc>Ep_h+(R+a0wQ*&=xV%PHNv)5HGWL*n=&TSA4F$VmgC0_c*e44yW(nyVfp;Dr z&PofAhSg)=FbTcm0fK5U!V?e;qqjkz`MOsH4_Ijyy*lO-z-Y2=_`p8}B&cf^-MEg! zIVV9o>DPIM0l&pIO81u5K{~H9aOdtc)`96qYOO|nrM+yb`wJrh?aGI!m=g>cRIJIU zH0p|PF#PTs+l8%^)xNu$uu~a}!r|Kwm@tDCZsIHo3)f&Paz+JhM_`n}X@3Sj&(^sT z{Q9&t8S6mYBhOk$r__g5BCc8CXzW^v^g%L6tdrH6wUjCquY;wb-Qr!yH%iBZ9wAme z>O?MWdN8MRaGO?3DHWY}KDC`>aql|H^Hi1UguSF=AJHKRZXfx^R|#r_kbBik34Gm7 zv6ltj`8ciNt7D-pPereyNd++LL|?bl^iiM5I}U6gJJKcx5!(*=q9k=>14Eswn;gc> zz7sgRo!_JwQLvi&M#bY)B6JN`5m!sBuOVV)d5u}FQ~mTaArGNBv{y5lxaH*56f+Wp zpXzm>?weB(W&9oAx^%x;S3d{<6q>B7 z?WHD*@BUL49?3)Paw5d1k*4=|NSuMczZfp6)>c2kpyGp zWj-7VS6#zne}P^YCh%9qSk4X=#eWF^lPqfl5tBj@u-q-oK(Fvl@Q1dKOKaNZ_PG4I zwS6*sHw<*%<}AkYELIZKau`g6zDdJW&YD|KYEa|C{|v#b0gvCc^4ANpZ@_GmR) zf%*8>vqq*X0f#tGnZWa80?*2_!8MfFAKhFmPh?NP71*FSUT6nnqg(!?t?e;qe|sf{ zwn*hA-}}CSm;9OU382^=o1zDfl~EdojjckFC8eoRBD=Rb6>1NnHKKLuLD&X|(Upb2 z@^-)uqPl_p^ktU*wP&oz@n#xJ*F z-qTfkHjB%uL_9jHwo8-Q%rSbIVl???Vh+;8gy05+4GNCzD%=~$L1|K?X0ugZhM|h1 zIw>{N+^N)5NtSSlqIcNe0M;lrxX>=jv6s)7K|qmph=EG}%tc4JOxG>(w#UcSc#lOm`|mb*T&=jmByT zlSaQ}-PFFKjrs;5gq|3LX5t7%1$E`cQr>(ZLC?3>0GZAKfVSF7u|csjXUjY$au-fB zy2-m$L{1U%jOZdN>gAbBg^NYSYq$!}tb?i@|+n?)=%#oJGS%KXW!w zKHaAME<=x9xm-Y!;^h!<@4oE~Zy5XN&NeD4?1?T_Lc_pkzFH973nP`U?F-VoFwENi z_jQBxsO2g)6gk2iL`(_fT$ug?_zd|w;{=6w9vp@M74QwGzrNuSzRs(B2_fbd|0OVr z&tjM9oxqTx{ch=yS?#lZ5#XKJPN zCATy&V7T!}<=>?Sxk3pb(e!RM$sHhLdw)MBmR>Wyvkwha%%-nq zA^72fi67kDPHb2BnrJkw)+;8LzD;0eyV~vc^|KyHie;#vzr)SrYx^H>FD3g)gfi#+ zB(7OBjd}tmh$J4&0wFfRrz3T!nlOiyrbvvD?dgn)(}+2HX)UocPJ-IM6aKe%ouqAS z?JjVViw{W?`SPwq{vdpU)F;2ky!4n9Z(4~^d4!g4r1BN`)5~0MVp?AOdV7$0kedk8 zz&o%tBN#+tqg6bEU=Ti>H*HYM)1?Movxcn38V=|b#!O!*sgmv`qa+TFRzb|=65QUD z2MU{SwccbC0uttsxPjv$Vlqq1Whza<9srJ1C)+@yx|PAdC|;q4M zn84LOqg4$zXT1wikSJ*(BBIQX1w&vN+l0N6$P`~DqQdfOPja0nB18y@T{H%NephTa z@zu|{UE!uN@@BM-2A`d;N zI|2~DI85*^CW&Fu7xCA?w39bl!60;u2yL`~=7q7nKWV28gt6s4*LU(}-A{B{yti1q zlnPJFcl7AFZ(SV5KMPnb-S9U5*I4#m2hJ4R{I&mJrK}?&cOH%2_Xs(UjVs!uQE>2( z+T`uYjNQw1ob?**Whz3TZkpP^e*=tKgsXDW9^LL8uus7~19t_^`^Ok}3vcG7YVu|~ zG+*s1MCJ*)x%AO~ZECmNk~fhpW)8f=g$y|61+$$biwDuWTUpmEdY3!6qkM^Puu)2p zu-1r|JFGMI<(O&4nK{y!W+o4btfPl@0SO-K!4gWP)($+Z%2Z_^^XxSJHnU4t8K?Cc zsqDv}UOZ%sHibv*V%@<_1e5$Q2%0Nr>2eq_k!T}2nY8M-C*GAYK@`Diy#Z?sj51t4 zbpQS*bm@&OocyR{dITm*RM#@j{&>m~F0Y4I+gMGAH&+ybbR92~sO~AMblsy+RNphm zga!Kz)(@~hA7dK9dm~}A7+&o5vt8h*+Z!16{@AcR6;ig?PrKzeb7o%cYOyzO8HN>* zy*a+52Byv*95kK30gfk!1xMUl(lPshy*=>GZK)_z5Kzhn0ZQqiwYpM>o?3^;7M&`b zqaW;mt$H~WbgfCNoIty}mg&fcD8w?HKZy!?aA=HmI>cy1f&8-L2% zPlatn6t2`!4A1=K7d8+sjm!dk&f8`6EBn)&lE^D%$@ zU)AJl6K)*(Y$iybgHxm*+$0f$W~WJ?UGpvw(o4E|Snqs&F%*ft!i(W^_Q%0Ey*Bj} zitz&*-hLmqe?|Y5Ju0zHmMm7v>bSIY{_ytpsq?iH2sVWKW@DQ!%OWQX?bvX;td#kp z!~?ea<~|fPhn|2Eog9F#>QkyRp1Q6lRZ-z2;tVANQ-<(9#ELGJOd2;zbK1nQ$;>f0 zkx(*2hIEG&1Wk<7GVKWWi1k2|*$ew= z;xGQQv8nXj+>Ka2{GE2W4Jf?7zcXRg1Tqp|O+r&8^H#`vonW}(dgjgQ^TUK{G%cmM zNkr+}1mFx=$PAvXhICDIxgl&Zu6q{f*CVr@37Y?5nD~2JH?9-&?*2{yj^6kYX0P`R zk*zJ;M8oVg09~@uBiOHt(i24q8jn{ZZF74uNBWJpMgfo5nB_kzSS`qC9UZOC^Zs9| zt(;#{N8N2_bb577$}T8NjK2ZJ54Z^~{hXDGZdt^^_bt336tl|Dqjn4q>uk%~dr&>J;_%pm&;TInh5 zlQA3zoWaT1D5UC9L|It6Z@z|0N2)QKMn*B7?~&`RM;MnO1w+6aNtI^zZ5U;Y=4GRe zbl=7UX!IUWwIdobr6kIC=f?Bnd^n+_!9FH<3Q0N8C!WM+(RWiw*>}cR$J+~|y><}{ zLy9Lp6^+I^N~JJ;a>~+;nTRr8#>4W=uVR~jSVSWXKotUi!|E}B*3j1MU=myNWtx!0 zwCtlmzy5OdqwZ=Iv7aXXg1>i|3x2Kk#|lOh7zq8Eh>X3KQ7!GdCq5|0hY3oD=P|g> zw#J>WvnC&SXwXWy`N^pFacLI9Q|ymzz#cn;4Y z`1=N?V+aRKe0h6*r;+h$n)r&KD5V*KwFjSOAB<;PLKt zhJT&md&uSvZuBVkb%qaYXF=BW(Dn*3ysvkB3VO$Y=jvxaWY0%Voe-vz8?`MT=5`k^ zs!k9_IqLO_op0qwNkjDs?>4{dT?DqAeR*DDsWl`kp{=7j{@nn=tSe%m7O zx4DVasumvBSxJw#kpb^;fRafYz|L93RN5j*s%{e=nyW%>eQ1tc=8Ep|>Qy$E72%z# zQWtIu!7Za@6o=w!TS&BpkEBlbm~!DEbvsF{#1^hb%~Gb&>3X$VKS$9UP27z`H@BOx zSClK_>7o7;CVmz*qn6LeVo$i3bs3Q)oES{itaTA=iaK3ExJivOdiUkEyQ8KumyipL zn*Zn+o)F_4K>Uc(Iepj4v2EwocneK6hEHMN4E_v#^iOC}g=0^|KVGU9!>GCDt0f3T z=kRJ#y{5m6b<@)~!I7F@bmU>?z>bNr)Jrd*>!VQ!=0Mb>nUipbyoo}BG^vTPy~lyx zeFuWAqoch8_Pa$Z3$RNc_m`z7K22~;H2%xr^MI3wO~ywCYHx@T%{n7Y$;bgZ4B46!ExW2dSzvA-I08m1KtT#S=@U zk$8xCy{DhG@5%lLoODekJq3RIZW=(S&#Zf`Xtua;Pb@B&VL#9h29g-I!@=d&OHk(3 zq%w%zLZG7Kr({s=R%1bRPkc~UhY9NCW@8hxch3^1?M03s3#UQiu@Au0Lj%C+gWbZ! zg-j+bs3Si01QlXLuqoGZMyi(4PpGaZmqg@E$6WocZZN~`GUwkTJv%A@Etp5FtbeCCIx}=ilN!wz!Wiua7O;2Y(9m5jG5bInLZJDa*F+#d;2C zW_|JRyu(184Hham5GZ+1u}19%uAwAyuAw44B`KoNM_v6x>|oX6!alrX4+cs@#sxFN zy-8QYn2I$q<=7lHM#qr!m_@uM4g;DKb-)xClC=jBJ|obDhpN~PDe5~dOhDS5)unijrN+4vp-~@=APhbi69%yz)@(9`j%}ylhGZ)Ie5|8X zD)CD@axGp621gPQP1Az7BF@f&A)+!^05f4LsJJQWK zF>HueK62zMpQ6jRJ<-QGy(a;WGXbX*{sP4Q+J&%?mY{F$*lVG;x*bQ%De2A7EZkaL zjkSVdLtC1R*g4&p@@W8|Z`5&rJ&cs34^b}r28@x#)lxH~F7&44G}u~kN~mpQYS5nZxm;!we}U}= zjuQ3t$y&X!UaXEbaSi(2wXw_wGTd6DjxokETX=o?&Z+&IccyH#H8z$xrp8d#(b3V( z@hm+(q@IGLMvs}H4%v<4wF8i)7uI2(1WoqRq}Og+yS?%>mbP*p|G<)7so*cD>#!we zBl3Lpr}EW!uef#-s&2aS4wVu$-v7Rf91kc zx%|{ze)`~SVP+OA-lI8kJiHm`MSP_De6ruj28=ZvKZl?)d3PzT66>k~ii+IbC z4;OBAUYs<(rfUy5r&z24Na!ca9FbjbP1xJj&sf_qijpM(QvGu!6-?d8myX6hzG zrUL=xT86TBaR19vqm8pJUWAGLTybkM``!|s;@Ioz#rBw~shXnPm3r85=eOb9XX&5{! zfErehgFyA!FB=ge5cg#?>A>3fhkKD9sC~%diQQ3I-FzV?Vtlh?q(nMWYHhbcQZRdr%Y|;=2PUBc(gT^F*?Db zK9J%@ywT13HpdRs+)o4?dZC}T?%SfD)B)ACHRnkC1U*9|UfdK-H&s)9+&LIM-V$%? zf%IXOiupH3M^V9u4zR~jx9Q~FU-g_>*D?yC z-$_qf$1UGxPlkWx1pkn29UscUY%xC%o5tMy{PfJ+^vvvZCO+JkwqT8Al=j?gRR;%Xho%Pie{TCbr*E{AO5c(2ar zun4F?3XZ_AJ;D9l+*-$7Xt;o7GW&45fxa4ab{@AqmY>Ex3a>C;)x+aBiqfEEKFR9I zA>@>zI;|EL$$Ew8<_+b!8AxKn?^B z&90%Y7HA%)Tec?A1+^5YP(Dot8M+=fR8IPau3d{|?(q`feI!ne&S|uVXJ=eR`kO%@cHUdT5Y_ zDqR~?7|D=KdjgM+_FS{*T49Fm%$ktDYI)n48R6{0X{^;ZcUr3zt$zSJg080swoiJ^ zBEJ$5#z!jOggU{Ihk^YH>|F$e?-^t;LE(e-1I&F_jATVzvL);kl>Y;^+upw`Y7SW0Bnx(e#ve)~pME1%1O$Qfop}BHhU-NJO~x#!3nI{@^;h7H-bt?T8AP z@nf=O)G(Wk%mVr+ceU?n9-BO>kIoBYnT3rNytJ`0`CzeCd>HrCmqzha*%9y?nG39| zVNok}cW3bn=WLCdS3BP_p6i9zF^!mk3yW#XbbQSG1(uxMIlSvJ^XIIPFe;wkNzY^E z;mfB@T;acUtU26c=E5PE9*-ZN$W2b?W(&F8>}+WWqWidTL_Ih&H9wclPE1YC&P-1ire>6vJvUjHnwp=To58s=KbbG& zrg4xpKTXfh&E{qf@=r6R=&{AuvVsFqNAuhW`;&%TufU`9L!*G3>tVeLc&~zL1PR6HyZx=48|Zd0eBuk zft~@*bCU{g2X$A7DU5>uqgDrJ3Rr0cvHDE&RlmP-u@izxe#bINjLCYL6bxrM6M(;G z_G?lwo2ctgC|snwls0KARC>}noOe~)b7(8VR#7`65zbAB!RQ_KpqEwoekGuF;g;a*616D2>Xyq-!5hC;K24_Mi$>%^iy0@|BF@Yw#zHuHJacBK9h7 zvMXm2Ri?W&dq`c+tF*6Rd|pT~%Vbd0RpY~4yn|@Et+Bf@d#Nyd9-2*Va&Cq)3P6LS z6Qhu5Gy6vm?%$j!ApE~D2A_+1glAj&*_div=x9vs?#y$$1Jeg5A!5-uPu*?dv2HfS z&BTy2*c>%FFs+-=6nMNT?n^hEMnlNUf}1S0oTgVW5Wmme;Ppm{^Fb7dcXAEnOALamA1dK|Q5>5ZvL6(&$anS(i$! zVrDPtq*xCez~DG~e7p+8W%g2lPMO|;R9P*J=Etc^n$t(j7-fu5#zTyN$MpUg_dfkV zZ|_|=e%JU%?mR=aeMUF;qs7FTF*JmY<_ry^5w`&3+zJ*uLz*(~I9OY4lvilBE6{;A z>VQeb<&YJJqJosHy94n_I?bJr1k)KphKLz$BHWa;ZRLWTY}d+|=K5%EJewcSJ`OmI z8!hR*r_rw(Q&2TxL|LDYuPEYDY2VLu(d2Kkm0Rn!Kc#O64Z*Wr_x(UE#Z0` zyEv6Tvu%}>cj|tI9_YRB3wz)220nX<6BvJ|f9M3L{=OY*P^nW-Z zWl!J)N5>fai+}8?X7``6bQH23&duX^%U|d7g*gn3LFQ)WaggOtbNN|5kmcs)XQtH@ za4O8}PqWk1Hj8tk>(F&GKb?SL82X6NQ|d=|tZH&?)LSvqpM z8M@iHZsw+E)f_PYdEH@dHm^S6tW3vk8ZL)ZKXpjc#CP@30cB?+yP2ES2!Szy&%Wr! z3^G@kCYZ7~=!y<4ZX8hab~f|2oB8SaoW^TmwxEvSbJJ4=f);0F*P%eMz>NdS&Bk;y z3tX#NW6pDoLxS6YJgZiUkgZVca6_LIQ1nU7hTc=%(5G2|M>C{e@tyyHA%qZ1O>%JZ zt4{^wHmFb2xp_64x!L@TA(lC^w@`=k)6+zPbf|Y7&L7OF)tiGkM=#XWtTF-+Me4Pk zo6j5So1fBTGY3NkFN*$!d!3n?n^JR_nM0<88aX#Vr)D?{E03NHj5g*y*mG3d`Ppe& z;Eb{zsoBf`5$5NE2i06*dNMROWrziT59${4Gnx)(4j!Cgkn?JIHOd?eQhHtmLNVcH zs-Ovbb|yEcXE=NCpdy=@gY$+{@>6Vw%H-9Q^t5@Us2kXnbcbLR)p!p ztx64Cm{+{4+v$1bG{~@M&6{;3W1CvXg65RD+|0be>ukXcJd9{qwiv@9H7Awc-G2%~hf+1l?d$120 zqRH9ScFUyjYXsk%V!{9>i&$q~AS3eT94}fXlGN|W*3p|I6kcH?>>M)- zF0}09=zi7`?5w3UO(I6j&CWV$VAvQ8Yx&PHj-z--s!U^KKNRAGMG?yZe1h4R7??gO z&SRcnmZ49I*6GtU6R8nxb2;Fhn_&So@1p}fE3lMiXK+JaGu1R;Rnq{&f|QL=a~;gV z!mC*aHcicKFzABXc?NT)dlJ&>+5Bt)on~}1Zw9&p*fet*z^UoHYBn=HYd*~!G;Qam zcvc!14+K4f8QFo}l4l@kbfJ3IZnZGe(FA92gM18MqGg{xEY80bU9~q`g6g z7~wT5kZ5p#8CVeP3}gp0Mgjvp)RmSxY842v3W+pvg#!ly{iDH536n9;*SFVPG|X?pCd^eq*a@$T^iaB(Iqp+z7exhg zE*BY!PnR3G8k*|!kOdR&#AI!goCLqjke*k)RSs zIl>3l|LRs|rBUY`PdOZofT~DH!)_zqt|&8d%-w6`qd_`zY@*6TMYo?lG!ziUVhpK6 ztmh|U6oc7zRKg3q^WZShEdUx$e|^Ivq`-kb*IrD%@1}#y^JWwG+=b>G$0ofQm_;%- ze}@wmj+;yd`s{C5Y5fb_MCeX! zXc;8U%#D+zvk1jWQx23Dolk0lh{=mYrgE#(P{UwhY`@gn0!pokJFu57{P2S7UXIbQ zE-%Ccq_-JIUU9L7a4k$cwyVvC>i-<;GSx2q8Mp3cO1w*7OeYc~Q0YOQ>4*{o$8+q;}kCPR` z1vj5Mir`C5xWS31N@W^!B=J_ZTCbnULRBip4l!OK#Ly+Mw)CH4(tS}y#`g0!%$Q(A1Bwj#>BeNDSvMy89*@Zu zw(mZ%R9Y?9&YK&yGjus~PS;h<<+o8)6;JZ!NuHm0Wl=kNkeo<2L2%pn!_Iyj8@{UN z=&$a(u)4kW)f9~S!hLqF-J%Ibeew}b!oj9l!*;78I%o$)L{MqDRcw{(rhe(Du6GLa zK>h$O7|@mNMX7i^A4Rd;v3)9>fld!oyXamp=&qWBL-R4V@HsT0F#TPz#;JJf#Z`-E zGdOQ?ZwcT@02ur^5deD$K<`Td9vdbgZ+VR^Q|@B zhS;HXc3yvn3&^NYdA+)VbYi;gsH4rv_?Bod8iwJ?S4Zi7J$YFz&QqN)#Bboj47wFN zH-1MuVyMILm0sqC;m{ldBYHZ(ct$Vd>ljtnUwMnVON?3;;3L7;4bGU?{$YS21Y`aI z%$k%OjQ?*?<@9}?!rwvWyJC%f`^W`SuC0`p5!h=?vN(d^|6>LPcsuCHS!g-+MxYG4 z{ym)~!I?|n9EVbD_MN{$^6bPUkFTm6?kNg(g(D*pFGSZqQT^)}XsHybTP~S3hZBPu z#H5WQwaF%(&+m4T4d}b?zz6V0hXx>2WzQUgBHVVUj$aa~=4SHc5p{>D*PtQkH9G?q z5kEIfVBak18m2hut?B$N0C2LdDF`X3C>(o)OKqS42TDQKv#X_Asew{gPm|anaZx8r zqbd{PNve=(qNcB8+aO3xmh}Gg1Bk`$rxoz>pJJ=xb4sFN!A;x{ML$h^0{N5JR8q0~ zKF96`6h1eFN(h)2(w7hry*nCkq!SgCwHb!<39!qAvp2J?zuv$T>v!ucG2mLqHy3So z7p*lZbz1tJO+1aI|GG!ZHBQW6uL807k*6LsOBeppE>dOB5!Q7t#-CnR1xhEs7dF1a zomLXRft!fU{4Fq-H;d;`zNS$vQ?50fpJp1t-`p(TqGoXo{Sg-l_M{fpxTpR3gp9nu z<*D19)>x>{PP2Y$TYfunq`bObjG20$?D!sNA|E}42K^4AM~-*nELN{Es4OY)w(`yd zYD{6{df>1}s2#@WuQ|fuG{h||(CM;FRVD+;T=Hhk4I{?)jjQCseH(OR5JUi~3_z(Q z|C&nhM1am}yIO3hyM1tj7Svj#+m&lb@pL?4Y7*Ej;f|Cu5&J>vCfE!P#CXcz4E9>^ z45x}G{-VssI_k-sCKluHmR$xj5fZ2+v%W1(#G;O6R4((l3)`Up~&k z!k_id@-c@%&%UUwkk_4^S;Ii|nt{g>5L5Uvmao@VokBP+eZS>OM+{;o|5kNiCE>`+ zs?{7g%e$}gK2@VmYsVBf=x!&rLWU$~tyL`7NNlQt>lh;@I5A9<_T9xYL@q~A>01cN zdGOXQQ*&aV`zv6aW=uTz((vs);4|{E=R5vN{fpROsU&9OSMA!E$+E<}u{(YR?7iMf z1Yd}LEndYFAGA*l6SUh>QH6jqWrIY3FE@l{7S}!S!F_g^;O=!)ZAXd3!@#tY<+~so z$I`y(c^U++fcJzZ(^u6@99Y~EW zFW^)^Va)iu+`pcf9_Rdqx~elrcI#g6i@BkVx{%Y`oa}zG@H+nN!ec!JAvm0e@n@-= z_pg5oUK()!dgi}d8R>{!>|fVW-aTzG(7-8vi~`|GJKuimpS^+q)50zMmYr*tKQ(oN6f#ptA`Yb75_yYIVjCJKFs&YJF!c!5W;sN!|~{lVAu+4lqx zC)Ty}Si9OPBe0p)_H?7Z&Nh}td3CL&&t^U@_GL#^F+oS#&@!Yb-vzZd> z7&rCAmm4`sc=5u3y60#g)**8M?FQ=QcC{@&Blj!-K=KwWhU&)lYnc<((&^TyB-2jj zKfx3|CSQ7r!lpbkRWFI)B*4ozphY7KgPXBd0}A=)zsVA*L#JDX=sH|ML1xbhGJCSA zwt03%#9f=;m1H0Zpni{)oN^Y;G`7}jk5NX)N*&fBROO~^=3b*ahJLb0sl1zrccgMK z0WZeR`od3I;Agpskb=MKWnXl0SDxL*@yWP+oahUBFChCelp01jQkO()2dMTKg*_he z0N8yB(c+fr%qohNqlyuHDS=a7^CN8xy5f{!<0E-%7x;wy>G}##{1t?0VMO+YtmjA~ zB$?&w{J}0BQ}hR7-KG+>Uv$f8rlk*a8nvA(BcQyo`}$F+mFdyAK72rTwVNyt6UdId zoA`vW#on5N?gU0sy`G4go24l26u*Wdl3w%a5=aRA7yuc_?XdtNQD~w+ zF11iceKrit(Mj`eW=p|9BnLxg%Mb2$PbKd6c2#;{ECQzrZWFzLBUo&*jQL)GIN+}N z;_rDIN8InR@ZVqrcm&muA(0!|bEtj{KShZykgU~f6P$tQTjM$uWy+C(E8N{ikx_yi z3Cr~sy^Zsh+XDj4JN6A^Ey62KdnvlDHp!V%Y~fA}%Jos{xdCOJbD0AhR>srnJDD4I zwkv-NbbWR0Bh`h5hbFW|)lbK}1MHM-gcyqDl5+lV0qJq04TzLaHF*2T;D^sfRt$_9b)D2A>Lt%E+T)(R>Bu@Wr z!R()l3B(@TQ`$tM&&RqNpZTLuf%@<1lahOQIKFI6>3te6afZlrv#0GbDOq7VxI(`a_QRb=C9E%+Ziq$q86dkOj%R5bGA5v2RFS&Tt zfTe~FJ*_pAX>isa4M1i9YY!NcPGn)P0*#pgcb}dpu2kq^0rC%YhKR*2LR`58yIu)S z1;`W*$jua&nlKg$;RwOB3C2d_wosOv5Ur#4nGu=4nxqIemvG?szcSa zk6Yq4Q(~LR6;LZIK?-R7=ShI{Ecy2QFz0(wc2vxgz6ItM(iaTW!j|(MqQl*?o|wg8 z{q#M5VFt76W`8gUgEWiY)z1|7{*_&Jhx^L(zBgNo7UJ8uu zBlv=V7e<(F^5V^tSzp=<$UA>a1bA1+#_NX((8buE1PuH&FzwVda$BmcPK=nc zL10ck?d%Gb`C+2+8dh55hAqGh{1^Z!J(^Rg0%H8z(lrRoX$WY3Y?x>c89L&-Tk;V= zFu2opU9;$#bMVI z-gm@?OohgM4vl8YtljQ)u-YYx#KQoHy%&IPQxt>I0)!$M;<=phHSmHIp7hAOOP;9g zA!SNy@*uwBJ}@$6#=5A9*BDfmBG`cN@i<<-=gq87X;brZ0|&&Sx$=lH#LW=1lKCw4%_=dZ;&>W*1av+#jmv=}rK zQGD$1U`L?@8;hLIi6`^17|bn~X9QcA1`x%uHmRsEZJEx>Ywl36d*U@6Jqu+v@FQsV z>SMl9#NX$|CP0n+DL4ynBj?cW32T zT8!i#I>vbkF;DslF{Bm0tgP+y+#k<;na$g-J+pEibU2_Z?33SMsnRX3W95Z=DdyNj z__8m|=TLT4dEDJ8$WfS|LMK*HJ0NQU)|E3X9Jk!eZd4%($kALx)$vAIIm9T!xrrFW zqYx1)Y&K)6{l#5MBw=VwH&>SxlRQ~m+ypB~vyBcyfxK|3;TK&D0scKeMdR?LPw|O( zVZ853M5L25QHqzr&G*M7kuTgX$g%x>u_03lzh{5Ul9`z@3%|DnNJAhY_;Ud4kTKDW zBiuj_(mHhsmQPJ|VtT{ruWxvSpW;n|1H{C<$ASKRGTGH0SRW=C+|ZR<1yDU+N(AwO zaKbagM8PF=nT&u|eGdTEo7M$wyn6s4CMGgaH-Y*0puMz_v;WI55g#(L$7M&dk|YFN zXdjKfWHVRz%CL3ph1D&(ISgSE$YE)=+(sg*3}UNUuOkYOr%m!TEncqDC=?FXw z)J*_Qy_ZQyzjq~)ub5?umjiR@v1DmWKzwPKOBRx3W=)M2lq|^vK{!d~nnia&AWUfY z-Gs9ZPHg<EdCApJa&f_{pQ;CXRltGQ#HeDQXo<@^@aaG|t5v50_U~aoE6skKTXe z$P?MabOkEnuFV{0JzrJ!F0ke6GW_Xv#4<_$&wbG?!0H@#OFW(i0>t!V`<&Mpy(9TCQ^5n%U7O9z8OK zcyg3oaasP^4DCDhjaGTR{It4CM&EHskrgIc@mF6X&hm5>vhe6T;|Ggin4`^C)p6G)lZs1~=Ht*vSa*IATni+(-JrBbW7 zeF8`I^X96z!`s`Z&TnjQZ_Dszs_=5+d}pDTt?daZseBs;%vaR8s{8^^Ye$)w^sQAV zC$^o5>a_`+r5LtjO(Y1}6du{<|G|^L@!a|7ddNFSO1@tg*I+^K#*KAKXn_N|{Ay=e zxtF+Rq;hwRd3tJC><4+_mb;7}g!Y9H`TkZPoX#>HLR ziW0XL%M-eE;1*R$&~#ex;`$L)-a0}5c>caLglk(a7ETph2Ec0!DoYAXu7LN_v&$oerw1x{)CkpypMoK&4we)rj${w^E3-`c1fqjnm%|0(} z1hC}05%0+`-F6Z$luJRI0fqg+AK=b%!e2D;JnR4E#0mUQ`_sdc_lY!so{l^RXIu!Y*jIB0CS z-mbF7h@`G1s`*QmL5hgj+iFpB9gU14c7O&lFP(#-LuNlh;f4J~tD~V}RQC>u9-#pa+!d(*=@|8gG_UwO{t@$9 zse>rQnnO+KC!Zw0F*bb9y~~u~yY}ZT5t^y7bzqh^)4r)hV05=V^o>Yi6L^y#QZW_p zaiISpF2bjWxd>yanMwfLN25ekT&8)|5TX6Y(o_0#aCaEYM?A**m#YlNvjUNCC8|pnFf@IGCK#L zQ10tv@o?(MwkV#JYZvTmaaw4R?0=}_Y_jlh*UGB8XQ-AX$Npp%o3&v@YfHL+U@(NJ z7(!=Y+W#{q%tC@D@XnPUI>oGFKLkebx1U_UD`A9l{|$Yr{rec;sq}}!mG3skUxO6Z zA1*iKAu!>dB_iRC_HrtG@~3&_2Yvh2K-27!GG;(AM)lq_AU2zc{@B1m7WLUMfWYL< zMXZ&RDgIgObD2Z2fGO{`StZKHE`(vB-%TX%ED>K`leTNlTg3rT^MG5$1JjlT-Li_U z;#M76ug_SXdEcBPjSNZku7#j-Kk?#7<=%c+lC5Tkj|b-Llj1La+3PuZtL3~VV6n^2 zg!|awguC=ifCvQPF2$6CM~h7qAa(l9WL7<4N1F0@DJPfB4{feBP=~yz{e^JK!Ain~ zY&KBX6W0ii*@&1I7V$K% z+8IY_-i9DJ(>Fw|5JbKpxG$CcFVFTrw*0XIMfN}b;5;pZcVrR5Eb#Q;Ebz>K2rQ`E z$)g(^3a@JOe--8r(;xZ6h`M0oC5V|>&{jKl7T@sM#i zn;j&51B=YccPf7P_5^$ySNtdcAB(h4auXplzVk^c+`}ZVYS>Ju0Lr*Uv*WBp9`uz) zePhEkx2B}*zWf1{_koQRISn-~qf8uS-S?DG-L$oXR8=;!uZp}j+=)n~uZ~=R2|5k= z!gLSL{xmI-@GARfmWzQQLje5Qt}Qdl=VFahsq8y$mCfLMvbcB9m9TS*2JR|=7{|Qb z9Nq#jBHxh5@PA9GhAVHjr?IE-=#8B^+IJJ;JJyUd-A{u+YF(ht-2 zFS7*dPSGiBJG>IM*MK7O)Rfj^1IQvRCfV}JnwKDAS z(QY0zuVs*QQKfsC5TLqVUn!q1LrKsTzsfb(=_r`WWM=6gBnl_e1|Ai6M^UQImBW{= zP!Ygp`}Ap;eK`AzBr(-6qrg-hM}+i_V{qxP%ZW2Y_%s5Cla;nE&gf!*EhHO%1;hPL zOqhhu=7D$aNQpl&V(KP=S^4rY-nk` zVQ!Jcws^QR@%Ry>1um6HgD+od=v|Im63HRSui0uK{sF-gSZ>x~NlV|u zZwQ{y4?u1A#CX+bcrVrJk#M>(9{b4piddJa*#CuZv*`!3GLtS2$fOoPsp?$4bTZPu&s#{TYb*xvx z^&LL}tk1*{?JZH1aFGA8SmRWy^grAxnZbFLZqKFyUBHvJMIxAc7@fvqp}$$mV5a-` z!vytBa^dVak@q+->12`IC8D>5|`@FDb-el!_pl6`ef&aMzs!ta9;22^D( z+Ix4;6aEi8LYGL?a2IE3v$a&OpHX#Elz>1W=Q;v@k&xNKg`M^Fatpbn`bGo}1}=dAD2Y$Au3(?BjmrpSi@0`{E_26KxosK-h_GX7X6&@B z(wWkw=4($8!-}iWTJ??cvMLP%48x(*C{>YEiQM)YfzOjfZjQdk49|;DPF2GBdL6)3 z%QYyU5E82;Xr@R)FT(&wuThFo6AMS7!%nF@G=y~)3_XI7fqA?P^5Sb_pr?`-(@tI(w6MGw3A2zuL$@~q!1rDR;evX2I2=K#RV{;klS4g=)dm##Ew#TsO?nM<0Mdc@k~J;}LpC0mJnYqTstB(xn<>kT zjhVq!S8@{lEo0iE&i^>fWxSX|shw2fuYqYNiwZ#} zPE_~?lFf{+?jaTSt!)vAz~&LJoO-B$O*ZSj;$K!mCD8r;ot6HTn}EeIv&zVcflVV1 z{GdJ3I&=%u$h#iKiL2wJ$%eS45{w-sTT&*)n|Ahp2rn=M-9>PpEASMexBhpKo45TcP_aEmx6KB?}=$Ub%IsIEREi6(rVO~HTV)X{Jx zOja81yZ}`>D1ujIcUvem&P8!5Toi}A@ABvN_F^Ue9Ubs}whH{N4>oMu|;@UKIU zVmK49jdXb<5kOCyORENac$mPw!`FFm_jE&EfWpSeR3I36DB;SDRQ4|6F%~A6OsO83nfvLSlv;VMwBKI>gGqN zjx&mQw#eR0#B8(#a=%%vAn7&BXqE4x{hZfAjJ%>N3LP}mUW1;JBg~ONe*e9kxj&<3ctVDv!v!Af!W2VGx zd|hbe-GEW}_W)oaQ?D7x>{xi`+D@VpqlJDAjMW2)Y1NW{7$y=^@qqv{-TMK+dn4I6 zV|?`7mWut%4wCY1pCYe4*~dBCD6riq@`kR0Kwz-POS?uJkelyY)QCClqH$oZ{^H%( zU6Pp<>-CDiOq0W0rjUjj=lA3-TM&WUvc;}8f?bVFL{02LD3e)UE!Ffr1Xji)Roqj% zuyd3flxfmxlo6-E#&~5*LiA0unJuqxKnCFgk8uiHM>M!jxuhr?_}ESDcj4Su5&2}M zU!hEVwS%6wJ44LxndwdkjWxMkdYH1u32=m<*xWaSDhq_<~ZTM z$r`9R-<=N`rH?+y0^hioJ@@t zNMMkD-7F$}9m1vwkytG+BX4{hBCD(W|~=6jDy8aaQj(QsTl5;PCOa z3LhV(KYdyFf6B*9=#Y3Uc9E`c0$jeWuTx9H(R=O+?q zCB>oh`9Ji?D1PXSMvE^YP{6E^;rv+}0x^t_cu_I+(G`F}rZtrzhd;h+Zwz zvB+0;qrnO3#XAE_A!L%OHldOg`Lmrt<>%G%|7_pO|I*>Wn4T{$`k9`~&-Q^Xaqy39 z8_$(o-F~vN?p8_cdE1Y^Mq;%r1I5u;hZweu8aF*uF?q zDf17m3Pj2$QbMy$Sf41@6F-sgaz88~Q49}7yuCU&pv^wJd^ppifC?8`iFb^%2u=Yi zkCcn^sxt!hxweJUc(4+y3k0&Obxt-#lrk58*>YO`2ZlX!aXuJ+-_TV4bBtg8lf_<( zH?uQ{Cq7wxDb`V{v&FSPU-OBl2s3XxLZD=ua(`S-IvEtMXUVpT1Pr z5l7TP4E`5V>=|J?QGjh9z=je?RMsk9({ns~{1}WPr7A2Awd}Dn3=~Lsuieo+Il9(r zZ8YyXaG==OET5gMH&zdz&gX&rOzz-h?qGiQ;26>>V7@?ca>&y)1XZHERfA%7)?t!I z#%$&Y?omNGswz$u#~&-L;dWJ=EsE7UaJo_wFmXz6kEH>U9eNx^wN*B zS~QFER`DyXiGf=T*R2D@hYV?HEd8fhn(M4iNon7{wt;lS3OMsc8pBGg2C9;AeH2aY(ZFJ{Ql+&WsZ{VMjREGCU$Y9x zDmM{3-G@`wB<&Q|X3ry?<8-}Rt)HXli2eJicmOI7oNm{+;Ib8vPYih^!39I_8pz#@ z@sCK^zl1Pt8}=9D|2czXj|A_<)T0r8-)a-vdw%T zCNmctXo$wpMW35n>v+c1l(bE`wKZmi(e3G`EM!dD7GTC7jd8wz+zh2_rOxE~saV(D z*Hy$@JTP*fu|1lpv0SOY+}O928NKX72bLvSMhe7rlaXJigSb|*s`Nb5HGkYbk7ry8 z`EFA*vbkE@hP@uXRotVZL?ynhmTTvWjYe^6`~33qb~c~AUA4>Jlg(vMoS1MA-jmIZ zXHVcrqu*Ci^DZ*%)iD{n$}E3=YjF8<_-;$TZW)C9nR2Q~SMlMMG=i3Dw(niFwGdYR znD`NyXZ^4xCwDBZ1Yq(F!oOtV1IbQ6zWOw~G4dJA>z(`H_T3XI00(IgH80D7JPDpB zDNQYLV=c~tuD!;J?8olTIn(fK0~ovTOxk}nIB7TjWq=F>X^)Vhq*3BXL)suUr5oz) z_OqR5vv z?yDUrpuQ()2?W$AokLxAQ;Y>Rl70FMtY0iL_VlC(pzlK=~Mz(RVID#TgVwYM;ss$RHN zyNtvTd9k;?uLo>SA?u|wEH@2pj~79Gu-k{r%~9P4IV1%suBk#{6s(AH17~skf`hV6 zbpu@V1v{WN&1K#ytPs_KP#CDShMENG?b8^xv{^*(j}lBD*rIrU+zqkJcX%B?^wh!= zA2{l)^vh>AQP+rF0l4)T!iwEB+SdT#hlx_vB7MylNwmNAXa5>Un2>S*%m9Z}I~9|? zzR~?sMN39@o3ECMBl843t;Txlz9A_G$6JhpL(r!*oIn4#Wo$D^-m7lvO~Y<(2`>hK zPZsH7Qcl{qX0g;fs0`j^WGPbfxC!(Qn+s&bRvw1n%^Mx(1xa<@<^;>14e(wszC*0QS8~E}jHOwOVK7+3r{k7ew;@g$2`tl-t+*WguGQt*@38R=YM$`@LgDV;(3Z!4GqI6Sr=lvH&nYCioe%%vYQ`#&8SMUL~ zo93lG(VmskQhOEsU3CuCl7TC{fm%B2c(NDu`j$%s)XvAEtI9PLx?Dv4Kirs9TiuEF zwp*ts<|mNKwG+L=|8bEofm=ka_LXX>0X)-Gms>m0)%AAE?`047vJ>4D`z6*z<)t zZIH{nwp?aRUy9B9G{6K#$}5XV3picg+*!Lcx~kZ2)fe5P=%O-+>dKY&`o^LqJRp`I zu!{}V|7hv1<|n{ztx3!89&I#B?UnlC<~oton@gLxgP^o1TQZd_w-(QqaXCS~L47S^ zzb`IT2@pNY%M3%TjYU@g7z9++SmVI!SL)XmPnQu}wFAz+YNNEV2$+x-LA4$6&K2|o z`GuuLqHX7|K6mciz5p_0)oTq!x><5;Pbv&Q5eWo=@DCn+960 zYMfq<4MR`dFt?js13XtG$~yzarCe&AR)f`-53IG;s~Bu=tGEPaSZS^8y#Mm(CXm+p zqUACR$YK*}Q)%bp(Fo5AWv1X7LHq?Mn6R}1l73U8c+P$W3%Ka_j^ZrP_%u zsn&_suRyvBIO`*AFme+u-@@P3*Trg`7NuouxKGWX7WUhh~ zYL#0+lw$mkgIwy%i0;9n8%c02$%bZo$$#&P()v}bzM(WPa?r*wnq!y>K9qgW+ ziI00B+6SllaGN)dEB(6IwPGL6BLZo_0Om&S9r2cU7zBPL?vDl9iR&TYD&P%&JwSJE zePQaZgPg?hYufNU)qf=tf^aT^k2Vtbqd+_HHUoG~yqEy|Nwj4FtwdE0u!-o(1)dP4 zlYlwIipjuIA~*#I5M9I*;>c9s5K%b|_?-BTI8PMh0W*kKL?7|Tbl`WQa|X~sT$u@6 zB5Lx1Y9hY?m`*$=o)O_$K!~U#wh@O4fp3VPJ^^kL;n_flXesCOuK@lf zCM*S_#7m-==v)SL5O-GqcZkfDK!o_L5-1`rtp>g)>em33 zx(+x=G_MDa5|Ir+I&qJ+!0H^R@V7dTI;Ww987YO)i#(IRDJiCuU>k%3EkrO($uOnD zln7HAOi3`M0LMb-n|j~W^QK-$OVGup-o~-e$);Y$8Aj)tde_vmrd~DmsHr#6LUf|V zn?A;kMILLaki?qK`UX2X1|2Pf1?e{#>`@RE4dxzDXa~}Pn_L_>9yrWJNh-=kNh%gW zB}qL%cl(lhmw`%>`istzq`u8UB}rB1ppvAzb5TiBWpq~WWMCB`UG=e&u0nK{bk)sD zx;jRCNmpy=Ea~bZE9t5*50!NF4=d^FDeWa)J*K^?^MPwK0qLrii_+CBI!n6hVI^Hf z=`87L2P^672<;_Z-KM>yt0=&nqy(p3*a=IiQ5+Dp3HO?ydKn@dnhSD9s~q^lxU z($xjpOS%ftS<=8hj>m2`DwH7e<hM{&pCoVf4zEJ(5FVZJIl5Wpe9q${xdsqv}K1Df`ESaqoW4 zP$v!F*WgbAUOMJLg9|~-C+hcN>VVw0<5Id44A-uv0ljnmOm#>Jw4ZK6E zfhh$35%pFy_SScQ>g{LaX%A`Icq3fgy1M1qQ)HsF-*`5Wda*U!-#BGDiq{Q>dySYv7;r_j7>1!S98;J1PE5 z<{i5wIyil`Y#$o|ryCM+6E}yc*>stTbB$7gRE_sVOHc>bOqn2gdgTk9pH6+BVt=}` zQ!*3`7RkuSz75-DqQ4Rws@^;s$h@*+xq9@~M5=ZtD`99Pb4YR|_bPZPKW!}_4_%f3 zMV25kd;;Y;1YUrjFVQG?|9KG~@&D-sBhwrV1C2W!+sDTzHZc)pz@v-izXRHaZU%V! z_|OXql2DEg3Q-zj<+Qeny(=j}eNO(LYiopNWl?J6iuv?98?Yl77#Wc;?qqd!b!BOA z|8qySg&#f;IXXJ7N=Xq`5{ry*k&uumBFE5Sgwxse8+WU-4QAZG#^{s%@0U#vV1 zJ04=qU;b|9uIS{%A(GtleE+lXw)4Neg@pEY3GyT*jcg&@+V-R20_RVzzoJFGHae|& zt;cdi=f1pXqgB!_&n-&*z{V|ze_`%XL7~X}3?{(z(szR-kUTYO{qP3`v#E=7Lo=TF3M%I1tB(`5} z(;i#O1_p`=x&B0fG9;f1;n7MZF5TUpHQ)UEg#={_xpp_$f336WL4!J@ap84-`<5<0 z8!_EGZa$4m!wN02ustDYyoD^iJDf^)zS>GiJ}8e)!ls*?U_;|o4Ea;97+rIx=&3&2 z+yUFj%L36gTBaG7jFwXq6TG`uZu89# zSYE5Pmz0!T1Rq2`G0CAuhY&{+koDaKsl-j~Ys=Y`U-1X)UCs@!NQvU9t!5Hd(IBzF zzmUvZnI{BMsG`jQmROcojZ{2;rFf*i+y(JV)jE`j@*^?XcOjuQ$!soU$8WC5Tkz}c zoZ!NRtZyz)SI2X6bD2D2WqCi;ZLWH}tHeFKc0>ft?&KS;$^>9rn)#r9O1CJ8iXm7D zpy`;uC2{&0h%VU_V1;UVSB)%zpT!eNwwc{pzp1fSFo6HI>B;XZbZ8=nf+v+wWN2t8 zf|D;PDG37;Q`X#kK6VzTaohh1FS#`@d62ZVoG#8u1Z|C5kDrw|M)njccpARR_eU_Yb?c+( z;Y7Cbq^%e7pM3t=5tUBX4VLEdi}NnwhHw$J3wm}k!{A^kH8r(%nyWv>FA;qtk7dfH zlKe+k`x0P6T5_4hr0do<4HW+G*ExmSuSoWSXUyiWy)QJb_x`D)U355p(Bpye|6P>! zMY=m)p*Xw%>&|<(!2Ji2_YYw5+A&DXbF<+ZhBeRz1HsdBYYRkYa=69u~Ma|8| z8V}Gz`x3}(cfQx0&(sD-S>0XE4vvlWi|@BbL}8O%9v2gEbo1*Nm;G+<#ic`u-IHDl zSH|`{a5Ld@GJSs7J+N6YYmrC?Zwm+MGt=7*K3HRb1E+%{2YEQvX|B8yaobhb@m}7Pr6V1z1d5WUq)M@j(wc9e29jL z-}jcw3{BE^RB(3r&tx&1H^rjQJt+gkZvDnPQGWB6DKTH71`4# zuPwV>S#Y1=7UWo@uW4phU`<{hIIlv1gJY^?nv? zpw7PIxyG-FV^ZjGa1sv_QvpsP*46IQ=HRz}f&0c^LdKbJvZoZY)36Y&{v#^!onShf zPrn%)S__iunwvW*O>*;dXF7GKf21DFB~%>3Wt8FOkW0hi{B(NvrCR=3K1|v|z~_3H11egQtkk|#%VQzgOQ_X%Fd?Qi&6*f9b=1ger& znsP#+`y=_=r{*@YV|9Gb^Y~1qJ3L6Cg7=^Cov}R~7I9#hRR6tJ(|A;%My7`i+fREM zzg-+`HZ+K)fa4=aLCdfBZ~Aik1>&{jR_@~CqfRAPAL&iqM(W8UgMM5X!m9DeN?DcY z{M4p1tTr>dTIe2-M?#gMxi*G*vk{?nThlJnrN<74u_Pp_KUvq1vq%EZND-;Be7aWKKR?lIp ze&smcD2oTHN1xovVZX2I$O!6e+R)B4V2>j?PDKs#YCzJS7bBw_o})r(DaSB8KJc09 zyP_v@$P%qPu3|whS+O-Ryawad+GIkBC>;SH5aRC$Q2(PxiMdZcO+Oxlqrc zS+WL^s(){eCIN9YyTB_Qf7*=>n`h&F(d=F6@mI*3Lz#$OE$9hrr zJ~wmuH8f68gEl*+0YQ9Fnht3m{F_2`u>4`t)*5y}o}t#UNh_Jbc#yM#+-<~6 zpSwVzskN-nPHn3PNqz=hZz|lxzM!4Ky5DPcbD7o6yilj%k3-w{GUAlgG{bvSOo%sw z?sqTL+Q+MdUo#uj_N7wElE2PY%jDg`h4P7gI5|WUYInqKrX6*re(o?Qg5bTz?Ng`# zj$>u-*6N{yEFNWBH57WiD*`b#*^@s6;33qgXJw?1d%Dpy=#ixyC2@Mz;m@+)P-uX@ zhLq-xrId2)5<^(A#-b!g?~;RHj`6g|BL_h$%ky)pQYGx%U1|rV}%GsW;x8%ob4*RIko9Z^oyZx`1 zs^cK4?@O~%f*e_1mWgiHMQ`x+*`_Ik@f~heW=z_=U_cyGOl2(N0pdbv3MTBlf4gi3 zalW>Atip#`c4*=D5HGj?w>IDbeYE*7h)IDmg@ksG-_PGh7BAS-LI_$mw-t`dMoK{i z$09%19S!0fOFrAWB2CLtRIVk^@LvwX4y?wDghxsXiY0wb_xbvCS?+l)n}`JeI!jw2 zjzm&=PHQZPb*{!(om;D~q`C0Wht2AE9~zCMz}5FF>JOHLN4f#Zi`ZN-j7_D(#w*kd zbk%xe*n~u|t$I#a6W#On#*jB^+uE!3;D@NJ%A}+DEtLe1@r`F$27%-B#mQ%E02U&u z9wA|TS0of3wq9tUm}vI<8D+9)I5DQE;zhBc;v7A@-Mhp2=iksKFA4I}_c8oYjx zxu?Nl)ip9s{n;1l94LdM8%nUO4~2QkF7uwfslB*!%YC?bW{4&Bz}y9oEZG1vrXp%; zHRy8D#iC_LtuWst!&3e8hy-1jd^zEyq@d&?kKzmfDTu4z`VeH+QBLnsOn}$SC2}FP zSWcb?e_g9L5x0Ca6NPv3!y*=UmXVdO``P|ZfJ5N+rRTn!I4WT#1cqV5 z618>EjQ5?30d(+de}rg%r_q}-U0kq+6l?&+!O(NKRhLk;{oW^B5bhm|^`IDz$d4Pt zBjousr4m&Ra39lkEj}d3vrIwP&qJ8lPNO{8HvyM*TMRmv>YRK1`0Q=M+266lrZBp9 zs9xF@k7k(AlCH4Er_PgFhS)@BV&A&Kzmu-(Oc`Z*4KA2_*}Qef*N55q9euOaFYz2nV1#x+ zUVj;@0^K))aLYC#^-U)5U;QFEd56Ncf7SgIOD7Vx5%$?uAun_8cL7%X{10_NZJyj@ z_w8->ebHL@Cz155KW5Frhr*xc$pUt$)|zL;W&joEer@);v&3eeQqM}mi9?W+o05s9 z_$Ud*vCj+E)*3toN_pOgqE07d8sT53Kp5V5Le_e@D>Z)fn(_X$gcS zUtwH30gaB+Te>}vGPmDe&8G_0hx)~YV@s&FYu^51^>F1M0q$o~wFL9}*pF;)ENK7= ziEW(IIgmh9moC(HsB_;R6jT^?g`>#w*Pp)a?VIi6AF?I1*T5=0AbYQ@{t}mUM{G-g zn^B@BnDhDew~9%OshIQ6){I`RG&L+?jL+~|*W5|%E@mbB2Gw86YC7}aJ^mCoYBqy& zKhHYGDG?+sLlBe~W7Rt<1GsIR~2k1rMI_A{<*8M*6CON!@s+Eq)L2^N3;d}P$9RdjPQkonoT z&NutiM?8ny^3-r@C|tfgKD8DOVU&4gPm!clmwufuJG2$_u1tl4H9fDbdNgV4gDfM{ ziyMKO^v%&+%HQ+`ucan9fP&9IVEiJq(J?cV>K^}s1Gfv9)+Lr zp}ONq=JWBm=ukUBi`1vc14x23pB?r-F-UbU-``-~*ZHtjndRzW2oa!!bL;VrRJrOW z?C2_XXwC7|)-b_Bg0@a=!!&7`@NRlOk#WW~zXDU}=v2>tbr>DD!vGmd;* z^m4ltzxOW%bd|t7ME30&`?M_u$$cG*n6sz8cPeKoKrr9P9Mii1egbChqYk7zq6@f(CvzPQ_&2Ix$fq>tW z5Y;cDZ-dD%Vx(Epz0zNL!qwE6BBIBz2I(qSuWuiDGuLmi>*q)3!>?Aig!cCK#tn9u zM%Bh)+uPgpwIR0`o4Qt3Jc~|FP6Tjx0$^lQJFVsAY_&VvJ3BT4mt`DW^da}Dj98xy zvd(LJhFx4oH&7cE0wE~u^@i}?a@k`%cstZmQ5tG;19dHQ&f5~lF!JOr1OTa~utQUw zjtwMYc@nN7_4fJ?cN10sy}tUzTuXY*jmUexCt7X!nG#>(0D3x}m!z33M9;;A8*;ry z8`HjM_lRCp)TEtSDu~?G)%Cpg?vkf=MgZ z;9tb6Hd#^;3kjnTMr@-PY{1AUR9`{J&rV^N3kLS{-|!vi>kOS31RON;{ViKM?DK4Z*QTiy)pLv7LWdU}MEl$1&@ zz#qxmfu36X1JC)0iJwIMHpEh5DWX{JbsT#Ivlf| zmnr#0P+7a0Uhc}7go(1tk?Pac1m~e@3h!6x)HEX@6Wfh=EI#GS+eDWXA~yTvBJ1rf z@a43|JwWn{!z4q{-PO`SNxEe`v-;cR{g6BHrz06*WS0ImgJ(bLY+zzyV!dXXnxm1@ z*!0>Nr%$!ih~*l)RB7JD_aCh(PsNVI z)wtO;W@cvNcK^fJ+J!bhp0Ql2#&LI7UO%0L5-%f{Dkt0##8eQPF(CiLH7_PNJLm)HIIiBS&#QX; z@xGa_oCq7@AFs2Za}Js~oqtX}ygc2hcbefa_vj-T93LNWuKgUnz3n7%z8nFeoJ|5v z<{-V}x^KrPTiCt7I|}<%cDDE*$^5`=c23hq3{g?hKfAjM9v*zj)Z)?UmVrY{v@t34 za-sEzN-U*NzU3E`euv?TTRMslU5yE&Tgn=U7ziq7(OjuslCBq=7}&~Ol|3MesS)J7 zWl5=nOYSeOLA+BtRo|n(ea>y0I}D)!`;}}xV%-C4|cVrruBaAC*!&N`h+_!eRrL*|6_46nfCS|#=*fMbjYsz`r`NyDCE{%;i$K_B9S;1 zE?crqGf48WN}TyLH~^v@bk&RHIB)k$hKQlCj=yex#rq`GBSnF)czq{f^@WjY=0>9T zMOKSo1VP4Fc+Ne*{7zqpd{%MEef=99yLWR&K_*aF@?=8Z|4(5|bdVd+z#?e)Gd1dr zIeWfX>FPd+kB<)$l#pBDJ)7PIOUVD_wJ_@Vo&=0_e9F;$73J3qgu!}5CM6XE*uhUu z-}&GRV#B=N-*UC1amSi+3DMRg@NtnZKisgtIr?d&P;O$M7BLXxKRh7gJbT0Xj0cPP zOcdo)?E}8x3{+NfR*%kK3n}?PG|ot)BAMv+=sg!%n7|~%?^PyGAt#w1zT|(+(B&ax zn@+;D@O{#%KnC!j_|1oL7&%~vEIuUS$Z-;+qTw1WOj0XqJe@;y<(`sOCy(UqMVsu= zZBF4@Ak|dJCF1klDj{36_u$eG#^S>0M&N>k1Y{(#DA?%<1FF7+_;OrCXyQq=W?2z; z3y;IzOQ9Q$s7D+1y!t8|UYEqd$c=(w!orgkm);4vMD| zAxnwtDpc>CdbXmugNOjCW?N-)_wr3Hf(n=?vfLAxy zgw@Hc>7Q=zcBlY|;KADjDASLsh-QQM?NPP8re%U}>+7g*Wto$b)QVSl8BG?-JSy}T z=V4VnQHak*i7zmPMvna6*Ta2DOm7Fn<=ODYivk__3Zcl#MtADUw+ags+GHg3xBwJd zyzqS^d@QNb$}`=biJ!dTwOf?wM* z0s1e=zm|~RkDU5n3=)wgL{C(@ZcxnBiwp5FZpc070k9Vot&sf9ZZe{n`s{j_@C?w`YPn=6ztQQl(9-ZxL7)mi2woV^E?apKK$}VY&)ylTg7*F(Avi%cDXzJbN)lo zg!Ho<7!WXfK zu{?fFC^7@9A{O5H>u6T>ZAXFrx^7SWW=VXWK&}rJEtV7bR)2{U{+p+7f&P+nG`nDJ>wERiA9>|kYI;gM+7}CS z6iqD4lMS*_+#FbsScuWTzReQuiv-cxT1oHS<7GaA>uDFG*D;(T-=0jp|6olLN5yUF znZ)&sS-I#-F@70kD?;(9OI=K{lf>*BuOzvjz|b#ai(7Nu1H@b+#P$?XJvdEpvWG`neum!I8?d zsSa9nXuTN~kKo#$OS_agQoii>gsV@%ry4Rx!itP4qm19$JxJU%{>yNa)VSkgg_=wQ z0OyJ0eppyNZ5>cz7GyIt56p2U{*piyHwMo&ir7W5aak|L;?|g-?+_v4wk*#+NyvVx zK3p@T_hS=q>Wze(QPYw)!+SjUleS*{E1aKEH49F%Ozoh7LYueQ=aNB%ISv;ryHUg3 z_&ze841?@gqvh9`+TW1T3)xtxCh$ zjabW&-c-yT<@IH<6bK0zlZe6C*Ov37JL!GMO4W%NA{74WZ0)L;9)Rqb~%?KK^$hBOm5*S`b{LcFYp{h=m(7}>u?iDqDNE{ zb^4T;4d2mNkLdjXxxHW#@x<_~Z)%PC_3)my%JMn1;YQv(ct4o^*A`ognG~6aacJ%Fgy)Tg3BQNCcDd{3!=)1HJF4m z?t#S1eV*Y?vzW>)1sW97Ko^G(b6u(u5%DW6?4t8~XjwdA1DuDiMF4QB^++cvclor; zI;%;R&x)LoA`Dhz4~i_hOBGjH4l)*44;wSUo+=3- zd{#$vF+a_gQ@zt$#qlJw2}?@GW=tt7lCdWHLJ^iv3XG@Y*VxScbyp4BC1 z;VuG%sa3G%#CUXcbO5j=-t)hClFvIm z<_mspO_hCq54;WVjgd@PL{}&J z^4l1pn4XO`SDK(+FZ8ruqEz`cZ* zY~AfimrZ=Lg$-aPB%6Ob@iE2ywqU5kp2u)d*UZ(@yTqG;T9(5pA}fnmBN;8H`ChYw z_VNGZ-;niGspk1X5B}kR^z8$O% z2mJ+r{#9yfcz8JS?&9ZPJ1xMaffG0mcWbtpJ8Lwp0fgkF^&;VR1nsvr4ZAMT$abD# z&R97A3bbc-3%wmx!+mPY&ilsfb#CwPDL1t!l05!+v~dw7bxf-5kJj7#gm{!> zZ3j2E=&3CQJ-yV~HC0trz$eI$1lify{r`TPt#kbaOagmt8KPb+SXfvGfMLYW3J3@! z?nwSmDt$2&9fO%8ltAsu5v!L@xK-bMCpiuatWgpIrj1fQn|TdnRsw$`S~BNlrlEnF zp}~KMIHItKz9l9lN&@>g>Aw^EmZv|R7LD)W964O8%P?$RVk9Bj#+V5Kp8iOkSyxCFTd(e z&PV)U*9C`Y>7WXgRZ5D+w8l5ZzNEh1BL%1zq+F&bA6le|*hNJH%=aC6$q7hEe)}A= znh;-;A%Of|?($%G_U><3RKr(m+j=vypJ^eLsaOE5G(VTUlT~(GMLTF*o-kc=Z=cVC z1?mj-)nH=uBYkYHxaL5d1WJOFs-vg3dg`yLib=|2DY0?J{_vr^np*t1S8(uc!PzzN zcJ!a--P)P9KcA%clb5k}Lw(xuH6EXge{P+@6IAD7A4P|5Ucsg@?_Q_VFfOKNn-LYv z)yS-FeV6d7UkYaw27vJu$71OHXj2fCkpO%>!*W$I=4L0ql@KP@@Tix%G zLrGd-*0^7md$Y#DsCzKce#f1Z@86$MFRuPwT&*Qy^1Y5H%?(}lK5P#0K>M^?E7xq9 z5UE0ckm_pWsWP=Gf;UCT00d>~-Qh zcdmFBp09a9bm|_kl+HtTe9036n!rDW^!dLU>=S0krLTUBAAHEaahX1AUrQE83{d-> zKk=7}(aakr#Rg)tQK@>1-U{h!lfxtIOWW8(;`O2<@sSz=S{oU!CK7Nr9ygry(b`%J z%Ec?7vK6L(n#<3ISSg>NrkB{7qUDV zxmbvS_y{T-r&w=mO0h;j@I_?6 z!GQH}{UZ4YNu~}NQYz`LM-^<0EW8Gvc*7X2$PAUt$pxq;?0pI%F4^z^wg~~1xle{?Qqf5o+gL^(zo>F62?oEjw)0pC{2@%mWJ4u#SrdFjD&lfoBPryBzoz`X zkvL^6WH5)2eD1eb+FMZ=I|vUE5X92`ig%pv~lW}vU(IO zEljw6g#F1ER`V8CK_YD`0hPKA_YCGm{7FPSkuZcw)xpqO0gxxj)4v&|p^7o6iQgMd zt$lQ+G(&V}7XeE_{cIFrKv6dM$gih93l9qarCG6u#@>k)&(TG_mwEadaoF$`8IH|_ zxW@Q}V7H#`U}HurD_`gQ6l|G<_)N-8Qxt`i^0?`VXy?5$nXy|#bsv3ij@a)D?>wo^ zhm0g6;f%Ibv=iRyowHUk%PC>B82O8_FNmEIIDf7ZyL}9sl|RNLPE&MHWv% z$=9Fj?LYNBw54KV-I0UD53iiBAkoezh;<2f39caFadjl!+4wUi@N5q_{%wY2 zJm;9PQz*9tR8j+P!_C@+^7rWQs2hfmTKq5M$kLZMEuZjHU}`E3VBrDtO?kj-aPZz` z>y>?W>SVz*jdbTDxY0Tb?11~Tb|&r@#rbl=^|obyJ&^HXn`VfDcGQl$0~~V+mHBfd zW;-3ed$$k(%m0VSW?%w_7t4L&+t|E=GxQ^Tt>uij$}jC|U)J$Bic=&w)LsajHL==n zSL;p(l20b`M;7$+=0EUK1Lx4t!ZMEnS=z{EQdtxa4c4EYDuGJTw!sj#~ z#QgkZ3Eenec=r8TSe8l>emJ#2-~s~4k?SAv6qRDU!w0~Bk*2H{p{Em#lSZe}%d3C5 zgg*h}+{~KzR`#`L#W_>A>p{N%3R{CNei_ot8C$ppx>vyhE`o|IY6*@YV`!a(I%hH$n zy}$RrpD-y@$p*TFSP*sl`I8VEX7D}@Pcn2gA_PYomiHbly9X77G2p`6=T<=<@K|@s zK&kH60esq_3s7rS!RR>#HF(?x^h9S5XevOUDjcl~lo{o>CDV22rM!;Lbq4(A&t51&K4NKsyU{%CFR zXcPYpCjzp0>9kc}SlL&^7ADUpf)r|)@NTNvosDy_>t{GsqX|lW^EaR*_C{_II1-Q1 z&eRCFv&g?vo`+Wj<&w~Hf6~&`OaGVX-*9~q5l?FWz0;;n#DG5tgs_D?3;oXNNZnOCuB);Q~`h+(M&>y1bqLk+}QfWf4J66!i+NN zDIDLE18TRbZof6Y>c0btS}Zb>f_BMx6fNjL;I97tYHu$)z$XjEWDtbq@;R~JG67Yq;8FiHQfee&DjFuBrj1Gh_ALWy_ZCLzBJc0&Dg_z_6%{pz|0z$- zY|6AL22h*9FufkGmjKVhH`|^*wGOo^zIW65hII$T{PcTzFg2!#$isJs$-fA1Y4tS= zdAA$m6Mi9IZfbzLlr&NXDQY#9zpee!12Nhrze7cyj|J2B5X$=DsL*s<#df z)ToPLG&4>rgvU!EExSH4`WcsFg5YjE?cPAh(#mbViqkW9>c|?lDj~L~Y6kQ(z%+JEo8rFRuL9!Puy$ z8p}(kQ5%(j?)1xHQG?ib`^(>N22i)$djkNiZMt-=w{B#*HwHJ;T%k}NXK~_(ZjgQd zHLAjL`}NV+!QtWXNe2Z>OB$)0lPR0p7iSB8^)5diF)=aGad2P(vU5*PKfebw6k8-2 z?!B|Kb9|(ZRZ^AZV8D?I2ZJ`ub(uPH5LSSLhRHufzOTnr%n#2`tyZErLCtpY`WCw*q?rA$6*?_|BBui zT{qd3@;NiRX$KqokHv5$tzUN5{b%FQ&gRnXzb1cR95}2Exxqf(94Dg% zbOAW-gQ?qi3KPkfx~i=y>W6)_`HUGQvV>p9+|Y8oSR|Kg1ejLQ)r_aoG%$t05#wKq zo$7t>N82T;=E~_53A_oFjo?{BEtB{;kbvpj96nyIW^$LE7jJ7sD z=rCcI5_0~|>GGoil{V-AX)*Z96?D9q`^*^fX2;}t1Mwnq$d1q*G~^K7=@2n}Tc{@~ zm^!zsAl6q>{SK;tbF@bdDYUxgj`}2t&r%3}!2qrks;|B!%^Z{1U1U=|nK$}sU6oI`_Q`mG);5+@rXyQz&nM)XGJ@#;QoT;`TMR(2 zdR*HteS3({Y0>K4>nuo#`yO=v*l>xUMIfQcAKXl2daQr~H8+|#AyM)0UniX&RSD5y z3~))I7;KOmRP@7UhG`7~jBf-USyT_es7r(7)6}Z_U}l-XJg?xvxH;|LVfueZ#dmk^ z7hpc*?&kd0(rt9M`YE5SjAH7!4{w1T@%I|DnEz3+{%`lh{pu_}-|qu;VD$S!HR!hi@{NqLa*Y3|zP4o4{bBn3 z`?rYiF1b;yWs>bca@;<<;h>8|K*s4qsqRojgcz2`*%>K=jf8H78NbB}g~7IDgC`;opF(mr^df2|O7{pD(}2SgVL`uq3qIoRK^(a~rb z8Z0CE(zN%1hm_NJdH*Fp`~4lx-C2}kX&EGHOdctB`xnK&M~fPVYd@BMM~?zBQr^vh z008=oS5y84TOY(d>Zh<|s1Jjog8;=U|D_G@!scnt9Z{kb#shhL$;cR*K!?H23bv__tm-^IhD>8k>v-d(>J=l6vlB6h)U((=}x@a zeHlYe>%?(1FpoP>8D%M=HspdKATgd0;;x2IYJXqU)5Pa0+a-nFcJoI#ahh~^M%SNsqv)g^v+=QgDilMVofft8dt8##l@UQj!jouBhPL5Apc{#{r+BYAL5rjpfK z1EkmqMCUa5?{T=yT%Bd_txll(5r(TkAdm zp3L~3Ou8BQ=@OksfEgiL{9QN%do~b-4(XY_qarq5EPd~;7wu*49IxL7u%Cxm%`nc` zz4=^4Paf;0Nn)HJX|Vv5U{I!IzFim$7-PGuwP2__(d4t9E+)k*aZgSHa1J+DZs1%a z4dn)@)AVJZ@)mW{O_(WiB9i|M_r;{(4+zSBoqj)Jx#OaLw^S`*HyeNi7^K=ZU*>QN z?q0^MviEBx4Ts;7=VhmU6Q{h2;2<&l^7MT)sP|3||Co2}gQ+*zfn$W`l<@0GEH?+L zKgFOT2_4!~A%jmRY(;u@bQK1=6SNVduhh%35bd8}z`;1Uz^gT_w~l|{E0`hY6N@)h zxbQ^zqj+98IUF?4{1ozO>7m%#i;($<%(3?xl{FMB)^f~aZ5TA&_%F4Yg4GG@64t(e z+hm!A1*s%HN^P^rDKDA7)nVHbpi$ZW`P|0u2sm2-3yhG=3GKessx;$zLgLaQhs@gP zV$7%BUOS~H(dSQ~+0TIxgckRr1zsvD?`7hKDQOBK(7I8yl8{%~kukIRftFv1{U2Q> z8g{wME#PAU22_>hu7r+3hf432FDuWL+N&@HS5^;gzn;!c=`4QR;;QlF?=*1e6vI|~ zFr1$+dYj=r=?OjMJEfQ+P?$8VA!Smch>(1TDNmXMb(`Z&&8Iom=BKH=kM`&^H*hld zo>Q7}t1m8|rCFaGME|7Q7q#=CFm=&BFZQnu7?0cdZIvmWK1^55j2@ueZvMR0tV~QO zbT<+aUq;S|SBCx3^)oabK!`sTLnqY@h0f!y$&T)^Lq*Q7H%89?)HaoT`H1$X_J;Ay zz~jFIFhqbgR(KV2P__Rj0`!;A7Rjo;(M|gp@y4?fi^<8$884C=&FL3sV}By-<2d{& z-+Q-Lek^I1E}vw(tMt}Glj2v|qoZf=kVC&t*+LNT7x;UeiB3|MvH(zucvq?UudGt0 zThC%9kWf4MkzDOeCkPH-iXRKsaIi!?-hY&4di!SeCsP;^O2$QPe{OWy+br(2z7M`S zUDXOuXhMwB)J~s%8uGS23YKr|puv_>$qWK$L-9cAH)t|eSxyWC^9>xE&<(fL$4U3D zS52MtWQGLbBUs6>Ko_mXW`2p-LL2V(Z&OK7X#56^VLZH3e|hlvBqoy+SJS>~tDM$a zSon=JvoZzn?ng*uEd#wGA!hD1BNHM#6qK$T#7~ojswVH7srWq|4d)Z$o*??s5*8Z7 zKzkAa@>J%GK~lXLQ{q6(Ps&R?#W%XFpL$+>Ac;ZIN>R~|#pERbdQ=ydli2-lx*GWW z{R}FxvNTEFHuYw3zZ|r2m`xxTpq`a~uS$vi2ntjKdK#Ov3!czV)%& z;B$yawA0i!5d$u0Xh0l>57I|Rw+J@v)&h0?fF~#@`AL&Q4F%B?Tq+VX1Y|z~Clrwl z=SWP(BNE29T{X-j<+iEK4fvwe-abrUXK~GaNhE4~92d0*Gl(wR+DLWQmCdehzbZ^7A1 z3uu}8r0gGXv!FI3cjfWRZR8sDbZvN7eA+iFzn7eYUQ__=Y?xJcg(M6Uq!j3hI| zpuDHZpt_9ms?k`Dgf!!Ef~PKe^Y-MncS=&x zViuLn+S_}uW=k_Dk_H?Qf12hAC8M0MYBM32bc>sqlbOl>qy1E3&$*Eom{r)`p!ZDX zj)u9ZRmQFhlOYeOn41hgNrOd`&SvKE7Sp13h`lMHNRO@}HwTZg-n|LS;G-$9r!dUP zr&5uLUx7{!f})j_Cy#)ZA!~1KQIKVXowwves@OKtpq9&utwo>;^m(v1w-JT)UxBc# zlDbW=WdQodvWxY(jEZsbk5t~l1kb4{e68=J69JcN5;$FK?ZILY@JglRHY0)aOae?M z(+(@|WcH#9ZE{^qtjN2I9pLu8II6&d2jF^Gq(?}8Ng?HR<;U@FIw@veygTXR#QQN0 zA|`QgIvM2uwUV6df3x`c`K$DFbYSv!oGM)beeD$9qo69p`)rJg90zSAlOO$8ll$51 z!3~zUjUHorVWCS#SKVC#U_X`Nk|-`?AP4hCZH0rl*R#q#oZW_WV#cvfs=eY4!b##Y zYPy(&bPEf*4(yzJ(C<9^zKgZp5y^jhvjn)jKtxbN0arjBG~}Za|%MbaX;N?HSa|&Z&mqQRbC$KLnW{^aIAXQP%uq2gY*X zpA@zuaq$$!Na>`|0N#k(ok|U;6Er3;xkZO=XiDcHpZ9}iiO3AymXG3xRh{)eTtqzA zG2Zf6?VX+<{r*}Xa(7E_1?D77c6JHTgDV1hn|FP$K)?D~o>3JE=#aM*u8?8x=;^uD z*3(#=ahSpJ5}u=yJ8pBzEOoym`tB&1tF>wgkc=5XGQ&K1-Al2@(a2MMtukQ4-MC7b zay5Wv-C2Rdjg6-wxmrxj%mI>lZ{9>kM@Q3J-8cWQpZ@o&08~^}DgI@xEPAc=C;4wz zl(8JDUdPNoRJx)yb~olUb7`h| zrG%w%7Fp8)1f~Xcr~kDY9Q`UMM`Hbyo}NB7Apw2}o@vUOx6?Ysa-7BpPh3nR#y5d_ zhKqE>1KoS5g6dO8LF4Gk1+ci+?HDlrCv!1@uR}0zH%@xHkrY}MRSVcLXr<~JSyvfR zP15tpXV%W}3CGiqhyx8&pxM!_3ii>J6f_=zvQ&Sf6_-fhXPSV305*2^!@%};?@$uR zcxa9Ufr1qA{_g+u6#xi8{){D}CaJCD4v80ajCu}&f?9Rk-Mw1>FztaJA;V(o*k=-o zrqw}f?AMqk2{AEiBDDdGtk;W`Hh_=bAE5Wmt61xsn`@w%T;9h=kS6Fr77D-m11!_$ zpxpu)@;~T8KU_`Vd2;{x4^MINs6;|XvxV3GHZ74Z9ZxFL_RT!DN_v(TfVOnKA$)jy zwQoE7-eRuFJs+G!ZHh`Np+5Z+`Gm2F`-T+ICLlnyyc#B`-T-bex^fb)e+nz-!RBY( ziWgsa|L_Vvq5uTMaEZO`A8#<3h~I(_nW?Gi!O4_%@s}?&EiEl`^|t6hw}GJ3(^E@9 zkA{YZI^d_SHf#FdNP7#Ys@k{RchTM54T6ZEvcAtefk zbW2N1OSgoCfHdrT`v1;2-#KTWefAh<497cojkV^QYd+6&$94T~;;VIgD*#goReM=@VkmWJ?-PI zbbD2a_OL`EkN!8Q8~*GwC0ngw^IJ_D;3a&)`MkfuG2X-GaWLOi*;h9_g?}tS=*<6r z>GF2HZ~t7iOwV}prE|-FZ}Q$+`P-E{4{uU=DNQcBjY)~@5#cT8L}_?ti9wotmCq2~ zhir;y!(HT_+B;W{Z+y98u7+kM5~Mk~-d!kz2qpQ?aU z=GD^vvO65&@7q)Jxy3Ntk@(FS{Du7kwo2gkDvitXznT4h!J*nALrq*WR*;##YQ&a< z=fx|eU<@P*G~AwU#29zXeeB_+CH8ABc0F?eRAZ6RMj8v}h=BC}DCSTmN>iql7#2Q_ zU}W{9xUDbM`tySXgk}zvZj)(Zx-Lt_XJ|()N+G&NA4FNs_6Qis+nU)%-SB;y=3{@D z%VlV}FRwX3vI6bnhc7Doe?>>V#(>BOHzHTR#u+=O`lGd8S)Q0zX@~rfE|GZHz4Q-F zd+9Ct6gN@OfExH|fg$_3CziDkh^JTP>H<*hLAK)NU52&se_j z^F5czjI0za>SoJiDG#eK*!Z8j9`px=1lcbtrVbCCIYhTUz8^Yb1A#Itc;i94SYXKC zk!p_r_mw|>l}J1GM2D@VGx-6}@TWqF%T*#u>^DUj(=!zGs2QJYsRRn+pJK3vrohua z>x}aywvvvnN{@D*D$TCPkH_)3EiqB)>F`$rofT{r{4cYSL=x34DznOggm3J1(u`z2 zHssO{W6{$=j(C)W`JR14wEWvrEZx>NDAZQ!!9&< zQ%uJ{U-cD#mw$E!#t9>;(NTxyvG9<|yOF_9oh{SvKrFtuukhuRC_t~-%tn=#FDWRo zAzx^1YV5|#-@n!Xp7cZK^g@t&kv2sgU5Q=rzWm!^KhOb{%&iqp8-n$zb5xF_bL)z# zl6iLQ1JX!T1cRoNRBL0J9jBcl&y|rY4iEVCQMm&h@|7{#-{V!YMt?mk?({F;|!Syd8NW zK`xf{-fA@Gz6AbqT4v=ZtuW{xF>zbkjC}31n10n5OIm1S|0dGE(h~wVOI$K_?TwcA zBh|7Ne($2zf1UsV0SQJ*c4Ttl(BaWAccZ*LnuCuOZ9SP_?JLy!EGl~P4x#c)TQ>U- z^X6^$M;~pj=j$84zc|wgZQ3C`&Z0Q#hc4tp+<`_2);`yb8r#Vl|JQDYdic^D)2>GN z&16y*tCe=X=B!(_u+zOD6Qg~mI=6}q^eRy$wkx89AZ@X{4$^4lP;b`&Def2<&?EJ) z5+7%M?HQO8Cx)^M_~f&oZzbv1tUiTRO0M;?nhf^B0Q2XMo9PL$ay|NDF_u1Y+O_#k zE)!MdaRxFDZhI1)G^>OPg96~#gFnxG8q^RjnWPm8c0DCcq6MHrl;r=*8pAE_7XFTu z2tFoO)h7{72Tn|?ll2OdN3Zs+x{KT5o*OuOc1j-P*EF2eRv0=ll^xK=ImqMAa}1>p zZ5wsc?bJ6bI2u~qvI|mxhZDD4T+I0|bf!So<&W_(PNj#uUA=lNPdBw`)mKS0^1G39 zyk8GP)lkCh1?#Ax4yKv2O#9HswCq~GzZ$xdT+2&gyuvps^l3$_8WY)3 zHig9sxz)O zB4unxZY|g?U<+;9Yw37M!aJ+u?o7thrkJD@Lo1@!WVcxk5()nWUoaVfe(&kST}1&p zp?d$;XA1Q4+a?A~*QVrRT4y_&u8|RjPx9_Th2|2ACRR=55Mge_+mySB{Nm*Db}z6! z)reAC+SQ-|B2N6PL<06DkV&EwuVbg$;8WRNBFoAeDa(93|;1uHw()AUB7@!$ItJC8!K!i=Pj2psQgChiQ zzxz*h3=29g>X{9_)qHq-_^^Z$3I^&aVrih~XwyDS3htF2OA+|>l~Fs3SI|ppFs0+RCS$xxB`{k(sogW_wO|J9P1=}xNQ{+K#t8fQw1i2(B z;qK{_>FaPg9Df{$`)F2JJk(=r#fjSf{DggYNX_&IX!=`IB^0SsO0E~v#3!{7_1o`r zXi2$9VT50}eZ>h#Wu$7G%ttad%kyHq>^Eb1t057EfR{b#TTNV zg739*W4Zkm$bx0*)~0r$rGARL*_)SgEN2MW14A|rmo z?uAuF&#eUCOE=c0^G<=ISg7CXq7Ci!v=U0+{)UfVTK(6px!8W>#ar?RU48PqBx7O? z)xJ;D!PypKv}SiS>_0d%5)8>)ljSw|g(!v}+uO7JeOWUVoqln;k|<`+{H?h;HYq6_ zSaCD}!7~{(_V`^kE8e^A0?pQw-7HMxBS?8pIiqBgTR-E&L;KO}njl%Nr#d;RDJdg3 zUR<^;p8H!h+IrZSZtVvps=CCn2l0%L0=1Oty13C#JZv}1Gd}h~t&}hZ082LyCIg_w zVz$zoI#%VxgY<*o@`ya@TFsjVvXpk#O)uz`VwhWNw(28Ft^4N7C+rxUeA()EU8)%lS z`{B+P(N<=iuOq67pqp{rbdl5+5LgqV83veEvD1n=qm&yd0gV78Ijb5zasUPcB3=L} zYKdP)by~_Hrc8^gwcF^>ckzYhQg&``L`+Cf5crVCO`A#hpy)2owTZ3Q5M)HO&^$QR z|I1G2!Gu*)z^G+J-{m(Tt2dGYS`a(iH&STuQfm-I)3bg|x97?z z8X>=bxFT~AW?bVk2iz|C`q8#1hE`eY_|8CZjP7`E_|EF`{-~4C6+KX{)?U2L`=|I$ z2^J6Uci68#CPlZM%c{;iP1wx;e*e{QpICNlFdTE>eD0Yle@N24rFoZjhBZWI$I;M% z+52!#>w3bq>(_U{I4}>`xPUZU8yh)o?H{2<6%)VptDbZ5@$qf%w6k~^*ay%5>AD)C zo*OX!voztj`=ST?OXXJ%xe!4p|Ljyddge(H{NQIT2<-{s4Q=XcV5 zB{fmTNBVR18lR6>imwI!Fq1p6Iw4^`n8B_QDtTJ^`k_l*Z;_0>-{wOu zE025*zUW8f7zpJTDWe6aZgFMKFnY)!)#AV*Gj+|2l8+?NZD*q=2H6@4)aNSi6IA)W z93K%!FSIlV=^R{YD7OiXifV-(y2QMQ)C`Mw^1FAd`@5RJA~oBZu9K!q9|9Xx`@ouu zLJb1~wVA0*dO&y>k*&-@$VRWvBrsHVz$?(}+iExb6^~%;b)shAV-d<45tSkHri@1C znK)(|#GL888C00 zxpXFM0+LKD10j@eU$01f6wp0_@uXT2L`a^U1@Mva}`0>c(CZi&7_8t(0C99AZjIv974~0kx z8k?+bsk84f6AcF;_!<@16X>FSc*Mbt9r1|WPd<`CFSGy*kjx)3=CGGMjSH9i2sY#2 zSaTCT(~Fm1rDjBl>kQz_K324Ks=nmXg=5(gl#x+N0aA?be^3O5wbeFF#>};UiK)6CXMwH+FN-QAlxN5dUr>`AHcT z{f8ovEfzpl_B)VHCABQ7ymerVe(onNDsH$hw|Hn3T8WY;8=>0D z7dH~FP(kSj2v!DobNcQd`k%hL-Mbk3+=KR~E~k31{}pl7oqMNI(9`0kq7WY>e>{B{ z_aEh~uV@NL=oR?#r4h@>zWbqTwt z1a-6nbS8=7Z&8YKhI@T)WDnOS7eiI$S>E!IzrK`G;FhMOa8C>cf~^2J*b!r!q|twj zZJyW@d7zZwG(*3S-#z6}T~8tF)0p=fUMnLrY%=LQ6KaCpmvV+3;>Zv^yTSXG&-2fy zZ%Cd5CbEyj`EN4;O(c=|bGBRfcWTM76AV42$L(R*sBaggan)b%J*>U}zes><`;$^y z#(Y`$beBp{G=>h^s)~VYWso6!c{mjxa%bkX$HC$sZgTN|Z%1OBOeCvpqZwX_CS~}o zzjlX974vFpDz5CdsB(U$I36P%>yjh}#fP|SW~bOrV$S*-sNS4fAh5vAHs^a3N9qAQusI)OWjn%qyun65WSP0O@Bj+H3#6ENT>-N-h6+RRz+mB1U zuFbd2Y`O6mFPa=v+7hPyv41mYwB#IwQC00L-)W4V}={+)A)4=K9lh~Ug2-aVy&DWt^u?URTBe5fHb&$xusRzwm9TEFFfs4mmEO(u5oDm8O;eDye9QE% zS2^DdKBsj2nRgl{eLLVQZ3dB|d%W``5k*E>d+=xJrUxmvM$Ey!k;f@)jeJx%m=7m1 zY<5;cKKCS))%e-W9@5ym2C!o5`$$(&DzKZhgSgib9*RO1f`l`k%0nnWp$1L@GB{@CT{1mNZCWOT?! z>I!?flD+jfLGi}_rp5rK0qE1A(ihfT;HE?;PfDTK`t!8sD_Vj~mE7ibBfE$g6=d_h zvaZd*7HpBkc>Y|h_@%U5xLZTS_dz*@L*{#lh*1IAZl{N$?&c`scqmh3e#_ElfJMU6 zr{gGbPX(Rlz3N?D#9)|NOeo6fV0pV-sWESoc1&6pFh1ucl2WEN2`|3aFeWCD`Ymtj zy%yW=(4W9qpNM9I#Q7 z5{1AH3G0XNp^(p;E7U42A;-G2U(3pn+*|OSD*QrPL_a4clstRR4rWNA7i#Sw+xt`9 zW>YpFtHgZE(^Cpka>t2h6&dB_BQfc>={c3?$bdIHH~+|^;HS&&!!+TP)AgectST$* z64_&*sL$Uv#zD<$Dts)Qc-;}U;pX1UfPMM$D~RhzucR(vG(pJstBf8D5wP_`^ZcAj z{9w|F1j)TqZ@8L6D*jLW`00Vj+PYosj^aP3F=(6JZZ^35e(-drp2@JnuC?Clq=4^GDddJ<@M9(KMMFCGhQ z_}#!%!0kxE+9GQ~XK)UF&MVWKypa8YC5(cA?~Yl_AH!EW|6d9D$pdg-FD@>!rLRMR zv)q%s16?R8AaG%!YLAwamG9nd{%l+W4O_9p^Je8xP+WPw$dD(Gx0VvDkPBqPoYKSj zLcvk|W6E2uSAk%uaVSv`?u-6ZZoyZ5cdGA(qC9j!N+Llo%jx@BtluZ%=s2ZYN`{05KlE)l5KkfbJKmvRs^>an!r?rQK9k zRc(o+yIyS7LoX~U8s5hw@f_2oh6()3G%R=3)D-OOHuJVVV%{cD&+?>ZlEvjahr4Bd zC1KU>qJDDisDlh{&WTv38ZAa+7X&9L@mGe|U+oz>R5$JZIXu~Ow%wHWBJjuhX3OYKvyu7?dkcZnE`JC+|4R1nh3}A!3 zA6+M-pjgj+LL*&)C3Mk3R!)FaC|&{hqfz7 zZf}+%`NF2f5X8E1@$rt(^}JPN|DWtW(Z}@89eik)J`^R0FnIp_+EY=6pFe-reztx3 zl<}{Z*wZmzNVRwL?%lf{t-*f)#SWWwv6 zyj_nkM>T^bWe5i9;$S8hQ7mehi~AOv`+&=*c+7u-*=kat0DAQ;?J?8FqB1fpPz^df z-R&!R*n|!+J^2ujlKX)%H|FS|?CaO}IXT#nmZE$CCiu%)67u?oAmc#!9v{C<5qCuI zlRnvawPl77_dA+vCFv0wLWvm|LV$)qLe3G@#QY;sLW4TxJsVfUp+2Hw0_G~^Z*n7| zv~P*(i+*MgJjJCYCO9t>sKc_iXD&oX8O4$Xe6;3-C)2kjaGi`PM;;13AmQs)6Ty1M z?@e$GC<>y;u2N`Fij70U+|m?)QvwSD@d%jE=^&zxzrSIe1K{%zqP+tMQFQe5%whFZ zLahrb8Zq`hCle?X)Np`=wva1x#(U@PT`fJmU@*C#Kmju?QTK!Mq8mN%iVSBh;~VkB zyA_7V9x2>UzuA#Rcf( zy7!HPii-tLp{VJvce&4-cR?Zg!@qc3t~>n#;u+{<)8N4?IA1LA$$#mk=76vZ}GJg z`Y1)jTHrPpM8kbkQQ`+EEZZ|NaPLgFV&rHtk^kakrUX{!0N~V)a_ou{=(O7=$FNX| zX}8gNXa&1Wp}h?ih-1lC+hw+ zm-W8LP>m^kOKBoj?;jI^9kyKV! z(qbu9M&?;}(kb>)n2r?PYYTv{;vL5$6E_+T-c_4QjHjpCn2QX5+>{Z;H%nQiF)@=S zgXP;F*uOfT0qKp4h>oZsIQN~&N!a1s8}q5B!|5{I+2|c~*lBWtx7bx+vx}HaY68`L zq*_h)yp&lcEv_dcB_89ud0vO?=;l@OE|>TSzU|^}Y?{7iQg-2~+WwJxk$FAb)1UJm`0!qD!maqhH#hE*1ul};-sVQ`IZPDW`0qq?VBXhPQ5PMAeiG$ z;ijK--gwmHP3)W`4VTuWzA#hGPbKT~G$I$^lHE5&uCOuEhhcN`rTXPw%188>)0)1H z+mNPNbe;2otrL<6nM%HUKXmIY6U&}-9Qx38Hp2@Blgmqr$T1f2MU$PI%d@iO# zrJH%#w?Jd`)$V>waQrg%5?<>wESf&~K`3zOi(gTP7iq1$f>1dw+1>pOl@K<#wfgJR zDWLeGbjNg7iFKmk4Y-33t>Zaoni1!nSBu!K+mRFOW{ivw8J8k>^_+~m@G^a0Pz#*l z6YLO*8;%Gh`>ovVnMDJaXeVfDfyaW*<5oO)Nb>o63k*65|Ew;Xl#s&bI;odv5}`u@ z*MtG;aa9sO3}vTY)EV#m;s_@s!yO6c6_scx5Z`S)Nm+3(@T0JlGA3%Mb|;4CAFQ^U zrYXDz_b~_rd(}hVS6;zm#b>Mtx?PY695BpV=t{xGMC%2sj;O#^r2+2ReuXbj)AEj7>2HZ}f* zLNOLR=5pj98%xQ5w*H@!fb7zrP_~->5rU7+SfB=mV-FtLtd3`7oclE4AMA#q1=F8xi173|O8YAG4=c9Fw`i4eqn zRTkBuv)6283o3_x*$>Ftsmb|bMt8qUHsIUA98`fADRIas~@{(|onpd*Y-OPgKYpLJ zV7Q)6m2lr+41h`syMRf85p|ZoK~QRrhH}!*tX2QT`P`qR^i-v13P{ozj_R{PQnn{)DK&A|HikcEP zo(WpF;)dkJobM!aCIKC_oTC`lH;~Cegm6ML=YUoL{P?RmZGl)G%E&i|z(IT~9d2&+ z^u1Euxg+O`MSqt|JXPq5NnTtp2FR&|O>u$3poN*{D6XCHVImx=H4a8TQ&e)2zvP9@ z?FD%&^C6jgSkBtNlC3y5@ZoyLCte||my}_zS=1-`{@o~h*q(lJHTi9r|0{}LDbtCA{vK|AKdcZ+WPToY3 z5cR5qtwZ4hW?WVz$k*UR5?`^?rhTg4xNAf%9;aXvGyz6O^{V!`8$ruaIN}WQZW6H0bxNlDwQR*XjSLn0HUdNC=M2IL@U8cnnqhmzC zC{VV*{b3QnvZw0S9KNo?p-G}{-tvjwizo31M zG{UYY17*?4F48rF=Q{I6f>&#ZU(3HZ^Cf@4T4c?0hvEpJA776t^lm|2!iIkqtI0jQ z8mzu81(Xq4xom(7vIW2IsAKCPOGEm?X!t*L`^XI+lD`y#o86_olK(i z;V?!DQ+D~RmQU61_qVE9ShK)bh<=B&PHN01R=+G#05jjodDN_;HQOI{r=Xa%+d{-Y z4{>>gCqI0uFF-S6-<09b@dP|&@=tR!h@J!fbaEtlBM>)mwUh0Z+roXn|7l--M})DR z$o(Y!;)rD@3Gllv{kyI+UKKJj;n|3;c~qKLDWN7QH#eD&w#nx;y8sDXro(~1FsdlyWeD{rWXD6pzNC9;g++!b^j#MO7diW zJsc$}?;FU3t|cGnh93M@pA%*#jCG28rn8t9$Dd~VJ@vk7YeRjZ(#O_d*uH3&*P}lEXrRlvH0jV&TnCFfAmN$ z65Ct^I0l6DxJ*K*`|@|H;NH=yYx^v1wDHw{ArGe12*cF?CyZ6d(ZPBhjKc^sZ1v{( z>52@;wQJ-vN4>7K%oo!K^&y3Y{G2>I3oT(32yG3~=f}mxvCXvqOVvqge{T?a^OeaQ zUf8{hIQSlz#Q<89I`gfmzYo59Z@M`ljOLQNT7nR`W6kN3)?7xI*LTY zq@^UOoYmkgPy)&39oAfx2%CVTsUdx|SnSuh;c~cbhNAtVPt&(+AuzuWJnRLJnG@zn z#jMc<+mXViA0O@_5GjyrFo2#!ro?ts01@m0tGm)Mi}u&kYwunqB#8EETp^j3(&w7C z-VB!2Ty$K!s7})rq{dV)=1U>xSa7Frkh)3l`*71|J88o=z3uAPgUl)O5cMuIMQzJQ z@2f%*0(U81O25&qz*#!D2j3(8LP8z*cDM8B?!J5X?hxAR|FZNxkg>DzKH2MSP4_rs?r8^keinbekdyxSwkw=Q#S;CW7LBLz4BhtNA>M(Cr=m9J9-B^;oItlL!2%FS zZXKQdd&ck=sKs}7c0i@UvR{3A>gnw4JiFT`)9#N&fI@{3Gs!6_;UKiKwRJK3=}5@a zjb5&P$TIQxv#2um+XZScgh#ba4}F{7Pli{g$+5Hj@Fm*v#v%ggc5@@EHSm7GT!mSO zODiM_3-$Et;|=M-z%1QomHbzJZZ*W~Y6Bo?_3HLp`pG-rTMiS&S}}=m;1HTKw`PgU zjLd522nnUrdHqR+FkmM7?*C3-zGl=G#2q^^KBpMq&1igoaMR~pD$V=&2_r!G-@JK) z=*Kr}chwPp@_pkMZyKbdvv-`ujAGdmqhdy#XWK`ydy%MuBPaSNm*(7ST9&uDHB&@r zl2O+`ngT32OF>?z|Ad~*f(OPzR#Rg9&av4nNA%K+INe+X#6pDLQQa?ruAup!#ySSd zuI9IB?cscc$!Lm%6E>7XOk$o*Ra3!qwVIi;&G!dG>-(3kTxo@S9s`5*pi4ftoNV7l zp&^C#NpHP@gu_fqqZ;x$V84M+!tWlMi&!xQBS}-Z{Jf&H(I#~pOoTxHa{|QWxtDWW ze=Uu9%DuJZzv(MN@3#$1Nw0^$&b1j`B>dj~dMtFHqvt8kPRM4t&k@{Ggw7)>N^M_% zvVX@T^nNv3J!)6v@cdrKz=wS@!di)MASyXWI5}nYPQx2X|!B2#>lns*X}amvwhPSC$Qwc~>`{{4 z&NU3tdN_8|Zfz&8hBds6mSg=^?C*=Or~ftTG^q92Ku5iwGAFQ!Ad~y~s!@yeEsj0{ z>q5|0C|_toawbQbM399sx(mwO+{9I`1Iw) zlF>a9)WfZDD{`@x;(sru9tGrYu$Gd5#nSu23p&r2uLt!w-m)q@6gP}SH=cW)NL$FP z{+=HpKbIsQbBW@^0FDu9om^#G2L30?(-*sdu)DLvfqf<5>weL8PLsI z4OZC9snsKPUw$rT4MD%KL@%B7G?+k3ZeALlX`Sar`7Zbd8I)M=$Mc@;JD_t!rk~Do zqS%OeUSX->9YJ`K0Z**HHaeRFzbH<9A(i?(M8`^1Nw4@|+0;xPurtx$`@G(VvJAMU$)nGB%II%q_d_0h7a={GfGp@rs( zYYKEHpQ1r3B8?2AI?HB^Z6n>5x_$Sv48Ex3ztl90`6I~IV%u}xEfX3p&p zcHk64CK^5J%qlbClibmSKZmKb$?JYk=Q%a_X;8A`zHa!YG}^W>X8_pZHvriiZA3Sg zv!t(fBU-2Ii0g$1aHW zz5HalBkjNDGOSa#?G9$1#SQO`SDjlz59gV2%ddWZtxKwl;*;;Ne55s(oE$A&t8X8S zHlq6kdhQhZEyVoA!}%U04vK5;+jP9=ioI^4)%>+4`i4m!h58l3?JMlo7w*(P^0q`m zq7YO!A$Ql^wVMcM#*)7HFbxT83?}@5P6*=LMNY*-srnFHslpJz z0E44v-(94%_1*7I8uIvZ$c*Z*>S?)e)ixUx(-+1gA(!Ts)@Jc-|8U=fr{Cg5XwZ;v zSQw**7NJ|qjA{gj7Qd5JLj~yP|KzrsZH;rkPP5s|FFSm!djpC)IuAW!uayYkG!Jk7v9-BGMho+nx~zE6P~UBS?o45=#`9&j z!NiJuI+~vzT2nSK@@dXN_hVncbl9x6;0-dA=F94V+%1pB-)Rq0)LL(cl>iG7YkrC5 zY6lulMy8{lQKH5q5o9>UH;mopkbLx}b+Yp0B@{$mUphnY<|J)DdWLgH!#HKn6D@FW zH~xj3r-oc08uXYnb`{Nx#IBPys(`2iD(1nz1kVDet=|uCU9T|QEm(!~q>b3XfiiSO zg%Jhw60lK2Xb^zDzm`C}OZ(A_jXuVw0VbWN25Awz@$7B|;ZqW_I9xf!N(S|{vY%Em@a+>4C z#pa}6PsA@Qf08y?j~m^Z^?do6?&e76!S$25;lY*@Hu?+701p4YeLJz?_IQVT?$zIX z_NVWIa|!edP@(V-6cVyhp3MuSs)8QGh3Bx~>cP*-1xh}{z%+%L5mWgoPpa?T*~*|* z0?yRjz1!DE2Z5@(Az>*8-`7wmn8OAqNF^*P za=UJ-Nga<~QT2ivH~8X;ytRo@$dE?>qt>b$etp7=6TMLUv|P|$Iw?CD3Nn!}6&VB7 zLxY9vU|>$;0HK^#xN-J<#4?HTvAe|&i%iY;|s>lB;)zNxdhg#?3mCtWTNjQoPe|nqqzN9N0I>s=fHcK%B*rZo~L` zSOOVkcS(Y)We0TS2ArW`j`C0D`H-We`WSO`s6Ce+O7DQ9MyE9m*>R0AL7|LpTt_RJ z16Cf_VpHShJeR2{B+{Q2rVC-%N7L{{DFcvf!oRZl;AAjDiU~T-d2sWa*=?j1SDNjr z7Y)xw*9tq;u2%rY+jPwm2%3k`uCzDI_JLf`dvs)9pxyLVR z1BDT0+^4s=XlszPsXi{1)SvbTe>%)zYta{!8$aD>GkAD8JeZ+@7HWOK_{X|)zxytA zE0Muj=nhm$xQc@^+Sf2qU>6YN9(0TiQ8|QJG6G)-7<8L9TJW%l$p0+7yCFcfrNP<1 zyA@)KLRAy_`aO8NM9^ zqrTZe!GG09#^^@QV5N1_r{9mtP`=44A7;xmzUR*-+&P@lxQwvYV$^CBsms7Q1zY% zGxDc5vh-MISX)6`M=-YK$f8W2d=|M1vOi9iY z!4P8W@XxviwaVTu=hMUTt4dyovDYponK1c=+9BL4mB~C*U(edgWvjWl^&AWoM6?`M zrEWRC4TmKTYF|28!x@sqzCU`HoCuRK`Mbk|;#V9ybq0$|uBRo;!^}T%rxF5~4;5vs z_l1&z0w#>|eRFCq0LXf}l1<5e1U&?e;7vRn)KdG11!Ept((?~qOVU;vOjU?efa4?x zl*ET^dzEAuHvy#TkWojo<;m7EvvG4mbzTvR@aq=`#t^U@iR+-H6l}G0&D2b;ANkRx z^u0-G^-;f#4iI(r?LW*m9d}e2zrZ5)%UJ-j=N{X)(S|2)$Jd27>3CoP?8G-P!Dvd& zZMEE`yo1+wXvYS-^9I>n!(WX*ug$?YSoXm2dD)u`GAI{!9T{$|LKEoTqM=|S$>CuNt>#9R!3+J3%8RJJ z0RX+rX6pY&PWI22gN~K9JhcLNWW;$tUr)3BQIh0R>#^v6C`sPhV)-A-dnF+5cEE%0 z)?MWOcieghT>5jZG^Q;yrk;L_iT%8$7x^Rev6?yZwmupFV!d9j+S(H zUL_Qw*t&|tH!yD7?gVqgde&fo{myK%QVZqG}v8nXEAX zt*XdeKu80dw9G)QEsy}@Yvy1jR!79Wegf2+8f?mux+$)Z=Ga0Cl&p@hNehbLRG zrPN79wz&g12KxK^eL+1Q5kp6aZRFG=GS=WDgF+aC#S_0xM&T2(i;3N@4W_-(H|dQh zML{{1vkzL^%u0hAP?=!`?gk{`10_{5}uHC!rYo6LQ0w{O!IKm1f09a+!&Vxc?;qnH9HdL98A; zBA23fr5XN6$^0tui*)V*6NlNgcP)kw9{hYYnorcHurg^MBpwEIAHn9m0cQ^FYb%=Fe>Ney^ z$RCC~5~TbSbF`mW@B`jb4kRRZ?%WadIrl`#agP8eWT*Rj9|{F%`}c#ZK)3gY$qq1f zbA8=$z6DR}WTRBRz6hxfJ>2d}T>7q0&EzY}|1H^Xx9#3`@ygAJax`JKOv$OLp6e~2@oEKV37*1tQ2o)Ynw+f@wM)|#m=kRKHiK9La#er zFAZS4VoCXBJzJY0AsTpaZUFwfL^h<&d6`@jsv7$P?9hH)?h z&o^7ba(-^ww~s~j;pOF`{6>|e2zdYoyS0uU?C;MtT%0uQR5Y9s)z#Hqx^$_r>uQ6P zRRzU|Fbd3Dq=BcjedkQCB*nD@Fo|!GV&3W?86Rn4!}Vvy_20&Vc~!^{nvDNHfAIdT zz@@9dvkW5~Sz`j>6 ziF7055bJ}FwCquOtaSRR*0FVVACFJ=Hk~e=r7GMu(!eil1pjUz46gdmo&2Bw&?^qg z7w-U29C5(20j4y06XXdqw6CL@o125GrxGw_o{CO{ZrPSS*y-SiVTCd}{7L2S@(D1` ztcPd_O8?y$$B14CuJzh!rD?9;1i%H0^I4`s1iJX2lK6M;Bpw&W$ebUB7R|XcLmiqE z7!+hMivSuT)I1t#g#DrIN{=3KA+Sa$jKd+ze&Ys%hSW|=o|E?XnK^hoBH{M|{<*lc zG&iUr!?bf;=W)P(^(u*C78wjQX}(-kOa4AKIz5U(Z2tS@qT801oa7V~JBVt>x;KSx zN2K{IHBH(}QZ|eE22uxq@5s%=6LUx};pNlVZ;RjVc-X1oeQj}H`{Eq_lwuO9lgesp zSnZB(TXhGuY3aXSR>HUkgz5vFO{eAVCOAF4B<;w>7g}Jt0su2wpqRSAmhLK$52i;S*8i_g-L`IUoWX?Ftrs4E)OiKdCN6)jG;bN5c3X%t zDViv;Q1Vs0>5bHAi%QPd?l;iy99yS*QTN?EU^MaEQSgM@jyU7H7m9VB!y~XQ-Lt7^F3g48xC8qB8A##6XjTL zixw8(PeN{%e*g|iCQw%ZY6Id&B@K<%aNl8Z{p)Ae92I;b z^727#LnPwnRUa2ej%tMWmzZDAK0e#u+nfDy_iAgz)q3&8T?zvd5+JA4Y*rI|)cf>p zXQ3ULURh{VMGjT=KU0nF=5n<=Z49-Ymh^jvAa-?&QfxM@bhzcY0qw12B5aJAfdQdK zkFtu2UCGqwnd%oG5658a1@hOnCaVTlEYb-@lcO|LRTrU~uu4`0J&uz@2=|ix=!Q5u zJ33|~!o%A<>$;Za_ssRV z?{6+2G1%7*te3z<9KQw_QR5}52Of?@7?Z;)CPtH=pFeLQHtB#-sCPMIctys1>pO2`^q_Nq`%-&Gi7hFPX$GOlwi)5?fK~uoYA*#-9mHOn*P0&p+;Le z9tn}Q<)cS)n>AaC?(Rp$quW61hAYw99r&uesnJN?$=B4$%C~nk=K~f zF^EbQndM_4BqRj0U6FA01pjLi!^6czbdvP2#C_Ll612piDrVTJrn;;*`>A63 zTRV$Sqzq7pq5p8z;cS1j*`^Hpakj+@LhS+kEaI$`I^Av_`}%|e8CPOfWIfZ_xMdJN zGpd;)v4Sl2duP-NH-auk9=mb`HwItm`!c|d*> z6v1HaRjIz1f@!avq>^i~eMaDT{0E%|kg<~21uVI{wdv6IgKY;Lbj63j>WbR(T)9EP za!5t?da`o16R9sp=pD6$7sj?2}Yp&96-Bk3y(2k2M@#;VaGVD3yy2_ zD-K1x!W<^ZVUu%kM_rwnl5==u1iNNRTKUt<`ZlZ5j8C6>y24=+a44d!T|J0?8|Jx; zL@bVuj>u8gc6Oqzt^F!C7Oiw#YI9UQu+uY_|K2a~Wy|9;ChUOp+V}Nq%AK9Iwl=c{ z3m?JhKK=XmL)Jgn5W|HcQ={Mo(9f8N6+rI)^}+A=_okIE4j|~1H(?S77z8K<9AcV=jTq@;TsWS9i6vjp4QHcdDlsy87>vuP z_W*|CQBP?s?UP=QcOcW+@IXI6uIH#OnS8??q^ z3m81`-{V>TbT8PzkXc9EqO*8{X?<>U->{58)D5$an_*uhS>YdGp*GmVF9MzS`O7_YqnrONs6%iO|m&xoMJ0l9Rs*NF?jigCc0 zPVq7wz*Xq1g@ut@YislFX)8>`IPl1K(NI!u1E65Z z_4m(Kja11uKJcuz9zZU?1hGRWi=?x%=SC9_%VMs2>i4amWf3wj_b!3lesmW`BJ*xJ zh@+p=g_wgmSPFH%Uev(+=Lkpxf8b;h=-ZW=86IxE*vpk!I@p@&yRW0OUE{j7yt})5 z#CtDi8!}Ws#=m)>R!H~RtXlbZb+xrAJ}}Dt5VpW`ASLWp_wMfQNcCN8x;8ARaZ_Bt zR`CZ>D_=})dB4?AQHh;gS#W3Lus_~gJ>4HQ?He5#`2*Om`5uZY&k$I(OD`mu8erc; zE^QeuvMVGcWEXn8QhmFp3o$aiMGwmE)Yikhk`NFqjD9j~M?Tpp7%|*a)!Q#%x;Wv8 z5^XHY#bG;g3Lb2XFYFr|@Kf(3`K6cS<%Pm>zTxwC!{8j04F6saW47Yi1a)MLAiK=j zs>abxkH6c1;ywk5_!0O_f?^^gb-EAQ9VAmdU%r$?Uf;9d>G{cdb#--19kFkvm7cCH z@a)R>9l%^;@-8~v>n~l=u+6`-_!P_}hsdGqsjQ6avpst&Jt`TqSG)>twHqqH4(=>< zQGP+eJhW^7$I|RfOs4er_CA#dF8$xPe!YJU@TkP33)xlG)jxp?tY?6voSmJ)PFlZi z9p3|W>6!2AzVH46Y=yPg$}#*uCY}EQ7(`;-t?|IkIPki}%Ffny?tY+cDqkxl z-1}r6itELknC+u>FT>=Mar(I@^D7>4?pwb6_-iZRRokDPvYr6j=?B%-)jzW}H}3!S zYW2_c`+jL1SS%0BC?AhaC@y>O)6MVxLvQ`PN77SLK2+_Uw;y;x!rq`2?{~kq`!_3l z-N#*Zz%}!KfH&e*?u|R2o|g6rbVC5M&7+ORcgmky{%5N@20T%&4b)WVbyJoX7Cu}L ztX&@b2NtI6bsv%+tlRzWQE*UD1u!C)FI)BrwEE=7WOe_p^QZs*PObqaa$tf5HffvZ zO}_p8_@x`{_kd~3Zr=0b+vMVa;}nm+_JFMW15^P@3g>5;o_^lc_qeirix{X=CeY%v nz@!k=KT!~2=aiu}\n", + "* Communications (email and more) via \n", "\n", - "* **Discord** channel will be added asap" + "* **Discord** channel at " ] }, { "cell_type": "markdown", - "id": "867e5431", + "id": "6b3a4a81", "metadata": { "editable": true }, @@ -127,7 +129,7 @@ }, { "cell_type": "markdown", - "id": "61ff07a3", + "id": "afc67709", "metadata": { "editable": true }, @@ -150,32 +152,32 @@ "\n", "* Karl Henrik Fredly, k.h.fredly@fys.uio.no\n", "\n", - "* Adam Jakobsen, adam.jakobsen@fys.uio.no\n", + "* Sigurd k. Huse, s.k.huse@fys.uio.no\n", "\n", - "* Daniel Haas Beccatini Lima, d.h.b.lima@fys.uio.no" + "* Odin Johansen, odin.johansen@fys.uio.no" ] }, { "cell_type": "markdown", - "id": "afa7d17c", + "id": "bbd60b9c", "metadata": { "editable": true }, "source": [ "## Deadlines for projects (tentative)\n", "\n", - "1. Project 1: October 9 (available September 4) graded with feedback)\n", + "1. Project 1: October 7 (available September 2) graded with feedback)\n", "\n", - "2. Project 2: November 6 (available October 6, graded with feedback)\n", + "2. Project 2: November 4 (available October 8, graded with feedback)\n", "\n", - "3. Project 3: December 11 (available November 10, graded with feedback)\n", + "3. Project 3: December 9 (available November 5, graded with feedback)\n", "\n", - "Extra Credit (not mandatory), weekly exercise assignments, 10 in total (due Friday same week), 10% additional score. The extra credit assignments are due each Friday and can be uploaed to **Canvas** in your preferred format (although we prefer jupyter-notebooks). First assignment is for week 35. Each weekly exercise set counts 1%." + "Extra Credit (not mandatory), weekly exercise assignments, 10 in total (due Friday same week), 10% additional score. The extra credit assignments are due each Sunday and can be uploaed to **Canvas** in your preferred format (although we prefer jupyter-notebooks). First assignment is for week 35. Each weekly exercise set counts 1%." ] }, { "cell_type": "markdown", - "id": "37a46b20", + "id": "5c4e0b8c", "metadata": { "editable": true }, @@ -203,7 +205,7 @@ }, { "cell_type": "markdown", - "id": "40b50d78", + "id": "cabba75a", "metadata": { "editable": true }, @@ -211,20 +213,41 @@ "## Reading material\n", "\n", "The lecture notes are collected as a jupyter-book at .\n", + "The lecture notes can also be retrieved as a standard PDF file at .\n", "\n", - "In addition to the lecture notes, we recommend the books of Bishop, Hastie et al, Murphy and Goodfellow et al. We will follow these texts closely and the weekly reading assignments refer to these texts. The text by Hastie et al is also widely used in the Machine Learning community. Finally, we also recommend the hands-on text by Geron, see next slide for links." + "In addition to the lecture notes, we recommend the books of Rasckha et\n", + "al and Goodfellow et al. We will follow these texts closely and the\n", + "weekly reading assignments refer to these texts. The text by Hastie et\n", + "al is also widely used in the Machine Learning community. See next slide for link to textbooks." ] }, { "cell_type": "markdown", - "id": "1ac7f5fa", + "id": "2240bbaf", "metadata": { "editable": true }, "source": [ - "## Textbooks\n", + "## Main textbooks\n", "\n", - "* [Goodfellow, Bengio, and Courville (GBC), Deep Learning](https://www.deeplearningbook.org/)\n", + "* Goodfellow, Bengio, and Courville (GBC), Deep Learning \n", + "\n", + "* Sebastian Raschka, Yuxi Lie, and Vahid Mirjalili (RLM), Machine Learning with PyTorch and Scikit-Learn at , see also \n", + "\n", + "The weekly reading suggestions are all from these two texts. The text by GBC can be accessed chapter by chapter from the abovementioned URL.\n", + "Each chapter of RLM gives access to the pertinent notebooks. These notebooks are highly recommended." + ] + }, + { + "cell_type": "markdown", + "id": "e11266d3", + "metadata": { + "editable": true + }, + "source": [ + "## Other popular texts\n", + "\n", + "**Other texts.**\n", "\n", "* Christopher M. Bishop (CB), Pattern Recognition and Machine Learning\n", "\n", @@ -232,24 +255,28 @@ "\n", "* [Aurelien Geron (AG), Hands‑On Machine Learning with Scikit‑Learn and TensorFlow, O'Reilly](https://www.oreilly.com/library/view/hands-on-machine-learning/9781492032632/). This text is very useful since it contains many code examples and hands-on applications of all algorithms discussed in this course.\n", "\n", - "* [Kevin Murphy (KM), Probabilistic Machine Learning, an Introduction](https://probml.github.io/pml-book/book1.html)" + "* [Kevin Murphy (KM), Probabilistic Machine Learning, an Introduction](https://probml.github.io/pml-book/book1.html)\n", + "\n", + "* David Foster (DF), Generative Deep Learning, \n", + "\n", + "* Babcock and Gavras (BG), Generative AI with Python and TensorFlow, " ] }, { "cell_type": "markdown", - "id": "c74dc137", + "id": "2f254181", "metadata": { "editable": true }, "source": [ "## Reading suggestions week 34\n", "\n", - "This week: Refresh linear algebra, GBC chapters 1 and 2. HTF chapters 2 and 3. Install scikit-learn. See lecture notes for week 34 at (these notes)." + "This week: Refresh linear algebra, GBC chapter 2. Install scikit-learn. See lecture notes for week 34 at (these notes)." ] }, { "cell_type": "markdown", - "id": "6af0d013", + "id": "a482f843", "metadata": { "editable": true }, @@ -269,7 +296,7 @@ }, { "cell_type": "markdown", - "id": "628fb74c", + "id": "1bfd35e8", "metadata": { "editable": true }, @@ -287,7 +314,7 @@ }, { "cell_type": "markdown", - "id": "bcfe0b24", + "id": "d28f3b65", "metadata": { "editable": true }, @@ -312,7 +339,7 @@ }, { "cell_type": "markdown", - "id": "f153abef", + "id": "1dd7eba4", "metadata": { "editable": true }, @@ -329,7 +356,17 @@ "\n", " * Support vector machines (only survey);\n", "\n", - " * Unsupervised learning and dimensionality reduction, from PCA to clustering; \n", + " * Unsupervised learning and dimensionality reduction, from PCA to clustering;" + ] + }, + { + "cell_type": "markdown", + "id": "f65d481e", + "metadata": { + "editable": true + }, + "source": [ + "## Deep learning methods\n", "\n", "* Deep learning \n", "\n", @@ -341,14 +378,14 @@ "\n", " * Autoencoders\n", "\n", - " * Generative methods with an emphasis on Boltzmann Machines, Variational Autoencoders and Generalized Adversarial Networks;\n", + " * Generative methods with an emphasis on Boltzmann Machines, Variational Autoencoders and Generalized Adversarial Networks(covered by FYS5429);\n", "\n", "Hands-on demonstrations, exercises and projects aim at deepening your understanding of these topics." ] }, { "cell_type": "markdown", - "id": "a6b0c4b8", + "id": "860d45f1", "metadata": { "editable": true }, @@ -364,7 +401,7 @@ }, { "cell_type": "markdown", - "id": "48eb8817", + "id": "8643a8e4", "metadata": { "editable": true }, @@ -386,7 +423,7 @@ }, { "cell_type": "markdown", - "id": "e8889321", + "id": "883a32ab", "metadata": { "editable": true }, @@ -404,27 +441,13 @@ }, { "cell_type": "markdown", - "id": "4ad1f253", + "id": "c36dca74", "metadata": { "editable": true }, "source": [ "## Learning outcomes\n", "\n", - "This course aims at giving you insights and knowledge about many of\n", - "the central algorithms used in Data Analysis and Machine Learning.\n", - "The course is project based and through various numerical projects,\n", - "normally three, you will be exposed to fundamental research problems\n", - "in these fields, with the aim to reproduce state of the art scientific\n", - "results. Both supervised and unsupervised methods will be covered. The\n", - "emphasis is on a frequentist approach, although we will try to link it\n", - "with a Bayesian approach as well. You will learn to develop and\n", - "structure large codes for studying different cases where Machine\n", - "Learning is applied to, get acquainted with computing facilities and\n", - "learn to handle large scientific projects. A good scientific and\n", - "ethical conduct is emphasized throughout the course. More\n", - "specifically, after this course you will\n", - "\n", "* Learn about basic data analysis, statistical analysis, Bayesian statistics, Monte Carlo sampling, data optimization and machine learning;\n", "\n", "* Be capable of extending the acquired knowledge to other systems and cases;\n", @@ -448,143 +471,7 @@ }, { "cell_type": "markdown", - "id": "ed3eddab", - "metadata": { - "editable": true - }, - "source": [ - "## Introduction\n", - "\n", - "Our emphasis throughout this series of lectures \n", - "is on understanding the mathematical aspects of\n", - "different algorithms used in the fields of data analysis and machine learning. \n", - "\n", - "However, where possible we will emphasize the\n", - "importance of using available software. We start thus with a hands-on\n", - "and top-down approach to machine learning. The aim is thus to start with\n", - "relevant data or data we have produced \n", - "and use these to introduce statistical data analysis\n", - "concepts and machine learning algorithms before we delve into the\n", - "algorithms themselves. The examples we will use in the beginning, start with simple\n", - "polynomials with random noise added. We will use the Python\n", - "software package [Scikit-Learn](http://scikit-learn.org/stable/) and\n", - "introduce various machine learning algorithms to make fits of\n", - "the data and predictions. We move thereafter to more interesting\n", - "cases such as data from say experiments (below we will look at experimental nuclear binding energies as an example).\n", - "These are examples where we can easily set up the data and\n", - "then use machine learning algorithms included in for example\n", - "**Scikit-Learn**. \n", - "\n", - "These examples will serve us the purpose of getting\n", - "started. Furthermore, they allow us to catch more than two birds with\n", - "a stone. They will allow us to bring in some programming specific\n", - "topics and tools as well as showing the power of various Python \n", - "libraries for machine learning and statistical data analysis. \n", - "\n", - "Although we have projects where you write your own codes, we will also focus on two\n", - "specific Python packages for Machine Learning, Scikit-Learn and\n", - "Tensorflow with Keras (see below for links etc). Moreover, the examples we\n", - "introduce will serve as inputs to many of our discussions later, as\n", - "well as allowing you to set up models and produce your own data and\n", - "get started with programming." - ] - }, - { - "cell_type": "markdown", - "id": "cd6f4f41", - "metadata": { - "editable": true - }, - "source": [ - "## AI/ML and some statements you may have heard (and what do they mean?)\n", - "\n", - "1. Fei-Fei Li on ImageNet: **map out the entire world of objects** ([The data that transformed AI research](https://cacm.acm.org/news/219702-the-data-that-transformed-ai-research-and-possibly-the-world/fulltext))\n", - "\n", - "2. Russell and Norvig in their popular textbook: **relevant to any intellectual task; it is truly a universal field** ([Artificial Intelligence, A modern approach](http://aima.cs.berkeley.edu/))\n", - "\n", - "3. Woody Bledsoe puts it more bluntly: **in the long run, AI is the only science** (quoted in Pamilla McCorduck, [Machines who think](https://www.pamelamccorduck.com/machines-who-think))\n", - "\n", - "If you wish to have a critical read on AI/ML from a societal point of view, see [Kate Crawford's recent text Atlas of AI](https://www.katecrawford.net/)\n", - "\n", - "**Here: with AI/ML we intend a collection of machine learning methods with an emphasis on statistical learning and data analysis**" - ] - }, - { - "cell_type": "markdown", - "id": "9bc6760a", - "metadata": { - "editable": true - }, - "source": [ - "## What is Machine Learning?\n", - "\n", - "Statistics, data science and machine learning form important fields of\n", - "research in modern science. They describe how to learn and make\n", - "predictions from data, as well as allowing us to extract important\n", - "correlations about physical process and the underlying laws of motion\n", - "in large data sets. The latter, big data sets, appear frequently in\n", - "essentially all disciplines, from the traditional Science, Technology,\n", - "Mathematics and Engineering fields to Life Science, Law, education\n", - "research, the Humanities and the Social Sciences. \n", - "\n", - "It has become more\n", - "and more common to see research projects on big data in for example\n", - "the Social Sciences where extracting patterns from complicated survey\n", - "data is one of many research directions. Having a solid grasp of data\n", - "analysis and machine learning is thus becoming central to scientific\n", - "computing in many fields, and competences and skills within the fields\n", - "of machine learning and scientific computing are nowadays strongly\n", - "requested by many potential employers. The latter cannot be\n", - "overstated, familiarity with machine learning has almost become a\n", - "prerequisite for many of the most exciting employment opportunities,\n", - "whether they are in bioinformatics, life science, physics or finance,\n", - "in the private or the public sector. This author has had several\n", - "students or met students who have been hired recently based on their\n", - "skills and competences in scientific computing and data science, often\n", - "with marginal knowledge of machine learning.\n", - "\n", - "Machine learning is a subfield of computer science, and is closely\n", - "related to computational statistics. It evolved from the study of\n", - "pattern recognition in artificial intelligence (AI) research, and has\n", - "made contributions to AI tasks like computer vision, natural language\n", - "processing and speech recognition. Many of the methods we will study are also \n", - "strongly rooted in basic mathematics and physics research. \n", - "\n", - "Ideally, machine learning represents the science of giving computers\n", - "the ability to learn without being explicitly programmed. The idea is\n", - "that there exist generic algorithms which can be used to find patterns\n", - "in a broad class of data sets without having to write code\n", - "specifically for each problem. The algorithm will build its own logic\n", - "based on the data. You should however always keep in mind that\n", - "machines and algorithms are to a large extent developed by humans. The\n", - "insights and knowledge we have about a specific system, play a central\n", - "role when we develop a specific machine learning algorithm. \n", - "\n", - "Machine learning is an extremely rich field, in spite of its young\n", - "age. The increases we have seen during the last three decades in\n", - "computational capabilities have been followed by developments of\n", - "methods and techniques for analyzing and handling large date sets,\n", - "relying heavily on statistics, computer science and mathematics. The\n", - "field is rather new and developing rapidly. Popular software packages\n", - "written in Python for machine learning like\n", - "[Scikit-learn](http://scikit-learn.org/stable/),\n", - "[Tensorflow](https://www.tensorflow.org/),\n", - "[PyTorch](http://pytorch.org/) and [Keras](https://keras.io/), all\n", - "freely available at their respective GitHub sites, encompass\n", - "communities of developers in the thousands or more. And the number of\n", - "code developers and contributors keeps increasing. Not all the\n", - "algorithms and methods can be given a rigorous mathematical\n", - "justification, opening up thereby large rooms for experimenting and\n", - "trial and error and thereby exciting new developments. However, a\n", - "solid command of linear algebra, multivariate theory, probability\n", - "theory, statistical data analysis, understanding errors and Monte\n", - "Carlo methods are central elements in a proper understanding of many\n", - "of algorithms and methods we will discuss." - ] - }, - { - "cell_type": "markdown", - "id": "17c6257a", + "id": "3331f004", "metadata": { "editable": true }, @@ -613,7 +500,7 @@ }, { "cell_type": "markdown", - "id": "9f4e80cf", + "id": "9805129a", "metadata": { "editable": true }, @@ -631,7 +518,7 @@ }, { "cell_type": "markdown", - "id": "828f3ad9", + "id": "b6ce1fec", "metadata": { "editable": true }, @@ -643,7 +530,7 @@ }, { "cell_type": "markdown", - "id": "8b12df05", + "id": "c3f855e6", "metadata": { "editable": true }, @@ -678,7 +565,7 @@ }, { "cell_type": "markdown", - "id": "6656791e", + "id": "db7df58f", "metadata": { "editable": true }, @@ -708,7 +595,7 @@ }, { "cell_type": "markdown", - "id": "85f146c9", + "id": "eae43d45", "metadata": { "editable": true }, @@ -739,7 +626,7 @@ }, { "cell_type": "markdown", - "id": "51f73840", + "id": "a14136b8", "metadata": { "editable": true }, @@ -778,7 +665,7 @@ }, { "cell_type": "markdown", - "id": "404f8680", + "id": "43ad2d3a", "metadata": { "editable": true }, @@ -811,7 +698,7 @@ }, { "cell_type": "markdown", - "id": "1b74192a", + "id": "260fc4f1", "metadata": { "editable": true }, @@ -841,12 +728,14 @@ "\n", "* [Keras](https://keras.io/) is a high-level neural networks API, written in Python and capable of running on top of TensorFlow, CNTK, or Theano\n", "\n", - "* And many more such as [pytorch](https://pytorch.org/), [Theano](https://pypi.org/project/Theano/) etc" + "* [Pytorch](https://pytorch.org/), highly recommened\n", + "\n", + "* [Theano](https://pypi.org/project/Theano/) and many other" ] }, { "cell_type": "markdown", - "id": "32b6b09c", + "id": "d79f5c48", "metadata": { "editable": true }, @@ -870,7 +759,7 @@ }, { "cell_type": "markdown", - "id": "0c8344b1", + "id": "14668766", "metadata": { "editable": true }, @@ -897,7 +786,7 @@ }, { "cell_type": "markdown", - "id": "40a41b04", + "id": "158a0a2b", "metadata": { "editable": true }, @@ -907,7 +796,7 @@ }, { "cell_type": "markdown", - "id": "367b0b81", + "id": "8ff2bfbf", "metadata": { "editable": true }, @@ -919,7 +808,7 @@ }, { "cell_type": "markdown", - "id": "e16a079a", + "id": "336a64f4", "metadata": { "editable": true }, @@ -940,7 +829,7 @@ }, { "cell_type": "markdown", - "id": "244cc56a", + "id": "53d76bcf", "metadata": { "editable": true }, @@ -952,7 +841,7 @@ { "cell_type": "code", "execution_count": 1, - "id": "1d8845bb", + "id": "c8cbf8e5", "metadata": { "collapsed": false, "editable": true @@ -964,7 +853,7 @@ }, { "cell_type": "markdown", - "id": "a339aed7", + "id": "2544ec17", "metadata": { "editable": true }, @@ -975,7 +864,7 @@ { "cell_type": "code", "execution_count": 2, - "id": "ce4b3b4e", + "id": "e6fed93a", "metadata": { "collapsed": false, "editable": true @@ -989,7 +878,7 @@ }, { "cell_type": "markdown", - "id": "307170c5", + "id": "671ec8e4", "metadata": { "editable": true }, @@ -1001,7 +890,7 @@ { "cell_type": "code", "execution_count": 3, - "id": "ea4fd74f", + "id": "03351553", "metadata": { "collapsed": false, "editable": true @@ -1015,7 +904,7 @@ }, { "cell_type": "markdown", - "id": "6428f55d", + "id": "ab7b4a4f", "metadata": { "editable": true }, @@ -1027,7 +916,7 @@ { "cell_type": "code", "execution_count": 4, - "id": "84e4a8fc", + "id": "7d547fee", "metadata": { "collapsed": false, "editable": true @@ -1041,7 +930,7 @@ }, { "cell_type": "markdown", - "id": "39bd657f", + "id": "fa3d6630", "metadata": { "editable": true }, @@ -1058,7 +947,7 @@ { "cell_type": "code", "execution_count": 5, - "id": "e5a5fe48", + "id": "a1410010", "metadata": { "collapsed": false, "editable": true @@ -1075,7 +964,7 @@ }, { "cell_type": "markdown", - "id": "d74eb874", + "id": "1fcdba92", "metadata": { "editable": true }, @@ -1087,7 +976,7 @@ { "cell_type": "code", "execution_count": 6, - "id": "1d657e01", + "id": "b2baed9c", "metadata": { "collapsed": false, "editable": true @@ -1101,7 +990,7 @@ }, { "cell_type": "markdown", - "id": "7f82621e", + "id": "341fe975", "metadata": { "editable": true }, @@ -1112,7 +1001,7 @@ { "cell_type": "code", "execution_count": 7, - "id": "c4a5e02b", + "id": "4c81d6d8", "metadata": { "collapsed": false, "editable": true @@ -1126,7 +1015,7 @@ }, { "cell_type": "markdown", - "id": "3af71bb0", + "id": "b606be11", "metadata": { "editable": true }, @@ -1137,7 +1026,7 @@ { "cell_type": "code", "execution_count": 8, - "id": "5cf0baf0", + "id": "dc5f484b", "metadata": { "collapsed": false, "editable": true @@ -1151,7 +1040,7 @@ }, { "cell_type": "markdown", - "id": "a70a4db0", + "id": "2ee4fd88", "metadata": { "editable": true }, @@ -1166,7 +1055,7 @@ { "cell_type": "code", "execution_count": 9, - "id": "262e8f46", + "id": "f54969e9", "metadata": { "collapsed": false, "editable": true @@ -1180,7 +1069,7 @@ }, { "cell_type": "markdown", - "id": "0f43d9cd", + "id": "3ffdc5bb", "metadata": { "editable": true }, @@ -1191,7 +1080,7 @@ { "cell_type": "code", "execution_count": 10, - "id": "f12d591b", + "id": "c517dc95", "metadata": { "collapsed": false, "editable": true @@ -1206,7 +1095,7 @@ }, { "cell_type": "markdown", - "id": "7c1cc7ed", + "id": "1aced303", "metadata": { "editable": true }, @@ -1217,7 +1106,7 @@ { "cell_type": "code", "execution_count": 11, - "id": "1f365f00", + "id": "32efbfb2", "metadata": { "collapsed": false, "editable": true @@ -1232,7 +1121,7 @@ }, { "cell_type": "markdown", - "id": "d5cf7244", + "id": "a95e02fd", "metadata": { "editable": true }, @@ -1243,7 +1132,7 @@ { "cell_type": "code", "execution_count": 12, - "id": "907260e4", + "id": "fcebfe97", "metadata": { "collapsed": false, "editable": true @@ -1259,7 +1148,7 @@ }, { "cell_type": "markdown", - "id": "375e0579", + "id": "5d767b5d", "metadata": { "editable": true }, @@ -1270,7 +1159,7 @@ { "cell_type": "code", "execution_count": 13, - "id": "79e19787", + "id": "8c8edcaf", "metadata": { "collapsed": false, "editable": true @@ -1286,7 +1175,7 @@ }, { "cell_type": "markdown", - "id": "be6c16b2", + "id": "1365ca9a", "metadata": { "editable": true }, @@ -1297,7 +1186,7 @@ { "cell_type": "code", "execution_count": 14, - "id": "901ecfe2", + "id": "85c9a904", "metadata": { "collapsed": false, "editable": true @@ -1313,7 +1202,7 @@ }, { "cell_type": "markdown", - "id": "be629f7b", + "id": "15700c5c", "metadata": { "editable": true }, @@ -1325,7 +1214,7 @@ }, { "cell_type": "markdown", - "id": "980cf441", + "id": "d5d413f6", "metadata": { "editable": true }, @@ -1340,7 +1229,7 @@ }, { "cell_type": "markdown", - "id": "d2ffe1f6", + "id": "81f680dd", "metadata": { "editable": true }, @@ -1350,7 +1239,7 @@ }, { "cell_type": "markdown", - "id": "4f4efdd4", + "id": "17c5a1bf", "metadata": { "editable": true }, @@ -1362,7 +1251,7 @@ }, { "cell_type": "markdown", - "id": "ee572849", + "id": "55a9b83d", "metadata": { "editable": true }, @@ -1373,7 +1262,7 @@ }, { "cell_type": "markdown", - "id": "df0a5acc", + "id": "0929cae0", "metadata": { "editable": true }, @@ -1388,7 +1277,7 @@ }, { "cell_type": "markdown", - "id": "7bc72a77", + "id": "f3181ff4", "metadata": { "editable": true }, @@ -1403,7 +1292,7 @@ { "cell_type": "code", "execution_count": 15, - "id": "4c493f06", + "id": "6c2c0ee5", "metadata": { "collapsed": false, "editable": true @@ -1430,7 +1319,7 @@ { "cell_type": "code", "execution_count": 16, - "id": "20bda99f", + "id": "cbe79e57", "metadata": { "collapsed": false, "editable": true @@ -1454,7 +1343,7 @@ }, { "cell_type": "markdown", - "id": "a9bff117", + "id": "f23e1ca6", "metadata": { "editable": true }, @@ -1480,7 +1369,7 @@ { "cell_type": "code", "execution_count": 17, - "id": "9ce8cf97", + "id": "8789f2ba", "metadata": { "collapsed": false, "editable": true @@ -1500,7 +1389,7 @@ }, { "cell_type": "markdown", - "id": "98b2cebb", + "id": "e9f51a5f", "metadata": { "editable": true }, @@ -1514,7 +1403,7 @@ { "cell_type": "code", "execution_count": 18, - "id": "88a877c3", + "id": "16b329b9", "metadata": { "collapsed": false, "editable": true @@ -1527,7 +1416,7 @@ }, { "cell_type": "markdown", - "id": "0928de6c", + "id": "cd1876fb", "metadata": { "editable": true }, @@ -1538,7 +1427,7 @@ { "cell_type": "code", "execution_count": 19, - "id": "d93baec5", + "id": "5b7e1c04", "metadata": { "collapsed": false, "editable": true @@ -1550,7 +1439,7 @@ }, { "cell_type": "markdown", - "id": "7a5b03a4", + "id": "10f0bb9d", "metadata": { "editable": true }, @@ -1561,7 +1450,7 @@ { "cell_type": "code", "execution_count": 20, - "id": "2b5968bf", + "id": "190b1a89", "metadata": { "collapsed": false, "editable": true @@ -1579,7 +1468,7 @@ }, { "cell_type": "markdown", - "id": "281789dd", + "id": "579fb43e", "metadata": { "editable": true }, @@ -1591,7 +1480,7 @@ { "cell_type": "code", "execution_count": 21, - "id": "226cafd5", + "id": "cb5f7e36", "metadata": { "collapsed": false, "editable": true @@ -1615,7 +1504,7 @@ }, { "cell_type": "markdown", - "id": "34d1241d", + "id": "51e35da5", "metadata": { "editable": true }, @@ -1626,7 +1515,7 @@ { "cell_type": "code", "execution_count": 22, - "id": "66de0f40", + "id": "6754efdc", "metadata": { "collapsed": false, "editable": true @@ -1655,7 +1544,7 @@ }, { "cell_type": "markdown", - "id": "fce1b00d", + "id": "f1750baf", "metadata": { "editable": true }, @@ -1666,7 +1555,7 @@ { "cell_type": "code", "execution_count": 23, - "id": "b31ec8b2", + "id": "4069afcc", "metadata": { "collapsed": false, "editable": true @@ -1681,7 +1570,7 @@ }, { "cell_type": "markdown", - "id": "399b4f0b", + "id": "dc04e1ff", "metadata": { "editable": true }, @@ -1698,7 +1587,7 @@ }, { "cell_type": "markdown", - "id": "b3c66ed4", + "id": "ff884c05", "metadata": { "editable": true }, @@ -1729,7 +1618,7 @@ }, { "cell_type": "markdown", - "id": "b7ec1f01", + "id": "10424430", "metadata": { "editable": true }, @@ -1741,7 +1630,7 @@ }, { "cell_type": "markdown", - "id": "5c4c6423", + "id": "d4456d18", "metadata": { "editable": true }, @@ -1769,7 +1658,7 @@ { "cell_type": "code", "execution_count": 24, - "id": "b026b228", + "id": "570b320d", "metadata": { "collapsed": false, "editable": true @@ -1799,7 +1688,7 @@ }, { "cell_type": "markdown", - "id": "121762a4", + "id": "a6e493ad", "metadata": { "editable": true }, @@ -1816,7 +1705,7 @@ }, { "cell_type": "markdown", - "id": "60728127", + "id": "8f1725d2", "metadata": { "editable": true }, @@ -1828,7 +1717,7 @@ }, { "cell_type": "markdown", - "id": "acf5b63f", + "id": "8df5914b", "metadata": { "editable": true }, @@ -1849,7 +1738,7 @@ }, { "cell_type": "markdown", - "id": "40040656", + "id": "7648e110", "metadata": { "editable": true }, @@ -1862,7 +1751,7 @@ }, { "cell_type": "markdown", - "id": "86948166", + "id": "17c3f9d8", "metadata": { "editable": true }, @@ -1893,7 +1782,7 @@ }, { "cell_type": "markdown", - "id": "2c7af90a", + "id": "0cb0e3fa", "metadata": { "editable": true }, @@ -1905,7 +1794,7 @@ }, { "cell_type": "markdown", - "id": "aebc9af3", + "id": "00fe7e8c", "metadata": { "editable": true }, @@ -1923,7 +1812,7 @@ { "cell_type": "code", "execution_count": 25, - "id": "eaa61d49", + "id": "7a17d6fe", "metadata": { "collapsed": false, "editable": true @@ -1950,7 +1839,7 @@ }, { "cell_type": "markdown", - "id": "f964fde3", + "id": "8f557979", "metadata": { "editable": true }, @@ -1972,7 +1861,7 @@ { "cell_type": "code", "execution_count": 26, - "id": "c7fe9388", + "id": "a5e9ee5a", "metadata": { "collapsed": false, "editable": true @@ -2010,7 +1899,7 @@ }, { "cell_type": "markdown", - "id": "14ad007a", + "id": "a2b45b0b", "metadata": { "editable": true }, @@ -2021,7 +1910,7 @@ }, { "cell_type": "markdown", - "id": "7dc68b06", + "id": "97da0991", "metadata": { "editable": true }, @@ -2034,7 +1923,7 @@ }, { "cell_type": "markdown", - "id": "471f97ed", + "id": "6664f912", "metadata": { "editable": true }, @@ -2055,7 +1944,7 @@ }, { "cell_type": "markdown", - "id": "65a80e19", + "id": "4ca74414", "metadata": { "editable": true }, @@ -2067,7 +1956,7 @@ }, { "cell_type": "markdown", - "id": "37e1d624", + "id": "9e1d8766", "metadata": { "editable": true }, @@ -2077,7 +1966,7 @@ }, { "cell_type": "markdown", - "id": "a81b3061", + "id": "4605a6c5", "metadata": { "editable": true }, @@ -2089,7 +1978,7 @@ }, { "cell_type": "markdown", - "id": "792fa6a1", + "id": "882cab00", "metadata": { "editable": true }, @@ -2101,7 +1990,7 @@ }, { "cell_type": "markdown", - "id": "2f6df05c", + "id": "7d365176", "metadata": { "editable": true }, @@ -2113,7 +2002,7 @@ }, { "cell_type": "markdown", - "id": "9eb85874", + "id": "ed69759f", "metadata": { "editable": true }, @@ -2124,7 +2013,7 @@ }, { "cell_type": "markdown", - "id": "a98d9555", + "id": "33745626", "metadata": { "editable": true }, @@ -2136,7 +2025,7 @@ }, { "cell_type": "markdown", - "id": "6766ecc9", + "id": "049e0384", "metadata": { "editable": true }, @@ -2158,7 +2047,7 @@ }, { "cell_type": "markdown", - "id": "fb3a9871", + "id": "5a9fe56d", "metadata": { "editable": true }, @@ -2170,7 +2059,7 @@ }, { "cell_type": "markdown", - "id": "57226a58", + "id": "be3f1edc", "metadata": { "editable": true }, @@ -2183,7 +2072,7 @@ }, { "cell_type": "markdown", - "id": "b333e60b", + "id": "39a78b9e", "metadata": { "editable": true }, @@ -2200,7 +2089,7 @@ }, { "cell_type": "markdown", - "id": "1adb10e6", + "id": "8c035b2b", "metadata": { "editable": true }, @@ -2212,7 +2101,7 @@ }, { "cell_type": "markdown", - "id": "77592d4e", + "id": "12c6c509", "metadata": { "editable": true }, @@ -2222,7 +2111,7 @@ }, { "cell_type": "markdown", - "id": "ba90405f", + "id": "81cb4b33", "metadata": { "editable": true }, @@ -2234,7 +2123,7 @@ }, { "cell_type": "markdown", - "id": "db7cef69", + "id": "f1aec311", "metadata": { "editable": true }, @@ -2244,7 +2133,7 @@ }, { "cell_type": "markdown", - "id": "e12b557f", + "id": "3f4f90ea", "metadata": { "editable": true }, @@ -2256,7 +2145,7 @@ }, { "cell_type": "markdown", - "id": "6f5462e0", + "id": "5535c1ab", "metadata": { "editable": true }, @@ -2266,7 +2155,7 @@ }, { "cell_type": "markdown", - "id": "0247179e", + "id": "b3efd5ad", "metadata": { "editable": true }, @@ -2278,7 +2167,7 @@ }, { "cell_type": "markdown", - "id": "cb6e7ad5", + "id": "a6d81840", "metadata": { "editable": true }, @@ -2294,7 +2183,7 @@ }, { "cell_type": "markdown", - "id": "b60eb119", + "id": "f69f2188", "metadata": { "editable": true }, @@ -2306,7 +2195,7 @@ }, { "cell_type": "markdown", - "id": "b38eb451", + "id": "cf70b128", "metadata": { "editable": true }, @@ -2317,7 +2206,7 @@ }, { "cell_type": "markdown", - "id": "d67cf525", + "id": "4bfa00ef", "metadata": { "editable": true }, @@ -2329,7 +2218,7 @@ }, { "cell_type": "markdown", - "id": "2f8449b2", + "id": "4750b7cb", "metadata": { "editable": true }, @@ -2343,7 +2232,7 @@ }, { "cell_type": "markdown", - "id": "55ca6490", + "id": "cc94773e", "metadata": { "editable": true }, @@ -2355,7 +2244,7 @@ }, { "cell_type": "markdown", - "id": "e716655b", + "id": "48a29815", "metadata": { "editable": true }, @@ -2380,7 +2269,7 @@ }, { "cell_type": "markdown", - "id": "fa63a9de", + "id": "2be22cb2", "metadata": { "editable": true }, @@ -2397,7 +2286,7 @@ { "cell_type": "code", "execution_count": 27, - "id": "cca448dd", + "id": "57ce58c1", "metadata": { "collapsed": false, "editable": true @@ -2441,7 +2330,7 @@ }, { "cell_type": "markdown", - "id": "aa35aba5", + "id": "856d936e", "metadata": { "editable": true }, @@ -2452,7 +2341,7 @@ { "cell_type": "code", "execution_count": 28, - "id": "c854893a", + "id": "f00c1cc8", "metadata": { "collapsed": false, "editable": true @@ -2474,7 +2363,7 @@ }, { "cell_type": "markdown", - "id": "74b3f235", + "id": "01f32685", "metadata": { "editable": true }, @@ -2491,7 +2380,7 @@ { "cell_type": "code", "execution_count": 29, - "id": "92e8847b", + "id": "c00626c0", "metadata": { "collapsed": false, "editable": true @@ -2512,7 +2401,7 @@ }, { "cell_type": "markdown", - "id": "8cbce288", + "id": "e3ac89b4", "metadata": { "editable": true }, @@ -2526,7 +2415,7 @@ { "cell_type": "code", "execution_count": 30, - "id": "b4398581", + "id": "292ced26", "metadata": { "collapsed": false, "editable": true @@ -2555,7 +2444,7 @@ }, { "cell_type": "markdown", - "id": "0f21a73f", + "id": "b21b5f18", "metadata": { "editable": true }, @@ -2575,7 +2464,7 @@ { "cell_type": "code", "execution_count": 31, - "id": "491e38a4", + "id": "18c931f7", "metadata": { "collapsed": false, "editable": true @@ -2592,7 +2481,7 @@ }, { "cell_type": "markdown", - "id": "07ac2cd3", + "id": "bf1a1139", "metadata": { "editable": true }, @@ -2604,7 +2493,7 @@ { "cell_type": "code", "execution_count": 32, - "id": "0462ebdd", + "id": "0c1a4a2d", "metadata": { "collapsed": false, "editable": true @@ -2622,7 +2511,7 @@ }, { "cell_type": "markdown", - "id": "66a31f58", + "id": "b1b537e6", "metadata": { "editable": true }, @@ -2633,7 +2522,7 @@ { "cell_type": "code", "execution_count": 33, - "id": "7d4bf033", + "id": "ef679107", "metadata": { "collapsed": false, "editable": true @@ -2646,7 +2535,7 @@ }, { "cell_type": "markdown", - "id": "3b9f86de", + "id": "718927c7", "metadata": { "editable": true }, @@ -2658,7 +2547,7 @@ { "cell_type": "code", "execution_count": 34, - "id": "b12b4d19", + "id": "ea124a61", "metadata": { "collapsed": false, "editable": true @@ -2689,7 +2578,7 @@ }, { "cell_type": "markdown", - "id": "4cf1be8b", + "id": "9b3a0eeb", "metadata": { "editable": true }, @@ -2703,7 +2592,7 @@ { "cell_type": "code", "execution_count": 35, - "id": "e80600eb", + "id": "1994899a", "metadata": { "collapsed": false, "editable": true @@ -2714,36 +2603,41 @@ "from sklearn.metrics import accuracy_score\n", "import seaborn as sns\n", "\n", + "\n", "X_train = X\n", "Y_train = Energies\n", - "n_hidden_neurons = 100\n", + "n_hidden_neurons = 50\n", "epochs = 100\n", "# store models for later use\n", - "eta_vals = np.logspace(-5, 1, 7)\n", - "lmbd_vals = np.logspace(-5, 1, 7)\n", + "eta_vals = np.logspace(-3, 0, 4)\n", + "lmbd_vals = np.logspace(-3, 0, 4)\n", "# store the models for later use\n", "DNN_scikit = np.zeros((len(eta_vals), len(lmbd_vals)), dtype=object)\n", "train_accuracy = np.zeros((len(eta_vals), len(lmbd_vals)))\n", "sns.set()\n", "for i, eta in enumerate(eta_vals):\n", " for j, lmbd in enumerate(lmbd_vals):\n", - " dnn = MLPRegressor(hidden_layer_sizes=(n_hidden_neurons), activation='logistic',\n", + " dnn = MLPRegressor(hidden_layer_sizes=(n_hidden_neurons), activation='relu', solver='adam',\n", " alpha=lmbd, learning_rate_init=eta, max_iter=epochs)\n", " dnn.fit(X_train, Y_train)\n", " DNN_scikit[i][j] = dnn\n", " train_accuracy[i][j] = dnn.score(X_train, Y_train)\n", - "\n", + " fity = dnn.predict(X_train)\n", + " MSE = mean_squared_error(Y_train, fity)\n", + " print(\"Mean squared error: %.2f\" % mean_squared_error(Y_train, fity))\n", + " train_accuracy[i][j] = MSE\n", "fig, ax = plt.subplots(figsize = (10, 10))\n", "sns.heatmap(train_accuracy, annot=True, ax=ax, cmap=\"viridis\")\n", "ax.set_title(\"Training Accuracy\")\n", "ax.set_ylabel(\"$\\eta$\")\n", "ax.set_xlabel(\"$\\lambda$\")\n", - "plt.show()" + "plt.show()\n", + "print(train_accuracy)" ] }, { "cell_type": "markdown", - "id": "d49cd4ec", + "id": "7373ec03", "metadata": { "editable": true }, @@ -2763,7 +2657,7 @@ }, { "cell_type": "markdown", - "id": "9a4706c7", + "id": "d6bf1bf5", "metadata": { "editable": true }, @@ -2795,7 +2689,7 @@ }, { "cell_type": "markdown", - "id": "b720efdc", + "id": "accb159e", "metadata": { "editable": true }, @@ -2817,7 +2711,7 @@ }, { "cell_type": "markdown", - "id": "0cb90bb5", + "id": "a92a5e51", "metadata": { "editable": true }, @@ -2845,7 +2739,7 @@ }, { "cell_type": "markdown", - "id": "e45e89d3", + "id": "5ae65ed4", "metadata": { "editable": true }, @@ -2860,7 +2754,7 @@ }, { "cell_type": "markdown", - "id": "f2471451", + "id": "687ef539", "metadata": { "editable": true }, @@ -2872,7 +2766,7 @@ }, { "cell_type": "markdown", - "id": "ee20b9ee", + "id": "9aeee4e8", "metadata": { "editable": true }, @@ -2887,7 +2781,7 @@ }, { "cell_type": "markdown", - "id": "ebc12338", + "id": "b387637a", "metadata": { "editable": true }, @@ -2900,7 +2794,7 @@ }, { "cell_type": "markdown", - "id": "0f5cb3d7", + "id": "ea565ad3", "metadata": { "editable": true }, @@ -2912,7 +2806,7 @@ }, { "cell_type": "markdown", - "id": "8be293e3", + "id": "3dc47fc2", "metadata": { "editable": true }, @@ -2922,7 +2816,7 @@ }, { "cell_type": "markdown", - "id": "c0a2104e", + "id": "00ea18d8", "metadata": { "editable": true }, @@ -2933,7 +2827,7 @@ }, { "cell_type": "markdown", - "id": "93b447fd", + "id": "7a125f42", "metadata": { "editable": true }, @@ -2951,7 +2845,7 @@ }, { "cell_type": "markdown", - "id": "94d59403", + "id": "6709a1b0", "metadata": { "editable": true }, @@ -2962,7 +2856,7 @@ }, { "cell_type": "markdown", - "id": "7b044c26", + "id": "3428c3a8", "metadata": { "editable": true }, @@ -2974,7 +2868,7 @@ }, { "cell_type": "markdown", - "id": "a4ec8b3e", + "id": "95c50e90", "metadata": { "editable": true }, @@ -2984,7 +2878,7 @@ }, { "cell_type": "markdown", - "id": "7e221f81", + "id": "3da4b4ce", "metadata": { "editable": true }, @@ -2996,7 +2890,7 @@ }, { "cell_type": "markdown", - "id": "729c5dd3", + "id": "4ba0a0a9", "metadata": { "editable": true }, @@ -3006,7 +2900,7 @@ }, { "cell_type": "markdown", - "id": "5eb54f13", + "id": "aafd46bd", "metadata": { "editable": true }, @@ -3018,7 +2912,7 @@ }, { "cell_type": "markdown", - "id": "51cad783", + "id": "c45d88f2", "metadata": { "editable": true }, @@ -3028,7 +2922,7 @@ }, { "cell_type": "markdown", - "id": "e38a17c1", + "id": "652c12db", "metadata": { "editable": true }, @@ -3047,7 +2941,7 @@ }, { "cell_type": "markdown", - "id": "c669704a", + "id": "287eebdf", "metadata": { "editable": true }, @@ -3057,7 +2951,7 @@ }, { "cell_type": "markdown", - "id": "6c2f1143", + "id": "37400e70", "metadata": { "editable": true }, @@ -3069,7 +2963,7 @@ }, { "cell_type": "markdown", - "id": "144ef4c2", + "id": "bcef14c0", "metadata": { "editable": true }, @@ -3079,7 +2973,7 @@ }, { "cell_type": "markdown", - "id": "d9da387d", + "id": "8e755bfd", "metadata": { "editable": true }, @@ -3095,7 +2989,7 @@ }, { "cell_type": "markdown", - "id": "16d9099a", + "id": "bf603c75", "metadata": { "editable": true }, @@ -3115,7 +3009,7 @@ }, { "cell_type": "markdown", - "id": "dac4b0d4", + "id": "42abb005", "metadata": { "editable": true }, @@ -3125,7 +3019,7 @@ }, { "cell_type": "markdown", - "id": "821d16ee", + "id": "f79e2da7", "metadata": { "editable": true }, @@ -3136,7 +3030,7 @@ }, { "cell_type": "markdown", - "id": "64804e58", + "id": "7a0b3900", "metadata": { "editable": true }, @@ -3155,7 +3049,7 @@ }, { "cell_type": "markdown", - "id": "28be47df", + "id": "7322cacc", "metadata": { "editable": true }, @@ -3165,7 +3059,7 @@ }, { "cell_type": "markdown", - "id": "f15f39a0", + "id": "1a10a334", "metadata": { "editable": true }, @@ -3177,7 +3071,7 @@ }, { "cell_type": "markdown", - "id": "03117774", + "id": "ec1915c1", "metadata": { "editable": true }, @@ -3187,7 +3081,7 @@ }, { "cell_type": "markdown", - "id": "2dadc99e", + "id": "c4fe6000", "metadata": { "editable": true }, @@ -3198,7 +3092,7 @@ }, { "cell_type": "markdown", - "id": "98d081e3", + "id": "41a78ecd", "metadata": { "editable": true }, @@ -3218,7 +3112,7 @@ }, { "cell_type": "markdown", - "id": "02c207e3", + "id": "d9184930", "metadata": { "editable": true }, @@ -3230,7 +3124,7 @@ }, { "cell_type": "markdown", - "id": "5b3ba5aa", + "id": "336efd0e", "metadata": { "editable": true }, @@ -3245,7 +3139,7 @@ { "cell_type": "code", "execution_count": 36, - "id": "97a71b30", + "id": "d7f7ee11", "metadata": { "collapsed": false, "editable": true @@ -3325,7 +3219,7 @@ }, { "cell_type": "markdown", - "id": "ed7eb3b8", + "id": "06b3c778", "metadata": { "editable": true }, @@ -3335,7 +3229,7 @@ }, { "cell_type": "markdown", - "id": "1ac7d0e5", + "id": "7fd7f1a9", "metadata": { "editable": true }, @@ -3347,7 +3241,7 @@ }, { "cell_type": "markdown", - "id": "8069a90f", + "id": "7a7d6f60", "metadata": { "editable": true }, @@ -3357,7 +3251,7 @@ }, { "cell_type": "markdown", - "id": "815493e0", + "id": "dcf4259b", "metadata": { "editable": true }, @@ -3368,7 +3262,7 @@ }, { "cell_type": "markdown", - "id": "7880ef32", + "id": "56e2c7b1", "metadata": { "editable": true }, @@ -3380,7 +3274,7 @@ }, { "cell_type": "markdown", - "id": "ecb0a16f", + "id": "83f24da1", "metadata": { "editable": true }, @@ -3390,7 +3284,7 @@ }, { "cell_type": "markdown", - "id": "d8782aad", + "id": "3e072e07", "metadata": { "editable": true }, @@ -3402,7 +3296,7 @@ }, { "cell_type": "markdown", - "id": "d2491d40", + "id": "ebb98625", "metadata": { "editable": true }, @@ -3412,7 +3306,7 @@ }, { "cell_type": "markdown", - "id": "1cf22842", + "id": "2208961c", "metadata": { "editable": true }, @@ -3424,7 +3318,7 @@ }, { "cell_type": "markdown", - "id": "71180218", + "id": "9fe2fec2", "metadata": { "editable": true }, @@ -3437,7 +3331,7 @@ }, { "cell_type": "markdown", - "id": "1c734def", + "id": "2469ff5a", "metadata": { "editable": true }, @@ -3449,7 +3343,7 @@ }, { "cell_type": "markdown", - "id": "85f6ff9d", + "id": "78c3608b", "metadata": { "editable": true }, @@ -3459,7 +3353,7 @@ }, { "cell_type": "markdown", - "id": "1ad66e97", + "id": "724d699f", "metadata": { "editable": true }, @@ -3471,7 +3365,7 @@ }, { "cell_type": "markdown", - "id": "6ff8d32a", + "id": "c81e30d6", "metadata": { "editable": true }, @@ -3483,7 +3377,7 @@ }, { "cell_type": "markdown", - "id": "fde1cca5", + "id": "b7539680", "metadata": { "editable": true }, @@ -3494,7 +3388,7 @@ }, { "cell_type": "markdown", - "id": "5b34fa19", + "id": "35bef2fb", "metadata": { "editable": true }, @@ -3506,7 +3400,7 @@ }, { "cell_type": "markdown", - "id": "e93804b1", + "id": "c9ba75f2", "metadata": { "editable": true }, @@ -3525,7 +3419,7 @@ }, { "cell_type": "markdown", - "id": "e3b2a85a", + "id": "0de9cf54", "metadata": { "editable": true }, @@ -3538,7 +3432,7 @@ }, { "cell_type": "markdown", - "id": "88b484a0", + "id": "c29fc4c3", "metadata": { "editable": true }, @@ -3548,7 +3442,7 @@ }, { "cell_type": "markdown", - "id": "0cae40f7", + "id": "806f82d4", "metadata": { "editable": true }, @@ -3560,7 +3454,7 @@ }, { "cell_type": "markdown", - "id": "3e3c19f7", + "id": "7101ec03", "metadata": { "editable": true }, @@ -3570,7 +3464,7 @@ }, { "cell_type": "markdown", - "id": "c5d9738a", + "id": "e3c91e71", "metadata": { "editable": true }, @@ -3582,7 +3476,7 @@ }, { "cell_type": "markdown", - "id": "49bf03c8", + "id": "28859238", "metadata": { "editable": true }, @@ -3592,7 +3486,7 @@ }, { "cell_type": "markdown", - "id": "acc52e20", + "id": "412d7d97", "metadata": { "editable": true }, @@ -3604,7 +3498,7 @@ }, { "cell_type": "markdown", - "id": "ecfc4d77", + "id": "a2d6e61f", "metadata": { "editable": true }, @@ -3615,7 +3509,7 @@ }, { "cell_type": "markdown", - "id": "7bc2250b", + "id": "3aab18ca", "metadata": { "editable": true }, @@ -3627,7 +3521,7 @@ }, { "cell_type": "markdown", - "id": "3c038483", + "id": "a5d3d3d4", "metadata": { "editable": true }, @@ -3637,7 +3531,7 @@ }, { "cell_type": "markdown", - "id": "d530cc8f", + "id": "6bc87ffc", "metadata": { "editable": true }, @@ -3649,7 +3543,7 @@ }, { "cell_type": "markdown", - "id": "667c132f", + "id": "e6d26432", "metadata": { "editable": true }, @@ -3659,7 +3553,7 @@ }, { "cell_type": "markdown", - "id": "1a592608", + "id": "68315dcb", "metadata": { "editable": true }, @@ -3671,7 +3565,7 @@ }, { "cell_type": "markdown", - "id": "fe968934", + "id": "251e4b2e", "metadata": { "editable": true }, @@ -3692,7 +3586,7 @@ }, { "cell_type": "markdown", - "id": "f182ccd2", + "id": "485307ed", "metadata": { "editable": true }, @@ -3706,7 +3600,7 @@ }, { "cell_type": "markdown", - "id": "3e23c6ac", + "id": "9a1d8612", "metadata": { "editable": true }, @@ -3717,7 +3611,7 @@ }, { "cell_type": "markdown", - "id": "2a10b1fa", + "id": "b053306a", "metadata": { "editable": true }, @@ -3729,7 +3623,7 @@ }, { "cell_type": "markdown", - "id": "753ac3da", + "id": "6509f810", "metadata": { "editable": true }, @@ -3739,7 +3633,7 @@ }, { "cell_type": "markdown", - "id": "abdc427a", + "id": "5f2b6cfb", "metadata": { "editable": true }, @@ -3751,7 +3645,7 @@ }, { "cell_type": "markdown", - "id": "a959437a", + "id": "d68edc03", "metadata": { "editable": true }, @@ -3761,7 +3655,7 @@ }, { "cell_type": "markdown", - "id": "764e589a", + "id": "e592d409", "metadata": { "editable": true }, @@ -3773,7 +3667,7 @@ }, { "cell_type": "markdown", - "id": "00e50636", + "id": "402a8712", "metadata": { "editable": true }, @@ -3785,7 +3679,7 @@ }, { "cell_type": "markdown", - "id": "7f1fb52c", + "id": "3297371d", "metadata": { "editable": true }, @@ -3799,7 +3693,7 @@ { "cell_type": "code", "execution_count": 37, - "id": "6e7ef8e3", + "id": "87fb9b2a", "metadata": { "collapsed": false, "editable": true @@ -3814,7 +3708,7 @@ }, { "cell_type": "markdown", - "id": "e8de20b3", + "id": "ee24edc8", "metadata": { "editable": true }, @@ -3825,7 +3719,7 @@ { "cell_type": "code", "execution_count": 38, - "id": "890c0e17", + "id": "f3f9658c", "metadata": { "collapsed": false, "editable": true @@ -3838,7 +3732,7 @@ }, { "cell_type": "markdown", - "id": "fa46eacd", + "id": "b4ed34de", "metadata": { "editable": true }, @@ -3849,7 +3743,7 @@ { "cell_type": "code", "execution_count": 39, - "id": "dd7bc08b", + "id": "609abf77", "metadata": { "collapsed": false, "editable": true @@ -3872,7 +3766,7 @@ }, { "cell_type": "markdown", - "id": "f1dac4cb", + "id": "7f3cfe27", "metadata": { "editable": true }, @@ -3886,7 +3780,7 @@ { "cell_type": "code", "execution_count": 40, - "id": "8253a870", + "id": "c825f110", "metadata": { "collapsed": false, "editable": true @@ -3899,7 +3793,7 @@ }, { "cell_type": "markdown", - "id": "25175ebc", + "id": "127f753b", "metadata": { "editable": true }, @@ -3910,7 +3804,7 @@ { "cell_type": "code", "execution_count": 41, - "id": "4106532b", + "id": "9002643d", "metadata": { "collapsed": false, "editable": true @@ -3922,7 +3816,7 @@ }, { "cell_type": "markdown", - "id": "3ae3cbe1", + "id": "3c10d523", "metadata": { "editable": true }, @@ -3933,7 +3827,7 @@ { "cell_type": "code", "execution_count": 42, - "id": "9cbc337d", + "id": "b0be976a", "metadata": { "collapsed": false, "editable": true @@ -3949,7 +3843,7 @@ }, { "cell_type": "markdown", - "id": "1f984da0", + "id": "a3c853fd", "metadata": { "editable": true }, @@ -3960,7 +3854,7 @@ { "cell_type": "code", "execution_count": 43, - "id": "91777701", + "id": "3e876e46", "metadata": { "collapsed": false, "editable": true @@ -3974,7 +3868,7 @@ }, { "cell_type": "markdown", - "id": "f504b559", + "id": "8bae9ae0", "metadata": { "editable": true }, @@ -3996,7 +3890,7 @@ }, { "cell_type": "markdown", - "id": "67440280", + "id": "e268fe32", "metadata": { "editable": true }, @@ -4008,7 +3902,7 @@ }, { "cell_type": "markdown", - "id": "c5190684", + "id": "0eb0a0b8", "metadata": { "editable": true }, @@ -4018,7 +3912,7 @@ }, { "cell_type": "markdown", - "id": "1b878f0e", + "id": "48244140", "metadata": { "editable": true }, @@ -4030,7 +3924,7 @@ }, { "cell_type": "markdown", - "id": "8ab0a4a3", + "id": "d285acf3", "metadata": { "editable": true }, @@ -4042,7 +3936,7 @@ }, { "cell_type": "markdown", - "id": "e9106c8d", + "id": "291407cc", "metadata": { "editable": true }, @@ -4052,7 +3946,7 @@ }, { "cell_type": "markdown", - "id": "03c4e9d7", + "id": "b80bef46", "metadata": { "editable": true }, @@ -4064,7 +3958,7 @@ }, { "cell_type": "markdown", - "id": "0e4abfb1", + "id": "ad91b94e", "metadata": { "editable": true }, @@ -4074,7 +3968,7 @@ }, { "cell_type": "markdown", - "id": "45af97a4", + "id": "59d64474", "metadata": { "editable": true }, @@ -4086,7 +3980,7 @@ }, { "cell_type": "markdown", - "id": "9ff2fda9", + "id": "f0f79d1c", "metadata": { "editable": true }, @@ -4096,7 +3990,7 @@ }, { "cell_type": "markdown", - "id": "c1593fa5", + "id": "a2c1adbd", "metadata": { "editable": true }, @@ -4108,7 +4002,7 @@ }, { "cell_type": "markdown", - "id": "d34ea7db", + "id": "77c55331", "metadata": { "editable": true }, @@ -4120,7 +4014,7 @@ }, { "cell_type": "markdown", - "id": "699612be", + "id": "464518fe", "metadata": { "editable": true }, @@ -4130,7 +4024,7 @@ }, { "cell_type": "markdown", - "id": "88ae1420", + "id": "7722ff6a", "metadata": { "editable": true }, @@ -4142,7 +4036,7 @@ }, { "cell_type": "markdown", - "id": "b827d1c6", + "id": "17a0a0bf", "metadata": { "editable": true }, @@ -4152,7 +4046,7 @@ }, { "cell_type": "markdown", - "id": "61900168", + "id": "db0729e5", "metadata": { "editable": true }, @@ -4164,7 +4058,7 @@ }, { "cell_type": "markdown", - "id": "eaab94fc", + "id": "a3342e4d", "metadata": { "editable": true }, @@ -4176,7 +4070,7 @@ }, { "cell_type": "markdown", - "id": "c8f542a4", + "id": "32797264", "metadata": { "editable": true }, @@ -4188,7 +4082,7 @@ }, { "cell_type": "markdown", - "id": "c6e93dd5", + "id": "6b4fa2ed", "metadata": { "editable": true }, @@ -4198,7 +4092,7 @@ }, { "cell_type": "markdown", - "id": "977ca552", + "id": "91b0f90c", "metadata": { "editable": true }, @@ -4210,7 +4104,7 @@ }, { "cell_type": "markdown", - "id": "ff3c6b13", + "id": "1788b899", "metadata": { "editable": true }, @@ -4220,7 +4114,7 @@ }, { "cell_type": "markdown", - "id": "ebbb06cf", + "id": "fbedd864", "metadata": { "editable": true }, @@ -4232,7 +4126,7 @@ }, { "cell_type": "markdown", - "id": "ed6f641e", + "id": "46ced7fc", "metadata": { "editable": true }, @@ -4242,7 +4136,7 @@ }, { "cell_type": "markdown", - "id": "94c50447", + "id": "126581f2", "metadata": { "editable": true }, @@ -4254,7 +4148,7 @@ }, { "cell_type": "markdown", - "id": "caa52732", + "id": "22263ac1", "metadata": { "editable": true }, @@ -4265,7 +4159,7 @@ }, { "cell_type": "markdown", - "id": "721f3130", + "id": "d2f1c4bf", "metadata": { "editable": true }, @@ -4277,7 +4171,7 @@ }, { "cell_type": "markdown", - "id": "1ecec855", + "id": "3c150c12", "metadata": { "editable": true }, @@ -4287,7 +4181,7 @@ }, { "cell_type": "markdown", - "id": "9f72bcd2", + "id": "54c4bd59", "metadata": { "editable": true }, @@ -4299,7 +4193,7 @@ }, { "cell_type": "markdown", - "id": "952c0807", + "id": "85450044", "metadata": { "editable": true }, @@ -4309,7 +4203,7 @@ }, { "cell_type": "markdown", - "id": "db7a0783", + "id": "f62678e4", "metadata": { "editable": true }, @@ -4321,7 +4215,7 @@ }, { "cell_type": "markdown", - "id": "03a57144", + "id": "06216620", "metadata": { "editable": true }, @@ -4334,7 +4228,7 @@ }, { "cell_type": "markdown", - "id": "22e8525a", + "id": "48b4d612", "metadata": { "editable": true }, @@ -4346,7 +4240,7 @@ }, { "cell_type": "markdown", - "id": "e7dc4b83", + "id": "44fe7e7a", "metadata": { "editable": true }, @@ -4358,7 +4252,7 @@ }, { "cell_type": "markdown", - "id": "5ceab08b", + "id": "989f2952", "metadata": { "editable": true }, @@ -4370,7 +4264,7 @@ }, { "cell_type": "markdown", - "id": "61608838", + "id": "0425932f", "metadata": { "editable": true }, @@ -4382,7 +4276,7 @@ }, { "cell_type": "markdown", - "id": "59fd7508", + "id": "7f095428", "metadata": { "editable": true }, @@ -4394,7 +4288,7 @@ }, { "cell_type": "markdown", - "id": "caca22c4", + "id": "a37ec316", "metadata": { "editable": true }, @@ -4404,7 +4298,7 @@ }, { "cell_type": "markdown", - "id": "b459c22c", + "id": "05921282", "metadata": { "editable": true }, @@ -4416,7 +4310,7 @@ }, { "cell_type": "markdown", - "id": "3715e857", + "id": "147b5033", "metadata": { "editable": true }, @@ -4428,7 +4322,7 @@ }, { "cell_type": "markdown", - "id": "3ad3eeb2", + "id": "fe77ebfe", "metadata": { "editable": true }, @@ -4441,7 +4335,7 @@ }, { "cell_type": "markdown", - "id": "d8b193ef", + "id": "2a2e48f9", "metadata": { "editable": true }, @@ -4468,7 +4362,7 @@ }, { "cell_type": "markdown", - "id": "11007882", + "id": "6c8cf2ea", "metadata": { "editable": true }, @@ -4479,7 +4373,7 @@ { "cell_type": "code", "execution_count": 44, - "id": "ee8cdde5", + "id": "4b4b43d0", "metadata": { "collapsed": false, "editable": true @@ -4575,7 +4469,7 @@ }, { "cell_type": "markdown", - "id": "1ea53cff", + "id": "e2a451c5", "metadata": { "editable": true }, @@ -4590,7 +4484,7 @@ }, { "cell_type": "markdown", - "id": "4d725567", + "id": "b59392e2", "metadata": { "editable": true }, @@ -4612,7 +4506,7 @@ { "cell_type": "code", "execution_count": 45, - "id": "aa6446c1", + "id": "7b909eeb", "metadata": { "collapsed": false, "editable": true @@ -4687,7 +4581,7 @@ }, { "cell_type": "markdown", - "id": "7b772723", + "id": "bec3ce40", "metadata": { "editable": true }, @@ -4699,7 +4593,7 @@ }, { "cell_type": "markdown", - "id": "3cf1d40f", + "id": "a321d502", "metadata": { "editable": true }, @@ -4768,7 +4662,7 @@ }, { "cell_type": "markdown", - "id": "59288b2d", + "id": "759fda61", "metadata": { "editable": true }, @@ -4782,7 +4676,7 @@ { "cell_type": "code", "execution_count": 46, - "id": "f06dd2f8", + "id": "93284b25", "metadata": { "collapsed": false, "editable": true @@ -4795,7 +4689,7 @@ }, { "cell_type": "markdown", - "id": "21171361", + "id": "a3388ab9", "metadata": { "editable": true }, @@ -4809,7 +4703,7 @@ }, { "cell_type": "markdown", - "id": "0389374f", + "id": "985f07fa", "metadata": { "editable": true }, @@ -4822,7 +4716,7 @@ }, { "cell_type": "markdown", - "id": "e85ae9f5", + "id": "65ca73e3", "metadata": { "editable": true }, @@ -4833,7 +4727,7 @@ }, { "cell_type": "markdown", - "id": "6eac8058", + "id": "97ccbc96", "metadata": { "editable": true }, @@ -4845,7 +4739,7 @@ }, { "cell_type": "markdown", - "id": "c9d88838", + "id": "0e7404ee", "metadata": { "editable": true }, @@ -4855,7 +4749,7 @@ }, { "cell_type": "markdown", - "id": "4a767648", + "id": "64aed9c5", "metadata": { "editable": true }, @@ -4867,7 +4761,7 @@ }, { "cell_type": "markdown", - "id": "3b1a7735", + "id": "e0a3bdb2", "metadata": { "editable": true }, @@ -4878,7 +4772,7 @@ }, { "cell_type": "markdown", - "id": "8c8ad214", + "id": "4ef8be54", "metadata": { "editable": true }, @@ -4897,7 +4791,7 @@ { "cell_type": "code", "execution_count": 47, - "id": "43caea5f", + "id": "5283ee66", "metadata": { "collapsed": false, "editable": true @@ -4913,7 +4807,7 @@ }, { "cell_type": "markdown", - "id": "9c604beb", + "id": "f275d73e", "metadata": { "editable": true }, @@ -4923,7 +4817,7 @@ }, { "cell_type": "markdown", - "id": "519328d9", + "id": "e2f0b55f", "metadata": { "editable": true }, @@ -4934,7 +4828,7 @@ }, { "cell_type": "markdown", - "id": "3fdc48c8", + "id": "5b01468f", "metadata": { "editable": true }, @@ -4946,7 +4840,7 @@ }, { "cell_type": "markdown", - "id": "e6774cc5", + "id": "5af2c631", "metadata": { "editable": true }, diff --git a/doc/LectureNotes/_build/html/_sources/week35.ipynb b/doc/LectureNotes/_build/html/_sources/week35.ipynb index 756f23c0b..40b6c66a9 100644 --- a/doc/LectureNotes/_build/html/_sources/week35.ipynb +++ b/doc/LectureNotes/_build/html/_sources/week35.ipynb @@ -2,7 +2,7 @@ "cells": [ { "cell_type": "markdown", - "id": "82630256", + "id": "ea977b24", "metadata": { "editable": true }, @@ -14,7 +14,7 @@ }, { "cell_type": "markdown", - "id": "342c9c77", + "id": "a247218b", "metadata": { "editable": true }, @@ -22,12 +22,12 @@ "# Week 35: From Ordinary Linear Regression to Ridge and Lasso Regression\n", "**Morten Hjorth-Jensen**, Department of Physics, University of Oslo and Department of Physics and Astronomy and National Superconducting Cyclotron Laboratory, Michigan State University\n", "\n", - "Date: **August 28-September 1**" + "Date: **August 26-30**" ] }, { "cell_type": "markdown", - "id": "8d89c4f2", + "id": "f234b76d", "metadata": { "editable": true }, @@ -42,18 +42,14 @@ "\n", "3. Discussion on how to prepare data and examples of applications of linear regression\n", "\n", - "4. Material for the lecture on Thursday: Mathematical interpretations of linear regression\n", + "4. Material for the lecture on Monday: Mathematical interpretations of linear regression\n", "\n", - "5. Thursday: Ridge and Lasso regression and Singular Value Decomposition\n", - "\n", - "6. [Video of lecture](https://youtu.be/qBNm-HGSxL4)\n", - "\n", - "7. [Whiteboard notes](https://github.com/CompPhysics/MachineLearning/blob/master/doc/HandWrittenNotes/2023/NotesAug31.pdf)" + "5. Monday: Ridge and Lasso regression and Singular Value Decomposition" ] }, { "cell_type": "markdown", - "id": "4dc0b391", + "id": "86d0671f", "metadata": { "editable": true }, @@ -62,14 +58,12 @@ "\n", "1. See lecture notes for week 35 at \n", "\n", - "2. Goodfellow, Bengio and Courville, Deep Learning, chapter 2 on linear algebra and sections 3.1-3.10 on elements of statistics (background)\n", - "\n", - "3. Hastie, Tibshirani and Friedman, The elements of statistical learning, sections 3.1-3.4 (on relevance for the discussion of linear regression)." + "2. Goodfellow, Bengio and Courville, Deep Learning, chapter 2 on linear algebra and sections 3.1-3.10 on elements of statistics (background)" ] }, { "cell_type": "markdown", - "id": "22518518", + "id": "0b0bc0ec", "metadata": { "editable": true }, @@ -103,7 +97,7 @@ }, { "cell_type": "markdown", - "id": "40a10f3c", + "id": "c30cfd06", "metadata": { "editable": true }, @@ -119,7 +113,7 @@ }, { "cell_type": "markdown", - "id": "76f1c739", + "id": "59d6452b", "metadata": { "editable": true }, @@ -131,7 +125,7 @@ }, { "cell_type": "markdown", - "id": "2710298f", + "id": "8649d84d", "metadata": { "editable": true }, @@ -141,7 +135,7 @@ }, { "cell_type": "markdown", - "id": "f1e8bd8f", + "id": "aaa65f06", "metadata": { "editable": true }, @@ -153,7 +147,7 @@ }, { "cell_type": "markdown", - "id": "79e795b0", + "id": "cc43802e", "metadata": { "editable": true }, @@ -174,7 +168,7 @@ }, { "cell_type": "markdown", - "id": "c868570e", + "id": "53877600", "metadata": { "editable": true }, @@ -186,7 +180,7 @@ }, { "cell_type": "markdown", - "id": "855e1dbf", + "id": "bc4478fc", "metadata": { "editable": true }, @@ -199,7 +193,7 @@ }, { "cell_type": "markdown", - "id": "e76339ee", + "id": "64bc2ac2", "metadata": { "editable": true }, @@ -211,7 +205,7 @@ }, { "cell_type": "markdown", - "id": "706dd49c", + "id": "d7b7d1d1", "metadata": { "editable": true }, @@ -223,7 +217,7 @@ }, { "cell_type": "markdown", - "id": "d068e28e", + "id": "f34563f6", "metadata": { "editable": true }, @@ -233,7 +227,7 @@ }, { "cell_type": "markdown", - "id": "bb734579", + "id": "1dbad69a", "metadata": { "editable": true }, @@ -245,7 +239,7 @@ }, { "cell_type": "markdown", - "id": "aba5029f", + "id": "2a16de00", "metadata": { "editable": true }, @@ -258,7 +252,7 @@ }, { "cell_type": "markdown", - "id": "6ac8d12b", + "id": "07115e56", "metadata": { "editable": true }, @@ -270,7 +264,7 @@ }, { "cell_type": "markdown", - "id": "7d3ac82a", + "id": "b90655a4", "metadata": { "editable": true }, @@ -280,7 +274,7 @@ }, { "cell_type": "markdown", - "id": "1eedadb6", + "id": "2ac208f1", "metadata": { "editable": true }, @@ -292,7 +286,7 @@ }, { "cell_type": "markdown", - "id": "61c29b5e", + "id": "a8197640", "metadata": { "editable": true }, @@ -304,7 +298,7 @@ }, { "cell_type": "markdown", - "id": "4cf9eba7", + "id": "7c72baae", "metadata": { "editable": true }, @@ -315,7 +309,7 @@ }, { "cell_type": "markdown", - "id": "0761eee3", + "id": "3c595093", "metadata": { "editable": true }, @@ -327,7 +321,7 @@ }, { "cell_type": "markdown", - "id": "ead917bf", + "id": "4dab1f87", "metadata": { "editable": true }, @@ -346,7 +340,7 @@ }, { "cell_type": "markdown", - "id": "92fe0780", + "id": "2a85bd46", "metadata": { "editable": true }, @@ -359,7 +353,7 @@ }, { "cell_type": "markdown", - "id": "396bf1e2", + "id": "5500dd61", "metadata": { "editable": true }, @@ -369,7 +363,7 @@ }, { "cell_type": "markdown", - "id": "6d5307de", + "id": "0072db82", "metadata": { "editable": true }, @@ -381,7 +375,7 @@ }, { "cell_type": "markdown", - "id": "45b68b6b", + "id": "078ec23d", "metadata": { "editable": true }, @@ -391,7 +385,7 @@ }, { "cell_type": "markdown", - "id": "8bec3f2b", + "id": "cc1760bc", "metadata": { "editable": true }, @@ -403,7 +397,7 @@ }, { "cell_type": "markdown", - "id": "80dc90da", + "id": "73d00905", "metadata": { "editable": true }, @@ -413,7 +407,7 @@ }, { "cell_type": "markdown", - "id": "64e3c687", + "id": "50dff40b", "metadata": { "editable": true }, @@ -425,7 +419,7 @@ }, { "cell_type": "markdown", - "id": "510d4d4c", + "id": "622bf5f5", "metadata": { "editable": true }, @@ -436,7 +430,7 @@ }, { "cell_type": "markdown", - "id": "f0b1c164", + "id": "48bfcf85", "metadata": { "editable": true }, @@ -448,7 +442,7 @@ }, { "cell_type": "markdown", - "id": "05896ad6", + "id": "07c395fe", "metadata": { "editable": true }, @@ -458,7 +452,7 @@ }, { "cell_type": "markdown", - "id": "bfa041c9", + "id": "d3ccdcb0", "metadata": { "editable": true }, @@ -470,7 +464,7 @@ }, { "cell_type": "markdown", - "id": "ae4e69aa", + "id": "c1ef9741", "metadata": { "editable": true }, @@ -480,7 +474,7 @@ }, { "cell_type": "markdown", - "id": "22a53165", + "id": "1646a521", "metadata": { "editable": true }, @@ -492,7 +486,7 @@ }, { "cell_type": "markdown", - "id": "02a2b1b8", + "id": "daa11d84", "metadata": { "editable": true }, @@ -512,7 +506,7 @@ }, { "cell_type": "markdown", - "id": "d1470cae", + "id": "78b271ce", "metadata": { "editable": true }, @@ -539,7 +533,7 @@ }, { "cell_type": "markdown", - "id": "fbc63e64", + "id": "9482d4e6", "metadata": { "editable": true }, @@ -551,7 +545,7 @@ }, { "cell_type": "markdown", - "id": "5475f4f0", + "id": "c7787334", "metadata": { "editable": true }, @@ -563,7 +557,7 @@ }, { "cell_type": "markdown", - "id": "7ccd0445", + "id": "a7c6c6e4", "metadata": { "editable": true }, @@ -579,7 +573,7 @@ }, { "cell_type": "markdown", - "id": "c40947ac", + "id": "dc9f4b6f", "metadata": { "editable": true }, @@ -597,7 +591,7 @@ }, { "cell_type": "markdown", - "id": "18e29324", + "id": "dbb092e9", "metadata": { "editable": true }, @@ -609,7 +603,7 @@ }, { "cell_type": "markdown", - "id": "6069e0fa", + "id": "47f695d0", "metadata": { "editable": true }, @@ -621,7 +615,7 @@ }, { "cell_type": "markdown", - "id": "2796afe6", + "id": "6ff6f849", "metadata": { "editable": true }, @@ -632,7 +626,7 @@ }, { "cell_type": "markdown", - "id": "2b66e25f", + "id": "3fab9d8e", "metadata": { "editable": true }, @@ -644,7 +638,7 @@ }, { "cell_type": "markdown", - "id": "86f9add1", + "id": "230d417b", "metadata": { "editable": true }, @@ -654,7 +648,7 @@ }, { "cell_type": "markdown", - "id": "ae97bea9", + "id": "ae3eea03", "metadata": { "editable": true }, @@ -666,7 +660,7 @@ }, { "cell_type": "markdown", - "id": "14510558", + "id": "97d7d08a", "metadata": { "editable": true }, @@ -680,7 +674,7 @@ }, { "cell_type": "markdown", - "id": "fbb54b4a", + "id": "dbcabc11", "metadata": { "editable": true }, @@ -692,7 +686,7 @@ }, { "cell_type": "markdown", - "id": "553845ce", + "id": "7278dcbd", "metadata": { "editable": true }, @@ -704,7 +698,7 @@ }, { "cell_type": "markdown", - "id": "e79fdc3c", + "id": "c16d222a", "metadata": { "editable": true }, @@ -716,7 +710,7 @@ }, { "cell_type": "markdown", - "id": "0713d61a", + "id": "0d85444e", "metadata": { "editable": true }, @@ -726,7 +720,7 @@ }, { "cell_type": "markdown", - "id": "2e522237", + "id": "4d26bab6", "metadata": { "editable": true }, @@ -738,7 +732,7 @@ }, { "cell_type": "markdown", - "id": "4baadc8b", + "id": "b6d57fdf", "metadata": { "editable": true }, @@ -750,7 +744,7 @@ }, { "cell_type": "markdown", - "id": "6e0fee06", + "id": "7a78e5dc", "metadata": { "editable": true }, @@ -762,7 +756,7 @@ }, { "cell_type": "markdown", - "id": "1d85d1c1", + "id": "6231367b", "metadata": { "editable": true }, @@ -776,7 +770,7 @@ }, { "cell_type": "markdown", - "id": "a6643a5f", + "id": "ab068594", "metadata": { "editable": true }, @@ -788,7 +782,7 @@ }, { "cell_type": "markdown", - "id": "f15d9044", + "id": "07d2f06b", "metadata": { "editable": true }, @@ -800,7 +794,7 @@ }, { "cell_type": "markdown", - "id": "658745bf", + "id": "d2382139", "metadata": { "editable": true }, @@ -812,7 +806,7 @@ }, { "cell_type": "markdown", - "id": "ba8bc828", + "id": "7d063f00", "metadata": { "editable": true }, @@ -822,7 +816,7 @@ }, { "cell_type": "markdown", - "id": "38512288", + "id": "5e119075", "metadata": { "editable": true }, @@ -834,7 +828,7 @@ }, { "cell_type": "markdown", - "id": "0a571ae1", + "id": "700eaedb", "metadata": { "editable": true }, @@ -844,7 +838,7 @@ }, { "cell_type": "markdown", - "id": "f26f46f8", + "id": "51e05fca", "metadata": { "editable": true }, @@ -856,7 +850,7 @@ }, { "cell_type": "markdown", - "id": "9e6c5896", + "id": "bba7f463", "metadata": { "editable": true }, @@ -866,7 +860,7 @@ }, { "cell_type": "markdown", - "id": "fa516251", + "id": "601577cc", "metadata": { "editable": true }, @@ -878,7 +872,7 @@ }, { "cell_type": "markdown", - "id": "10db7624", + "id": "ea31952c", "metadata": { "editable": true }, @@ -890,7 +884,7 @@ }, { "cell_type": "markdown", - "id": "7cdeda2b", + "id": "fc6c86a7", "metadata": { "editable": true }, @@ -902,7 +896,7 @@ }, { "cell_type": "markdown", - "id": "2b9a8aed", + "id": "ffe09390", "metadata": { "editable": true }, @@ -917,7 +911,7 @@ }, { "cell_type": "markdown", - "id": "758969d3", + "id": "22f4970c", "metadata": { "editable": true }, @@ -929,7 +923,7 @@ }, { "cell_type": "markdown", - "id": "d7203c02", + "id": "4ba751cb", "metadata": { "editable": true }, @@ -939,7 +933,7 @@ }, { "cell_type": "markdown", - "id": "16f3ca20", + "id": "87052e13", "metadata": { "editable": true }, @@ -951,7 +945,7 @@ }, { "cell_type": "markdown", - "id": "f7caf01e", + "id": "e24dea19", "metadata": { "editable": true }, @@ -961,7 +955,7 @@ }, { "cell_type": "markdown", - "id": "b1e5ad17", + "id": "6b52c737", "metadata": { "editable": true }, @@ -973,7 +967,7 @@ }, { "cell_type": "markdown", - "id": "587c347e", + "id": "904b93aa", "metadata": { "editable": true }, @@ -983,7 +977,7 @@ }, { "cell_type": "markdown", - "id": "5279b1cb", + "id": "439e197d", "metadata": { "editable": true }, @@ -995,7 +989,7 @@ }, { "cell_type": "markdown", - "id": "0c0d18ed", + "id": "f5658ed9", "metadata": { "editable": true }, @@ -1007,7 +1001,7 @@ }, { "cell_type": "markdown", - "id": "ba1b34c9", + "id": "6f99984d", "metadata": { "editable": true }, @@ -1019,7 +1013,7 @@ }, { "cell_type": "markdown", - "id": "b859b644", + "id": "eeb1373c", "metadata": { "editable": true }, @@ -1029,7 +1023,7 @@ }, { "cell_type": "markdown", - "id": "a6451ed1", + "id": "f3c557ba", "metadata": { "editable": true }, @@ -1041,7 +1035,7 @@ }, { "cell_type": "markdown", - "id": "6879be83", + "id": "412789d5", "metadata": { "editable": true }, @@ -1054,7 +1048,7 @@ }, { "cell_type": "markdown", - "id": "bda465e5", + "id": "65fbbb29", "metadata": { "editable": true }, @@ -1066,7 +1060,7 @@ }, { "cell_type": "markdown", - "id": "aeb97168", + "id": "f4cd65e4", "metadata": { "editable": true }, @@ -1076,7 +1070,7 @@ }, { "cell_type": "markdown", - "id": "d5339f3b", + "id": "9ee329c3", "metadata": { "editable": true }, @@ -1088,7 +1082,7 @@ }, { "cell_type": "markdown", - "id": "924aee00", + "id": "47023d81", "metadata": { "editable": true }, @@ -1098,7 +1092,7 @@ }, { "cell_type": "markdown", - "id": "856a72bf", + "id": "40d4cc36", "metadata": { "editable": true }, @@ -1110,7 +1104,7 @@ }, { "cell_type": "markdown", - "id": "ad9fe745", + "id": "e266851f", "metadata": { "editable": true }, @@ -1120,7 +1114,7 @@ }, { "cell_type": "markdown", - "id": "5a72fd42", + "id": "f4d0941c", "metadata": { "editable": true }, @@ -1132,7 +1126,7 @@ }, { "cell_type": "markdown", - "id": "569524a1", + "id": "6f4b2a9d", "metadata": { "editable": true }, @@ -1142,7 +1136,7 @@ }, { "cell_type": "markdown", - "id": "4e8d401f", + "id": "62cab30b", "metadata": { "editable": true }, @@ -1154,7 +1148,7 @@ }, { "cell_type": "markdown", - "id": "24230b58", + "id": "4c8c6398", "metadata": { "editable": true }, @@ -1164,7 +1158,7 @@ }, { "cell_type": "markdown", - "id": "fe2c5d6e", + "id": "f9c6ab8a", "metadata": { "editable": true }, @@ -1176,7 +1170,7 @@ }, { "cell_type": "markdown", - "id": "9b68b468", + "id": "b7945d33", "metadata": { "editable": true }, @@ -1188,7 +1182,7 @@ }, { "cell_type": "markdown", - "id": "bf6a5077", + "id": "80421efe", "metadata": { "editable": true }, @@ -1200,7 +1194,7 @@ }, { "cell_type": "markdown", - "id": "ddf09a27", + "id": "cc1fb4bf", "metadata": { "editable": true }, @@ -1212,7 +1206,7 @@ }, { "cell_type": "markdown", - "id": "e1665513", + "id": "c149bd15", "metadata": { "editable": true }, @@ -1224,7 +1218,7 @@ }, { "cell_type": "markdown", - "id": "e754746c", + "id": "4aeb6fad", "metadata": { "editable": true }, @@ -1240,7 +1234,7 @@ }, { "cell_type": "markdown", - "id": "922d0d8c", + "id": "fecdf631", "metadata": { "editable": true }, @@ -1252,7 +1246,7 @@ }, { "cell_type": "markdown", - "id": "acf89848", + "id": "7ffbaccd", "metadata": { "editable": true }, @@ -1262,7 +1256,7 @@ }, { "cell_type": "markdown", - "id": "12d22c90", + "id": "ba12c9f2", "metadata": { "editable": true }, @@ -1274,7 +1268,7 @@ }, { "cell_type": "markdown", - "id": "9dbcb6d7", + "id": "871cfd8e", "metadata": { "editable": true }, @@ -1292,7 +1286,7 @@ }, { "cell_type": "markdown", - "id": "b797b390", + "id": "0ad332cd", "metadata": { "editable": true }, @@ -1304,7 +1298,7 @@ }, { "cell_type": "markdown", - "id": "b78ab217", + "id": "5e7042e9", "metadata": { "editable": true }, @@ -1316,7 +1310,7 @@ }, { "cell_type": "markdown", - "id": "e0a0542d", + "id": "43b825ce", "metadata": { "editable": true }, @@ -1326,7 +1320,7 @@ }, { "cell_type": "markdown", - "id": "fd640b28", + "id": "58a4ed44", "metadata": { "editable": true }, @@ -1338,7 +1332,7 @@ }, { "cell_type": "markdown", - "id": "6a073b35", + "id": "202c5775", "metadata": { "editable": true }, @@ -1348,7 +1342,7 @@ }, { "cell_type": "markdown", - "id": "f7daf28e", + "id": "0eab64e4", "metadata": { "editable": true }, @@ -1360,7 +1354,7 @@ }, { "cell_type": "markdown", - "id": "d8e03fdc", + "id": "d17063fa", "metadata": { "editable": true }, @@ -1370,7 +1364,7 @@ }, { "cell_type": "markdown", - "id": "058aed61", + "id": "02cca57e", "metadata": { "editable": true }, @@ -1384,7 +1378,7 @@ }, { "cell_type": "markdown", - "id": "c7d35183", + "id": "d5a0e65b", "metadata": { "editable": true }, @@ -1396,7 +1390,7 @@ }, { "cell_type": "markdown", - "id": "bad6fd9a", + "id": "03f47788", "metadata": { "editable": true }, @@ -1407,7 +1401,7 @@ }, { "cell_type": "markdown", - "id": "1bd57074", + "id": "ab07b7cf", "metadata": { "editable": true }, @@ -1420,7 +1414,7 @@ { "cell_type": "code", "execution_count": 1, - "id": "9895174d", + "id": "f51e672d", "metadata": { "collapsed": false, "editable": true @@ -1447,7 +1441,7 @@ }, { "cell_type": "markdown", - "id": "0d7ad6dc", + "id": "e44be45e", "metadata": { "editable": true }, @@ -1458,7 +1452,7 @@ { "cell_type": "code", "execution_count": 2, - "id": "e52ec127", + "id": "b4786589", "metadata": { "collapsed": false, "editable": true @@ -1471,7 +1465,7 @@ }, { "cell_type": "markdown", - "id": "c66acc10", + "id": "af2dcc52", "metadata": { "editable": true }, @@ -1485,7 +1479,7 @@ { "cell_type": "code", "execution_count": 3, - "id": "85f5f060", + "id": "2bc65bc5", "metadata": { "collapsed": false, "editable": true @@ -1498,7 +1492,7 @@ }, { "cell_type": "markdown", - "id": "ef359561", + "id": "46bda600", "metadata": { "editable": true }, @@ -1509,7 +1503,7 @@ { "cell_type": "code", "execution_count": 4, - "id": "21b8437f", + "id": "9bdae7bf", "metadata": { "collapsed": false, "editable": true @@ -1521,7 +1515,7 @@ }, { "cell_type": "markdown", - "id": "b1c814a4", + "id": "64eeaaef", "metadata": { "editable": true }, @@ -1532,7 +1526,7 @@ { "cell_type": "code", "execution_count": 5, - "id": "de8f1db6", + "id": "cafbda91", "metadata": { "collapsed": false, "editable": true @@ -1548,7 +1542,7 @@ }, { "cell_type": "markdown", - "id": "421ff6ee", + "id": "831a5888", "metadata": { "editable": true }, @@ -1559,7 +1553,7 @@ { "cell_type": "code", "execution_count": 6, - "id": "77d5b744", + "id": "90f6a538", "metadata": { "collapsed": false, "editable": true @@ -1573,7 +1567,7 @@ }, { "cell_type": "markdown", - "id": "0afffa89", + "id": "dc364c27", "metadata": { "editable": true }, @@ -1594,7 +1588,7 @@ }, { "cell_type": "markdown", - "id": "83fc18dd", + "id": "1598259c", "metadata": { "editable": true }, @@ -1605,7 +1599,7 @@ { "cell_type": "code", "execution_count": 7, - "id": "c908e069", + "id": "ca994e68", "metadata": { "collapsed": false, "editable": true @@ -1658,7 +1652,7 @@ }, { "cell_type": "markdown", - "id": "f69cf8d1", + "id": "7353f2e7", "metadata": { "editable": true }, @@ -1669,7 +1663,7 @@ { "cell_type": "code", "execution_count": 8, - "id": "03acb6ba", + "id": "05a066db", "metadata": { "collapsed": false, "editable": true @@ -1694,7 +1688,7 @@ }, { "cell_type": "markdown", - "id": "0d8db71d", + "id": "1f30de64", "metadata": { "editable": true }, @@ -1706,7 +1700,7 @@ }, { "cell_type": "markdown", - "id": "29fc4792", + "id": "80fa8b7d", "metadata": { "editable": true }, @@ -1735,7 +1729,7 @@ }, { "cell_type": "markdown", - "id": "5d2323e6", + "id": "7e92be20", "metadata": { "editable": true }, @@ -1760,7 +1754,7 @@ }, { "cell_type": "markdown", - "id": "084a05ce", + "id": "052e8c0c", "metadata": { "editable": true }, @@ -1780,7 +1774,7 @@ }, { "cell_type": "markdown", - "id": "2cf236cf", + "id": "d752c7f4", "metadata": { "editable": true }, @@ -1807,7 +1801,7 @@ }, { "cell_type": "markdown", - "id": "f7ef3d03", + "id": "4b40d092", "metadata": { "editable": true }, @@ -1820,7 +1814,7 @@ }, { "cell_type": "markdown", - "id": "30df9a47", + "id": "f8526e57", "metadata": { "editable": true }, @@ -1832,7 +1826,7 @@ }, { "cell_type": "markdown", - "id": "fa957ecb", + "id": "5cfb3455", "metadata": { "editable": true }, @@ -1843,7 +1837,7 @@ }, { "cell_type": "markdown", - "id": "c6b8f467", + "id": "363e0117", "metadata": { "editable": true }, @@ -1859,7 +1853,7 @@ { "cell_type": "code", "execution_count": 9, - "id": "a2480cf9", + "id": "4c7ecfc5", "metadata": { "collapsed": false, "editable": true @@ -1893,7 +1887,7 @@ }, { "cell_type": "markdown", - "id": "7643608b", + "id": "981f65fb", "metadata": { "editable": true }, @@ -1903,7 +1897,7 @@ }, { "cell_type": "markdown", - "id": "5e6e489d", + "id": "9ddcca79", "metadata": { "editable": true }, @@ -1918,7 +1912,7 @@ }, { "cell_type": "markdown", - "id": "ff073975", + "id": "02bed8b3", "metadata": { "editable": true }, @@ -1930,7 +1924,7 @@ }, { "cell_type": "markdown", - "id": "6a176186", + "id": "64033f1d", "metadata": { "editable": true }, @@ -1940,7 +1934,7 @@ }, { "cell_type": "markdown", - "id": "784ddba6", + "id": "1cfc52cc", "metadata": { "editable": true }, @@ -1956,7 +1950,7 @@ { "cell_type": "code", "execution_count": 10, - "id": "83686834", + "id": "06b67f41", "metadata": { "collapsed": false, "editable": true @@ -1973,7 +1967,7 @@ }, { "cell_type": "markdown", - "id": "dd641a05", + "id": "773210a0", "metadata": { "editable": true }, @@ -1986,7 +1980,7 @@ { "cell_type": "code", "execution_count": 11, - "id": "447d12ce", + "id": "34cb4217", "metadata": { "collapsed": false, "editable": true @@ -2033,7 +2027,7 @@ }, { "cell_type": "markdown", - "id": "96fc590b", + "id": "4ae9cee9", "metadata": { "editable": true }, @@ -2044,7 +2038,7 @@ { "cell_type": "code", "execution_count": 12, - "id": "8de8bbfc", + "id": "9be1964e", "metadata": { "collapsed": false, "editable": true @@ -2147,7 +2141,7 @@ }, { "cell_type": "markdown", - "id": "8dfe4a90", + "id": "f0fe5870", "metadata": { "editable": true }, @@ -2175,7 +2169,7 @@ }, { "cell_type": "markdown", - "id": "c0edb6d6", + "id": "9b60a7bd", "metadata": { "editable": true }, @@ -2210,7 +2204,7 @@ }, { "cell_type": "markdown", - "id": "ed0f6bc0", + "id": "a31dcc5d", "metadata": { "editable": true }, @@ -2225,7 +2219,7 @@ { "cell_type": "code", "execution_count": 13, - "id": "99a1133f", + "id": "225671c5", "metadata": { "collapsed": false, "editable": true @@ -2250,7 +2244,7 @@ }, { "cell_type": "markdown", - "id": "5ef9b25c", + "id": "ac1448c8", "metadata": { "editable": true }, @@ -2266,7 +2260,7 @@ }, { "cell_type": "markdown", - "id": "80ca5485", + "id": "c6e308a3", "metadata": { "editable": true }, @@ -2278,7 +2272,7 @@ }, { "cell_type": "markdown", - "id": "17ad9823", + "id": "a2f2dab5", "metadata": { "editable": true }, @@ -2293,7 +2287,7 @@ }, { "cell_type": "markdown", - "id": "7560f426", + "id": "8a7df606", "metadata": { "editable": true }, @@ -2305,7 +2299,7 @@ }, { "cell_type": "markdown", - "id": "a7444f64", + "id": "31e595c9", "metadata": { "editable": true }, @@ -2315,7 +2309,7 @@ }, { "cell_type": "markdown", - "id": "2aad0c8b", + "id": "f5f389db", "metadata": { "editable": true }, @@ -2327,7 +2321,7 @@ }, { "cell_type": "markdown", - "id": "de870a72", + "id": "1dd4b34d", "metadata": { "editable": true }, @@ -2337,7 +2331,7 @@ }, { "cell_type": "markdown", - "id": "7a6c517e", + "id": "f931e286", "metadata": { "editable": true }, @@ -2349,7 +2343,7 @@ }, { "cell_type": "markdown", - "id": "753afefe", + "id": "4cbda41b", "metadata": { "editable": true }, @@ -2362,7 +2356,7 @@ }, { "cell_type": "markdown", - "id": "3005c150", + "id": "6657a435", "metadata": { "editable": true }, @@ -2374,7 +2368,7 @@ }, { "cell_type": "markdown", - "id": "79eace73", + "id": "91f7475b", "metadata": { "editable": true }, @@ -2384,7 +2378,7 @@ }, { "cell_type": "markdown", - "id": "38d75fef", + "id": "98482060", "metadata": { "editable": true }, @@ -2396,7 +2390,7 @@ }, { "cell_type": "markdown", - "id": "60f367fa", + "id": "01e12c29", "metadata": { "editable": true }, @@ -2406,7 +2400,7 @@ }, { "cell_type": "markdown", - "id": "9131a799", + "id": "38fa32e4", "metadata": { "editable": true }, @@ -2418,7 +2412,7 @@ }, { "cell_type": "markdown", - "id": "8cbfafa2", + "id": "ea483f66", "metadata": { "editable": true }, @@ -2428,7 +2422,7 @@ }, { "cell_type": "markdown", - "id": "9d4a45df", + "id": "d5862089", "metadata": { "editable": true }, @@ -2440,7 +2434,7 @@ }, { "cell_type": "markdown", - "id": "19284bfb", + "id": "0456f62e", "metadata": { "editable": true }, @@ -2450,7 +2444,7 @@ }, { "cell_type": "markdown", - "id": "e1ccefe0", + "id": "1ed14941", "metadata": { "editable": true }, @@ -2462,7 +2456,7 @@ }, { "cell_type": "markdown", - "id": "e6228ac9", + "id": "43387b69", "metadata": { "editable": true }, @@ -2472,7 +2466,7 @@ }, { "cell_type": "markdown", - "id": "474d165a", + "id": "06bd01bf", "metadata": { "editable": true }, @@ -2484,7 +2478,7 @@ }, { "cell_type": "markdown", - "id": "01c6f359", + "id": "9cad411e", "metadata": { "editable": true }, @@ -2494,7 +2488,7 @@ }, { "cell_type": "markdown", - "id": "104df9ea", + "id": "c37f7792", "metadata": { "editable": true }, @@ -2506,7 +2500,7 @@ }, { "cell_type": "markdown", - "id": "86f33ebf", + "id": "8a7f23f8", "metadata": { "editable": true }, @@ -2518,7 +2512,7 @@ }, { "cell_type": "markdown", - "id": "b8893d78", + "id": "a7fdf6e8", "metadata": { "editable": true }, @@ -2530,7 +2524,7 @@ }, { "cell_type": "markdown", - "id": "cc8ec307", + "id": "3ac73282", "metadata": { "editable": true }, @@ -2543,7 +2537,7 @@ }, { "cell_type": "markdown", - "id": "234e3f6e", + "id": "e55db5a0", "metadata": { "editable": true }, @@ -2555,7 +2549,7 @@ }, { "cell_type": "markdown", - "id": "d1c0397f", + "id": "966cd383", "metadata": { "editable": true }, @@ -2565,7 +2559,7 @@ }, { "cell_type": "markdown", - "id": "799912a7", + "id": "360cb45f", "metadata": { "editable": true }, @@ -2579,7 +2573,7 @@ { "cell_type": "code", "execution_count": 14, - "id": "5a3de91e", + "id": "2099267d", "metadata": { "collapsed": false, "editable": true @@ -2676,7 +2670,7 @@ }, { "cell_type": "markdown", - "id": "0f069973", + "id": "9ba9afe9", "metadata": { "editable": true }, @@ -2697,7 +2691,7 @@ }, { "cell_type": "markdown", - "id": "e76beb96", + "id": "ea4bf6fe", "metadata": { "editable": true }, @@ -2709,7 +2703,7 @@ }, { "cell_type": "markdown", - "id": "4fe81d64", + "id": "98ca9b28", "metadata": { "editable": true }, @@ -2719,7 +2713,7 @@ }, { "cell_type": "markdown", - "id": "bb22d80f", + "id": "996fc4f6", "metadata": { "editable": true }, @@ -2731,7 +2725,7 @@ }, { "cell_type": "markdown", - "id": "293ce41e", + "id": "b5db8128", "metadata": { "editable": true }, @@ -2741,7 +2735,7 @@ }, { "cell_type": "markdown", - "id": "8a969677", + "id": "745d6bff", "metadata": { "editable": true }, @@ -2753,7 +2747,7 @@ }, { "cell_type": "markdown", - "id": "d93685ad", + "id": "2ecb048e", "metadata": { "editable": true }, @@ -2769,7 +2763,7 @@ }, { "cell_type": "markdown", - "id": "9abd5b44", + "id": "73eb2f08", "metadata": { "editable": true }, @@ -2813,7 +2807,7 @@ }, { "cell_type": "markdown", - "id": "b8bd6825", + "id": "41d9c008", "metadata": { "editable": true }, @@ -2825,7 +2819,7 @@ { "cell_type": "code", "execution_count": 15, - "id": "2c2b3d87", + "id": "0af3b38a", "metadata": { "collapsed": false, "editable": true @@ -2841,7 +2835,7 @@ }, { "cell_type": "markdown", - "id": "fea1bc2e", + "id": "41771944", "metadata": { "editable": true }, @@ -2852,7 +2846,7 @@ { "cell_type": "code", "execution_count": 16, - "id": "a80976dc", + "id": "c0ad90ff", "metadata": { "collapsed": false, "editable": true @@ -2870,7 +2864,7 @@ }, { "cell_type": "markdown", - "id": "aa3b722c", + "id": "ef2f9bce", "metadata": { "editable": true }, @@ -2881,7 +2875,7 @@ { "cell_type": "code", "execution_count": 17, - "id": "828172e1", + "id": "150d1433", "metadata": { "collapsed": false, "editable": true @@ -2895,7 +2889,7 @@ }, { "cell_type": "markdown", - "id": "eee71c11", + "id": "1be017ef", "metadata": { "editable": true }, @@ -2906,7 +2900,7 @@ { "cell_type": "code", "execution_count": 18, - "id": "7c8a5c54", + "id": "01ef8953", "metadata": { "collapsed": false, "editable": true @@ -2919,7 +2913,7 @@ }, { "cell_type": "markdown", - "id": "a0c893b5", + "id": "adc486b5", "metadata": { "editable": true }, @@ -2930,7 +2924,7 @@ { "cell_type": "code", "execution_count": 19, - "id": "58711c38", + "id": "2471fc63", "metadata": { "collapsed": false, "editable": true @@ -2947,7 +2941,7 @@ }, { "cell_type": "markdown", - "id": "d899ec3f", + "id": "e26d39f7", "metadata": { "editable": true }, @@ -2958,7 +2952,7 @@ { "cell_type": "code", "execution_count": 20, - "id": "59925df7", + "id": "6bb60001", "metadata": { "collapsed": false, "editable": true @@ -2974,7 +2968,7 @@ }, { "cell_type": "markdown", - "id": "083a679e", + "id": "90f47dc1", "metadata": { "editable": true }, @@ -2985,7 +2979,7 @@ { "cell_type": "code", "execution_count": 21, - "id": "127a3dda", + "id": "a1f980e4", "metadata": { "collapsed": false, "editable": true @@ -3009,7 +3003,7 @@ }, { "cell_type": "markdown", - "id": "c72d1b7f", + "id": "9efdaaaa", "metadata": { "editable": true }, @@ -3020,7 +3014,7 @@ { "cell_type": "code", "execution_count": 22, - "id": "a1378976", + "id": "01e9afe5", "metadata": { "collapsed": false, "editable": true @@ -3033,7 +3027,7 @@ }, { "cell_type": "markdown", - "id": "d85205c1", + "id": "73335565", "metadata": { "editable": true }, @@ -3044,7 +3038,7 @@ { "cell_type": "code", "execution_count": 23, - "id": "040b1e85", + "id": "f865febb", "metadata": { "collapsed": false, "editable": true @@ -3064,7 +3058,7 @@ }, { "cell_type": "markdown", - "id": "32d25d47", + "id": "88f5a339", "metadata": { "editable": true }, @@ -3075,7 +3069,7 @@ { "cell_type": "code", "execution_count": 24, - "id": "1b0fac0d", + "id": "bacdbf9b", "metadata": { "collapsed": false, "editable": true @@ -3118,7 +3112,7 @@ { "cell_type": "code", "execution_count": 25, - "id": "02279b28", + "id": "09aa7ac9", "metadata": { "collapsed": false, "editable": true @@ -3133,7 +3127,7 @@ }, { "cell_type": "markdown", - "id": "cd590eba", + "id": "cb088f7a", "metadata": { "editable": true }, @@ -3143,7 +3137,7 @@ }, { "cell_type": "markdown", - "id": "9968e6df", + "id": "a452bf26", "metadata": { "editable": true }, @@ -3157,7 +3151,7 @@ }, { "cell_type": "markdown", - "id": "6e0b933c", + "id": "603ea987", "metadata": { "editable": true }, @@ -3169,7 +3163,7 @@ }, { "cell_type": "markdown", - "id": "e3019867", + "id": "61b65c66", "metadata": { "editable": true }, @@ -3181,7 +3175,7 @@ }, { "cell_type": "markdown", - "id": "84b218f8", + "id": "d08fd064", "metadata": { "editable": true }, @@ -3193,7 +3187,7 @@ }, { "cell_type": "markdown", - "id": "19a7596b", + "id": "e8f62983", "metadata": { "editable": true }, @@ -3203,7 +3197,7 @@ }, { "cell_type": "markdown", - "id": "bd703e67", + "id": "d68a9415", "metadata": { "editable": true }, @@ -3215,7 +3209,7 @@ }, { "cell_type": "markdown", - "id": "123c9939", + "id": "3307fed7", "metadata": { "editable": true }, @@ -3225,7 +3219,7 @@ }, { "cell_type": "markdown", - "id": "e25cd9d9", + "id": "8a910e57", "metadata": { "editable": true }, @@ -3237,7 +3231,7 @@ }, { "cell_type": "markdown", - "id": "7a90c314", + "id": "218a6b48", "metadata": { "editable": true }, @@ -3248,7 +3242,7 @@ }, { "cell_type": "markdown", - "id": "342cbb0e", + "id": "8f3748ba", "metadata": { "editable": true }, @@ -3260,7 +3254,7 @@ }, { "cell_type": "markdown", - "id": "8174f656", + "id": "d0385420", "metadata": { "editable": true }, @@ -3272,7 +3266,7 @@ }, { "cell_type": "markdown", - "id": "9d4a6e02", + "id": "4644a05e", "metadata": { "editable": true }, @@ -3282,7 +3276,7 @@ }, { "cell_type": "markdown", - "id": "6165636b", + "id": "bfb350df", "metadata": { "editable": true }, @@ -3294,7 +3288,7 @@ }, { "cell_type": "markdown", - "id": "cd5ead70", + "id": "508acac7", "metadata": { "editable": true }, @@ -3306,7 +3300,7 @@ }, { "cell_type": "markdown", - "id": "ea18f6fe", + "id": "1cde0c41", "metadata": { "editable": true }, @@ -3316,7 +3310,7 @@ }, { "cell_type": "markdown", - "id": "9b42e1cf", + "id": "683baaea", "metadata": { "editable": true }, @@ -3328,7 +3322,7 @@ }, { "cell_type": "markdown", - "id": "ddc58b22", + "id": "ec9c67ea", "metadata": { "editable": true }, @@ -3338,7 +3332,7 @@ }, { "cell_type": "markdown", - "id": "288e8e6a", + "id": "cdc9c6fc", "metadata": { "editable": true }, @@ -3350,7 +3344,7 @@ }, { "cell_type": "markdown", - "id": "4fd80694", + "id": "c7590b65", "metadata": { "editable": true }, @@ -3360,7 +3354,7 @@ }, { "cell_type": "markdown", - "id": "b006a8c2", + "id": "f2d7afb2", "metadata": { "editable": true }, @@ -3400,7 +3394,7 @@ }, { "cell_type": "markdown", - "id": "725d878b", + "id": "69fd907d", "metadata": { "editable": true }, @@ -3417,7 +3411,7 @@ }, { "cell_type": "markdown", - "id": "fd5e5178", + "id": "33b93521", "metadata": { "editable": true }, @@ -3440,7 +3434,7 @@ }, { "cell_type": "markdown", - "id": "153ac58e", + "id": "600d8db6", "metadata": { "editable": true }, @@ -3457,7 +3451,7 @@ }, { "cell_type": "markdown", - "id": "3a4c4a00", + "id": "22fc0a80", "metadata": { "editable": true }, @@ -3476,7 +3470,7 @@ }, { "cell_type": "markdown", - "id": "c102eee7", + "id": "bd71990f", "metadata": { "editable": true }, @@ -3487,7 +3481,7 @@ }, { "cell_type": "markdown", - "id": "7005d428", + "id": "587d44ae", "metadata": { "editable": true }, @@ -3499,7 +3493,7 @@ }, { "cell_type": "markdown", - "id": "ebdbde59", + "id": "2158156f", "metadata": { "editable": true }, @@ -3517,7 +3511,7 @@ }, { "cell_type": "markdown", - "id": "8757437b", + "id": "10eb0b7c", "metadata": { "editable": true }, @@ -3533,7 +3527,7 @@ }, { "cell_type": "markdown", - "id": "dba77cf1", + "id": "2aceb644", "metadata": { "editable": true }, @@ -3545,7 +3539,7 @@ }, { "cell_type": "markdown", - "id": "2f275695", + "id": "1465b8be", "metadata": { "editable": true }, @@ -3555,7 +3549,7 @@ }, { "cell_type": "markdown", - "id": "32c17033", + "id": "b3afc822", "metadata": { "editable": true }, @@ -3570,7 +3564,7 @@ }, { "cell_type": "markdown", - "id": "13d50641", + "id": "4357f67d", "metadata": { "editable": true }, @@ -3582,7 +3576,7 @@ }, { "cell_type": "markdown", - "id": "e32d182b", + "id": "b2ed8199", "metadata": { "editable": true }, @@ -3592,7 +3586,7 @@ }, { "cell_type": "markdown", - "id": "566185cc", + "id": "a28f5e2a", "metadata": { "editable": true }, @@ -3604,7 +3598,7 @@ }, { "cell_type": "markdown", - "id": "69cc07d3", + "id": "dda00171", "metadata": { "editable": true }, @@ -3614,7 +3608,7 @@ }, { "cell_type": "markdown", - "id": "5a62e55b", + "id": "99e49156", "metadata": { "editable": true }, @@ -3626,7 +3620,7 @@ }, { "cell_type": "markdown", - "id": "185a7b6c", + "id": "3de354b0", "metadata": { "editable": true }, @@ -3638,7 +3632,7 @@ }, { "cell_type": "markdown", - "id": "b63994c4", + "id": "9b719377", "metadata": { "editable": true }, @@ -3653,7 +3647,7 @@ }, { "cell_type": "markdown", - "id": "1b5e5ea8", + "id": "f46453c7", "metadata": { "editable": true }, @@ -3664,7 +3658,7 @@ }, { "cell_type": "markdown", - "id": "c7cba8d9", + "id": "0255efb1", "metadata": { "editable": true }, @@ -3684,7 +3678,7 @@ }, { "cell_type": "markdown", - "id": "34a321a1", + "id": "61df6aad", "metadata": { "editable": true }, @@ -3696,7 +3690,7 @@ }, { "cell_type": "markdown", - "id": "adeb4e2a", + "id": "ac44e8fa", "metadata": { "editable": true }, @@ -3706,7 +3700,7 @@ }, { "cell_type": "markdown", - "id": "983c4d05", + "id": "a73ed285", "metadata": { "editable": true }, @@ -3718,7 +3712,7 @@ }, { "cell_type": "markdown", - "id": "30746d8f", + "id": "4809c104", "metadata": { "editable": true }, @@ -3747,7 +3741,7 @@ }, { "cell_type": "markdown", - "id": "15b1904e", + "id": "9ff4078a", "metadata": { "editable": true }, @@ -3774,7 +3768,7 @@ }, { "cell_type": "markdown", - "id": "825d56c0", + "id": "78a8b113", "metadata": { "editable": true }, @@ -3785,7 +3779,7 @@ { "cell_type": "code", "execution_count": 26, - "id": "83389e7a", + "id": "47f6d805", "metadata": { "collapsed": false, "editable": true @@ -3825,7 +3819,7 @@ }, { "cell_type": "markdown", - "id": "6c1d5c64", + "id": "5d841c14", "metadata": { "editable": true }, @@ -3842,7 +3836,7 @@ }, { "cell_type": "markdown", - "id": "092d08fb", + "id": "579b46a4", "metadata": { "editable": true }, @@ -3865,7 +3859,7 @@ }, { "cell_type": "markdown", - "id": "680ca861", + "id": "1bb48e3c", "metadata": { "editable": true }, @@ -3879,7 +3873,7 @@ }, { "cell_type": "markdown", - "id": "d9109bdb", + "id": "a872fcf9", "metadata": { "editable": true }, @@ -3898,7 +3892,7 @@ }, { "cell_type": "markdown", - "id": "1bc782ad", + "id": "f0565ccd", "metadata": { "editable": true }, @@ -3908,7 +3902,7 @@ }, { "cell_type": "markdown", - "id": "fd98474c", + "id": "a659e96f", "metadata": { "editable": true }, @@ -3920,7 +3914,7 @@ }, { "cell_type": "markdown", - "id": "27505b56", + "id": "fcfcf6b0", "metadata": { "editable": true }, @@ -3934,7 +3928,7 @@ }, { "cell_type": "markdown", - "id": "97458ec0", + "id": "ea39064c", "metadata": { "editable": true }, @@ -3946,7 +3940,7 @@ }, { "cell_type": "markdown", - "id": "6a940c34", + "id": "0096e499", "metadata": { "editable": true }, @@ -3956,7 +3950,7 @@ }, { "cell_type": "markdown", - "id": "beb7c9c1", + "id": "bf32dfa9", "metadata": { "editable": true }, @@ -3968,7 +3962,7 @@ }, { "cell_type": "markdown", - "id": "892eca8e", + "id": "e0d6fee2", "metadata": { "editable": true }, @@ -3985,7 +3979,7 @@ }, { "cell_type": "markdown", - "id": "d716176c", + "id": "0cb15d9d", "metadata": { "editable": true }, @@ -3995,7 +3989,7 @@ }, { "cell_type": "markdown", - "id": "d6f76ea3", + "id": "754f4312", "metadata": { "editable": true }, @@ -4011,7 +4005,7 @@ }, { "cell_type": "markdown", - "id": "6cd96381", + "id": "5bd1e9b0", "metadata": { "editable": true }, @@ -4021,7 +4015,7 @@ }, { "cell_type": "markdown", - "id": "3235bb2a", + "id": "2a839ac1", "metadata": { "editable": true }, @@ -4037,7 +4031,7 @@ }, { "cell_type": "markdown", - "id": "cfb5e5fa", + "id": "69e34c64", "metadata": { "editable": true }, @@ -4047,7 +4041,7 @@ }, { "cell_type": "markdown", - "id": "30c811c8", + "id": "b32ae1de", "metadata": { "editable": true }, @@ -4063,7 +4057,7 @@ }, { "cell_type": "markdown", - "id": "b64ff89b", + "id": "00c3ff66", "metadata": { "editable": true }, @@ -4073,7 +4067,7 @@ }, { "cell_type": "markdown", - "id": "d2d214b1", + "id": "92f1238d", "metadata": { "editable": true }, @@ -4090,7 +4084,7 @@ }, { "cell_type": "markdown", - "id": "1734cbea", + "id": "71f43637", "metadata": { "editable": true }, @@ -4102,7 +4096,7 @@ }, { "cell_type": "markdown", - "id": "18b87d79", + "id": "4bac0a15", "metadata": { "editable": true }, @@ -4114,7 +4108,7 @@ }, { "cell_type": "markdown", - "id": "7424dbeb", + "id": "b523b964", "metadata": { "editable": true }, @@ -4126,7 +4120,7 @@ }, { "cell_type": "markdown", - "id": "8bfde7d9", + "id": "3d7f8195", "metadata": { "editable": true }, @@ -4136,7 +4130,7 @@ }, { "cell_type": "markdown", - "id": "d7fae153", + "id": "f308dd0a", "metadata": { "editable": true }, @@ -4148,7 +4142,7 @@ }, { "cell_type": "markdown", - "id": "a5fe659e", + "id": "929784cf", "metadata": { "editable": true }, @@ -4160,7 +4154,7 @@ }, { "cell_type": "markdown", - "id": "0494a740", + "id": "09dccee1", "metadata": { "editable": true }, @@ -4172,7 +4166,7 @@ }, { "cell_type": "markdown", - "id": "cd9e9a2d", + "id": "165b3f17", "metadata": { "editable": true }, @@ -4182,7 +4176,7 @@ }, { "cell_type": "markdown", - "id": "a36f09cb", + "id": "24a8dd50", "metadata": { "editable": true }, @@ -4194,7 +4188,7 @@ }, { "cell_type": "markdown", - "id": "c595c4ab", + "id": "2597dc03", "metadata": { "editable": true }, @@ -4204,7 +4198,7 @@ }, { "cell_type": "markdown", - "id": "54ea720c", + "id": "4d40ddce", "metadata": { "editable": true }, @@ -4216,7 +4210,7 @@ }, { "cell_type": "markdown", - "id": "3b8cb8cc", + "id": "41d0e0cb", "metadata": { "editable": true }, @@ -4232,7 +4226,7 @@ }, { "cell_type": "markdown", - "id": "e825b356", + "id": "e4bafe51", "metadata": { "editable": true }, @@ -4244,7 +4238,7 @@ }, { "cell_type": "markdown", - "id": "2cbc23f9", + "id": "aab4d56f", "metadata": { "editable": true }, @@ -4256,7 +4250,7 @@ }, { "cell_type": "markdown", - "id": "8665bb8b", + "id": "861395ef", "metadata": { "editable": true }, @@ -4266,7 +4260,7 @@ }, { "cell_type": "markdown", - "id": "2aedf32c", + "id": "299b8198", "metadata": { "editable": true }, @@ -4278,7 +4272,7 @@ }, { "cell_type": "markdown", - "id": "e64ed163", + "id": "2096c2e7", "metadata": { "editable": true }, @@ -4289,7 +4283,7 @@ }, { "cell_type": "markdown", - "id": "b060bb08", + "id": "4ad3b043", "metadata": { "editable": true }, @@ -4301,7 +4295,7 @@ }, { "cell_type": "markdown", - "id": "0e9f682e", + "id": "66bf91e3", "metadata": { "editable": true }, @@ -4311,7 +4305,7 @@ }, { "cell_type": "markdown", - "id": "084d10ae", + "id": "95afc99c", "metadata": { "editable": true }, @@ -4323,7 +4317,7 @@ }, { "cell_type": "markdown", - "id": "322ae2b5", + "id": "73334115", "metadata": { "editable": true }, @@ -4333,7 +4327,7 @@ }, { "cell_type": "markdown", - "id": "2b934378", + "id": "fb6f936e", "metadata": { "editable": true }, @@ -4345,7 +4339,7 @@ }, { "cell_type": "markdown", - "id": "76fa0775", + "id": "f9093b47", "metadata": { "editable": true }, @@ -4356,7 +4350,7 @@ }, { "cell_type": "markdown", - "id": "4ab1ab5e", + "id": "fe539ee1", "metadata": { "editable": true }, @@ -4368,7 +4362,7 @@ }, { "cell_type": "markdown", - "id": "5c3528cd", + "id": "d130c8c1", "metadata": { "editable": true }, @@ -4386,7 +4380,7 @@ }, { "cell_type": "markdown", - "id": "99446c56", + "id": "6787b5c2", "metadata": { "editable": true }, @@ -4402,7 +4396,7 @@ }, { "cell_type": "markdown", - "id": "52b4ef86", + "id": "b2e599e5", "metadata": { "editable": true }, @@ -4414,7 +4408,7 @@ }, { "cell_type": "markdown", - "id": "14d03f17", + "id": "854ff040", "metadata": { "editable": true }, @@ -4426,7 +4420,7 @@ }, { "cell_type": "markdown", - "id": "08983b4e", + "id": "aaf5e54e", "metadata": { "editable": true }, @@ -4438,7 +4432,7 @@ }, { "cell_type": "markdown", - "id": "bf4aff1c", + "id": "444a68be", "metadata": { "editable": true }, @@ -4451,7 +4445,7 @@ }, { "cell_type": "markdown", - "id": "d1a70450", + "id": "56e0f274", "metadata": { "editable": true }, @@ -4467,7 +4461,7 @@ }, { "cell_type": "markdown", - "id": "4441a82e", + "id": "a55a54c3", "metadata": { "editable": true }, @@ -4481,7 +4475,7 @@ }, { "cell_type": "markdown", - "id": "985fe9f4", + "id": "b614c964", "metadata": { "editable": true }, @@ -4491,7 +4485,7 @@ }, { "cell_type": "markdown", - "id": "7d0b48ad", + "id": "624b1c18", "metadata": { "editable": true }, @@ -4503,7 +4497,7 @@ }, { "cell_type": "markdown", - "id": "927a1cc9", + "id": "63dc085a", "metadata": { "editable": true }, @@ -4513,7 +4507,7 @@ }, { "cell_type": "markdown", - "id": "28fe8612", + "id": "28db2f6a", "metadata": { "editable": true }, @@ -4525,7 +4519,7 @@ }, { "cell_type": "markdown", - "id": "643c5c24", + "id": "a9f1ebdd", "metadata": { "editable": true }, @@ -4535,7 +4529,7 @@ }, { "cell_type": "markdown", - "id": "31eb5551", + "id": "0b8bf07b", "metadata": { "editable": true }, @@ -4549,7 +4543,7 @@ }, { "cell_type": "markdown", - "id": "ee97772f", + "id": "5f237448", "metadata": { "editable": true }, @@ -4566,7 +4560,7 @@ }, { "cell_type": "markdown", - "id": "fdef2a70", + "id": "75b7044c", "metadata": { "editable": true }, @@ -4582,7 +4576,7 @@ }, { "cell_type": "markdown", - "id": "68211a1f", + "id": "51268862", "metadata": { "editable": true }, @@ -4594,7 +4588,7 @@ }, { "cell_type": "markdown", - "id": "9a8a18e2", + "id": "608b9dff", "metadata": { "editable": true }, @@ -4607,7 +4601,7 @@ }, { "cell_type": "markdown", - "id": "e7d94e46", + "id": "b06c316f", "metadata": { "editable": true }, @@ -4621,7 +4615,7 @@ }, { "cell_type": "markdown", - "id": "0c9c0c07", + "id": "e82ba709", "metadata": { "editable": true }, @@ -4631,7 +4625,7 @@ }, { "cell_type": "markdown", - "id": "3fc933af", + "id": "92d739a1", "metadata": { "editable": true }, @@ -4644,7 +4638,7 @@ }, { "cell_type": "markdown", - "id": "e97cce9c", + "id": "14ce5cea", "metadata": { "editable": true }, @@ -4663,7 +4657,7 @@ }, { "cell_type": "markdown", - "id": "d1be42f8", + "id": "f7e1f2b1", "metadata": { "editable": true }, @@ -4675,7 +4669,7 @@ }, { "cell_type": "markdown", - "id": "e957492f", + "id": "71910404", "metadata": { "editable": true }, @@ -4687,7 +4681,7 @@ }, { "cell_type": "markdown", - "id": "6f4bd14c", + "id": "cbd60268", "metadata": { "editable": true }, @@ -4697,7 +4691,7 @@ }, { "cell_type": "markdown", - "id": "ba1b4c89", + "id": "e6c94e3d", "metadata": { "editable": true }, @@ -4709,7 +4703,7 @@ }, { "cell_type": "markdown", - "id": "c9563317", + "id": "20cf812e", "metadata": { "editable": true }, @@ -4722,7 +4716,7 @@ }, { "cell_type": "markdown", - "id": "ed451710", + "id": "dd1cb8be", "metadata": { "editable": true }, @@ -4741,7 +4735,7 @@ }, { "cell_type": "markdown", - "id": "4eabcccb", + "id": "98a4e944", "metadata": { "editable": true }, @@ -4751,7 +4745,7 @@ }, { "cell_type": "markdown", - "id": "78678f6f", + "id": "8c6e3845", "metadata": { "editable": true }, @@ -4770,7 +4764,7 @@ }, { "cell_type": "markdown", - "id": "5840e451", + "id": "bc13a77d", "metadata": { "editable": true }, @@ -4788,7 +4782,7 @@ }, { "cell_type": "markdown", - "id": "75f212b9", + "id": "19d6cd9e", "metadata": { "editable": true }, @@ -4802,7 +4796,7 @@ }, { "cell_type": "markdown", - "id": "af4b97f1", + "id": "c5c7eee1", "metadata": { "editable": true }, @@ -4817,7 +4811,7 @@ { "cell_type": "code", "execution_count": 27, - "id": "bceeb8a6", + "id": "6ab6bcc3", "metadata": { "collapsed": false, "editable": true @@ -4838,7 +4832,7 @@ }, { "cell_type": "markdown", - "id": "e438fa73", + "id": "839a512c", "metadata": { "editable": true }, @@ -4855,7 +4849,7 @@ { "cell_type": "code", "execution_count": 28, - "id": "01ec3279", + "id": "bad7396d", "metadata": { "collapsed": false, "editable": true @@ -4887,7 +4881,7 @@ }, { "cell_type": "markdown", - "id": "fb6ba409", + "id": "365c6ef8", "metadata": { "editable": true }, @@ -4901,7 +4895,7 @@ }, { "cell_type": "markdown", - "id": "6c5bfe67", + "id": "6fd82fe9", "metadata": { "editable": true }, @@ -4914,7 +4908,7 @@ { "cell_type": "code", "execution_count": 29, - "id": "b2b07565", + "id": "80ba738c", "metadata": { "collapsed": false, "editable": true @@ -4939,7 +4933,7 @@ }, { "cell_type": "markdown", - "id": "e26d9b42", + "id": "4f390c8f", "metadata": { "editable": true }, @@ -4949,7 +4943,7 @@ }, { "cell_type": "markdown", - "id": "6200c4da", + "id": "4bceabcb", "metadata": { "editable": true }, @@ -4960,7 +4954,7 @@ { "cell_type": "code", "execution_count": 30, - "id": "1a0f5c54", + "id": "0146e7c8", "metadata": { "collapsed": false, "editable": true @@ -5014,7 +5008,7 @@ }, { "cell_type": "markdown", - "id": "be666eb5", + "id": "6e15d041", "metadata": { "editable": true }, @@ -5031,7 +5025,7 @@ }, { "cell_type": "markdown", - "id": "cc79dbf1", + "id": "107d5b46", "metadata": { "editable": true }, @@ -5043,7 +5037,7 @@ }, { "cell_type": "markdown", - "id": "7aaa9582", + "id": "e47d0e76", "metadata": { "editable": true }, @@ -5055,7 +5049,7 @@ }, { "cell_type": "markdown", - "id": "3c9ca18c", + "id": "86b8daf6", "metadata": { "editable": true }, @@ -5065,7 +5059,7 @@ }, { "cell_type": "markdown", - "id": "7450e1de", + "id": "934cc6c5", "metadata": { "editable": true }, @@ -5082,7 +5076,7 @@ }, { "cell_type": "markdown", - "id": "c190057c", + "id": "2a384ee9", "metadata": { "editable": true }, @@ -5092,7 +5086,7 @@ }, { "cell_type": "markdown", - "id": "20f4c172", + "id": "e9a632a7", "metadata": { "editable": true }, @@ -5107,7 +5101,7 @@ }, { "cell_type": "markdown", - "id": "746607df", + "id": "8cbf4cb8", "metadata": { "editable": true }, @@ -5117,7 +5111,7 @@ }, { "cell_type": "markdown", - "id": "d2419f36", + "id": "b29a7909", "metadata": { "editable": true }, @@ -5131,7 +5125,7 @@ }, { "cell_type": "markdown", - "id": "0c4d5713", + "id": "31b9c6a9", "metadata": { "editable": true }, @@ -5143,7 +5137,7 @@ }, { "cell_type": "markdown", - "id": "c51b1e85", + "id": "cdc2f810", "metadata": { "editable": true }, @@ -5155,7 +5149,7 @@ }, { "cell_type": "markdown", - "id": "df3d6e17", + "id": "0b7d368d", "metadata": { "editable": true }, @@ -5167,7 +5161,7 @@ }, { "cell_type": "markdown", - "id": "bda15ad2", + "id": "6d5ddd28", "metadata": { "editable": true }, @@ -5177,7 +5171,7 @@ }, { "cell_type": "markdown", - "id": "40ad7cbc", + "id": "a18622fc", "metadata": { "editable": true }, @@ -5189,7 +5183,7 @@ }, { "cell_type": "markdown", - "id": "305bd308", + "id": "b5a8893c", "metadata": { "editable": true }, @@ -5199,7 +5193,7 @@ }, { "cell_type": "markdown", - "id": "bb83e451", + "id": "50a0a62a", "metadata": { "editable": true }, @@ -5216,7 +5210,7 @@ }, { "cell_type": "markdown", - "id": "64d007a7", + "id": "20380d89", "metadata": { "editable": true }, @@ -5226,7 +5220,7 @@ }, { "cell_type": "markdown", - "id": "c0fe2564", + "id": "10805b50", "metadata": { "editable": true }, @@ -5238,7 +5232,7 @@ }, { "cell_type": "markdown", - "id": "630c43cb", + "id": "b9c31a46", "metadata": { "editable": true }, @@ -5248,7 +5242,7 @@ }, { "cell_type": "markdown", - "id": "1e412f4c", + "id": "1f48b48e", "metadata": { "editable": true }, @@ -5260,7 +5254,7 @@ }, { "cell_type": "markdown", - "id": "2294efa0", + "id": "ad8f7a8c", "metadata": { "editable": true }, @@ -5274,7 +5268,7 @@ }, { "cell_type": "markdown", - "id": "ec2d9133", + "id": "9e0dec01", "metadata": { "editable": true }, @@ -5286,7 +5280,7 @@ }, { "cell_type": "markdown", - "id": "be85e557", + "id": "46fd0b6d", "metadata": { "editable": true }, @@ -5308,7 +5302,7 @@ }, { "cell_type": "markdown", - "id": "61531c33", + "id": "3d2047ca", "metadata": { "editable": true }, @@ -5320,7 +5314,7 @@ }, { "cell_type": "markdown", - "id": "549a9854", + "id": "4a5f5016", "metadata": { "editable": true }, @@ -5335,7 +5329,7 @@ }, { "cell_type": "markdown", - "id": "ace8d1d3", + "id": "52651fc6", "metadata": { "editable": true }, @@ -5347,7 +5341,7 @@ }, { "cell_type": "markdown", - "id": "4624e6fc", + "id": "fea09344", "metadata": { "editable": true }, @@ -5359,7 +5353,7 @@ }, { "cell_type": "markdown", - "id": "4b8a8b55", + "id": "bcfd303f", "metadata": { "editable": true }, @@ -5369,7 +5363,7 @@ }, { "cell_type": "markdown", - "id": "e8a41480", + "id": "f684d942", "metadata": { "editable": true }, @@ -5381,7 +5375,7 @@ }, { "cell_type": "markdown", - "id": "6a36c786", + "id": "1e54bd36", "metadata": { "editable": true }, @@ -5391,7 +5385,7 @@ }, { "cell_type": "markdown", - "id": "462349df", + "id": "4cdcdef2", "metadata": { "editable": true }, @@ -5403,7 +5397,7 @@ }, { "cell_type": "markdown", - "id": "f3e432cb", + "id": "a6d5bd03", "metadata": { "editable": true }, @@ -5413,7 +5407,7 @@ }, { "cell_type": "markdown", - "id": "20a1bdac", + "id": "a4d9fc21", "metadata": { "editable": true }, @@ -5425,7 +5419,7 @@ }, { "cell_type": "markdown", - "id": "43ac5bba", + "id": "119bc56e", "metadata": { "editable": true }, @@ -5442,7 +5436,7 @@ }, { "cell_type": "markdown", - "id": "ff1f6546", + "id": "d15cad60", "metadata": { "editable": true }, @@ -5455,7 +5449,7 @@ }, { "cell_type": "markdown", - "id": "cf2d5142", + "id": "f725d905", "metadata": { "editable": true }, @@ -5467,7 +5461,7 @@ }, { "cell_type": "markdown", - "id": "0e74ad82", + "id": "a2a5b25f", "metadata": { "editable": true }, @@ -5477,7 +5471,7 @@ }, { "cell_type": "markdown", - "id": "f0e17a56", + "id": "a9f43162", "metadata": { "editable": true }, @@ -5490,7 +5484,7 @@ }, { "cell_type": "markdown", - "id": "b11ffbe6", + "id": "debb0a19", "metadata": { "editable": true }, @@ -5500,7 +5494,7 @@ }, { "cell_type": "markdown", - "id": "3f4e49db", + "id": "2764c014", "metadata": { "editable": true }, @@ -5512,7 +5506,7 @@ }, { "cell_type": "markdown", - "id": "e22c2482", + "id": "ad141726", "metadata": { "editable": true }, @@ -5525,7 +5519,7 @@ }, { "cell_type": "markdown", - "id": "a7e7dfe5", + "id": "d194482f", "metadata": { "editable": true }, @@ -5538,7 +5532,7 @@ }, { "cell_type": "markdown", - "id": "94414ad1", + "id": "7ccf56c7", "metadata": { "editable": true }, @@ -5550,7 +5544,7 @@ }, { "cell_type": "markdown", - "id": "cbb571a8", + "id": "41939010", "metadata": { "editable": true }, @@ -5562,7 +5556,7 @@ }, { "cell_type": "markdown", - "id": "08d69de8", + "id": "93d38078", "metadata": { "editable": true }, @@ -5572,7 +5566,7 @@ }, { "cell_type": "markdown", - "id": "17827d0b", + "id": "9c6d063a", "metadata": { "editable": true }, @@ -5585,7 +5579,7 @@ }, { "cell_type": "markdown", - "id": "a2606f59", + "id": "90d9a525", "metadata": { "editable": true }, @@ -5597,7 +5591,7 @@ }, { "cell_type": "markdown", - "id": "1a261469", + "id": "d1c9d3ea", "metadata": { "editable": true }, @@ -5609,7 +5603,7 @@ }, { "cell_type": "markdown", - "id": "2c25d0ff", + "id": "6a03fd03", "metadata": { "editable": true }, @@ -5621,7 +5615,7 @@ }, { "cell_type": "markdown", - "id": "1cbbda83", + "id": "12f9e2f4", "metadata": { "editable": true }, @@ -5633,7 +5627,7 @@ }, { "cell_type": "markdown", - "id": "10e5cd79", + "id": "0bd449c0", "metadata": { "editable": true }, @@ -5647,7 +5641,7 @@ }, { "cell_type": "markdown", - "id": "8149c527", + "id": "528f4c54", "metadata": { "editable": true }, @@ -5659,7 +5653,7 @@ }, { "cell_type": "markdown", - "id": "86370c66", + "id": "a4e89b45", "metadata": { "editable": true }, @@ -5669,7 +5663,7 @@ }, { "cell_type": "markdown", - "id": "ca970c01", + "id": "af51b23c", "metadata": { "editable": true }, @@ -5681,7 +5675,7 @@ }, { "cell_type": "markdown", - "id": "0a6651d6", + "id": "26945717", "metadata": { "editable": true }, @@ -5693,7 +5687,7 @@ }, { "cell_type": "markdown", - "id": "feb46caa", + "id": "70a85186", "metadata": { "editable": true }, @@ -5705,7 +5699,7 @@ }, { "cell_type": "markdown", - "id": "ba2ccc4c", + "id": "86de1af1", "metadata": { "editable": true }, @@ -5717,7 +5711,7 @@ }, { "cell_type": "markdown", - "id": "99bd5e5f", + "id": "a7eaaac6", "metadata": { "editable": true }, @@ -5729,7 +5723,7 @@ }, { "cell_type": "markdown", - "id": "122ac3fa", + "id": "732d4020", "metadata": { "editable": true }, @@ -5748,7 +5742,7 @@ }, { "cell_type": "markdown", - "id": "2ed2f1af", + "id": "06f71f9c", "metadata": { "editable": true }, @@ -5760,7 +5754,7 @@ }, { "cell_type": "markdown", - "id": "ab6d373f", + "id": "04266404", "metadata": { "editable": true }, @@ -5770,7 +5764,7 @@ }, { "cell_type": "markdown", - "id": "12e89aa0", + "id": "753d4bf0", "metadata": { "editable": true }, @@ -5782,7 +5776,7 @@ }, { "cell_type": "markdown", - "id": "f5ad1a22", + "id": "ea8b1f8f", "metadata": { "editable": true }, @@ -5792,7 +5786,7 @@ }, { "cell_type": "markdown", - "id": "972a591b", + "id": "12703a7e", "metadata": { "editable": true }, @@ -5804,7 +5798,7 @@ }, { "cell_type": "markdown", - "id": "29b0a40c", + "id": "90522189", "metadata": { "editable": true }, @@ -5816,7 +5810,7 @@ }, { "cell_type": "markdown", - "id": "974b89b6", + "id": "b81abc7b", "metadata": { "editable": true }, @@ -5832,7 +5826,7 @@ }, { "cell_type": "markdown", - "id": "d32b5a75", + "id": "115018b1", "metadata": { "editable": true }, @@ -5844,7 +5838,7 @@ }, { "cell_type": "markdown", - "id": "b7b0e4a9", + "id": "8741b7a9", "metadata": { "editable": true }, @@ -5856,7 +5850,7 @@ }, { "cell_type": "markdown", - "id": "00480506", + "id": "5fe75d98", "metadata": { "editable": true }, @@ -5866,7 +5860,7 @@ }, { "cell_type": "markdown", - "id": "e478d349", + "id": "522e6278", "metadata": { "editable": true }, @@ -5878,7 +5872,7 @@ }, { "cell_type": "markdown", - "id": "9941badc", + "id": "eaa39cca", "metadata": { "editable": true }, @@ -5888,7 +5882,7 @@ }, { "cell_type": "markdown", - "id": "d78d129f", + "id": "230a8059", "metadata": { "editable": true }, @@ -5900,7 +5894,7 @@ }, { "cell_type": "markdown", - "id": "81e43d35", + "id": "698a93f7", "metadata": { "editable": true }, @@ -5917,7 +5911,7 @@ }, { "cell_type": "markdown", - "id": "ab030d9f", + "id": "96e49fbc", "metadata": { "editable": true }, @@ -5929,7 +5923,7 @@ }, { "cell_type": "markdown", - "id": "5c1a039a", + "id": "f2043d81", "metadata": { "editable": true }, @@ -5941,7 +5935,7 @@ }, { "cell_type": "markdown", - "id": "64005abb", + "id": "f2dd8e44", "metadata": { "editable": true }, @@ -5951,7 +5945,7 @@ }, { "cell_type": "markdown", - "id": "dd03458c", + "id": "0ab90bb2", "metadata": { "editable": true }, @@ -5963,7 +5957,7 @@ }, { "cell_type": "markdown", - "id": "c1845e9a", + "id": "1090467c", "metadata": { "editable": true }, @@ -5973,7 +5967,7 @@ }, { "cell_type": "markdown", - "id": "9daa3df6", + "id": "8bc71963", "metadata": { "editable": true }, @@ -5985,7 +5979,7 @@ }, { "cell_type": "markdown", - "id": "add636f0", + "id": "918da4ad", "metadata": { "editable": true }, @@ -5995,7 +5989,7 @@ }, { "cell_type": "markdown", - "id": "79c36fde", + "id": "ee673e3d", "metadata": { "editable": true }, @@ -6007,7 +6001,7 @@ }, { "cell_type": "markdown", - "id": "d4b4abb2", + "id": "03352030", "metadata": { "editable": true }, @@ -6017,7 +6011,7 @@ }, { "cell_type": "markdown", - "id": "93a6f35c", + "id": "1b29a63e", "metadata": { "editable": true }, @@ -6029,7 +6023,7 @@ }, { "cell_type": "markdown", - "id": "62647fc5", + "id": "206bcec2", "metadata": { "editable": true }, diff --git a/doc/LectureNotes/_build/html/exercisesweek34.html b/doc/LectureNotes/_build/html/exercisesweek34.html index 2295e962d..d574ae7a5 100644 --- a/doc/LectureNotes/_build/html/exercisesweek34.html +++ b/doc/LectureNotes/_build/html/exercisesweek34.html @@ -268,123 +268,6 @@ const thebe_selector_output = ".output, .cell_output" Week 35: From Ordinary Linear Regression to Ridge and Lasso Regression -

  • - - Exercises week 36 - -
  • -
  • - - Week 36: Statistical interpretation of Linear Regression and Resampling techniques - -
  • -
  • - - Exercises week 37 - -
  • -
  • - - Week 37: Statistical interpretations and Resampling Methods - -
  • -
  • - - Exercises week 38 - -
  • -
  • - - Week 38: Logistic Regression and Optimization - -
  • -
  • - - Exercises week 39 - -
  • -
  • - - Week 39: Optimization and Gradient Methods - -
  • -
  • - - Week 40: Gradient descent methods (continued) and start Neural networks - -
  • -
  • - - Exercises week 41 - -
  • -
  • - - Week 41 Neural networks and constructing a neural network code - -
  • -
  • - - Exercises week 42 - -
  • -
  • - - Week 42 Constructing a Neural Network code with introduction to Tensor flow - -
  • -
  • - - Exercises weeks 43 and 44 - -
  • -
  • - - Week 43: Deep Learning: Constructing a Neural Network code and solving differential equations - -
  • -
  • - - Week 44, Convolutional Neural Networks (CNN) - -
  • -
  • - - Week 45, Recurrent Neural Networks - -
  • -
  • - - Week 46: Decision Trees, Ensemble methods and Random Forests - -
  • -
  • - - Week 47: From Decision Trees to Ensemble Methods, Random Forests and Boosting Methods and Summary of Course - -
  • -
  • - - Exercise week 47 - -
  • - -

    - - Projects - -

    - @@ -530,7 +413,7 @@ doconce format html exercisesweek34.do.txt -->

    Exercises week 34

    FYS-STK3155/4155

    -

    Date: August 21-25, 2023

    +

    Date: August 19-23, 2024

    Exercises

    Here are three possible exercises for week 34

    @@ -605,7 +488,7 @@ The following simple Python instructions define our
    ---------------------------------------------------------------------------
     NameError                                 Traceback (most recent call last)
    -Input In [1], in <cell line: 1>()
    +Cell In[1], line 1
     ----> 1 x = np.random.rand(100,1)
           2 y = 2.0+5*x*x+0.1*np.random.randn(100,1)
     
    diff --git a/doc/LectureNotes/_build/html/exercisesweek35.html b/doc/LectureNotes/_build/html/exercisesweek35.html
    index 8aacf37e0..e0b625700 100644
    --- a/doc/LectureNotes/_build/html/exercisesweek35.html
    +++ b/doc/LectureNotes/_build/html/exercisesweek35.html
    @@ -268,123 +268,6 @@ const thebe_selector_output = ".output, .cell_output"
        Week 35: From Ordinary Linear Regression to Ridge and Lasso Regression
       
      
    - 
  • - - Exercises week 36 - -
  • -
  • - - Week 36: Statistical interpretation of Linear Regression and Resampling techniques - -
  • -
  • - - Exercises week 37 - -
  • -
  • - - Week 37: Statistical interpretations and Resampling Methods - -
  • -
  • - - Exercises week 38 - -
  • -
  • - - Week 38: Logistic Regression and Optimization - -
  • -
  • - - Exercises week 39 - -
  • -
  • - - Week 39: Optimization and Gradient Methods - -
  • -
  • - - Week 40: Gradient descent methods (continued) and start Neural networks - -
  • -
  • - - Exercises week 41 - -
  • -
  • - - Week 41 Neural networks and constructing a neural network code - -
  • -
  • - - Exercises week 42 - -
  • -
  • - - Week 42 Constructing a Neural Network code with introduction to Tensor flow - -
  • -
  • - - Exercises weeks 43 and 44 - -
  • -
  • - - Week 43: Deep Learning: Constructing a Neural Network code and solving differential equations - -
  • -
  • - - Week 44, Convolutional Neural Networks (CNN) - -
  • -
  • - - Week 45, Recurrent Neural Networks - -
  • -
  • - - Week 46: Decision Trees, Ensemble methods and Random Forests - -
  • -
  • - - Week 47: From Decision Trees to Ensemble Methods, Random Forests and Boosting Methods and Summary of Course - -
  • -
  • - - Exercise week 47 - -
  • - -

    - - Projects - -

    -
    @@ -519,8 +402,8 @@ const thebe_selector_output = ".output, .cell_output" doconce format html exercisesweek35.do.txt -->

    Exercises week 35

    -

    August 28-September 1, 2023

    -

    Date: Deadline is Friday September 1 at midnight

    +

    August 26-30, 2024

    +

    Date: Deadline is Friday August 30 at midnight

    Exercise 1: Analytical exercises

    In this exercise we derive the expressions for various derivatives of diff --git a/doc/LectureNotes/_build/html/genindex.html b/doc/LectureNotes/_build/html/genindex.html index d29f94064..10e0e9656 100644 --- a/doc/LectureNotes/_build/html/genindex.html +++ b/doc/LectureNotes/_build/html/genindex.html @@ -264,123 +264,6 @@ const thebe_selector_output = ".output, .cell_output" Week 35: From Ordinary Linear Regression to Ridge and Lasso Regression -

  • - - Exercises week 36 - -
  • -
  • - - Week 36: Statistical interpretation of Linear Regression and Resampling techniques - -
  • -
  • - - Exercises week 37 - -
  • -
  • - - Week 37: Statistical interpretations and Resampling Methods - -
  • -
  • - - Exercises week 38 - -
  • -
  • - - Week 38: Logistic Regression and Optimization - -
  • -
  • - - Exercises week 39 - -
  • -
  • - - Week 39: Optimization and Gradient Methods - -
  • -
  • - - Week 40: Gradient descent methods (continued) and start Neural networks - -
  • -
  • - - Exercises week 41 - -
  • -
  • - - Week 41 Neural networks and constructing a neural network code - -
  • -
  • - - Exercises week 42 - -
  • -
  • - - Week 42 Constructing a Neural Network code with introduction to Tensor flow - -
  • -
  • - - Exercises weeks 43 and 44 - -
  • -
  • - - Week 43: Deep Learning: Constructing a Neural Network code and solving differential equations - -
  • -
  • - - Week 44, Convolutional Neural Networks (CNN) - -
  • -
  • - - Week 45, Recurrent Neural Networks - -
  • -
  • - - Week 46: Decision Trees, Ensemble methods and Random Forests - -
  • -
  • - - Week 47: From Decision Trees to Ensemble Methods, Random Forests and Boosting Methods and Summary of Course - -
  • -
  • - - Exercise week 47 - -
  • - -

    - - Projects - -

    -
    diff --git a/doc/LectureNotes/_build/html/intro.html b/doc/LectureNotes/_build/html/intro.html index 20f41dfa9..b1f405215 100644 --- a/doc/LectureNotes/_build/html/intro.html +++ b/doc/LectureNotes/_build/html/intro.html @@ -265,123 +265,6 @@ const thebe_selector_output = ".output, .cell_output" Week 35: From Ordinary Linear Regression to Ridge and Lasso Regression -
  • - - Exercises week 36 - -
  • -
  • - - Week 36: Statistical interpretation of Linear Regression and Resampling techniques - -
  • -
  • - - Exercises week 37 - -
  • -
  • - - Week 37: Statistical interpretations and Resampling Methods - -
  • -
  • - - Exercises week 38 - -
  • -
  • - - Week 38: Logistic Regression and Optimization - -
  • -
  • - - Exercises week 39 - -
  • -
  • - - Week 39: Optimization and Gradient Methods - -
  • -
  • - - Week 40: Gradient descent methods (continued) and start Neural networks - -
  • -
  • - - Exercises week 41 - -
  • -
  • - - Week 41 Neural networks and constructing a neural network code - -
  • -
  • - - Exercises week 42 - -
  • -
  • - - Week 42 Constructing a Neural Network code with introduction to Tensor flow - -
  • -
  • - - Exercises weeks 43 and 44 - -
  • -
  • - - Week 43: Deep Learning: Constructing a Neural Network code and solving differential equations - -
  • -
  • - - Week 44, Convolutional Neural Networks (CNN) - -
  • -
  • - - Week 45, Recurrent Neural Networks - -
  • -
  • - - Week 46: Decision Trees, Ensemble methods and Random Forests - -
  • -
  • - - Week 47: From Decision Trees to Ensemble Methods, Random Forests and Boosting Methods and Summary of Course - -
  • -
  • - - Exercise week 47 - -
  • - -

    - - Projects - -

    -
    @@ -736,8 +619,6 @@ It provides composable transformations of Python+NumPy programs: differentiate,
    -
    -
    - @@ -268,123 +267,6 @@ const thebe_selector_output = ".output, .cell_output" Week 35: From Ordinary Linear Regression to Ridge and Lasso Regression -
  • - - Exercises week 36 - -
  • -
  • - - Week 36: Statistical interpretation of Linear Regression and Resampling techniques - -
  • -
  • - - Exercises week 37 - -
  • -
  • - - Week 37: Statistical interpretations and Resampling Methods - -
  • -
  • - - Exercises week 38 - -
  • -
  • - - Week 38: Logistic Regression and Optimization - -
  • -
  • - - Exercises week 39 - -
  • -
  • - - Week 39: Optimization and Gradient Methods - -
  • -
  • - - Week 40: Gradient descent methods (continued) and start Neural networks - -
  • -
  • - - Exercises week 41 - -
  • -
  • - - Week 41 Neural networks and constructing a neural network code - -
  • -
  • - - Exercises week 42 - -
  • -
  • - - Week 42 Constructing a Neural Network code with introduction to Tensor flow - -
  • -
  • - - Exercises weeks 43 and 44 - -
  • -
  • - - Week 43: Deep Learning: Constructing a Neural Network code and solving differential equations - -
  • -
  • - - Week 44, Convolutional Neural Networks (CNN) - -
  • -
  • - - Week 45, Recurrent Neural Networks - -
  • -
  • - - Week 46: Decision Trees, Ensemble methods and Random Forests - -
  • -
  • - - Week 47: From Decision Trees to Ensemble Methods, Random Forests and Boosting Methods and Summary of Course - -
  • -
  • - - Exercise week 47 - -
  • - -

    - - Projects - -

    -
    @@ -1240,7 +1122,7 @@ doconce format html week35.do.txt --no_mako -->

    Week 35: From Ordinary Linear Regression to Ridge and Lasso Regression

    Morten Hjorth-Jensen, Department of Physics, University of Oslo and Department of Physics and Astronomy and National Superconducting Cyclotron Laboratory, Michigan State University

    -

    Date: August 28-September 1

    +

    Date: August 26-30

    Plans for week 35

    The main topics are:

    @@ -1248,17 +1130,14 @@ doconce format html week35.do.txt --no_mako -->
  • Brief repetition from last week

  • Derivation of the equations for ordinary least squares

  • Discussion on how to prepare data and examples of applications of linear regression

  • -
  • Material for the lecture on Thursday: Mathematical interpretations of linear regression

  • -
  • Thursday: Ridge and Lasso regression and Singular Value Decomposition

  • -
  • Video of lecture

  • -
  • Whiteboard notes

  • +
  • Material for the lecture on Monday: Mathematical interpretations of linear regression

  • +
  • Monday: Ridge and Lasso regression and Singular Value Decomposition

  • Reading recommendations:

    1. See lecture notes for week 35 at https://compphysics.github.io/MachineLearning/doc/web/course.html

    2. Goodfellow, Bengio and Courville, Deep Learning, chapter 2 on linear algebra and sections 3.1-3.10 on elements of statistics (background)

    3. -
    4. Hastie, Tibshirani and Friedman, The elements of statistical learning, sections 3.1-3.4 (on relevance for the discussion of linear regression).

    @@ -1731,7 +1610,7 @@ Since we are not using Scikit-Learn here we can define our own
    -
    0.9958946686888259
    +
    0.9952638231265687
     
    @@ -1748,7 +1627,7 @@ Since we are not using Scikit-Learn here we can define our own
    -
    0.008142188979400687
    +
    0.011761161707539526
     
    @@ -1763,23 +1642,23 @@ Since we are not using Scikit-Learn here we can define our own
    -
    [0.0476021  0.02689869 0.01088331 0.01783105 0.00544013 0.05110385
    - 0.02900389 0.01629703 0.05594058 0.02527366 0.00657884 0.04127087
    - 0.01925607 0.02221978 0.01212083 0.04919181 0.00745959 0.03110176
    - 0.010203   0.0076995  0.00298213 0.01702968 0.04557362 0.03192124
    - 0.06668218 0.0178392  0.00706728 0.0095239  0.00784983 0.05197707
    - 0.01519861 0.0134093  0.00291822 0.00311528 0.02036289 0.01136976
    - 0.0189559  0.04908155 0.01384493 0.01715895 0.01262581 0.00756465
    - 0.00473818 0.00224783 0.01773579 0.03804636 0.03945128 0.01662346
    - 0.05137822 0.00206124 0.06090176 0.01632212 0.01220987 0.06361921
    - 0.00318122 0.00362359 0.03177421 0.06554078 0.00123144 0.01091059
    - 0.04958045 0.00291334 0.01541622 0.00607264 0.05274561 0.007352
    - 0.06263415 0.01593612 0.00853836 0.01006042 0.00223784 0.02106518
    - 0.02410507 0.08294341 0.0043675  0.06502562 0.03422156 0.00213264
    - 0.02365779 0.01883403 0.00683222 0.01848399 0.02930957 0.02161016
    - 0.02746315 0.02774744 0.03591454 0.04814746 0.00568413 0.00215333
    - 0.03631783 0.02866734 0.01684326 0.00953152 0.01001378 0.00119895
    - 0.02603725 0.00127672 0.04770636 0.028797  ]
    +
    [0.00035753 0.04937621 0.02268114 0.03112297 0.01856502 0.05322899
    + 0.01397927 0.03999935 0.02508836 0.01834042 0.0652633  0.00887114
    + 0.01956921 0.01987248 0.06294313 0.01152476 0.00328431 0.03564082
    + 0.02337045 0.01743586 0.01278035 0.02400968 0.08388138 0.03270341
    + 0.00335956 0.01031903 0.09575469 0.00956774 0.00900879 0.01867985
    + 0.01191227 0.02090296 0.04045671 0.03582958 0.06692165 0.06615863
    + 0.06594872 0.03756493 0.00488992 0.01405237 0.00117071 0.0017567
    + 0.05006306 0.02545639 0.03456485 0.00373984 0.02576476 0.03530741
    + 0.00092902 0.0275742  0.05948007 0.01321652 0.18500705 0.00382166
    + 0.00327313 0.01853877 0.01771317 0.05293662 0.07199977 0.00836148
    + 0.01541649 0.00343257 0.00626797 0.05350297 0.01548272 0.05235058
    + 0.04310698 0.00225189 0.02356396 0.01690512 0.03467756 0.00064364
    + 0.02593596 0.00019607 0.0029508  0.0180194  0.06825695 0.01659559
    + 0.01971341 0.02012338 0.02241311 0.00135736 0.0095653  0.05695438
    + 0.00395659 0.07068033 0.02699873 0.00919237 0.02493299 0.00803115
    + 0.0293055  0.02178063 0.00594353 0.04081883 0.01325225 0.0386443
    + 0.01889695 0.02810253 0.0181166  0.01135924]
     
    @@ -1848,15 +1727,15 @@ but now splitting the data into a training set and a test set.

    -
    [ 2.02283241  0.15972118  3.84256187  1.89005305 -0.93145755]
    +
    [ 2.00507876  0.39026883  3.20764972  2.73806921 -1.39609089]
     Training R2
    -0.9959044445566834
    +0.9972493421341901
     Training MSE
    -0.010349061754867921
    +0.007021475481484069
     Test R2
    -0.9961996615568259
    +0.9976639055733267
     Test MSE
    -0.008771887357306985
    +0.00575158411598985
     
    @@ -2903,45 +2782,73 @@ the house using the features (predictors) listed here.

    -
    /Users/mhjensen/miniforge3/envs/myenv/lib/python3.9/site-packages/sklearn/utils/deprecation.py:87: FutureWarning: Function load_boston is deprecated; `load_boston` is deprecated in 1.0 and will be removed in 1.2.
    +
    ---------------------------------------------------------------------------
    +ImportError                               Traceback (most recent call last)
    +Cell In[16], line 1
    +----> 1 from sklearn.datasets import load_boston
    +      3 boston_dataset = load_boston()
    +      5 # boston_dataset is a dictionary
    +      6 # let's check what it contains
     
    -    The Boston housing prices dataset has an ethical problem. You can refer to
    -    the documentation of this function for further details.
    +File ~/miniforge3/envs/myenv/lib/python3.9/site-packages/sklearn/datasets/__init__.py:157, in __getattr__(name)
    +    108 if name == "load_boston":
    +    109     msg = textwrap.dedent("""
    +    110         `load_boston` has been removed from scikit-learn since version 1.2.
    +    111 
    +   (...)
    +    155         <https://www.researchgate.net/publication/4974606_Hedonic_housing_prices_and_the_demand_for_clean_air>
    +    156         """)
    +--> 157     raise ImportError(msg)
    +    158 try:
    +    159     return globals()[name]
     
    -    The scikit-learn maintainers therefore strongly discourage the use of this
    -    dataset unless the purpose of the code is to study and educate about
    -    ethical issues in data science and machine learning.
    +ImportError: 
    +`load_boston` has been removed from scikit-learn since version 1.2.
     
    -    In this special case, you can fetch the dataset from the original
    -    source::
    +The Boston housing prices dataset has an ethical problem: as
    +investigated in [1], the authors of this dataset engineered a
    +non-invertible variable "B" assuming that racial self-segregation had a
    +positive impact on house prices [2]. Furthermore the goal of the
    +research that led to the creation of this dataset was to study the
    +impact of air quality but it did not give adequate demonstration of the
    +validity of this assumption.
     
    -        import pandas as pd
    -        import numpy as np
    +The scikit-learn maintainers therefore strongly discourage the use of
    +this dataset unless the purpose of the code is to study and educate
    +about ethical issues in data science and machine learning.
     
    +In this special case, you can fetch the dataset from the original
    +source::
     
    -        data_url = "http://lib.stat.cmu.edu/datasets/boston"
    -        raw_df = pd.read_csv(data_url, sep="\s+", skiprows=22, header=None)
    -        data = np.hstack([raw_df.values[::2, :], raw_df.values[1::2, :2]])
    -        target = raw_df.values[1::2, 2]
    +    import pandas as pd
    +    import numpy as np
     
    -    Alternative datasets include the California housing dataset (i.e.
    -    :func:`~sklearn.datasets.fetch_california_housing`) and the Ames housing
    -    dataset. You can load the datasets as follows::
    +    data_url = "http://lib.stat.cmu.edu/datasets/boston"
    +    raw_df = pd.read_csv(data_url, sep="\s+", skiprows=22, header=None)
    +    data = np.hstack([raw_df.values[::2, :], raw_df.values[1::2, :2]])
    +    target = raw_df.values[1::2, 2]
     
    -        from sklearn.datasets import fetch_california_housing
    -        housing = fetch_california_housing()
    +Alternative datasets include the California housing dataset and the
    +Ames housing dataset. You can load the datasets as follows::
     
    -    for the California housing dataset and::
    +    from sklearn.datasets import fetch_california_housing
    +    housing = fetch_california_housing()
     
    -        from sklearn.datasets import fetch_openml
    -        housing = fetch_openml(name="house_prices", as_frame=True)
    +for the California housing dataset and::
     
    -    for the Ames housing dataset.
    -    
    -  warnings.warn(msg, category=FutureWarning)
    -
    -
    -
    dict_keys(['data', 'target', 'feature_names', 'DESCR', 'filename', 'data_module'])
    +    from sklearn.datasets import fetch_openml
    +    housing = fetch_openml(name="house_prices", as_frame=True)
    +
    +for the Ames housing dataset.
    +
    +[1] M Carlisle.
    +"Racist data destruction?"
    +<https://medium.com/@docintangible/racist-data-destruction-113e3eff54a8>
    +
    +[2] Harrison Jr, David, and Daniel L. Rubinfeld.
    +"Hedonic housing prices and the demand for clean air."
    +Journal of environmental economics and management 5.1 (1978): 81-102.
    +<https://www.researchgate.net/publication/4974606_Hedonic_housing_prices_and_the_demand_for_clean_air>
     
    @@ -2964,25 +2871,6 @@ the house using the features (predictors) listed here.

    -
    -
    CRIM       0
    -ZN         0
    -INDUS      0
    -CHAS       0
    -NOX        0
    -RM         0
    -AGE        0
    -DIS        0
    -RAD        0
    -TAX        0
    -PTRATIO    0
    -B          0
    -LSTAT      0
    -MEDV       0
    -dtype: int64
    -
    -
    -

    We can then visualize the data

    @@ -2996,13 +2884,6 @@ dtype: int64
    -
    -
    /Users/mhjensen/miniforge3/envs/myenv/lib/python3.9/site-packages/seaborn/distributions.py:2619: FutureWarning: `distplot` is a deprecated function and will be removed in a future version. Please adapt your code to use either `displot` (a figure-level function with similar flexibility) or `histplot` (an axes-level function for histograms).
    -  warnings.warn(msg, FutureWarning)
    -
    -
    -_images/week35_199_1.png -

    It is now useful to look at the correlation matrix

    @@ -3015,12 +2896,6 @@ dtype: int64
    -
    -
    <AxesSubplot:>
    -
    -
    -_images/week35_201_1.png -

    From the above coorelation plot we can see that MEDV is strongly correlated to LSTAT and RM. We see also that RAD and TAX are stronly correlated, but we don’t include this in our features together to avoid multi-colinearity

    @@ -3041,9 +2916,6 @@ dtype: int64
    -
    -_images/week35_203_0.png -

    Now we start training our model

    @@ -3069,14 +2941,6 @@ dtype: int64
    -
    -
    (404, 2)
    -(102, 2)
    -(404,)
    -(102,)
    -
    -
    -

    Then we use the linear regression functionality from Scikit-Learn

    @@ -3115,20 +2979,6 @@ dtype: int64
    -
    -
    The model performance for training set
    ---------------------------------------
    -RMSE is 5.637129335071195
    -R2 score is 0.6300745149331701
    -
    -
    -The model performance for testing set
    ---------------------------------------
    -RMSE is 5.137400784702911
    -R2 score is 0.6628996975186953
    -
    -
    -
    @@ -3139,9 +2989,6 @@ R2 score is 0.6628996975186953
    -
    -_images/week35_210_0.png -
    @@ -3421,25 +3268,6 @@ In general the economy-size SVD leads to less FLOPS and still conserving the des
    -
    -
    [[ 1. -1.]
    - [ 1. -1.]]
    -test U
    -[[0. 0.]
    - [0. 0.]]
    -test VT
    -[[0. 0.]
    - [0. 0.]]
    -[[-0.70710678 -0.70710678]
    - [-0.70710678  0.70710678]]
    -[2.00000000e+00 3.35470445e-17]
    -[[-0.70710678  0.70710678]
    - [ 0.70710678  0.70710678]]
    -[[-3.33066907e-16  4.44089210e-16]
    - [ 0.00000000e+00  2.22044605e-16]]
    -
    -
    -

    The matrix \(\boldsymbol{X}\) has columns that are linearly dependent. The first column is the row-wise sum of the other two columns. The rank of a @@ -3795,14 +3623,6 @@ covariance matrix through the np.linalg.eig() function.

    -
    -
    0.10790125813226321
    -4.340071371496255
    -[[ 1.04193203  3.08165104]
    - [ 3.08165104 10.18383522]]
    -
    -
    -
    @@ -3838,14 +3658,6 @@ a more brute force way. Here we scale the mean values for each column of the des
    -
    -
    0.08881497884574564
    -1.7086067479626619
    -[[1.         0.66080313]
    - [0.66080313 1.        ]]
    -
    -
    -

    We see that the matrix elements along the diagonal are one as they should be and that the matrix is symmetric. Furthermore, diagonalizing @@ -3874,34 +3686,6 @@ this matrix we easily see that it is a positive definite matrix.

    -
    -
    [[-0.40620066 -2.01265755]
    - [ 0.01458611  0.37737221]
    - [-1.0895387  -3.65442354]
    - [ 0.2338675   1.12044974]
    - [ 0.4676059   1.54393936]
    - [-0.65891389 -3.16304863]
    - [-0.1715252   0.39197698]
    - [ 0.71142161  2.95511792]
    - [ 0.39214397  0.13069442]
    - [ 0.50655336  2.3105791 ]]
    -          0         1
    -0 -0.406201 -2.012658
    -1  0.014586  0.377372
    -2 -1.089539 -3.654424
    -3  0.233868  1.120450
    -4  0.467606  1.543939
    -5 -0.658914 -3.163049
    -6 -0.171525  0.391977
    -7  0.711422  2.955118
    -8  0.392144  0.130694
    -9  0.506553  2.310579
    -          0         1
    -0  1.000000  0.952387
    -1  0.952387  1.000000
    -
    -
    -

    We expand this model to the Franke function discussed above.

    @@ -3955,43 +3739,6 @@ this matrix we easily see that it is a positive definite matrix.

    -
    -
         0         1         2         3         4         5         6         7   \
    -0   0.0  0.000000  0.000000  0.000000  0.000000  0.000000  0.000000  0.000000   
    -1   0.0  0.078974  0.081276  0.075889  0.077168  0.078540  0.065410  0.066474   
    -2   0.0  0.081276  0.084076  0.078336  0.079946  0.081655  0.067707  0.069028   
    -3   0.0  0.075889  0.078336  0.077460  0.078986  0.080616  0.069452  0.070737   
    -4   0.0  0.077168  0.079946  0.078986  0.080764  0.082653  0.070986  0.072476   
    -5   0.0  0.078540  0.081655  0.080616  0.082653  0.084809  0.072621  0.074323   
    -6   0.0  0.065410  0.067707  0.069452  0.070986  0.072621  0.064074  0.065378   
    -7   0.0  0.066474  0.069028  0.070737  0.072476  0.074323  0.065378  0.066854   
    -8   0.0  0.067637  0.070457  0.072132  0.074084  0.076150  0.066787  0.068441   
    -9   0.0  0.068906  0.072000  0.073644  0.075816  0.078110  0.068307  0.070146   
    -10  0.0  0.055734  0.057835  0.060872  0.062337  0.063894  0.057393  0.058645   
    -11  0.0  0.056683  0.058996  0.062016  0.063653  0.065390  0.058552  0.059951   
    -12  0.0  0.057722  0.060254  0.063260  0.065077  0.066999  0.059807  0.061359   
    -13  0.0  0.058854  0.061614  0.064609  0.066612  0.068727  0.061163  0.062874   
    -14  0.0  0.060083  0.063080  0.066066  0.068264  0.070582  0.062624  0.064501   
    -
    -          8         9         10        11        12        13        14  
    -0   0.000000  0.000000  0.000000  0.000000  0.000000  0.000000  0.000000  
    -1   0.067637  0.068906  0.055734  0.056683  0.057722  0.058854  0.060083  
    -2   0.070457  0.072000  0.057835  0.058996  0.060254  0.061614  0.063080  
    -3   0.072132  0.073644  0.060872  0.062016  0.063260  0.064609  0.066066  
    -4   0.074084  0.075816  0.062337  0.063653  0.065077  0.066612  0.068264  
    -5   0.076150  0.078110  0.063894  0.065390  0.066999  0.068727  0.070582  
    -6   0.066787  0.068307  0.057393  0.058552  0.059807  0.061163  0.062624  
    -7   0.068441  0.070146  0.058645  0.059951  0.061359  0.062874  0.064501  
    -8   0.070213  0.072111  0.059993  0.061452  0.063019  0.064699  0.066500  
    -9   0.072111  0.074210  0.061443  0.063061  0.064793  0.066647  0.068629  
    -10  0.059993  0.061443  0.052305  0.053417  0.054617  0.055910  0.057300  
    -11  0.061452  0.063061  0.053417  0.054655  0.055987  0.057418  0.058952  
    -12  0.063019  0.064793  0.054617  0.055987  0.057457  0.059031  0.060716  
    -13  0.064699  0.066647  0.055910  0.057418  0.059031  0.060756  0.062599  
    -14  0.066500  0.068629  0.057300  0.058952  0.060716  0.062599  0.064606  
    -
    -
    -

    We note here that the covariance is zero for the first rows and columns since all matrix elements in the design matrix were set to one @@ -4331,13 +4078,6 @@ C(\boldsymbol{X},\boldsymbol{\beta})=\frac{1}{n}\left\{(\boldsymbol{y}-\boldsymb

    Exercises week 35

    - -
    -

    next

    -

    Exercises week 36

    -
    - -
    diff --git a/doc/LectureNotes/_build/jupyter_execute/exercisesweek34.ipynb b/doc/LectureNotes/_build/jupyter_execute/exercisesweek34.ipynb index 53b974273..a70430253 100644 --- a/doc/LectureNotes/_build/jupyter_execute/exercisesweek34.ipynb +++ b/doc/LectureNotes/_build/jupyter_execute/exercisesweek34.ipynb @@ -2,7 +2,7 @@ "cells": [ { "cell_type": "markdown", - "id": "241c4a61", + "id": "72dc0997", "metadata": { "editable": true }, @@ -14,7 +14,7 @@ }, { "cell_type": "markdown", - "id": "a33815b9", + "id": "8c591125", "metadata": { "editable": true }, @@ -22,12 +22,12 @@ "# Exercises week 34\n", "**FYS-STK3155/4155**\n", "\n", - "Date: **August 21-25, 2023**" + "Date: **August 19-23, 2024**" ] }, { "cell_type": "markdown", - "id": "2990585c", + "id": "1ad21876", "metadata": { "editable": true }, @@ -39,7 +39,7 @@ }, { "cell_type": "markdown", - "id": "be056de0", + "id": "4eaa91e2", "metadata": { "editable": true }, @@ -108,7 +108,7 @@ }, { "cell_type": "markdown", - "id": "f0f4ffae", + "id": "360adb56", "metadata": { "editable": true }, @@ -122,7 +122,7 @@ { "cell_type": "code", "execution_count": 1, - "id": "93d6a2b2", + "id": "278aa34f", "metadata": { "collapsed": false, "editable": true @@ -135,7 +135,7 @@ "traceback": [ "\u001b[0;31m---------------------------------------------------------------------------\u001b[0m", "\u001b[0;31mNameError\u001b[0m Traceback (most recent call last)", - "Input \u001b[0;32mIn [1]\u001b[0m, in \u001b[0;36m\u001b[0;34m()\u001b[0m\n\u001b[0;32m----> 1\u001b[0m x \u001b[38;5;241m=\u001b[39m \u001b[43mnp\u001b[49m\u001b[38;5;241m.\u001b[39mrandom\u001b[38;5;241m.\u001b[39mrand(\u001b[38;5;241m100\u001b[39m,\u001b[38;5;241m1\u001b[39m)\n\u001b[1;32m 2\u001b[0m y \u001b[38;5;241m=\u001b[39m \u001b[38;5;241m2.0\u001b[39m\u001b[38;5;241m+\u001b[39m\u001b[38;5;241m5\u001b[39m\u001b[38;5;241m*\u001b[39mx\u001b[38;5;241m*\u001b[39mx\u001b[38;5;241m+\u001b[39m\u001b[38;5;241m0.1\u001b[39m\u001b[38;5;241m*\u001b[39mnp\u001b[38;5;241m.\u001b[39mrandom\u001b[38;5;241m.\u001b[39mrandn(\u001b[38;5;241m100\u001b[39m,\u001b[38;5;241m1\u001b[39m)\n", + "Cell \u001b[0;32mIn[1], line 1\u001b[0m\n\u001b[0;32m----> 1\u001b[0m x \u001b[38;5;241m=\u001b[39m \u001b[43mnp\u001b[49m\u001b[38;5;241m.\u001b[39mrandom\u001b[38;5;241m.\u001b[39mrand(\u001b[38;5;241m100\u001b[39m,\u001b[38;5;241m1\u001b[39m)\n\u001b[1;32m 2\u001b[0m y \u001b[38;5;241m=\u001b[39m \u001b[38;5;241m2.0\u001b[39m\u001b[38;5;241m+\u001b[39m\u001b[38;5;241m5\u001b[39m\u001b[38;5;241m*\u001b[39mx\u001b[38;5;241m*\u001b[39mx\u001b[38;5;241m+\u001b[39m\u001b[38;5;241m0.1\u001b[39m\u001b[38;5;241m*\u001b[39mnp\u001b[38;5;241m.\u001b[39mrandom\u001b[38;5;241m.\u001b[39mrandn(\u001b[38;5;241m100\u001b[39m,\u001b[38;5;241m1\u001b[39m)\n", "\u001b[0;31mNameError\u001b[0m: name 'np' is not defined" ] } @@ -147,7 +147,7 @@ }, { "cell_type": "markdown", - "id": "45392145", + "id": "1ff20e45", "metadata": { "editable": true }, @@ -161,7 +161,7 @@ }, { "cell_type": "markdown", - "id": "3eed315b", + "id": "e8809de1", "metadata": { "editable": true }, @@ -174,7 +174,7 @@ }, { "cell_type": "markdown", - "id": "26038071", + "id": "8c9e5277", "metadata": { "editable": true }, @@ -185,7 +185,7 @@ }, { "cell_type": "markdown", - "id": "4c750d55", + "id": "85a5881c", "metadata": { "editable": true }, @@ -197,7 +197,7 @@ }, { "cell_type": "markdown", - "id": "30b4731e", + "id": "4fb35d0d", "metadata": { "editable": true }, @@ -207,7 +207,7 @@ }, { "cell_type": "markdown", - "id": "49afe51d", + "id": "608f9780", "metadata": { "editable": true }, @@ -219,7 +219,7 @@ }, { "cell_type": "markdown", - "id": "81f16b80", + "id": "014bbc09", "metadata": { "editable": true }, @@ -230,7 +230,7 @@ }, { "cell_type": "markdown", - "id": "cb71cb1c", + "id": "f28863ad", "metadata": { "editable": true }, @@ -249,7 +249,7 @@ { "cell_type": "code", "execution_count": 2, - "id": "b8c919e5", + "id": "85f75a99", "metadata": { "collapsed": false, "editable": true @@ -265,7 +265,7 @@ }, { "cell_type": "markdown", - "id": "50629e14", + "id": "bee8d814", "metadata": { "editable": true }, @@ -275,7 +275,7 @@ }, { "cell_type": "markdown", - "id": "0578f08c", + "id": "7c94f8bd", "metadata": { "editable": true }, @@ -286,7 +286,7 @@ }, { "cell_type": "markdown", - "id": "125ec9a1", + "id": "c0e789dd", "metadata": { "editable": true }, @@ -298,7 +298,7 @@ }, { "cell_type": "markdown", - "id": "e5bb2036", + "id": "5ee1d70e", "metadata": { "editable": true }, @@ -319,7 +319,7 @@ "name": "python", "nbconvert_exporter": "python", "pygments_lexer": "ipython3", - "version": "3.9.10" + "version": "3.9.18" } }, "nbformat": 4, diff --git a/doc/LectureNotes/_build/jupyter_execute/exercisesweek34.py b/doc/LectureNotes/_build/jupyter_execute/exercisesweek34.py index cf8d3b297..088a52f36 100644 --- a/doc/LectureNotes/_build/jupyter_execute/exercisesweek34.py +++ b/doc/LectureNotes/_build/jupyter_execute/exercisesweek34.py @@ -8,7 +8,7 @@ # # Exercises week 34 # **FYS-STK3155/4155** # -# Date: **August 21-25, 2023** +# Date: **August 19-23, 2024** # ## Exercises # diff --git a/doc/LectureNotes/_build/jupyter_execute/exercisesweek35.ipynb b/doc/LectureNotes/_build/jupyter_execute/exercisesweek35.ipynb index 0b4eb4f75..18171513f 100644 --- a/doc/LectureNotes/_build/jupyter_execute/exercisesweek35.ipynb +++ b/doc/LectureNotes/_build/jupyter_execute/exercisesweek35.ipynb @@ -2,7 +2,7 @@ "cells": [ { "cell_type": "markdown", - "id": "053b96d5", + "id": "a15180da", "metadata": { "editable": true }, @@ -14,20 +14,20 @@ }, { "cell_type": "markdown", - "id": "a09cb811", + "id": "ac77b923", "metadata": { "editable": true }, "source": [ "# Exercises week 35\n", - "**August 28-September 1, 2023**\n", + "**August 26-30, 2024**\n", "\n", - "Date: **Deadline is Friday September 1 at midnight**" + "Date: **Deadline is Friday August 30 at midnight**" ] }, { "cell_type": "markdown", - "id": "8e83839e", + "id": "e8b90270", "metadata": { "editable": true }, @@ -49,7 +49,7 @@ }, { "cell_type": "markdown", - "id": "fe2b1c49", + "id": "2e2e8f1a", "metadata": { "editable": true }, @@ -61,7 +61,7 @@ }, { "cell_type": "markdown", - "id": "259f2ad1", + "id": "1cdc68da", "metadata": { "editable": true }, @@ -71,7 +71,7 @@ }, { "cell_type": "markdown", - "id": "5ac63202", + "id": "b87f9fdd", "metadata": { "editable": true }, @@ -83,7 +83,7 @@ }, { "cell_type": "markdown", - "id": "a52c6353", + "id": "6ab53932", "metadata": { "editable": true }, @@ -93,7 +93,7 @@ }, { "cell_type": "markdown", - "id": "910282dd", + "id": "1a7a8ec2", "metadata": { "editable": true }, @@ -105,7 +105,7 @@ }, { "cell_type": "markdown", - "id": "f3d0f2f5", + "id": "3bdb1514", "metadata": { "editable": true }, @@ -120,7 +120,7 @@ }, { "cell_type": "markdown", - "id": "5fe4bc49", + "id": "3e54eca9", "metadata": { "editable": true }, @@ -132,7 +132,7 @@ }, { "cell_type": "markdown", - "id": "55fee214", + "id": "3db49a1c", "metadata": { "editable": true }, @@ -142,7 +142,7 @@ }, { "cell_type": "markdown", - "id": "92b0b614", + "id": "5d4d3a0e", "metadata": { "editable": true }, @@ -154,7 +154,7 @@ }, { "cell_type": "markdown", - "id": "6b68973e", + "id": "90eecd1c", "metadata": { "editable": true }, @@ -164,7 +164,7 @@ }, { "cell_type": "markdown", - "id": "89e679e8", + "id": "7eb7605f", "metadata": { "editable": true }, @@ -176,7 +176,7 @@ }, { "cell_type": "markdown", - "id": "a35b6ab2", + "id": "b30dd90f", "metadata": { "editable": true }, @@ -186,7 +186,7 @@ }, { "cell_type": "markdown", - "id": "747d2724", + "id": "1167ec1f", "metadata": { "editable": true }, @@ -198,7 +198,7 @@ }, { "cell_type": "markdown", - "id": "911dc89a", + "id": "8f309e9e", "metadata": { "editable": true }, @@ -216,7 +216,7 @@ { "cell_type": "code", "execution_count": 1, - "id": "09971906", + "id": "2df1063f", "metadata": { "collapsed": false, "editable": true @@ -230,7 +230,7 @@ }, { "cell_type": "markdown", - "id": "de82ebe8", + "id": "0cb75ec5", "metadata": { "editable": true }, @@ -244,7 +244,7 @@ }, { "cell_type": "markdown", - "id": "21b2c91f", + "id": "f0c36bdb", "metadata": { "editable": true }, @@ -257,7 +257,7 @@ }, { "cell_type": "markdown", - "id": "3b542aa1", + "id": "8c3ce778", "metadata": { "editable": true }, @@ -268,7 +268,7 @@ }, { "cell_type": "markdown", - "id": "5393a93f", + "id": "f861d243", "metadata": { "editable": true }, @@ -280,7 +280,7 @@ }, { "cell_type": "markdown", - "id": "df1b8e23", + "id": "51500e4b", "metadata": { "editable": true }, @@ -290,7 +290,7 @@ }, { "cell_type": "markdown", - "id": "30ad9bb6", + "id": "fda9dadd", "metadata": { "editable": true }, @@ -302,7 +302,7 @@ }, { "cell_type": "markdown", - "id": "0e2c0d15", + "id": "6b691499", "metadata": { "editable": true }, @@ -313,7 +313,7 @@ }, { "cell_type": "markdown", - "id": "80eab896", + "id": "b6f10ab9", "metadata": { "editable": true }, @@ -333,7 +333,7 @@ { "cell_type": "code", "execution_count": 2, - "id": "887378fa", + "id": "285159ae", "metadata": { "collapsed": false, "editable": true @@ -349,7 +349,7 @@ }, { "cell_type": "markdown", - "id": "a059a330", + "id": "c2840fc9", "metadata": { "editable": true }, @@ -359,7 +359,7 @@ }, { "cell_type": "markdown", - "id": "e2614fe9", + "id": "9dbda275", "metadata": { "editable": true }, @@ -370,7 +370,7 @@ }, { "cell_type": "markdown", - "id": "8522c8f4", + "id": "824dba6f", "metadata": { "editable": true }, @@ -382,7 +382,7 @@ }, { "cell_type": "markdown", - "id": "c4e99901", + "id": "a3f059cf", "metadata": { "editable": true }, @@ -403,7 +403,7 @@ "name": "python", "nbconvert_exporter": "python", "pygments_lexer": "ipython3", - "version": "3.9.10" + "version": "3.9.18" } }, "nbformat": 4, diff --git a/doc/LectureNotes/_build/jupyter_execute/exercisesweek35.py b/doc/LectureNotes/_build/jupyter_execute/exercisesweek35.py index 68069029a..315da02e7 100644 --- a/doc/LectureNotes/_build/jupyter_execute/exercisesweek35.py +++ b/doc/LectureNotes/_build/jupyter_execute/exercisesweek35.py @@ -6,9 +6,9 @@ # # # Exercises week 35 -# **August 28-September 1, 2023** +# **August 26-30, 2024** # -# Date: **Deadline is Friday September 1 at midnight** +# Date: **Deadline is Friday August 30 at midnight** # ## Exercise 1: Analytical exercises # diff --git a/doc/LectureNotes/_build/jupyter_execute/week34.ipynb b/doc/LectureNotes/_build/jupyter_execute/week34.ipynb index 26cff2c3b..2dde5869a 100644 --- a/doc/LectureNotes/_build/jupyter_execute/week34.ipynb +++ b/doc/LectureNotes/_build/jupyter_execute/week34.ipynb @@ -2,7 +2,7 @@ "cells": [ { "cell_type": "markdown", - "id": "390f1bd7", + "id": "e68d0f91", "metadata": { "editable": true }, @@ -14,7 +14,7 @@ }, { "cell_type": "markdown", - "id": "2c8cea05", + "id": "919216dd", "metadata": { "editable": true }, @@ -22,12 +22,12 @@ "# Week 34: Introduction to the course, Logistics and Practicalities\n", "**Morten Hjorth-Jensen**, Department of Physics and Center for Computing in Science Education, University of Oslo, Norway and Department of Physics and Astronomy and Facility for Rare Isotope Beams, Michigan State University, USA\n", "\n", - "Date: **Week 34, August 21-25, 2023**" + "Date: **Week 34, August 19-23, 2024**" ] }, { "cell_type": "markdown", - "id": "725240be", + "id": "d990119b", "metadata": { "editable": true }, @@ -44,39 +44,41 @@ "\n", " * Wednesdays 815am-12pm and 1215pm-4pm.\n", "\n", - "4. On Thursdays we have a regular lecture. These lectures start at 1215pm and end at 2pm and serve the aims of giving an overview over various topics. These lectures will also be recorded.\n", + "4. On Mondays we have a regular lecture which will be organized as a mix of active learning sessions and regular lectures. These lectures/active learning sessions start at 1015am and end at 12pm and serve the aims of giving an overview over various topics as well as solving specific problems. These lectures will also be recorded.\n", + "\n", + " * [Link to recording of lecture TBA](https://youtu.be/)\n", "\n", "The labs are also available till 6pm Tuesdays and Wednesdays. Videos and learning material with reading suggestions will be made available before each week starts." ] }, { "cell_type": "markdown", - "id": "c18f9a3c", + "id": "12fb6433", "metadata": { "editable": true }, "source": [ "## Schedule first week\n", "\n", - " * August 22: Presentation of the course, aims and content. Introduction to software and repetition of Python Programming, linear algebra and basic elements of statistics. Please select group.\n", + " * August 19: Lecture: Presentation of course, Linear regression, examples and theory \n", "\n", - " * August 23: Presentation of the course, aims and content. Introduction to software and repetition of Python Programming, linear algebra and basic elements of statistics. Please select group.\n", + " * August 20: Introduction to software and repetition of Python Programming, linear algebra and basic elements of statistics. Please select group.\n", "\n", - " * August 24: Lecture: Linear regression, examples and theory" + " * August 23: Introduction to software and repetition of Python Programming, linear algebra and basic elements of statistics. Please select group." ] }, { "cell_type": "markdown", - "id": "769cbfc6", + "id": "fc7733d1", "metadata": { "editable": true }, "source": [ "## Lectures and ComputerLab\n", "\n", - " * The sessions on Tuesdays and Wednesdays last four hours and will include partly lectures in a flipped mode (promoting active learning) and work on exercices and projects.\n", + " * Mondays: regular lectures/active learning sessions (10.15am-12pm) \n", "\n", - " * Thursdays: regular lectures (12.15pm-2pm) \n", + " * The sessions on Tuesdays and Wednesdays last four hours and will include partly lectures and discussions in the beginning.\n", "\n", " * Weekly reading assignments and videos needed to solve projects and exercises.\n", "\n", @@ -91,21 +93,21 @@ }, { "cell_type": "markdown", - "id": "5040ec52", + "id": "7b62d5a2", "metadata": { "editable": true }, "source": [ "## Communication channels\n", "\n", - "* Chat and communications via \n", + "* Communications (email and more) via \n", "\n", - "* **Discord** channel will be added asap" + "* **Discord** channel at " ] }, { "cell_type": "markdown", - "id": "867e5431", + "id": "6b3a4a81", "metadata": { "editable": true }, @@ -127,7 +129,7 @@ }, { "cell_type": "markdown", - "id": "61ff07a3", + "id": "afc67709", "metadata": { "editable": true }, @@ -150,32 +152,32 @@ "\n", "* Karl Henrik Fredly, k.h.fredly@fys.uio.no\n", "\n", - "* Adam Jakobsen, adam.jakobsen@fys.uio.no\n", + "* Sigurd k. Huse, s.k.huse@fys.uio.no\n", "\n", - "* Daniel Haas Beccatini Lima, d.h.b.lima@fys.uio.no" + "* Odin Johansen, odin.johansen@fys.uio.no" ] }, { "cell_type": "markdown", - "id": "afa7d17c", + "id": "bbd60b9c", "metadata": { "editable": true }, "source": [ "## Deadlines for projects (tentative)\n", "\n", - "1. Project 1: October 9 (available September 4) graded with feedback)\n", + "1. Project 1: October 7 (available September 2) graded with feedback)\n", "\n", - "2. Project 2: November 6 (available October 6, graded with feedback)\n", + "2. Project 2: November 4 (available October 8, graded with feedback)\n", "\n", - "3. Project 3: December 11 (available November 10, graded with feedback)\n", + "3. Project 3: December 9 (available November 5, graded with feedback)\n", "\n", - "Extra Credit (not mandatory), weekly exercise assignments, 10 in total (due Friday same week), 10% additional score. The extra credit assignments are due each Friday and can be uploaed to **Canvas** in your preferred format (although we prefer jupyter-notebooks). First assignment is for week 35. Each weekly exercise set counts 1%." + "Extra Credit (not mandatory), weekly exercise assignments, 10 in total (due Friday same week), 10% additional score. The extra credit assignments are due each Sunday and can be uploaed to **Canvas** in your preferred format (although we prefer jupyter-notebooks). First assignment is for week 35. Each weekly exercise set counts 1%." ] }, { "cell_type": "markdown", - "id": "37a46b20", + "id": "5c4e0b8c", "metadata": { "editable": true }, @@ -203,7 +205,7 @@ }, { "cell_type": "markdown", - "id": "40b50d78", + "id": "cabba75a", "metadata": { "editable": true }, @@ -211,20 +213,41 @@ "## Reading material\n", "\n", "The lecture notes are collected as a jupyter-book at .\n", + "The lecture notes can also be retrieved as a standard PDF file at .\n", "\n", - "In addition to the lecture notes, we recommend the books of Bishop, Hastie et al, Murphy and Goodfellow et al. We will follow these texts closely and the weekly reading assignments refer to these texts. The text by Hastie et al is also widely used in the Machine Learning community. Finally, we also recommend the hands-on text by Geron, see next slide for links." + "In addition to the lecture notes, we recommend the books of Rasckha et\n", + "al and Goodfellow et al. We will follow these texts closely and the\n", + "weekly reading assignments refer to these texts. The text by Hastie et\n", + "al is also widely used in the Machine Learning community. See next slide for link to textbooks." ] }, { "cell_type": "markdown", - "id": "1ac7f5fa", + "id": "2240bbaf", "metadata": { "editable": true }, "source": [ - "## Textbooks\n", + "## Main textbooks\n", "\n", - "* [Goodfellow, Bengio, and Courville (GBC), Deep Learning](https://www.deeplearningbook.org/)\n", + "* Goodfellow, Bengio, and Courville (GBC), Deep Learning \n", + "\n", + "* Sebastian Raschka, Yuxi Lie, and Vahid Mirjalili (RLM), Machine Learning with PyTorch and Scikit-Learn at , see also \n", + "\n", + "The weekly reading suggestions are all from these two texts. The text by GBC can be accessed chapter by chapter from the abovementioned URL.\n", + "Each chapter of RLM gives access to the pertinent notebooks. These notebooks are highly recommended." + ] + }, + { + "cell_type": "markdown", + "id": "e11266d3", + "metadata": { + "editable": true + }, + "source": [ + "## Other popular texts\n", + "\n", + "**Other texts.**\n", "\n", "* Christopher M. Bishop (CB), Pattern Recognition and Machine Learning\n", "\n", @@ -232,24 +255,28 @@ "\n", "* [Aurelien Geron (AG), Hands‑On Machine Learning with Scikit‑Learn and TensorFlow, O'Reilly](https://www.oreilly.com/library/view/hands-on-machine-learning/9781492032632/). This text is very useful since it contains many code examples and hands-on applications of all algorithms discussed in this course.\n", "\n", - "* [Kevin Murphy (KM), Probabilistic Machine Learning, an Introduction](https://probml.github.io/pml-book/book1.html)" + "* [Kevin Murphy (KM), Probabilistic Machine Learning, an Introduction](https://probml.github.io/pml-book/book1.html)\n", + "\n", + "* David Foster (DF), Generative Deep Learning, \n", + "\n", + "* Babcock and Gavras (BG), Generative AI with Python and TensorFlow, " ] }, { "cell_type": "markdown", - "id": "c74dc137", + "id": "2f254181", "metadata": { "editable": true }, "source": [ "## Reading suggestions week 34\n", "\n", - "This week: Refresh linear algebra, GBC chapters 1 and 2. HTF chapters 2 and 3. Install scikit-learn. See lecture notes for week 34 at (these notes)." + "This week: Refresh linear algebra, GBC chapter 2. Install scikit-learn. See lecture notes for week 34 at (these notes)." ] }, { "cell_type": "markdown", - "id": "6af0d013", + "id": "a482f843", "metadata": { "editable": true }, @@ -269,7 +296,7 @@ }, { "cell_type": "markdown", - "id": "628fb74c", + "id": "1bfd35e8", "metadata": { "editable": true }, @@ -287,7 +314,7 @@ }, { "cell_type": "markdown", - "id": "bcfe0b24", + "id": "d28f3b65", "metadata": { "editable": true }, @@ -312,7 +339,7 @@ }, { "cell_type": "markdown", - "id": "f153abef", + "id": "1dd7eba4", "metadata": { "editable": true }, @@ -329,7 +356,17 @@ "\n", " * Support vector machines (only survey);\n", "\n", - " * Unsupervised learning and dimensionality reduction, from PCA to clustering; \n", + " * Unsupervised learning and dimensionality reduction, from PCA to clustering;" + ] + }, + { + "cell_type": "markdown", + "id": "f65d481e", + "metadata": { + "editable": true + }, + "source": [ + "## Deep learning methods\n", "\n", "* Deep learning \n", "\n", @@ -341,14 +378,14 @@ "\n", " * Autoencoders\n", "\n", - " * Generative methods with an emphasis on Boltzmann Machines, Variational Autoencoders and Generalized Adversarial Networks;\n", + " * Generative methods with an emphasis on Boltzmann Machines, Variational Autoencoders and Generalized Adversarial Networks(covered by FYS5429);\n", "\n", "Hands-on demonstrations, exercises and projects aim at deepening your understanding of these topics." ] }, { "cell_type": "markdown", - "id": "a6b0c4b8", + "id": "860d45f1", "metadata": { "editable": true }, @@ -364,7 +401,7 @@ }, { "cell_type": "markdown", - "id": "48eb8817", + "id": "8643a8e4", "metadata": { "editable": true }, @@ -386,7 +423,7 @@ }, { "cell_type": "markdown", - "id": "e8889321", + "id": "883a32ab", "metadata": { "editable": true }, @@ -404,27 +441,13 @@ }, { "cell_type": "markdown", - "id": "4ad1f253", + "id": "c36dca74", "metadata": { "editable": true }, "source": [ "## Learning outcomes\n", "\n", - "This course aims at giving you insights and knowledge about many of\n", - "the central algorithms used in Data Analysis and Machine Learning.\n", - "The course is project based and through various numerical projects,\n", - "normally three, you will be exposed to fundamental research problems\n", - "in these fields, with the aim to reproduce state of the art scientific\n", - "results. Both supervised and unsupervised methods will be covered. The\n", - "emphasis is on a frequentist approach, although we will try to link it\n", - "with a Bayesian approach as well. You will learn to develop and\n", - "structure large codes for studying different cases where Machine\n", - "Learning is applied to, get acquainted with computing facilities and\n", - "learn to handle large scientific projects. A good scientific and\n", - "ethical conduct is emphasized throughout the course. More\n", - "specifically, after this course you will\n", - "\n", "* Learn about basic data analysis, statistical analysis, Bayesian statistics, Monte Carlo sampling, data optimization and machine learning;\n", "\n", "* Be capable of extending the acquired knowledge to other systems and cases;\n", @@ -448,143 +471,7 @@ }, { "cell_type": "markdown", - "id": "ed3eddab", - "metadata": { - "editable": true - }, - "source": [ - "## Introduction\n", - "\n", - "Our emphasis throughout this series of lectures \n", - "is on understanding the mathematical aspects of\n", - "different algorithms used in the fields of data analysis and machine learning. \n", - "\n", - "However, where possible we will emphasize the\n", - "importance of using available software. We start thus with a hands-on\n", - "and top-down approach to machine learning. The aim is thus to start with\n", - "relevant data or data we have produced \n", - "and use these to introduce statistical data analysis\n", - "concepts and machine learning algorithms before we delve into the\n", - "algorithms themselves. The examples we will use in the beginning, start with simple\n", - "polynomials with random noise added. We will use the Python\n", - "software package [Scikit-Learn](http://scikit-learn.org/stable/) and\n", - "introduce various machine learning algorithms to make fits of\n", - "the data and predictions. We move thereafter to more interesting\n", - "cases such as data from say experiments (below we will look at experimental nuclear binding energies as an example).\n", - "These are examples where we can easily set up the data and\n", - "then use machine learning algorithms included in for example\n", - "**Scikit-Learn**. \n", - "\n", - "These examples will serve us the purpose of getting\n", - "started. Furthermore, they allow us to catch more than two birds with\n", - "a stone. They will allow us to bring in some programming specific\n", - "topics and tools as well as showing the power of various Python \n", - "libraries for machine learning and statistical data analysis. \n", - "\n", - "Although we have projects where you write your own codes, we will also focus on two\n", - "specific Python packages for Machine Learning, Scikit-Learn and\n", - "Tensorflow with Keras (see below for links etc). Moreover, the examples we\n", - "introduce will serve as inputs to many of our discussions later, as\n", - "well as allowing you to set up models and produce your own data and\n", - "get started with programming." - ] - }, - { - "cell_type": "markdown", - "id": "cd6f4f41", - "metadata": { - "editable": true - }, - "source": [ - "## AI/ML and some statements you may have heard (and what do they mean?)\n", - "\n", - "1. Fei-Fei Li on ImageNet: **map out the entire world of objects** ([The data that transformed AI research](https://cacm.acm.org/news/219702-the-data-that-transformed-ai-research-and-possibly-the-world/fulltext))\n", - "\n", - "2. Russell and Norvig in their popular textbook: **relevant to any intellectual task; it is truly a universal field** ([Artificial Intelligence, A modern approach](http://aima.cs.berkeley.edu/))\n", - "\n", - "3. Woody Bledsoe puts it more bluntly: **in the long run, AI is the only science** (quoted in Pamilla McCorduck, [Machines who think](https://www.pamelamccorduck.com/machines-who-think))\n", - "\n", - "If you wish to have a critical read on AI/ML from a societal point of view, see [Kate Crawford's recent text Atlas of AI](https://www.katecrawford.net/)\n", - "\n", - "**Here: with AI/ML we intend a collection of machine learning methods with an emphasis on statistical learning and data analysis**" - ] - }, - { - "cell_type": "markdown", - "id": "9bc6760a", - "metadata": { - "editable": true - }, - "source": [ - "## What is Machine Learning?\n", - "\n", - "Statistics, data science and machine learning form important fields of\n", - "research in modern science. They describe how to learn and make\n", - "predictions from data, as well as allowing us to extract important\n", - "correlations about physical process and the underlying laws of motion\n", - "in large data sets. The latter, big data sets, appear frequently in\n", - "essentially all disciplines, from the traditional Science, Technology,\n", - "Mathematics and Engineering fields to Life Science, Law, education\n", - "research, the Humanities and the Social Sciences. \n", - "\n", - "It has become more\n", - "and more common to see research projects on big data in for example\n", - "the Social Sciences where extracting patterns from complicated survey\n", - "data is one of many research directions. Having a solid grasp of data\n", - "analysis and machine learning is thus becoming central to scientific\n", - "computing in many fields, and competences and skills within the fields\n", - "of machine learning and scientific computing are nowadays strongly\n", - "requested by many potential employers. The latter cannot be\n", - "overstated, familiarity with machine learning has almost become a\n", - "prerequisite for many of the most exciting employment opportunities,\n", - "whether they are in bioinformatics, life science, physics or finance,\n", - "in the private or the public sector. This author has had several\n", - "students or met students who have been hired recently based on their\n", - "skills and competences in scientific computing and data science, often\n", - "with marginal knowledge of machine learning.\n", - "\n", - "Machine learning is a subfield of computer science, and is closely\n", - "related to computational statistics. It evolved from the study of\n", - "pattern recognition in artificial intelligence (AI) research, and has\n", - "made contributions to AI tasks like computer vision, natural language\n", - "processing and speech recognition. Many of the methods we will study are also \n", - "strongly rooted in basic mathematics and physics research. \n", - "\n", - "Ideally, machine learning represents the science of giving computers\n", - "the ability to learn without being explicitly programmed. The idea is\n", - "that there exist generic algorithms which can be used to find patterns\n", - "in a broad class of data sets without having to write code\n", - "specifically for each problem. The algorithm will build its own logic\n", - "based on the data. You should however always keep in mind that\n", - "machines and algorithms are to a large extent developed by humans. The\n", - "insights and knowledge we have about a specific system, play a central\n", - "role when we develop a specific machine learning algorithm. \n", - "\n", - "Machine learning is an extremely rich field, in spite of its young\n", - "age. The increases we have seen during the last three decades in\n", - "computational capabilities have been followed by developments of\n", - "methods and techniques for analyzing and handling large date sets,\n", - "relying heavily on statistics, computer science and mathematics. The\n", - "field is rather new and developing rapidly. Popular software packages\n", - "written in Python for machine learning like\n", - "[Scikit-learn](http://scikit-learn.org/stable/),\n", - "[Tensorflow](https://www.tensorflow.org/),\n", - "[PyTorch](http://pytorch.org/) and [Keras](https://keras.io/), all\n", - "freely available at their respective GitHub sites, encompass\n", - "communities of developers in the thousands or more. And the number of\n", - "code developers and contributors keeps increasing. Not all the\n", - "algorithms and methods can be given a rigorous mathematical\n", - "justification, opening up thereby large rooms for experimenting and\n", - "trial and error and thereby exciting new developments. However, a\n", - "solid command of linear algebra, multivariate theory, probability\n", - "theory, statistical data analysis, understanding errors and Monte\n", - "Carlo methods are central elements in a proper understanding of many\n", - "of algorithms and methods we will discuss." - ] - }, - { - "cell_type": "markdown", - "id": "17c6257a", + "id": "3331f004", "metadata": { "editable": true }, @@ -613,7 +500,7 @@ }, { "cell_type": "markdown", - "id": "9f4e80cf", + "id": "9805129a", "metadata": { "editable": true }, @@ -631,7 +518,7 @@ }, { "cell_type": "markdown", - "id": "828f3ad9", + "id": "b6ce1fec", "metadata": { "editable": true }, @@ -643,7 +530,7 @@ }, { "cell_type": "markdown", - "id": "8b12df05", + "id": "c3f855e6", "metadata": { "editable": true }, @@ -678,7 +565,7 @@ }, { "cell_type": "markdown", - "id": "6656791e", + "id": "db7df58f", "metadata": { "editable": true }, @@ -708,7 +595,7 @@ }, { "cell_type": "markdown", - "id": "85f146c9", + "id": "eae43d45", "metadata": { "editable": true }, @@ -739,7 +626,7 @@ }, { "cell_type": "markdown", - "id": "51f73840", + "id": "a14136b8", "metadata": { "editable": true }, @@ -778,7 +665,7 @@ }, { "cell_type": "markdown", - "id": "404f8680", + "id": "43ad2d3a", "metadata": { "editable": true }, @@ -811,7 +698,7 @@ }, { "cell_type": "markdown", - "id": "1b74192a", + "id": "260fc4f1", "metadata": { "editable": true }, @@ -841,12 +728,14 @@ "\n", "* [Keras](https://keras.io/) is a high-level neural networks API, written in Python and capable of running on top of TensorFlow, CNTK, or Theano\n", "\n", - "* And many more such as [pytorch](https://pytorch.org/), [Theano](https://pypi.org/project/Theano/) etc" + "* [Pytorch](https://pytorch.org/), highly recommened\n", + "\n", + "* [Theano](https://pypi.org/project/Theano/) and many other" ] }, { "cell_type": "markdown", - "id": "32b6b09c", + "id": "d79f5c48", "metadata": { "editable": true }, @@ -870,7 +759,7 @@ }, { "cell_type": "markdown", - "id": "0c8344b1", + "id": "14668766", "metadata": { "editable": true }, @@ -897,7 +786,7 @@ }, { "cell_type": "markdown", - "id": "40a41b04", + "id": "158a0a2b", "metadata": { "editable": true }, @@ -907,7 +796,7 @@ }, { "cell_type": "markdown", - "id": "367b0b81", + "id": "8ff2bfbf", "metadata": { "editable": true }, @@ -919,7 +808,7 @@ }, { "cell_type": "markdown", - "id": "e16a079a", + "id": "336a64f4", "metadata": { "editable": true }, @@ -940,7 +829,7 @@ }, { "cell_type": "markdown", - "id": "244cc56a", + "id": "53d76bcf", "metadata": { "editable": true }, @@ -952,7 +841,7 @@ { "cell_type": "code", "execution_count": 1, - "id": "1d8845bb", + "id": "c8cbf8e5", "metadata": { "collapsed": false, "editable": true @@ -964,7 +853,7 @@ }, { "cell_type": "markdown", - "id": "a339aed7", + "id": "2544ec17", "metadata": { "editable": true }, @@ -975,7 +864,7 @@ { "cell_type": "code", "execution_count": 2, - "id": "ce4b3b4e", + "id": "e6fed93a", "metadata": { "collapsed": false, "editable": true @@ -985,8 +874,8 @@ "name": "stdout", "output_type": "stream", "text": [ - "[ 1.99876055 1.26944417 1.08159052 -0.19114964 -0.60407268 0.65062476\n", - " 1.21910072 1.34814162 -0.23692158 0.52823177]\n" + "[-0.44642273 -0.20366091 -0.49369173 0.65652778 0.49580918 -0.93137583\n", + " 1.23177548 1.6608592 -0.69492254 0.11655508]\n" ] } ], @@ -998,7 +887,7 @@ }, { "cell_type": "markdown", - "id": "307170c5", + "id": "671ec8e4", "metadata": { "editable": true }, @@ -1010,7 +899,7 @@ { "cell_type": "code", "execution_count": 3, - "id": "ea4fd74f", + "id": "03351553", "metadata": { "collapsed": false, "editable": true @@ -1032,7 +921,7 @@ }, { "cell_type": "markdown", - "id": "6428f55d", + "id": "ab7b4a4f", "metadata": { "editable": true }, @@ -1044,7 +933,7 @@ { "cell_type": "code", "execution_count": 4, - "id": "84e4a8fc", + "id": "7d547fee", "metadata": { "collapsed": false, "editable": true @@ -1066,7 +955,7 @@ }, { "cell_type": "markdown", - "id": "39bd657f", + "id": "fa3d6630", "metadata": { "editable": true }, @@ -1083,7 +972,7 @@ { "cell_type": "code", "execution_count": 5, - "id": "e5a5fe48", + "id": "a1410010", "metadata": { "collapsed": false, "editable": true @@ -1108,7 +997,7 @@ }, { "cell_type": "markdown", - "id": "d74eb874", + "id": "1fcdba92", "metadata": { "editable": true }, @@ -1120,7 +1009,7 @@ { "cell_type": "code", "execution_count": 6, - "id": "1d657e01", + "id": "b2baed9c", "metadata": { "collapsed": false, "editable": true @@ -1142,7 +1031,7 @@ }, { "cell_type": "markdown", - "id": "7f82621e", + "id": "341fe975", "metadata": { "editable": true }, @@ -1153,7 +1042,7 @@ { "cell_type": "code", "execution_count": 7, - "id": "c4a5e02b", + "id": "4c81d6d8", "metadata": { "collapsed": false, "editable": true @@ -1175,7 +1064,7 @@ }, { "cell_type": "markdown", - "id": "3af71bb0", + "id": "b606be11", "metadata": { "editable": true }, @@ -1186,7 +1075,7 @@ { "cell_type": "code", "execution_count": 8, - "id": "5cf0baf0", + "id": "dc5f484b", "metadata": { "collapsed": false, "editable": true @@ -1208,7 +1097,7 @@ }, { "cell_type": "markdown", - "id": "a70a4db0", + "id": "2ee4fd88", "metadata": { "editable": true }, @@ -1223,7 +1112,7 @@ { "cell_type": "code", "execution_count": 9, - "id": "262e8f46", + "id": "f54969e9", "metadata": { "collapsed": false, "editable": true @@ -1247,7 +1136,7 @@ }, { "cell_type": "markdown", - "id": "0f43d9cd", + "id": "3ffdc5bb", "metadata": { "editable": true }, @@ -1258,7 +1147,7 @@ { "cell_type": "code", "execution_count": 10, - "id": "f12d591b", + "id": "c517dc95", "metadata": { "collapsed": false, "editable": true @@ -1281,7 +1170,7 @@ }, { "cell_type": "markdown", - "id": "7c1cc7ed", + "id": "1aced303", "metadata": { "editable": true }, @@ -1292,7 +1181,7 @@ { "cell_type": "code", "execution_count": 11, - "id": "1f365f00", + "id": "32efbfb2", "metadata": { "collapsed": false, "editable": true @@ -1315,7 +1204,7 @@ }, { "cell_type": "markdown", - "id": "d5cf7244", + "id": "a95e02fd", "metadata": { "editable": true }, @@ -1326,7 +1215,7 @@ { "cell_type": "code", "execution_count": 12, - "id": "907260e4", + "id": "fcebfe97", "metadata": { "collapsed": false, "editable": true @@ -1359,7 +1248,7 @@ }, { "cell_type": "markdown", - "id": "375e0579", + "id": "5d767b5d", "metadata": { "editable": true }, @@ -1370,7 +1259,7 @@ { "cell_type": "code", "execution_count": 13, - "id": "79e19787", + "id": "8c8edcaf", "metadata": { "collapsed": false, "editable": true @@ -1403,7 +1292,7 @@ }, { "cell_type": "markdown", - "id": "be6c16b2", + "id": "1365ca9a", "metadata": { "editable": true }, @@ -1414,7 +1303,7 @@ { "cell_type": "code", "execution_count": 14, - "id": "901ecfe2", + "id": "85c9a904", "metadata": { "collapsed": false, "editable": true @@ -1424,26 +1313,26 @@ "name": "stdout", "output_type": "stream", "text": [ - "[[0.07178725 0.08695635 0.89462507 0.75563845 0.30666456 0.0295741\n", - " 0.79835897 0.68599651 0.09215268 0.92098926]\n", - " [0.66013062 0.05466359 0.48935121 0.8554451 0.40293251 0.1690242\n", - " 0.62412322 0.13571683 0.5735888 0.22524684]\n", - " [0.77325382 0.25018275 0.77615813 0.91438463 0.79009118 0.67199316\n", - " 0.35858674 0.54205622 0.95558887 0.35799174]\n", - " [0.42109456 0.19802685 0.8478361 0.20265997 0.78724182 0.91581662\n", - " 0.92419995 0.65805069 0.64192269 0.23499198]\n", - " [0.18302441 0.97198474 0.70796162 0.06124676 0.14967691 0.83091912\n", - " 0.9697031 0.96649164 0.48613114 0.79595791]\n", - " [0.15400455 0.92643252 0.75309058 0.24605947 0.50661281 0.47991139\n", - " 0.54220589 0.10645534 0.55295871 0.71213744]\n", - " [0.85824275 0.00915265 0.88395664 0.86901486 0.00286269 0.47340594\n", - " 0.5703663 0.13201296 0.99246148 0.75848064]\n", - " [0.94578579 0.81175543 0.74233133 0.80589357 0.64101039 0.02053512\n", - " 0.98904619 0.19457423 0.98598055 0.19429581]\n", - " [0.27377363 0.89454132 0.31780875 0.11925465 0.02636112 0.23754723\n", - " 0.20580025 0.53632918 0.39822715 0.69355844]\n", - " [0.15449587 0.45133278 0.03230546 0.07962234 0.17757752 0.07225884\n", - " 0.99267755 0.87211615 0.36537059 0.28596284]]\n" + "[[0.49486583 0.8087144 0.91855299 0.6448861 0.74849204 0.91699467\n", + " 0.94466321 0.75162857 0.32220836 0.25549693]\n", + " [0.3825029 0.15654521 0.93482217 0.24809277 0.25772788 0.96856697\n", + " 0.64064106 0.47128426 0.66855692 0.51821339]\n", + " [0.83509815 0.36348681 0.23395094 0.99418976 0.69827131 0.7659922\n", + " 0.81307569 0.20752401 0.99377492 0.89976047]\n", + " [0.34498001 0.33880129 0.43233857 0.35329636 0.62606121 0.85466682\n", + " 0.76097737 0.84421309 0.08145936 0.64110154]\n", + " [0.96019951 0.96087803 0.38220141 0.46609435 0.56733919 0.46895658\n", + " 0.22679825 0.96852109 0.00704347 0.63565881]\n", + " [0.21074205 0.97861433 0.38382691 0.49873827 0.87196574 0.08434487\n", + " 0.3546689 0.11053892 0.02865084 0.87134207]\n", + " [0.32078531 0.07563916 0.97346886 0.79529368 0.20430356 0.45047066\n", + " 0.83446313 0.17964265 0.37054827 0.95115279]\n", + " [0.59922967 0.00145601 0.93873645 0.02592329 0.68250601 0.48699577\n", + " 0.50083166 0.20525241 0.03880581 0.34975242]\n", + " [0.17016741 0.09648484 0.47781605 0.58621153 0.32019835 0.91700604\n", + " 0.93363269 0.83167477 0.34254681 0.08319649]\n", + " [0.38845241 0.09706624 0.34606431 0.93082209 0.5105983 0.97939372\n", + " 0.8773885 0.12911793 0.54129367 0.58662003]]\n" ] } ], @@ -1457,7 +1346,7 @@ }, { "cell_type": "markdown", - "id": "be629f7b", + "id": "15700c5c", "metadata": { "editable": true }, @@ -1469,7 +1358,7 @@ }, { "cell_type": "markdown", - "id": "980cf441", + "id": "d5d413f6", "metadata": { "editable": true }, @@ -1484,7 +1373,7 @@ }, { "cell_type": "markdown", - "id": "d2ffe1f6", + "id": "81f680dd", "metadata": { "editable": true }, @@ -1494,7 +1383,7 @@ }, { "cell_type": "markdown", - "id": "4f4efdd4", + "id": "17c5a1bf", "metadata": { "editable": true }, @@ -1506,7 +1395,7 @@ }, { "cell_type": "markdown", - "id": "ee572849", + "id": "55a9b83d", "metadata": { "editable": true }, @@ -1517,7 +1406,7 @@ }, { "cell_type": "markdown", - "id": "df0a5acc", + "id": "0929cae0", "metadata": { "editable": true }, @@ -1532,7 +1421,7 @@ }, { "cell_type": "markdown", - "id": "7bc72a77", + "id": "f3181ff4", "metadata": { "editable": true }, @@ -1547,7 +1436,7 @@ { "cell_type": "code", "execution_count": 15, - "id": "4c493f06", + "id": "6c2c0ee5", "metadata": { "collapsed": false, "editable": true @@ -1557,13 +1446,13 @@ "name": "stdout", "output_type": "stream", "text": [ - "-0.02192091870116783\n", - "3.774553354452195\n", - "-0.536915581616642\n", - "[[ 0.97075378 2.86906683 4.23997187]\n", - " [ 2.86906683 9.35109296 12.76954723]\n", - " [ 4.23997187 12.76954723 33.47704686]]\n", - "[39.63504283 0.07780377 4.08604699]\n" + "-0.0963911829588757\n", + "3.757019617707678\n", + "0.10552836390308734\n", + "[[ 1.11105306 3.48263731 4.1473833 ]\n", + " [ 3.48263731 11.83909743 12.7296587 ]\n", + " [ 4.1473833 12.7296587 29.56151035]]\n", + "[36.9908934 0.07119676 5.44957069]\n" ] } ], @@ -1588,7 +1477,7 @@ { "cell_type": "code", "execution_count": 16, - "id": "20bda99f", + "id": "cbe79e57", "metadata": { "collapsed": false, "editable": true @@ -1610,14 +1499,14 @@ }, { "data": { - "image/png": "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\n", + "image/png": "iVBORw0KGgoAAAANSUhEUgAAAjgAAAGdCAYAAAAfTAk2AAAAOXRFWHRTb2Z0d2FyZQBNYXRwbG90bGliIHZlcnNpb24zLjguMCwgaHR0cHM6Ly9tYXRwbG90bGliLm9yZy81sbWrAAAACXBIWXMAAA9hAAAPYQGoP6dpAACUoUlEQVR4nO29eXhU5d3//z4zmSXrZN8gGyGsQcUoECxuARS3LipaW9SnSGutRqA+rXT5uXy/LdWnNRiXqn1Q2mrFtojabykaIqDIokBAQZaB7CQh+zrJrOf3x5n7ZCb7MstZPq/rmovJzJnJPcyd+37fn5XjeZ4HQRAEQRCEgtAEewAEQRAEQRC+hgQOQRAEQRCKgwQOQRAEQRCKgwQOQRAEQRCKgwQOQRAEQRCKgwQOQRAEQRCKgwQOQRAEQRCKgwQOQRAEQRCKIyTYAwgGLpcLdXV1iIyMBMdxwR4OQRAEQRBjgOd5dHV1ITU1FRrNyDYaVQqcuro6pKWlBXsYBEEQBEFMgJqaGkydOnXEa1QpcCIjIwEI/0FRUVFBHg1BEARBEGOhs7MTaWlp4j4+EqoUOMwtFRUVRQKHIAiCIGTGWMJLKMiYIAiCIAjFQQKHIAiCIAjFQQKHIAiCIAjFQQKHIAiCIAjFQQKHIAiCIAjFQQKHIAiCIAjFQQKHIAiCIAjFQQKHIAiCIAjFQQKHIAiCIAjF4VeB88knn+DWW29FamoqOI7De++9N+pr9u7di7y8PBiNRkybNg2vvPLKoGu2bduGOXPmwGAwYM6cOdi+fbsfRk+onaKSsyguNQ/5XHGpGUUlZwM8IoIgCGKs+FXg9PT04NJLL8WLL744pusrKipw0003YcmSJSgrK8MvfvELFBYWYtu2beI1Bw4cwF133YVVq1bh+PHjWLVqFVauXIlDhw7562MQKkWr4fDcECKnuNSM50rOQquhTvTEYEgYE+OF5ox/8GsvqhUrVmDFihVjvv6VV15Beno6Nm3aBACYPXs2Dh8+jN///ve4/fbbAQCbNm3CsmXLsGHDBgDAhg0bsHfvXmzatAlvv/22zz8DoV4KC3IAAM+5F5fCghxR3KxfNkN8niA8YcIYEOZMkYcYZnOHUVxqhtPFY53HY4T6oDnjHyTVbPPAgQNYvny512M33HADNm/eDLvdDp1OhwMHDmDdunWDrmGiaCisViusVqv4c2dnp0/HTSgXT5Hz/C4znDyPxdlxQ4obWngIwHvOnG7oQkqUEZs/qwAAL2HsKZYJdeM5Z7r7HNCFcHi+9DwAmjOTQVJBxg0NDUhKSvJ6LCkpCQ6HA83NzSNe09DQMOz7bty4ESaTSbylpaX5fvCEYlmcHQcAcPI8AGD/+RY8/a+TXteQ24rw5MFrspEWE4odX9WL4gYAOnrtAECWQGIQhQU5uHleCl77tBwv7T4vPr7/fDM+r2ilOTMBJGXBAQa3QOfdm4rn40NdM1Lr9A0bNmD9+vXiz52dnSRyiEEws7Dn4nGkqg33/GlwfNfrn1XiQHkLXlt1BbaXXaCFhxDheR6/3P4Vatp6Bz23eV8FXv+sAjwPmi+EF+eburHnTOOgxw+Wt2LlqwcA0JwZL5ISOMnJyYMsMY2NjQgJCUFcXNyI1wy06nhiMBhgMBh8P2BCUQz0gx+tbsN3XzsIm9MFAHjk+ulo6rJi6xc1AIBT9V1Y8uxuALTwqJWhRPHLe87jH0dqxZ91Wg52J4+0mFDUtPWC5zHoNYS66bU58dCbR9FjcwLonzPXzEjAJ+YmuM/5+ME3soI4SvkhKRdVfn4+SkpKvB776KOPcMUVV0Cn0414zeLFiwM2TkKZFBbkYP2yGXiu5Cw2vPsV7n7VW9z8dPlM/O72Swb5v2mzUi8DM+3eP3YB//PhGfH5xdlxMP/mJqxfNsPLouN08Xh25+mAj5cIPgMzpniex6/eO4EzF7sAAHnp0eKc2Xu2X9wAwP2vfx7o4coavwqc7u5uHDt2DMeOHQMgpIEfO3YM1dXVAATX0b333ite/+CDD6Kqqgrr16/HqVOn8Prrr2Pz5s147LHHxGseffRRfPTRR3jmmWdw+vRpPPPMM9i1axfWrl3rz49CqITCghw88I0svP159SBx43kNi8sBhM3qDx+dGfRehPLxFMU/3/Yl/vsfX4rPLc6Ow9/WLBr0mpgw4bD28p7zw6YGE8ploCj+++EabDvab/G7ZmbioNd8a34qAOBwVRue/OBEYAaqAPzqojp8+DCuu+468WcWB3Pfffdhy5YtqK+vF8UOAGRlZWHHjh1Yt24dXnrpJaSmpqK4uFhMEQeAxYsXY+vWrfjVr36FX//618jOzsY777yDhQsX+vOjECrCM1BYp+W8xA0gBIjuP9+CRwty8G5ZLWpae/HCx+eg02rIkqNCCgtyYHO48OLuc+Jj+dNiRXEzMPPFfLEL//qyfpBLlFAHnhlTjV1W/ONwjfgcc3UPnDNOF4+s+DBUNFuwZX8VYsL0eHQppY6Phl8FzrXXXisGCQ/Fli1bBj12zTXX4OjRoyO+7x133IE77rhjssMjiEFYHU785UAVACBEI/jBi0vNQ6ZpFhbkYEpMKH72zy8RqtPSZqVi0mJDxfs6LYe3f5gv/ux08V4xWjzP40h1G+ra+zAnJQpOl/caSZuV8iksyAHP8yja1W/BW7c0R5wjA+cMAHT3ObC5WcjIO9PQJT5OqePDI6kYHIIINuu2HkOv3YkIQwhO/58bRfcDMycPXHi+M38KMuLC0Gt34hvT4wdtVoQ6eN69UWm5flHMWDdgo+I4DtfMENwQX9d34oa5yeJzVG5APVw3q98VpdNyXhaZgXMGAH596xwsmhYLAPjE3Iweq4NSx0dBUllUBBFMikvN2HFCyNBbs2QaQjxcTsw6M/BU/cLH5zA7OQpVLRacqOvAH79/udf70Ulc+Tz5wUnUdfSB44ADG67H1i9qRrXmbfzOPBypasXZi9348ZtHsPdn19FmpTKeeF+opaXhMMhSPBxb/msBFvx2Fzp7HZj35IdwUbmBESELDkG4aerqAyDE4Nx1ZX+dJBZIOpR1RqvhsPNkA2LCdGi32PHn/ZUA6CSuFopLzdji/s4LZiUiMcroFXg8UhDx/957JTQcUNVqwfRf7CBxoyKKSs6irKYdALD5vivHNF8AwKjT4n/uuBQA4OIFyw/Nl+EhCw5BuAnRCnq/YFYikk1Gr+eGW0QGWnhe+6QcvXYnXtp9njYrFWB3uhCm18Jic+KOPG9RDGBEl2V6XBjuW5yJNz6rhMPFQ09B6qqguNSM591CJj5CjyU58aK7aixxfKfr+1sNjdXyo1ZI4BAEhEJb29zF2e5ZmD6u1xYW5MDF89i0y4zOPgeJGxVxWVo0LDYn4sL1uH6Wd3rvWL5/zyQMm9NFm5UKcLp4zEiKwNmL3bj10lTxYDUWUVxcakbRLjMumWrCl7UdyJ0SRckNI0AuKkKVDCy29f++rENnnwNTY0JxvKYdRe5FY6ysXTpDdEdxoMVGLfzdneL77flToA8Z33IquLeqEO2ui3PzvJQxuSkIebN6SRaqWiwAgO/Mn+r1XGFBzrAxe54xWj+/cRYAoK69D2sLcmjeDAMJHEKVDCy29bfPhXpMmXFhKNplHnfsDAsoBgAeoCq1KqC524rSU0LvoDuvGF9vO8/NaqX7tSFabsyxGIR82flVA6wOF6YnRiB3StSYX+eZwbkgKxbRYTq09tiwcFrcsDGCaodcVIQq8S621Yey6nZoOGDfuZZxu5c8N6t/Ha+DubEbL+85D6NOS5YcBTGw79R7ZRfgcPG4NC0aH55swI6v6secMee5WR2ubMVrn5Rj9+lG/P7OS8XnCWXybpngCv/2/CkjNokeiOfc0mk1WDY7Cf84UoudJ+rx1DdzfT5OJUACh1AtAwOEJ5JyOTC1t8fmgLmxG7OSI8k3rjA8Kw8/cv10vONuuhofoR93oTXPzWp+egziwvVo6bHh84pWmi8Kw1MYX2jvxcHyVgDAt+ZPmVQpiRXzkgWBc7IBT9w6FxrK2BwEuagIVfPwddPF+yETaJo5sPBfwSyhq31Dp+Abp5O4cvBM//7F9hMwN3ZDq+FQeqpxUkHlWg2HgtlCgHLJ1xd9OWRCAni6w98/dgEAsGhaLLYdqZ1UKYmrpscjwhCCi51WMeWc8IYsOISq+f8+OCned7jGn3I58OR1eXo0TKFCTZyrcuJxZWasz8ZKBJ+BVr+hSupPhGVzkvH3w7X46GQDnrh1zrhcF4S08ZwzseF6AECkMWTSdY8MIVpcPysRHxyvw4cnG5CXEeOzMSsFsuAQqqW41Iw3Dwp9p66dmeCTAM8QrQbXzkwAADEAlVAWnhvSRKx+Q/GN6fEw6jSo6+jDybrO0V9AyIrCghx8b2E6WntsAICSrydn9WOsyBXafPznRP2IfR/VCgkcQpWw2JmsuDAAwFXZ8WOuQDsarB7K7tMkcJTIb/99SrzPrH6TJVSvxZIcQRiTm0qZMOsNAJ8UdSwqOYuv6zth1GlQ09rrJYyLS83jLnWhREjgEKrE6eLxaEEOGrusAID87DgAI7dlGCvXzEiAVsPhzMUu1LRafDJeQhoUl5rx2qflAIB5U0w+TetePkeI3yKBo0zePSrE32g1nFjUcTJoNRxe+PgcpkYLnew/PCn00aM2Mf1QDA6hStYtm4HDla14vtSMmDAd5qT016OY7MkqOkyPvIwYfF7Rit1nGnFvfuYkR0tIAbZx5KZG4URdJ/Kz4wbF5Ex07hSVnIXN4YKGEzqM17ZZMDUmTPy91LRV3jz30RlcaO8FAJSsuxr/78v6Sc+ZgXPvPycaoNNqqKeZB2TBIVTLZ+daAAjWG1+nWBa43VQUh6McWEBxZ58DgJAJA/jG6qfVcPjj3vNIMQmn8V1uKw6dxuVPcakZxR+fAwAkRBqQFR/uM3d4YUEOfnJdNgDgXGM3iZsBkAWHUC2fnW8GACzOjvfp+xaVnEVHrxBMeOB8C3qsDoQbhD81Oo3Ll3XLZuBCe68oODwz5Ca7oQw8jZecuojOPgdtWArA6eKRPy0OB8pbsDArVsyQG0vvqbHw3zfMwst7zoPn4VWIkiALDqFSem1OlFW3ARDqSfgSrYbDlv1VMIXqYHO68Nk5QUjRaVz+HDwvWP1yp5gQadT59L0LC3Lwg6syAQjWRRI3ymDdshnQuHfahVneZSNG6j01VopLzWAJVE4fBb0rBRI4hCr5orIVdiePVJMRme5MKl/BzM8dvXYAwMenGwdVPCbkyYFyQeAw95Sv+f9unSve91UKOhFcbA4XjlQJh6mF0+J8+t5sXbnrSqGfWZheS73MPCCBQ6gS0T01Pd4vRdUKC3Jw++VTAABbv6ghcaMQDrgtOPk+3qgYnhuTr1LQieDy1YUO9NldiA3XIycxwmfv63loeuq2udBpOVhsTqz+RhaJHDckcAhVst8dYHzVdP9sVADw2+/ME+/rtHQalzs1rRZcaO9FyID4G1/BNqxl7rYNU2NCaaNSAIcqhLXmyswYnx6mPKtoG3Va5E4xAQByp0RRd3E3FGRMqI52iw0n6joA+D7A2JNX95aL9+3O8beBIKQFc09dMtUkBo37Cs/T+I25ySg51YiWbhvWFuRQ01aZc8jdXHNhlm8PUwNjd/LSY1BW3Y4jVW34v9+aN8yr1AVZcAjVcbC8BTwPTE+MQFKU0S+/g21Yl6dHAwAuSzPRaVzmsADjRX5wT3mexqcnRCDSEIJeuxNL5yTRaVzGOJye8Tf+7Ut3RabQi+pwZZtff4+cIAsOoQqK3NlLhQU5Yv2bxe7qxb5O3fY8jWfGh+NodRl4HmLdC4BO43KD53kcLO+vm+RrPOeeRsPhsvRofGpuRllNO80VGfN1fSe6rQ5EGkMwKzlq9BdMgsvTBYFz5mIXuvrsPs/ykyNkwSFUgVbDiRYUz/o3/kjd9jyNz0+LBiAsdD+8ehqdxmVKdasFdR190Gm5gHRtnu/erMqq6DQuZz6vENxTCzJj/V4eIjHKiLTYUPA8cKym3a+/Sy6QBYdQBQMLqWk44Mvadry857zPs5s8T+NTY0IRF65HS48NJ+s66TQuIzytfix76tKp0QjTh/i9YCNzbR6tJoEjZw66428WZPnXPcXIS49BTWsvDle2ic1b1QxZcAjVUFiQgxW5yQAAnodfxM1AOI7DfPdmRacqeeFp9fN0TwWiYOP8NMGCU9liQWuPzW+/h/AfLhePLyrdAcZ+KiswkDx3dh8JYwGy4BCqggUV8wD0Wk1ALCqXpUVj16lGEjgyw9PqF27QAgDqO/rwzyO1fhfGpjAdshPCcb6pB2XVbSiYneS330X4Dk+r35mLXejotSNMr0VualRA2rTkMddmdTucLl71VdPJgkOoipKvGwAIp3Ob0xWQrKbL3KfxYzV0qpIbhQU5+K+rMtFjdQJAQMQNgwWN0mlcPnha/Q65rX55GTF4ec/5gLRpmZkciQhDCLqtDpxp6PLr75IDZMEhVMOmXWdxob0PALDz0SX4z4mGgGQ1XZJmAscBNa29aO62Ij7C4LffRfiey9yB4kDgrH4AcHlGDP5xpBZHq9oD8vuIyeNp9WNVi108H7BK5lqN4BL/1NyMI9VtmJPq38wtqUMWHEIVFJeasWmXYK0J1WkxLSFC7Bnl7/o0UUYdshOExe5Ydbvffg/hH/56oAqAEJgeKKsfADF263htO2XeyYjCghysW5oDc2M3AKFxaiDbtIiWP8rAC4zAefnll5GVlQWj0Yi8vDx8+umnw157//33g+O4Qbe5c/ub0G3ZsmXIa/r6+gLxcQgZ4nTxYoDxnNQo0VTMRI6/NxCWLk5xOPKiuNSMw+6NYuN35gVEEDNyEgV3g8XmJHeDzLg9b6p4P9BtWlgZg8NVrQH7nVLF7wLnnXfewdq1a/HLX/4SZWVlWLJkCVasWIHq6uohr3/++edRX18v3mpqahAbG4s777zT67qoqCiv6+rr62E0+qcqLSF/1i2bgRRTKABgnrtnC6OwIMevgX8AcBllUskOli1lCBGWybmppoBZ/QDB3cDcYxSHIy+e3XkGAMChv01LICgqOYtDFS2iS7yxs//QX1xqRpHbJa8W/C5wnnvuOaxevRoPPPAAZs+ejU2bNiEtLQ1//OMfh7zeZDIhOTlZvB0+fBhtbW34r//6L6/rOI7zui45OdnfH4WQOScuCP2ncgcInEDANqrjNe1wkbtBFjhdPFZ/IwtWhws6LYcZSZEAAmf1A/rdVGXk2pQNxaVmfHC8DoBgyQmk1U+r4fDS7vOIC9cD6BfGgShtIEX8GmRss9lw5MgRPP74416PL1++HPv37x/Te2zevBlLly5FRkaG1+Pd3d3IyMiA0+nEZZddhv/zf/4P5s+fP+R7WK1WWK1W8efOzs5xfhJC7rhcPE66G2wOtOAEgplJkQjVadFldeB8Uzdy3JslIV3WLZuBnSfqsXlfBWYkRUIf0n8eDHQ8RRlZcGQBExLT4sNR3tyDualR+K+rsgAgIAkNAwuaHq5sw9mL3QELcpYafrXgNDc3w+l0IinJu4ZDUlISGhoaRn19fX09/vOf/+CBBx7wenzWrFnYsmULPvjgA7z99tswGo246qqrYDYPrZA3btwIk8kk3tLS0ib+oQhZUt7cgx6bE0adBtkJ4QH//SFajSisyshNJRtOXBAOQ7mpgRfFRSVnxUJx5c09aPMo+KdGd4McYG1a+uxCWYE5KUIWUyCtfp4FTTfvq1CtuAECFGTMcd5mMZ7nBz02FFu2bEF0dDS+9a1veT2+aNEifP/738ell16KJUuW4O9//ztmzJiBF154Ycj32bBhAzo6OsRbTU3NhD8LIU+Y9WZOShRCtMFJHqSKxvLjRB1zawY+3Var4fDynvOICROaJrJ5o1Z3gxxYt2wGVi3KQF2HEPvimaYdiFg/xuMrZgEQCpoGOshZSvjVRRUfHw+tVjvIWtPY2DjIqjMQnufx+uuvY9WqVdDr9SNeq9FocOWVVw5rwTEYDDAYqPaImvmqNnjxN4BwGq9r7wUwOJ4iEBVOiYlxsk6w4MwNwrwZ6G44Wt2Gry50qPpELge+rhfmTEZcWNA6er9XdkG8z4Kc1Thf/HqU1ev1yMvLQ0lJidfjJSUlWLx48Yiv3bt3L86dO4fVq1eP+nt4nsexY8eQkpIyqfESyuWrIAYYA8Jp/F9f1gMAzjR0wmJzAKDTuJRp7OxDU5cVGg6YnRycgmmFBTkomJ0IAHjx43MkbmQAsxbPDVKRveJSM4p2mZFqErKKV+QmByzIWWr4vZLx+vXrsWrVKlxxxRXIz8/Ha6+9hurqajz44IMABPfRhQsX8Je//MXrdZs3b8bChQuRm5s76D2feuopLFq0CDk5Oejs7ERxcTGOHTuGl156yd8fh5AhQoCxcKoKRoAx4H0ad/GCRelQRSttWBKGuaeyEyIQqtcGbRyPFuSg9FRjQPunEROHrTUs/iaQsAPT+mUz0NRlxV8PViE9LkzM5AICFyAvBfwucO666y60tLTg6aefRn19PXJzc7Fjxw4xK6q+vn5QTZyOjg5s27YNzz///JDv2d7ejh/+8IdoaGiAyWTC/Pnz8cknn2DBggX+/jiEDKls6UG31QFDiEYsnx4MCgty8MGxOpxr6sY9fzoEJ8+TuJEwYoBxkEQxo+Tri+J9VkmZ5ox0+Zq5NYMQmM6CnAsLcvDWIaEC96n6LvzlBwvE59VEQHpRPfTQQ3jooYeGfG7Lli2DHjOZTLBYLMO+X1FREYqKinw1PELhMPfU7CAGGDO+kzcFz+48AyfP02lc4gTb1QAIJ/IXPj6HmDAd2ix23H75FFWexOVCr82J801Ci4ZgzBvPOL7ZbgvSaXdMkBrnC/WiIhQPK/AXLPeUJ2cvCiX3OQS2rxExfpgFJxgnccDb3ZCfHQcAmJUcFdDCccT4ON3QCRcPxEcYkBgV3Mr6M5MiwXFAY5cVLd3W0V+gQEjgEIrnK4kInOJSM94rEyqcajUcHi3IoY1KorT12HDBnfUWrI7Mnu6GWe4g59MNXQGtqUKMDzH+RgJdvMMNIciIDQMgzBs1EhAXFUEEC5eLx0l2Eg9CLRMGO42vW5qD/91Xga4+B1bMS4ZWw5HLQYKwjSojLgym0OCk+nq6G2YmC5WvTzeo190gB1iKeDDdmp7MSo5CZYsFp+o7cdX0+GAPJ+CQBYdQNNWtFnRZHdCHaMReQsGAncYfXToDM93jOEOnccnC4m+CUcF4KFiaurmxGw6nK8ijIYZDrJskFYGTIqw1p+rJgkMQiqDIXVemsCCnP8A4ORI6rSZoRfU8f9+M5EgcrmrD6YYufBN0GpciJ+qCb/XzZGpMKML1WvTYnKhs6cH0ROplJjUcTpcY0BusuK2BsEDjU/Xq7L9IFhxCcTC3T3Gp2auDuFSK6s1K7rfgENLk5AWWQSWNjUqj4TAjWd2ncalT3twDq8OFcL1WjH0JNszyd66xG3YVWv7IgkMoDs+iemkxoQCEqrRvHaqWRN0ZTxcVIQ08rX5dfXaUN/cAEFwNUmmlMSs5CmXV7Tjd0IlbL00N6liIwbD6N7NToqCRSGXyqTGhiDCEoNvqQHlTjxjLpRbIgkMoksKCHKxbmoOaNiETpuRUoyTEDQAxI+ZCey+6+uxBHg0BeFv9mIUkxWTE3w5VS8LqBwCzU0gYSxkp1E0aiEbDDQpQVxMkcAjFcveCdPG+lDrqmsJ0SHbXyGB1cYjgwoK9nys5i5f3nAMAhOq0kmqlwSx/5KKSJieDWMF4JGarONCYBA6hWJ7deUa8zzrqSoX+U5X6Fh2pwkTOnjNNAISYCqmIG8Db8tdJlr+gU+RRw4rnea8aOMWlZhS5yz8EGzZv1BhoTAKHUCTFpWZsO1oLAFg+J0ly1V8p0FiaFBbkgDmjQjTSsfoBguUvxd0h+izNm6Dj6das6+hDR68dIRoOH33dIBm3JuDRskGFLioKMiYUB8uWmjfFhK8udGBGUqRX4DEQ/NRsVpOHLDjSYtOus2AViRwuXnKNLWclR6K+ow+nGrpwRWZssIejajzXlHONQv+p6DA9ikvPScryx6zFFzutaO2xITZcH+QRBQ6y4BCKgxXVM4QI0zsnSeggLqWiejM9LDg8H/zxEIIw3rRLsPDpQzRYu1R6rTRmDWigSAQXtqZ8cFxowdLcbZWUuAGACEMIMuLcLRtUNm9I4BCKY92yGXjk+ukwu09VOR5F0QoLcoKe7gsA0xMjoNVw6Oi1o7FLnY3wpASz+n3rMiH9OjshAmuXziDXJjEqhQU5YN4orcTcmgw2b74mgUMQ8qepy4qOXjs0HDAtITzYwxmEUadFZpy6G+FJCWb1YxaS6YnSs/oB8Gq6SZY/aVBcagabHk6XtJIZGP1xOOpaaygGh1AkzHqTERcOo04b5NEMzazkKJxv6sGZhk5cMyMh2MNRNcyq99O/HwcA5LgFDhD8eC1PpiWEQ6fl0G11oLatF2kSqZirVpjlT8MBLh544BtZkonz80StmVRkwSEUidldX2a6x0YlNShVXHqcaxS+ixyJzhudVoPsBGFs5KYKLkzc3L84Ey5eqJv0i5tmS8qtyVLZ57gtOOaL/c1apZTK7i9I4BCK5KzbgjMjSZobFeAdaEwEH57nxWyYHAnPGzWn/UoJ5tbMz44DAGQnhkPjjsGRiluTpbJvL6tFuF4Lm9OF8uYeyfTl8zfkoiIUybmLgwOMpQarTGtuFE5VIVo6bwST+o4+9NicCNFwyIiTXtwW65fFAkZPeQhjqfTLUhPs//ql3ULl64HJDFLAM5U9xWREj82JTSVnseNEg+SyvfwBraiE4uB5HmeZq0HCJ/H02DCE6rSwOVyoarUEeziqh8VtZcWHQydBsclO48ylySx/ajmNSxVm9ZOqO5xZlOo7+gBANeIGIIFDKJDmbhvaLUIGFYtXkCIaDSe60MhNFXxY3JZURTHbqLaXXQAAlDd147mPzkiqX5YaYQJHymtNYUGOKIA5TjoWJn9DAodQHGyjSo8Nk2wGFQv+GyrQWA3Bf1JEPIlLfKNat1TYnFw8UPyxtKrmqg2Xi8f5JunHbTEXJgDwPCQRAB0ISOAQisMsmoylG3/D3A0XO4Uif2fcAaPkbgge4rxJku68AYBHl84Q+2VJtbCcWqjv7IPF5oROyyFDoin7bE15YEkWAEDDQTJZXv6GBA6hOM5K3NUA9Lsb9p4VOlefaegSFyI6kQcenuf7XVQSjaVgFJeaxX5ZUi0spxbYnMmMC5dkkoDnmvKLFbMRqtPCxQP/tThTFSJHet+IDCkaYaKQuyHwmGWQIg4IIufBa6YBACpbLCRugkhTtxWdfQ5oOCHIWKqwDYsVhsxJjFDFRiVVpB5gzFLZCwtyoNFwYlX3xdPjJZPK7k9I4PgA5m4YuMiQuyHweJ/Epe1qAIDHV8wW74eQuyFosLICUq587Xka/6+rMgEIAaNSKiynNsT4G4kKnHUDDkwsEPp8U7dk+vL5E6qD4wM8aw3wPI/vL8rAW4eq6UQeBFp6bGiz2MFJPIOK4bkpOdzuBpovgccs8ZM44H0ar3GXFahstuAn100XnycCi5hBJeF544kocNzjVjokcHxEYUEOGjr7ULTLjKJdwqZF4ibwmN0n8bSYMITqpXkSZ7AT+dzUKJys68SiabGS7GOjBsyN0m/t4XnaTo0OhSFEA6vDhdo2C82XIMDzvCyEsSdsnMzypHTIReVD1i7tX2R0WnI3BAO2UUk9/sbT3XDbpakAgIRII7kbgoT5orRdDQPRajgxVqi8qSfIo1EnLT1CvS25WIsBoZ0EAJxv6lFFN3oSOD7k7UPV4n27k7IbggHbqKScIg54uxumuRfHcrdfXA3Bf1JD7EEl8XnjiWc8BRF42JxJi5Fuva2BZMaFg+OAjl47WnpswR6O3yEXlY8oLhVcU8lRBjR0WnHrJankbggCLEVc6hYcT3cDy2yoaBZOVTRfAktrj01c7NkJVw6weUMCJzjIzT0FAEadFmkxYahuteB8YzfiIwzBHpJfCYgF5+WXX0ZWVhaMRiPy8vLw6aefDnvtnj17wHHcoNvp06e9rtu2bRvmzJkDg8GAOXPmYPv27f7+GMPi6W5YNE3oLDs7NZLcDQHCM01/4ElcDmn66bFhCNFwsNicaOjsC/ZwVAebM1NjQhGml8+Zr9+CQy6qYHBehgIHALIT+t1USsfvAuedd97B2rVr8ctf/hJlZWVYsmQJVqxYgerq6hFfd+bMGdTX14u3nJz+U+2BAwdw1113YdWqVTh+/DhWrVqFlStX4tChQ/7+OEMytLuhh9wNAYKl6f/uP6fQ0mMDxwmLjlzS9HVaDdLdVVApniLwsLgtucTfMJgFp5wsOEFBDq09hkJNrk2/H1eee+45rF69Gg888AAAYNOmTfjwww/xxz/+ERs3bhz2dYmJiYiOjh7yuU2bNmHZsmXYsGEDAGDDhg3Yu3cvNm3ahLffftvnn2E0hnM3AOSeCgSeafqAcBL/06flskrTn5YQjvLmHpQ3deOq6fHBHo6qEAOMJd6iYSDsMNXcbUOHxQ5TmC7II1IXosCRuDt8INkqyqTyqwXHZrPhyJEjWL58udfjy5cvx/79+0d87fz585GSkoKCggLs3r3b67kDBw4Mes8bbrhh2Pe0Wq3o7Oz0uvmL/swG5U8eKVFYkIPrZwnVXWvbemUlboD+zUoNZmMpMJRbk53E5eDWBIAIQwiSooQYivPNtN4Eks4+u+hOlp+LigSOT2hubobT6URSUpLX40lJSWhoaBjyNSkpKXjttdewbds2vPvuu5g5cyYKCgrwySefiNc0NDSM6z03btwIk8kk3tLS0ib5yYaHCZw2ix1tKohSlxLpscL/Pc8Deq1GNuIGAKYxYdxMAicQeFYfF2vgJMnHrcnI9nCJE4GDxd8kRhoQZZSX5YzF4NS29aLP7gzyaPxLQCLqOM57seB5ftBjjJkzZ2LmzJniz/n5+aipqcHvf/97XH311RN6zw0bNmD9+vXiz52dnX4TOWH6EKSajKjr6EN5cw/ywvV++T3EYPacaQQgbF42p0tWVYE9U8UJ/zPQrQkApacu4qXd52Vm+QvH/vMtqjiNSwmp96AaidhwPaLDdGi32FHR3IPZKVHBHpLf8KsFJz4+HlqtdpBlpbGxcZAFZiQWLVoEs7k/Eyk5OXlc72kwGBAVFeV18ydZFPwXcIpLzahsEcrX/+2BhbLLYGOxWxfalX+qkgqFBTm4e0H/QUdu4gbwtODQWuNvvNyaA3pQycWtCQjGAbW4qfwqcPR6PfLy8lBSUuL1eElJCRYvXjzm9ykrK0NKSor4c35+/qD3/Oijj8b1nv5kWrx70SF3Q0BgbgVmv8uKDxcz2OQicuLC9YgyhoDn+wPUCf+Tlx4j3pebWxOg2K1A4unWPHex34IjN7cm4JEq3qjseeN3F9X69euxatUqXHHFFcjPz8drr72G6upqPPjggwAE99GFCxfwl7/8BYCQIZWZmYm5c+fCZrPhzTffxLZt27Bt2zbxPR999FFcffXVeOaZZ/DNb34T77//Pnbt2oV9+/b5++OMCTGTihadgOB08bh/cQa27K9CuF6LhEgh8JJtVnJI0+c4DtMSInCsph3lTco2G0uJfxyuAQBoOMjOrQn0b1RVLT1wOF0I0VJxen/h6dY0hQpxN8drO/DPI7Wytfwp3YLjd4Fz1113oaWlBU8//TTq6+uRm5uLHTt2ICMjAwBQX1/vVRPHZrPhsccew4ULFxAaGoq5c+fi3//+N2666SbxmsWLF2Pr1q341a9+hV//+tfIzs7GO++8g4ULF/r744wJMZOKMhsCwrplM1Dy9UVs2V+FrIRwr1gsOS060xLC3QKH5k0gKC414/PKNgDAL26aDYvNKbvq46mmUBh1GvTZXahp6xXXHsI/FBbkwOF0ofjjcwAgS3EDkMDxKQ899BAeeuihIZ/bsmWL188/+9nP8LOf/WzU97zjjjtwxx13+GJ4PodNnsoWC5wuXlamS7lS4RaTWfHyC/pjiPEU5KLyO8ytEB9hQHO3FdMSwnH9LCGGT04iR6PhkBUfgVP1nShv6iaBEwBuuiRFFDhydGsC/bVwypt64HLx0Ch0jyJ7ph9IjQ6FPkQDm8OFuvbeYA9HFbC4FTkv8NkUnB4wnC4e65bmoMfqACA0IQQgy+rj2dSTKqC85BY3HPrdmnIjLSYUOi2HXrsT9QpuDyOfxisyQqvhkBkXhrMXu3G+qRtp7jL8hP9gdUCy4uX7f+3Z5mOksgfE5Fm3bAYaOvpQtMsMrYbz+huV24l8GtXCCRjFpWb868t6AMBtl6UiOyFCVhY/RohWg8y4cJgbu3G+sRtTokODPSS/QBYcP8EyqSgjJjBUtjCBI18XVUZcGDQc0GV1oKnbGuzhKB4WIyecZuW7FJIFJzAwt2ZuqpAAkBknv2xNT9QQh0MWHD/R3wiPBI6/6bE6cLFTEARZcfJ1URlCtJgaE4bqVgvKm3qQGGkM9pAUTWWzUDcpU8ZuTYC6igcK1lR537lmAP3ucDllawJCPR+thkN2Yjhw0lvgFJeaBfetR39FOSPfY4vEoUyqwMGsZHHhetk3HCRhHDj6rX7yFjhs/K09NmoP40fWubOlKt3rjacwLizIkY0oYPV8WA0c9q8c6/mMBgkcP8H84lQLx/9UDLHgyBWxSKSCzcZSoT9uS97zJtwQghSTYO2jA5V/6bE60Nglb2sxc6vtPCl0Azjf1C2KGzmmvI8Euaj8BPOL13X0wWJzIExP/9X+olIBGVQM0YJDsVt+RwkWHNHdkBCB+o4+nG/qQV5GLADluRukAJszMWE6WVuLCwtyYHU48dLu82jssipS3ABkwfEb0WF6xLj/ACjQ2L8oIUWcMY0CRgOC08Wj2t27LFOmJ3Gg393QbbUD6J83SnQ3SAEWt6WEtea/b5gl3g/RcIoTNwAJHL8iuqlI4PgVZu2YpoBFhwWM1rRaYHVQ001/UdfeC5vTBb1Wg1QZp8gyd8Oxmg4AgttNqe4GKcAKiirBHe6Z9eVw8bLLAhsLJHD8CNtwKWDUvyglBqeo5Cy2fl6NcL0WLh6ihQGQV7diOcDmTEZcmOytHIUFObj98ikAgJKvL5K48SMVzIIjY6sf0G/hm+NOeV+cHSfLVPfRIIHjR7KoMq3faeuxoaNXMM/L2dUACO6Gol1mhBuEeC2W9kvuBt+jFFHM8IyzkWv7ADnAYnDkPG88LXw3z0sBAKSYQmVbz2ckSOD4ESr253+YeyrVZESoXhvk0UwO5m5gWRrlzcrNbgg2SorbAoSmjwy5tg+QA0pIaGD1fAoLcpARJ1TwrmzpkWWbktGg1B4/wDIbVuQmA/AuvU+ZDb5F3KgS5LvgeFJYkIMD51twoLwFv//wDFw8SNz4ASVkUDGKS83YtMuMmDAd2ix23H75VFm2D5A6nX12tLjrDMnZguO59zCrd5X770Fp84UsOH6AZTb868s6r9L75GrwPWLQn8zdU57cszAdAODiyd3gL0QXlcznjaeFLy8jBgBwWXq0It0NwYZZb+IjDIgwKMM2wCw4zd02dPXZgzwa30MCxw8wU19x6TlEGoVU8d9/eIZcDX5ASWmbjIPlLeJ9cjf4HpvDhdq2XgD9aflyxdvd4D6NNyvT3RBs+t2a8m3oO5BIow7xEXoAQJVHUoNSUIYMlSBMxDBT8d8P15K48QNiirjMNypGcakZbx2qFn9++Lrp5G7wMTVtFjhdPML0WiRGGoI9nEnh7W5g8RTCRkXzxbeIvctkbvUbSGZcOJq7bahs6UHuFFOwh+NTyILjRwoLcsC8URqOFhxf43LxHkF/8u0izvB0N7AikTfNSyF3g4+pFFPEw8FxynEXZwyIpyB8ixIyqIaCzZtKBSbDkMDxI8WlZjALsYsHbVA+5mJXH3rtTmg1HKbGyLdYG2NId4NCsxuCSYWCCkN6IgaMtlrgornic5SWeccYaPlTEuSi8hPsNP7t+VOwvewC4iP05GrwMayRaXpsGHRa+Wv1ge6GYzXt5G7wA/01cJQTSwEAqdFGhGg42BwuNHT2ybpCsxRRSmD6QJhFSomWP/nvChJkqNolPVYn1i3NIVeDD6lQUKrvQMjd4D/6U8Tl79b0JESrQXpsf10Twnd4FRRVmDBmgo1VaVYSZMHxA56uBpvDBa2GQ6/die8uSAfHceRqmASsxlBhQY5owWECR0k1htgiShuV7+mfN8raqAAh7be8uQeVzRYszg72aJQDO0wlRRkQplfWtpkRz1LFrei2OhSTAg+QwPELXmXTQzSYEh2K6lYLKlss5GqYJKzGEOBdbt/TaqYE+i04yjtVBZM+uxN1HX0AlOdqANi8aSLLn49RQgXj4Ygy6hAXrkdLjw2VzcrKpCKBEwAy4sJQ3WpBVUsPFmTFBns4ssYz/Z5lGh2vacc/jygrDZ9tvvUdfeizO2HUybsNhVRggjHKGILYcH2QR+N7MuPI8ucPlCxwAGGPaumxoarFoiiBQzE4AYBVi6TTuG8oLMjB2oIctFkEn7jSxA0AxITpEGkUzh/VrTRvJkORR9wbq3ydFR8utk5RUpf2jHiy/PmDihZl1sBhsEBjpQljEjgBgP1RKG3yBJNvXz5FvK/EdgYcx/XPGwXWpwgkzK1ZXGoWAyk93ZpKap3iudbwPMX6+YpKhXWfH4hS1xpyUQUAltlApyrf8bz7RM6hv52B0kRORlwYvrrQQRacSeLp1sxNjQIANHb24f1jdYqz/E2NCYVWw6HP7kJjlxVJUcZgD0n28DyvChcVoLw9igROAPA0/7Gu4sTEKS41492jFwAABbMTccnUaEXWGCLLn+8Y2DrlQHmr4sQNAOi0GkyNCUVViwWVzT0kcHxAS48NXVYHOK7/sKo0sshFRUwU9kfR1edAu0V5HVsDCXMr5KVHAwDSY8PFSr9KqzGk1FNVsPAUMyHuUgNKJIOE8aTxjtsS/h9TTaEw6rSKi9sC+udMY5cVPVZHkEfjO0jgBACjTotk90mKFp3JwWoMxUYITRJZvRgltjNQauBfsPjDR2fE+w4Xrygx7ImSS+8HCu+4rf7K10qM2wIAU6hOzCpU0oGKXFQBIiMuDA2dfahqsWB+ekywhyNbWI2hG4o+AeBtMlbaiZxZcC609cLmcEEfQueRiVJcasYLH58DICzmq7+RpUi3JkBVsH2Bp0tzQaawXnf1OQZVqFcSGXFhaO0RuorPcceqyR1aMQNEJhVu8xk8z6Oqtb8jtFJJiDAgTK+Fiwdq22jeTBR26r7t0lQAwkKuVLcm4GHBUWDp/UDC5sjnlW0AgC9rOxQrbgBlxvwFROC8/PLLyMrKgtFoRF5eHj799NNhr3333XexbNkyJCQkICoqCvn5+fjwww+9rtmyZQs4jht06+vr8/dHmTDpYjyFciZPsGjssqLP7oKGA6YouKEgx3GUgecDmFtznruAGfs/VaJbE/C24FCq+OQoLMgBc0YpOW4L8DiEK0gY+13gvPPOO1i7di1++ctfoqysDEuWLMGKFStQXV095PWffPIJli1bhh07duDIkSO47rrrcOutt6KsrMzruqioKNTX13vdjEbpZgwoUR0HC7bZT4kJVbzbhubN5FnnPnX3W/283ZpK6F3mSVpsKDQc0GNzornbFuzhyJrnd50Fk4hKjtsC+uMZKxS01vg9Bue5557D6tWr8cADDwAANm3ahA8//BB//OMfsXHjxkHXb9q0yevn3/72t3j//ffxr3/9C/Pnzxcf5zgOycnJfh27L6GMGN/BrGAZscp1TzFYIzyaN5OH/R8qfd4YQrRIjQ5FbVsvqlp6kBBpCPaQZElxqRlFu/oFTeH10xUbtwUoM3bLr8dfm82GI0eOYPny5V6PL1++HPv37x/Te7hcLnR1dSE21ruHU3d3NzIyMjB16lTccsstgyw8nlitVnR2dnrdAg0TOC09NnT1Uar4ZGCF79LjlFmTwhOy4PgONc6bCoVVpg0ULG7ruwvSAAhdxNcvn6nYuC0AyHLPmYudVlhsykgV96vAaW5uhtPpRFJSktfjSUlJaGhoGNN7/OEPf0BPTw9WrlwpPjZr1ixs2bIFH3zwAd5++20YjUZcddVVMJuHnnQbN26EyWQSb2lpaRP/UBMk0t2xFaDT+GSpFE/iyt+oyPLnG+xOFy609QLwdlEpFZo3k4PFbS2aFgeg3+qn1LitopKz+POBSkS7Gxh7zhs51/0JSADDwMq9Y63m+/bbb+PJJ5/EO++8g8TERPHxRYsW4fvf/z4uvfRSLFmyBH//+98xY8YMvPDCC0O+z4YNG9DR0SHeampqJveBJggtOr6hukX5GVQMdhKvbbPA4XQFeTTypa69Fw4XD32IBkmR0o3V8xVk+ZscYtxWy2CrnxLjtljdH2OIFkC/m0rudX/8GoMTHx8PrVY7yFrT2Ng4yKozkHfeeQerV6/GP/7xDyxdunTEazUaDa688sphLTgGgwEGQ/D90Jlx4Tha3S4GOxITo8rtalDDSTw5ygh9iAY2hwv1HX1IU4HVyh9UeVj9NDJdrMcDHaZ8Q5VKrMUDW5lUNFtEcSPn1Hi/WnD0ej3y8vJQUlLi9XhJSQkWL1487Ovefvtt3H///fjb3/6Gm2++edTfw/M8jh07hpSUlEmP2Z+IqeIKSsMLNB0Wu9juQql9YTzRaDhxcaXT+MRRiyhmLQayBvS/A+TtaggWNSqK2yosyMGiaUKs6/98eFr24gYIgItq/fr1+N///V+8/vrrOHXqFNatW4fq6mo8+OCDAAT30b333ite//bbb+Pee+/FH/7wByxatAgNDQ1oaGhAR0eHeM1TTz2FDz/8EOXl5Th27BhWr16NY8eOie8pVchsPHmY9Ss+woBwgzoKcff3FiJhPFGYWzNd4RlUzNXwr+N14Dih+m6bxS57V0OwYOuNGg5TALDyCiE+1cUDeq1G1uIGCECa+F133YWWlhY8/fTTqK+vR25uLnbs2IGMjAwAQH19vVdNnFdffRUOhwM/+clP8JOf/ER8/L777sOWLVsAAO3t7fjhD3+IhoYGmEwmzJ8/H5988gkWLFjg748zKchsPHnY/12mCk5UjEzR8kfCeKKIrgaFzxtPV0OkIQRdVgee/fA0tn5eI/vTeKDpsztxsdMKQB3xfgDweUWreN/mdKG41CzrOROQI/BDDz2Ehx56aMjnmGhh7NmzZ9T3KyoqQlFRkQ9GFljYH0lDZx/67E4Yddogj0h+qCnVt8h94s6IH2zBKS41w+niFRfs6C/UNG8GxlOQuJkYbM5EGkIQ484uUjLFpWZs/UJIwOE44BEF1P1RdhlYiRETpkOkUdCU7I+HGB9qKvLH3A3HqoVeOErJbAg0PM+Lf29KDxZlFBbkgE0PLafsFgP+wjODaixZv3KGrSnrluYgTK8FzwPfumyK7Ov+kMAJIBzH9cfhkLthQlSqxNUA9Nfc2Hb0AgAhUPb5XWcVEfwXSJq6rbDYnNBwwNQY5c8bQNiwWKkWJ6/sFgP+QjxMqWCtYXV/Hl06o7//XatF9nV/1BGlKSHS48Lw1YUOisOZINVD1KVQMoUFOXC5eGwqNcPmcKFol5nEzThhcybFpPzeZUD/afyWeSn4f1/VI9VklL2rIRiIbk0VWIs9Xd3psWE43dAl/t3Iec4o/69dIrD0TTFg1KMWDqVvjo0+uxMNnULH+EyVBP0BwFqPxUfpHY39gVoCjAF41S750TXZAACbk5e9qyEYqGneeMI+rxLCKEjgBAgWT2G+2A2g/4+H4inGTo3Kgv4YnpuS0jsa+4MqFVW+Zq6GwoIc0crZ3G3FA0uyZO1qCAZqi9tiiC4qBXgZyEUVIAZmNlS29CiiUmQgqVRR0B+DzZFLp5pwvLYDCzJjyN0wTtRS5A/wdjWYQnWIDtOh3WJHtTueghgbTheP2jZ1ucMZ6e6DQLUCKu6TBSeAFBbk4IdXTwMA1LT2krgZJ2oK+gO83Q23XpoKAEiMMpK7YZyopdz+UCjpNB5I6tp7YXfy0Gk5pJhCgz2cgML+TqpbLWIVbLlCAifAbFgxS7yv01I8xXgQTcYqcDUA3u6GNI9FR+6ZDYFGTTVwBsIETo0C4ikCCZszaTFhqgsfSI0OhYYD+uwuNHVZgz2cSUEuqgDzwsfnxPt2Jy/7SpGBRG0ncU93w8DAP5ozY6Orz47WHhsA9QhjT8iCMzGG6iKuFvQhGqRGh6K2rRdVrRYkRhmDPaQJQxacAMJcDtPclWmvn5VIroZxwFxUalx02EbVbrGjo9ce5NHIB7ZRxYXrEaGS3mWeiO1hyIIzLliWq1oOUwNRSlshEjgBwjOe4pqZCQCA7IRwiqcYIw6nC7VtvQDUeRIP04cgPsIAgNwN40HN7ikAomuT5sz46K+3pb61Buiv/SP3VHESOAHCM54ig+IpxkSRh/Cr7+iDw8VDH6JBSpRRlbWDlHKqCiRqc2sOhB0GatsstMaMA7XPG2Yxrm6RdyaV+my2QcKrUuSAjYriKYaG1Q4CgMvTYwAAaTGheHH3OdEapibSY8NwpKpN9qeqQMJSXdV6Ek+OMkKv1cDmdKG+o1c1rSomg1fvMpVa/pTi2iSBEwSY+a/GnYanlpou48WzdlDBrEQAgIuHatPrxVOVAupTBAp2iMhU6Ual1XCYGhOK8uYeVLdYSOCMgdYeG7qtDgD9Lj610W/BkbfAIRdVEJgaEwqOA3psTrS4MzyIoWEuvNLTjQCAiuYeVYobwFPgyHvRCSRqLbfvSbpCTuOBgv0/JUcZYdRpgzya4MDmTIuH2JMjJHCCgFGnRbI79Y42q9EpLMgBM3JpVdyLiWJwxgaL3bI6nKjrEALTmdVUjbFbJIzHh9oa+g5FlFEntsORsxWHBE6QSFOICTAQFJeawQpqOlXci4ltVHXtvbA5XEEejXRhsVsbd5wGzwNhei3iI/Sq7fumFHdDoFB7gDFDCS0bSOAEiQw6VY0JtinptcJUvX9xhmrT6hMiDTDqNHDxgsghhoa5NbfsrwQgbPAvfHyOYrdorRkTYg0cFVtwAGXMGxI4QYIqjI4OEzcPXjMNNqdgsXh8xWzV1g7iOK5/3sh40QkEhQU5uM5db+rMxS7VihugP1W8SuYpv/7EsyTFwBo4anRrAv2HcDnvUSRwggTz71IBruFhtYNumJsMoD/oT821g5RSgCsQZMVHAAB4HtBrNaoUN0D/Yaqzz4F2CyU1DAVzaxaXmvu7z8eGqdatCfTvUXJeayhNPEgowfznb1jtoPePXQDgHfSn9s1K7gW4AsGeM0LmnVbDweZ0qbbvW6hei4RIA5q6rKhutSA6TB/sIUkOz5IUjA9PNuDlPedVa/lTgpeBLDhBgpmNGzr70Gd3Bnk00kY0Gas86A8Y3HSTGJriUjPKmwUR+Mb9V6rWrclQgrvB3xQW5ODe/AzxZzWLG6B/rbnQ3guHU55JDSRwgkRMmE5s/lfbRovOSIj9hEjgDKqCTQyGuRVC3G6F9Ngw0a2pVpFDFuOx8Y3p8eJ9Nbs1ASAp0gh9iAZOF4+69r5gD2dCkMAJEl4Bo7RZjUiVysume8LmDKuCTQzG6eLxo6unweHioeGA1OhQAFB37FYcpYqPhbcOVQEANBxEt6Za0Wg8kxrk6RKnGJwgkh4bhq/rO+lUNQosEFutZdM9GVgFm3UYJ/pZt2wGDle24tVPypEaHQp9SP85Tq0ncrlvVIGguNSMvWebAQA/uiYboTqtGJOj5nlzrrFbtnsUCZwgQpVpR6fP7kRDp2AeVXvhLQAwhGiREmVEXUcfqlstJHCGgdya3mSIWZtUP2komFszMy4MlS0WpMeG4bsL0gFA1SJH7kUiSeAEkbRYShUfjdq2XvA8EK7XIjacsj8Awd1Q19GH6haL2GWd8IZ6UHnDygvUdfTC6nDCEKLOHkvDwUpSvMcyNt1rMxM1anNrFrlT44c6hBeXmuF08WKWq5ShGJwgopSW9P7E0z1FXdcFKGB0dMit6U18hB5hei14HrjQRlacgaxbNgM/uW46altZ7zLvkhRy2Mx9CasLdLymHUD/HiW3ukBkwQkingGjLhcPjUwmTSBh1VfpJN5Pf2VaEjjDUUUuKi9YUsPphi5UtVowLSEi2EOSHBc7+2BzuhCi4ZBiMgZ7OEFlYF2gmlYLnt91FkW7zLJKnScLThBJjQ6FVsPB6nChscsa7OFIkuohTlRqh1ybo1MtVqMND/JIpAM1+B0ZdmCYGhOKEC1tjYUFOSi8fjoAoNvqkJ24AUjgBBWdVoPUaOGkQO6GoWGdbFlfGMKjaBtlxAxJr82JJveBgYRxf5+loRr8qrXP0lCQW3Mw65fPFO+HaDhZiRsgQALn5ZdfRlZWFoxGI/Ly8vDpp5+OeP3evXuRl5cHo9GIadOm4ZVXXhl0zbZt2zBnzhwYDAbMmTMH27dv99fw/Qo7YVIjvKGhbJjBsP+Li51WqoI9BGzOmEJ1MIXpgjya4MPiKcqbuwH0WyrkFk/hb2itGYxnHSCHi5ddXSC/C5x33nkHa9euxS9/+UuUlZVhyZIlWLFiBaqrq4e8vqKiAjfddBOWLFmCsrIy/OIXv0BhYSG2bdsmXnPgwAHcddddWLVqFY4fP45Vq1Zh5cqVOHTokL8/js8hd8Pw8DxPi84QRIfpEGkUwudo3gyG5ow3rMDhx6ebAAhzhokbubkc/AkVFPWGzZG5qVEAgMXZcbKrBO53gfPcc89h9erVeOCBBzB79mxs2rQJaWlp+OMf/zjk9a+88grS09OxadMmzJ49Gw888AB+8IMf4Pe//714zaZNm7Bs2TJs2LABs2bNwoYNG1BQUIBNmzb5++P4HMqkGp6mLiv67C5oOGCKuxqt2ikqOYsXPj43ZBVscjcIkMAZTGFBDv7rqkwAwJmLXSRuhoDmTT+eAvjGuckAhJhRubU78avAsdlsOHLkCJYvX+71+PLly7F///4hX3PgwIFB199www04fPgw7Hb7iNcM955WqxWdnZ1eN6lAKb/Dw/5PUkze1WjVDHM32BxC87tqmaZv+hPWaT2dTuJebFgxW7yv08ovnsLfiPOGAtPFukCFBTn9bT5aLbJrd+LXNPHm5mY4nU4kJSV5PZ6UlISGhoYhX9PQ0DDk9Q6HA83NzUhJSRn2muHec+PGjXjqqacm8Un8h9wrRfoTKtY2mIHpm9XkbhgEncSH5pW958X7dqcQT0HzRaCzz442i3CATosla7Fn3Z+Be5Sc5kxAjsUDC7TxPD9i0bahrh/4+Hjec8OGDejo6BBvNTU14xq/P2HquKXHhm6rI8ijkRa0UQ1NYUEOls5OBAD8+UAliZsBiLEUNG9EmAhOixE27xvnJsvK1eBvWCxbbLgekUYKTPeErb8NnX2yS2rwqwUnPj4eWq12kGWlsbFxkAWGkZycPOT1ISEhiIuLG/Ga4d7TYDDAYJBezx5WDjs6TId2ix3VLRbMcQd0yakctr+gtM3h+a+rsrDrVCN4HtBrNSRu3LhcvFiNluaNgKeFr669F1u/qMHM5EjMSY1SdZ8lT5h1gg5Tg4kN1yPCEIJuqwO1bRZMT4wM9pDGjF8tOHq9Hnl5eSgpKfF6vKSkBIsXLx7yNfn5+YOu/+ijj3DFFVdAp9ONeM1w7ylVWDyF0R1fQvEU3lBWw/B8fLpRvG9zuugk7uZiF1WjHYhnPEVarHzjKfwJWYuHh+M4r3kjJ/zeqmH9+vVYtWoVrrjiCuTn5+O1115DdXU1HnzwQQCC++jChQv4y1/+AgB48MEH8eKLL2L9+vVYs2YNDhw4gM2bN+Ptt98W3/PRRx/F1VdfjWeeeQbf/OY38f7772PXrl3Yt2+fvz+OTxmqHDbFU/RDi87QFJeasXlfBTQc4OKBNUuy6CTuhqrRDsbTCpwR571RqX2+MOgwNTIZsWE4Vd8pu/Ywfhc4d911F1paWvD000+jvr4eubm52LFjBzIyMgAA9fX1XjVxsrKysGPHDqxbtw4vvfQSUlNTUVxcjNtvv128ZvHixdi6dSt+9atf4de//jWys7PxzjvvYOHChf7+OD6nsCAH+8414fOKNmz8zym4eJC4AWCxOaga7RB4CuBtR2tR1WJBwewkRBp1JHLQv3GTe2pohiovQJA7fDTS48iCMywPPfQQHnrooSGf27Jly6DHrrnmGhw9enTE97zjjjtwxx13+GJ4Qef2y6fi84o2uCieQqTGHUcRZQxBdJg+yKORDp7uhi8qW1HVYhHdDex5NVNNmXcjwiqnN3dbYbE5EKanfssAWYtHQ67ZvjS7JcDhyjbxPounULvIERcc2qi8GOhu+NQsz/RNf0Eb1ciYwnQwherQ0WtHdasFs5Kjgj2koONwunChTThQkTAeGrnWayMndZApLjXjH0dqAQjNzNYW5FD6Jvp7c1E36OGR66LjT0jgjI5cT+P+or6jDw4XD32IBkmRFJg+FJ6xW6xsixwggRNEWDzF2qU50Gs1cLh43J43VXblsP0B+cRHh1VcpTYf/fQLHBLGwyHXeAp/weKR0mJCoVF55upwpEaHQqvhYHW40OiOjZQDJHCCCIunWLt0Bqa6q2dWtag3fbPIQ9RVDTiJU5+lwfSfxKkTPQB09dnR2mMDQK7NkSDLnzdk9RsdnVaD1GjBuiWneUMxOEHEK54iNgzlTT2qTt9kdYGA/j+ijLgwr8whoh+2ibdZ7OjssyNK5RVY2ZyJcxcmI4YmgzKpvCCBMzbSY8NQ09qLqhYLrsyMDfZwxgStAhIhIy4cQBOqWtV7GvesC6R1t934+HQjNu+roNT5IYgwhCA+Qo/mbhuqWyzInWIK9pCCCrk1xwbbyGtkdBL3J9WtrDkruTVHIj02HJ+hRVYWHHJRSYQ0CvwDIIicNUuy4HQHspG4GRm5Vhj1FZ5uzYEncXJrDg2z/NW0WVTnBh8KsuCMDTm6xEngSIQMlW9Unlw/q7+nGNUFGhm1zxvm1iwuNXt1n6d2J8OTYgqFTsvB7uRR39Eb7OEEFZ7nveYNMTwDq2DLAXJRSQRx8rRYRu22rnRe/6wcAMBxVBdoNNRemdbTrcnE3pmGLnz09UWy/A2DVsNhakwYKpqFmL+pMerd2Dt67ejqcwAA0lT8/zAW5BicTgJHIjBXQ5fVgTaLHbHh6qzeW1xqRsnXQiPJ7y1MR2KkkVoQjACLG1BzPMXAnm4kbkYnLdYtcFosWJwd7NEED7ZZJ0QaEKrXBnk00oa5Npu7beixOhAug0B+clFJBKNOi6QoAwB5KWRfwtwKM5IiAAhF/ljKvNrrAg0Hs/ypOTgdAB66tn+X1mk5EjejoGbXplc5CuaeoritUYky6hAdJmRq1rTJY96QwJEQrGpvlYyCuHwJqwtkCBFOUuzEoNa6QGOBmY3r2vtgd7qCPJrgsfE/p8X7didPYngURNemCgWOZ9yWZ4AxxW2NjtxKDEjfxqQi0mLD8Hllq2ozqVhdoP/9VIjB8Qz6oxP50CRGGmAI0cDqcKGuvdddbkBdFJeasXlfBQBgemIEbrs0ldyaoyBmUqlQ4Hi6NHNThV5c9R29eLfsArk2RyEtNgzHaztkM29I4EiIfneDPCaPP2i32NDpDvqjtM3R4TgO6bFhMDd2o6rFojqBw07dBbMSUXq6ERmxYYNicmjDGgwFp3vPkQPlrSRuxoDc5g25qCSEHNPwfA37w0mINCBMT/p7LKh53jC3ZnaiELdFbs2xwTaqjl47Oiz2II8mOHiKmRANxW2NBbmtNSRwJAQV++u3XmWQ9WbMsMaScll0fMk696m7v/u8t1tzHbX3GJJwQwjiI9Sd1PBcyRnxvsNFcVtjQW6FRUngSAi2ODd09qHP7gzyaIIDq5JJzRLHTrrYqFWdwemARzaMylx0k4HNG7lsVr6kuNSM4tJzAIAwvRbrluZQpuYYYH9ftTKpgk0CR0LEejQJrJVJGp6v6U/bpI1qrLBFp7pVnVVpeZ7vz4YhYTxm2LxRW4kBFrf1rfmpAAR33aNLZ1A5ijGQHGWUVRVsCnKQEBzHIS02DKfqO1HVYsH0xMhgDyngVHl0ESfGRppHjxg1VsFu7rbBYnOC44CpMaHBHo5sYPNGLhkxvoLFbUUaQ/BeWR0y3UKPxeDIwTIRDIrcKfRpMWEoH1AFu7jUDKeLl5xLmCw4EkNudQZ8TQ2dxMdNWmwoOA7osTnR2mML9nACDusGnWoKFWsoEaOj1rWmP25r8GGK4raGh9UPcrkbIbNYUSnXDyKBIzHkFqXuS/rsTjR09gGgIOPxYAjRIiXKCECdJQaoWeLEYIcItQkcRhXF+40LlplY6Z4v1a0WUdxINcWeBI7ESFexwKlts4DngQhDiGp7cU0UNWfgVZLAmRDsEFHf0QubQ31VsPszNineb6wUFuTgmhnxAIBX9p6XtLgBSOBIjv5CSuoK/AP6T5LpsWGqiyOZLGq2/ImZd7RRjQnWiykh0gCjTgMXD1xoFwJG1dKLyeniUesOyidhPD6+tzADAODiAb1WI1lxA5DAkRzsNFHT1guXyoLdyNUwceRWYdSXUGD6+GCxFC98fE6cN57uBinGUviahs4+2Jwu6LQcUqMpMH087DvXLN63OV2SzjqjLCqJkRpthFbDweZw4WJXH1JM6vnjo1TfiZPuzgRRW0YM0O+Wo9YeY8OzTcG0eGHe/Hl/BT4+3SRpd4MvqWoWrH5TY8JUIeh8RXGpGX85UCX+/ONrsiXdEoUEjsQI0WowJToU1a0WVLVYVCVw+qvRkqthrLDUzWtmJADwrmki1dRNX9JtdaDFnTlGFpyxM7AXk5rEDdBv9SNRPHY8A4r/dqgaDZ19WD43CaF6rWRFDrmoJIgYT6EydwO5GsYPczfsPNEAALjYaUWf3akadwMTxbHhekQadUEejbwoLMgR5wfHSW9z8ifMlZtJa82YYfWDCgtyvGL+pNz3jSw4EiRdZv0+fIFn0B+dqsaO50lcH6KBzeHCxh2n8OcDVao4kZN7auIwCx8A8Lzws9LnC4PVTkqn1h5jxtMSnBkXjkMVrahsFv7+pDpvSOBICOZuEANGPQSO0t0NFPQ3cQa6G9QibgCy+k0UZuH7wVWZeP2zStESCEh3s/IlbGOmelsTo7+GkrSzfclFJSHYInPiQgeA/vRXNbgb2B8KBf1NjMKCHLD/Nq2GU8UmBXj2LqONaqx4xlL84qbZCNFwcLp4rFmSpYpeTJ69y0gYTwzW3qJS4gKHLDgSYuBJXA6VIn0FuRomR3GpGcwF7nTxqnE3iIHp5GoYM56xFIDQv6uyxYLrZyUh0qiTZCyFL2ntsaHb6gDH9RfIJMaHXOpu+dWC09bWhlWrVsFkMsFkMmHVqlVob28f9nq73Y6f//znmDdvHsLDw5Gamop7770XdXV1Xtdde+214DjO63b33Xf786MEjMKCHDx83XQAQJvFrgpxA5CrYTIwEbx8ThIAwZqhhpM4QLWTJsK6AeuJ2FW8pUcVvZjYWpMcZYRRR73LJgL7e2vutqGrzx7k0QyPXwXOPffcg2PHjmHnzp3YuXMnjh07hlWrVg17vcViwdGjR/HrX/8aR48exbvvvouzZ8/itttuG3TtmjVrUF9fL95effVVf36UgPLYDTPF+yEqcTeQBWdieFr4Vn8jCwDAA1i/bIbiRY7N4UJ9hzswnQTOhGGbVaVKsjbFHlS01kyYSKMOce52OlIuLuo3F9WpU6ewc+dOHDx4EAsXLgQA/OlPf0J+fj7OnDmDmTNnDnqNyWRCSUmJ12MvvPACFixYgOrqaqSnp4uPh4WFITk52V/DDyqem5JDJe4GVr+FXA3jw9Pd0OhuVFrbZsGD12SLzyuV2jYLXDwQptciIcIQ7OHIFk8Ljhogq59vyIgLQ0uPDdWtFuROMQV7OEPiNwvOgQMHYDKZRHEDAIsWLYLJZML+/fvH/D4dHR3gOA7R0dFej7/11luIj4/H3Llz8dhjj6Grq8tXQw8q7EQ+OyUSAHBVdpziT+I8z9OiM0E83Q0JkQaE6rRibyGluxs8i7VR77KJk6kyC061uNbQYWoyZMgg0NhvFpyGhgYkJiYOejwxMRENDQ1jeo++vj48/vjjuOeeexAVFSU+/r3vfQ9ZWVlITk7GiRMnsGHDBhw/fnyQ9YdhtVphtVrFnzs7O8f5aQKDp7uBA3Cqvgsp0aGiuwFQZgpnu8WOrj4HADIbTwaO45ARF4bTDV2obOlBVryyF3Bya/oGtlFVt/SA53nFi0WK9/MN7P+vqlm6wnjcFpwnn3xyUIDvwNvhw4cBYMg/lLH+Adntdtx9991wuVx4+eWXvZ5bs2YNli5ditzcXNx999345z//iV27duHo0aNDvtfGjRvFQGeTyYS0tLTxfuyA4FUp0r05VTb3SLpS5EQp8rBKsQUnKcoAo06rmo7G/kBM32yW7qnKV5DVzzekxYaC44AemxPN3bZgD8fvUEsY3yCHVPFxW3AefvjhUTOWMjMz8eWXX+LixYuDnmtqakJSUtKIr7fb7Vi5ciUqKirw8ccfe1lvhuLyyy+HTqeD2WzG5ZdfPuj5DRs2YP369eLPnZ2dkhQ5nu6ELHHySLtS5ETxLCzGNqiM2HAvKxYxfjLi1dNVnKrR+gZDiBapplBcaO9FVUsPEiKVG8/UbXWIIo4C0yeHHFLFxy1w4uPjER8fP+p1+fn56OjowOeff44FCxYAAA4dOoSOjg4sXrx42NcxcWM2m7F7927ExcWN+rtOnjwJu92OlJSUIZ83GAwwGOT1R5supuFZ0dVnV1yfHc+aP4uzhe+42+ZQTVq8v5DDqcpXVFKRP5+RGR+GC+29qGyx4IrM2GAPx28wt2ZMmA6mUGWtqYGGuTbrO/rQZ3dKMuXeb0HGs2fPxo033og1a9bg4MGDOHjwINasWYNbbrnFK4Nq1qxZ2L59OwDA4XDgjjvuwOHDh/HWW2/B6XSioaEBDQ0NsNkE1X3+/Hk8/fTTOHz4MCorK7Fjxw7ceeedmD9/Pq666ip/fZyAYwrVIVYGaXiTgbne9p9vAQB8XddJ4maSiH5xhc4ZhsvVX402kyw4k0YtmVRk9fMdMWE6RBoFG4lUrTh+rYPz1ltvYd68eVi+fDmWL1+OSy65BH/961+9rjlz5gw6OoTWBLW1tfjggw9QW1uLyy67DCkpKeKNZV7p9XqUlpbihhtuwMyZM1FYWIjly5dj165d0GqlpyAnQ6YKNqvCghywiCw1tRjwFyywuKbVAofTFeTR+B4Wu3Wxqw82hwshGg6p0UYAoNitSaCWTCqy+vkOjuPEw4VU9yi/tmqIjY3Fm2++OeI1PN8fOJuZmen181CkpaVh7969Phmf1MmMC8fR6nZFuxuKS81g37iaWgz4i6RIIwwhGlgdLtS19ykuzoDFbtW0CQvqlJhQhGg1FLs1SdRiwaHAdN+SHheGry50SHbeUC8qCZMZr+yMGLYpMX5yXbai0+EDgUYjpIqfvdiNipYexQmcgf3a0mPDVNOvzZ+wk3hFs7JTxaupoKhP6bf8SXOPom7iEiZD4pNnMrBN6XsLherUceF6/PcNs1TRYsDfKP00XliQgwVZMQCAz841k7jxAayWUFefA+0W6fYWmgheJSkGWHDIrTk5MtTsoiImB4unUKJfnNX8yYoPx1uHqkVrFduklFTzJ9CIpyoJF+CaLAkRQtyNiwf0Wg2Jm0kSqtciOcqIhs4+VLb0IMad4KAEmFvT6eJR1y70LssYYPkjJgaLZSKBQ4wbVoiqqcuKHqsD4QblfF2s5s8L7pOVZyYMbVaTQ+kWHAA4VNEKQGhGa3O6KHbLB2TEhaGhsw9VLRbMT48J9nB8xkC3ZqhOi7c/r0bRLjNZ/iYJO5jWtllgc7igD5GWU0haoyG8MIXpEBMm1GpQopsKACrcnysrXlmxIsFE6bVwnt91Fs3dQuuVj9ZdTW5NH6HkeVNYkINvz58CAOizO0nc+IjESAOMOo3Y/05qkMCROEwhS9UEOFlYAHWmwvsmBZJMt1isae1VnKuvuNSMol2CkNFqOKTFhon1lEjkTA6lV8G+ZKrQ8ZoHuTV9hXequPSEMQkciaPkUxXQH19Exdp8R4opFHqtBjanS4w5UApOF48786YCANJiQqHTCkuYEvu1BRqlrzXvH7sAANBwEN2axORJl3AcjnKCOhSKkpsndvTa0dojVKhWeufrQCJYNkJxvqkHVS0WpCmoqNm6ZTPw9ufV+MeR2kFWPzqRTw4pb1STpbjUjGM1QkHZ333nEjR09lFJCh8hljORoDAmgSNxmLtBiZlUTLQlRhoUFUAtBTLjwnG+qQeVLT34Rs7ovePkRAVza5LVz6ew1OnWHhs6++yIUkj/O5YtFWUMQWefA1kJ4Vh5pdBsmUTO5JFyexjaVSROhoItOEzxU/yN71FyJhUTONMSaN74kkijDvERejR321DdYkHuFFOwh+QTnC4ehddPxwu7zwHoF8ZUkmJyFJWchVbD4XJ3xp3nWlNcaobTxYvZssGCYnAkTpb7j7GxywqLzRHk0fgWtlFl0Unc5yjZ8kcWHP+RocA4nHXLZuCWS1PB80CkIQTxEf01fgoLcoK+CcsVVl9o95lGAP1JDcxiptUEvxo2WXAkjilMh+gwHdotdlS1WDA7JSrYQ/IZlEHlP5RqwXG6eFS7RRvFbfmejLgwHKlqk6S7YTKIh6mEcMW2oQg0nvWFWOD2xh2n8L/7KiSTgk8CRwZkxoXjmKUdlc09ihI4FeJGpZwgWKng2Yne5eKhkcBpyhfUtffC5nRBr9UgNTo02MNRDMzdMFRSg1TcDZNBFDgkin3KwCKKUhI3ALmoZEF/QzPlnKp4nkdFUzcAsuD4gynRoQjRcLA6XGjo7Av2cHwG26jS48IkYQJXCszdcLq+E0B/wKiU3A2ToaKJ3Jr+orAgB8woptVwkhE3AAkcWaDEruJtFjs6+4SYItaSgvAdIVqNmB6upHiKyhY6ifsDVkdox4kGAML/s5K6tFNguv8oLjWDd8dpsxgcqUACRwYosQAXW3BSTEaE6rVBHo2yYN2Th0rflHv35PImEjj+orAgBw9dmw1ASGpQirgBPFvC0LzxJUwEL52dCEDwNkipojgJHBkg5ToDE6WSMmH8BnM3dFjsAPqFsRLcDWTB8S8/u3GWeD9EYu6GidLVZ0dTl9C7jNzhvsPTwvfAkmkAABcPSbVNoSBjGcAW84bOPvTanIqweFANHP8xMPCvqtmiGHcDpYj7F89NyeF2N8h5vgBAZbNwMIyP0CumeKEUcLp4cT1pdMf51bZZ8KNrponPBxsSOBKHZTeYQnXo6LWjqrUHs5KFTCo5Zzf0ZzVQBpU/KCzIQUVzD7aXXcCHJxuw82SD7MWN3elCbZvQW4tiKXwPE8FzU6Nwsq4T+dNiFVHpt7xZSGYgq59v8dx3EiINiDCEoNvqQHWLRTLzhVxUEoe5G0J1gtWGnUbk7m4QLTh0EvcbbJFRSvfkmlYLnC4eYXotEiMNwR6OovC08N1ySSoAICHSKCl3w0RhayYJHP/BcZx46DjfJJ1YURI4EodlN7BUXyVkN/A8T4tOAHi/7IJ4Xwndk5nVLyOOirX5Gk93A9uoypu7FdGlvUK04EQEeSTKhq3lzGImBchFJQMKC3Kw/3wzDpa34tmdp8VALjmKGwBo7rah2+oAxwn1TAjfU1xqxqZSM2LD9WjtseE7l0+RvbtBTPUlUexzPN0N2W6BU9HUA57nZTtfGOQODwzT3AKygiw4xHi5y9391sXL393A3FNTokNhCJF/wLTU8LTwXZkpNMKbN8Uke3eDGGBMG5VfSY8Nh1bDocfmxMVOa7CHMyl4nke5KHDIguNP+i1/JHCIcfJFZZt4X+7uBiqb7l+83Q3Con6+Sf7uhv4Ucdqo/Ik+RIO0GKENRnmTdNwNE6G1x4auPsFanEHWYr8iuqgkNGfIRSUDikvN+NuhavHnh67NlrW7gWrg+Bdvd4MgBliBPDnOF0ZFE7kaAsW0hAhUtlhwvrkHi6fHB3s4E4YdplJNoTDqyFrsT5gFp81iR1uPDTHh+lFe4X/IgiNxPN0NyVFGAMDSOUmydjdQDZzA0Z/ZIJ1T1UTosztR1yEE2pMFx/9Mk+BpfCKUk7U4YITpQ5BiEvYoqbipSOBIHE93Q3aie7NqlJ+7ochDjFU0e3cRl3v7ACmT7RYDFzut6LY6gjyaicOqeEcZQxATRsXa/M20AZY/uULu8MAiNTcVuagkzkB3w2fnWsQ6A3JyN7B6PkKKeL+LytNCRfgeU5gO8RF6NHfbUN7UjUumRgd7SBOiwqNYG6WI+x/PVHE5U0kCJ6BMSwjH/vMtorAMNiRwZES2R8Co3BjYPkCr4fD+sTo8X2qWdcq7HJiWEIHm7laUN/XIWOBQ3aRAwgRObVsv+uxO2caviBYcqnwdEFiquFQsf+SikhFyFjiAIHLuzJsKQHC9kbgJDNkyjcPxdmsKY2dxW+TW9C8JEQZEGkLA8/Jt8uty8VQ7KcBkSczyRwJHRrAYnOoWC+xOV5BHMzEuTYsW78u9no9cGJhJJReYW7O41OxV+VrubUrkAMdxmJbI5o00NqvxUt/ZB6vDhRANhynRocEejipgMX+VLRZJxIf6VeC0tbVh1apVMJlMMJlMWLVqFdrb20d8zf333w+O47xuixYt8rrGarXikUceQXx8PMLDw3HbbbehtrbWj59EGiRHGRGm18Lh4mV7qtp2RPieNJz86/nIBblmUrFA+udKzuJEXQcA4FBFq6zblMiJ7Hh5zhsGKyuQHheGEC2d5QPBlJhQ6LUa2Bwu1LX3Bns4/hU499xzD44dO4adO3di586dOHbsGFatWjXq62688UbU19eLtx07dng9v3btWmzfvh1bt27Fvn370N3djVtuuQVOp9NfH0UScBwnazdVcakZZTXtAIDffecSWae6ywk2ZyqaeyRxqhoPhQU5+Ml12bDYhL/tvx2qJnETIMRAYxlZ/rzcmi3e7ilya/ofrYYTCypKYY/yW5DxqVOnsHPnThw8eBALFy4EAPzpT39Cfn4+zpw5g5kzZw77WoPBgOTk5CGf6+jowObNm/HXv/4VS5cuBQC8+eabSEtLw65du3DDDTf4/sNIiOyEcHx1oUMSk2c8MLdChCEE3VYHshMjsNLdfkLORQvlwNSYMOi1Gljdp6q0WHkVyls2Jxkv7T4PgNyagUSsgi2RjJixwNyaANBusQPwdmtStqb/mZYQDnNjNyqae3Dt8Nt8QPCbBefAgQMwmUyiuAGARYsWwWQyYf/+/SO+ds+ePUhMTMSMGTOwZs0aNDY2is8dOXIEdrsdy5cvFx9LTU1Fbm7uqO+rBEQLTqN8Fh1ACCr+yXXZYi2W6W7/vtzq+cgRrYYT+zfJTRgDwMu7zwEAOJBbM5D0W3C6wfPy+Pv0dGvuPn0RgFB0jtyagUNKNZT8ZsFpaGhAYmLioMcTExPR0NAw7OtWrFiBO++8ExkZGaioqMCvf/1rXH/99Thy5AgMBgMaGhqg1+sRExPj9bqkpKRh39dqtcJq7W8a19nZOcFPFXyyE+Xpolq3bAbKqtvw0u7zSIw0wBTaX6yNFh3/k50QgbMXu3G+KfinqvFQXGrGR18LG9W9+RmIizCQxS9AZMaFg+OArj4HmrttSIg0BHtIY2JgSYrSU40kbgKIWOxPAplU47bgPPnkk4OCgAfeDh8+DABDFuTieX7EQl133XUXbr75ZuTm5uLWW2/Ff/7zH5w9exb//ve/RxzXSO+7ceNGMdDZZDIhLS1tHJ9YWnjG4MjlVMU41yhMeGa9IQKH52lcLjC3AouhmJ4U6XVCJ0uOfzHqtGL2kZzmDQD88Opp4n2dliNxE0BYWYoKCVhwxi1wHn74YZw6dWrEW25uLpKTk3Hx4sVBr29qakJSUtKYf19KSgoyMjJgNguLWXJyMmw2G9ra2ryua2xsHPZ9N2zYgI6ODvFWU1Mzjk8sLTLiwqBxn6qauq2jv0BCnHMvkjkkcAKOHIPTWZsSh9t9mUNuzYAjuhtkFIcDAP/336fE+3YnT2I4gLBif3UdfbDYgtseZtwuqvj4eMTHj95dNj8/Hx0dHfj888+xYMECAMChQ4fQ0dGBxYsXj/n3tbS0oKamBikpKQCAvLw86HQ6lJSUYOXKlQCA+vp6nDhxAs8+++yQ72EwGGAwyMO8OhpGnRZpsWGoarHgfGMPEiONwR7SmDlPFpygISW/+FhZt2wGem1OFO0SXA2ewphO5IFhWnw4PjnbJCsLTnGpGW8erAIAXJERg6tnJJBbM4DEhOsRHaZDu8WOiuYezE01BW0sfgsynj17Nm688UasWbMGBw8exMGDB7FmzRrccsstXhlUs2bNwvbt2wEA3d3deOyxx3DgwAFUVlZiz549uPXWWxEfH49vf/vbAACTyYTVq1fjpz/9KUpLS1FWVobvf//7mDdvnphVpXTkeBoHALNb4GSTwAk4zEXV2GVFV589yKMZO4IrFogN1yMuQhmHFDmRLbNUcebWXJgVCwDIIbdmQGFp+syt7NmTKhhp+n6tg/PWW29h3rx5WL58OZYvX45LLrkEf/3rX72uOXPmDDo6hCJeWq0WX331Fb75zW9ixowZuO+++zBjxgwcOHAAkZGR4muKiorwrW99CytXrsRVV12FsLAw/Otf/4JWK89+KeNFjqX3++xO1LQKxQnJghN4oow6MUhULpsV4BG3lUBzJhjIzUXF3JrR7o7z5NYMLCxNv88uVNpna02wqo/7tdlmbGws3nzzzRGv8QyUDQ0NxYcffjjq+xqNRrzwwgt44YUXJj1GOdJvwZHHogMISt7FA6ZQHRLoJB4UshPC0dRlxfmmbq+WGVLG3NgFAJieRAInGDDLX3WrBTaHC/oQaVcEXueuc3P97/cAAHKSyK0ZSAZmsJU3dXvVIAr0d0DdxGWImCreKB8Ljtkj/makLDrCf0xLiMDB8lZZWXDMFykwPVgUlZyFhgPC9FpYbE5Ut1pE62txqRlOFy8KCilhdThR6a5iPCMpcpSrCV9TWJAD88Uu/OvLerx/rA48ELQ0fWnLcWJImAWnrqMXvTZ5tKcgV0PwkWPsVn/mHW1UgUar4VC0y4xwg3AOZoHGUm92Wt4kWIsjjSFIlEntHqXx8PWCmOER3OrjJHBkSGy4HjFhOvC8dxCXlKEMquAjt95CVodTbCqbQy6qgMPiVpq6hHIU5c09QXU3jBVmLZ6RFEnW4iDxnxP1AARxE8zq4+SikinZCRE4XNWG803dmJMaFezhjIpowaGNKuAUuU/b354/BYDQhNDp4qHVcJJ2NVQ2W+B08XQSDyKFBTnYf74ZB8tb8ezO03DxwXM3jBXzRSFui9yawaG41IxNu8ziPGGiGAh8HBQJHJniKXCkjsPpEst2k4sq8LDMBhfPwxAiNN280NaL945dkHQDQjHAmOK2gsqqRZk4WN4KFy+PZqdi3BbF3wScoSx8AwOPAzl/SODIDHYaz05kqeLedQakeBqvbrXA7uQR6lH6nQgcngtMfIQe1m4binadxfayC5I+jVOAsTT4orJFvM/cDVKdM0C/MKZ5E3hYmv7A+cF+DnSaPgkcmcFO49+6LBVAf2yLp3KWGsw9NS0hHBqJBiYqnYGnKKmLG6B/3lCAcfAoLjVjy/4qaDUcnC4eP7gqU9JVgYUMKiFuizKoAs9Ih2vKoiJGhQX+vXesDoDQsfX5XWclHfhHPaikQWFBDrRuV4+Gk+YG5QnFbQUXz0PTTLdYWDgtTtJVgcW4LUMIkqIobkvtkMCRIYUFOVjr3pz67C4UeQR0SZFzFymDSgoUl5rhdBfWdPGQ5AbF8IzbImEcHDzdDbOSBYFzpqFL0lWBz7IA4ySK2yLIRSVb1i6bgedLzeABhGg4yYoboN+CQwIneLDT+A+uysTrn1WKrk5AmpacKnfcVphei1QTxW0FA093w0wPgQNIc84A/Sni5NYkALLgyJZit7gBAIeLl+xpnOd5qoETZDxdDb+6eQ7C9Fo4XTzuX5wpWVcDCzDOToiguC0JIAoct4VEqpg9LDgEQQJHhrAN66rpcQCExUeqG1V9Rx96bE6EaDhkxIUHeziqxNPVoNFwYvDlFZkxknU1nKNMGEkxK1motVXR3AOrQ7rV00ULDgUYEyAXlezwPI3Pm2LCZ+da4HJvYFJxObBU9sKCHHHByYwPh06rkWwqu5IZ+H89KzkSx2racbq+C4/dMDNIoxoZMwUYS4qkKAOijCHo7HPgXGM35qaagj2kQdgcLlS6K7uTMCYAEjiyw/M0Xt/RC0Aoof7Dq6eJzwcbz/gO1sdmekKEpFPZ1QQLGD3dIF13Q38NHDqJSwGO4zArOQqfV7biTEOXJAVOZUsPHC4eEYYQpJiMwR4OIQFI4MgMz9N4cpQR0WE6tFvsONfYHXTLDcOz5sq8KcJC2GaxSTqVXU3MShHcDacbOoM8kqFxunixQjedxKXDzORIUeBIEZZBRZWvCQbF4MgY4VQlnHBP1Utrs2KppF9d6AAAHKpoJXEjEdicqW3rRVefPcijESjyiCG70NYLq8MFfYgGabFhKC41o8htESSCh9QDjZnVbwa5NQk3JHBkzmz3afxUvfQWnUeuny7el3oqu5qIDtMjOUow4Z+VyGbF3JrFpWax1H52QgRe2n0Oz7ljuojgMmtAqrjU6G/RQG5NQoAEjsyZnSxdd8P//fcp8b6UU9nVyEzR8ieNzYpZ/J4rOYst+ysBAC6eJ7emhJjhnjP1HX3osEjP8tffZFOw4JDljyCBI3P6LTid4PngBxgzikvN2LyvAgCQOyVK0uXd1cisFBZoLB1hzETOp+ZmAIKlgMSNdIgy6sRmuVJxUzHLX1HJWVSwDKqkSDGhgSx/6oYEjszJSYqAhgPaLHY0dlmDPRwA/ansC7NiAQBzUqK8TugkcoIPs/xJzd1QWJADtiWRW1N6sPiWMxIRxmxdeb7UDIeLR7hei38eriHLHwGABI7sMeq0mJYgLDpfSyTQmKWysxRxllIq5R42aoO5qE7Xd0nK8vfcR2dkUaFbrcwUXeLSEcaFBTm45ZIUAIDF5pR8bz4icFCauAKYlRyJc43dOF3fhetmJgZ7OGIq+6LflgIA5qZGic/RoiMNshMiEKLh0GV14EJ7L6bGhAV7SCguNaP443MAgLhwPe7Nz5BM8UpCgAUaSyU4nTEtXqiSzgPQazU0XwgAZMFRBJ5xOFKhpduKhs4+cFx/3RVCOuhDNGJvMCm4qZhbs2C2INDnpEbh0aUzyK0pMWZ6FImUkuXvX8frAAgxOTani+YLAYAsOIpgtgQDRk/WCWPJjAtHhIGmmRSZmRyJ0w1dON3QhYLZSUEdC3Nr1nf0AQByp/S7NdnzRPARLX99DtR39CE1Ovid3p/fdRYVLRYAwN9/lI/PzjWT5Y8AQAJHETALzvmmHvTZnTDqtEEeUb/AmZNK1hupMis5Cu+jThKWP+bW/OaL+wAAuR6tAGiTkg76EA2mJYTj7MVunGnoCrrAKS41o2iXYK3RcEJCQ15GDACQyCHIRaUEkqOMMIXq4HTxOOduUhhsWMDzXBI4kkVqhdvsThdOuceSO4XmjVSRUqCx08Xjm5elAhAK/IXqhcMdJTQQAAkcRcBxnOimksJpHABO1gktGqTYlI8QYLVwypsFy1+wOdfYDZvDhUhjCNJjgx/0THjDiur1C+P+tSZYRfXWLZuBjDghwJi5NRmFBTlevfsI9UECRyHMktCpqsfqEItuzaEAY8kiNcvfCXffsjkpUdQsUYKwonosg+qMu3JwsIvqsXkzj6x+xAAoBkchzJFQJtXphk7wPJAYaUBCpCHYwyGGoMi9Ic1MjsTnFUKHaHYCLi41w+niA376ZXFbA0/ihDRgsSwstuV8YzeKSs7i+dLg1p0RBc5UmjeEN2TBUQizPFxUwU7f/LqO4m+kDjuN2xyCa4pl4AXzNM7cmhR/I10KC3KwbqkgZGxOV9DFTWNnHxq7rNBw/ckWBMEggaMQZiRFSqZlw0lR4NCJSqqwIMxjNYKoON3QJYqbYGxYLhffb8GheSNpHl06Q2ynoQ1yO42v3Nab7IQIhOnJIUF441eB09bWhlWrVsFkMsFkMmHVqlVob28f8TUcxw15+5//+R/xmmuvvXbQ83fffbc/P4qkKSo5i9c+KUeWu5qnp5sqGMF/lCIuDwoLcnD3gjQAwKfm5qD276lo6YHF5oRRpxFbjxDSpLjULLbTcAa5ncZXYvwNiWJiMH4VOPfccw+OHTuGnTt3YufOnTh27BhWrVo14mvq6+u9bq+//jo4jsPtt9/udd2aNWu8rnv11Vf9+VEkDXM3MLfCqXohCDAY7ga70yV2GiYXlfT59c1zxPs6bfBO40wUz06Jog7QEoatKbe6ez8lRBiCWmmaxd9Q3BYxFH6z6Z06dQo7d+7EwYMHsXDhQgDAn/70J+Tn5+PMmTOYOXPmkK9LTk72+vn999/Hddddh2nTpnk9HhYWNuhatTIw+O90Q2fQ3A3nm9ypvoYQpEmgvxExMpv3VYj37U7hNB4MkXOSbVTknpIsnmvKnVdMxb++rEerxYZHrp8etKJ6X1GAMTECfrPgHDhwACaTSRQ3ALBo0SKYTCbs379/TO9x8eJF/Pvf/8bq1asHPffWW28hPj4ec+fOxWOPPYauruCnRweTwoIcfGu+UPDq/WN1QXM3nLzgPomnRkFDJ3FJwzYstjnkZUQH7TR+ggKMJQ9rp1FYkIMUUyiSogxwungsyUkISlG9xq4+XOy0guOoHAUxNH6z4DQ0NCAxcXBn68TERDQ0NIzpPf785z8jMjIS3/nOd7we/973voesrCwkJyfjxIkT2LBhA44fP46SkpIh38dqtcJq7Q+87ewMfiq1P/j/bpmL98qEpnPBcjeI8Te04Egaz9N4anQoHvvHcQCc2NwSCNxpnOd5CkyXAQPLBlyWFo0PT17EsZq2IFn9hDmTnRCBcOp3RwzBuC04Tz755LCBwOx2+PBhABiyWBfP82Mu4vX666/je9/7HoxGo9fja9aswdKlS5Gbm4u7774b//znP7Fr1y4cPXp0yPfZuHGjGOhsMpmQlpY2zk8tD948WCXeZ+6GQFDkcer/up5VMBYETrAqnBIj43kavzw9GoBg7n/wmuyAn8YvtPei3WKHTsthRlJkwH4vMTkuSxN6PpVVtwfl91OAMTEa45a9Dz/88KgZS5mZmfjyyy9x8eLFQc81NTUhKWn0zsWffvopzpw5g3feeWfUay+//HLodDqYzWZcfvnlg57fsGED1q9fL/7c2dmpOJHDTuRzUqPwdV0nFmTFBOwkzoKceZ73qIFj8rISENLC8zSeFR+O6DAd2i12fF3fGfDT+An3SXxGUiT0IVS5Qi7MdwvjYzXtQfn9X1GAMTEK4xY48fHxiI+PH/W6/Px8dHR04PPPP8eCBQsAAIcOHUJHRwcWL1486us3b96MvLw8XHrppaNee/LkSdjtdqSkpAz5vMFggMGg3Iq6nkIiIdKADe9+BQ0XOHfDwCBnvVaDD082BL0IGDE2OI7D/LRo7D7ThKNVbbgsLdrvv5NVUi4syOkv8Jca3ErKxPiYN8UEDQfUd/ThYmcfkqKMo7/Ih4gZVJStSQyD345Ls2fPxo033og1a9bg4MGDOHjwINasWYNbbrnFK4Nq1qxZ2L59u9drOzs78Y9//AMPPPDAoPc9f/48nn76aRw+fBiVlZXYsWMH7rzzTsyfPx9XXXWVvz6OpPF0N1yRIZiNj9d04MfXBs7dUFiQI6aO2iVQ4ZQYH5enu90NATqNM6tfcanZo0VDVND7GhFjJ9wQIroUA+2mau62or6jDxwHzCULDjEMfo3Meuutt1BYWIjly5cDAG677Ta8+OKLXtecOXMGHR0dXo9t3boVPM/ju9/97qD31Ov1KC0txfPPP4/u7m6kpaXh5ptvxhNPPAGtVuu/DyNhPE+62QkRiDKGoLPPgVMBdjewExwPwYpD4kY+XO4Wxker2gLy+zytfuF64e/2ZF0ntn5RQ8JYRsxPj8bphi6U1bThxlz/lu3wtPox91RWfDgiDCFk9SOGxK8CJzY2Fm+++eaI1wzVN+mHP/whfvjDHw55fVpaGvbu3euT8SkRjYbD5Rkx2HOmCUeq2nDJ1OiA/e4PjgsZXFoNB5vTFbSaKsT4uWSqCRwnBPw2dvYhMQDuhsKCHPRYHXj1k3IAIHEjQ+anxeDtz2twLAAWHGb1AyC2ipg3hWL9iOGhiD4FwtxURwJ0GgeA//nwtNgD67OfXy/G/wSzjDsxdiKNOsx0uxuOVgdu3njG+5DVT35c5pGB529XOOuf9lzJWbx/7AIAoN1iC2qLEULakMBRIJcHWOAUl5rx0u7zAICMuDAkm4xeixGJHHkwPz3wab+vfiLMGw0H0epHyIfshAhEGEJgsTlx9qL/i62ydeVcUw8AYO/ZZhI3xLCQwFEgl06NhlbDob6jD3XtvX7/fU4Xjyszhc1xQWas+DhbjAJd4ZSYGKweTqAsOMWlZrGb+cvfyyNBLEO0Gg6XuCthB0oY35E3VbwfzP5phPQhgaNAwg0hmJ0iuBsCYcVZ5yFiFk6L83qusCCHAv9kArPgfFnbAZvD5dffxeImAIDjgIVZsWT1kyn99XACI4yf/OAkACEOJ5AFTQn5QQJHoVyRIVhSAiFwLDYHvqwVTuILs2JHuZqQKtPiw2EK1cHqcOF0g3/bmThdPG6eJ5QVmJUchZhwPQCy+skRVtE4EAX/ikvN+OhroYDsQ9dlkyAmRoQEjkIJZBzO0ap2OFw8Uk1GTI0J9fvvI/yDRsOJp3F/p4uvWzYD0WE6AMCiad6imKx+8qGo5CwOV7YCAMyN3ejqs4vP+bpNC7P6hRuEsgKLs+PJ6keMCAkchZLnFjhf13fCYnP49Xd9XtECQHBPjbXPGCFNWMG/owGIpzhQLsyb/AFuTUI+aDUcXv2kHJHGEPA8REuuPwo2Ol087l+ciR6rE/oQjbjGkdWPGA5qwapQpkSHIsVkRH1HH47XdCA/23+byMEK4QRH7il5U1RyFrVtFgBA2YB4Cl8XUmvs7EN5U487/oYEjlwZ2KblWE07jlS1+SV1e92yGfjLgUoAQikMo66/sCsFGhNDQRYcBdPvpmr12+/osztF3/sCEjiyRqvhsO2oUF+kprUXTe66Rv44jTPrzZyUKJjcripCnhQW5OCaGUJ/wt9/dMavdWk+O9cMALhq+uj9EAmCLDgKhJU0z0uPwb+/rPeKw/H1Sfx4TTtsDhcSIg3Iig/3yXsSwWHgafxodRvONHT5ZcM6SO4pRfHY8lnYe3YfeN5/qdtOF48D54V5s9iPFmlCOZAFR4GwkubnmroBCPEULhfvl5P4IQ/3FMXfyJ/CghzMmyJ0Z/7xm0f8dho/WC7MG3+6TonA8fHpi+J9f6Vun6zrQGefA5GGEMyjBpvEGCCBo0BY0N3fDlUjRMOho9eOp/510i+b1ecUf6M4fnh1NgDAxfunfUJDRx8qmnug4YArad7InuJSM4p2mZHrFsbz06L9ktX02bn+ZIYQLW1dxOjQLFEoTOQ43JkFfz5Q5XNxY3e6RPfXwAJ/hHzxrIHjj/YJB8qFOIrcKSZEGSn+Rs54NrosvF5YW5p7rFi3NMfnImf/eRZ/Q2sNMTYoBkfBFBbk4Hl3zA0H32QasPiewoIcfFnbgV67E7HheuQkRvg8vocIPKyvWEZsGKpaLViSEy/G5PhKHLM4ikUkimWP08WLB6ceqwP6EA1qWntx8yUp4DjOZ6nbVocTX7jr7SzOpgBjYmyQwFEwTHAAAA/gmf+cxs9XzJrUe7L4HgDQuc3EV2bG4IWPz4knOUKeeJ7GY8L1+PV7J9BjdYiF1ICJiRxPUQx4xN9MiyNRLHM8v7dwQwjyp8Vh79kmlJ5q9Km1+GhVO/rsLsRHGDAjKcJn70soG3JRKRTPzWpOiuAb/+Pe85M2GXtWDn3ni2oAgNXu8mtqKBEYPE/jy2YnAQDKatrx3QXpkyqkxkRxcakZF9p7Ud1qgVbD4XBVq8+D3ongUjA7EQBQerrRp+97wO2eWpxNxUSJsUMWHAXi5RcvyAEHoaJxVlyYT9wNhQU5sDtdeOHjcwCAPWebSNwoAM/TeLLJiEummvBlbQdKT12c9HwBhPTzk3VCfE9ChAEv7T5P80ZhXDczEcBJHKlqQ7vFhugw/YTeZ6DV7zO3W/Oq6WT1I8YOWXAUiOdJHABWzEsGANS29+In12X7xC8+PbHfTOyPTBsi+DArTsnXF0e5cnSY5e/Dkw0AgIbOPhI3CiQtNgwzkyLhdPHYe7Zpwu/jafXrtjpw3F1M9OzFbrL6EWOGBI4CWTdg45ieGInshHDYnTxmJEX65OTDmuhpOP9k2hDBZ9lcQeB8eq4ZPdbJ9zP74dXTxPshGv8UgyOCz/VuN9XHk3BTebrCf/XeV3C4eJhCddi8r4KEMTFmSOCohBW5KQCA/3zVMOn32rjjFCpbhJ5Fu9ZfQ918FcrMpEikxYbC5nDhU/PET+OM9X8/Lt53uPxTDI4IPgWzBIGz50wTHE7XhN+HiZz3yuoAAB29dhI3xLgggaMSbswV3FR7zjZOqrt4cakZr35SDgC4NC0a0xIivE5btGkpB47jsGy2MG8+mqSbqrjUjB1f1QMAzRcFU1RyFvvONSM6TIeOXrtXV/riUrNo+R0rq7+RJd4nqx8xXkjgqIS5qVGYGhOKPrsLe89M/DTudPFIjDQAAL4zf4r4ONu0fFX3ggg+RSVn0WW1AxDcDZ6n8fFsVizonXFn3lQSOQpFq+GwaZcZKSYjAKDU3cJhom1i1m4tE++T1Y8YLyRwVALHcVjhtuLsPDlxN9Wtl6agscuKEA2HWy9N9XqusCCHMhsUhFbD4R+Ha2HUadBuseOwu2r1eDcrp4sXm2ouzo5DWmwYABLFSoR9p6fquwAAH59qHJTVOVaKS80oOSXE8fziplkkiIlxQ2niKqGo5Cy6+gTX1MenGmF1OGEI0QIYX4fxd49eAABcOzMBseETSwEl5MHA7uIlX1/E5xWt496sHi3IwdX/sxsAsPKKtCF/B6EcCgty0Gd34uU952Fu7J6wuGHzTq/V4I68NHG98XVlbUK5kAVHJWg1HLZ+UYNwgxZdVgc+OycUzhrPadzl4vH+MSHg79vzp/p1vIQ0KCzIwa2XCAHqm/dVTGizOljegtq2XkQaQ8RYMELZ/OzGWWArioYbvxhxunjkpgoFSlfMSxbFDVn9iPFAAkclsIWhx+oEAOw80TAm03GRh0n4UEUrLrQLG1XB7MQJBQ0S8uOZOy4R708k0PPvh2sAALddmgqjTuvTsRHSpLjUDCZBXDzw2x2nxvX61UuycL6pBwDwvYUZXs+RK5wYKyRwVERhQQ7uyBMsL38/XDum07hnwa3tZbUAgJvnpeC1T8qp4JZK+N9PK8T7DhePTbtGFrWeorij147/nBBivlZekUaiWAWwg9O6pTm4IiMGAPDaJ+Xjip15r+wCeu1O5CRG4MrMGH8NlVA4FIOjMp65/RJsO1ILHmMzHXvGYejdzTVdPE+9p1QC26x+fE023jxUha4+BzbtMkPDDW/J8WzIGhuuh9XhwsykSOw504iiXWZqyKpgBlqFr8yMxT3/ewhajhsxdsazNQPP83jroNDn7nsL0/HCx+eoNQMxIciCozJe2n3Oy3T8+LYvR31NYUEObpybDJs7Tfjvh2tJ3KgAz83q5ytm4eHrpgMAIgwhI2azeKaAv/ixcE2yySCKG5o3ymVgm5j87DgszIqFk+dxyVTTsLEznpbiI1VtOHOxC0adBo1dVrIUExOGLDgqwnPDqm614J9HarH1ixokm4xYu3T401FNqwUHylvEn6n3lDoYuFndtzgTfzlQhQvtvfjG9LgRAz0LC3Jwob0X73whxN/sPdtM4kYFDLSycByHqTGhOFQBnKrvxMvfu9zr+YEZnM+VnMV/TkQCALITIvDyHmrISkwcsuCohIGm45gwHfQhwte/aZfZ6zTuGSdhdTjxk78dRUevUPBNp+Wo95RKGNjTzKjTIneKkNlyvKYD9+Z7B396zpuaVgt2eVQ/JlGsXjLiwgEAdiePl3afEx8fmMFZWJCDuxekiTV0TtZ1krghJoVfBc5vfvMbLF68GGFhYYiOjh7Ta3iex5NPPonU1FSEhobi2muvxcmTJ72usVqteOSRRxAfH4/w8HDcdtttqK2t9cMnUA4DT+ORRh1sDsHlZAjRoNvqQFHJWdzzp4Nei85v/n0KX9Z2AAAuT4+G+Tc3UcEtFTMnRRA4XVYHXvj4nBhQ7LlZdVjsuP+Nz9HSYwNAoljtFBbk4K4rhfpH73xRgyc/OCmuM55r0rGadrx75IL4OhLFxGTxq8Cx2Wy488478eMf/3jMr3n22Wfx3HPP4cUXX8QXX3yB5ORkLFu2DF1dXeI1a9euxfbt27F161bs27cP3d3duOWWW+B0Ov3xMRTBwNN4YUEO1rp/tjpc6Oy144vKVuw/34LF2XEoLMjBB8fr8JcDVeJrrp2ZKL6WRI46eXTpDDET7y8HKtHZa8dzJWfFzerBa7Lx4JtHxBTfKzJiSBQTeOb2S5ARFwYXD2zZX+m1zgDAl7XtWPnqATHOj0Qx4Qs4nuf9XjFpy5YtWLt2Ldrb20e8jud5pKamYu3atfj5z38OQLDWJCUl4ZlnnsGPfvQjdHR0ICEhAX/9619x1113AQDq6uqQlpaGHTt24IYbbhh1PJ2dnTCZTOjo6EBUVNSkP5+c+fm2L8U4CQDIjAtDZYsF312QjvePXYDFJojGoUzF46mATCiLa/9nt9hRnvHwddPR0NmHfx4RrKmXTDXhg4e/IT4/0ZL9hDI4VtOOb730mddjq6/Kwrcvn4Lb/7gfVrdF+eHrpuOxG2bSfCGGZDz7t6RicCoqKtDQ0IDly5eLjxkMBlxzzTXYv38/AODIkSOw2+1e16SmpiI3N1e8hhg7z9x+CTwTFNim9fbn1aK4Wbs0Z8gFhgpuqZc//2ABBua1vLj7nChuZqdEeokbgKrQqp1PzgpNfj3nzebPKnDLC/sGiRuALMXE5JFUFlVDg1AQLCkpyevxpKQkVFVVidfo9XrExMQMuoa9fiBWqxVWq1X8ubOz05fDljXFpWa4eKFCrcPFY1p8OKwOFy609wIQTMUjZVgR6uT9Y3XgIcwPu5NHdJgO7RYhEF2r4fCfR68e8nV0ElcnA60xj2/7Els9LMeAt7hhsPlCopiYCOO24Dz55JPgOG7E2+HDhyc1KI7zPhvyPD/osYGMdM3GjRthMpnEW1pa2pDXqQ3PRefcb4U4ifLmHmTECd2e2eZFpyfCE895w+JrmLgJ0XBwumjOEP0M5Wr63e2XYHG20GGeLdssq3MgZCkmJsq4LTgPP/ww7r777hGvyczMnNBgkpOFRnwNDQ1ISUkRH29sbBStOsnJybDZbGhra/Oy4jQ2NmLx4sVDvu+GDRuwfv168efOzk7Vi5yhFp3CghwcLG8RAwD/tmaRV1dfOn0To8VFDOxATnOGGJjBCQjziK0zV2bGelW/pjlD+IpxC5z4+HjEx8f7YyzIyspCcnIySkpKMH/+fABCJtbevXvxzDPPAADy8vKg0+lQUlKClStXAgDq6+tx4sQJPPvss0O+r8FggMFg8MuY5cpYFh2ANizCm4HzxlPwsOc9i7YBNGfUzkDry0gimeYM4Uv8GoNTXV2N1tZWVFdXw+l04tixYwCA6dOnIyIiAgAwa9YsbNy4Ed/+9rfBcRzWrl2L3/72t8jJyUFOTg5++9vfIiwsDPfccw8AwGQyYfXq1fjpT3+KuLg4xMbG4rHHHsO8efOwdOlSf34cRTGUyXco0QOQH5zoZ+C8oTlDjBeaM0Sg8Gua+P33348///nPgx7fvXs3rr32WmEAHIc33ngD999/PwAhluapp57Cq6++ira2NixcuBAvvfQScnNzxdf39fXhv//7v/G3v/0Nvb29KCgowMsvvzxmtxOliRMEQRCE/BjP/h2QOjhSgwQOQRAEQcgP2dbBIQiCIAiC8AUkcAiCIAiCUBwkcAiCIAiCUBwkcAiCIAiCUBwkcAiCIAiCUBwkcAiCIAiCUBwkcAiCIAiCUBwkcAiCIAiCUBwkcAiCIAiCUBx+7UUlVVjx5s7OziCPhCAIgiCIscL27bE0YVClwOnq6gKAMfeuIgiCIAhCOnR1dcFkMo14jSp7UblcLtTV1SEyMhIcx/n0vTs7O5GWloaamhpF9rlS+ucDlP8Z6fPJH6V/Rvp88sdfn5HneXR1dSE1NRUazchRNqq04Gg0GkydOtWvvyMqKkqxExdQ/ucDlP8Z6fPJH6V/Rvp88scfn3E0yw2DgowJgiAIglAcJHAIgiAIglAcJHB8jMFgwBNPPAGDwRDsofgFpX8+QPmfkT6f/FH6Z6TPJ3+k8BlVGWRMEARBEISyIQsOQRAEQRCKgwQOQRAEQRCKgwQOQRAEQRCKgwQOQRAEQRCKgwTOOPnNb36DxYsXIywsDNHR0UNeU11djVtvvRXh4eGIj49HYWEhbDbbiO9rtVrxyCOPID4+HuHh4bjttttQW1vrh08wPvbs2QOO44a8ffHFF8O+7v777x90/aJFiwI48rGTmZk5aKyPP/74iK/heR5PPvkkUlNTERoaimuvvRYnT54M0IjHR2VlJVavXo2srCyEhoYiOzsbTzzxxKhzUsrf4csvv4ysrCwYjUbk5eXh008/HfH6vXv3Ii8vD0ajEdOmTcMrr7wSoJGOn40bN+LKK69EZGQkEhMT8a1vfQtnzpwZ8TXD/Z2ePn06QKMeO08++eSgcSYnJ4/4Gjl9f8DQawrHcfjJT34y5PVS//4++eQT3HrrrUhNTQXHcXjvvfe8np/oerht2zbMmTMHBoMBc+bMwfbt2306bhI448Rms+HOO+/Ej3/84yGfdzqduPnmm9HT04N9+/Zh69at2LZtG37605+O+L5r167F9u3bsXXrVuzbtw/d3d245ZZb4HQ6/fExxszixYtRX1/vdXvggQeQmZmJK664YsTX3njjjV6v27FjR4BGPX6efvppr7H+6le/GvH6Z599Fs899xxefPFFfPHFF0hOTsayZcvEPmdS4vTp03C5XHj11Vdx8uRJFBUV4ZVXXsEvfvGLUV8rxe/wnXfewdq1a/HLX/4SZWVlWLJkCVasWIHq6uohr6+oqMBNN92EJUuWoKysDL/4xS9QWFiIbdu2BXjkY2Pv3r34yU9+goMHD6KkpAQOhwPLly9HT0/PqK89c+aM1/eVk5MTgBGPn7lz53qN86uvvhr2Wrl9fwDwxRdfeH2+kpISAMCdd9454uuk+v319PTg0ksvxYsvvjjk8xNZDw8cOIC77roLq1atwvHjx7Fq1SqsXLkShw4d8t3AeWJCvPHGG7zJZBr0+I4dO3iNRsNfuHBBfOztt9/mDQYD39HRMeR7tbe38zqdjt+6dav42IULF3iNRsPv3LnT52OfDDabjU9MTOSffvrpEa+77777+G9+85uBGdQkycjI4IuKisZ8vcvl4pOTk/nf/e534mN9fX28yWTiX3nlFT+M0Pc8++yzfFZW1ojXSPU7XLBgAf/ggw96PTZr1iz+8ccfH/L6n/3sZ/ysWbO8HvvRj37EL1q0yG9j9CWNjY08AH7v3r3DXrN7924eAN/W1ha4gU2QJ554gr/00kvHfL3cvz+e5/lHH32Uz87O5l0u15DPy+n7A8Bv375d/Hmi6+HKlSv5G2+80euxG264gb/77rt9Nlay4PiYAwcOIDc3F6mpqeJjN9xwA6xWK44cOTLka44cOQK73Y7ly5eLj6WmpiI3Nxf79+/3+5jHwwcffIDm5mbcf//9o167Z88eJCYmYsaMGVizZg0aGxv9P8AJ8swzzyAuLg6XXXYZfvOb34zovqmoqEBDQ4PX92UwGHDNNddI7vsajo6ODsTGxo56ndS+Q5vNhiNHjnj93wPA8uXLh/2/P3DgwKDrb7jhBhw+fBh2u91vY/UVHR0dADCm72v+/PlISUlBQUEBdu/e7e+hTRiz2YzU1FRkZWXh7rvvRnl5+bDXyv37s9lsePPNN/GDH/xg1ObOcvn+PJnoejjc9+rLNZQEjo9paGhAUlKS12MxMTHQ6/VoaGgY9jV6vR4xMTFejyclJQ37mmCxefNm3HDDDUhLSxvxuhUrVuCtt97Cxx9/jD/84Q/44osvcP3118NqtQZopGPn0UcfxdatW7F79248/PDD2LRpEx566KFhr2ffycDvWYrf11CcP38eL7zwAh588MERr5Pid9jc3Ayn0zmu//uh/iaTkpLgcDjQ3Nzst7H6Ap7nsX79enzjG99Abm7usNelpKTgtddew7Zt2/Duu+9i5syZKCgowCeffBLA0Y6NhQsX4i9/+Qs+/PBD/OlPf0JDQwMWL16MlpaWIa+X8/cHAO+99x7a29tHPBTK6fsbyETXw+G+V1+uoarsJj6QJ598Ek899dSI13zxxRejxpwwhlLpPM+Pqt598ZqxMpHPXFtbiw8//BB///vfR33/u+66S7yfm5uLK664AhkZGfj3v/+N73znOxMf+BgZz+dbt26d+Ngll1yCmJgY3HHHHaJVZzgGfjf+/L6GYiLfYV1dHW688UbceeedeOCBB0Z8bbC/w5EY7//9UNcP9bjUePjhh/Hll19i3759I143c+ZMzJw5U/w5Pz8fNTU1+P3vf4+rr77a38McFytWrBDvz5s3D/n5+cjOzsaf//xnrF+/fsjXyPX7A4RD4YoVK7ys+gOR0/c3HBNZD/29hpLAgbCI3H333SNek5mZOab3Sk5OHhQk1dbWBrvdPkiter7GZrOhra3Ny4rT2NiIxYsXj+n3jpeJfOY33ngDcXFxuO2228b9+1JSUpCRkQGz2Tzu106EyXynLFPo3LlzQwoclvHR0NCAlJQU8fHGxsZhv2N/MN7PWFdXh+uuuw75+fl47bXXxv37Av0dDkV8fDy0Wu2gU95I//fJyclDXh8SEjKigA02jzzyCD744AN88sknmDp16rhfv2jRIrz55pt+GJlvCQ8Px7x584adV3L9/gCgqqoKu3btwrvvvjvu18rl+5voejjc9+rLNZQEDoRFMz4+3ifvlZ+fj9/85jeor68Xv+yPPvoIBoMBeXl5Q74mLy8POp0OJSUlWLlyJQCgvr4eJ06cwLPPPuuTcQ1kvJ+Z53m88cYbuPfee6HT6cb9+1paWlBTU+P1B+BPJvOdlpWVAcCwY83KykJycjJKSkowf/58AIKffe/evXjmmWcmNuAJMJ7PeOHCBVx33XXIy8vDG2+8AY1m/N7pQH+HQ6HX65GXl4eSkhJ8+9vfFh8vKSnBN7/5zSFfk5+fj3/9619ej3300Ue44oorJjSX/Q3P83jkkUewfft27NmzB1lZWRN6n7KysqB+V2PFarXi1KlTWLJkyZDPy+378+SNN95AYmIibr755nG/Vi7f30TXw/z8fJSUlHhZ0D/66CPfHup9Fq6sEqqqqviysjL+qaee4iMiIviysjK+rKyM7+rq4nme5x0OB5+bm8sXFBTwR48e5Xft2sVPnTqVf/jhh8X3qK2t5WfOnMkfOnRIfOzBBx/kp06dyu/atYs/evQof/311/OXXnop73A4Av4Zh2LXrl08AP7rr78e8vmZM2fy7777Ls/zPN/V1cX/9Kc/5ffv389XVFTwu3fv5vPz8/kpU6bwnZ2dgRz2qOzfv59/7rnn+LKyMr68vJx/5513+NTUVP62227zus7z8/E8z//ud7/jTSYT/+677/JfffUV/93vfpdPSUmR3OfjeSEjb/r06fz111/P19bW8vX19eLNE7l8h1u3buV1Oh2/efNm/uuvv+bXrl3Lh4eH85WVlTzP8/zjjz/Or1q1Sry+vLycDwsL49etW8d//fXX/ObNm3mdTsf/85//DNZHGJEf//jHvMlk4vfs2eP1XVksFvGagZ+xqKiI3759O3/27Fn+xIkT/OOPP84D4Ldt2xaMjzAiP/3pT/k9e/bw5eXl/MGDB/lbbrmFj4yMVMz3x3A6nXx6ejr/85//fNBzcvv+urq6xL0OgLhmVlVV8Tw/tvVw1apVXpmOn332Ga/Vavnf/e53/KlTp/jf/e53fEhICH/w4EGfjZsEzji57777eACDbrt37xavqaqq4m+++WY+NDSUj42N5R9++GG+r69PfL6iomLQa3p7e/mHH36Yj42N5UNDQ/lbbrmFr66uDuAnG5nvfve7/OLFi4d9HgD/xhtv8DzP8xaLhV++fDmfkJDA63Q6Pj09nb/vvvsk9XkYR44c4RcuXMibTCbeaDTyM2fO5J944gm+p6fH6zrPz8fzQmrkE088wScnJ/MGg4G/+uqr+a+++irAox8bb7zxxpBzduD5Rk7f4UsvvcRnZGTwer2ev/zyy71SqO+77z7+mmuu8bp+z549/Pz583m9Xs9nZmbyf/zjHwM84rEz3HflOf8GfsZnnnmGz87O5o1GIx8TE8N/4xvf4P/9738HfvBj4K677uJTUlJ4nU7Hp6am8t/5znf4kydPis/L/ftjfPjhhzwA/syZM4Oek9v3x9LYB97uu+8+nufHth5ec8014vWMf/zjH/zMmTN5nU7Hz5o1y+eCjuN5d7QWQRAEQRCEQqA0cYIgCIIgFAcJHIIgCIIgFAcJHIIgCIIgFAcJHIIgCIIgFAcJHIIgCIIgFAcJHIIgCIIgFAcJHIIgCIIgFAcJHIIgCIIgFAcJHIIgCIIgFAcJHIIgCIIgFAcJHIIgCIIgFAcJHIIgCIIgFMf/D6TbNr/nUq9MAAAAAElFTkSuQmCC", "text/plain": [ "
    " ] }, "metadata": { "filenames": { - "image/png": "/Users/mhjensen/Teaching/MachineLearning/doc/LectureNotes/_build/jupyter_execute/week34_74_1.png" + "image/png": "/Users/mhjensen/Teaching/MachineLearning/doc/LectureNotes/_build/jupyter_execute/week34_73_1.png" } }, "output_type": "display_data" @@ -1641,7 +1530,7 @@ }, { "cell_type": "markdown", - "id": "a9bff117", + "id": "f23e1ca6", "metadata": { "editable": true }, @@ -1667,7 +1556,7 @@ { "cell_type": "code", "execution_count": 17, - "id": "9ce8cf97", + "id": "8789f2ba", "metadata": { "collapsed": false, "editable": true @@ -1759,7 +1648,7 @@ }, { "cell_type": "markdown", - "id": "98b2cebb", + "id": "e9f51a5f", "metadata": { "editable": true }, @@ -1773,7 +1662,7 @@ { "cell_type": "code", "execution_count": 18, - "id": "88a877c3", + "id": "16b329b9", "metadata": { "collapsed": false, "editable": true @@ -1858,7 +1747,7 @@ }, { "cell_type": "markdown", - "id": "0928de6c", + "id": "cd1876fb", "metadata": { "editable": true }, @@ -1869,7 +1758,7 @@ { "cell_type": "code", "execution_count": 19, - "id": "d93baec5", + "id": "5b7e1c04", "metadata": { "collapsed": false, "editable": true @@ -1895,7 +1784,7 @@ }, { "cell_type": "markdown", - "id": "7a5b03a4", + "id": "10f0bb9d", "metadata": { "editable": true }, @@ -1906,98 +1795,23 @@ { "cell_type": "code", "execution_count": 20, - "id": "2b5968bf", + "id": "190b1a89", "metadata": { "collapsed": false, "editable": true }, "outputs": [ { - "name": "stderr", - "output_type": "stream", - "text": [ - "/var/folders/td/3yk470mj5p931p9dtkk0y6jw0000gn/T/ipykernel_15510/1326197715.py:6: FutureWarning: The frame.append method is deprecated and will be removed from pandas in a future version. Use pandas.concat instead.\n", - " data_pandas=data_pandas.append(pd.DataFrame(new_hobbit, index=['Pippin']))\n" + "ename": "AttributeError", + "evalue": "'DataFrame' object has no attribute 'append'", + "output_type": "error", + "traceback": [ + "\u001b[0;31m---------------------------------------------------------------------------\u001b[0m", + "\u001b[0;31mAttributeError\u001b[0m Traceback (most recent call last)", + "\u001b[0;32m/var/folders/td/3yk470mj5p931p9dtkk0y6jw0000gn/T/ipykernel_12649/1326197715.py\u001b[0m in \u001b[0;36m?\u001b[0;34m()\u001b[0m\n\u001b[0;32m----> 6\u001b[0;31m new_hobbit = {'First Name': [\"Peregrin\"],\n\u001b[0m\u001b[1;32m 7\u001b[0m \u001b[0;34m'Last Name'\u001b[0m\u001b[0;34m:\u001b[0m \u001b[0;34m[\u001b[0m\u001b[0;34m\"Took\"\u001b[0m\u001b[0;34m]\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 8\u001b[0m \u001b[0;34m'Place of birth'\u001b[0m\u001b[0;34m:\u001b[0m \u001b[0;34m[\u001b[0m\u001b[0;34m\"Shire\"\u001b[0m\u001b[0;34m]\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 9\u001b[0m \u001b[0;34m'Date of Birth T.A.'\u001b[0m\u001b[0;34m:\u001b[0m \u001b[0;34m[\u001b[0m\u001b[0;36m2990\u001b[0m\u001b[0;34m]\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n", + "\u001b[0;32m~/miniforge3/envs/myenv/lib/python3.9/site-packages/pandas/core/generic.py\u001b[0m in \u001b[0;36m?\u001b[0;34m(self, name)\u001b[0m\n\u001b[1;32m 6200\u001b[0m \u001b[0;32mand\u001b[0m \u001b[0mname\u001b[0m \u001b[0;32mnot\u001b[0m \u001b[0;32min\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0m_accessors\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 6201\u001b[0m \u001b[0;32mand\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0m_info_axis\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0m_can_hold_identifiers_and_holds_name\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mname\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 6202\u001b[0m ):\n\u001b[1;32m 6203\u001b[0m \u001b[0;32mreturn\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m[\u001b[0m\u001b[0mname\u001b[0m\u001b[0;34m]\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m-> 6204\u001b[0;31m \u001b[0;32mreturn\u001b[0m \u001b[0mobject\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0m__getattribute__\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mself\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mname\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m", + "\u001b[0;31mAttributeError\u001b[0m: 'DataFrame' object has no attribute 'append'" ] - }, - { - "data": { - "text/html": [ - "
    \n", - "\n", - "\n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - "
    First NameLast NamePlace of birthDate of Birth T.A.
    FrodoFrodoBagginsShire2968
    BilboBilboBagginsShire2890
    AragornAragorn IIElessarEriador2931
    SamSamwiseGamgeeShire2980
    PippinPeregrinTookShire2990
    \n", - "
    " - ], - "text/plain": [ - " First Name Last Name Place of birth Date of Birth T.A.\n", - "Frodo Frodo Baggins Shire 2968\n", - "Bilbo Bilbo Baggins Shire 2890\n", - "Aragorn Aragorn II Elessar Eriador 2931\n", - "Sam Samwise Gamgee Shire 2980\n", - "Pippin Peregrin Took Shire 2990" - ] - }, - "metadata": {}, - "output_type": "display_data" } ], "source": [ @@ -2012,7 +1826,7 @@ }, { "cell_type": "markdown", - "id": "281789dd", + "id": "579fb43e", "metadata": { "editable": true }, @@ -2024,291 +1838,12 @@ { "cell_type": "code", "execution_count": 21, - "id": "226cafd5", + "id": "cb5f7e36", "metadata": { "collapsed": false, "editable": true }, - "outputs": [ - { - "data": { - "text/html": [ - "
    \n", - "\n", - "\n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - "
    01234
    0-1.7497650.3426801.153036-0.2524360.981321
    10.5142190.221180-1.070043-0.1894960.255001
    2-0.4580270.435163-0.5835950.8168470.672721
    3-0.104411-0.5312801.029733-0.438136-1.118318
    41.6189821.541605-0.251879-0.8424360.184519
    50.9370820.7310001.361556-0.3262380.055676
    60.222400-1.443217-0.7563520.8164540.750445
    7-0.4559471.189622-1.690617-1.356399-1.232435
    8-0.544439-0.6681720.007315-0.6129391.299748
    9-1.733096-0.9833100.357508-1.6135791.470714
    \n", - "
    " - ], - "text/plain": [ - " 0 1 2 3 4\n", - "0 -1.749765 0.342680 1.153036 -0.252436 0.981321\n", - "1 0.514219 0.221180 -1.070043 -0.189496 0.255001\n", - "2 -0.458027 0.435163 -0.583595 0.816847 0.672721\n", - "3 -0.104411 -0.531280 1.029733 -0.438136 -1.118318\n", - "4 1.618982 1.541605 -0.251879 -0.842436 0.184519\n", - "5 0.937082 0.731000 1.361556 -0.326238 0.055676\n", - "6 0.222400 -1.443217 -0.756352 0.816454 0.750445\n", - "7 -0.455947 1.189622 -1.690617 -1.356399 -1.232435\n", - "8 -0.544439 -0.668172 0.007315 -0.612939 1.299748\n", - "9 -1.733096 -0.983310 0.357508 -1.613579 1.470714" - ] - }, - "metadata": {}, - "output_type": "display_data" - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "0 -0.175300\n", - "1 0.083527\n", - "2 -0.044334\n", - "3 -0.399836\n", - "4 0.331939\n", - "dtype: float64\n", - "0 1.069584\n", - "1 0.965548\n", - "2 1.018232\n", - "3 0.793167\n", - "4 0.918992\n", - "dtype: float64\n" - ] - }, - { - "data": { - "text/html": [ - "
    \n", - "\n", - "\n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - "
    01234
    03.0616790.1174301.3294920.0637240.962990
    10.2644210.0489201.1449930.0359090.065026
    20.2097890.1893670.3405830.6672390.452553
    30.0109020.2822591.0603490.1919631.250636
    42.6211022.3765470.0634430.7096980.034047
    50.8781230.5343621.8538350.1064310.003100
    60.0494622.0828750.5720690.6665970.563167
    70.2078881.4152012.8581851.8398181.518895
    80.2964140.4464530.0000540.3756941.689345
    93.0036200.9668990.1278122.6036362.162999
    \n", - "
    " - ], - "text/plain": [ - " 0 1 2 3 4\n", - "0 3.061679 0.117430 1.329492 0.063724 0.962990\n", - "1 0.264421 0.048920 1.144993 0.035909 0.065026\n", - "2 0.209789 0.189367 0.340583 0.667239 0.452553\n", - "3 0.010902 0.282259 1.060349 0.191963 1.250636\n", - "4 2.621102 2.376547 0.063443 0.709698 0.034047\n", - "5 0.878123 0.534362 1.853835 0.106431 0.003100\n", - "6 0.049462 2.082875 0.572069 0.666597 0.563167\n", - "7 0.207888 1.415201 2.858185 1.839818 1.518895\n", - "8 0.296414 0.446453 0.000054 0.375694 1.689345\n", - "9 3.003620 0.966899 0.127812 2.603636 2.162999" - ] - }, - "metadata": {}, - "output_type": "display_data" - } - ], + "outputs": [], "source": [ "import numpy as np\n", "import pandas as pd\n", @@ -2327,7 +1862,7 @@ }, { "cell_type": "markdown", - "id": "34d1241d", + "id": "51e35da5", "metadata": { "editable": true }, @@ -2338,200 +1873,12 @@ { "cell_type": "code", "execution_count": 22, - "id": "66de0f40", + "id": "6754efdc", "metadata": { "collapsed": false, "editable": true }, - "outputs": [ - { - "data": { - "text/html": [ - "
    \n", - "\n", - "\n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - "
    FirstSecondThirdFourthFifth
    0-1.7497650.3426801.153036-0.2524360.981321
    10.5142190.221180-1.070043-0.1894960.255001
    2-0.4580270.435163-0.5835950.8168470.672721
    3-0.104411-0.5312801.029733-0.438136-1.118318
    41.6189821.541605-0.251879-0.8424360.184519
    50.9370820.7310001.361556-0.3262380.055676
    60.222400-1.443217-0.7563520.8164540.750445
    7-0.4559471.189622-1.690617-1.356399-1.232435
    8-0.544439-0.6681720.007315-0.6129391.299748
    9-1.733096-0.9833100.357508-1.6135791.470714
    \n", - "
    " - ], - "text/plain": [ - " First Second Third Fourth Fifth\n", - "0 -1.749765 0.342680 1.153036 -0.252436 0.981321\n", - "1 0.514219 0.221180 -1.070043 -0.189496 0.255001\n", - "2 -0.458027 0.435163 -0.583595 0.816847 0.672721\n", - "3 -0.104411 -0.531280 1.029733 -0.438136 -1.118318\n", - "4 1.618982 1.541605 -0.251879 -0.842436 0.184519\n", - "5 0.937082 0.731000 1.361556 -0.326238 0.055676\n", - "6 0.222400 -1.443217 -0.756352 0.816454 0.750445\n", - "7 -0.455947 1.189622 -1.690617 -1.356399 -1.232435\n", - "8 -0.544439 -0.668172 0.007315 -0.612939 1.299748\n", - "9 -1.733096 -0.983310 0.357508 -1.613579 1.470714" - ] - }, - "metadata": {}, - "output_type": "display_data" - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "0.08352721390288316\n", - "\n", - "Int64Index: 10 entries, 0 to 9\n", - "Data columns (total 5 columns):\n", - " # Column Non-Null Count Dtype \n", - "--- ------ -------------- ----- \n", - " 0 First 10 non-null float64\n", - " 1 Second 10 non-null float64\n", - " 2 Third 10 non-null float64\n", - " 3 Fourth 10 non-null float64\n", - " 4 Fifth 10 non-null float64\n", - "dtypes: float64(5)\n", - "memory usage: 480.0 bytes\n", - "None\n", - " First Second Third Fourth Fifth\n", - "count 10.000000 10.000000 10.000000 10.000000 10.000000\n", - "mean -0.175300 0.083527 -0.044334 -0.399836 0.331939\n", - "std 1.069584 0.965548 1.018232 0.793167 0.918992\n", - "min -1.749765 -1.443217 -1.690617 -1.613579 -1.232435\n", - "25% -0.522836 -0.633949 -0.713163 -0.785061 0.087887\n", - "50% -0.280179 0.281930 -0.122282 -0.382187 0.463861\n", - "75% 0.441264 0.657041 0.861676 -0.205231 0.923602\n", - "max 1.618982 1.541605 1.361556 0.816847 1.470714\n" - ] - }, - { - "data": { - "image/png": "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\n", - "text/plain": [ - "
    " - ] - }, - "metadata": { - "filenames": { - "image/png": "/Users/mhjensen/Teaching/MachineLearning/doc/LectureNotes/_build/jupyter_execute/week34_86_2.png" - } - }, - "output_type": "display_data" - }, - { - "data": { - "image/png": "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\n", - "text/plain": [ - "
    " - ] - }, - "metadata": { - "filenames": { - "image/png": "/Users/mhjensen/Teaching/MachineLearning/doc/LectureNotes/_build/jupyter_execute/week34_86_3.png" - } - }, - "output_type": "display_data" - } - ], + "outputs": [], "source": [ "df.columns = ['First', 'Second', 'Third', 'Fourth', 'Fifth']\n", "df.index = np.arange(10)\n", @@ -2555,7 +1902,7 @@ }, { "cell_type": "markdown", - "id": "fce1b00d", + "id": "f1750baf", "metadata": { "editable": true }, @@ -2566,28 +1913,12 @@ { "cell_type": "code", "execution_count": 23, - "id": "b31ec8b2", + "id": "4069afcc", "metadata": { "collapsed": false, "editable": true }, - "outputs": [ - { - "name": "stdout", - "output_type": "stream", - "text": [ - "[[ 0 1 2 3]\n", - " [ 4 5 6 7]\n", - " [ 8 9 10 11]\n", - " [12 13 14 15]]\n", - " 0 1 2 3\n", - "0 0 1 2 3\n", - "1 4 5 6 7\n", - "2 8 9 10 11\n", - "3 12 13 14 15\n" - ] - } - ], + "outputs": [], "source": [ "b = np.arange(16).reshape((4,4))\n", "print(b)\n", @@ -2597,7 +1928,7 @@ }, { "cell_type": "markdown", - "id": "399b4f0b", + "id": "dc04e1ff", "metadata": { "editable": true }, @@ -2614,7 +1945,7 @@ }, { "cell_type": "markdown", - "id": "b3c66ed4", + "id": "ff884c05", "metadata": { "editable": true }, @@ -2645,7 +1976,7 @@ }, { "cell_type": "markdown", - "id": "b7ec1f01", + "id": "10424430", "metadata": { "editable": true }, @@ -2657,7 +1988,7 @@ }, { "cell_type": "markdown", - "id": "5c4c6423", + "id": "d4456d18", "metadata": { "editable": true }, @@ -2685,27 +2016,12 @@ { "cell_type": "code", "execution_count": 24, - "id": "b026b228", + "id": "570b320d", "metadata": { "collapsed": false, "editable": true }, - "outputs": [ - { - "data": { - "image/png": "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\n", - "text/plain": [ - "
    " - ] - }, - "metadata": { - "filenames": { - "image/png": "/Users/mhjensen/Teaching/MachineLearning/doc/LectureNotes/_build/jupyter_execute/week34_93_0.png" - } - }, - "output_type": "display_data" - } - ], + "outputs": [], "source": [ "# Importing various packages\n", "import numpy as np\n", @@ -2730,7 +2046,7 @@ }, { "cell_type": "markdown", - "id": "121762a4", + "id": "a6e493ad", "metadata": { "editable": true }, @@ -2747,7 +2063,7 @@ }, { "cell_type": "markdown", - "id": "60728127", + "id": "8f1725d2", "metadata": { "editable": true }, @@ -2759,7 +2075,7 @@ }, { "cell_type": "markdown", - "id": "acf5b63f", + "id": "8df5914b", "metadata": { "editable": true }, @@ -2780,7 +2096,7 @@ }, { "cell_type": "markdown", - "id": "40040656", + "id": "7648e110", "metadata": { "editable": true }, @@ -2793,7 +2109,7 @@ }, { "cell_type": "markdown", - "id": "86948166", + "id": "17c3f9d8", "metadata": { "editable": true }, @@ -2824,7 +2140,7 @@ }, { "cell_type": "markdown", - "id": "2c7af90a", + "id": "0cb0e3fa", "metadata": { "editable": true }, @@ -2836,7 +2152,7 @@ }, { "cell_type": "markdown", - "id": "aebc9af3", + "id": "00fe7e8c", "metadata": { "editable": true }, @@ -2854,27 +2170,12 @@ { "cell_type": "code", "execution_count": 25, - "id": "eaa61d49", + "id": "7a17d6fe", "metadata": { "collapsed": false, "editable": true }, - "outputs": [ - { - "data": { - "image/png": "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\n", - "text/plain": [ - "
    " - ] - }, - "metadata": { - "filenames": { - "image/png": "/Users/mhjensen/Teaching/MachineLearning/doc/LectureNotes/_build/jupyter_execute/week34_101_0.png" - } - }, - "output_type": "display_data" - } - ], + "outputs": [], "source": [ "import numpy as np\n", "import matplotlib.pyplot as plt\n", @@ -2896,7 +2197,7 @@ }, { "cell_type": "markdown", - "id": "f964fde3", + "id": "8f557979", "metadata": { "editable": true }, @@ -2918,41 +2219,12 @@ { "cell_type": "code", "execution_count": 26, - "id": "c7fe9388", + "id": "a5e9ee5a", "metadata": { "collapsed": false, "editable": true }, - "outputs": [ - { - "name": "stdout", - "output_type": "stream", - "text": [ - "The intercept alpha: \n", - " [2.18780801]\n", - "Coefficient beta : \n", - " [[4.72228205]]\n", - "Mean squared error: 0.37\n", - "Variance score: 0.83\n", - "Mean squared log error: 0.01\n", - "Mean absolute error: 0.47\n" - ] - }, - { - "data": { - "image/png": "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\n", - "text/plain": [ - "
    " - ] - }, - "metadata": { - "filenames": { - "image/png": "/Users/mhjensen/Teaching/MachineLearning/doc/LectureNotes/_build/jupyter_execute/week34_103_1.png" - } - }, - "output_type": "display_data" - } - ], + "outputs": [], "source": [ "import numpy as np \n", "import matplotlib.pyplot as plt \n", @@ -2985,7 +2257,7 @@ }, { "cell_type": "markdown", - "id": "14ad007a", + "id": "a2b45b0b", "metadata": { "editable": true }, @@ -2996,7 +2268,7 @@ }, { "cell_type": "markdown", - "id": "7dc68b06", + "id": "97da0991", "metadata": { "editable": true }, @@ -3009,7 +2281,7 @@ }, { "cell_type": "markdown", - "id": "471f97ed", + "id": "6664f912", "metadata": { "editable": true }, @@ -3030,7 +2302,7 @@ }, { "cell_type": "markdown", - "id": "65a80e19", + "id": "4ca74414", "metadata": { "editable": true }, @@ -3042,7 +2314,7 @@ }, { "cell_type": "markdown", - "id": "37e1d624", + "id": "9e1d8766", "metadata": { "editable": true }, @@ -3052,7 +2324,7 @@ }, { "cell_type": "markdown", - "id": "a81b3061", + "id": "4605a6c5", "metadata": { "editable": true }, @@ -3064,7 +2336,7 @@ }, { "cell_type": "markdown", - "id": "792fa6a1", + "id": "882cab00", "metadata": { "editable": true }, @@ -3076,7 +2348,7 @@ }, { "cell_type": "markdown", - "id": "2f6df05c", + "id": "7d365176", "metadata": { "editable": true }, @@ -3088,7 +2360,7 @@ }, { "cell_type": "markdown", - "id": "9eb85874", + "id": "ed69759f", "metadata": { "editable": true }, @@ -3099,7 +2371,7 @@ }, { "cell_type": "markdown", - "id": "a98d9555", + "id": "33745626", "metadata": { "editable": true }, @@ -3111,7 +2383,7 @@ }, { "cell_type": "markdown", - "id": "6766ecc9", + "id": "049e0384", "metadata": { "editable": true }, @@ -3133,7 +2405,7 @@ }, { "cell_type": "markdown", - "id": "fb3a9871", + "id": "5a9fe56d", "metadata": { "editable": true }, @@ -3145,7 +2417,7 @@ }, { "cell_type": "markdown", - "id": "57226a58", + "id": "be3f1edc", "metadata": { "editable": true }, @@ -3158,7 +2430,7 @@ }, { "cell_type": "markdown", - "id": "b333e60b", + "id": "39a78b9e", "metadata": { "editable": true }, @@ -3175,7 +2447,7 @@ }, { "cell_type": "markdown", - "id": "1adb10e6", + "id": "8c035b2b", "metadata": { "editable": true }, @@ -3187,7 +2459,7 @@ }, { "cell_type": "markdown", - "id": "77592d4e", + "id": "12c6c509", "metadata": { "editable": true }, @@ -3197,7 +2469,7 @@ }, { "cell_type": "markdown", - "id": "ba90405f", + "id": "81cb4b33", "metadata": { "editable": true }, @@ -3209,7 +2481,7 @@ }, { "cell_type": "markdown", - "id": "db7cef69", + "id": "f1aec311", "metadata": { "editable": true }, @@ -3219,7 +2491,7 @@ }, { "cell_type": "markdown", - "id": "e12b557f", + "id": "3f4f90ea", "metadata": { "editable": true }, @@ -3231,7 +2503,7 @@ }, { "cell_type": "markdown", - "id": "6f5462e0", + "id": "5535c1ab", "metadata": { "editable": true }, @@ -3241,7 +2513,7 @@ }, { "cell_type": "markdown", - "id": "0247179e", + "id": "b3efd5ad", "metadata": { "editable": true }, @@ -3253,7 +2525,7 @@ }, { "cell_type": "markdown", - "id": "cb6e7ad5", + "id": "a6d81840", "metadata": { "editable": true }, @@ -3269,7 +2541,7 @@ }, { "cell_type": "markdown", - "id": "b60eb119", + "id": "f69f2188", "metadata": { "editable": true }, @@ -3281,7 +2553,7 @@ }, { "cell_type": "markdown", - "id": "b38eb451", + "id": "cf70b128", "metadata": { "editable": true }, @@ -3292,7 +2564,7 @@ }, { "cell_type": "markdown", - "id": "d67cf525", + "id": "4bfa00ef", "metadata": { "editable": true }, @@ -3304,7 +2576,7 @@ }, { "cell_type": "markdown", - "id": "2f8449b2", + "id": "4750b7cb", "metadata": { "editable": true }, @@ -3318,7 +2590,7 @@ }, { "cell_type": "markdown", - "id": "55ca6490", + "id": "cc94773e", "metadata": { "editable": true }, @@ -3330,7 +2602,7 @@ }, { "cell_type": "markdown", - "id": "e716655b", + "id": "48a29815", "metadata": { "editable": true }, @@ -3355,7 +2627,7 @@ }, { "cell_type": "markdown", - "id": "fa63a9de", + "id": "2be22cb2", "metadata": { "editable": true }, @@ -3372,7 +2644,7 @@ { "cell_type": "code", "execution_count": 27, - "id": "cca448dd", + "id": "57ce58c1", "metadata": { "collapsed": false, "editable": true @@ -3416,7 +2688,7 @@ }, { "cell_type": "markdown", - "id": "aa35aba5", + "id": "856d936e", "metadata": { "editable": true }, @@ -3427,7 +2699,7 @@ { "cell_type": "code", "execution_count": 28, - "id": "c854893a", + "id": "f00c1cc8", "metadata": { "collapsed": false, "editable": true @@ -3449,7 +2721,7 @@ }, { "cell_type": "markdown", - "id": "74b3f235", + "id": "01f32685", "metadata": { "editable": true }, @@ -3466,23 +2738,12 @@ { "cell_type": "code", "execution_count": 29, - "id": "92e8847b", + "id": "c00626c0", "metadata": { "collapsed": false, "editable": true }, - "outputs": [ - { - "data": { - "text/plain": [ - "' \\nThis is taken from the data file of the mass 2016 evaluation. \\nAll files are 3436 lines long with 124 character per line. \\n Headers are 39 lines long. \\n col 1 : Fortran character control: 1 = page feed 0 = line feed \\n format : a1,i3,i5,i5,i5,1x,a3,a4,1x,f13.5,f11.5,f11.3,f9.3,1x,a2,f11.3,f9.3,1x,i3,1x,f12.5,f11.5 \\n These formats are reflected in the pandas widths variable below, see the statement \\n widths=(1,3,5,5,5,1,3,4,1,13,11,11,9,1,2,11,9,1,3,1,12,11,1), \\n Pandas has also a variable header, with length 39 in this case. \\n'" - ] - }, - "execution_count": 29, - "metadata": {}, - "output_type": "execute_result" - } - ], + "outputs": [], "source": [ "\"\"\" \n", "This is taken from the data file of the mass 2016 evaluation. \n", @@ -3498,7 +2759,7 @@ }, { "cell_type": "markdown", - "id": "8cbce288", + "id": "e3ac89b4", "metadata": { "editable": true }, @@ -3512,26 +2773,12 @@ { "cell_type": "code", "execution_count": 30, - "id": "b4398581", + "id": "292ced26", "metadata": { "collapsed": false, "editable": true }, - "outputs": [ - { - "ename": "ValueError", - "evalue": "Length of colspecs must match length of names", - "output_type": "error", - "traceback": [ - "\u001b[0;31m---------------------------------------------------------------------------\u001b[0m", - "\u001b[0;31mValueError\u001b[0m Traceback (most recent call last)", - "Input \u001b[0;32mIn [30]\u001b[0m, in \u001b[0;36m\u001b[0;34m()\u001b[0m\n\u001b[1;32m 1\u001b[0m \u001b[38;5;66;03m# Read the experimental data with Pandas\u001b[39;00m\n\u001b[0;32m----> 2\u001b[0m Masses \u001b[38;5;241m=\u001b[39m \u001b[43mpd\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mread_fwf\u001b[49m\u001b[43m(\u001b[49m\u001b[43minfile\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43musecols\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43m(\u001b[49m\u001b[38;5;241;43m2\u001b[39;49m\u001b[43m,\u001b[49m\u001b[38;5;241;43m3\u001b[39;49m\u001b[43m,\u001b[49m\u001b[38;5;241;43m4\u001b[39;49m\u001b[43m,\u001b[49m\u001b[38;5;241;43m6\u001b[39;49m\u001b[43m,\u001b[49m\u001b[38;5;241;43m11\u001b[39;49m\u001b[43m)\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 3\u001b[0m \u001b[43m \u001b[49m\u001b[43mnames\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43m(\u001b[49m\u001b[38;5;124;43m'\u001b[39;49m\u001b[38;5;124;43mN\u001b[39;49m\u001b[38;5;124;43m'\u001b[39;49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;124;43m'\u001b[39;49m\u001b[38;5;124;43mZ\u001b[39;49m\u001b[38;5;124;43m'\u001b[39;49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;124;43m'\u001b[39;49m\u001b[38;5;124;43mA\u001b[39;49m\u001b[38;5;124;43m'\u001b[39;49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;124;43m'\u001b[39;49m\u001b[38;5;124;43mElement\u001b[39;49m\u001b[38;5;124;43m'\u001b[39;49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;124;43m'\u001b[39;49m\u001b[38;5;124;43mEbinding\u001b[39;49m\u001b[38;5;124;43m'\u001b[39;49m\u001b[43m)\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 4\u001b[0m \u001b[43m \u001b[49m\u001b[43mwidths\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43m(\u001b[49m\u001b[38;5;241;43m1\u001b[39;49m\u001b[43m,\u001b[49m\u001b[38;5;241;43m3\u001b[39;49m\u001b[43m,\u001b[49m\u001b[38;5;241;43m5\u001b[39;49m\u001b[43m,\u001b[49m\u001b[38;5;241;43m5\u001b[39;49m\u001b[43m,\u001b[49m\u001b[38;5;241;43m5\u001b[39;49m\u001b[43m,\u001b[49m\u001b[38;5;241;43m1\u001b[39;49m\u001b[43m,\u001b[49m\u001b[38;5;241;43m3\u001b[39;49m\u001b[43m,\u001b[49m\u001b[38;5;241;43m4\u001b[39;49m\u001b[43m,\u001b[49m\u001b[38;5;241;43m1\u001b[39;49m\u001b[43m,\u001b[49m\u001b[38;5;241;43m13\u001b[39;49m\u001b[43m,\u001b[49m\u001b[38;5;241;43m11\u001b[39;49m\u001b[43m,\u001b[49m\u001b[38;5;241;43m11\u001b[39;49m\u001b[43m,\u001b[49m\u001b[38;5;241;43m9\u001b[39;49m\u001b[43m,\u001b[49m\u001b[38;5;241;43m1\u001b[39;49m\u001b[43m,\u001b[49m\u001b[38;5;241;43m2\u001b[39;49m\u001b[43m,\u001b[49m\u001b[38;5;241;43m11\u001b[39;49m\u001b[43m,\u001b[49m\u001b[38;5;241;43m9\u001b[39;49m\u001b[43m,\u001b[49m\u001b[38;5;241;43m1\u001b[39;49m\u001b[43m,\u001b[49m\u001b[38;5;241;43m3\u001b[39;49m\u001b[43m,\u001b[49m\u001b[38;5;241;43m1\u001b[39;49m\u001b[43m,\u001b[49m\u001b[38;5;241;43m12\u001b[39;49m\u001b[43m,\u001b[49m\u001b[38;5;241;43m11\u001b[39;49m\u001b[43m,\u001b[49m\u001b[38;5;241;43m1\u001b[39;49m\u001b[43m)\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 5\u001b[0m \u001b[43m \u001b[49m\u001b[43mheader\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[38;5;241;43m39\u001b[39;49m\u001b[43m,\u001b[49m\n\u001b[1;32m 6\u001b[0m \u001b[43m \u001b[49m\u001b[43mindex_col\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[38;5;28;43;01mFalse\u001b[39;49;00m\u001b[43m)\u001b[49m\n\u001b[1;32m 8\u001b[0m \u001b[38;5;66;03m# Extrapolated values are indicated by '#' in place of the decimal place, so\u001b[39;00m\n\u001b[1;32m 9\u001b[0m \u001b[38;5;66;03m# the Ebinding column won't be numeric. Coerce to float and drop these entries.\u001b[39;00m\n\u001b[1;32m 10\u001b[0m Masses[\u001b[38;5;124m'\u001b[39m\u001b[38;5;124mEbinding\u001b[39m\u001b[38;5;124m'\u001b[39m] \u001b[38;5;241m=\u001b[39m pd\u001b[38;5;241m.\u001b[39mto_numeric(Masses[\u001b[38;5;124m'\u001b[39m\u001b[38;5;124mEbinding\u001b[39m\u001b[38;5;124m'\u001b[39m], errors\u001b[38;5;241m=\u001b[39m\u001b[38;5;124m'\u001b[39m\u001b[38;5;124mcoerce\u001b[39m\u001b[38;5;124m'\u001b[39m)\n", - "File \u001b[0;32m~/miniforge3/envs/myenv/lib/python3.9/site-packages/pandas/util/_decorators.py:311\u001b[0m, in \u001b[0;36mdeprecate_nonkeyword_arguments..decorate..wrapper\u001b[0;34m(*args, **kwargs)\u001b[0m\n\u001b[1;32m 305\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m \u001b[38;5;28mlen\u001b[39m(args) \u001b[38;5;241m>\u001b[39m num_allow_args:\n\u001b[1;32m 306\u001b[0m warnings\u001b[38;5;241m.\u001b[39mwarn(\n\u001b[1;32m 307\u001b[0m msg\u001b[38;5;241m.\u001b[39mformat(arguments\u001b[38;5;241m=\u001b[39marguments),\n\u001b[1;32m 308\u001b[0m \u001b[38;5;167;01mFutureWarning\u001b[39;00m,\n\u001b[1;32m 309\u001b[0m stacklevel\u001b[38;5;241m=\u001b[39mstacklevel,\n\u001b[1;32m 310\u001b[0m )\n\u001b[0;32m--> 311\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[43mfunc\u001b[49m\u001b[43m(\u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43margs\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43mkwargs\u001b[49m\u001b[43m)\u001b[49m\n", - "File \u001b[0;32m~/miniforge3/envs/myenv/lib/python3.9/site-packages/pandas/io/parsers/readers.py:871\u001b[0m, in \u001b[0;36mread_fwf\u001b[0;34m(filepath_or_buffer, colspecs, widths, infer_nrows, **kwds)\u001b[0m\n\u001b[1;32m 869\u001b[0m len_index \u001b[38;5;241m=\u001b[39m \u001b[38;5;28mlen\u001b[39m(index_col)\n\u001b[1;32m 870\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m \u001b[38;5;28mlen\u001b[39m(names) \u001b[38;5;241m+\u001b[39m len_index \u001b[38;5;241m!=\u001b[39m \u001b[38;5;28mlen\u001b[39m(colspecs):\n\u001b[0;32m--> 871\u001b[0m \u001b[38;5;28;01mraise\u001b[39;00m \u001b[38;5;167;01mValueError\u001b[39;00m(\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mLength of colspecs must match length of names\u001b[39m\u001b[38;5;124m\"\u001b[39m)\n\u001b[1;32m 873\u001b[0m kwds[\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mcolspecs\u001b[39m\u001b[38;5;124m\"\u001b[39m] \u001b[38;5;241m=\u001b[39m colspecs\n\u001b[1;32m 874\u001b[0m kwds[\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124minfer_nrows\u001b[39m\u001b[38;5;124m\"\u001b[39m] \u001b[38;5;241m=\u001b[39m infer_nrows\n", - "\u001b[0;31mValueError\u001b[0m: Length of colspecs must match length of names" - ] - } - ], + "outputs": [], "source": [ "# Read the experimental data with Pandas\n", "Masses = pd.read_fwf(infile, usecols=(2,3,4,6,11),\n", @@ -3555,7 +2802,7 @@ }, { "cell_type": "markdown", - "id": "0f21a73f", + "id": "b21b5f18", "metadata": { "editable": true }, @@ -3575,7 +2822,7 @@ { "cell_type": "code", "execution_count": 31, - "id": "491e38a4", + "id": "18c931f7", "metadata": { "collapsed": false, "editable": true @@ -3592,7 +2839,7 @@ }, { "cell_type": "markdown", - "id": "07ac2cd3", + "id": "bf1a1139", "metadata": { "editable": true }, @@ -3604,7 +2851,7 @@ { "cell_type": "code", "execution_count": 32, - "id": "0462ebdd", + "id": "0c1a4a2d", "metadata": { "collapsed": false, "editable": true @@ -3622,7 +2869,7 @@ }, { "cell_type": "markdown", - "id": "66a31f58", + "id": "b1b537e6", "metadata": { "editable": true }, @@ -3633,7 +2880,7 @@ { "cell_type": "code", "execution_count": 33, - "id": "7d4bf033", + "id": "ef679107", "metadata": { "collapsed": false, "editable": true @@ -3646,7 +2893,7 @@ }, { "cell_type": "markdown", - "id": "3b9f86de", + "id": "718927c7", "metadata": { "editable": true }, @@ -3658,7 +2905,7 @@ { "cell_type": "code", "execution_count": 34, - "id": "b12b4d19", + "id": "ea124a61", "metadata": { "collapsed": false, "editable": true @@ -3689,7 +2936,7 @@ }, { "cell_type": "markdown", - "id": "4cf1be8b", + "id": "9b3a0eeb", "metadata": { "editable": true }, @@ -3703,7 +2950,7 @@ { "cell_type": "code", "execution_count": 35, - "id": "e80600eb", + "id": "1994899a", "metadata": { "collapsed": false, "editable": true @@ -3714,36 +2961,41 @@ "from sklearn.metrics import accuracy_score\n", "import seaborn as sns\n", "\n", + "\n", "X_train = X\n", "Y_train = Energies\n", - "n_hidden_neurons = 100\n", + "n_hidden_neurons = 50\n", "epochs = 100\n", "# store models for later use\n", - "eta_vals = np.logspace(-5, 1, 7)\n", - "lmbd_vals = np.logspace(-5, 1, 7)\n", + "eta_vals = np.logspace(-3, 0, 4)\n", + "lmbd_vals = np.logspace(-3, 0, 4)\n", "# store the models for later use\n", "DNN_scikit = np.zeros((len(eta_vals), len(lmbd_vals)), dtype=object)\n", "train_accuracy = np.zeros((len(eta_vals), len(lmbd_vals)))\n", "sns.set()\n", "for i, eta in enumerate(eta_vals):\n", " for j, lmbd in enumerate(lmbd_vals):\n", - " dnn = MLPRegressor(hidden_layer_sizes=(n_hidden_neurons), activation='logistic',\n", + " dnn = MLPRegressor(hidden_layer_sizes=(n_hidden_neurons), activation='relu', solver='adam',\n", " alpha=lmbd, learning_rate_init=eta, max_iter=epochs)\n", " dnn.fit(X_train, Y_train)\n", " DNN_scikit[i][j] = dnn\n", " train_accuracy[i][j] = dnn.score(X_train, Y_train)\n", - "\n", + " fity = dnn.predict(X_train)\n", + " MSE = mean_squared_error(Y_train, fity)\n", + " print(\"Mean squared error: %.2f\" % mean_squared_error(Y_train, fity))\n", + " train_accuracy[i][j] = MSE\n", "fig, ax = plt.subplots(figsize = (10, 10))\n", "sns.heatmap(train_accuracy, annot=True, ax=ax, cmap=\"viridis\")\n", "ax.set_title(\"Training Accuracy\")\n", "ax.set_ylabel(\"$\\eta$\")\n", "ax.set_xlabel(\"$\\lambda$\")\n", - "plt.show()" + "plt.show()\n", + "print(train_accuracy)" ] }, { "cell_type": "markdown", - "id": "d49cd4ec", + "id": "7373ec03", "metadata": { "editable": true }, @@ -3763,7 +3015,7 @@ }, { "cell_type": "markdown", - "id": "9a4706c7", + "id": "d6bf1bf5", "metadata": { "editable": true }, @@ -3795,7 +3047,7 @@ }, { "cell_type": "markdown", - "id": "b720efdc", + "id": "accb159e", "metadata": { "editable": true }, @@ -3817,7 +3069,7 @@ }, { "cell_type": "markdown", - "id": "0cb90bb5", + "id": "a92a5e51", "metadata": { "editable": true }, @@ -3845,7 +3097,7 @@ }, { "cell_type": "markdown", - "id": "e45e89d3", + "id": "5ae65ed4", "metadata": { "editable": true }, @@ -3860,7 +3112,7 @@ }, { "cell_type": "markdown", - "id": "f2471451", + "id": "687ef539", "metadata": { "editable": true }, @@ -3872,7 +3124,7 @@ }, { "cell_type": "markdown", - "id": "ee20b9ee", + "id": "9aeee4e8", "metadata": { "editable": true }, @@ -3887,7 +3139,7 @@ }, { "cell_type": "markdown", - "id": "ebc12338", + "id": "b387637a", "metadata": { "editable": true }, @@ -3900,7 +3152,7 @@ }, { "cell_type": "markdown", - "id": "0f5cb3d7", + "id": "ea565ad3", "metadata": { "editable": true }, @@ -3912,7 +3164,7 @@ }, { "cell_type": "markdown", - "id": "8be293e3", + "id": "3dc47fc2", "metadata": { "editable": true }, @@ -3922,7 +3174,7 @@ }, { "cell_type": "markdown", - "id": "c0a2104e", + "id": "00ea18d8", "metadata": { "editable": true }, @@ -3933,7 +3185,7 @@ }, { "cell_type": "markdown", - "id": "93b447fd", + "id": "7a125f42", "metadata": { "editable": true }, @@ -3951,7 +3203,7 @@ }, { "cell_type": "markdown", - "id": "94d59403", + "id": "6709a1b0", "metadata": { "editable": true }, @@ -3962,7 +3214,7 @@ }, { "cell_type": "markdown", - "id": "7b044c26", + "id": "3428c3a8", "metadata": { "editable": true }, @@ -3974,7 +3226,7 @@ }, { "cell_type": "markdown", - "id": "a4ec8b3e", + "id": "95c50e90", "metadata": { "editable": true }, @@ -3984,7 +3236,7 @@ }, { "cell_type": "markdown", - "id": "7e221f81", + "id": "3da4b4ce", "metadata": { "editable": true }, @@ -3996,7 +3248,7 @@ }, { "cell_type": "markdown", - "id": "729c5dd3", + "id": "4ba0a0a9", "metadata": { "editable": true }, @@ -4006,7 +3258,7 @@ }, { "cell_type": "markdown", - "id": "5eb54f13", + "id": "aafd46bd", "metadata": { "editable": true }, @@ -4018,7 +3270,7 @@ }, { "cell_type": "markdown", - "id": "51cad783", + "id": "c45d88f2", "metadata": { "editable": true }, @@ -4028,7 +3280,7 @@ }, { "cell_type": "markdown", - "id": "e38a17c1", + "id": "652c12db", "metadata": { "editable": true }, @@ -4047,7 +3299,7 @@ }, { "cell_type": "markdown", - "id": "c669704a", + "id": "287eebdf", "metadata": { "editable": true }, @@ -4057,7 +3309,7 @@ }, { "cell_type": "markdown", - "id": "6c2f1143", + "id": "37400e70", "metadata": { "editable": true }, @@ -4069,7 +3321,7 @@ }, { "cell_type": "markdown", - "id": "144ef4c2", + "id": "bcef14c0", "metadata": { "editable": true }, @@ -4079,7 +3331,7 @@ }, { "cell_type": "markdown", - "id": "d9da387d", + "id": "8e755bfd", "metadata": { "editable": true }, @@ -4095,7 +3347,7 @@ }, { "cell_type": "markdown", - "id": "16d9099a", + "id": "bf603c75", "metadata": { "editable": true }, @@ -4115,7 +3367,7 @@ }, { "cell_type": "markdown", - "id": "dac4b0d4", + "id": "42abb005", "metadata": { "editable": true }, @@ -4125,7 +3377,7 @@ }, { "cell_type": "markdown", - "id": "821d16ee", + "id": "f79e2da7", "metadata": { "editable": true }, @@ -4136,7 +3388,7 @@ }, { "cell_type": "markdown", - "id": "64804e58", + "id": "7a0b3900", "metadata": { "editable": true }, @@ -4155,7 +3407,7 @@ }, { "cell_type": "markdown", - "id": "28be47df", + "id": "7322cacc", "metadata": { "editable": true }, @@ -4165,7 +3417,7 @@ }, { "cell_type": "markdown", - "id": "f15f39a0", + "id": "1a10a334", "metadata": { "editable": true }, @@ -4177,7 +3429,7 @@ }, { "cell_type": "markdown", - "id": "03117774", + "id": "ec1915c1", "metadata": { "editable": true }, @@ -4187,7 +3439,7 @@ }, { "cell_type": "markdown", - "id": "2dadc99e", + "id": "c4fe6000", "metadata": { "editable": true }, @@ -4198,7 +3450,7 @@ }, { "cell_type": "markdown", - "id": "98d081e3", + "id": "41a78ecd", "metadata": { "editable": true }, @@ -4218,7 +3470,7 @@ }, { "cell_type": "markdown", - "id": "02c207e3", + "id": "d9184930", "metadata": { "editable": true }, @@ -4230,7 +3482,7 @@ }, { "cell_type": "markdown", - "id": "5b3ba5aa", + "id": "336efd0e", "metadata": { "editable": true }, @@ -4245,7 +3497,7 @@ { "cell_type": "code", "execution_count": 36, - "id": "97a71b30", + "id": "d7f7ee11", "metadata": { "collapsed": false, "editable": true @@ -4325,7 +3577,7 @@ }, { "cell_type": "markdown", - "id": "ed7eb3b8", + "id": "06b3c778", "metadata": { "editable": true }, @@ -4335,7 +3587,7 @@ }, { "cell_type": "markdown", - "id": "1ac7d0e5", + "id": "7fd7f1a9", "metadata": { "editable": true }, @@ -4347,7 +3599,7 @@ }, { "cell_type": "markdown", - "id": "8069a90f", + "id": "7a7d6f60", "metadata": { "editable": true }, @@ -4357,7 +3609,7 @@ }, { "cell_type": "markdown", - "id": "815493e0", + "id": "dcf4259b", "metadata": { "editable": true }, @@ -4368,7 +3620,7 @@ }, { "cell_type": "markdown", - "id": "7880ef32", + "id": "56e2c7b1", "metadata": { "editable": true }, @@ -4380,7 +3632,7 @@ }, { "cell_type": "markdown", - "id": "ecb0a16f", + "id": "83f24da1", "metadata": { "editable": true }, @@ -4390,7 +3642,7 @@ }, { "cell_type": "markdown", - "id": "d8782aad", + "id": "3e072e07", "metadata": { "editable": true }, @@ -4402,7 +3654,7 @@ }, { "cell_type": "markdown", - "id": "d2491d40", + "id": "ebb98625", "metadata": { "editable": true }, @@ -4412,7 +3664,7 @@ }, { "cell_type": "markdown", - "id": "1cf22842", + "id": "2208961c", "metadata": { "editable": true }, @@ -4424,7 +3676,7 @@ }, { "cell_type": "markdown", - "id": "71180218", + "id": "9fe2fec2", "metadata": { "editable": true }, @@ -4437,7 +3689,7 @@ }, { "cell_type": "markdown", - "id": "1c734def", + "id": "2469ff5a", "metadata": { "editable": true }, @@ -4449,7 +3701,7 @@ }, { "cell_type": "markdown", - "id": "85f6ff9d", + "id": "78c3608b", "metadata": { "editable": true }, @@ -4459,7 +3711,7 @@ }, { "cell_type": "markdown", - "id": "1ad66e97", + "id": "724d699f", "metadata": { "editable": true }, @@ -4471,7 +3723,7 @@ }, { "cell_type": "markdown", - "id": "6ff8d32a", + "id": "c81e30d6", "metadata": { "editable": true }, @@ -4483,7 +3735,7 @@ }, { "cell_type": "markdown", - "id": "fde1cca5", + "id": "b7539680", "metadata": { "editable": true }, @@ -4494,7 +3746,7 @@ }, { "cell_type": "markdown", - "id": "5b34fa19", + "id": "35bef2fb", "metadata": { "editable": true }, @@ -4506,7 +3758,7 @@ }, { "cell_type": "markdown", - "id": "e93804b1", + "id": "c9ba75f2", "metadata": { "editable": true }, @@ -4525,7 +3777,7 @@ }, { "cell_type": "markdown", - "id": "e3b2a85a", + "id": "0de9cf54", "metadata": { "editable": true }, @@ -4538,7 +3790,7 @@ }, { "cell_type": "markdown", - "id": "88b484a0", + "id": "c29fc4c3", "metadata": { "editable": true }, @@ -4548,7 +3800,7 @@ }, { "cell_type": "markdown", - "id": "0cae40f7", + "id": "806f82d4", "metadata": { "editable": true }, @@ -4560,7 +3812,7 @@ }, { "cell_type": "markdown", - "id": "3e3c19f7", + "id": "7101ec03", "metadata": { "editable": true }, @@ -4570,7 +3822,7 @@ }, { "cell_type": "markdown", - "id": "c5d9738a", + "id": "e3c91e71", "metadata": { "editable": true }, @@ -4582,7 +3834,7 @@ }, { "cell_type": "markdown", - "id": "49bf03c8", + "id": "28859238", "metadata": { "editable": true }, @@ -4592,7 +3844,7 @@ }, { "cell_type": "markdown", - "id": "acc52e20", + "id": "412d7d97", "metadata": { "editable": true }, @@ -4604,7 +3856,7 @@ }, { "cell_type": "markdown", - "id": "ecfc4d77", + "id": "a2d6e61f", "metadata": { "editable": true }, @@ -4615,7 +3867,7 @@ }, { "cell_type": "markdown", - "id": "7bc2250b", + "id": "3aab18ca", "metadata": { "editable": true }, @@ -4627,7 +3879,7 @@ }, { "cell_type": "markdown", - "id": "3c038483", + "id": "a5d3d3d4", "metadata": { "editable": true }, @@ -4637,7 +3889,7 @@ }, { "cell_type": "markdown", - "id": "d530cc8f", + "id": "6bc87ffc", "metadata": { "editable": true }, @@ -4649,7 +3901,7 @@ }, { "cell_type": "markdown", - "id": "667c132f", + "id": "e6d26432", "metadata": { "editable": true }, @@ -4659,7 +3911,7 @@ }, { "cell_type": "markdown", - "id": "1a592608", + "id": "68315dcb", "metadata": { "editable": true }, @@ -4671,7 +3923,7 @@ }, { "cell_type": "markdown", - "id": "fe968934", + "id": "251e4b2e", "metadata": { "editable": true }, @@ -4692,7 +3944,7 @@ }, { "cell_type": "markdown", - "id": "f182ccd2", + "id": "485307ed", "metadata": { "editable": true }, @@ -4706,7 +3958,7 @@ }, { "cell_type": "markdown", - "id": "3e23c6ac", + "id": "9a1d8612", "metadata": { "editable": true }, @@ -4717,7 +3969,7 @@ }, { "cell_type": "markdown", - "id": "2a10b1fa", + "id": "b053306a", "metadata": { "editable": true }, @@ -4729,7 +3981,7 @@ }, { "cell_type": "markdown", - "id": "753ac3da", + "id": "6509f810", "metadata": { "editable": true }, @@ -4739,7 +3991,7 @@ }, { "cell_type": "markdown", - "id": "abdc427a", + "id": "5f2b6cfb", "metadata": { "editable": true }, @@ -4751,7 +4003,7 @@ }, { "cell_type": "markdown", - "id": "a959437a", + "id": "d68edc03", "metadata": { "editable": true }, @@ -4761,7 +4013,7 @@ }, { "cell_type": "markdown", - "id": "764e589a", + "id": "e592d409", "metadata": { "editable": true }, @@ -4773,7 +4025,7 @@ }, { "cell_type": "markdown", - "id": "00e50636", + "id": "402a8712", "metadata": { "editable": true }, @@ -4785,7 +4037,7 @@ }, { "cell_type": "markdown", - "id": "7f1fb52c", + "id": "3297371d", "metadata": { "editable": true }, @@ -4799,7 +4051,7 @@ { "cell_type": "code", "execution_count": 37, - "id": "6e7ef8e3", + "id": "87fb9b2a", "metadata": { "collapsed": false, "editable": true @@ -4814,7 +4066,7 @@ }, { "cell_type": "markdown", - "id": "e8de20b3", + "id": "ee24edc8", "metadata": { "editable": true }, @@ -4825,7 +4077,7 @@ { "cell_type": "code", "execution_count": 38, - "id": "890c0e17", + "id": "f3f9658c", "metadata": { "collapsed": false, "editable": true @@ -4838,7 +4090,7 @@ }, { "cell_type": "markdown", - "id": "fa46eacd", + "id": "b4ed34de", "metadata": { "editable": true }, @@ -4849,7 +4101,7 @@ { "cell_type": "code", "execution_count": 39, - "id": "dd7bc08b", + "id": "609abf77", "metadata": { "collapsed": false, "editable": true @@ -4872,7 +4124,7 @@ }, { "cell_type": "markdown", - "id": "f1dac4cb", + "id": "7f3cfe27", "metadata": { "editable": true }, @@ -4886,7 +4138,7 @@ { "cell_type": "code", "execution_count": 40, - "id": "8253a870", + "id": "c825f110", "metadata": { "collapsed": false, "editable": true @@ -4899,7 +4151,7 @@ }, { "cell_type": "markdown", - "id": "25175ebc", + "id": "127f753b", "metadata": { "editable": true }, @@ -4910,7 +4162,7 @@ { "cell_type": "code", "execution_count": 41, - "id": "4106532b", + "id": "9002643d", "metadata": { "collapsed": false, "editable": true @@ -4922,7 +4174,7 @@ }, { "cell_type": "markdown", - "id": "3ae3cbe1", + "id": "3c10d523", "metadata": { "editable": true }, @@ -4933,7 +4185,7 @@ { "cell_type": "code", "execution_count": 42, - "id": "9cbc337d", + "id": "b0be976a", "metadata": { "collapsed": false, "editable": true @@ -4949,7 +4201,7 @@ }, { "cell_type": "markdown", - "id": "1f984da0", + "id": "a3c853fd", "metadata": { "editable": true }, @@ -4960,7 +4212,7 @@ { "cell_type": "code", "execution_count": 43, - "id": "91777701", + "id": "3e876e46", "metadata": { "collapsed": false, "editable": true @@ -4974,7 +4226,7 @@ }, { "cell_type": "markdown", - "id": "f504b559", + "id": "8bae9ae0", "metadata": { "editable": true }, @@ -4996,7 +4248,7 @@ }, { "cell_type": "markdown", - "id": "67440280", + "id": "e268fe32", "metadata": { "editable": true }, @@ -5008,7 +4260,7 @@ }, { "cell_type": "markdown", - "id": "c5190684", + "id": "0eb0a0b8", "metadata": { "editable": true }, @@ -5018,7 +4270,7 @@ }, { "cell_type": "markdown", - "id": "1b878f0e", + "id": "48244140", "metadata": { "editable": true }, @@ -5030,7 +4282,7 @@ }, { "cell_type": "markdown", - "id": "8ab0a4a3", + "id": "d285acf3", "metadata": { "editable": true }, @@ -5042,7 +4294,7 @@ }, { "cell_type": "markdown", - "id": "e9106c8d", + "id": "291407cc", "metadata": { "editable": true }, @@ -5052,7 +4304,7 @@ }, { "cell_type": "markdown", - "id": "03c4e9d7", + "id": "b80bef46", "metadata": { "editable": true }, @@ -5064,7 +4316,7 @@ }, { "cell_type": "markdown", - "id": "0e4abfb1", + "id": "ad91b94e", "metadata": { "editable": true }, @@ -5074,7 +4326,7 @@ }, { "cell_type": "markdown", - "id": "45af97a4", + "id": "59d64474", "metadata": { "editable": true }, @@ -5086,7 +4338,7 @@ }, { "cell_type": "markdown", - "id": "9ff2fda9", + "id": "f0f79d1c", "metadata": { "editable": true }, @@ -5096,7 +4348,7 @@ }, { "cell_type": "markdown", - "id": "c1593fa5", + "id": "a2c1adbd", "metadata": { "editable": true }, @@ -5108,7 +4360,7 @@ }, { "cell_type": "markdown", - "id": "d34ea7db", + "id": "77c55331", "metadata": { "editable": true }, @@ -5120,7 +4372,7 @@ }, { "cell_type": "markdown", - "id": "699612be", + "id": "464518fe", "metadata": { "editable": true }, @@ -5130,7 +4382,7 @@ }, { "cell_type": "markdown", - "id": "88ae1420", + "id": "7722ff6a", "metadata": { "editable": true }, @@ -5142,7 +4394,7 @@ }, { "cell_type": "markdown", - "id": "b827d1c6", + "id": "17a0a0bf", "metadata": { "editable": true }, @@ -5152,7 +4404,7 @@ }, { "cell_type": "markdown", - "id": "61900168", + "id": "db0729e5", "metadata": { "editable": true }, @@ -5164,7 +4416,7 @@ }, { "cell_type": "markdown", - "id": "eaab94fc", + "id": "a3342e4d", "metadata": { "editable": true }, @@ -5176,7 +4428,7 @@ }, { "cell_type": "markdown", - "id": "c8f542a4", + "id": "32797264", "metadata": { "editable": true }, @@ -5188,7 +4440,7 @@ }, { "cell_type": "markdown", - "id": "c6e93dd5", + "id": "6b4fa2ed", "metadata": { "editable": true }, @@ -5198,7 +4450,7 @@ }, { "cell_type": "markdown", - "id": "977ca552", + "id": "91b0f90c", "metadata": { "editable": true }, @@ -5210,7 +4462,7 @@ }, { "cell_type": "markdown", - "id": "ff3c6b13", + "id": "1788b899", "metadata": { "editable": true }, @@ -5220,7 +4472,7 @@ }, { "cell_type": "markdown", - "id": "ebbb06cf", + "id": "fbedd864", "metadata": { "editable": true }, @@ -5232,7 +4484,7 @@ }, { "cell_type": "markdown", - "id": "ed6f641e", + "id": "46ced7fc", "metadata": { "editable": true }, @@ -5242,7 +4494,7 @@ }, { "cell_type": "markdown", - "id": "94c50447", + "id": "126581f2", "metadata": { "editable": true }, @@ -5254,7 +4506,7 @@ }, { "cell_type": "markdown", - "id": "caa52732", + "id": "22263ac1", "metadata": { "editable": true }, @@ -5265,7 +4517,7 @@ }, { "cell_type": "markdown", - "id": "721f3130", + "id": "d2f1c4bf", "metadata": { "editable": true }, @@ -5277,7 +4529,7 @@ }, { "cell_type": "markdown", - "id": "1ecec855", + "id": "3c150c12", "metadata": { "editable": true }, @@ -5287,7 +4539,7 @@ }, { "cell_type": "markdown", - "id": "9f72bcd2", + "id": "54c4bd59", "metadata": { "editable": true }, @@ -5299,7 +4551,7 @@ }, { "cell_type": "markdown", - "id": "952c0807", + "id": "85450044", "metadata": { "editable": true }, @@ -5309,7 +4561,7 @@ }, { "cell_type": "markdown", - "id": "db7a0783", + "id": "f62678e4", "metadata": { "editable": true }, @@ -5321,7 +4573,7 @@ }, { "cell_type": "markdown", - "id": "03a57144", + "id": "06216620", "metadata": { "editable": true }, @@ -5334,7 +4586,7 @@ }, { "cell_type": "markdown", - "id": "22e8525a", + "id": "48b4d612", "metadata": { "editable": true }, @@ -5346,7 +4598,7 @@ }, { "cell_type": "markdown", - "id": "e7dc4b83", + "id": "44fe7e7a", "metadata": { "editable": true }, @@ -5358,7 +4610,7 @@ }, { "cell_type": "markdown", - "id": "5ceab08b", + "id": "989f2952", "metadata": { "editable": true }, @@ -5370,7 +4622,7 @@ }, { "cell_type": "markdown", - "id": "61608838", + "id": "0425932f", "metadata": { "editable": true }, @@ -5382,7 +4634,7 @@ }, { "cell_type": "markdown", - "id": "59fd7508", + "id": "7f095428", "metadata": { "editable": true }, @@ -5394,7 +4646,7 @@ }, { "cell_type": "markdown", - "id": "caca22c4", + "id": "a37ec316", "metadata": { "editable": true }, @@ -5404,7 +4656,7 @@ }, { "cell_type": "markdown", - "id": "b459c22c", + "id": "05921282", "metadata": { "editable": true }, @@ -5416,7 +4668,7 @@ }, { "cell_type": "markdown", - "id": "3715e857", + "id": "147b5033", "metadata": { "editable": true }, @@ -5428,7 +4680,7 @@ }, { "cell_type": "markdown", - "id": "3ad3eeb2", + "id": "fe77ebfe", "metadata": { "editable": true }, @@ -5441,7 +4693,7 @@ }, { "cell_type": "markdown", - "id": "d8b193ef", + "id": "2a2e48f9", "metadata": { "editable": true }, @@ -5468,7 +4720,7 @@ }, { "cell_type": "markdown", - "id": "11007882", + "id": "6c8cf2ea", "metadata": { "editable": true }, @@ -5479,7 +4731,7 @@ { "cell_type": "code", "execution_count": 44, - "id": "ee8cdde5", + "id": "4b4b43d0", "metadata": { "collapsed": false, "editable": true @@ -5575,7 +4827,7 @@ }, { "cell_type": "markdown", - "id": "1ea53cff", + "id": "e2a451c5", "metadata": { "editable": true }, @@ -5590,7 +4842,7 @@ }, { "cell_type": "markdown", - "id": "4d725567", + "id": "b59392e2", "metadata": { "editable": true }, @@ -5612,7 +4864,7 @@ { "cell_type": "code", "execution_count": 45, - "id": "aa6446c1", + "id": "7b909eeb", "metadata": { "collapsed": false, "editable": true @@ -5687,7 +4939,7 @@ }, { "cell_type": "markdown", - "id": "7b772723", + "id": "bec3ce40", "metadata": { "editable": true }, @@ -5699,7 +4951,7 @@ }, { "cell_type": "markdown", - "id": "3cf1d40f", + "id": "a321d502", "metadata": { "editable": true }, @@ -5768,7 +5020,7 @@ }, { "cell_type": "markdown", - "id": "59288b2d", + "id": "759fda61", "metadata": { "editable": true }, @@ -5782,7 +5034,7 @@ { "cell_type": "code", "execution_count": 46, - "id": "f06dd2f8", + "id": "93284b25", "metadata": { "collapsed": false, "editable": true @@ -5795,7 +5047,7 @@ }, { "cell_type": "markdown", - "id": "21171361", + "id": "a3388ab9", "metadata": { "editable": true }, @@ -5809,7 +5061,7 @@ }, { "cell_type": "markdown", - "id": "0389374f", + "id": "985f07fa", "metadata": { "editable": true }, @@ -5822,7 +5074,7 @@ }, { "cell_type": "markdown", - "id": "e85ae9f5", + "id": "65ca73e3", "metadata": { "editable": true }, @@ -5833,7 +5085,7 @@ }, { "cell_type": "markdown", - "id": "6eac8058", + "id": "97ccbc96", "metadata": { "editable": true }, @@ -5845,7 +5097,7 @@ }, { "cell_type": "markdown", - "id": "c9d88838", + "id": "0e7404ee", "metadata": { "editable": true }, @@ -5855,7 +5107,7 @@ }, { "cell_type": "markdown", - "id": "4a767648", + "id": "64aed9c5", "metadata": { "editable": true }, @@ -5867,7 +5119,7 @@ }, { "cell_type": "markdown", - "id": "3b1a7735", + "id": "e0a3bdb2", "metadata": { "editable": true }, @@ -5878,7 +5130,7 @@ }, { "cell_type": "markdown", - "id": "8c8ad214", + "id": "4ef8be54", "metadata": { "editable": true }, @@ -5897,7 +5149,7 @@ { "cell_type": "code", "execution_count": 47, - "id": "43caea5f", + "id": "5283ee66", "metadata": { "collapsed": false, "editable": true @@ -5913,7 +5165,7 @@ }, { "cell_type": "markdown", - "id": "9c604beb", + "id": "f275d73e", "metadata": { "editable": true }, @@ -5923,7 +5175,7 @@ }, { "cell_type": "markdown", - "id": "519328d9", + "id": "e2f0b55f", "metadata": { "editable": true }, @@ -5934,7 +5186,7 @@ }, { "cell_type": "markdown", - "id": "3fdc48c8", + "id": "5b01468f", "metadata": { "editable": true }, @@ -5946,7 +5198,7 @@ }, { "cell_type": "markdown", - "id": "e6774cc5", + "id": "5af2c631", "metadata": { "editable": true }, @@ -5967,7 +5219,7 @@ "name": "python", "nbconvert_exporter": "python", "pygments_lexer": "ipython3", - "version": "3.9.10" + "version": "3.9.18" } }, "nbformat": 4, diff --git a/doc/LectureNotes/_build/jupyter_execute/week34.py b/doc/LectureNotes/_build/jupyter_execute/week34.py index 80c831eda..26590e7b6 100644 --- a/doc/LectureNotes/_build/jupyter_execute/week34.py +++ b/doc/LectureNotes/_build/jupyter_execute/week34.py @@ -8,7 +8,7 @@ # # Week 34: Introduction to the course, Logistics and Practicalities # **Morten Hjorth-Jensen**, Department of Physics and Center for Computing in Science Education, University of Oslo, Norway and Department of Physics and Astronomy and Facility for Rare Isotope Beams, Michigan State University, USA # -# Date: **Week 34, August 21-25, 2023** +# Date: **Week 34, August 19-23, 2024** # ## Overview of first week # @@ -22,23 +22,25 @@ # # * Wednesdays 815am-12pm and 1215pm-4pm. # -# 4. On Thursdays we have a regular lecture. These lectures start at 1215pm and end at 2pm and serve the aims of giving an overview over various topics. These lectures will also be recorded. +# 4. On Mondays we have a regular lecture which will be organized as a mix of active learning sessions and regular lectures. These lectures/active learning sessions start at 1015am and end at 12pm and serve the aims of giving an overview over various topics as well as solving specific problems. These lectures will also be recorded. +# +# * [Link to recording of lecture TBA](https://youtu.be/) # # The labs are also available till 6pm Tuesdays and Wednesdays. Videos and learning material with reading suggestions will be made available before each week starts. # ## Schedule first week # -# * August 22: Presentation of the course, aims and content. Introduction to software and repetition of Python Programming, linear algebra and basic elements of statistics. Please select group. +# * August 19: Lecture: Presentation of course, Linear regression, examples and theory # -# * August 23: Presentation of the course, aims and content. Introduction to software and repetition of Python Programming, linear algebra and basic elements of statistics. Please select group. +# * August 20: Introduction to software and repetition of Python Programming, linear algebra and basic elements of statistics. Please select group. # -# * August 24: Lecture: Linear regression, examples and theory +# * August 23: Introduction to software and repetition of Python Programming, linear algebra and basic elements of statistics. Please select group. # ## Lectures and ComputerLab # -# * The sessions on Tuesdays and Wednesdays last four hours and will include partly lectures in a flipped mode (promoting active learning) and work on exercices and projects. +# * Mondays: regular lectures/active learning sessions (10.15am-12pm) # -# * Thursdays: regular lectures (12.15pm-2pm) +# * The sessions on Tuesdays and Wednesdays last four hours and will include partly lectures and discussions in the beginning. # # * Weekly reading assignments and videos needed to solve projects and exercises. # @@ -52,9 +54,9 @@ # ## Communication channels # -# * Chat and communications via +# * Communications (email and more) via # -# * **Discord** channel will be added asap +# * **Discord** channel at # ## Course Format # @@ -88,19 +90,19 @@ # # * Karl Henrik Fredly, k.h.fredly@fys.uio.no # -# * Adam Jakobsen, adam.jakobsen@fys.uio.no +# * Sigurd k. Huse, s.k.huse@fys.uio.no # -# * Daniel Haas Beccatini Lima, d.h.b.lima@fys.uio.no +# * Odin Johansen, odin.johansen@fys.uio.no # ## Deadlines for projects (tentative) # -# 1. Project 1: October 9 (available September 4) graded with feedback) +# 1. Project 1: October 7 (available September 2) graded with feedback) # -# 2. Project 2: November 6 (available October 6, graded with feedback) +# 2. Project 2: November 4 (available October 8, graded with feedback) # -# 3. Project 3: December 11 (available November 10, graded with feedback) +# 3. Project 3: December 9 (available November 5, graded with feedback) # -# Extra Credit (not mandatory), weekly exercise assignments, 10 in total (due Friday same week), 10% additional score. The extra credit assignments are due each Friday and can be uploaed to **Canvas** in your preferred format (although we prefer jupyter-notebooks). First assignment is for week 35. Each weekly exercise set counts 1%. +# Extra Credit (not mandatory), weekly exercise assignments, 10 in total (due Friday same week), 10% additional score. The extra credit assignments are due each Sunday and can be uploaed to **Canvas** in your preferred format (although we prefer jupyter-notebooks). First assignment is for week 35. Each weekly exercise set counts 1%. # ## Grading # @@ -125,12 +127,25 @@ # ## Reading material # # The lecture notes are collected as a jupyter-book at . +# The lecture notes can also be retrieved as a standard PDF file at . # -# In addition to the lecture notes, we recommend the books of Bishop, Hastie et al, Murphy and Goodfellow et al. We will follow these texts closely and the weekly reading assignments refer to these texts. The text by Hastie et al is also widely used in the Machine Learning community. Finally, we also recommend the hands-on text by Geron, see next slide for links. +# In addition to the lecture notes, we recommend the books of Rasckha et +# al and Goodfellow et al. We will follow these texts closely and the +# weekly reading assignments refer to these texts. The text by Hastie et +# al is also widely used in the Machine Learning community. See next slide for link to textbooks. -# ## Textbooks +# ## Main textbooks # -# * [Goodfellow, Bengio, and Courville (GBC), Deep Learning](https://www.deeplearningbook.org/) +# * Goodfellow, Bengio, and Courville (GBC), Deep Learning +# +# * Sebastian Raschka, Yuxi Lie, and Vahid Mirjalili (RLM), Machine Learning with PyTorch and Scikit-Learn at , see also +# +# The weekly reading suggestions are all from these two texts. The text by GBC can be accessed chapter by chapter from the abovementioned URL. +# Each chapter of RLM gives access to the pertinent notebooks. These notebooks are highly recommended. + +# ## Other popular texts +# +# **Other texts.** # # * Christopher M. Bishop (CB), Pattern Recognition and Machine Learning # @@ -139,10 +154,14 @@ # * [Aurelien Geron (AG), Hands‑On Machine Learning with Scikit‑Learn and TensorFlow, O'Reilly](https://www.oreilly.com/library/view/hands-on-machine-learning/9781492032632/). This text is very useful since it contains many code examples and hands-on applications of all algorithms discussed in this course. # # * [Kevin Murphy (KM), Probabilistic Machine Learning, an Introduction](https://probml.github.io/pml-book/book1.html) +# +# * David Foster (DF), Generative Deep Learning, +# +# * Babcock and Gavras (BG), Generative AI with Python and TensorFlow, # ## Reading suggestions week 34 # -# This week: Refresh linear algebra, GBC chapters 1 and 2. HTF chapters 2 and 3. Install scikit-learn. See lecture notes for week 34 at (these notes). +# This week: Refresh linear algebra, GBC chapter 2. Install scikit-learn. See lecture notes for week 34 at (these notes). # ## Prerequisites # @@ -195,7 +214,9 @@ # # * Support vector machines (only survey); # -# * Unsupervised learning and dimensionality reduction, from PCA to clustering; +# * Unsupervised learning and dimensionality reduction, from PCA to clustering; + +# ## Deep learning methods # # * Deep learning # @@ -207,7 +228,7 @@ # # * Autoencoders # -# * Generative methods with an emphasis on Boltzmann Machines, Variational Autoencoders and Generalized Adversarial Networks; +# * Generative methods with an emphasis on Boltzmann Machines, Variational Autoencoders and Generalized Adversarial Networks(covered by FYS5429); # # Hands-on demonstrations, exercises and projects aim at deepening your understanding of these topics. @@ -245,20 +266,6 @@ # ## Learning outcomes # -# This course aims at giving you insights and knowledge about many of -# the central algorithms used in Data Analysis and Machine Learning. -# The course is project based and through various numerical projects, -# normally three, you will be exposed to fundamental research problems -# in these fields, with the aim to reproduce state of the art scientific -# results. Both supervised and unsupervised methods will be covered. The -# emphasis is on a frequentist approach, although we will try to link it -# with a Bayesian approach as well. You will learn to develop and -# structure large codes for studying different cases where Machine -# Learning is applied to, get acquainted with computing facilities and -# learn to handle large scientific projects. A good scientific and -# ethical conduct is emphasized throughout the course. More -# specifically, after this course you will -# # * Learn about basic data analysis, statistical analysis, Bayesian statistics, Monte Carlo sampling, data optimization and machine learning; # # * Be capable of extending the acquired knowledge to other systems and cases; @@ -279,118 +286,6 @@ # # * Work on numerical projects to illustrate the theory. The projects play a central role and you are expected to know modern programming languages like Python or C++ and/or Fortran (Fortran2003 or later) or Julia or other. -# ## Introduction -# -# Our emphasis throughout this series of lectures -# is on understanding the mathematical aspects of -# different algorithms used in the fields of data analysis and machine learning. -# -# However, where possible we will emphasize the -# importance of using available software. We start thus with a hands-on -# and top-down approach to machine learning. The aim is thus to start with -# relevant data or data we have produced -# and use these to introduce statistical data analysis -# concepts and machine learning algorithms before we delve into the -# algorithms themselves. The examples we will use in the beginning, start with simple -# polynomials with random noise added. We will use the Python -# software package [Scikit-Learn](http://scikit-learn.org/stable/) and -# introduce various machine learning algorithms to make fits of -# the data and predictions. We move thereafter to more interesting -# cases such as data from say experiments (below we will look at experimental nuclear binding energies as an example). -# These are examples where we can easily set up the data and -# then use machine learning algorithms included in for example -# **Scikit-Learn**. -# -# These examples will serve us the purpose of getting -# started. Furthermore, they allow us to catch more than two birds with -# a stone. They will allow us to bring in some programming specific -# topics and tools as well as showing the power of various Python -# libraries for machine learning and statistical data analysis. -# -# Although we have projects where you write your own codes, we will also focus on two -# specific Python packages for Machine Learning, Scikit-Learn and -# Tensorflow with Keras (see below for links etc). Moreover, the examples we -# introduce will serve as inputs to many of our discussions later, as -# well as allowing you to set up models and produce your own data and -# get started with programming. - -# ## AI/ML and some statements you may have heard (and what do they mean?) -# -# 1. Fei-Fei Li on ImageNet: **map out the entire world of objects** ([The data that transformed AI research](https://cacm.acm.org/news/219702-the-data-that-transformed-ai-research-and-possibly-the-world/fulltext)) -# -# 2. Russell and Norvig in their popular textbook: **relevant to any intellectual task; it is truly a universal field** ([Artificial Intelligence, A modern approach](http://aima.cs.berkeley.edu/)) -# -# 3. Woody Bledsoe puts it more bluntly: **in the long run, AI is the only science** (quoted in Pamilla McCorduck, [Machines who think](https://www.pamelamccorduck.com/machines-who-think)) -# -# If you wish to have a critical read on AI/ML from a societal point of view, see [Kate Crawford's recent text Atlas of AI](https://www.katecrawford.net/) -# -# **Here: with AI/ML we intend a collection of machine learning methods with an emphasis on statistical learning and data analysis** - -# ## What is Machine Learning? -# -# Statistics, data science and machine learning form important fields of -# research in modern science. They describe how to learn and make -# predictions from data, as well as allowing us to extract important -# correlations about physical process and the underlying laws of motion -# in large data sets. The latter, big data sets, appear frequently in -# essentially all disciplines, from the traditional Science, Technology, -# Mathematics and Engineering fields to Life Science, Law, education -# research, the Humanities and the Social Sciences. -# -# It has become more -# and more common to see research projects on big data in for example -# the Social Sciences where extracting patterns from complicated survey -# data is one of many research directions. Having a solid grasp of data -# analysis and machine learning is thus becoming central to scientific -# computing in many fields, and competences and skills within the fields -# of machine learning and scientific computing are nowadays strongly -# requested by many potential employers. The latter cannot be -# overstated, familiarity with machine learning has almost become a -# prerequisite for many of the most exciting employment opportunities, -# whether they are in bioinformatics, life science, physics or finance, -# in the private or the public sector. This author has had several -# students or met students who have been hired recently based on their -# skills and competences in scientific computing and data science, often -# with marginal knowledge of machine learning. -# -# Machine learning is a subfield of computer science, and is closely -# related to computational statistics. It evolved from the study of -# pattern recognition in artificial intelligence (AI) research, and has -# made contributions to AI tasks like computer vision, natural language -# processing and speech recognition. Many of the methods we will study are also -# strongly rooted in basic mathematics and physics research. -# -# Ideally, machine learning represents the science of giving computers -# the ability to learn without being explicitly programmed. The idea is -# that there exist generic algorithms which can be used to find patterns -# in a broad class of data sets without having to write code -# specifically for each problem. The algorithm will build its own logic -# based on the data. You should however always keep in mind that -# machines and algorithms are to a large extent developed by humans. The -# insights and knowledge we have about a specific system, play a central -# role when we develop a specific machine learning algorithm. -# -# Machine learning is an extremely rich field, in spite of its young -# age. The increases we have seen during the last three decades in -# computational capabilities have been followed by developments of -# methods and techniques for analyzing and handling large date sets, -# relying heavily on statistics, computer science and mathematics. The -# field is rather new and developing rapidly. Popular software packages -# written in Python for machine learning like -# [Scikit-learn](http://scikit-learn.org/stable/), -# [Tensorflow](https://www.tensorflow.org/), -# [PyTorch](http://pytorch.org/) and [Keras](https://keras.io/), all -# freely available at their respective GitHub sites, encompass -# communities of developers in the thousands or more. And the number of -# code developers and contributors keeps increasing. Not all the -# algorithms and methods can be given a rigorous mathematical -# justification, opening up thereby large rooms for experimenting and -# trial and error and thereby exciting new developments. However, a -# solid command of linear algebra, multivariate theory, probability -# theory, statistical data analysis, understanding errors and Monte -# Carlo methods are central elements in a proper understanding of many -# of algorithms and methods we will discuss. - # ## Types of Machine Learning # # The approaches to machine learning are many, but are often split into @@ -579,7 +474,9 @@ # # * [Keras](https://keras.io/) is a high-level neural networks API, written in Python and capable of running on top of TensorFlow, CNTK, or Theano # -# * And many more such as [pytorch](https://pytorch.org/), [Theano](https://pypi.org/project/Theano/) etc +# * [Pytorch](https://pytorch.org/), highly recommened +# +# * [Theano](https://pypi.org/project/Theano/) and many other # ## Installing R, C++, cython or Julia # @@ -1551,31 +1448,36 @@ from sklearn.neural_network import MLPRegressor from sklearn.metrics import accuracy_score import seaborn as sns + X_train = X Y_train = Energies -n_hidden_neurons = 100 +n_hidden_neurons = 50 epochs = 100 # store models for later use -eta_vals = np.logspace(-5, 1, 7) -lmbd_vals = np.logspace(-5, 1, 7) +eta_vals = np.logspace(-3, 0, 4) +lmbd_vals = np.logspace(-3, 0, 4) # store the models for later use DNN_scikit = np.zeros((len(eta_vals), len(lmbd_vals)), dtype=object) train_accuracy = np.zeros((len(eta_vals), len(lmbd_vals))) sns.set() for i, eta in enumerate(eta_vals): for j, lmbd in enumerate(lmbd_vals): - dnn = MLPRegressor(hidden_layer_sizes=(n_hidden_neurons), activation='logistic', + dnn = MLPRegressor(hidden_layer_sizes=(n_hidden_neurons), activation='relu', solver='adam', alpha=lmbd, learning_rate_init=eta, max_iter=epochs) dnn.fit(X_train, Y_train) DNN_scikit[i][j] = dnn train_accuracy[i][j] = dnn.score(X_train, Y_train) - + fity = dnn.predict(X_train) + MSE = mean_squared_error(Y_train, fity) + print("Mean squared error: %.2f" % mean_squared_error(Y_train, fity)) + train_accuracy[i][j] = MSE fig, ax = plt.subplots(figsize = (10, 10)) sns.heatmap(train_accuracy, annot=True, ax=ax, cmap="viridis") ax.set_title("Training Accuracy") ax.set_ylabel("$\eta$") ax.set_xlabel("$\lambda$") plt.show() +print(train_accuracy) # ## A first summary diff --git a/doc/LectureNotes/_build/jupyter_execute/week34_73_1.png b/doc/LectureNotes/_build/jupyter_execute/week34_73_1.png new file mode 100644 index 0000000000000000000000000000000000000000..c4d631d2cb166fed698195c479be65e2a0f28a05 GIT binary patch literal 38196 zcmbrm1yogG`#pHz(k%^_ZjhAj?oR0tP?}4JNOy@S(k%@VqNLI(DIlmc2olmr!@PXo ztXaRA|EyWFW?Zw0<5Id44A-uv0ljnmOm#>Jw4ZK6E zfhh$35%pFy_SScQ>g{LaX%A`Icq3fgy1M1qQ)HsF-*`5Wda*U!-#BGDiq{Q>dySYv7;r_j7>1!S98;J1PE5 z<{i5wIyil`Y#$o|ryCM+6E}yc*>stTbB$7gRE_sVOHc>bOqn2gdgTk9pH6+BVt=}` zQ!*3`7RkuSz75-DqQ4Rws@^;s$h@*+xq9@~M5=ZtD`99Pb4YR|_bPZPKW!}_4_%f3 zMV25kd;;Y;1YUrjFVQG?|9KG~@&D-sBhwrV1C2W!+sDTzHZc)pz@v-izXRHaZU%V! z_|OXql2DEg3Q-zj<+Qeny(=j}eNO(LYiopNWl?J6iuv?98?Yl77#Wc;?qqd!b!BOA z|8qySg&#f;IXXJ7N=Xq`5{ry*k&uumBFE5Sgwxse8+WU-4QAZG#^{s%@0U#vV1 zJ04=qU;b|9uIS{%A(GtleE+lXw)4Neg@pEY3GyT*jcg&@+V-R20_RVzzoJFGHae|& zt;cdi=f1pXqgB!_&n-&*z{V|ze_`%XL7~X}3?{(z(szR-kUTYO{qP3`v#E=7Lo=TF3M%I1tB(`5} z(;i#O1_p`=x&B0fG9;f1;n7MZF5TUpHQ)UEg#={_xpp_$f336WL4!J@ap84-`<5<0 z8!_EGZa$4m!wN02ustDYyoD^iJDf^)zS>GiJ}8e)!ls*?U_;|o4Ea;97+rIx=&3&2 z+yUFj%L36gTBaG7jFwXq6TG`uZu89# zSYE5Pmz0!T1Rq2`G0CAuhY&{+koDaKsl-j~Ys=Y`U-1X)UCs@!NQvU9t!5Hd(IBzF zzmUvZnI{BMsG`jQmROcojZ{2;rFf*i+y(JV)jE`j@*^?XcOjuQ$!soU$8WC5Tkz}c zoZ!NRtZyz)SI2X6bD2D2WqCi;ZLWH}tHeFKc0>ft?&KS;$^>9rn)#r9O1CJ8iXm7D zpy`;uC2{&0h%VU_V1;UVSB)%zpT!eNwwc{pzp1fSFo6HI>B;XZbZ8=nf+v+wWN2t8 zf|D;PDG37;Q`X#kK6VzTaohh1FS#`@d62ZVoG#8u1Z|C5kDrw|M)njccpARR_eU_Yb?c+( z;Y7Cbq^%e7pM3t=5tUBX4VLEdi}NnwhHw$J3wm}k!{A^kH8r(%nyWv>FA;qtk7dfH zlKe+k`x0P6T5_4hr0do<4HW+G*ExmSuSoWSXUyiWy)QJb_x`D)U355p(Bpye|6P>! zMY=m)p*Xw%>&|<(!2Ji2_YYw5+A&DXbF<+ZhBeRz1HsdBYYRkYa=69u~Ma|8| z8V}Gz`x3}(cfQx0&(sD-S>0XE4vvlWi|@BbL}8O%9v2gEbo1*Nm;G+<#ic`u-IHDl zSH|`{a5Ld@GJSs7J+N6YYmrC?Zwm+MGt=7*K3HRb1E+%{2YEQvX|B8yaobhb@m}7Pr6V1z1d5WUq)M@j(wc9e29jL z-}jcw3{BE^RB(3r&tx&1H^rjQJt+gkZvDnPQGWB6DKTH71`4# zuPwV>S#Y1=7UWo@uW4phU`<{hIIlv1gJY^?nv? zpw7PIxyG-FV^ZjGa1sv_QvpsP*46IQ=HRz}f&0c^LdKbJvZoZY)36Y&{v#^!onShf zPrn%)S__iunwvW*O>*;dXF7GKf21DFB~%>3Wt8FOkW0hi{B(NvrCR=3K1|v|z~_3H11egQtkk|#%VQzgOQ_X%Fd?Qi&6*f9b=1ger& znsP#+`y=_=r{*@YV|9Gb^Y~1qJ3L6Cg7=^Cov}R~7I9#hRR6tJ(|A;%My7`i+fREM zzg-+`HZ+K)fa4=aLCdfBZ~Aik1>&{jR_@~CqfRAPAL&iqM(W8UgMM5X!m9DeN?DcY z{M4p1tTr>dTIe2-M?#gMxi*G*vk{?nThlJnrN<74u_Pp_KUvq1vq%EZND-;Be7aWKKR?lIp ze&smcD2oTHN1xovVZX2I$O!6e+R)B4V2>j?PDKs#YCzJS7bBw_o})r(DaSB8KJc09 zyP_v@$P%qPu3|whS+O-Ryawad+GIkBC>;SH5aRC$Q2(PxiMdZcO+Oxlqrc zS+WL^s(){eCIN9YyTB_Qf7*=>n`h&F(d=F6@mI*3Lz#$OE$9hrr zJ~wmuH8f68gEl*+0YQ9Fnht3m{F_2`u>4`t)*5y}o}t#UNh_Jbc#yM#+-<~6 zpSwVzskN-nPHn3PNqz=hZz|lxzM!4Ky5DPcbD7o6yilj%k3-w{GUAlgG{bvSOo%sw z?sqTL+Q+MdUo#uj_N7wElE2PY%jDg`h4P7gI5|WUYInqKrX6*re(o?Qg5bTz?Ng`# zj$>u-*6N{yEFNWBH57WiD*`b#*^@s6;33qgXJw?1d%Dpy=#ixyC2@Mz;m@+)P-uX@ zhLq-xrId2)5<^(A#-b!g?~;RHj`6g|BL_h$%ky)pQYGx%U1|rV}%GsW;x8%ob4*RIko9Z^oyZx`1 zs^cK4?@O~%f*e_1mWgiHMQ`x+*`_Ik@f~heW=z_=U_cyGOl2(N0pdbv3MTBlf4gi3 zalW>Atip#`c4*=D5HGj?w>IDbeYE*7h)IDmg@ksG-_PGh7BAS-LI_$mw-t`dMoK{i z$09%19S!0fOFrAWB2CLtRIVk^@LvwX4y?wDghxsXiY0wb_xbvCS?+l)n}`JeI!jw2 zjzm&=PHQZPb*{!(om;D~q`C0Wht2AE9~zCMz}5FF>JOHLN4f#Zi`ZN-j7_D(#w*kd zbk%xe*n~u|t$I#a6W#On#*jB^+uE!3;D@NJ%A}+DEtLe1@r`F$27%-B#mQ%E02U&u z9wA|TS0of3wq9tUm}vI<8D+9)I5DQE;zhBc;v7A@-Mhp2=iksKFA4I}_c8oYjx zxu?Nl)ip9s{n;1l94LdM8%nUO4~2QkF7uwfslB*!%YC?bW{4&Bz}y9oEZG1vrXp%; zHRy8D#iC_LtuWst!&3e8hy-1jd^zEyq@d&?kKzmfDTu4z`VeH+QBLnsOn}$SC2}FP zSWcb?e_g9L5x0Ca6NPv3!y*=UmXVdO``P|ZfJ5N+rRTn!I4WT#1cqV5 z618>EjQ5?30d(+de}rg%r_q}-U0kq+6l?&+!O(NKRhLk;{oW^B5bhm|^`IDz$d4Pt zBjousr4m&Ra39lkEj}d3vrIwP&qJ8lPNO{8HvyM*TMRmv>YRK1`0Q=M+266lrZBp9 zs9xF@k7k(AlCH4Er_PgFhS)@BV&A&Kzmu-(Oc`Z*4KA2_*}Qef*N55q9euOaFYz2nV1#x+ zUVj;@0^K))aLYC#^-U)5U;QFEd56Ncf7SgIOD7Vx5%$?uAun_8cL7%X{10_NZJyj@ z_w8->ebHL@Cz155KW5Frhr*xc$pUt$)|zL;W&joEer@);v&3eeQqM}mi9?W+o05s9 z_$Ud*vCj+E)*3toN_pOgqE07d8sT53Kp5V5Le_e@D>Z)fn(_X$gcS zUtwH30gaB+Te>}vGPmDe&8G_0hx)~YV@s&FYu^51^>F1M0q$o~wFL9}*pF;)ENK7= ziEW(IIgmh9moC(HsB_;R6jT^?g`>#w*Pp)a?VIi6AF?I1*T5=0AbYQ@{t}mUM{G-g zn^B@BnDhDew~9%OshIQ6){I`RG&L+?jL+~|*W5|%E@mbB2Gw86YC7}aJ^mCoYBqy& zKhHYGDG?+sLlBe~W7Rt<1GsIR~2k1rMI_A{<*8M*6CON!@s+Eq)L2^N3;d}P$9RdjPQkonoT z&NutiM?8ny^3-r@C|tfgKD8DOVU&4gPm!clmwufuJG2$_u1tl4H9fDbdNgV4gDfM{ ziyMKO^v%&+%HQ+`ucan9fP&9IVEiJq(J?cV>K^}s1Gfv9)+Lr zp}ONq=JWBm=ukUBi`1vc14x23pB?r-F-UbU-``-~*ZHtjndRzW2oa!!bL;VrRJrOW z?C2_XXwC7|)-b_Bg0@a=!!&7`@NRlOk#WW~zXDU}=v2>tbr>DD!vGmd;* z^m4ltzxOW%bd|t7ME30&`?M_u$$cG*n6sz8cPeKoKrr9P9Mii1egbChqYk7zq6@f(CvzPQ_&2Ix$fq>tW z5Y;cDZ-dD%Vx(Epz0zNL!qwE6BBIBz2I(qSuWuiDGuLmi>*q)3!>?Aig!cCK#tn9u zM%Bh)+uPgpwIR0`o4Qt3Jc~|FP6Tjx0$^lQJFVsAY_&VvJ3BT4mt`DW^da}Dj98xy zvd(LJhFx4oH&7cE0wE~u^@i}?a@k`%cstZmQ5tG;19dHQ&f5~lF!JOr1OTa~utQUw zjtwMYc@nN7_4fJ?cN10sy}tUzTuXY*jmUexCt7X!nG#>(0D3x}m!z33M9;;A8*;ry z8`HjM_lRCp)TEtSDu~?G)%Cpg?vkf=MgZ z;9tb6Hd#^;3kjnTMr@-PY{1AUR9`{J&rV^N3kLS{-|!vi>kOS31RON;{ViKM?DK4Z*QTiy)pLv7LWdU}MEl$1&@ zz#qxmfu36X1JC)0iJwIMHpEh5DWX{JbsT#Ivlf| zmnr#0P+7a0Uhc}7go(1tk?Pac1m~e@3h!6x)HEX@6Wfh=EI#GS+eDWXA~yTvBJ1rf z@a43|JwWn{!z4q{-PO`SNxEe`v-;cR{g6BHrz06*WS0ImgJ(bLY+zzyV!dXXnxm1@ z*!0>Nr%$!ih~*l)RB7JD_aCh(PsNVI z)wtO;W@cvNcK^fJ+J!bhp0Ql2#&LI7UO%0L5-%f{Dkt0##8eQPF(CiLH7_PNJLm)HIIiBS&#QX; z@xGa_oCq7@AFs2Za}Js~oqtX}ygc2hcbefa_vj-T93LNWuKgUnz3n7%z8nFeoJ|5v z<{-V}x^KrPTiCt7I|}<%cDDE*$^5`=c23hq3{g?hKfAjM9v*zj)Z)?UmVrY{v@t34 za-sEzN-U*NzU3E`euv?TTRMslU5yE&Tgn=U7ziq7(OjuslCBq=7}&~Ol|3MesS)J7 zWl5=nOYSeOLA+BtRo|n(ea>y0I}D)!`;}}xV%-C4|cVrruBaAC*!&N`h+_!eRrL*|6_46nfCS|#=*fMbjYsz`r`NyDCE{%;i$K_B9S;1 zE?crqGf48WN}TyLH~^v@bk&RHIB)k$hKQlCj=yex#rq`GBSnF)czq{f^@WjY=0>9T zMOKSo1VP4Fc+Ne*{7zqpd{%MEef=99yLWR&K_*aF@?=8Z|4(5|bdVd+z#?e)Gd1dr zIeWfX>FPd+kB<)$l#pBDJ)7PIOUVD_wJ_@Vo&=0_e9F;$73J3qgu!}5CM6XE*uhUu z-}&GRV#B=N-*UC1amSi+3DMRg@NtnZKisgtIr?d&P;O$M7BLXxKRh7gJbT0Xj0cPP zOcdo)?E}8x3{+NfR*%kK3n}?PG|ot)BAMv+=sg!%n7|~%?^PyGAt#w1zT|(+(B&ax zn@+;D@O{#%KnC!j_|1oL7&%~vEIuUS$Z-;+qTw1WOj0XqJe@;y<(`sOCy(UqMVsu= zZBF4@Ak|dJCF1klDj{36_u$eG#^S>0M&N>k1Y{(#DA?%<1FF7+_;OrCXyQq=W?2z; z3y;IzOQ9Q$s7D+1y!t8|UYEqd$c=(w!orgkm);4vMD| zAxnwtDpc>CdbXmugNOjCW?N-)_wr3Hf(n=?vfLAxy zgw@Hc>7Q=zcBlY|;KADjDASLsh-QQM?NPP8re%U}>+7g*Wto$b)QVSl8BG?-JSy}T z=V4VnQHak*i7zmPMvna6*Ta2DOm7Fn<=ODYivk__3Zcl#MtADUw+ags+GHg3xBwJd zyzqS^d@QNb$}`=biJ!dTwOf?wM* z0s1e=zm|~RkDU5n3=)wgL{C(@ZcxnBiwp5FZpc070k9Vot&sf9ZZe{n`s{j_@C?w`YPn=6ztQQl(9-ZxL7)mi2woV^E?apKK$}VY&)ylTg7*F(Avi%cDXzJbN)lo zg!Ho<7!WXfK zu{?fFC^7@9A{O5H>u6T>ZAXFrx^7SWW=VXWK&}rJEtV7bR)2{U{+p+7f&P+nG`nDJ>wERiA9>|kYI;gM+7}CS z6iqD4lMS*_+#FbsScuWTzReQuiv-cxT1oHS<7GaA>uDFG*D;(T-=0jp|6olLN5yUF znZ)&sS-I#-F@70kD?;(9OI=K{lf>*BuOzvjz|b#ai(7Nu1H@b+#P$?XJvdEpvWG`neum!I8?d zsSa9nXuTN~kKo#$OS_agQoii>gsV@%ry4Rx!itP4qm19$JxJU%{>yNa)VSkgg_=wQ z0OyJ0eppyNZ5>cz7GyIt56p2U{*piyHwMo&ir7W5aak|L;?|g-?+_v4wk*#+NyvVx zK3p@T_hS=q>Wze(QPYw)!+SjUleS*{E1aKEH49F%Ozoh7LYueQ=aNB%ISv;ryHUg3 z_&ze841?@gqvh9`+TW1T3)xtxCh$ zjabW&-c-yT<@IH<6bK0zlZe6C*Ov37JL!GMO4W%NA{74WZ0)L;9)Rqb~%?KK^$hBOm5*S`b{LcFYp{h=m(7}>u?iDqDNE{ zb^4T;4d2mNkLdjXxxHW#@x<_~Z)%PC_3)my%JMn1;YQv(ct4o^*A`ognG~6aacJ%Fgy)Tg3BQNCcDd{3!=)1HJF4m z?t#S1eV*Y?vzW>)1sW97Ko^G(b6u(u5%DW6?4t8~XjwdA1DuDiMF4QB^++cvclor; zI;%;R&x)LoA`Dhz4~i_hOBGjH4l)*44;wSUo+=3- zd{#$vF+a_gQ@zt$#qlJw2}?@GW=tt7lCdWHLJ^iv3XG@Y*VxScbyp4BC1 z;VuG%sa3G%#CUXcbO5j=-t)hClFvIm z<_mspO_hCq54;WVjgd@PL{}&J z^4l1pn4XO`SDK(+FZ8ruqEz`cZ* zY~AfimrZ=Lg$-aPB%6Ob@iE2ywqU5kp2u)d*UZ(@yTqG;T9(5pA}fnmBN;8H`ChYw z_VNGZ-;niGspk1X5B}kR^z8$O% z2mJ+r{#9yfcz8JS?&9ZPJ1xMaffG0mcWbtpJ8Lwp0fgkF^&;VR1nsvr4ZAMT$abD# z&R97A3bbc-3%wmx!+mPY&ilsfb#CwPDL1t!l05!+v~dw7bxf-5kJj7#gm{!> zZ3j2E=&3CQJ-yV~HC0trz$eI$1lify{r`TPt#kbaOagmt8KPb+SXfvGfMLYW3J3@! z?nwSmDt$2&9fO%8ltAsu5v!L@xK-bMCpiuatWgpIrj1fQn|TdnRsw$`S~BNlrlEnF zp}~KMIHItKz9l9lN&@>g>Aw^EmZv|R7LD)W964O8%P?$RVk9Bj#+V5Kp8iOkSyxCFTd(e z&PV)U*9C`Y>7WXgRZ5D+w8l5ZzNEh1BL%1zq+F&bA6le|*hNJH%=aC6$q7hEe)}A= znh;-;A%Of|?($%G_U><3RKr(m+j=vypJ^eLsaOE5G(VTUlT~(GMLTF*o-kc=Z=cVC z1?mj-)nH=uBYkYHxaL5d1WJOFs-vg3dg`yLib=|2DY0?J{_vr^np*t1S8(uc!PzzN zcJ!a--P)P9KcA%clb5k}Lw(xuH6EXge{P+@6IAD7A4P|5Ucsg@?_Q_VFfOKNn-LYv z)yS-FeV6d7UkYaw27vJu$71OHXj2fCkpO%>!*W$I=4L0ql@KP@@Tix%G zLrGd-*0^7md$Y#DsCzKce#f1Z@86$MFRuPwT&*Qy^1Y5H%?(}lK5P#0K>M^?E7xq9 z5UE0ckm_pWsWP=Gf;UCT00d>~-Qh zcdmFBp09a9bm|_kl+HtTe9036n!rDW^!dLU>=S0krLTUBAAHEaahX1AUrQE83{d-> zKk=7}(aakr#Rg)tQK@>1-U{h!lfxtIOWW8(;`O2<@sSz=S{oU!CK7Nr9ygry(b`%J z%Ec?7vK6L(n#<3ISSg>NrkB{7qUDV zxmbvS_y{T-r&w=mO0h;j@I_?6 z!GQH}{UZ4YNu~}NQYz`LM-^<0EW8Gvc*7X2$PAUt$pxq;?0pI%F4^z^wg~~1xle{?Qqf5o+gL^(zo>F62?oEjw)0pC{2@%mWJ4u#SrdFjD&lfoBPryBzoz`X zkvL^6WH5)2eD1eb+FMZ=I|vUE5X92`ig%pv~lW}vU(IO zEljw6g#F1ER`V8CK_YD`0hPKA_YCGm{7FPSkuZcw)xpqO0gxxj)4v&|p^7o6iQgMd zt$lQ+G(&V}7XeE_{cIFrKv6dM$gih93l9qarCG6u#@>k)&(TG_mwEadaoF$`8IH|_ zxW@Q}V7H#`U}HurD_`gQ6l|G<_)N-8Qxt`i^0?`VXy?5$nXy|#bsv3ij@a)D?>wo^ zhm0g6;f%Ibv=iRyowHUk%PC>B82O8_FNmEIIDf7ZyL}9sl|RNLPE&MHWv% z$=9Fj?LYNBw54KV-I0UD53iiBAkoezh;<2f39caFadjl!+4wUi@N5q_{%wY2 zJm;9PQz*9tR8j+P!_C@+^7rWQs2hfmTKq5M$kLZMEuZjHU}`E3VBrDtO?kj-aPZz` z>y>?W>SVz*jdbTDxY0Tb?11~Tb|&r@#rbl=^|obyJ&^HXn`VfDcGQl$0~~V+mHBfd zW;-3ed$$k(%m0VSW?%w_7t4L&+t|E=GxQ^Tt>uij$}jC|U)J$Bic=&w)LsajHL==n zSL;p(l20b`M;7$+=0EUK1Lx4t!ZMEnS=z{EQdtxa4c4EYDuGJTw!sj#~ z#QgkZ3Eenec=r8TSe8l>emJ#2-~s~4k?SAv6qRDU!w0~Bk*2H{p{Em#lSZe}%d3C5 zgg*h}+{~KzR`#`L#W_>A>p{N%3R{CNei_ot8C$ppx>vyhE`o|IY6*@YV`!a(I%hH$n zy}$RrpD-y@$p*TFSP*sl`I8VEX7D}@Pcn2gA_PYomiHbly9X77G2p`6=T<=<@K|@s zK&kH60esq_3s7rS!RR>#HF(?x^h9S5XevOUDjcl~lo{o>CDV22rM!;Lbq4(A&t51&K4NKsyU{%CFR zXcPYpCjzp0>9kc}SlL&^7ADUpf)r|)@NTNvosDy_>t{GsqX|lW^EaR*_C{_II1-Q1 z&eRCFv&g?vo`+Wj<&w~Hf6~&`OaGVX-*9~q5l?FWz0;;n#DG5tgs_D?3;oXNNZnOCuB);Q~`h+(M&>y1bqLk+}QfWf4J66!i+NN zDIDLE18TRbZof6Y>c0btS}Zb>f_BMx6fNjL;I97tYHu$)z$XjEWDtbq@;R~JG67Yq;8FiHQfee&DjFuBrj1Gh_ALWy_ZCLzBJc0&Dg_z_6%{pz|0z$- zY|6AL22h*9FufkGmjKVhH`|^*wGOo^zIW65hII$T{PcTzFg2!#$isJs$-fA1Y4tS= zdAA$m6Mi9IZfbzLlr&NXDQY#9zpee!12Nhrze7cyj|J2B5X$=DsL*s<#df z)ToPLG&4>rgvU!EExSH4`WcsFg5YjE?cPAh(#mbViqkW9>c|?lDj~L~Y6kQ(z%+JEo8rFRuL9!Puy$ z8p}(kQ5%(j?)1xHQG?ib`^(>N22i)$djkNiZMt-=w{B#*HwHJ;T%k}NXK~_(ZjgQd zHLAjL`}NV+!QtWXNe2Z>OB$)0lPR0p7iSB8^)5diF)=aGad2P(vU5*PKfebw6k8-2 z?!B|Kb9|(ZRZ^AZV8D?I2ZJ`ub(uPH5LSSLhRHufzOTnr%n#2`tyZErLCtpY`WCw*q?rA$6*?_|BBui zT{qd3@;NiRX$KqokHv5$tzUN5{b%FQ&gRnXzb1cR95}2Exxqf(94Dg% zbOAW-gQ?qi3KPkfx~i=y>W6)_`HUGQvV>p9+|Y8oSR|Kg1ejLQ)r_aoG%$t05#wKq zo$7t>N82T;=E~_53A_oFjo?{BEtB{;kbvpj96nyIW^$LE7jJ7sD z=rCcI5_0~|>GGoil{V-AX)*Z96?D9q`^*^fX2;}t1Mwnq$d1q*G~^K7=@2n}Tc{@~ zm^!zsAl6q>{SK;tbF@bdDYUxgj`}2t&r%3}!2qrks;|B!%^Z{1U1U=|nK$}sU6oI`_Q`mG);5+@rXyQz&nM)XGJ@#;QoT;`TMR(2 zdR*HteS3({Y0>K4>nuo#`yO=v*l>xUMIfQcAKXl2daQr~H8+|#AyM)0UniX&RSD5y z3~))I7;KOmRP@7UhG`7~jBf-USyT_es7r(7)6}Z_U}l-XJg?xvxH;|LVfueZ#dmk^ z7hpc*?&kd0(rt9M`YE5SjAH7!4{w1T@%I|DnEz3+{%`lh{pu_}-|qu;VD$S!HR!hi@{NqLa*Y3|zP4o4{bBn3 z`?rYiF1b;yWs>bca@;<<;h>8|K*s4qsqRojgcz2`*%>K=jf8H78NbB}g~7IDgC`;opF(mr^df2|O7{pD(}2SgVL`uq3qIoRK^(a~rb z8Z0CE(zN%1hm_NJdH*Fp`~4lx-C2}kX&EGHOdctB`xnK&M~fPVYd@BMM~?zBQr^vh z008=oS5y84TOY(d>Zh<|s1Jjog8;=U|D_G@!scnt9Z{kb#shhL$;cR*K!?H23bv__tm-^IhD>8k>v-d(>J=l6vlB6h)U((=}x@a zeHlYe>%?(1FpoP>8D%M=HspdKATgd0;;x2IYJXqU)5Pa0+a-nFcJoI#ahh~^M%SNsqv)g^v+=QgDilMVofft8dt8##l@UQj!jouBhPL5Apc{#{r+BYAL5rjpfK z1EkmqMCUa5?{T=yT%Bd_txll(5r(TkAdm zp3L~3Ou8BQ=@OksfEgiL{9QN%do~b-4(XY_qarq5EPd~;7wu*49IxL7u%Cxm%`nc` zz4=^4Paf;0Nn)HJX|Vv5U{I!IzFim$7-PGuwP2__(d4t9E+)k*aZgSHa1J+DZs1%a z4dn)@)AVJZ@)mW{O_(WiB9i|M_r;{(4+zSBoqj)Jx#OaLw^S`*HyeNi7^K=ZU*>QN z?q0^MviEBx4Ts;7=VhmU6Q{h2;2<&l^7MT)sP|3||Co2}gQ+*zfn$W`l<@0GEH?+L zKgFOT2_4!~A%jmRY(;u@bQK1=6SNVduhh%35bd8}z`;1Uz^gT_w~l|{E0`hY6N@)h zxbQ^zqj+98IUF?4{1ozO>7m%#i;($<%(3?xl{FMB)^f~aZ5TA&_%F4Yg4GG@64t(e z+hm!A1*s%HN^P^rDKDA7)nVHbpi$ZW`P|0u2sm2-3yhG=3GKessx;$zLgLaQhs@gP zV$7%BUOS~H(dSQ~+0TIxgckRr1zsvD?`7hKDQOBK(7I8yl8{%~kukIRftFv1{U2Q> z8g{wME#PAU22_>hu7r+3hf432FDuWL+N&@HS5^;gzn;!c=`4QR;;QlF?=*1e6vI|~ zFr1$+dYj=r=?OjMJEfQ+P?$8VA!Smch>(1TDNmXMb(`Z&&8Iom=BKH=kM`&^H*hld zo>Q7}t1m8|rCFaGME|7Q7q#=CFm=&BFZQnu7?0cdZIvmWK1^55j2@ueZvMR0tV~QO zbT<+aUq;S|SBCx3^)oabK!`sTLnqY@h0f!y$&T)^Lq*Q7H%89?)HaoT`H1$X_J;Ay zz~jFIFhqbgR(KV2P__Rj0`!;A7Rjo;(M|gp@y4?fi^<8$884C=&FL3sV}By-<2d{& z-+Q-Lek^I1E}vw(tMt}Glj2v|qoZf=kVC&t*+LNT7x;UeiB3|MvH(zucvq?UudGt0 zThC%9kWf4MkzDOeCkPH-iXRKsaIi!?-hY&4di!SeCsP;^O2$QPe{OWy+br(2z7M`S zUDXOuXhMwB)J~s%8uGS23YKr|puv_>$qWK$L-9cAH)t|eSxyWC^9>xE&<(fL$4U3D zS52MtWQGLbBUs6>Ko_mXW`2p-LL2V(Z&OK7X#56^VLZH3e|hlvBqoy+SJS>~tDM$a zSon=JvoZzn?ng*uEd#wGA!hD1BNHM#6qK$T#7~ojswVH7srWq|4d)Z$o*??s5*8Z7 zKzkAa@>J%GK~lXLQ{q6(Ps&R?#W%XFpL$+>Ac;ZIN>R~|#pERbdQ=ydli2-lx*GWW z{R}FxvNTEFHuYw3zZ|r2m`xxTpq`a~uS$vi2ntjKdK#Ov3!czV)%& z;B$yawA0i!5d$u0Xh0l>57I|Rw+J@v)&h0?fF~#@`AL&Q4F%B?Tq+VX1Y|z~Clrwl z=SWP(BNE29T{X-j<+iEK4fvwe-abrUXK~GaNhE4~92d0*Gl(wR+DLWQmCdehzbZ^7A1 z3uu}8r0gGXv!FI3cjfWRZR8sDbZvN7eA+iFzn7eYUQ__=Y?xJcg(M6Uq!j3hI| zpuDHZpt_9ms?k`Dgf!!Ef~PKe^Y-MncS=&x zViuLn+S_}uW=k_Dk_H?Qf12hAC8M0MYBM32bc>sqlbOl>qy1E3&$*Eom{r)`p!ZDX zj)u9ZRmQFhlOYeOn41hgNrOd`&SvKE7Sp13h`lMHNRO@}HwTZg-n|LS;G-$9r!dUP zr&5uLUx7{!f})j_Cy#)ZA!~1KQIKVXowwves@OKtpq9&utwo>;^m(v1w-JT)UxBc# zlDbW=WdQodvWxY(jEZsbk5t~l1kb4{e68=J69JcN5;$FK?ZILY@JglRHY0)aOae?M z(+(@|WcH#9ZE{^qtjN2I9pLu8II6&d2jF^Gq(?}8Ng?HR<;U@FIw@veygTXR#QQN0 zA|`QgIvM2uwUV6df3x`c`K$DFbYSv!oGM)beeD$9qo69p`)rJg90zSAlOO$8ll$51 z!3~zUjUHorVWCS#SKVC#U_X`Nk|-`?AP4hCZH0rl*R#q#oZW_WV#cvfs=eY4!b##Y zYPy(&bPEf*4(yzJ(C<9^zKgZp5y^jhvjn)jKtxbN0arjBG~}Za|%MbaX;N?HSa|&Z&mqQRbC$KLnW{^aIAXQP%uq2gY*X zpA@zuaq$$!Na>`|0N#k(ok|U;6Er3;xkZO=XiDcHpZ9}iiO3AymXG3xRh{)eTtqzA zG2Zf6?VX+<{r*}Xa(7E_1?D77c6JHTgDV1hn|FP$K)?D~o>3JE=#aM*u8?8x=;^uD z*3(#=ahSpJ5}u=yJ8pBzEOoym`tB&1tF>wgkc=5XGQ&K1-Al2@(a2MMtukQ4-MC7b zay5Wv-C2Rdjg6-wxmrxj%mI>lZ{9>kM@Q3J-8cWQpZ@o&08~^}DgI@xEPAc=C;4wz zl(8JDUdPNoRJx)yb~olUb7`h| zrG%w%7Fp8)1f~Xcr~kDY9Q`UMM`Hbyo}NB7Apw2}o@vUOx6?Ysa-7BpPh3nR#y5d_ zhKqE>1KoS5g6dO8LF4Gk1+ci+?HDlrCv!1@uR}0zH%@xHkrY}MRSVcLXr<~JSyvfR zP15tpXV%W}3CGiqhyx8&pxM!_3ii>J6f_=zvQ&Sf6_-fhXPSV305*2^!@%};?@$uR zcxa9Ufr1qA{_g+u6#xi8{){D}CaJCD4v80ajCu}&f?9Rk-Mw1>FztaJA;V(o*k=-o zrqw}f?AMqk2{AEiBDDdGtk;W`Hh_=bAE5Wmt61xsn`@w%T;9h=kS6Fr77D-m11!_$ zpxpu)@;~T8KU_`Vd2;{x4^MINs6;|XvxV3GHZ74Z9ZxFL_RT!DN_v(TfVOnKA$)jy zwQoE7-eRuFJs+G!ZHh`Np+5Z+`Gm2F`-T+ICLlnyyc#B`-T-bex^fb)e+nz-!RBY( ziWgsa|L_Vvq5uTMaEZO`A8#<3h~I(_nW?Gi!O4_%@s}?&EiEl`^|t6hw}GJ3(^E@9 zkA{YZI^d_SHf#FdNP7#Ys@k{RchTM54T6ZEvcAtefk zbW2N1OSgoCfHdrT`v1;2-#KTWefAh<497cojkV^QYd+6&$94T~;;VIgD*#goReM=@VkmWJ?-PI zbbD2a_OL`EkN!8Q8~*GwC0ngw^IJ_D;3a&)`MkfuG2X-GaWLOi*;h9_g?}tS=*<6r z>GF2HZ~t7iOwV}prE|-FZ}Q$+`P-E{4{uU=DNQcBjY)~@5#cT8L}_?ti9wotmCq2~ zhir;y!(HT_+B;W{Z+y98u7+kM5~Mk~-d!kz2qpQ?aU z=GD^vvO65&@7q)Jxy3Ntk@(FS{Du7kwo2gkDvitXznT4h!J*nALrq*WR*;##YQ&a< z=fx|eU<@P*G~AwU#29zXeeB_+CH8ABc0F?eRAZ6RMj8v}h=BC}DCSTmN>iql7#2Q_ zU}W{9xUDbM`tySXgk}zvZj)(Zx-Lt_XJ|()N+G&NA4FNs_6Qis+nU)%-SB;y=3{@D z%VlV}FRwX3vI6bnhc7Doe?>>V#(>BOHzHTR#u+=O`lGd8S)Q0zX@~rfE|GZHz4Q-F zd+9Ct6gN@OfExH|fg$_3CziDkh^JTP>H<*hLAK)NU52&se_j z^F5czjI0za>SoJiDG#eK*!Z8j9`px=1lcbtrVbCCIYhTUz8^Yb1A#Itc;i94SYXKC zk!p_r_mw|>l}J1GM2D@VGx-6}@TWqF%T*#u>^DUj(=!zGs2QJYsRRn+pJK3vrohua z>x}aywvvvnN{@D*D$TCPkH_)3EiqB)>F`$rofT{r{4cYSL=x34DznOggm3J1(u`z2 zHssO{W6{$=j(C)W`JR14wEWvrEZx>NDAZQ!!9&< zQ%uJ{U-cD#mw$E!#t9>;(NTxyvG9<|yOF_9oh{SvKrFtuukhuRC_t~-%tn=#FDWRo zAzx^1YV5|#-@n!Xp7cZK^g@t&kv2sgU5Q=rzWm!^KhOb{%&iqp8-n$zb5xF_bL)z# zl6iLQ1JX!T1cRoNRBL0J9jBcl&y|rY4iEVCQMm&h@|7{#-{V!YMt?mk?({F;|!Syd8NW zK`xf{-fA@Gz6AbqT4v=ZtuW{xF>zbkjC}31n10n5OIm1S|0dGE(h~wVOI$K_?TwcA zBh|7Ne($2zf1UsV0SQJ*c4Ttl(BaWAccZ*LnuCuOZ9SP_?JLy!EGl~P4x#c)TQ>U- z^X6^$M;~pj=j$84zc|wgZQ3C`&Z0Q#hc4tp+<`_2);`yb8r#Vl|JQDYdic^D)2>GN z&16y*tCe=X=B!(_u+zOD6Qg~mI=6}q^eRy$wkx89AZ@X{4$^4lP;b`&Def2<&?EJ) z5+7%M?HQO8Cx)^M_~f&oZzbv1tUiTRO0M;?nhf^B0Q2XMo9PL$ay|NDF_u1Y+O_#k zE)!MdaRxFDZhI1)G^>OPg96~#gFnxG8q^RjnWPm8c0DCcq6MHrl;r=*8pAE_7XFTu z2tFoO)h7{72Tn|?ll2OdN3Zs+x{KT5o*OuOc1j-P*EF2eRv0=ll^xK=ImqMAa}1>p zZ5wsc?bJ6bI2u~qvI|mxhZDD4T+I0|bf!So<&W_(PNj#uUA=lNPdBw`)mKS0^1G39 zyk8GP)lkCh1?#Ax4yKv2O#9HswCq~GzZ$xdT+2&gyuvps^l3$_8WY)3 zHig9sxz)O zB4unxZY|g?U<+;9Yw37M!aJ+u?o7thrkJD@Lo1@!WVcxk5()nWUoaVfe(&kST}1&p zp?d$;XA1Q4+a?A~*QVrRT4y_&u8|RjPx9_Th2|2ACRR=55Mge_+mySB{Nm*Db}z6! z)reAC+SQ-|B2N6PL<06DkV&EwuVbg$;8WRNBFoAeDa(93|;1uHw()AUB7@!$ItJC8!K!i=Pj2psQgChiQ zzxz*h3=29g>X{9_)qHq-_^^Z$3I^&aVrih~XwyDS3htF2OA+|>l~Fs3SI|ppFs0+RCS$xxB`{k(sogW_wO|J9P1=}xNQ{+K#t8fQw1i2(B z;qK{_>FaPg9Df{$`)F2JJk(=r#fjSf{DggYNX_&IX!=`IB^0SsO0E~v#3!{7_1o`r zXi2$9VT50}eZ>h#Wu$7G%ttad%kyHq>^Eb1t057EfR{b#TTNV zg739*W4Zkm$bx0*)~0r$rGARL*_)SgEN2MW14A|rmo z?uAuF&#eUCOE=c0^G<=ISg7CXq7Ci!v=U0+{)UfVTK(6px!8W>#ar?RU48PqBx7O? z)xJ;D!PypKv}SiS>_0d%5)8>)ljSw|g(!v}+uO7JeOWUVoqln;k|<`+{H?h;HYq6_ zSaCD}!7~{(_V`^kE8e^A0?pQw-7HMxBS?8pIiqBgTR-E&L;KO}njl%Nr#d;RDJdg3 zUR<^;p8H!h+IrZSZtVvps=CCn2l0%L0=1Oty13C#JZv}1Gd}h~t&}hZ082LyCIg_w zVz$zoI#%VxgY<*o@`ya@TFsjVvXpk#O)uz`VwhWNw(28Ft^4N7C+rxUeA()EU8)%lS z`{B+P(N<=iuOq67pqp{rbdl5+5LgqV83veEvD1n=qm&yd0gV78Ijb5zasUPcB3=L} zYKdP)by~_Hrc8^gwcF^>ckzYhQg&``L`+Cf5crVCO`A#hpy)2owTZ3Q5M)HO&^$QR z|I1G2!Gu*)z^G+J-{m(Tt2dGYS`a(iH&STuQfm-I)3bg|x97?z z8X>=bxFT~AW?bVk2iz|C`q8#1hE`eY_|8CZjP7`E_|EF`{-~4C6+KX{)?U2L`=|I$ z2^J6Uci68#CPlZM%c{;iP1wx;e*e{QpICNlFdTE>eD0Yle@N24rFoZjhBZWI$I;M% z+52!#>w3bq>(_U{I4}>`xPUZU8yh)o?H{2<6%)VptDbZ5@$qf%w6k~^*ay%5>AD)C zo*OX!voztj`=ST?OXXJ%xe!4p|Ljyddge(H{NQIT2<-{s4Q=XcV5 zB{fmTNBVR18lR6>imwI!Fq1p6Iw4^`n8B_QDtTJ^`k_l*Z;_0>-{wOu zE025*zUW8f7zpJTDWe6aZgFMKFnY)!)#AV*Gj+|2l8+?NZD*q=2H6@4)aNSi6IA)W z93K%!FSIlV=^R{YD7OiXifV-(y2QMQ)C`Mw^1FAd`@5RJA~oBZu9K!q9|9Xx`@ouu zLJb1~wVA0*dO&y>k*&-@$VRWvBrsHVz$?(}+iExb6^~%;b)shAV-d<45tSkHri@1C znK)(|#GL888C00 zxpXFM0+LKD10j@eU$01f6wp0_@uXT2L`a^U1@Mva}`0>c(CZi&7_8t(0C99AZjIv974~0kx z8k?+bsk84f6AcF;_!<@16X>FSc*Mbt9r1|WPd<`CFSGy*kjx)3=CGGMjSH9i2sY#2 zSaTCT(~Fm1rDjBl>kQz_K324Ks=nmXg=5(gl#x+N0aA?be^3O5wbeFF#>};UiK)6CXMwH+FN-QAlxN5dUr>`AHcT z{f8ovEfzpl_B)VHCABQ7ymerVe(onNDsH$hw|Hn3T8WY;8=>0D z7dH~FP(kSj2v!DobNcQd`k%hL-Mbk3+=KR~E~k31{}pl7oqMNI(9`0kq7WY>e>{B{ z_aEh~uV@NL=oR?#r4h@>zWbqTwt z1a-6nbS8=7Z&8YKhI@T)WDnOS7eiI$S>E!IzrK`G;FhMOa8C>cf~^2J*b!r!q|twj zZJyW@d7zZwG(*3S-#z6}T~8tF)0p=fUMnLrY%=LQ6KaCpmvV+3;>Zv^yTSXG&-2fy zZ%Cd5CbEyj`EN4;O(c=|bGBRfcWTM76AV42$L(R*sBaggan)b%J*>U}zes><`;$^y z#(Y`$beBp{G=>h^s)~VYWso6!c{mjxa%bkX$HC$sZgTN|Z%1OBOeCvpqZwX_CS~}o zzjlX974vFpDz5CdsB(U$I36P%>yjh}#fP|SW~bOrV$S*-sNS4fAh5vAHs^a3N9qAQusI)OWjn%qyun65WSP0O@Bj+H3#6ENT>-N-h6+RRz+mB1U zuFbd2Y`O6mFPa=v+7hPyv41mYwB#IwQC00L-)W4V}={+)A)4=K9lh~Ug2-aVy&DWt^u?URTBe5fHb&$xusRzwm9TEFFfs4mmEO(u5oDm8O;eDye9QE% zS2^DdKBsj2nRgl{eLLVQZ3dB|d%W``5k*E>d+=xJrUxmvM$Ey!k;f@)jeJx%m=7m1 zY<5;cKKCS))%e-W9@5ym2C!o5`$$(&DzKZhgSgib9*RO1f`l`k%0nnWp$1L@GB{@CT{1mNZCWOT?! z>I!?flD+jfLGi}_rp5rK0qE1A(ihfT;HE?;PfDTK`t!8sD_Vj~mE7ibBfE$g6=d_h zvaZd*7HpBkc>Y|h_@%U5xLZTS_dz*@L*{#lh*1IAZl{N$?&c`scqmh3e#_ElfJMU6 zr{gGbPX(Rlz3N?D#9)|NOeo6fV0pV-sWESoc1&6pFh1ucl2WEN2`|3aFeWCD`Ymtj zy%yW=(4W9qpNM9I#Q7 z5{1AH3G0XNp^(p;E7U42A;-G2U(3pn+*|OSD*QrPL_a4clstRR4rWNA7i#Sw+xt`9 zW>YpFtHgZE(^Cpka>t2h6&dB_BQfc>={c3?$bdIHH~+|^;HS&&!!+TP)AgectST$* z64_&*sL$Uv#zD<$Dts)Qc-;}U;pX1UfPMM$D~RhzucR(vG(pJstBf8D5wP_`^ZcAj z{9w|F1j)TqZ@8L6D*jLW`00Vj+PYosj^aP3F=(6JZZ^35e(-drp2@JnuC?Clq=4^GDddJ<@M9(KMMFCGhQ z_}#!%!0kxE+9GQ~XK)UF&MVWKypa8YC5(cA?~Yl_AH!EW|6d9D$pdg-FD@>!rLRMR zv)q%s16?R8AaG%!YLAwamG9nd{%l+W4O_9p^Je8xP+WPw$dD(Gx0VvDkPBqPoYKSj zLcvk|W6E2uSAk%uaVSv`?u-6ZZoyZ5cdGA(qC9j!N+Llo%jx@BtluZ%=s2ZYN`{05KlE)l5KkfbJKmvRs^>an!r?rQK9k zRc(o+yIyS7LoX~U8s5hw@f_2oh6()3G%R=3)D-OOHuJVVV%{cD&+?>ZlEvjahr4Bd zC1KU>qJDDisDlh{&WTv38ZAa+7X&9L@mGe|U+oz>R5$JZIXu~Ow%wHWBJjuhX3OYKvyu7?dkcZnE`JC+|4R1nh3}A!3 zA6+M-pjgj+LL*&)C3Mk3R!)FaC|&{hqfz7 zZf}+%`NF2f5X8E1@$rt(^}JPN|DWtW(Z}@89eik)J`^R0FnIp_+EY=6pFe-reztx3 zl<}{Z*wZmzNVRwL?%lf{t-*f)#SWWwv6 zyj_nkM>T^bWe5i9;$S8hQ7mehi~AOv`+&=*c+7u-*=kat0DAQ;?J?8FqB1fpPz^df z-R&!R*n|!+J^2ujlKX)%H|FS|?CaO}IXT#nmZE$CCiu%)67u?oAmc#!9v{C<5qCuI zlRnvawPl77_dA+vCFv0wLWvm|LV$)qLe3G@#QY;sLW4TxJsVfUp+2Hw0_G~^Z*n7| zv~P*(i+*MgJjJCYCO9t>sKc_iXD&oX8O4$Xe6;3-C)2kjaGi`PM;;13AmQs)6Ty1M z?@e$GC<>y;u2N`Fij70U+|m?)QvwSD@d%jE=^&zxzrSIe1K{%zqP+tMQFQe5%whFZ zLahrb8Zq`hCle?X)Np`=wva1x#(U@PT`fJmU@*C#Kmju?QTK!Mq8mN%iVSBh;~VkB zyA_7V9x2>UzuA#Rcf( zy7!HPii-tLp{VJvce&4-cR?Zg!@qc3t~>n#;u+{<)8N4?IA1LA$$#mk=76vZ}GJg z`Y1)jTHrPpM8kbkQQ`+EEZZ|NaPLgFV&rHtk^kakrUX{!0N~V)a_ou{=(O7=$FNX| zX}8gNXa&1Wp}h?ih-1lC+hw+ zm-W8LP>m^kOKBoj?;jI^9kyKV! z(qbu9M&?;}(kb>)n2r?PYYTv{;vL5$6E_+T-c_4QjHjpCn2QX5+>{Z;H%nQiF)@=S zgXP;F*uOfT0qKp4h>oZsIQN~&N!a1s8}q5B!|5{I+2|c~*lBWtx7bx+vx}HaY68`L zq*_h)yp&lcEv_dcB_89ud0vO?=;l@OE|>TSzU|^}Y?{7iQg-2~+WwJxk$FAb)1UJm`0!qD!maqhH#hE*1ul};-sVQ`IZPDW`0qq?VBXhPQ5PMAeiG$ z;ijK--gwmHP3)W`4VTuWzA#hGPbKT~G$I$^lHE5&uCOuEhhcN`rTXPw%188>)0)1H z+mNPNbe;2otrL<6nM%HUKXmIY6U&}-9Qx38Hp2@Blgmqr$T1f2MU$PI%d@iO# zrJH%#w?Jd`)$V>waQrg%5?<>wESf&~K`3zOi(gTP7iq1$f>1dw+1>pOl@K<#wfgJR zDWLeGbjNg7iFKmk4Y-33t>Zaoni1!nSBu!K+mRFOW{ivw8J8k>^_+~m@G^a0Pz#*l z6YLO*8;%Gh`>ovVnMDJaXeVfDfyaW*<5oO)Nb>o63k*65|Ew;Xl#s&bI;odv5}`u@ z*MtG;aa9sO3}vTY)EV#m;s_@s!yO6c6_scx5Z`S)Nm+3(@T0JlGA3%Mb|;4CAFQ^U zrYXDz_b~_rd(}hVS6;zm#b>Mtx?PY695BpV=t{xGMC%2sj;O#^r2+2ReuXbj)AEj7>2HZ}f* zLNOLR=5pj98%xQ5w*H@!fb7zrP_~->5rU7+SfB=mV-FtLtd3`7oclE4AMA#q1=F8xi173|O8YAG4=c9Fw`i4eqn zRTkBuv)6283o3_x*$>Ftsmb|bMt8qUHsIUA98`fADRIas~@{(|onpd*Y-OPgKYpLJ zV7Q)6m2lr+41h`syMRf85p|ZoK~QRrhH}!*tX2QT`P`qR^i-v13P{ozj_R{PQnn{)DK&A|HikcEP zo(WpF;)dkJobM!aCIKC_oTC`lH;~Cegm6ML=YUoL{P?RmZGl)G%E&i|z(IT~9d2&+ z^u1Euxg+O`MSqt|JXPq5NnTtp2FR&|O>u$3poN*{D6XCHVImx=H4a8TQ&e)2zvP9@ z?FD%&^C6jgSkBtNlC3y5@ZoyLCte||my}_zS=1-`{@o~h*q(lJHTi9r|0{}LDbtCA{vK|AKdcZ+WPToY3 z5cR5qtwZ4hW?WVz$k*UR5?`^?rhTg4xNAf%9;aXvGyz6O^{V!`8$ruaIN}WQZW6H0bxNlDwQR*XjSLn0HUdNC=M2IL@U8cnnqhmzC zC{VV*{b3QnvZw0S9KNo?p-G}{-tvjwizo31M zG{UYY17*?4F48rF=Q{I6f>&#ZU(3HZ^Cf@4T4c?0hvEpJA776t^lm|2!iIkqtI0jQ z8mzu81(Xq4xom(7vIW2IsAKCPOGEm?X!t*L`^XI+lD`y#o86_olK(i z;V?!DQ+D~RmQU61_qVE9ShK)bh<=B&PHN01R=+G#05jjodDN_;HQOI{r=Xa%+d{-Y z4{>>gCqI0uFF-S6-<09b@dP|&@=tR!h@J!fbaEtlBM>)mwUh0Z+roXn|7l--M})DR z$o(Y!;)rD@3Gllv{kyI+UKKJj;n|3;c~qKLDWN7QH#eD&w#nx;y8sDXro(~1FsdlyWeD{rWXD6pzNC9;g++!b^j#MO7diW zJsc$}?;FU3t|cGnh93M@pA%*#jCG28rn8t9$Dd~VJ@vk7YeRjZ(#O_d*uH3&*P}lEXrRlvH0jV&TnCFfAmN$ z65Ct^I0l6DxJ*K*`|@|H;NH=yYx^v1wDHw{ArGe12*cF?CyZ6d(ZPBhjKc^sZ1v{( z>52@;wQJ-vN4>7K%oo!K^&y3Y{G2>I3oT(32yG3~=f}mxvCXvqOVvqge{T?a^OeaQ zUf8{hIQSlz#Q<89I`gfmzYo59Z@M`ljOLQNT7nR`W6kN3)?7xI*LTY zq@^UOoYmkgPy)&39oAfx2%CVTsUdx|SnSuh;c~cbhNAtVPt&(+AuzuWJnRLJnG@zn z#jMc<+mXViA0O@_5GjyrFo2#!ro?ts01@m0tGm)Mi}u&kYwunqB#8EETp^j3(&w7C z-VB!2Ty$K!s7})rq{dV)=1U>xSa7Frkh)3l`*71|J88o=z3uAPgUl)O5cMuIMQzJQ z@2f%*0(U81O25&qz*#!D2j3(8LP8z*cDM8B?!J5X?hxAR|FZNxkg>DzKH2MSP4_rs?r8^keinbekdyxSwkw=Q#S;CW7LBLz4BhtNA>M(Cr=m9J9-B^;oItlL!2%FS zZXKQdd&ck=sKs}7c0i@UvR{3A>gnw4JiFT`)9#N&fI@{3Gs!6_;UKiKwRJK3=}5@a zjb5&P$TIQxv#2um+XZScgh#ba4}F{7Pli{g$+5Hj@Fm*v#v%ggc5@@EHSm7GT!mSO zODiM_3-$Et;|=M-z%1QomHbzJZZ*W~Y6Bo?_3HLp`pG-rTMiS&S}}=m;1HTKw`PgU zjLd522nnUrdHqR+FkmM7?*C3-zGl=G#2q^^KBpMq&1igoaMR~pD$V=&2_r!G-@JK) z=*Kr}chwPp@_pkMZyKbdvv-`ujAGdmqhdy#XWK`ydy%MuBPaSNm*(7ST9&uDHB&@r zl2O+`ngT32OF>?z|Ad~*f(OPzR#Rg9&av4nNA%K+INe+X#6pDLQQa?ruAup!#ySSd zuI9IB?cscc$!Lm%6E>7XOk$o*Ra3!qwVIi;&G!dG>-(3kTxo@S9s`5*pi4ftoNV7l zp&^C#NpHP@gu_fqqZ;x$V84M+!tWlMi&!xQBS}-Z{Jf&H(I#~pOoTxHa{|QWxtDWW ze=Uu9%DuJZzv(MN@3#$1Nw0^$&b1j`B>dj~dMtFHqvt8kPRM4t&k@{Ggw7)>N^M_% zvVX@T^nNv3J!)6v@cdrKz=wS@!di)MASyXWI5}nYPQx2X|!B2#>lns*X}amvwhPSC$Qwc~>`{{4 z&NU3tdN_8|Zfz&8hBds6mSg=^?C*=Or~ftTG^q92Ku5iwGAFQ!Ad~y~s!@yeEsj0{ z>q5|0C|_toawbQbM399sx(mwO+{9I`1Iw) zlF>a9)WfZDD{`@x;(sru9tGrYu$Gd5#nSu23p&r2uLt!w-m)q@6gP}SH=cW)NL$FP z{+=HpKbIsQbBW@^0FDu9om^#G2L30?(-*sdu)DLvfqf<5>weL8PLsI z4OZC9snsKPUw$rT4MD%KL@%B7G?+k3ZeALlX`Sar`7Zbd8I)M=$Mc@;JD_t!rk~Do zqS%OeUSX->9YJ`K0Z**HHaeRFzbH<9A(i?(M8`^1Nw4@|+0;xPurtx$`@G(VvJAMU$)nGB%II%q_d_0h7a={GfGp@rs( zYYKEHpQ1r3B8?2AI?HB^Z6n>5x_$Sv48Ex3ztl90`6I~IV%u}xEfX3p&p zcHk64CK^5J%qlbClibmSKZmKb$?JYk=Q%a_X;8A`zHa!YG}^W>X8_pZHvriiZA3Sg zv!t(fBU-2Ii0g$1aHW zz5HalBkjNDGOSa#?G9$1#SQO`SDjlz59gV2%ddWZtxKwl;*;;Ne55s(oE$A&t8X8S zHlq6kdhQhZEyVoA!}%U04vK5;+jP9=ioI^4)%>+4`i4m!h58l3?JMlo7w*(P^0q`m zq7YO!A$Ql^wVMcM#*)7HFbxT83?}@5P6*=LMNY*-srnFHslpJz z0E44v-(94%_1*7I8uIvZ$c*Z*>S?)e)ixUx(-+1gA(!Ts)@Jc-|8U=fr{Cg5XwZ;v zSQw**7NJ|qjA{gj7Qd5JLj~yP|KzrsZH;rkPP5s|FFSm!djpC)IuAW!uayYkG!Jk7v9-BGMho+nx~zE6P~UBS?o45=#`9&j z!NiJuI+~vzT2nSK@@dXN_hVncbl9x6;0-dA=F94V+%1pB-)Rq0)LL(cl>iG7YkrC5 zY6lulMy8{lQKH5q5o9>UH;mopkbLx}b+Yp0B@{$mUphnY<|J)DdWLgH!#HKn6D@FW zH~xj3r-oc08uXYnb`{Nx#IBPys(`2iD(1nz1kVDet=|uCU9T|QEm(!~q>b3XfiiSO zg%Jhw60lK2Xb^zDzm`C}OZ(A_jXuVw0VbWN25Awz@$7B|;ZqW_I9xf!N(S|{vY%Em@a+>4C z#pa}6PsA@Qf08y?j~m^Z^?do6?&e76!S$25;lY*@Hu?+701p4YeLJz?_IQVT?$zIX z_NVWIa|!edP@(V-6cVyhp3MuSs)8QGh3Bx~>cP*-1xh}{z%+%L5mWgoPpa?T*~*|* z0?yRjz1!DE2Z5@(Az>*8-`7wmn8OAqNF^*P za=UJ-Nga<~QT2ivH~8X;ytRo@$dE?>qt>b$etp7=6TMLUv|P|$Iw?CD3Nn!}6&VB7 zLxY9vU|>$;0HK^#xN-J<#4?HTvAe|&i%iY;|s>lB;)zNxdhg#?3mCtWTNjQoPe|nqqzN9N0I>s=fHcK%B*rZo~L` zSOOVkcS(Y)We0TS2ArW`j`C0D`H-We`WSO`s6Ce+O7DQ9MyE9m*>R0AL7|LpTt_RJ z16Cf_VpHShJeR2{B+{Q2rVC-%N7L{{DFcvf!oRZl;AAjDiU~T-d2sWa*=?j1SDNjr z7Y)xw*9tq;u2%rY+jPwm2%3k`uCzDI_JLf`dvs)9pxyLVR z1BDT0+^4s=XlszPsXi{1)SvbTe>%)zYta{!8$aD>GkAD8JeZ+@7HWOK_{X|)zxytA zE0Muj=nhm$xQc@^+Sf2qU>6YN9(0TiQ8|QJG6G)-7<8L9TJW%l$p0+7yCFcfrNP<1 zyA@)KLRAy_`aO8NM9^ zqrTZe!GG09#^^@QV5N1_r{9mtP`=44A7;xmzUR*-+&P@lxQwvYV$^CBsms7Q1zY% zGxDc5vh-MISX)6`M=-YK$f8W2d=|M1vOi9iY z!4P8W@XxviwaVTu=hMUTt4dyovDYponK1c=+9BL4mB~C*U(edgWvjWl^&AWoM6?`M zrEWRC4TmKTYF|28!x@sqzCU`HoCuRK`Mbk|;#V9ybq0$|uBRo;!^}T%rxF5~4;5vs z_l1&z0w#>|eRFCq0LXf}l1<5e1U&?e;7vRn)KdG11!Ept((?~qOVU;vOjU?efa4?x zl*ET^dzEAuHvy#TkWojo<;m7EvvG4mbzTvR@aq=`#t^U@iR+-H6l}G0&D2b;ANkRx z^u0-G^-;f#4iI(r?LW*m9d}e2zrZ5)%UJ-j=N{X)(S|2)$Jd27>3CoP?8G-P!Dvd& zZMEE`yo1+wXvYS-^9I>n!(WX*ug$?YSoXm2dD)u`GAI{!9T{$|LKEoTqM=|S$>CuNt>#9R!3+J3%8RJJ z0RX+rX6pY&PWI22gN~K9JhcLNWW;$tUr)3BQIh0R>#^v6C`sPhV)-A-dnF+5cEE%0 z)?MWOcieghT>5jZG^Q;yrk;L_iT%8$7x^Rev6?yZwmupFV!d9j+S(H zUL_Qw*t&|tH!yD7?gVqgde&fo{myK%QVZqG}v8nXEAX zt*XdeKu80dw9G)QEsy}@Yvy1jR!79Wegf2+8f?mux+$)Z=Ga0Cl&p@hNehbLRG zrPN79wz&g12KxK^eL+1Q5kp6aZRFG=GS=WDgF+aC#S_0xM&T2(i;3N@4W_-(H|dQh zML{{1vkzL^%u0hAP?=!`?gk{`10_{5}uHC!rYo6LQ0w{O!IKm1f09a+!&Vxc?;qnH9HdL98A; zBA23fr5XN6$^0tui*)V*6NlNgcP)kw9{hYYnorcHurg^MBpwEIAHn9m0cQ^FYb%=Fe>Ney^ z$RCC~5~TbSbF`mW@B`jb4kRRZ?%WadIrl`#agP8eWT*Rj9|{F%`}c#ZK)3gY$qq1f zbA8=$z6DR}WTRBRz6hxfJ>2d}T>7q0&EzY}|1H^Xx9#3`@ygAJax`JKOv$OLp6e~2@oEKV37*1tQ2o)Ynw+f@wM)|#m=kRKHiK9La#er zFAZS4VoCXBJzJY0AsTpaZUFwfL^h<&d6`@jsv7$P?9hH)?h z&o^7ba(-^ww~s~j;pOF`{6>|e2zdYoyS0uU?C;MtT%0uQR5Y9s)z#Hqx^$_r>uQ6P zRRzU|Fbd3Dq=BcjedkQCB*nD@Fo|!GV&3W?86Rn4!}Vvy_20&Vc~!^{nvDNHfAIdT zz@@9dvkW5~Sz`j>6 ziF7055bJ}FwCquOtaSRR*0FVVACFJ=Hk~e=r7GMu(!eil1pjUz46gdmo&2Bw&?^qg z7w-U29C5(20j4y06XXdqw6CL@o125GrxGw_o{CO{ZrPSS*y-SiVTCd}{7L2S@(D1` ztcPd_O8?y$$B14CuJzh!rD?9;1i%H0^I4`s1iJX2lK6M;Bpw&W$ebUB7R|XcLmiqE z7!+hMivSuT)I1t#g#DrIN{=3KA+Sa$jKd+ze&Ys%hSW|=o|E?XnK^hoBH{M|{<*lc zG&iUr!?bf;=W)P(^(u*C78wjQX}(-kOa4AKIz5U(Z2tS@qT801oa7V~JBVt>x;KSx zN2K{IHBH(}QZ|eE22uxq@5s%=6LUx};pNlVZ;RjVc-X1oeQj}H`{Eq_lwuO9lgesp zSnZB(TXhGuY3aXSR>HUkgz5vFO{eAVCOAF4B<;w>7g}Jt0su2wpqRSAmhLK$52i;S*8i_g-L`IUoWX?Ftrs4E)OiKdCN6)jG;bN5c3X%t zDViv;Q1Vs0>5bHAi%QPd?l;iy99yS*QTN?EU^MaEQSgM@jyU7H7m9VB!y~XQ-Lt7^F3g48xC8qB8A##6XjTL zixw8(PeN{%e*g|iCQw%ZY6Id&B@K<%aNl8Z{p)Ae92I;b z^727#LnPwnRUa2ej%tMWmzZDAK0e#u+nfDy_iAgz)q3&8T?zvd5+JA4Y*rI|)cf>p zXQ3ULURh{VMGjT=KU0nF=5n<=Z49-Ymh^jvAa-?&QfxM@bhzcY0qw12B5aJAfdQdK zkFtu2UCGqwnd%oG5658a1@hOnCaVTlEYb-@lcO|LRTrU~uu4`0J&uz@2=|ix=!Q5u zJ33|~!o%A<>$;Za_ssRV z?{6+2G1%7*te3z<9KQw_QR5}52Of?@7?Z;)CPtH=pFeLQHtB#-sCPMIctys1>pO2`^q_Nq`%-&Gi7hFPX$GOlwi)5?fK~uoYA*#-9mHOn*P0&p+;Le z9tn}Q<)cS)n>AaC?(Rp$quW61hAYw99r&uesnJN?$=B4$%C~nk=K~f zF^EbQndM_4BqRj0U6FA01pjLi!^6czbdvP2#C_Ll612piDrVTJrn;;*`>A63 zTRV$Sqzq7pq5p8z;cS1j*`^Hpakj+@LhS+kEaI$`I^Av_`}%|e8CPOfWIfZ_xMdJN zGpd;)v4Sl2duP-NH-auk9=mb`HwItm`!c|d*> z6v1HaRjIz1f@!avq>^i~eMaDT{0E%|kg<~21uVI{wdv6IgKY;Lbj63j>WbR(T)9EP za!5t?da`o16R9sp=pD6$7sj?2}Yp&96-Bk3y(2k2M@#;VaGVD3yy2_ zD-K1x!W<^ZVUu%kM_rwnl5==u1iNNRTKUt<`ZlZ5j8C6>y24=+a44d!T|J0?8|Jx; zL@bVuj>u8gc6Oqzt^F!C7Oiw#YI9UQu+uY_|K2a~Wy|9;ChUOp+V}Nq%AK9Iwl=c{ z3m?JhKK=XmL)Jgn5W|HcQ={Mo(9f8N6+rI)^}+A=_okIE4j|~1H(?S77z8K<9AcV=jTq@;TsWS9i6vjp4QHcdDlsy87>vuP z_W*|CQBP?s?UP=QcOcW+@IXI6uIH#OnS8??q^ z3m81`-{V>TbT8PzkXc9EqO*8{X?<>U->{58)D5$an_*uhS>YdGp*GmVF9MzS`O7_YqnrONs6%iO|m&xoMJ0l9Rs*NF?jigCc0 zPVq7wz*Xq1g@ut@YislFX)8>`IPl1K(NI!u1E65Z z_4m(Kja11uKJcuz9zZU?1hGRWi=?x%=SC9_%VMs2>i4amWf3wj_b!3lesmW`BJ*xJ zh@+p=g_wgmSPFH%Uev(+=Lkpxf8b;h=-ZW=86IxE*vpk!I@p@&yRW0OUE{j7yt})5 z#CtDi8!}Ws#=m)>R!H~RtXlbZb+xrAJ}}Dt5VpW`ASLWp_wMfQNcCN8x;8ARaZ_Bt zR`CZ>D_=})dB4?AQHh;gS#W3Lus_~gJ>4HQ?He5#`2*Om`5uZY&k$I(OD`mu8erc; zE^QeuvMVGcWEXn8QhmFp3o$aiMGwmE)Yikhk`NFqjD9j~M?Tpp7%|*a)!Q#%x;Wv8 z5^XHY#bG;g3Lb2XFYFr|@Kf(3`K6cS<%Pm>zTxwC!{8j04F6saW47Yi1a)MLAiK=j zs>abxkH6c1;ywk5_!0O_f?^^gb-EAQ9VAmdU%r$?Uf;9d>G{cdb#--19kFkvm7cCH z@a)R>9l%^;@-8~v>n~l=u+6`-_!P_}hsdGqsjQ6avpst&Jt`TqSG)>twHqqH4(=>< zQGP+eJhW^7$I|RfOs4er_CA#dF8$xPe!YJU@TkP33)xlG)jxp?tY?6voSmJ)PFlZi z9p3|W>6!2AzVH46Y=yPg$}#*uCY}EQ7(`;-t?|IkIPki}%Ffny?tY+cDqkxl z-1}r6itELknC+u>FT>=Mar(I@^D7>4?pwb6_-iZRRokDPvYr6j=?B%-)jzW}H}3!S zYW2_c`+jL1SS%0BC?AhaC@y>O)6MVxLvQ`PN77SLK2+_Uw;y;x!rq`2?{~kq`!_3l z-N#*Zz%}!KfH&e*?u|R2o|g6rbVC5M&7+ORcgmky{%5N@20T%&4b)WVbyJoX7Cu}L ztX&@b2NtI6bsv%+tlRzWQE*UD1u!C)FI)BrwEE=7WOe_p^QZs*PObqaa$tf5HffvZ zO}_p8_@x`{_kd~3Zr=0b+vMVa;}nm+_JFMW15^P@3g>5;o_^lc_qeirix{X=CeY%v nz@!k=KT!~2=aiu}\n", "\n", - "2. Goodfellow, Bengio and Courville, Deep Learning, chapter 2 on linear algebra and sections 3.1-3.10 on elements of statistics (background)\n", - "\n", - "3. Hastie, Tibshirani and Friedman, The elements of statistical learning, sections 3.1-3.4 (on relevance for the discussion of linear regression)." + "2. Goodfellow, Bengio and Courville, Deep Learning, chapter 2 on linear algebra and sections 3.1-3.10 on elements of statistics (background)" ] }, { "cell_type": "markdown", - "id": "22518518", + "id": "0b0bc0ec", "metadata": { "editable": true }, @@ -103,7 +97,7 @@ }, { "cell_type": "markdown", - "id": "40a10f3c", + "id": "c30cfd06", "metadata": { "editable": true }, @@ -119,7 +113,7 @@ }, { "cell_type": "markdown", - "id": "76f1c739", + "id": "59d6452b", "metadata": { "editable": true }, @@ -131,7 +125,7 @@ }, { "cell_type": "markdown", - "id": "2710298f", + "id": "8649d84d", "metadata": { "editable": true }, @@ -141,7 +135,7 @@ }, { "cell_type": "markdown", - "id": "f1e8bd8f", + "id": "aaa65f06", "metadata": { "editable": true }, @@ -153,7 +147,7 @@ }, { "cell_type": "markdown", - "id": "79e795b0", + "id": "cc43802e", "metadata": { "editable": true }, @@ -174,7 +168,7 @@ }, { "cell_type": "markdown", - "id": "c868570e", + "id": "53877600", "metadata": { "editable": true }, @@ -186,7 +180,7 @@ }, { "cell_type": "markdown", - "id": "855e1dbf", + "id": "bc4478fc", "metadata": { "editable": true }, @@ -199,7 +193,7 @@ }, { "cell_type": "markdown", - "id": "e76339ee", + "id": "64bc2ac2", "metadata": { "editable": true }, @@ -211,7 +205,7 @@ }, { "cell_type": "markdown", - "id": "706dd49c", + "id": "d7b7d1d1", "metadata": { "editable": true }, @@ -223,7 +217,7 @@ }, { "cell_type": "markdown", - "id": "d068e28e", + "id": "f34563f6", "metadata": { "editable": true }, @@ -233,7 +227,7 @@ }, { "cell_type": "markdown", - "id": "bb734579", + "id": "1dbad69a", "metadata": { "editable": true }, @@ -245,7 +239,7 @@ }, { "cell_type": "markdown", - "id": "aba5029f", + "id": "2a16de00", "metadata": { "editable": true }, @@ -258,7 +252,7 @@ }, { "cell_type": "markdown", - "id": "6ac8d12b", + "id": "07115e56", "metadata": { "editable": true }, @@ -270,7 +264,7 @@ }, { "cell_type": "markdown", - "id": "7d3ac82a", + "id": "b90655a4", "metadata": { "editable": true }, @@ -280,7 +274,7 @@ }, { "cell_type": "markdown", - "id": "1eedadb6", + "id": "2ac208f1", "metadata": { "editable": true }, @@ -292,7 +286,7 @@ }, { "cell_type": "markdown", - "id": "61c29b5e", + "id": "a8197640", "metadata": { "editable": true }, @@ -304,7 +298,7 @@ }, { "cell_type": "markdown", - "id": "4cf9eba7", + "id": "7c72baae", "metadata": { "editable": true }, @@ -315,7 +309,7 @@ }, { "cell_type": "markdown", - "id": "0761eee3", + "id": "3c595093", "metadata": { "editable": true }, @@ -327,7 +321,7 @@ }, { "cell_type": "markdown", - "id": "ead917bf", + "id": "4dab1f87", "metadata": { "editable": true }, @@ -346,7 +340,7 @@ }, { "cell_type": "markdown", - "id": "92fe0780", + "id": "2a85bd46", "metadata": { "editable": true }, @@ -359,7 +353,7 @@ }, { "cell_type": "markdown", - "id": "396bf1e2", + "id": "5500dd61", "metadata": { "editable": true }, @@ -369,7 +363,7 @@ }, { "cell_type": "markdown", - "id": "6d5307de", + "id": "0072db82", "metadata": { "editable": true }, @@ -381,7 +375,7 @@ }, { "cell_type": "markdown", - "id": "45b68b6b", + "id": "078ec23d", "metadata": { "editable": true }, @@ -391,7 +385,7 @@ }, { "cell_type": "markdown", - "id": "8bec3f2b", + "id": "cc1760bc", "metadata": { "editable": true }, @@ -403,7 +397,7 @@ }, { "cell_type": "markdown", - "id": "80dc90da", + "id": "73d00905", "metadata": { "editable": true }, @@ -413,7 +407,7 @@ }, { "cell_type": "markdown", - "id": "64e3c687", + "id": "50dff40b", "metadata": { "editable": true }, @@ -425,7 +419,7 @@ }, { "cell_type": "markdown", - "id": "510d4d4c", + "id": "622bf5f5", "metadata": { "editable": true }, @@ -436,7 +430,7 @@ }, { "cell_type": "markdown", - "id": "f0b1c164", + "id": "48bfcf85", "metadata": { "editable": true }, @@ -448,7 +442,7 @@ }, { "cell_type": "markdown", - "id": "05896ad6", + "id": "07c395fe", "metadata": { "editable": true }, @@ -458,7 +452,7 @@ }, { "cell_type": "markdown", - "id": "bfa041c9", + "id": "d3ccdcb0", "metadata": { "editable": true }, @@ -470,7 +464,7 @@ }, { "cell_type": "markdown", - "id": "ae4e69aa", + "id": "c1ef9741", "metadata": { "editable": true }, @@ -480,7 +474,7 @@ }, { "cell_type": "markdown", - "id": "22a53165", + "id": "1646a521", "metadata": { "editable": true }, @@ -492,7 +486,7 @@ }, { "cell_type": "markdown", - "id": "02a2b1b8", + "id": "daa11d84", "metadata": { "editable": true }, @@ -512,7 +506,7 @@ }, { "cell_type": "markdown", - "id": "d1470cae", + "id": "78b271ce", "metadata": { "editable": true }, @@ -539,7 +533,7 @@ }, { "cell_type": "markdown", - "id": "fbc63e64", + "id": "9482d4e6", "metadata": { "editable": true }, @@ -551,7 +545,7 @@ }, { "cell_type": "markdown", - "id": "5475f4f0", + "id": "c7787334", "metadata": { "editable": true }, @@ -563,7 +557,7 @@ }, { "cell_type": "markdown", - "id": "7ccd0445", + "id": "a7c6c6e4", "metadata": { "editable": true }, @@ -579,7 +573,7 @@ }, { "cell_type": "markdown", - "id": "c40947ac", + "id": "dc9f4b6f", "metadata": { "editable": true }, @@ -597,7 +591,7 @@ }, { "cell_type": "markdown", - "id": "18e29324", + "id": "dbb092e9", "metadata": { "editable": true }, @@ -609,7 +603,7 @@ }, { "cell_type": "markdown", - "id": "6069e0fa", + "id": "47f695d0", "metadata": { "editable": true }, @@ -621,7 +615,7 @@ }, { "cell_type": "markdown", - "id": "2796afe6", + "id": "6ff6f849", "metadata": { "editable": true }, @@ -632,7 +626,7 @@ }, { "cell_type": "markdown", - "id": "2b66e25f", + "id": "3fab9d8e", "metadata": { "editable": true }, @@ -644,7 +638,7 @@ }, { "cell_type": "markdown", - "id": "86f9add1", + "id": "230d417b", "metadata": { "editable": true }, @@ -654,7 +648,7 @@ }, { "cell_type": "markdown", - "id": "ae97bea9", + "id": "ae3eea03", "metadata": { "editable": true }, @@ -666,7 +660,7 @@ }, { "cell_type": "markdown", - "id": "14510558", + "id": "97d7d08a", "metadata": { "editable": true }, @@ -680,7 +674,7 @@ }, { "cell_type": "markdown", - "id": "fbb54b4a", + "id": "dbcabc11", "metadata": { "editable": true }, @@ -692,7 +686,7 @@ }, { "cell_type": "markdown", - "id": "553845ce", + "id": "7278dcbd", "metadata": { "editable": true }, @@ -704,7 +698,7 @@ }, { "cell_type": "markdown", - "id": "e79fdc3c", + "id": "c16d222a", "metadata": { "editable": true }, @@ -716,7 +710,7 @@ }, { "cell_type": "markdown", - "id": "0713d61a", + "id": "0d85444e", "metadata": { "editable": true }, @@ -726,7 +720,7 @@ }, { "cell_type": "markdown", - "id": "2e522237", + "id": "4d26bab6", "metadata": { "editable": true }, @@ -738,7 +732,7 @@ }, { "cell_type": "markdown", - "id": "4baadc8b", + "id": "b6d57fdf", "metadata": { "editable": true }, @@ -750,7 +744,7 @@ }, { "cell_type": "markdown", - "id": "6e0fee06", + "id": "7a78e5dc", "metadata": { "editable": true }, @@ -762,7 +756,7 @@ }, { "cell_type": "markdown", - "id": "1d85d1c1", + "id": "6231367b", "metadata": { "editable": true }, @@ -776,7 +770,7 @@ }, { "cell_type": "markdown", - "id": "a6643a5f", + "id": "ab068594", "metadata": { "editable": true }, @@ -788,7 +782,7 @@ }, { "cell_type": "markdown", - "id": "f15d9044", + "id": "07d2f06b", "metadata": { "editable": true }, @@ -800,7 +794,7 @@ }, { "cell_type": "markdown", - "id": "658745bf", + "id": "d2382139", "metadata": { "editable": true }, @@ -812,7 +806,7 @@ }, { "cell_type": "markdown", - "id": "ba8bc828", + "id": "7d063f00", "metadata": { "editable": true }, @@ -822,7 +816,7 @@ }, { "cell_type": "markdown", - "id": "38512288", + "id": "5e119075", "metadata": { "editable": true }, @@ -834,7 +828,7 @@ }, { "cell_type": "markdown", - "id": "0a571ae1", + "id": "700eaedb", "metadata": { "editable": true }, @@ -844,7 +838,7 @@ }, { "cell_type": "markdown", - "id": "f26f46f8", + "id": "51e05fca", "metadata": { "editable": true }, @@ -856,7 +850,7 @@ }, { "cell_type": "markdown", - "id": "9e6c5896", + "id": "bba7f463", "metadata": { "editable": true }, @@ -866,7 +860,7 @@ }, { "cell_type": "markdown", - "id": "fa516251", + "id": "601577cc", "metadata": { "editable": true }, @@ -878,7 +872,7 @@ }, { "cell_type": "markdown", - "id": "10db7624", + "id": "ea31952c", "metadata": { "editable": true }, @@ -890,7 +884,7 @@ }, { "cell_type": "markdown", - "id": "7cdeda2b", + "id": "fc6c86a7", "metadata": { "editable": true }, @@ -902,7 +896,7 @@ }, { "cell_type": "markdown", - "id": "2b9a8aed", + "id": "ffe09390", "metadata": { "editable": true }, @@ -917,7 +911,7 @@ }, { "cell_type": "markdown", - "id": "758969d3", + "id": "22f4970c", "metadata": { "editable": true }, @@ -929,7 +923,7 @@ }, { "cell_type": "markdown", - "id": "d7203c02", + "id": "4ba751cb", "metadata": { "editable": true }, @@ -939,7 +933,7 @@ }, { "cell_type": "markdown", - "id": "16f3ca20", + "id": "87052e13", "metadata": { "editable": true }, @@ -951,7 +945,7 @@ }, { "cell_type": "markdown", - "id": "f7caf01e", + "id": "e24dea19", "metadata": { "editable": true }, @@ -961,7 +955,7 @@ }, { "cell_type": "markdown", - "id": "b1e5ad17", + "id": "6b52c737", "metadata": { "editable": true }, @@ -973,7 +967,7 @@ }, { "cell_type": "markdown", - "id": "587c347e", + "id": "904b93aa", "metadata": { "editable": true }, @@ -983,7 +977,7 @@ }, { "cell_type": "markdown", - "id": "5279b1cb", + "id": "439e197d", "metadata": { "editable": true }, @@ -995,7 +989,7 @@ }, { "cell_type": "markdown", - "id": "0c0d18ed", + "id": "f5658ed9", "metadata": { "editable": true }, @@ -1007,7 +1001,7 @@ }, { "cell_type": "markdown", - "id": "ba1b34c9", + "id": "6f99984d", "metadata": { "editable": true }, @@ -1019,7 +1013,7 @@ }, { "cell_type": "markdown", - "id": "b859b644", + "id": "eeb1373c", "metadata": { "editable": true }, @@ -1029,7 +1023,7 @@ }, { "cell_type": "markdown", - "id": "a6451ed1", + "id": "f3c557ba", "metadata": { "editable": true }, @@ -1041,7 +1035,7 @@ }, { "cell_type": "markdown", - "id": "6879be83", + "id": "412789d5", "metadata": { "editable": true }, @@ -1054,7 +1048,7 @@ }, { "cell_type": "markdown", - "id": "bda465e5", + "id": "65fbbb29", "metadata": { "editable": true }, @@ -1066,7 +1060,7 @@ }, { "cell_type": "markdown", - "id": "aeb97168", + "id": "f4cd65e4", "metadata": { "editable": true }, @@ -1076,7 +1070,7 @@ }, { "cell_type": "markdown", - "id": "d5339f3b", + "id": "9ee329c3", "metadata": { "editable": true }, @@ -1088,7 +1082,7 @@ }, { "cell_type": "markdown", - "id": "924aee00", + "id": "47023d81", "metadata": { "editable": true }, @@ -1098,7 +1092,7 @@ }, { "cell_type": "markdown", - "id": "856a72bf", + "id": "40d4cc36", "metadata": { "editable": true }, @@ -1110,7 +1104,7 @@ }, { "cell_type": "markdown", - "id": "ad9fe745", + "id": "e266851f", "metadata": { "editable": true }, @@ -1120,7 +1114,7 @@ }, { "cell_type": "markdown", - "id": "5a72fd42", + "id": "f4d0941c", "metadata": { "editable": true }, @@ -1132,7 +1126,7 @@ }, { "cell_type": "markdown", - "id": "569524a1", + "id": "6f4b2a9d", "metadata": { "editable": true }, @@ -1142,7 +1136,7 @@ }, { "cell_type": "markdown", - "id": "4e8d401f", + "id": "62cab30b", "metadata": { "editable": true }, @@ -1154,7 +1148,7 @@ }, { "cell_type": "markdown", - "id": "24230b58", + "id": "4c8c6398", "metadata": { "editable": true }, @@ -1164,7 +1158,7 @@ }, { "cell_type": "markdown", - "id": "fe2c5d6e", + "id": "f9c6ab8a", "metadata": { "editable": true }, @@ -1176,7 +1170,7 @@ }, { "cell_type": "markdown", - "id": "9b68b468", + "id": "b7945d33", "metadata": { "editable": true }, @@ -1188,7 +1182,7 @@ }, { "cell_type": "markdown", - "id": "bf6a5077", + "id": "80421efe", "metadata": { "editable": true }, @@ -1200,7 +1194,7 @@ }, { "cell_type": "markdown", - "id": "ddf09a27", + "id": "cc1fb4bf", "metadata": { "editable": true }, @@ -1212,7 +1206,7 @@ }, { "cell_type": "markdown", - "id": "e1665513", + "id": "c149bd15", "metadata": { "editable": true }, @@ -1224,7 +1218,7 @@ }, { "cell_type": "markdown", - "id": "e754746c", + "id": "4aeb6fad", "metadata": { "editable": true }, @@ -1240,7 +1234,7 @@ }, { "cell_type": "markdown", - "id": "922d0d8c", + "id": "fecdf631", "metadata": { "editable": true }, @@ -1252,7 +1246,7 @@ }, { "cell_type": "markdown", - "id": "acf89848", + "id": "7ffbaccd", "metadata": { "editable": true }, @@ -1262,7 +1256,7 @@ }, { "cell_type": "markdown", - "id": "12d22c90", + "id": "ba12c9f2", "metadata": { "editable": true }, @@ -1274,7 +1268,7 @@ }, { "cell_type": "markdown", - "id": "9dbcb6d7", + "id": "871cfd8e", "metadata": { "editable": true }, @@ -1292,7 +1286,7 @@ }, { "cell_type": "markdown", - "id": "b797b390", + "id": "0ad332cd", "metadata": { "editable": true }, @@ -1304,7 +1298,7 @@ }, { "cell_type": "markdown", - "id": "b78ab217", + "id": "5e7042e9", "metadata": { "editable": true }, @@ -1316,7 +1310,7 @@ }, { "cell_type": "markdown", - "id": "e0a0542d", + "id": "43b825ce", "metadata": { "editable": true }, @@ -1326,7 +1320,7 @@ }, { "cell_type": "markdown", - "id": "fd640b28", + "id": "58a4ed44", "metadata": { "editable": true }, @@ -1338,7 +1332,7 @@ }, { "cell_type": "markdown", - "id": "6a073b35", + "id": "202c5775", "metadata": { "editable": true }, @@ -1348,7 +1342,7 @@ }, { "cell_type": "markdown", - "id": "f7daf28e", + "id": "0eab64e4", "metadata": { "editable": true }, @@ -1360,7 +1354,7 @@ }, { "cell_type": "markdown", - "id": "d8e03fdc", + "id": "d17063fa", "metadata": { "editable": true }, @@ -1370,7 +1364,7 @@ }, { "cell_type": "markdown", - "id": "058aed61", + "id": "02cca57e", "metadata": { "editable": true }, @@ -1384,7 +1378,7 @@ }, { "cell_type": "markdown", - "id": "c7d35183", + "id": "d5a0e65b", "metadata": { "editable": true }, @@ -1396,7 +1390,7 @@ }, { "cell_type": "markdown", - "id": "bad6fd9a", + "id": "03f47788", "metadata": { "editable": true }, @@ -1407,7 +1401,7 @@ }, { "cell_type": "markdown", - "id": "1bd57074", + "id": "ab07b7cf", "metadata": { "editable": true }, @@ -1420,7 +1414,7 @@ { "cell_type": "code", "execution_count": 1, - "id": "9895174d", + "id": "f51e672d", "metadata": { "collapsed": false, "editable": true @@ -1447,7 +1441,7 @@ }, { "cell_type": "markdown", - "id": "0d7ad6dc", + "id": "e44be45e", "metadata": { "editable": true }, @@ -1458,7 +1452,7 @@ { "cell_type": "code", "execution_count": 2, - "id": "e52ec127", + "id": "b4786589", "metadata": { "collapsed": false, "editable": true @@ -1471,7 +1465,7 @@ }, { "cell_type": "markdown", - "id": "c66acc10", + "id": "af2dcc52", "metadata": { "editable": true }, @@ -1485,7 +1479,7 @@ { "cell_type": "code", "execution_count": 3, - "id": "85f5f060", + "id": "2bc65bc5", "metadata": { "collapsed": false, "editable": true @@ -1498,7 +1492,7 @@ }, { "cell_type": "markdown", - "id": "ef359561", + "id": "46bda600", "metadata": { "editable": true }, @@ -1509,7 +1503,7 @@ { "cell_type": "code", "execution_count": 4, - "id": "21b8437f", + "id": "9bdae7bf", "metadata": { "collapsed": false, "editable": true @@ -1519,7 +1513,7 @@ "name": "stdout", "output_type": "stream", "text": [ - "0.9958946686888259\n" + "0.9952638231265687\n" ] } ], @@ -1529,7 +1523,7 @@ }, { "cell_type": "markdown", - "id": "b1c814a4", + "id": "64eeaaef", "metadata": { "editable": true }, @@ -1540,7 +1534,7 @@ { "cell_type": "code", "execution_count": 5, - "id": "de8f1db6", + "id": "cafbda91", "metadata": { "collapsed": false, "editable": true @@ -1550,7 +1544,7 @@ "name": "stdout", "output_type": "stream", "text": [ - "0.008142188979400687\n" + "0.011761161707539526\n" ] } ], @@ -1564,7 +1558,7 @@ }, { "cell_type": "markdown", - "id": "421ff6ee", + "id": "831a5888", "metadata": { "editable": true }, @@ -1575,7 +1569,7 @@ { "cell_type": "code", "execution_count": 6, - "id": "77d5b744", + "id": "90f6a538", "metadata": { "collapsed": false, "editable": true @@ -1585,23 +1579,23 @@ "name": "stdout", "output_type": "stream", "text": [ - "[0.0476021 0.02689869 0.01088331 0.01783105 0.00544013 0.05110385\n", - " 0.02900389 0.01629703 0.05594058 0.02527366 0.00657884 0.04127087\n", - " 0.01925607 0.02221978 0.01212083 0.04919181 0.00745959 0.03110176\n", - " 0.010203 0.0076995 0.00298213 0.01702968 0.04557362 0.03192124\n", - " 0.06668218 0.0178392 0.00706728 0.0095239 0.00784983 0.05197707\n", - " 0.01519861 0.0134093 0.00291822 0.00311528 0.02036289 0.01136976\n", - " 0.0189559 0.04908155 0.01384493 0.01715895 0.01262581 0.00756465\n", - " 0.00473818 0.00224783 0.01773579 0.03804636 0.03945128 0.01662346\n", - " 0.05137822 0.00206124 0.06090176 0.01632212 0.01220987 0.06361921\n", - " 0.00318122 0.00362359 0.03177421 0.06554078 0.00123144 0.01091059\n", - " 0.04958045 0.00291334 0.01541622 0.00607264 0.05274561 0.007352\n", - " 0.06263415 0.01593612 0.00853836 0.01006042 0.00223784 0.02106518\n", - " 0.02410507 0.08294341 0.0043675 0.06502562 0.03422156 0.00213264\n", - " 0.02365779 0.01883403 0.00683222 0.01848399 0.02930957 0.02161016\n", - " 0.02746315 0.02774744 0.03591454 0.04814746 0.00568413 0.00215333\n", - " 0.03631783 0.02866734 0.01684326 0.00953152 0.01001378 0.00119895\n", - " 0.02603725 0.00127672 0.04770636 0.028797 ]\n" + "[0.00035753 0.04937621 0.02268114 0.03112297 0.01856502 0.05322899\n", + " 0.01397927 0.03999935 0.02508836 0.01834042 0.0652633 0.00887114\n", + " 0.01956921 0.01987248 0.06294313 0.01152476 0.00328431 0.03564082\n", + " 0.02337045 0.01743586 0.01278035 0.02400968 0.08388138 0.03270341\n", + " 0.00335956 0.01031903 0.09575469 0.00956774 0.00900879 0.01867985\n", + " 0.01191227 0.02090296 0.04045671 0.03582958 0.06692165 0.06615863\n", + " 0.06594872 0.03756493 0.00488992 0.01405237 0.00117071 0.0017567\n", + " 0.05006306 0.02545639 0.03456485 0.00373984 0.02576476 0.03530741\n", + " 0.00092902 0.0275742 0.05948007 0.01321652 0.18500705 0.00382166\n", + " 0.00327313 0.01853877 0.01771317 0.05293662 0.07199977 0.00836148\n", + " 0.01541649 0.00343257 0.00626797 0.05350297 0.01548272 0.05235058\n", + " 0.04310698 0.00225189 0.02356396 0.01690512 0.03467756 0.00064364\n", + " 0.02593596 0.00019607 0.0029508 0.0180194 0.06825695 0.01659559\n", + " 0.01971341 0.02012338 0.02241311 0.00135736 0.0095653 0.05695438\n", + " 0.00395659 0.07068033 0.02699873 0.00919237 0.02493299 0.00803115\n", + " 0.0293055 0.02178063 0.00594353 0.04081883 0.01325225 0.0386443\n", + " 0.01889695 0.02810253 0.0181166 0.01135924]\n" ] } ], @@ -1613,7 +1607,7 @@ }, { "cell_type": "markdown", - "id": "0afffa89", + "id": "dc364c27", "metadata": { "editable": true }, @@ -1634,7 +1628,7 @@ }, { "cell_type": "markdown", - "id": "83fc18dd", + "id": "1598259c", "metadata": { "editable": true }, @@ -1645,7 +1639,7 @@ { "cell_type": "code", "execution_count": 7, - "id": "c908e069", + "id": "ca994e68", "metadata": { "collapsed": false, "editable": true @@ -1655,15 +1649,15 @@ "name": "stdout", "output_type": "stream", "text": [ - "[ 2.02283241 0.15972118 3.84256187 1.89005305 -0.93145755]\n", + "[ 2.00507876 0.39026883 3.20764972 2.73806921 -1.39609089]\n", "Training R2\n", - "0.9959044445566834\n", + "0.9972493421341901\n", "Training MSE\n", - "0.010349061754867921\n", + "0.007021475481484069\n", "Test R2\n", - "0.9961996615568259\n", + "0.9976639055733267\n", "Test MSE\n", - "0.008771887357306985\n" + "0.00575158411598985\n" ] } ], @@ -1714,7 +1708,7 @@ }, { "cell_type": "markdown", - "id": "f69cf8d1", + "id": "7353f2e7", "metadata": { "editable": true }, @@ -1725,7 +1719,7 @@ { "cell_type": "code", "execution_count": 8, - "id": "03acb6ba", + "id": "05a066db", "metadata": { "collapsed": false, "editable": true @@ -1750,7 +1744,7 @@ }, { "cell_type": "markdown", - "id": "0d8db71d", + "id": "1f30de64", "metadata": { "editable": true }, @@ -1762,7 +1756,7 @@ }, { "cell_type": "markdown", - "id": "29fc4792", + "id": "80fa8b7d", "metadata": { "editable": true }, @@ -1791,7 +1785,7 @@ }, { "cell_type": "markdown", - "id": "5d2323e6", + "id": "7e92be20", "metadata": { "editable": true }, @@ -1816,7 +1810,7 @@ }, { "cell_type": "markdown", - "id": "084a05ce", + "id": "052e8c0c", "metadata": { "editable": true }, @@ -1836,7 +1830,7 @@ }, { "cell_type": "markdown", - "id": "2cf236cf", + "id": "d752c7f4", "metadata": { "editable": true }, @@ -1863,7 +1857,7 @@ }, { "cell_type": "markdown", - "id": "f7ef3d03", + "id": "4b40d092", "metadata": { "editable": true }, @@ -1876,7 +1870,7 @@ }, { "cell_type": "markdown", - "id": "30df9a47", + "id": "f8526e57", "metadata": { "editable": true }, @@ -1888,7 +1882,7 @@ }, { "cell_type": "markdown", - "id": "fa957ecb", + "id": "5cfb3455", "metadata": { "editable": true }, @@ -1899,7 +1893,7 @@ }, { "cell_type": "markdown", - "id": "c6b8f467", + "id": "363e0117", "metadata": { "editable": true }, @@ -1915,7 +1909,7 @@ { "cell_type": "code", "execution_count": 9, - "id": "a2480cf9", + "id": "4c7ecfc5", "metadata": { "collapsed": false, "editable": true @@ -2358,7 +2352,7 @@ }, { "cell_type": "markdown", - "id": "7643608b", + "id": "981f65fb", "metadata": { "editable": true }, @@ -2368,7 +2362,7 @@ }, { "cell_type": "markdown", - "id": "5e6e489d", + "id": "9ddcca79", "metadata": { "editable": true }, @@ -2383,7 +2377,7 @@ }, { "cell_type": "markdown", - "id": "ff073975", + "id": "02bed8b3", "metadata": { "editable": true }, @@ -2395,7 +2389,7 @@ }, { "cell_type": "markdown", - "id": "6a176186", + "id": "64033f1d", "metadata": { "editable": true }, @@ -2405,7 +2399,7 @@ }, { "cell_type": "markdown", - "id": "784ddba6", + "id": "1cfc52cc", "metadata": { "editable": true }, @@ -2421,7 +2415,7 @@ { "cell_type": "code", "execution_count": 10, - "id": "83686834", + "id": "06b67f41", "metadata": { "collapsed": false, "editable": true @@ -2438,7 +2432,7 @@ }, { "cell_type": "markdown", - "id": "dd641a05", + "id": "773210a0", "metadata": { "editable": true }, @@ -2451,7 +2445,7 @@ { "cell_type": "code", "execution_count": 11, - "id": "447d12ce", + "id": "34cb4217", "metadata": { "collapsed": false, "editable": true @@ -2459,7 +2453,7 @@ "outputs": [ { "data": { - "image/png": "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\n", + "image/png": "iVBORw0KGgoAAAANSUhEUgAAAiwAAAGdCAYAAAAxCSikAAAAOXRFWHRTb2Z0d2FyZQBNYXRwbG90bGliIHZlcnNpb24zLjguMCwgaHR0cHM6Ly9tYXRwbG90bGliLm9yZy81sbWrAAAACXBIWXMAAA9hAAAPYQGoP6dpAABcpUlEQVR4nO3dd3wUdf7H8dfuppGQBEIgoYQQOkEIEHpRUKRjOxX1FD31PBQL8POsp4DeiZ6onAXUs93pCUFBRUQhFpooSgkgIXQIJSGEkgZpu/P7Y5NIIIQkJJndzfv5eMxjJ5Pvzn6GUfbNzHy/X4thGAYiIiIiLsxqdgEiIiIiF6LAIiIiIi5PgUVERERcngKLiIiIuDwFFhEREXF5CiwiIiLi8hRYRERExOUpsIiIiIjL8zK7gOricDg4fPgwgYGBWCwWs8sRERGRCjAMg6ysLJo1a4bVev7rKB4TWA4fPkxERITZZYiIiEgVHDhwgBYtWpz39x4TWAIDAwHnAQcFBZlcjYiIiFREZmYmERERJd/j5+MxgaX4NlBQUJACi4iIiJu50OMceuhWREREXJ4Ci4iIiLg8BRYRERFxeR7zDIuIiLgvwzAoLCzEbrebXYpUM5vNhpeX10UPOaLAIiIipsrPzyclJYVTp06ZXYrUEH9/f5o2bYqPj0+V96HAIiIipnE4HOzduxebzUazZs3w8fHR4J8exDAM8vPzOXr0KHv37qVdu3blDg5XHgUWERExTX5+Pg6Hg4iICPz9/c0uR2pAvXr18Pb2Zv/+/eTn5+Pn51el/eihWxERMV1V/9Ut7qE6zq/+CxERERGXp8AiIiIiLk+BRURERFyeAouIiEglWCyWcpc77rijyvtu1aoVs2bNqlC7sj77+eefr/Jnuzr1EhKPZhgGn64/iN1h8IfYFnjblNFF5OKkpKSUrMfFxfH000+zffv2km316tWrlTqeeeYZ/vznP5fadr4Zjw3DwG634+VV+ms/Pz+/SmOjVPV9F0N/e4vHysot4N6PNvDXTzfz2MItjPzXKlbtPGp2WSJSDsMwOJVfaMpiGEaFagwPDy9ZgoODsVgspbatXLmS2NhY/Pz8aN26NdOnT6ewsLDk/dOmTaNly5b4+vrSrFkzHnzwQQAGDx7M/v37mTx5cskVk/IEBgaW+tzw8HACAgIAWL58ORaLhaVLl9KzZ098fX1ZtWoVgwcP5v7772fKlCmEhoZy5ZVXArBixQp69+6Nr68vTZs25bHHHitV8/neV5t0hUU80o4jWUz4cD170nPwsVkJ8LWxKy2b2979hSujw3hqdDQtG2nMBxFXc7rATvTTS0357MRnhuPvc3Ffi0uXLuXWW2/l1VdfZdCgQezevZt77rkHgKlTp/Lpp5/yyiuvMG/ePDp37kxqaiqbNm0CYOHChcTExHDPPfecc+Wkqh555BFmzpxJ69atadCgAQD/+c9/uPfee/nxxx8xDINDhw4xatQo7rjjDv773/+SlJTEn//8Z/z8/Jg2bVrJvs5+X21TYBGP8+Wmwzy6YDOn8u00C/Zj9q2xRDUKYNZ3O/jvT/uJTzzCiu1H+fOlUdw3uC0BvvrfQESqxz/+8Q8ee+wxbr/9dgBat27Ns88+yyOPPMLUqVNJTk4mPDycoUOH4u3tTcuWLenduzcAISEh2Gy2kisnF/Loo4/yt7/9rdS2xYsXM3jw4JKfn3nmmXOuhrRt25Z//vOfJT8/+eSTRERE8Prrr2OxWOjYsSOHDx/m0Ucf5emnny4ZQ+Xs99U2/U0tHqPA7mDGkiTe+3EvAAPaNuLVm7rTqL4vAFPHdubm3i155stEVu9K540fdvPp+oM8PrITV3drpuHARVxAPW8bic8MN+2zL9b69ev59ddf+cc//lGyzW63k5uby6lTp7jhhhuYNWsWrVu3ZsSIEYwaNYqxY8ee82xJRfz1r3895wHf5s2bl/q5Z8+e57zv7G3btm2jX79+pf4OHDBgANnZ2Rw8eJCWLVued1+1SYFFPEJaZi4TP97Ar/tOAHDf4Db837AO2KylQ0j7sEA+vKs3yxKP8PevEjlw/DST4hL46Of9TLuqM5c0DzajfBEpYrFYLvq2jJkcDgfTp0/nuuuuO+d3fn5+REREsH37duLj4/n222+57777ePHFF1mxYgXe3t6V+qzQ0FDatm1bbpviZ1rK22YYxjn/YCu+5XPm9rL2VZvc978KkSK/7D3OxI83cDQrj0BfL166MYZhnc9/OdVisTC8cziXtW/MO6v28MYPu1m3/wRjX1/NuJ4RPDy8A6FFV2VERCqjR48ebN++vdwgUa9ePa666iquuuoqJk6cSMeOHdmyZQs9evTAx8cHu91eixVDdHQ0CxYsKBVc1qxZQ2Bg4DlXbMykwCJuyzAM3vtxH88t2YbdYdAhLJA3b4slKrRi/wrw87Zx/+Xt+ENsC57/OokvEg4z79cDfLUlhUlD2zO+X6S6QYtIpTz99NOMGTOGiIgIbrjhBqxWK5s3b2bLli38/e9/54MPPsBut9OnTx/8/f358MMPqVevHpGRkYBzfJWVK1dy00034evrS2ho6Hk/Kysri9TU1FLb/P39CQoKqlTN9913H7NmzeKBBx7g/vvvZ/v27UydOpUpU6a41BxPrlOJSCXk5BXywNyNPLs4EbvD4OpuzfhsYv8Kh5UzNQ2ux79u6s4nE/rRuVkQWbmFPLs4kZH/WsXKHeoGLSIVN3z4cBYvXkx8fDy9evWib9++vPzyyyWBpEGDBvz73/9mwIABdO3ale+++44vv/ySRo0aAc6HZPft20ebNm1o3LhxuZ/19NNP07Rp01LLI488UumamzdvzpIlS/jll1+IiYlhwoQJ3HXXXec80Gs2i2FG36QakJmZSXBwMBkZGZVOl+Jedh/NZsKH69mZlo2X1cLfRnfi9v6tquWhWbvDYP66A7y4dDvHc/IBuDI6jL+N7kRkI3Pv34p4otzcXPbu3UtUVBR+fn5mlyM1pLzzXNHvb11hEbfyzW8pXP36j+xMy6ZJoC/z7unLHQOiqq2Hj81q4ebeLfnh4cHcOSAKm9VCfOIRrnx5Jf/8JomcvMIL70RERKqdAou4hUK7gxlfb2PCRxvIziukd1QIix8cSM9WITXyecH1vHl6bDTfPDSIQe1Cybc7mL18N5e/tJzPNx4yZdAkEZG6TIFFXF56dh63vfsLb63YA8CfB0Xxv7v70CSw5i8ftwsL5L939ubt22JpGeLPkcw8JsUlcP2bP7HlYEaNf76IiDgpsIhL25B8gjGvruanPcfw97Hxxi09eHJ0dK323rFYLAzrHM6yyZfy1+EdqOdtY/3+E1z1xmoe/XQz6dl5tVaLiEhdpcAiLskwDD78aR/j3vqJ1Mxc2jQOYNH9AxjdtalpNfl525g4pC0/PDyYa7o1wzAgbt0Bhry4nHdW7aHA7jCtNhERT6fAIi7ndL6d/5u/iae+2EqB3WBUl3C+uH8gbZuUPW16bQsP9mPWTd35dEI/LmkeRFZeIX//ahsjZq1khbpBi4jUCAUWcSn7j+Vw7ewfWbjxEDarhSdHdeKNW3pQ3wUnKOzZKoQvJg7k+eu60CjAh91Hc7j9vV+4+z+/si89x+zyREQ8igKLuIxvE48w5rXVJKVmEVrfh//d3Yc/X9rapScltFkt3NS7Jd8XdYP2slr4dlsaw15ZyQvqBi0iUm0UWMR0dofBS8u2c/d/15GVW0hsZEMWPzCIvq0bmV1ahZV0g570ezfoOct3M2Tmcj7beFDdoEXkggYPHsykSZPMLsNlKbCIqU7k5HPH+7/w2ve7ALijfyvm/rkv4cHuOeJl2yalu0GnZeUxOW4Tf5izhs0HT5pdnohUA4vFUu5yxx13VGm/Cxcu5Nlnn72o2u64444yaxoxYsRF7dcVuN6DAa7EYYc1r8KWBTD+cwg4/yRUUnmbD57k3o82cOjkaep523j+D124upvrzAxaVcXdoC9t35h3V+/ljR92sSH5JFe/8SM3xLbgr8M70jhQs0GLuKuUlJSS9bi4OJ5++mm2b99esq1evXql2hcUFODt7X3B/YaEVM9AmCNGjOD9998vtc3X9/x/55RVX0Vrrsi+qouusJTHaoOtn8ORLbDlU7Or8Sjzfknm+jk/cejkaVo18uezif09Iqycqbgb9Pf/93s36PnrDnL5TGc36PxCdYMWcUfh4eElS3BwMBaLpeTn3NxcGjRowPz58xk8eDB+fn589NFHHDt2jJtvvpkWLVrg7+9Ply5dmDt3bqn9nn1LqFWrVjz33HPceeedBAYG0rJlS95+++0L1ufr61uqxvDwcBo2bFjye4vFwptvvsnVV19NQEAAf//735k2bRrdunXjvffeo3Xr1vj6+mIYBsnJyVx99dXUr1+foKAgbrzxRo4cOVKyr/O9ryYosFxIt1ucr5s+NrcOD5FbYOeRTzfx2MIt5NsdXBkdxqIHBtIx3HMnrCzuBr3g3n50aR78ezfof61k+fY0s8sTcS2GAfk55izV+EX76KOP8uCDD7Jt2zaGDx9Obm4usbGxLF68mN9++4177rmH2267jbVr15a7n5deeomePXuyceNG7rvvPu69916SkpIuur6pU6dy9dVXs2XLFu68804Adu3axfz581mwYAEJCQkAXHPNNRw/fpwVK1YQHx/P7t27GTduXKl9lfW+mqBbQhdyyfWw9ElI2QRHEiEs2uyK3NaB46e493/r+e1QJlYL/N+wDtx7WRusVtftBVSdYiND+HziAD4pmg16z9Ec7nj/V4Z2asLfRkfTKlSzQYtQcAqea2bOZz9xGHyq5//DSZMmcd1115Xa9vDDD5esP/DAA3zzzTd88skn9OnT57z7GTVqFPfddx/gDEGvvPIKy5cvp2PHjud9z+LFi6lfv36pbY8++ihPPfVUyc+33HJLSVAplp+fz4cffkjjxo0BiI+PZ/Pmzezdu5eIiAgAPvzwQzp37syvv/5Kr169ynxfTVFguZCARtB+OCQthk1zYdjFPRBVVy3fnsakuAROniogJMCHV2/qzsB2de+ZoOJu0CO7NOXV73bynzX7+HZbGit3pHPnwCjuv7ytS445IyKV07Nnz1I/2+12nn/+eeLi4jh06BB5eXnk5eUREFB+QOratWvJevGtp7S08q/MDhkyhDlz5pTadvbzMWfXBxAZGVkqdGzbto2IiIiSsAIQHR1NgwYN2LZtW0lgOft9NUV/M1ZEzM3OwLJ5PlwxFWz6Y6soh8Pg9R928cq3OzAMiGkRzOxbY2neoN6F3+zBgut589SYaG7uHcEzi7excsdR3lyxm4UbDvLYyI5c0615nbnyJFKKt7/zSodZn11Nzg4iL730Eq+88gqzZs2iS5cuBAQEMGnSJPLz88sv6awHWC0WCw5H+c+/BQQE0LZt20rVV9Y2wzDKHAfr7O0XCl3VRd+8FdFuGNQLgexU2LMc2g01uyK3kHGqgMnzE/g+yfmvgVv6tGTq2Gh8vWwmV+Y62jYJ5D9/6sV329J49qtE9h87xZT5m/jw5/1MG9uZmIgGZpcoUrsslmq7LeNKVq1axdVXX82tt94KgMPhYOfOnXTq1Mnkys4vOjqa5ORkDhw4UHKVJTExkYyMDFPq1kO3FeHlA12ud67r4dsK2Xo4g7Gvr+b7pDR8vay8eH1Xnru2i8JKGSwWC0Ojw1g2+VIeGdEBfx8bG5NPcs3sH3nk000czdJs0CLurm3btsTHx7NmzRq2bdvGX/7yF1JTU2vks/Ly8khNTS21pKenV3o/Q4cOpWvXrvzxj39kw4YN/PLLL4wfP57LLruszFtKNU2BpaJibna+Jn0FuRnm1uLiFqw/yHWz15B8/BQRIfVYcG9/bugZceE31nG+XjbuG+ycDfra7s1LdYP+90p1gxZxZ0899RQ9evRg+PDhDB48mPDwcK655poa+axvvvmGpk2blloGDhxY6f1YLBY+//xzGjZsyKWXXsrQoUNp3bo1cXFxNVB1BeoxPGTM8MzMTIKDg8nIyCAoqAa6yBoGzO4LR5Ng7L8g9o7q/ww3l1do59nFiXz0czIAgzs0Zta4bjTw9zG5Mve0fv8Jpi3aypZDzoDcunEAT42JZkiHJiZXJlJ9cnNz2bt3L1FRUfj5uecI13Jh5Z3nin5/6wpLRVksv19lSZhbfts66PDJ09z41s989HMyFgtMGtqO927vpbByEWIjG/LFxAH88w9dCa3vw56jOfzp/V+564Nf2avZoEWkjlFgqYyu48BihQM/w/E9ZlfjMn7clc6Y11az6cBJgut5894dvZg0tL16uVQDq9XCjb0i+P7hwdw90Dkb9HdJaQx7ZQUzvt5GtmaDFpE6QoGlMoKaQushzvVN88ytxQUYhsGc5bu57d21HM/Jp3OzIBY/MFC3LGpAkJ83fxsTzTeTLuXS9o0psBu8tWIPQ2YuZ8H6gzgcHnFnV0TkvBRYKqtkqP65cIG+8J4sM7eACR+t54VvknAYcENsCxbc25+IkOobx0DO1bZJff7zp168M74nkY38OZqVx/99sonr5qxh04GTZpcnIlJjFFgqq+No8A2Ck8mQvMbsakyxPTWLq1//kaVbj+BjszLjui788/qu+Hmry3JtOLMb9KMjOuLvYyPhgHM26L9+som0rFyzSxQRqXYKLJXlXQ+ir3au18GHb79IOMQ1b/zI3vQcmgX78cmEftzcu2WZoyFKzfL1snHv4Db88PBgruvunOn6k/UHuXzmCt5euVvdoMWteEiHVTmP6ji/CixVUXxbKPFz5wyfdUCB3cH0L7fy0LwEThfYGdQulMUPDtJIrC4gLMiPl8d1Y8G9/enaIpjsvEKeW5LEiFkr+UGzQYuLKx56/tSpUyZXIjWp+PyePdVAZWgclqowDHi1G5zYB9e+DTHjLvQOt5aWmct9/9vAuv0nALh/SFsmX9kem3oBuRyHw+DT9Qf559Ik0rOdc5Rc3rEJT42JJkqzQYuLSklJ4eTJkzRp0gR/f39dsfUghmFw6tQp0tLSaNCgAU2bNj2nTUW/v6sUWGbPns2LL75ISkoKnTt3ZtasWQwaNKjMtgsXLmTOnDkkJCSQl5dH586dmTZtGsOHDy9p88EHH/CnP/3pnPeePn26wgMJ1WpgAVj+PCyf4ew1NP7zmv88k6zdc4yJH28kPTuPQF8vXh7XjSujw8wuSy4gM7eA177byfs/7qPQYeBts3DnwCgeuLydZoMWl2MYBqmpqZw8edLsUqSGNGjQgPDw8DLDaEW/vyv9N1dcXByTJk1i9uzZDBgwgLfeeouRI0eSmJhIy5Ytz2m/cuVKrrzySp577jkaNGjA+++/z9ixY1m7di3du3cvaRcUFMT27dtLvdelRz2MuckZWPYsh4xDENzc7IqqlWEYvLt6LzO+TsLuMOgYHsicW2P1r3Q3EeTnzZOjoxnXqyXPLk5kxY6jvLViDws3HOLRER25rrtmgxbXYbFYaNq0KU2aNKGgoMDscqSaeXt7Y7NdfKeMSl9h6dOnDz169GDOnDkl2zp16sQ111zDjBkzKrSPzp07M27cOJ5++mnAeYVl0qRJF5Wua/0KC8D7o2D/j3DFVBg0pXY+sxZk5xXy6Keb+WpLCgDXdGvGc9d1wd9H/zJ3R4Zh8H1SGs8uTmTfMed95G4RDZh2VWe66RkkETFZjQzNn5+fz/r16xk2bFip7cOGDWPNmop18XU4HGRlZRESElJqe3Z2NpGRkbRo0YIxY8awcePGcveTl5dHZmZmqaXWFQ/Vv2mu87kWD7ArLZtr3viRr7ak4GW18MzVnXllXDeFFTdmsVi4olMYSydfymMjOxJQ1A36mjd+5GF1gxYRN1GpwJKeno7dbicsrPQzDGFhYRWeJvull14iJyeHG2+8sWRbx44d+eCDD1i0aBFz587Fz8+PAQMGsHPnzvPuZ8aMGQQHB5csEREmzAYcfTV41YP0HXBoQ+1/fjX7eksKV7++ml1p2YQF+RL3l76M79dKD8B5CF8vGxMuK+oG3cN5C/NTdYMWETdRpW7NZ3+BGYZRoS+1uXPnMm3aNOLi4mjS5Pfh2/v27cutt95KTEwMgwYNYv78+bRv357XXnvtvPt6/PHHycjIKFkOHDhQlUO5OH5B0GmMc33Tx7X/+dWk0O7guSXbuPd/G8jJt9MnKoTFDwwiNjLkwm8Wt9MkyI+Xb+zGwvv6E3N2N+gkdYMWEddUqcASGhqKzWY752pKWlraOVddzhYXF8ddd93F/PnzGTp0aPlFWa306tWr3Cssvr6+BAUFlVpMUXxbaMunUJhnTg0X4WhWHre+u5a3Vzonc7zn0tb87+4+NA70NbkyqWk9Wjbks/sG8M/ruxJa35c96Tn86YNfuVOzQYuIC6pUYPHx8SE2Npb4+PhS2+Pj4+nfv/953zd37lzuuOMOPv74Y0aPHn3BzzEMg4SEhDL7a7uc1oMhsBnknoQd35hdTaWs33+CMa+t4uc9xwnwsTH7jz14YlQnvGwaT7CusFot3Ngzgh8evox7Lm2Nl9XC98WzQS/ZRlauemyIiGuo9DfTlClTeOedd3jvvffYtm0bkydPJjk5mQkTJgDOWzXjx48vaT937lzGjx/PSy+9RN++fUlNTSU1NZWMjIySNtOnT2fp0qXs2bOHhIQE7rrrLhISEkr26dKsNuha9DyOm8zgbBgG/1mzj5ve/okjmXm0bVKfL+4fyKgubhAQpUYE+nnzxKhOLJ18KYM7FM0GvXIPl7+0gk/WHdBs0CJiukoHlnHjxjFr1iyeeeYZunXrxsqVK1myZAmRkZGAc8TC5OTkkvZvvfUWhYWFTJw4kaZNm5YsDz30UEmbkydPcs8999CpUyeGDRvGoUOHWLlyJb17966GQ6wFxUP171wGOenm1nIBp/ILmRyXwNRFWymwG4zu0pTPJw6gbZP6ZpcmLqBN4/p88KfevHdHT6JCAzialcdfP93MtXPWsDH5hNnliUgdpqH5q8vbQ+DwBhjxPPS9t/Y/vwL2pecw4aP1JKVmYbNaeHxkR+4aGKVeQFKmvEI77/+4j9e+20lOvh2AP/RowaMjOtAkyIUHdRQRt1Ij47BIOYqvsiS4Zm+h+MQjjH19NUmpWYTW9+Xju/tw96DWCityXmd2g/5DjxYALNhwkCEzl/PWCnWDFpHapSss1eXUcZjZHhwFcO8aCOtc+zWUwe4weCV+B6//sAuAnpENeeOPPQjTv5ClkjYmn2Daoq1sOuh8/iwqNICnxnTi8o6aW0pEqk5XWGqbfwi0L5rQ0UWushzPyeeO938pCSt/GtCKuff0VViRKule1A36xaJu0HvTc7jzg3Xc8f4v7D6abXZ5IuLhFFiqU/Ftoc3zwV5oaimbDpxk7GurWbUznXreNv51Uzemju2Mt7osy0WwWi3ccEY3aG+bheXbjzJi1kqeUzdoEalB+vaqTm2vBP9GkJMGu783pQTDMJj7SzI3vPkTh06eJio0gM8nDuDqbp41m7SYq6Qb9KRLGVLUDfrtlXsYMlPdoEWkZiiwVCcvH+hyg3N909xa//jcAjuPLtjM4wu3kG93MCw6jC/uH0CH8MBar0XqhtaN6/P+Gd2g07PVDVpEaoYeuq1uhxPg7cvA5gsP74B6DWrlYw8cP8WEj9az9XAmVgv8dXhHJlymXkBSe/ILHbz/415ePaMb9HU9mvPYiI7qBi0i56WHbs3SNAaaRIM9D7Z+Visf+cP2NMa8tpqthzMJCfDhw7v6cO/gNgorUqt8vKz85bI2/PDXwVwf6+wGvXDDIYbMXM6bK3aTV2g3uUIRcWcKLNXNYvl9QsQavi3kcBjM+nYHd37wKxmnC4iJaMDiBwYyoG1ojX6uSHmaBPox84YYPruvPzERDcjJt/P810kMf2Ul3ycdMbs8EXFTuiVUE7JS4eVOYDjggQ3QqE21f8TJU/lMjkvgh+1HAbi1b0ueGhONr5et2j9LpKocDoOFGw/xwjdJHM1yzmY+uENjnhoTTZvGmg5CRHRLyFyB4dDmcud6DVxl+e1QBmNfX80P24/i62Vl5g0x/P2aLgor4nKsVgvXx7bg+/+7jL9c9ns36OGvrOQfXyWqG7SIVJgCS00puS00DxzVN4T5J+sO8Ic5azhw/DQRIfVYeF//kucFRFxVoJ83j490doO+vGMTCh0G/161lyEzVzBf3aBFpAIUWGpKx9HgGwwZB2D/6oveXV6hnSc+28JfP91MXqGDyzs2YfH9g+jcLLgaihWpHa0b1+e9O3rx/h29aF3UDfqRTzdz7ewf2aBu0CJSDgWWmuJdDzpf41zfNO+idnXo5GlufPMnPl6bjMUCU65szzvjexLs733xdYqYYEjHJnwz6VKeGNWR+r5ebDqYwXWz1zAlLoEjmblmlyciLkiBpSYVD9Wf+AXk51RpF6t3pjP2tdVsOphBA39v3r+jFw9e0Q6rVV2Wxb35eFm559I2fP/wZdxQ3A164yEun7mcOcvVDVpESlNgqUkRfSCkNeRnw7YvK/VWh8PgjR92Mf69tRzPyeeS5kF8ef9ABndoUkPFipijSaAfL94Qw+cTB9CtqBv0C984u0F/m3gED+nIKCIXSYGlJp05JkslZnDOzC3gLx+t58Wl23EYMK5nBJ9O6E9EiH8NFSpivm4RDVh4b39euiGGxoG+7Dt2irv/u4473v+VXWmaDVqkrlNgqWldxzlf966EjIMXbJ6UmslVr60mPvEIPl5Wnr+uCy9c3xU/b3VZFs9ntVr4Q2wLfnh4cEk36BU7nLNBf/jzfrPLExETKbDUtIaREDkQMC748O0XCYe49o017Dt2iuYN6vHphH7c1Ltl7dQp4kLq+3rx+MhOLJt8WUk36Ge/TGT/sao9CyYi7k+BpTZ0O2Oo/jLux+cXOpi2aCsPzUvgdIGdQe1C+fKBgXRt0aB26xRxMVGhAbx7e08Gtg0l3+7g719tM7skETGJAkttiL4avP3h2C44uK7Ur45k5nLzv3/mgzX7AHjg8rZ88KfehAT4mFCoiOuxWCxMHRuNl9VCfOIRVuw4anZJImICBZba4BsIncY6188Yqv/nPccY/epq1u8/QaCfF++M78n/DeuATV2WRUppFxbI7f1bATD9y63kF1bf6NEi4h4UWGpLcW+h3xZgFOTy75V7+OM7a0nPzqNjeCBf3j+QodFh5tYo4sIeGtqO0Po+7Dmaw3+KrkiKSN2hwFJboi6FoOaQe5J33p3NP5Zsw+4wuLZ7cz67bwCtQgPMrlDEpQX5efPI8I4A/Ou7naRlaURckbpEgaW2WG0cb3stAFGHFuFts/Ds1Z15+cYY6vmoy7JIRVwf24KuLYLJzivkn99sN7scEalFCiy1ZMmWFMavaw3AYNsmFoxvy239WmGx6HkVkYqyWi1Mv6ozAJ+uP8hGTZgoUmcosNSwQruDf3yVyH3/28Bv+eHs8u6AFw66Ho83uzQRt9S9ZUOuL5p7aNqirTgcGrpfpC5QYKlBaVm5/PGdtfx71V4A/nJZa6KG3u38ZcLcct4pIuV5ZESHklmeP11/4RGkRcT9KbDUkHX7jjPm1dWs3Xuc+r5ezPljDx4f2Qlbl+vB5gNHtkDqFrPLFHFLTQL9eOiKdgC88E0SGacLTK5IRGqaAks1MwyDD37cy01v/0xaVh7tmtTni/sHMLJLU2cD/xBoP8K5foGh+kXk/G7v34rWjQM4lpPPq9/tNLscEalhCizV6FR+IZPiEpj2ZSKFDoMxXZvy+cQBtGlcv3TDbrc4XzfPB3th7Rcq4gF8vKxMG+t8APc/a/ax80iWyRWJSE1SYKkme9NzuPaNNXyRcBgvq4Wnx0Tz2s3dCfD1Ordx26HgHwo5abD7u9ovVsRDXNq+MVdGh1HoMJj+ZSJGGXN1iYhnUGCpBsu2pnLVa6vZfiSLxoG+fPznvtw5MOr8XZZt3tD1Rud6wse1V6iIB3pqdDQ+XlZW70pn6dYjZpcjIjVEgeUi2B0G//wmiXs+XE9WXiG9WjXkqwcG0jsq5MJvLh6qf/sSOK2xJESqqmUjf+4Z5Bzj6O9fJZJbYDe5IhGpCQosVXQsO4/b3/uF2ct3A3DXwCg+/nNfmgT5VWwH4V2gSWew58NvC2uwUhHPd9+QNjQN9uPgidO8vXKP2eWISA1QYKmChAMnGfvaalbvSsffx8ZrN3fnqTHReNsq8cdpsUC3oqssmzQmi8jF8Pfx4olRnQCYvXwXh06eNrkiEaluCiyVYBgG/1u7nxvf/InDGbm0Dg3g84kDGBvTrGo77HIjWGxw8FdIV7dMkYsxpmtTekeFkFvg4LmvtpldjohUMwWWCsotsPPXTzfz5Ge/kW93MLxzGF/cP4D2YYFV32lgGLS9wrmuMVlELorFYmHa2M5YLfDVlhTW7E43uyQRqUYKLBWQfOwU181ew6frD2K1wOMjO/LmrbEE+nlf/M6LH77dHAcOx8XvT6QOi24WxB/7RAIwfVEihXb9PyXiKRRYLuCHpDTGvr6axJRMGgX48NFdffjLZW2qb5blDqPALxgyDsC+VdWzT5E6bMqV7Wng7832I1n8b22y2eWISDVRYCnHqfxCHlmwmYzTBXSLaMDiBwfSv21o9X6Itx90vs65rodvRS5awwAfHh7WAYCXlm3nWHaeyRWJSHVQYCmHv48Xr97UnfH9Ion7S1+aBtermQ8qHqo/cRHkZdfMZ4jUITf3bkmnpkFk5hYyc9kOs8sRkWqgwHIB/do04pmrL8HXy1ZzH9KiF4S0gYIc2Lao5j5HpI6wWS1Mv8o5z9C8X5P57VCGyRWJyMVSYHEFFsvvD99qqH6RatE7KoSrYpphGDB10VbNMyTi5hRYXEXMOOfrvlVwUg8KilSHJ0Z1wt/Hxvr9J/gi4bDZ5YjIRVBgcRUNWkKrQc71zXHm1iLiIcKD/Zg4pC0Azy3ZRnZeockViUhVKbC4kuKHbxPmgi5fi1SLuwZGEdnIn7SsPF7/fpfZ5YhIFSmwuJJOV4F3ABzf7RyuX0Qump+3jadGRwPw7uo97E3PMbkiEakKBRZX4lsfoq9yruvhW5Fqc0WnJlzWvjEFdoNnFyeaXY6IVIECi6sp7i20dSEU5Jpbi4iHsFgsPD02Gm+bhe+T0vg+6YjZJYlIJSmwuJpWgyCoBeRmwPYlZlcj4jHaNK7PnQOiAHjmy0TyCu0mVyQilaHA4mqs1t+7OGuofpFqdf/lbWkc6Mu+Y6d4b/U+s8sRkUpQYHFFxbeFdn0HWbp0LVJdAv28eWxERwBe+34nRzJ121XEXSiwuKLQds7h+g07bPnE7GpEPMq13ZvTvWUDTuXbef7rJLPLEZEKqlJgmT17NlFRUfj5+REbG8uqVavO23bhwoVceeWVNG7cmKCgIPr168fSpUvPabdgwQKio6Px9fUlOjqazz77rCqleY7iqyy6LSRSraxF8wxZLPDZxkOs23fc7JJEpAIqHVji4uKYNGkSTz75JBs3bmTQoEGMHDmS5OSyh5NfuXIlV155JUuWLGH9+vUMGTKEsWPHsnHjxpI2P/30E+PGjeO2225j06ZN3Hbbbdx4442sXbu26kfm7i65Dmy+cOQ3SNlsdjUiHqVriwaM6xkBOOcZsjs0UKOIq7MYlZwRrE+fPvTo0YM5c+aUbOvUqRPXXHMNM2bMqNA+OnfuzLhx43j66acBGDduHJmZmXz99dclbUaMGEHDhg2ZO7diVxgyMzMJDg4mIyODoKCgShyRC5t/OyR+Dn3vgxEV+7MVkYpJz85jyMzlZOUW8ty1XbilT0uzSxKpkyr6/V2pKyz5+fmsX7+eYcOGldo+bNgw1qxZU6F9OBwOsrKyCAkJKdn2008/nbPP4cOHl7vPvLw8MjMzSy0ep3io/s3zwV5gbi0iHia0vi+Th7YH4MWlSWSc0v9jIq6sUoElPT0du91OWFhYqe1hYWGkpqZWaB8vvfQSOTk53HjjjSXbUlNTK73PGTNmEBwcXLJERERU4kjcRJvLIaAxnEqHXd+aXY2Ix7mtXyTtw+pz4lQBr3y7w+xyRKQcVXro1mKxlPrZMIxztpVl7ty5TJs2jbi4OJo0aXJR+3z88cfJyMgoWQ4cOFCJI3ATNm/oUhTsNFS/SLXztlmZOrYzAB/+vJ+kVA+8UiviISoVWEJDQ7HZbOdc+UhLSzvnCsnZ4uLiuOuuu5g/fz5Dhw4t9bvw8PBK79PX15egoKBSi0fqVtRbaMc3cEq9GUSq24C2oYy8JBy7w2Daoq1U8rE+EakllQosPj4+xMbGEh8fX2p7fHw8/fv3P+/75s6dyx133MHHH3/M6NGjz/l9v379ztnnsmXLyt1nnRHeBcK6gD3fOb+QiFS7J0Z1wtfLys97jrNkS8Vub4tI7ar0LaEpU6bwzjvv8N5777Ft2zYmT55McnIyEyZMAJy3asaPH1/Sfu7cuYwfP56XXnqJvn37kpqaSmpqKhkZGSVtHnroIZYtW8YLL7xAUlISL7zwAt9++y2TJk26+CP0BMVXWRI0JotITYgI8WfCZW0A+MdXiZzO1zxDIq6m0oFl3LhxzJo1i2eeeYZu3bqxcuVKlixZQmRkJAApKSmlxmR56623KCwsZOLEiTRt2rRkeeihh0ra9O/fn3nz5vH+++/TtWtXPvjgA+Li4ujTp081HKIH6HIDWGxwaB2k7zS7GhGPdO/gNjRvUI/DGbnMWbHb7HJE5CyVHofFVXnkOCxn+nic8zmWgVNg6FSzqxHxSF9vSeHe/23Ax8vKd1MuIyLE3+ySRDxejYzDIiaKucn5ujkOHLpcLVITRlwSTv82jcgvdPD3rxLNLkdEzqDA4i7ajwS/YMg8BHtXml2NiEeyWCxMHdsZm9XC0q1HWLXzqNkliUgRBRZ34e0Hl/zBua4JEUVqTIfwQG7r63wmb/qXiRTYHSZXJCKgwOJeYoqG6t/2JeRlmVuLiAebfGV7QgJ82JWWzX9/2m92OSKCAot7adETGrWFglOQuMjsakQ8VnA9bx4Z3gGAWfE7OJqVZ3JFIqLA4k4sFogpGpNFt4VEatQNPSPo0jyYrLxCXlyaZHY5InWeAou7ibkJsMC+VXBCl6pFaorNamHaVc55huavO0jCgZPmFiRSxymwuJvgFhB1qXN9c5y5tYh4uNjIhlzXozkA0xZtxeHwiGGrRNySAos7OvO2kGeM+yfish4b0ZEAHxsJB06yYMNBs8sRqbMUWNxRp7HgHQDH98CBtWZXI+LRmgT58eAV7QB44ZvtZOYWmFyRSN2kwOKOfOtD9NXO9YSPza1FpA7404AoWocGkJ6dx2vfaT4vETMosLir4hmct34OBadNLUXE0/l4WXlqbDQA7/+4j11p2SZXJFL3KLC4q8iBENwS8jJg+xKzqxHxeEM6NGFopyYUOgymf7kVD5k3VsRtKLC4K6sVYsY51xM0JotIbfjb6Gh8bFZW7UwnPvGI2eWI1CkKLO6suLfQ7u8gK9XcWkTqgFahAdw9KAqAZ79KJLdAM6eL1BYFFnfWqA1E9AHDAZvnm12NSJ0wcUhbwoJ8OXD8NO+s2mN2OSJ1hgKLu4u5yfmqMVlEakWArxdPjOoEwBs/7ObwST30LlIbFFjcXefrwOYLaYmQssnsakTqhKtimtGrVUNOF9iZ8bXmGRKpDQos7q5eA+g4yrmuCRFFaoXF4pxnyGqBLzcd5uc9x8wuScTjKbB4gphbnK9bPgG7RuEUqQ2dmwVzc++WgHOeoUK7w+SKRDybAosnaHM51A+DU8dgZ7zZ1YjUGQ8P60BwPW+SUrOY+0uy2eWIeDQFFk9g84IuNzjXN2mofpHa0jDAh4eHtQdg5rIdnMjJN7kiEc+lwOIpuhXdFtr+DZw6bm4tInXIzb1b0jE8kIzTBcxctt3sckQ8lgKLpwjrDOFdwVEAvy0wuxqROsPLZmXaVZ0B+PiXZH47lGFyRSKeSYHFkxSPfKsZnEVqVd/WjRjTtSmGgeYZEqkhCiyepMsNYPWCwxvgqC5Ni9SmJ0Z1op63jV/3nWDRpsNmlyPicRRYPEn9xtD2Sue6rrKI1KpmDeoxcUgbAGYsSSInr9DkikQ8iwKLp+lWdFto83xwaGI2kdp096DWRITUIzUzlzd+2GV2OSIeRYHF07QfAX4NIOsw7F1hdjUidYqft42nRkcD8M6qvexLzzG5IhHPocDiabx8ocv1zvUEDdUvUtuujA5jULtQ8u0O/v5VotnliHgMBRZPVDxU/7YvITfT3FpE6hiLxcLUsZ3xslr4dlsaP2xPM7skEY+gwOKJmveA0PZQeBoSvzC7GpE6p22T+vxpQCsAnv0ykfxCzTMkcrEUWDyRxQIxNznXNYOziCkevKIdofV92ZOew/s/7jW7HBG3p8DiqbreBFhg/49wYp/Z1YjUOYF+3jw6ogMAr363k7TMXJMrEnFvCiyeKrg5tL7Mub5pnrm1iNRRf+jRgm4RDcjJt/P8N0lmlyPi1hRYPFnxw7eb5oKGChepdVarhelF8wwt3HCI9ftPmFyRiPtSYPFkncaAT33nLaHkn82uRqROiolowI09WwAwbdFW7A7940GkKhRYPJlPAERf41zfpKH6Rczy1+EdCfT1YsuhDD5Zd8DsckTckgKLpyseqn/r51Bw2tRSROqqxoG+PDS0HQD/XLqdjNMFJlck4n4UWDxdy/7QoCXkZULSV2ZXI1Jn3d6/FW2b1Od4Tj6zvt1hdjkibkeBxdNZrUVdnNEMziIm8rZZmTrWOc/Qf3/az44jWSZXJOJeFFjqguJB5Pb8AJkp5tYiUocNateY4Z3DsDsMpi3aiqHeeyIVpsBSFzRqAxF9wXDA5jizqxGp0/42OhofLytrdh/jm99SzS5HxG0osNQVxQ/fakwWEVNFhPgz4dLWAPz9q22czrebXJGIe1BgqSs6XwtefnA0CVISzK5GpE67d3BbmgX7cejkad5audvsckTcggJLXeEXDB1HO9cTNCGiiJnq+dh4crTzAdw5y3dz8MQpkysScX0KLHVJ8VD9Wz6BwnxzaxGp40Z1Cadv6xDyCh3846ttZpcj4vIUWOqS1oOhfjicPg47l5ldjUidZrFYmHZVZ6wW+Pq3VH7clW52SSIuTYGlLrF5QdcbnOubdFtIxGwdw4O4rW8kANO/3EqB3WFyRSKuS4Glrim+LbRjKeQcM7cWEWHKlR1o6O/NjiPZfPTzfrPLEXFZCix1TVg0NI0BRwH89qnZ1YjUecH+3vx1eEcAXo7fwbHsPJMrEnFNCix1UfFVFt0WEnEJ43pF0LlZEFm5hby4dLvZ5Yi4JAWWuqjL9WD1gsMbIS3J7GpE6jyb1cL0qzoDELfuAJsPnjS3IBEXpMBSFwWEQrvhzvVNmhBRxBX0bBXCNd2aYRgwbdFWHA6NSC1ypioFltmzZxMVFYWfnx+xsbGsWrXqvG1TUlK45ZZb6NChA1arlUmTJp3T5oMPPsBisZyz5ObmVqU8qYjiofo3zweHhgYXcQWPj+qEv4+NDckn+TzhkNnliLiUSgeWuLg4Jk2axJNPPsnGjRsZNGgQI0eOJDk5ucz2eXl5NG7cmCeffJKYmJjz7jcoKIiUlJRSi5+fX2XLk4pqNxzqNYSsFOcsziJiurAgPx64vB0AM75OIiu3wOSKRFxHpQPLyy+/zF133cXdd99Np06dmDVrFhEREcyZM6fM9q1ateJf//oX48ePJzg4+Lz7tVgshIeHl1qkBnn5wCXXO9c1VL+Iy7hzYCtaNfLnaFYer3+/y+xyRFxGpQJLfn4+69evZ9iwYaW2Dxs2jDVr1lxUIdnZ2URGRtKiRQvGjBnDxo0by22fl5dHZmZmqUUqqfi2UNJiyM0wtxYRAcDXy8bTY53zDL334152H802uSIR11CpwJKeno7dbicsLKzU9rCwMFJTU6tcRMeOHfnggw9YtGgRc+fOxc/PjwEDBrBz587zvmfGjBkEBweXLBEREVX+/DqrWQ8I7QCFuZD4hdnViEiRyzuGcXnHJhTYDZ75MhHD0AO4IlV66NZisZT62TCMc7ZVRt++fbn11luJiYlh0KBBzJ8/n/bt2/Paa6+d9z2PP/44GRkZJcuBAweq/Pl1lsXy+1UW3RYScSlPjYnG22ZhxY6jfJ+UZnY5IqarVGAJDQ3FZrOdczUlLS3tnKsuF1WU1UqvXr3KvcLi6+tLUFBQqUWqoOs4sFgheQ0c32t2NSJSJCo0gLsGtgbgmcWJ5BaoN5/UbZUKLD4+PsTGxhIfH19qe3x8PP3796+2ogzDICEhgaZNm1bbPuU8gpo5Z3EG2DTP1FJEpLT7L29Lk0Bf9h87xbur9Q8KqdsqfUtoypQpvPPOO7z33nts27aNyZMnk5yczIQJEwDnrZrx48eXek9CQgIJCQlkZ2dz9OhREhISSExMLPn99OnTWbp0KXv27CEhIYG77rqLhISEkn1KDTtzqH6HZosVcRX1fb14fJRznqHXv99FSsZpkysSMY9XZd8wbtw4jh07xjPPPENKSgqXXHIJS5YsITLSOUV6SkrKOWOydO/evWR9/fr1fPzxx0RGRrJv3z4ATp48yT333ENqairBwcF0796dlStX0rt374s4NKmwjqPBJxBO7ofkn6DVALMrEpEi13Rrzkc/J7N+/wme/zqJf93U/cJvEvFAFsNDHj/PzMwkODiYjIwMPc9SFV9MhI0fQfdb4eo3zK5GRM7w26EMxr6+GsOATyb0o1erELNLEqk2Ff3+1lxC4lR8W2jrF5B/ytxaRKSUS5oHc1OvlgBM/WIrds0zJHWQAos4tewHDSIhPwuSvjK7GhE5y8PD2hPk50ViSiZzfyl7KhQRT6bAIk5WK8QUjcmiGZxFXE6j+r5MubI9ADOXbefkqXyTKxKpXQos8ruYm5yve5ZD5mFTSxGRc93aN5IOYYGcPFXAy/E7zC5HpFYpsMjvQqKgZX8wHLA5zuxqROQsXjYrU69yzjP00c/7STysOdSk7lBgkdLOHKrfMzqQiXiU/m1CGd2lKQ4Dpn25VfMMSZ2hwCKlRV8DXn6Qvh0ObzC7GhEpwxOjO+HnbeWXvcdZvDnF7HJEaoUCi5TmFwQdxzjXNSGiiEtq3qAe9w1uC8BzS7ZxKr/Q5IpEap4Ci5yr+LbQb59CYZ65tYhIme65tDUtGtYjJSOXOct3m12OSI1TYJFztR4CgU3h9AnYuczsakSkDH7eNv422vkA7lsr95B8TAM+imdTYJFzWW3Q9Ubnum4Libis4Z3DGNg2lPxCB89+lXjhN4i4MQUWKVvxUP07l0JOurm1iEiZLBYLU8dG42W1EJ94hBU7jppdkkiNUWCRsjXpCM26g6MQtnxqdjUich7twgK5vX8rAKZ/uZX8Qoe5BYnUEAUWOb/iqywaql/EpT00tB2h9X3YczSH//60z+xyRGqEAouc3yV/AKs3pGyCI7o/LuKqgvy8eWR4RwBmfbuTtKxckysSqX4KLHJ+AY2g/XDnuq6yiLi062Nb0LVFMNl5hfzzm+1mlyNS7RRYpHzFMzhvng92DU4l4qqsVgvTr+oMwKfrD7Ix+YTJFYlULwUWKV+7YVAvBLKPOGdxFhGX1b1lQ66PbQHAtEVbcTg0z5B4DgUWKZ+XD3S5wbmu20IiLu+RER2o7+vFpoMZfLr+oNnliFQbBRa5sOKh+pO+gtwMc2sRkXI1CfTjoSvaAfDCN0lknC4wuSKR6qHAIhfWtBs07gSFubD1M7OrEZELuL1/K1o3DuBYTj6vfrfT7HJEqoUCi1yYxfL7VRYN1S/i8ny8rEwb63wA9z9r9rHzSJbJFYlcPAUWqZguN4LFCgd+hmOaGVbE1V3avjFXRodR6DCY/mUihqEHcMW9KbBIxQQ1dc7iDLBpnrm1iEiFPDU6Gh8vK6t3pbN06xGzyxG5KAosUnHdiofqnwcOzVci4upaNvLnnkGtAfj7V4nkFthNrkik6hRYpOI6jgbfIMhIhuQ1ZlcjIhVw35A2NA324+CJ07y9co/Z5YhUmQKLVJx3Peh8jXNdD9+KuAV/Hy+eGNUJgNnLd3Ho5GmTKxKpGgUWqZziGZwTP4f8HFNLEZGKGdO1Kb2jQsgtcPDckm1mlyNSJQosUjkt+0LDKMjPhm2Lza5GRCrAYrEwbWxnrBb4anMKa3anm12SSKUpsEjlWCy/T4ioofpF3EZ0syD+2CcSgOmLEim068F5cS8KLFJ5MeOcr3tWQIbmKhFxF1OubE8Df2+2H8nif2uTzS5HpFIUWKTyGraCyAGAAZvjzK5GRCqoYYAPDw/rAMBLy7ZzPCff5IpEKk6BRaom5oyh+jWCpojbuLl3Szo1DSIzt5AXl243uxyRClNgkaqJvhq86sGxnXBog9nViEgF2awWpl/lnGdo3q/J/HZIM7CLe1BgkarxC4JOY53revhWxK30jgrhqphmGAZMXbRV8wyJW1BgkaornsF5y6dQmGduLSJSKU+M6oS/j431+0/wRcJhs8sRuSAFFqm6qMsgsBnknoQd35hdjYhUQniwHxOHtAXguSXbyM4rNLkikfIpsEjVWW2/d3HWUP0ibueugVFENvInLSuP17/fZXY5IuVSYJGLU9xbaFc8ZB81txYRqRQ/bxtPjY4G4N3Ve9ibruk2xHUpsMjFadwBmvUARyFs+cTsakSkkq7o1ITL2jemwG7w7OJEs8sROS8FFrl43YomRFRvIRG3Y7FYeHpsNN42C98npfF90hGzSxIpkwKLXLxL/gBWb0jdAqm/mV2NiFRSm8b1uXNAFADPLt5GXqHd5IpEzqXAIhfPPwQ6jHCub9LDtyLu6P7L29I40Je96Tm8t3qf2eWInEOBRapHTNFtoc3zwa7ukSLuJtDPm8dGdATgte93ciQz1+SKREpTYJHq0e5K8A+FnDTY/b3Z1YhIFVzbvTndWzbgVL6d579OMrsckVIUWKR62Lyhyw3OdT18K+KWrEXzDFks8NnGQ6zbd9zskkRKKLBI9Ym5yfmatAROnzC3FhGpkq4tGjCuZwQA077cit2heYbENSiwSPVpGgNNosGeB1s/M7saEamih4d3INDPi98OZRL36wGzyxEBFFikOlksv498q6H6RdxWaH1fJg9tD8CLS5PIOFVgckUiCixS3breCBYrHPwFju02uxoRqaLb+kXSPqw+J04V8Mq3O8wuR0SBRapZYDi0ucK5rjFZRNyWt83K1LGdAfjw5/0kpWaaXJHUdQosUv26Fd0W2jQPHA5zaxGRKhvQNpSRl4RjdxhMW7QVw9ADuGIeBRapfh1Gg28wZByA/avNrkZELsITozrh62Xl5z3HWbIl1exypA5TYJHq5+0Hl1zrXNfDtyJuLSLEnwmXtQHgH18lcjpf8wyJOaoUWGbPnk1UVBR+fn7ExsayatWq87ZNSUnhlltuoUOHDlitViZNmlRmuwULFhAdHY2vry/R0dF89pm6xbq14t5CiV9AXra5tYjIRbl3cBuaN6jH4Yxc5qzQw/RijkoHlri4OCZNmsSTTz7Jxo0bGTRoECNHjiQ5ObnM9nl5eTRu3Jgnn3ySmJiYMtv89NNPjBs3jttuu41NmzZx2223ceONN7J27drKlieuIqIPhLSGghzY9qXZ1YjIRfDztvG30Z0AeHPFbg4cP2VyRVIXWYxKPkXVp08fevTowZw5c0q2derUiWuuuYYZM2aU+97BgwfTrVs3Zs2aVWr7uHHjyMzM5Ouvvy7ZNmLECBo2bMjcuRW7pZCZmUlwcDAZGRkEBQVV/ICk5qz4J/zwD4i6DG5fZHY1InIRDMPgj++sZc3uYwzvHMZbt/U0uyTxEBX9/q7UFZb8/HzWr1/PsGHDSm0fNmwYa9asqVqlOK+wnL3P4cOHl7vPvLw8MjMzSy3iYrqOc77uXQkZB82tRUQuisViYerYztisFpZuPcKqnUfNLknqmEoFlvT0dOx2O2FhYaW2h4WFkZpa9afHU1NTK73PGTNmEBwcXLJERERU+fOlhjSMhFaDAMPZxVlE3FqH8EBu6xsJwPQvEymwa9gCqT1VeujWYrGU+tkwjHO21fQ+H3/8cTIyMkqWAwc034VLKn74dtNc0BgOIm5v8pXtCQnwYVdaNv/9ab/Z5UgdUqnAEhoais1mO+fKR1pa2jlXSCojPDy80vv09fUlKCio1CIuKPoq8PaHY7vg4DqzqxGRixRcz5tHhncAYFb8DtKz80yuSOqKSgUWHx8fYmNjiY+PL7U9Pj6e/v37V7mIfv36nbPPZcuWXdQ+xUX4BkKnq5zrmz42txYRqRY39IygS/NgsvIK+ec3SWaXI3VEpW8JTZkyhXfeeYf33nuPbdu2MXnyZJKTk5kwYQLgvFUzfvz4Uu9JSEggISGB7Oxsjh49SkJCAomJiSW/f+ihh1i2bBkvvPACSUlJvPDCC3z77bfnHbNF3EzMTc7X3xZAQa65tYjIRbNZLUy7yjnP0Px1B0k4cNLcgqRO8KrsG8aNG8exY8d45plnSElJ4ZJLLmHJkiVERjofxEpJSTlnTJbu3buXrK9fv56PP/6YyMhI9u3bB0D//v2ZN28ef/vb33jqqado06YNcXFx9OnT5yIOTVxG1KUQ1BwyD8GOr6HztWZXJCIXKTayIdf1aM7CDYeYtmgrC+/tj9V6cc8yipSn0uOwuCqNw+Livp0Oq1+G9iPgljizqxGRapCWmcuQmcvJybcz84YYro9tYXZJ4oZqZBwWkSrrdovzdWc8ZKeZW4uIVIsmQX48eEU7AJ7/OonM3AKTKxJPpsAitSO0HTTvCYYdtnxidjUiUk3+NCCK1qEBpGfn8dp3O80uRzyYAovUnm5FY7JoBmcRj+HjZeWpsdEAvP/jPnalabJTqRkKLFJ7Ol8HNh84sgVSt5hdjYhUkyEdmjC0UxMKHQbTv9yKhzwaKS5GgUVqj38IdBjpXNdVFhGP8rfR0fjYrKzamc632/ScmlQ/BRapXcVD9W+ZD3Y9oCfiKVqFBnD3oCgAnl2cSG6B3eSKxNMosEjtajsU/EMh5yjs+s7sakSkGk0c0pawIF+Sj5/inVV7zC5HPIwCi9Qumzd0vdG5vkm3hUQ8SYCvF0+M6gTAGz/s5vDJ0yZXJJ5EgUVqX/Ftoe1L4PQJc2sRkWp1VUwzerVqyOkCOzO+1jxDUn0UWKT2Ne0KYZeAPR9+W2h2NSJSjSwW5zxDVgt8uekwa/ccM7sk8RAKLGKO4qssui0k4nE6Nwvm5t4tAZi6aCuFdofJFYknUGARc3S9ESw2OPgrpGt0TBFP8/CwDgTX8yYpNYu5vyRf+A0iF6DAIuao38TZYwh0lUXEAzUM8OHhYe0BmLlsBydy8k2uSNydAouYJ+Ym5+umOHDokrGIp7m5d0s6hgeScbqAl+K3m12OuDkFFjFPh1HgFwyZB2HfSrOrEZFq5mWzMu2qzgB8vDaZl5dtZ83udA0qJ1XiZXYBUod5+znnF1r/PmyaB60Hm12RiFSzvq0bcVVMMxZtOsyr3+/i1e934WOzEhMRTJ+oRvSOCiE2siEBvvo6kvJZDA+ZpSozM5Pg4GAyMjIICgoyuxypqAO/wLtXgncAPLwDfOubXZGIVLP8QgcLNhzkp93HWLv3GEcy80r93stq4ZLmwfRpHUKfqBB6tgohyM/bpGqltlX0+1uBRcxlGPBaLBzfDdfMgW63mF2RiNQgwzDYf+wUa/ceY+3e46zdc5xDZ42Ia7VAdLOgkiswvVuF0DDAx6SKpaYpsIj7WPkifP93aDUI7lhsdjUiUssOnjjFL0XhZe3eY+w7duqcNh3DA+kdFVISYhoH+ppQqdQEBRZxHycPwKwugAGTtkCDlmZXJCImOpKZW3T1xXkVZlda9jlt2jQOoHdUI/q2doaY8GA/EyqV6qDAIu7lP2Nh70oY8je47K9mVyMiLiQ9O49f9x5n7d7j/LznGNuPZHH2N1dkI396twqhT+tG9IkKISLE35xipdIUWMS9JHwMn98LIW3ggfVgsZhdkYi4qJOn8vl134mSKzBbD2fgOOubrHmDekW3kJwhplUjfyz6e8UlKbCIe8nLhpntoSAH7lwGLfuYXZGIuIms3ALW7T9R8gzMloMZFJ6VYJoE+joDTNEVmHZN6ivAuAgFFnE/n01wDtMf+ycYO8vsakTETZ3KL2TD/pPOnkh7jpNw4CT5Z03AGBLgU3QLyfkMTMfwQKxWBRgzKLCI+9mzAv57lXP02//b4RxYTkTkIuUW2Ek4cJK1e47zy75jrN9/gtyC0gEmyM+rVC+kzs2C8LJpMPjaoMAi7sfhgH91hYwDcP37cMl1ZlckIh4ov9DBlkMn+XnPcX7Ze5x1+46Tk196uoD6vl7ERjYsGcyuS/MG+HgpwNQEBRZxT989C6tmQrth8MdPzK5GROqAQruDrYczWbv3GL/sdYaYzNzCUm38vK3ERjakd6tG9GkdQreIBvh520yq2LMosIh7St8Fr8eCxQZTtkFgmNkViUgdY3cYJKVmOm8h7T3OL/uOczwnv1QbHy8r3SIaOHshRTWiR2QD/H00H1JVKLCI+3rnSjj4Cwz7O/R/wOxqRKSOczgMdh3NLjWY3dGsc+dD6toimN5RziswPSMbEqj5kCpEgUXc16/vwldToElnuPdHjckiIi7FMAz2puc4pxMoCjGHM3JLtbFa4JLmwSWD2fVuFUKwvwJMWRRYxH2dPgEzO4A9D/6yEprGmF2RiMh5GYbBwROnS12BST5eej4kiwU6hAXSt2gcmN5RITSqr/mQQIHF7HLkYs2/HRI/h773wYgZZlcjIlIpKRmn+WXvcX4uGsxuz9Gcc9q0bVK/ZCTevlEhNAmqm0M5KLCIe9uxFD6+EfxD4f+SwKZLqSLivo5m5RXdQnIOZrf9SNY5bVo18qdP0TMwfVo3onmDeiZUWvsUWMS92Qvh5U6QkwY3z4MOI82uSESk2pzIyeeXfcdLphNITMk8Z0LH5g3q0ad1CH2LBrOL9ND5kBRYxP0tfRJ+eh06XQXjPjS7GhGRGpNxuoD1+4sDzHG2HMrAftZ8SGFBviUj8fZtHUKbxp4xH5ICi7i/1N/gzQFg84H/2w7+IWZXJCJSK3LyClm//0TJYHYJB05SYC/9dR1a34feUSElPZE6hLnnfEgKLOIZ3hwIqVtg1Ezo/WezqxERMUVugZ0NySdKBrPbkHyCvMLS8yE18PemV6uQksHsopsFYXODAKPAIp7hpzdg6RPQPBb+/L3Z1YiIuIS8QjubD2aUdKNev/8Ep86aDynQ14uerRqWDGbXpXkw3i44oaMCi3iG7DR4qSMYdpj4KzRub3ZFIiIup8Du4LdDGSWD2f269zhZeaXnQ6rnbXNO6FjUlTomIhhfL/PnQ1JgEc/x8TjY8Q0MnAJDp5pdjYiIy7M7DLalZJYMZvfLvuOcPFVQqo2Pl5XuEQ1KxoHp3rIh9XxqP8AosIjn2Po5fHI7BDWHSVvAav6/CERE3InDYbAjLct5BaaoK3V6dukJHb1tFrq2aFByBSY2siH1fWt+QkcFFvEchXkwsz3knoTbPoc2Q8yuSETErRmGwe6jOaUGs0vNLD0fks1q4ZJmQfQpmk6gZ6sQgutV/yCeCiziWRZPgXXvQtdxcN3bZlcjIuJRDMPgwPHT/FwUXtbuPcbBE6dLtbFY4N+39WRodFi1fnZFv79r/lqPSHXodoszsGz7EvKywDfQ7IpERDyGxWKhZSN/Wjby58aeEQAcOnmaX0oCzHH2pucQ3cy8CwIKLOIemsdCo3ZwbCckfgHdbzW7IhERj9a8QT2u7d6Ca7u3AJzzITUONG+GadfrkC1SFosFYm5yrifMNbcWEZE6yMywAgos4k5ibgIssH81nNhndjUiIlKLFFjEfQS3gKhLneub55tbi4iI1CoFFnEv3W5xvm6ayzlzsYuIiMdSYBH30mks+NSH43vgwFqzqxERkVqiwCLuxScAoq92rid8bG4tIiJSaxRYxP3E3Ox83foZFJwuv62IiHgEBRZxP5EDILgl5GVC0ldmVyMiIrVAgUXcj9UKMeOc65s0JouISF1QpcAye/ZsoqKi8PPzIzY2llWrVpXbfsWKFcTGxuLn50fr1q158803S/3+gw8+wGKxnLPk5uaeZ49S5xXfFtr9PWSlmluLiIjUuEoHlri4OCZNmsSTTz7Jxo0bGTRoECNHjiQ5ObnM9nv37mXUqFEMGjSIjRs38sQTT/Dggw+yYMGCUu2CgoJISUkptfj5+VXtqMTzNWoDEX3AcGhMFhGROqDSgeXll1/mrrvu4u6776ZTp07MmjWLiIgI5syZU2b7N998k5YtWzJr1iw6derE3XffzZ133snMmTNLtbNYLISHh5daRMpVfJVFY7KIiHi8SgWW/Px81q9fz7Bhw0ptHzZsGGvWrCnzPT/99NM57YcPH866desoKCgo2ZadnU1kZCQtWrRgzJgxbNy4sdxa8vLyyMzMLLVIHdP5WrD5QloipGwyuxoREalBlQos6enp2O12wsLCSm0PCwsjNbXs5whSU1PLbF9YWEh6ejoAHTt25IMPPmDRokXMnTsXPz8/BgwYwM6dO89by4wZMwgODi5ZIiIiKnMo4gnqNYCOo53revhWRMSjVemhW4vFUupnwzDO2Xah9mdu79u3L7feeisxMTEMGjSI+fPn0759e1577bXz7vPxxx8nIyOjZDlw4EBVDkXcXfFQ/Vs+gcJ8c2sREZEa41WZxqGhodhstnOupqSlpZ1zFaVYeHh4me29vLxo1KhRme+xWq306tWr3Cssvr6++PqaO9W1uIDWQ6B+GGQfgV3xv19xERERj1KpKyw+Pj7ExsYSHx9fant8fDz9+/cv8z39+vU7p/2yZcvo2bMn3t7eZb7HMAwSEhJo2rRpZcqTusjmBV1ucK5rqH4REY9V6VtCU6ZM4Z133uG9995j27ZtTJ48meTkZCZMmAA4b9WMHz++pP2ECRPYv38/U6ZMYdu2bbz33nu8++67PPzwwyVtpk+fztKlS9mzZw8JCQncddddJCQklOxTpFzFt4V2LIVTx82tRUREakSlbgkBjBs3jmPHjvHMM8+QkpLCJZdcwpIlS4iMjAQgJSWl1JgsUVFRLFmyhMmTJ/PGG2/QrFkzXn31Vf7whz+UtDl58iT33HMPqampBAcH0717d1auXEnv3r2r4RDF44V1hvCukLoZflsAvf9sdkUiIlLNLIbhGQNYZGZmEhwcTEZGBkFBQWaXI7Xt5znwzWPQrAfc84PZ1YiISAVV9PtbcwmJZ+hyA1i94PAGOLrd7GpERKSaKbCIZwgIhXZFAxTq4VsREY+jwCKeo3io/s1x4LCbW4uIiFQrBRbxHO2HQ72GkJUCe5abXY2IiFQjBRbxHF6+cElR7zMN1S8i4lEUWMSzxBSNybJtMeRqQkwREU+hwCKepXkPCG0Phach8QuzqxERkWqiwCKexWL5/eFb3RYSEfEYCiziebqOAyyw/0c4sc/sakREpBoosIjnCW4OrQc71zfNM7UUERGpHgos4pmKJ0TcNBc8Y/YJEZE6TYFFPFPHMeBT33lLKPkns6sREZGLpMAinsnHH6Kvca5rqH4REbenwCKeq1tRb6Gtn0PBaVNLERGRi6PAIp6rZX9o0BLysyDpK7OrERGRi+BldgEiNcZqdY7JsuIFWD0Lju8Fq61o8QKLrYyfvc6zzVp2m5Kfy9pWvA/rWT8Xt7OY/SckIuI2FFjEs8Xc5AwsR7Y4F1diqUh4sv4eiC7UprYCV3kh7ILhr6IBUYFOREpTYBHPFtIarvu3s6eQw+5cDDs4Cot+LgTDUfrnsrYZ9t/fX9bP52tjOM5fm2EHux3s+bX35+FOLNbSgapeAwgIhYDGENDEuV6/SdHPoUXbGoN/I7DprzYRT6P/q8Xzdb3RuZjBMM4KOYVlBJ/C84SpM38+X5vywtWFAlchOByUDlxnbLtQbZWq/4xX46z18/7ZOYqOrcD5c34WZByowB+6BfxDfg81AY2Lgs0ZoSagMdQvevUJqJZTLSI1S4FFpCZZLM5/7etf/GUzjIoFLkchnD4JOWmQcxSy0yAn3bmeU7SenQanjgGG8/XUMThagRq8A8oJNmdexWkC9Ro6b6+JSK3T36IiYh6L5fdnW6qDww6njp8RbI4WhZqzgk1OuvPnwlwoyIGTOXByfwXqtZ1xW+qMYFN8tebsxduveo5LRBRYRMSDWG3O8FC/8YXbGgbkZ58VbM64cnNmsMk5CqdPOK/+ZB9xLhXhG3RGsDnzas0ZS/FVHb8GetBYpBwKLCJSN1ks4BvoXEJaX7i9veDc21BlBZviqziOAsjLdC7H91x4/1bvMm5DnRlsGlPqgWOb98X/GYi4EQUWEZGKsHlDUFPnciGGAbkZZ9yOKiPYlFzVSYe8DGfAyTrsXCrCr0HFgk39Js55tXT1RtycAouISHWzWJzdsOs1gNB2F25fkAun0s//MHFxsCneZtgh96RzSd9x4f17+Z0n1JTRRdy/UfU9UyRSjRRYRETM5u0HwS2cy4U4HM7nacp8mPjouVdxCnKcDxdnHKhEt/BG53+Y+OyrOj7+F334IhWhwCIi4k6sVgho5FzoeOH2+TlnBJmjZwSbM29XFb2WdAtPdy5Ht114/94B596GKquL+JlXbizWoltUltKvFuu52878nW5r1WkKLCIinswnwLk0bHXhtvZCOH38PA8Tn9VNPDsN7HnOKzgncuDEvpo+kjOcGWYqGn6oZPsz3nfe351vX2VsK699qd9RwbrO3heVbF+BmsvaV9/7oGFkDZzTC1NgERERJ5uX88pI/SYQ1rn8tsXdws/XS+rsqzinT1RjoYbz86H80ZKl+l1yvQKLiIi4kTO7hTdqc+H2DgclQcM4Y/3s1zJ/R9FUDRVtb5zRnnJ+d6F9Ucn2Z/6ujG0V3hcV/Jzz7auSn13yOy58jBXpJVdDFFhERKTmaUoDuUj6L0hERERcngKLiIiIuDwFFhEREXF5CiwiIiLi8hRYRERExOUpsIiIiIjLU2ARERERl6fAIiIiIi5PgUVERERcngKLiIiIuDwFFhEREXF5CiwiIiLi8hRYRERExOV5zGzNRtGU3JmZmSZXIiIiIhVV/L1d/D1+Ph4TWLKysgCIiIgwuRIRERGprKysLIKDg8/7e4txoUjjJhwOB4cPHyYwMBCLxVJt+83MzCQiIoIDBw4QFBRUbft1JZ5+jDo+9+fpx6jjc3+efow1eXyGYZCVlUWzZs2wWs//pIrHXGGxWq20aNGixvYfFBTkkf8RnsnTj1HH5/48/Rh1fO7P04+xpo6vvCsrxfTQrYiIiLg8BRYRERFxeQosF+Dr68vUqVPx9fU1u5Qa4+nHqONzf55+jDo+9+fpx+gKx+cxD92KiIiI59IVFhEREXF5CiwiIiLi8hRYRERExOUpsIiIiIjLU2ABZs+eTVRUFH5+fsTGxrJq1apy269YsYLY2Fj8/Pxo3bo1b775Zi1VWjWVOb7ly5djsVjOWZKSkmqx4opbuXIlY8eOpVmzZlgsFj7//PMLvsfdzl9lj9HdzuGMGTPo1asXgYGBNGnShGuuuYbt27df8H3uch6rcnzudA7nzJlD165dSwYU69evH19//XW573GXc1esssfoTuevLDNmzMBisTBp0qRy29X2eazzgSUuLo5Jkybx5JNPsnHjRgYNGsTIkSNJTk4us/3evXsZNWoUgwYNYuPGjTzxxBM8+OCDLFiwoJYrr5jKHl+x7du3k5KSUrK0a9euliqunJycHGJiYnj99dcr1N7dzh9U/hiLucs5XLFiBRMnTuTnn38mPj6ewsJChg0bRk5Oznnf407nsSrHV8wdzmGLFi14/vnnWbduHevWrePyyy/n6quvZuvWrWW2d6dzV6yyx1jMHc7f2X799VfefvttunbtWm47U86jUcf17t3bmDBhQqltHTt2NB577LEy2z/yyCNGx44dS237y1/+YvTt27fGarwYlT2+H374wQCMEydO1EJ11QswPvvss3LbuNv5O1tFjtGdz6FhGEZaWpoBGCtWrDhvG3c+jxU5Pnc/hw0bNjTeeeedMn/nzufuTOUdo7uev6ysLKNdu3ZGfHy8cdlllxkPPfTQeduacR7r9BWW/Px81q9fz7Bhw0ptHzZsGGvWrCnzPT/99NM57YcPH866desoKCiosVqroirHV6x79+40bdqUK664gh9++KEmy6xV7nT+Lpa7nsOMjAwAQkJCztvGnc9jRY6vmLudQ7vdzrx588jJyaFfv35ltnHncwcVO8Zi7nb+Jk6cyOjRoxk6dOgF25pxHut0YElPT8dutxMWFlZqe1hYGKmpqWW+JzU1tcz2hYWFpKen11itVVGV42vatClvv/02CxYsYOHChXTo0IErrriClStX1kbJNc6dzl9VufM5NAyDKVOmMHDgQC655JLztnPX81jR43O3c7hlyxbq16+Pr68vEyZM4LPPPiM6OrrMtu567ipzjO52/gDmzZvHhg0bmDFjRoXam3EePWa25othsVhK/WwYxjnbLtS+rO2uojLH16FDBzp06FDyc79+/Thw4AAzZ87k0ksvrdE6a4u7nb/KcudzeP/997N582ZWr159wbbueB4renzudg47dOhAQkICJ0+eZMGCBdx+++2sWLHivF/o7njuKnOM7nb+Dhw4wEMPPcSyZcvw8/Or8Ptq+zzW6SssoaGh2Gy2c642pKWlnZMci4WHh5fZ3svLi0aNGtVYrVVRleMrS9++fdm5c2d1l2cKdzp/1ckdzuEDDzzAokWL+OGHH2jRokW5bd3xPFbm+MriyufQx8eHtm3b0rNnT2bMmEFMTAz/+te/ymzrjucOKneMZXHl87d+/XrS0tKIjY3Fy8sLLy8vVqxYwauvvoqXlxd2u/2c95hxHut0YPHx8SE2Npb4+PhS2+Pj4+nfv3+Z7+nXr9857ZctW0bPnj3x9vausVqroirHV5aNGzfStGnT6i7PFO50/qqTK59DwzC4//77WbhwId9//z1RUVEXfI87nceqHF9ZXPkcns0wDPLy8sr8nTudu/KUd4xlceXzd8UVV7BlyxYSEhJKlp49e/LHP/6RhIQEbDbbOe8x5TzW2OO8bmLevHmGt7e38e677xqJiYnGpEmTjICAAGPfvn2GYRjGY489Ztx2220l7ffs2WP4+/sbkydPNhITE413333X8Pb2Nj799FOzDqFclT2+V155xfjss8+MHTt2GL/99pvx2GOPGYCxYMECsw6hXFlZWcbGjRuNjRs3GoDx8ssvGxs3bjT2799vGIb7nz/DqPwxuts5vPfee43g4GBj+fLlRkpKSsly6tSpkjbufB6rcnzudA4ff/xxY+XKlcbevXuNzZs3G0888YRhtVqNZcuWGYbh3ueuWGWP0Z3O3/mc3UvIFc5jnQ8shmEYb7zxhhEZGWn4+PgYPXr0KNXd8Pbbbzcuu+yyUu2XL19udO/e3fDx8TFatWplzJkzp5YrrpzKHN8LL7xgtGnTxvDz8zMaNmxoDBw40Pjqq69MqLpiirsPnr3cfvvthmF4xvmr7DG62zks69gA4/333y9p487nsSrH507n8M477yz5+6Vx48bGFVdcUfJFbhjufe6KVfYY3en8nc/ZgcUVzqPFMIqekhERERFxUXX6GRYRERFxDwosIiIi4vIUWERERMTlKbCIiIiIy1NgEREREZenwCIiIiIuT4FFREREXJ4Ci4iIiLg8BRYRERFxeQosIiIi4vIUWERERMTlKbCIiIiIy/t/aaICYngcq68AAAAASUVORK5CYII=", "text/plain": [ "
    " ] @@ -2513,7 +2507,7 @@ }, { "cell_type": "markdown", - "id": "96fc590b", + "id": "4ae9cee9", "metadata": { "editable": true }, @@ -2524,7 +2518,7 @@ { "cell_type": "code", "execution_count": 12, - "id": "8de8bbfc", + "id": "9be1964e", "metadata": { "collapsed": false, "editable": true @@ -2660,7 +2654,7 @@ }, { "cell_type": "markdown", - "id": "8dfe4a90", + "id": "f0fe5870", "metadata": { "editable": true }, @@ -2688,7 +2682,7 @@ }, { "cell_type": "markdown", - "id": "c0edb6d6", + "id": "9b60a7bd", "metadata": { "editable": true }, @@ -2723,7 +2717,7 @@ }, { "cell_type": "markdown", - "id": "ed0f6bc0", + "id": "a31dcc5d", "metadata": { "editable": true }, @@ -2738,7 +2732,7 @@ { "cell_type": "code", "execution_count": 13, - "id": "99a1133f", + "id": "225671c5", "metadata": { "collapsed": false, "editable": true @@ -2763,7 +2757,7 @@ }, { "cell_type": "markdown", - "id": "5ef9b25c", + "id": "ac1448c8", "metadata": { "editable": true }, @@ -2779,7 +2773,7 @@ }, { "cell_type": "markdown", - "id": "80ca5485", + "id": "c6e308a3", "metadata": { "editable": true }, @@ -2791,7 +2785,7 @@ }, { "cell_type": "markdown", - "id": "17ad9823", + "id": "a2f2dab5", "metadata": { "editable": true }, @@ -2806,7 +2800,7 @@ }, { "cell_type": "markdown", - "id": "7560f426", + "id": "8a7df606", "metadata": { "editable": true }, @@ -2818,7 +2812,7 @@ }, { "cell_type": "markdown", - "id": "a7444f64", + "id": "31e595c9", "metadata": { "editable": true }, @@ -2828,7 +2822,7 @@ }, { "cell_type": "markdown", - "id": "2aad0c8b", + "id": "f5f389db", "metadata": { "editable": true }, @@ -2840,7 +2834,7 @@ }, { "cell_type": "markdown", - "id": "de870a72", + "id": "1dd4b34d", "metadata": { "editable": true }, @@ -2850,7 +2844,7 @@ }, { "cell_type": "markdown", - "id": "7a6c517e", + "id": "f931e286", "metadata": { "editable": true }, @@ -2862,7 +2856,7 @@ }, { "cell_type": "markdown", - "id": "753afefe", + "id": "4cbda41b", "metadata": { "editable": true }, @@ -2875,7 +2869,7 @@ }, { "cell_type": "markdown", - "id": "3005c150", + "id": "6657a435", "metadata": { "editable": true }, @@ -2887,7 +2881,7 @@ }, { "cell_type": "markdown", - "id": "79eace73", + "id": "91f7475b", "metadata": { "editable": true }, @@ -2897,7 +2891,7 @@ }, { "cell_type": "markdown", - "id": "38d75fef", + "id": "98482060", "metadata": { "editable": true }, @@ -2909,7 +2903,7 @@ }, { "cell_type": "markdown", - "id": "60f367fa", + "id": "01e12c29", "metadata": { "editable": true }, @@ -2919,7 +2913,7 @@ }, { "cell_type": "markdown", - "id": "9131a799", + "id": "38fa32e4", "metadata": { "editable": true }, @@ -2931,7 +2925,7 @@ }, { "cell_type": "markdown", - "id": "8cbfafa2", + "id": "ea483f66", "metadata": { "editable": true }, @@ -2941,7 +2935,7 @@ }, { "cell_type": "markdown", - "id": "9d4a45df", + "id": "d5862089", "metadata": { "editable": true }, @@ -2953,7 +2947,7 @@ }, { "cell_type": "markdown", - "id": "19284bfb", + "id": "0456f62e", "metadata": { "editable": true }, @@ -2963,7 +2957,7 @@ }, { "cell_type": "markdown", - "id": "e1ccefe0", + "id": "1ed14941", "metadata": { "editable": true }, @@ -2975,7 +2969,7 @@ }, { "cell_type": "markdown", - "id": "e6228ac9", + "id": "43387b69", "metadata": { "editable": true }, @@ -2985,7 +2979,7 @@ }, { "cell_type": "markdown", - "id": "474d165a", + "id": "06bd01bf", "metadata": { "editable": true }, @@ -2997,7 +2991,7 @@ }, { "cell_type": "markdown", - "id": "01c6f359", + "id": "9cad411e", "metadata": { "editable": true }, @@ -3007,7 +3001,7 @@ }, { "cell_type": "markdown", - "id": "104df9ea", + "id": "c37f7792", "metadata": { "editable": true }, @@ -3019,7 +3013,7 @@ }, { "cell_type": "markdown", - "id": "86f33ebf", + "id": "8a7f23f8", "metadata": { "editable": true }, @@ -3031,7 +3025,7 @@ }, { "cell_type": "markdown", - "id": "b8893d78", + "id": "a7fdf6e8", "metadata": { "editable": true }, @@ -3043,7 +3037,7 @@ }, { "cell_type": "markdown", - "id": "cc8ec307", + "id": "3ac73282", "metadata": { "editable": true }, @@ -3056,7 +3050,7 @@ }, { "cell_type": "markdown", - "id": "234e3f6e", + "id": "e55db5a0", "metadata": { "editable": true }, @@ -3068,7 +3062,7 @@ }, { "cell_type": "markdown", - "id": "d1c0397f", + "id": "966cd383", "metadata": { "editable": true }, @@ -3078,7 +3072,7 @@ }, { "cell_type": "markdown", - "id": "799912a7", + "id": "360cb45f", "metadata": { "editable": true }, @@ -3092,7 +3086,7 @@ { "cell_type": "code", "execution_count": 14, - "id": "5a3de91e", + "id": "2099267d", "metadata": { "collapsed": false, "editable": true @@ -3121,7 +3115,7 @@ }, { "data": { - "image/png": "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\n", + "image/png": "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", "text/plain": [ "
    " ] @@ -3225,7 +3219,7 @@ }, { "cell_type": "markdown", - "id": "0f069973", + "id": "9ba9afe9", "metadata": { "editable": true }, @@ -3246,7 +3240,7 @@ }, { "cell_type": "markdown", - "id": "e76beb96", + "id": "ea4bf6fe", "metadata": { "editable": true }, @@ -3258,7 +3252,7 @@ }, { "cell_type": "markdown", - "id": "4fe81d64", + "id": "98ca9b28", "metadata": { "editable": true }, @@ -3268,7 +3262,7 @@ }, { "cell_type": "markdown", - "id": "bb22d80f", + "id": "996fc4f6", "metadata": { "editable": true }, @@ -3280,7 +3274,7 @@ }, { "cell_type": "markdown", - "id": "293ce41e", + "id": "b5db8128", "metadata": { "editable": true }, @@ -3290,7 +3284,7 @@ }, { "cell_type": "markdown", - "id": "8a969677", + "id": "745d6bff", "metadata": { "editable": true }, @@ -3302,7 +3296,7 @@ }, { "cell_type": "markdown", - "id": "d93685ad", + "id": "2ecb048e", "metadata": { "editable": true }, @@ -3318,7 +3312,7 @@ }, { "cell_type": "markdown", - "id": "9abd5b44", + "id": "73eb2f08", "metadata": { "editable": true }, @@ -3362,7 +3356,7 @@ }, { "cell_type": "markdown", - "id": "b8bd6825", + "id": "41d9c008", "metadata": { "editable": true }, @@ -3374,7 +3368,7 @@ { "cell_type": "code", "execution_count": 15, - "id": "2c2b3d87", + "id": "0af3b38a", "metadata": { "collapsed": false, "editable": true @@ -3390,7 +3384,7 @@ }, { "cell_type": "markdown", - "id": "fea1bc2e", + "id": "41771944", "metadata": { "editable": true }, @@ -3401,63 +3395,23 @@ { "cell_type": "code", "execution_count": 16, - "id": "a80976dc", + "id": "c0ad90ff", "metadata": { "collapsed": false, "editable": true }, "outputs": [ { - "name": "stderr", - "output_type": "stream", - "text": [ - "/Users/mhjensen/miniforge3/envs/myenv/lib/python3.9/site-packages/sklearn/utils/deprecation.py:87: FutureWarning: Function load_boston is deprecated; `load_boston` is deprecated in 1.0 and will be removed in 1.2.\n", - "\n", - " The Boston housing prices dataset has an ethical problem. You can refer to\n", - " the documentation of this function for further details.\n", - "\n", - " The scikit-learn maintainers therefore strongly discourage the use of this\n", - " dataset unless the purpose of the code is to study and educate about\n", - " ethical issues in data science and machine learning.\n", - "\n", - " In this special case, you can fetch the dataset from the original\n", - " source::\n", - "\n", - " import pandas as pd\n", - " import numpy as np\n", - "\n", - "\n", - " data_url = \"http://lib.stat.cmu.edu/datasets/boston\"\n", - " raw_df = pd.read_csv(data_url, sep=\"\\s+\", skiprows=22, header=None)\n", - " data = np.hstack([raw_df.values[::2, :], raw_df.values[1::2, :2]])\n", - " target = raw_df.values[1::2, 2]\n", - "\n", - " Alternative datasets include the California housing dataset (i.e.\n", - " :func:`~sklearn.datasets.fetch_california_housing`) and the Ames housing\n", - " dataset. You can load the datasets as follows::\n", - "\n", - " from sklearn.datasets import fetch_california_housing\n", - " housing = fetch_california_housing()\n", - "\n", - " for the California housing dataset and::\n", - "\n", - " from sklearn.datasets import fetch_openml\n", - " housing = fetch_openml(name=\"house_prices\", as_frame=True)\n", - "\n", - " for the Ames housing dataset.\n", - " \n", - " warnings.warn(msg, category=FutureWarning)\n" + "ename": "ImportError", + "evalue": "\n`load_boston` has been removed from scikit-learn since version 1.2.\n\nThe Boston housing prices dataset has an ethical problem: as\ninvestigated in [1], the authors of this dataset engineered a\nnon-invertible variable \"B\" assuming that racial self-segregation had a\npositive impact on house prices [2]. Furthermore the goal of the\nresearch that led to the creation of this dataset was to study the\nimpact of air quality but it did not give adequate demonstration of the\nvalidity of this assumption.\n\nThe scikit-learn maintainers therefore strongly discourage the use of\nthis dataset unless the purpose of the code is to study and educate\nabout ethical issues in data science and machine learning.\n\nIn this special case, you can fetch the dataset from the original\nsource::\n\n import pandas as pd\n import numpy as np\n\n data_url = \"http://lib.stat.cmu.edu/datasets/boston\"\n raw_df = pd.read_csv(data_url, sep=\"\\s+\", skiprows=22, header=None)\n data = np.hstack([raw_df.values[::2, :], raw_df.values[1::2, :2]])\n target = raw_df.values[1::2, 2]\n\nAlternative datasets include the California housing dataset and the\nAmes housing dataset. You can load the datasets as follows::\n\n from sklearn.datasets import fetch_california_housing\n housing = fetch_california_housing()\n\nfor the California housing dataset and::\n\n from sklearn.datasets import fetch_openml\n housing = fetch_openml(name=\"house_prices\", as_frame=True)\n\nfor the Ames housing dataset.\n\n[1] M Carlisle.\n\"Racist data destruction?\"\n\n\n[2] Harrison Jr, David, and Daniel L. Rubinfeld.\n\"Hedonic housing prices and the demand for clean air.\"\nJournal of environmental economics and management 5.1 (1978): 81-102.\n\n", + "output_type": "error", + "traceback": [ + "\u001b[0;31m---------------------------------------------------------------------------\u001b[0m", + "\u001b[0;31mImportError\u001b[0m Traceback (most recent call last)", + "Cell \u001b[0;32mIn[16], line 1\u001b[0m\n\u001b[0;32m----> 1\u001b[0m \u001b[38;5;28;01mfrom\u001b[39;00m \u001b[38;5;21;01msklearn\u001b[39;00m\u001b[38;5;21;01m.\u001b[39;00m\u001b[38;5;21;01mdatasets\u001b[39;00m \u001b[38;5;28;01mimport\u001b[39;00m load_boston\n\u001b[1;32m 3\u001b[0m boston_dataset \u001b[38;5;241m=\u001b[39m load_boston()\n\u001b[1;32m 5\u001b[0m \u001b[38;5;66;03m# boston_dataset is a dictionary\u001b[39;00m\n\u001b[1;32m 6\u001b[0m \u001b[38;5;66;03m# let's check what it contains\u001b[39;00m\n", + "File \u001b[0;32m~/miniforge3/envs/myenv/lib/python3.9/site-packages/sklearn/datasets/__init__.py:157\u001b[0m, in \u001b[0;36m__getattr__\u001b[0;34m(name)\u001b[0m\n\u001b[1;32m 108\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m name \u001b[38;5;241m==\u001b[39m \u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mload_boston\u001b[39m\u001b[38;5;124m\"\u001b[39m:\n\u001b[1;32m 109\u001b[0m msg \u001b[38;5;241m=\u001b[39m textwrap\u001b[38;5;241m.\u001b[39mdedent(\u001b[38;5;124m\"\"\"\u001b[39m\n\u001b[1;32m 110\u001b[0m \u001b[38;5;124m `load_boston` has been removed from scikit-learn since version 1.2.\u001b[39m\n\u001b[1;32m 111\u001b[0m \n\u001b[0;32m (...)\u001b[0m\n\u001b[1;32m 155\u001b[0m \u001b[38;5;124m \u001b[39m\n\u001b[1;32m 156\u001b[0m \u001b[38;5;124m \u001b[39m\u001b[38;5;124m\"\"\"\u001b[39m)\n\u001b[0;32m--> 157\u001b[0m \u001b[38;5;28;01mraise\u001b[39;00m \u001b[38;5;167;01mImportError\u001b[39;00m(msg)\n\u001b[1;32m 158\u001b[0m \u001b[38;5;28;01mtry\u001b[39;00m:\n\u001b[1;32m 159\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[38;5;28mglobals\u001b[39m()[name]\n", + "\u001b[0;31mImportError\u001b[0m: \n`load_boston` has been removed from scikit-learn since version 1.2.\n\nThe Boston housing prices dataset has an ethical problem: as\ninvestigated in [1], the authors of this dataset engineered a\nnon-invertible variable \"B\" assuming that racial self-segregation had a\npositive impact on house prices [2]. Furthermore the goal of the\nresearch that led to the creation of this dataset was to study the\nimpact of air quality but it did not give adequate demonstration of the\nvalidity of this assumption.\n\nThe scikit-learn maintainers therefore strongly discourage the use of\nthis dataset unless the purpose of the code is to study and educate\nabout ethical issues in data science and machine learning.\n\nIn this special case, you can fetch the dataset from the original\nsource::\n\n import pandas as pd\n import numpy as np\n\n data_url = \"http://lib.stat.cmu.edu/datasets/boston\"\n raw_df = pd.read_csv(data_url, sep=\"\\s+\", skiprows=22, header=None)\n data = np.hstack([raw_df.values[::2, :], raw_df.values[1::2, :2]])\n target = raw_df.values[1::2, 2]\n\nAlternative datasets include the California housing dataset and the\nAmes housing dataset. You can load the datasets as follows::\n\n from sklearn.datasets import fetch_california_housing\n housing = fetch_california_housing()\n\nfor the California housing dataset and::\n\n from sklearn.datasets import fetch_openml\n housing = fetch_openml(name=\"house_prices\", as_frame=True)\n\nfor the Ames housing dataset.\n\n[1] M Carlisle.\n\"Racist data destruction?\"\n\n\n[2] Harrison Jr, David, and Daniel L. Rubinfeld.\n\"Hedonic housing prices and the demand for clean air.\"\nJournal of environmental economics and management 5.1 (1978): 81-102.\n\n" ] - }, - { - "data": { - "text/plain": [ - "dict_keys(['data', 'target', 'feature_names', 'DESCR', 'filename', 'data_module'])" - ] - }, - "execution_count": 16, - "metadata": {}, - "output_type": "execute_result" } ], "source": [ @@ -3472,7 +3426,7 @@ }, { "cell_type": "markdown", - "id": "aa3b722c", + "id": "ef2f9bce", "metadata": { "editable": true }, @@ -3483,7 +3437,7 @@ { "cell_type": "code", "execution_count": 17, - "id": "828172e1", + "id": "150d1433", "metadata": { "collapsed": false, "editable": true @@ -3497,7 +3451,7 @@ }, { "cell_type": "markdown", - "id": "eee71c11", + "id": "1be017ef", "metadata": { "editable": true }, @@ -3508,37 +3462,12 @@ { "cell_type": "code", "execution_count": 18, - "id": "7c8a5c54", + "id": "01ef8953", "metadata": { "collapsed": false, "editable": true }, - "outputs": [ - { - "data": { - "text/plain": [ - "CRIM 0\n", - "ZN 0\n", - "INDUS 0\n", - "CHAS 0\n", - "NOX 0\n", - "RM 0\n", - "AGE 0\n", - "DIS 0\n", - "RAD 0\n", - "TAX 0\n", - "PTRATIO 0\n", - "B 0\n", - "LSTAT 0\n", - "MEDV 0\n", - "dtype: int64" - ] - }, - "execution_count": 18, - "metadata": {}, - "output_type": "execute_result" - } - ], + "outputs": [], "source": [ "# check for missing values in all the columns\n", "boston.isnull().sum()" @@ -3546,7 +3475,7 @@ }, { "cell_type": "markdown", - "id": "a0c893b5", + "id": "adc486b5", "metadata": { "editable": true }, @@ -3557,35 +3486,12 @@ { "cell_type": "code", "execution_count": 19, - "id": "58711c38", + "id": "2471fc63", "metadata": { "collapsed": false, "editable": true }, - "outputs": [ - { - "name": "stderr", - "output_type": "stream", - "text": [ - "/Users/mhjensen/miniforge3/envs/myenv/lib/python3.9/site-packages/seaborn/distributions.py:2619: FutureWarning: `distplot` is a deprecated function and will be removed in a future version. Please adapt your code to use either `displot` (a figure-level function with similar flexibility) or `histplot` (an axes-level function for histograms).\n", - " warnings.warn(msg, FutureWarning)\n" - ] - }, - { - "data": { - "image/png": "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\n", - "text/plain": [ - "
    " - ] - }, - "metadata": { - "filenames": { - "image/png": "/Users/mhjensen/Teaching/MachineLearning/doc/LectureNotes/_build/jupyter_execute/week35_199_1.png" - } - }, - "output_type": "display_data" - } - ], + "outputs": [], "source": [ "# set the size of the figure\n", "sns.set(rc={'figure.figsize':(11.7,8.27)})\n", @@ -3597,7 +3503,7 @@ }, { "cell_type": "markdown", - "id": "d899ec3f", + "id": "e26d39f7", "metadata": { "editable": true }, @@ -3608,37 +3514,12 @@ { "cell_type": "code", "execution_count": 20, - "id": "59925df7", + "id": "6bb60001", "metadata": { "collapsed": false, "editable": true }, - "outputs": [ - { - "data": { - "text/plain": [ - "" - ] - }, - "execution_count": 20, - "metadata": {}, - "output_type": "execute_result" - }, - { - "data": { - "image/png": "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\n", - "text/plain": [ - "
    " - ] - }, - "metadata": { - "filenames": { - "image/png": "/Users/mhjensen/Teaching/MachineLearning/doc/LectureNotes/_build/jupyter_execute/week35_201_1.png" - } - }, - "output_type": "display_data" - } - ], + "outputs": [], "source": [ "# compute the pair wise correlation for all columns \n", "correlation_matrix = boston.corr().round(2)\n", @@ -3649,7 +3530,7 @@ }, { "cell_type": "markdown", - "id": "083a679e", + "id": "90f47dc1", "metadata": { "editable": true }, @@ -3660,27 +3541,12 @@ { "cell_type": "code", "execution_count": 21, - "id": "127a3dda", + "id": "a1f980e4", "metadata": { "collapsed": false, "editable": true }, - "outputs": [ - { - "data": { - "image/png": "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\n", - "text/plain": [ - "
    " - ] - }, - "metadata": { - "filenames": { - "image/png": "/Users/mhjensen/Teaching/MachineLearning/doc/LectureNotes/_build/jupyter_execute/week35_203_0.png" - } - }, - "output_type": "display_data" - } - ], + "outputs": [], "source": [ "plt.figure(figsize=(20, 5))\n", "\n", @@ -3699,7 +3565,7 @@ }, { "cell_type": "markdown", - "id": "c72d1b7f", + "id": "9efdaaaa", "metadata": { "editable": true }, @@ -3710,7 +3576,7 @@ { "cell_type": "code", "execution_count": 22, - "id": "a1378976", + "id": "01e9afe5", "metadata": { "collapsed": false, "editable": true @@ -3723,7 +3589,7 @@ }, { "cell_type": "markdown", - "id": "d85205c1", + "id": "73335565", "metadata": { "editable": true }, @@ -3734,23 +3600,12 @@ { "cell_type": "code", "execution_count": 23, - "id": "040b1e85", + "id": "f865febb", "metadata": { "collapsed": false, "editable": true }, - "outputs": [ - { - "name": "stdout", - "output_type": "stream", - "text": [ - "(404, 2)\n", - "(102, 2)\n", - "(404,)\n", - "(102,)\n" - ] - } - ], + "outputs": [], "source": [ "from sklearn.model_selection import train_test_split\n", "\n", @@ -3765,7 +3620,7 @@ }, { "cell_type": "markdown", - "id": "32d25d47", + "id": "88f5a339", "metadata": { "editable": true }, @@ -3776,29 +3631,12 @@ { "cell_type": "code", "execution_count": 24, - "id": "1b0fac0d", + "id": "bacdbf9b", "metadata": { "collapsed": false, "editable": true }, - "outputs": [ - { - "name": "stdout", - "output_type": "stream", - "text": [ - "The model performance for training set\n", - "--------------------------------------\n", - "RMSE is 5.637129335071195\n", - "R2 score is 0.6300745149331701\n", - "\n", - "\n", - "The model performance for testing set\n", - "--------------------------------------\n", - "RMSE is 5.137400784702911\n", - "R2 score is 0.6628996975186953\n" - ] - } - ], + "outputs": [], "source": [ "from sklearn.linear_model import LinearRegression\n", "from sklearn.metrics import mean_squared_error, r2_score\n", @@ -3836,27 +3674,12 @@ { "cell_type": "code", "execution_count": 25, - "id": "02279b28", + "id": "09aa7ac9", "metadata": { "collapsed": false, "editable": true }, - "outputs": [ - { - "data": { - "image/png": "iVBORw0KGgoAAAANSUhEUgAAA7wAAAKrCAYAAADS54GgAAAAOXRFWHRTb2Z0d2FyZQBNYXRwbG90bGliIHZlcnNpb24zLjUuMSwgaHR0cHM6Ly9tYXRwbG90bGliLm9yZy/YYfK9AAAACXBIWXMAAA9hAAAPYQGoP6dpAABNDklEQVR4nO3df3CdZ3kn/EvHwnIi5EhyrRiIcYwjywQXYhwPhlJggqCzP9hWTXd2bcIUyrTZ1BOmUyD0JXQbhk2hbRrKD8NCyE4zCzawOM60bLtMtO90oW1oY71Q1jiWFGqMShoElhQrIlZin/P+4R4nkuyjc47Oj+c8z+czk0n86JHOraPbjr/Pfd/X1VYoFAoBAAAAKZNr9gAAAACgHgReAAAAUkngBQAAIJUEXgAAAFJJ4AUAACCVBF4AAABSSeAFAAAglQReAAAAUqm92QNYTqFQiHy+0OxhEBG5XJufBZll/pNV5j5ZZv6TZUmf/7lcW7S1tS17X+IDbz5fiKmpuWYPI/Pa23PR09MZp0//NM6ezTd7ONBQ5j9ZZe6TZeY/WdYK87+3tzNWrVo+8NrSDAAAQCoJvAAAAKSSwAsAAEAqCbwAAACkksALAABAKgm8AAAApFLVgffEiROxY8eOuP/++y9ce+SRR+Kmm26K6667Lt7whjfEvffeW5NBAgAAQKWqCrzPPPNMvOc974mf/vSnF65NT0/HO97xjrj66qvj0KFDceutt8bHPvaxOHToUM0GCwAAAOVqr+aTPvGJT0RnZ+eCa1/+8pdj9erVcccdd0R7e3ts2bIlTp48Gffcc0/ceOONNRksAAAAlKviwPvwww/Hl770pXjggQfiDW94w4XrR44ciV27dkV7+7Nfcvfu3fGZz3wmTp06FevWrat+kO2OGjfbqlW5Bf+GLDH/ySpznywz/8myNM3/igLv6dOn47bbbosPfOAD8YIXvGDBxx5//PHYunXrgmt9fX0REfHYY49VHXhzubbo6elc/kYaYu3ay5o9BGga85+sMvfJMvOfLEvD/K8o8N5xxx1x3XXXxVve8pYlHztz5kysXr16wbWOjo6IiJifn696gPl8IU6f/unyN1JXq1blYu3ay+L06afi3Ll8s4cDDWX+k1XmPllm/pNlrTD/1669rKwV6LID7wMPPBBHjhyJP//zP7/ox9esWRNPP/30gmvFoHv55ZeX+zIXdfZsMt/kLDp3Lu/nQWaZ/2SVuU+Wmf9kWRrmf9mB99ChQ3Hq1KkF53YjIn7v934v7r333njhC18Yk5OTCz5W/PWVV1658pECAABABcoOvHfddVecOXNmwbU3v/nN8a53vSv+9b/+1/E//+f/jC9+8Ytx7ty5WLVqVUREPPTQQ7F58+YVFawCAACAapRdduvKK6+MTZs2LfgnImLdunXxohe9KG688cZ48skn4/bbb49HH3007r///rjvvvvi5ptvrtvgAQAA4FJqVmd63bp18bnPfS5OnDgRQ0ND8clPfjJuu+22GBoaqtVLAAAAQNkq7sP7XKOjowt+/fKXvzy+9KUvrWhAAAAAUAut30kYAAAALkLgBQAAIJUEXgAAAFJJ4AUAACCVVlS0CgAAgPTI5wvxyPen4pkT0/G8tkJseeEVkcu1NXtYVRN4AQAAiJHRyTgwPB7Ts/MXrvV0dcTewf7YOdDXxJFVz5ZmAACAjBsZnYz9h48uCLsREdOz87H/8NEYGZ1s0shWRuAFAADIsHy+EAeGx0vec3B4PPL5QoNGVDsCLwAAQIaNTcwsWdldbGp2PsYmZhozoBoSeAEAADJsZq502K30viQReAEAADKsu7OjpvclicALAACQYVs3dkdPV+kw29vVEVs3djdmQDUk8AIAAGRYLtcWewf7S96zZ7C/JfvxCrwAAAAZt3OgL/YNbV+y0tvb1RH7hra3bB/e9mYPAAAAgObbOdAXO/rXx/ceeyKeKbTF89oKseWFV7Tkym6RwAsAAEBEnN/e/NKre6OnpzOmp+fi7Nl8s4e0IrY0AwAAkEoCLwAAAKkk8AIAAJBKzvACAABNk88XYmxiJmbm5qO783yv11YukkSyCLwAAEBTjIxOxoHh8Zienb9wraerI/YO9rdsGxySxZZmAACg4UZGJ2P/4aMLwm5ExPTsfOw/fDRGRiebNDLSROAFAAAaKp8vxIHh8ZL3HBwej3y+0KARkVYCLwAAdZHPF+L4yen45rHH4/jJaeGFC8YmZpas7C42NTsfYxMzjRkQqeUMLwAANedsJqXMzJUOu5XeB5dihRcAgJpyNpPldHd21PQ+uBSBFwCAmnE2k3Js3dgdPV2lw2xv1/kWRbASAi8AADXjbCblyOXaYu9gf8l79gz268fLigm8AADUjLOZlGvnQF/sG9q+ZKW3t6sj9g1td9a7BAXhyqdoFQAANeNsJpXYOdAXO/rXx9jETMzMzUd35/ltzFZ2L01BuMpY4QUAoGaczaRSuVxbbNvUE7uv3RDbNvUIuyUoCFc5gRcAgJpxNhPqQ0G46gi8AADUlLOZUHsKwlXHGV4AAGrO2UyoLQXhqiPwAgBQF8WzmcDKKQhXHVuaAQAAEk5BuOoIvAAAAAmnIFx1BF4AAIAWoCBc5ZzhBQAAaBEKwlVG4AUAAGghCsKVz5ZmAAAAUkngBQAAIJVsaQYAACqSzxecIaUlCLwAAEDZRkYn48DweEzPzl+41tPVEXsH+1UJJnFsaQYAAMoyMjoZ+w8fXRB2IyKmZ+dj/+GjMTI62aSRwcUJvAAAwLLy+UIcGB4vec/B4fHI5wsNGhEsT+AFAACWNTYxs2Rld7Gp2fkYm5hpzICgDAIvAACwrJm50mG30vugEQReAABgWd2dHTW9DxpB4AUAAJa1dWN39HSVDrO9XedbFEFSCLwAAMCycrm22DvYX/KePYP9+vG2uHy+EI98fyr+z//3T/HI96davgiZPrwAAEBZdg70xb6h7Uv68PZ2dcQefXhbXhp7LAu8AABA2XYO9MWO/vUxNjETM3Pz0d15fhuzld3WVuyxvFixx/K+oe0tGXoFXgAAoCK5XFts29TT7GFQI+X2WN7Rv77lHmw4wwsAAJBhae6xLPACAABkWJp7LAu8AAAAGZbmHssCLwAAQIaluceywAsAAJBhae6xLPACAABkXLHH8uKV3t6ujpZtSRShLREAAADxbI/l7z32RDxTaIvntRViywuvaMmV3SKBFwAAgIg4v735pVf3Rk9PZ0xPz8XZs/lmD2lFbGkGAAAglQReAAAAUkngBQAAIJUEXgAAAFJJ4AUAACCVBF4AAABSSeAFAAAglQReAAAAUkngBQAAIJUEXgAAAFJJ4AUAACCVBF4AAABSSeAFAAAglQReAAAAUqm92QMAAOC8fL4QYxMzMTM3H92dHbF1Y3fkcm3NHhZAyxJ4AQASYGR0Mg4Mj8f07PyFaz1dHbF3sD92DvQ1cWQArcuWZgCAJhsZnYz9h48uCLsREdOz87H/8NEYGZ1s0sgAWpvACwDQRPl8IQ4Mj5e85+DweOTzhQaNCCA9bGkGAGiisYmZJSu7i03NzsfwkYlY+/zVzvYCVEDgBQBoopm50mG36Iv/76MX/tvZXoDy2NIMANBE3Z0dFX+Os70A5RF4AQCaaOvG7ujpqjz0RjjbC7AcgRcAoIlyubbYO9hf1edOzc7H2MRMbQcEkCICLwBAk+0c6It9Q9urWukt9wwwQBYpWgUAkAA7B/piR//6GJuYiZm5+Tj95NMLClVdSjVngAGyQuAFAEiIXK4ttm3qiYjz/Xm/9vBEyZZFvV3nWxQBcHG2NAMAJFA5Z3v3DPbrxwtQgsALAJBQlzrb29vVEfuGtuvDC7AMW5oBABJs8dne7s7z25it7AIsT+AFAEi4557tBaB8tjQDAACQSlZ4AQD+RT5fsHUYIEUEXgCAiBgZnYwDw+ML2gD1dHXE3sF+xaEAWpQtzQBA5o2MTsb+w0eX9Lydnp2P/YePxsjoZJNGBsBKCLwAQKbl84U4MDxe8p6Dw+ORzxcaNCIAakXgBQAybWxiZsnK7mJTs/MxNjHTmAEBUDMCLwCQaTNzpcNupfcBkBwCLwCQad2dHTW9D4DkEHgBgEzburE7erpKh9nervMtigBoLQIvAJBpuVxb7B3sL3nPnsF+/XgBWpDACwBk3s6Bvtg3tH3JSm9vV0fsG9quDy9Ai2pv9gAAAJJg50Bf7OhfH2MTMzEzNx/dnee3MVvZBWhdAi8AwL/I5dpi26aeZg8DgBqxpRkAAIBUEngBAABIJVuaAQCgwfL5gvPi0AACLwAANNDI6GQcGB6P6dn5C9d6ujpi72C/iuBQY7Y0AwBAg4yMTsb+w0cXhN2IiOnZ+dh/+GiMjE42aWSQTgIvAAA0QD5fiAPD4yXvOTg8Hvl8oUEjgvQTeAEAoAHGJmaWrOwuNjU7H2MTM40ZEGSAM7wAABmgSFLzzcyVDruV3gcsT+AFAEg5RZKSobuzo6b3AcuzpRkAIMUUSUqOrRu7o6erdJjt7Tq/+g7UhsALAJBSiiQlSy7XFnsH+0ves2ew31ZzqCGBF4AVy+cLcfzkdHzz2ONx/OS0vzxDQiiSlDw7B/pi39D2JSu9vV0dsW9ouy3mUGPO8AKwIs4GQnIpkpRMOwf6Ykf/ekXEoAEEXgCqVjwbuFjxbKDVCmguRZKSK5dri22bepo9DEg9W5oBqIqzgZB8iiQBWSfwAlAVZwOz4Vy+EI98f8r57BalSBKQdbY0A1CVNJ8NzOcLztZFxMPHJ+PAg2Nx6okzF645n916ikWSFp+17+3qiD1+lkDKCbwAVCWtZwMV4TrP+ex0USQJyCpbmgGoShrPBhZD3uKt2sWQNzI62aSRNZbz2elULJK0+9oNsW1Tj7ALZILAC0BV0nY2UMh7lvPZAKSFwAtA1YpnAxev9PZ2dbTcllch71lpPp8NQLZUfIb31KlT8ZGPfCS+8Y1vxPz8fOzatStuu+22uOaaayIi4pFHHok777wzjh49Gt3d3fG2t70t3vnOd9Z84AAkQ1rOBgp5z0rr+WwAsqfiFd5bbrklJiYm4p577omvfOUrsWbNmnj7298eTz31VExPT8c73vGOuPrqq+PQoUNx6623xsc+9rE4dOhQPcYOQELU6mxgPl+I4yenm9ICR8h7VhrPZwOQTRWt8E5PT8dVV10Vt9xyS/T3nz+39Zu/+Zvxi7/4izE+Ph4PPfRQrF69Ou64445ob2+PLVu2xMmTJ+Oee+6JG2+8sS7fAADp0OzqyMWQV2pbcy1DXpJbHxXPZ1+sSnNRK53PBiC7Klrh7enpibvvvvtC2P3JT34S9957b2zYsCGuueaaOHLkSOzatSva25/N0bt3744TJ07EqVOnajtyAFIjCdWRG1mEa2R0Mt776b+NPzz4rfjsnx2LPzz4rXjvp/82UVWgdw70xa2/8vJYd8WaBddb8Xw2ANlVdR/e3/3d340vf/nLsXr16vj0pz8dl19+eTz++OOxdevWBff19Z3/H+Jjjz0W69atq26Q7WprNduqVbkF/4YsMf/rK58vxMHlqiP/7/HY9dIr676i+KqXbYjcqlx84WujMfWc8N27tiPe+uaB2LVt5SHv4eOl+9ve+isvr8nr1MLul22IN77q6nj46GMx9cSZ6H7+6hh4sXY2ZIM/+8myNM3/qgPvr/7qr8Z/+A//IQ4ePBj79u2LAwcOxJkzZ2L16tUL7uvoOH8GaH6+uiIfuVxb9PR0VjtMamzt2suaPQRoGvO/Pv7voz9ZEC4vZur0fDw2fSZ+9pqfqft43vzqzfHGV10dx/7xVEydPhO9a9fEtS9ZF6tqEPLO5Qtx4MGxkvccHB6PN77q6pq8Xq3sfvmLmj2ESzqXL9TlZwVF/uwny9Iw/6sOvMWqzB/60Ifi29/+dnz+85+PNWvWxNNPP73gvmLQvfzyy6t6nXy+EKdP/7TaYVIjq1blYu3ay+L06afi3Ll8s4cDDWX+19fEPz9R9n1XrWvc/3ivWnfZhdc7/URt/j/0yPen4tQTZ0re85OZp+Lv/uGf4qVX99bkNVci6XP/4eOTS1fjuzrirb9Qm9V4si3p8x/qqRXm/9q1l5W1Al1R4D116lQ89NBD8a/+1b+KVatWRURELpeLLVu2xOTkZGzYsCEmJxeePyr++sorr6zkpRY4ezaZb3IWnTuX9/Mgs8z/+ui67Hll39fq7/+p06XD7nPvS9L3msS5Xzz3vdjU7Hx84ivfcc6Ymkni/IdGScP8r2hT9uTkZLz73e+Ov//7v79w7Zlnnoljx47Fli1bYteuXTEyMhLnzp278PGHHnooNm/eXPX5XQDSLUstcLQ+qo18vhAHljv3PTze0LZWACRTRYF327Zt8drXvjY++MEPxpEjR2JsbCze9773xenTp+Ptb3973HjjjfHkk0/G7bffHo8++mjcf//9cd9998XNN99cr/ED0OIaWR252bIU7utpbGKmZPuoiPMrvWMTM40ZEACJVVHgbWtriz/5kz+J3bt3x2/91m/Fv//3/z6eeOKJ+MIXvhAvfOELY926dfG5z30uTpw4EUNDQ/HJT34ybrvtthgaGqrX+AFIgZ0DfbFvaPuSMJi2FjhZCvf1NDNXXiHMcu8DIL3aCoVCovf7nDuXj6mpuWYPI/Pa23PR09MZ09NzLb+PHypl/jdOPl+IsYmZmJmbj+7O8yudaQx/I6OTcWB4fMEqZW9XR+wZ7E9UuE/q3D9+cjr+8OC3lr3vtj07YtumngaMiDRK6vyHRmiF+d/b21n7olUAUE+5XFsmAsrOgb7Y0b8+E+G+Hopbw0tta7Y1HICICrc0AwC1UQz3u6/dENs29Qi7FbA1HIByCbwA1Fw+X4jjJ6fjm8cej+Mnp1XLpeaycu4bgJWxpRmAmrrY+dSero7Ym7Dzqa0oK2ecy2VrOADLEXgBqJmR0cnYf/jokuvTs/Ox//DRilbehLuFPEi4uKyc+wagOgIvADWRzxfiwPB4yXsODo/Hjv71ywZX4W6hWj5IAIAscYYXgJoYm5gpWTU3ImJqdj7GJmZK3lMMd4u/VjHcjYxOrnSoLaXcBwnOSQPAUgIvADUxM1c67JZzn3C3VK0eJABAFgm8ANREd2fH8jctc59wt1QtHiQAQFYJvADUxNaN3UtaxCzW23W++NSlCHdL1eJBAgBklcALQE3kcm2xd7C/5D17BvtLFqwS7paqxYMEAMgqgReAmtk50Bf7hrYvCWi9XR1lVRIW7paqxYOEZsvnC3H85HR889jjcfzkdKbOYAPQXNoSAVBTOwf6Ykf/+qp66BbD3cVa8BQlPdzVQ/FBwuJWTb1dHbEn4a2atJgCoJnaCoVCoh+znjuXj6mpuWYPI/Pa23PR09MZ09NzcfZsvtnDgYYy/xvvYiGpFcJdveXzhaoeJFRrpXP/Uv2Di/QPJsn82U+WtcL87+3tjFWrlt+wbIUXgMRZySpxmuVybbFtU0+zh1GWcltM7ehfn/mfKwD1I/ACkEitFO5YqpIWU37OANSLolUAQM1pMQVAEljhBaDpGn02lfrTYgqAJBB4AWgqVXxrJ0kPDootpkpta85aiykAGk/gBaBpLlXFd3p2PvYfPqqKbwWS9uBAiykAksAZXoAUyOcLcfzkdHzz2ONx/OR05POJ7jgXEeVX8W2F76XZig8OFq+mFh8cjIxOVv21z+UL8cj3p6qaW8X+wT1dC7ct93Z1eJgBQENY4QVocUlb2SuXKr61Uc/2Pw8fn4wDD47FqSfOXLhW6dzSYgqAZrLCC9DC6rmyV29pqOKbhJX1Sh4cVGJkdDI+8ZXvLAi7EdXNrWKLqd3Xbohtm3qEXQAaxgovQIuq58peI7R6Fd+krKzX48FBq88tACiywgvQouq1stcoxSq+pSS1im+SVtbr8eCg1ecWABQJvAAtqtW3BBer+JaSxCq+SSu2VY8HB60+twCgSOAFaFGtuCV48ZnXHf3rW66Kb9JWP+vx4KAV5xYAXIwzvAAtqriyVyp8JWlLcKkzr390y2tapopvElc/i+1/Fr+/vV0dsaeKM8WtNrcA4FIEXoAWVVzZ23/46CXvqWRlL58v1C10Fs+8LlY885rU1dyLSerqZy3b/9R6bgFAswi8AC2sVit79aw4nLaKv0le/Sy2/6mFnQN9ceuvvHxJH95qV40BoBkEXoAWt9KVvXqvvlZy5rVWYa2esrT6uWtbX7zxVVfH3/3DP8Wp02cSv90cABYTeAFSoNqVvUasvibxzOtK1frMbJKtyrXFS6/ujbNn880eCgBUTOAFyLBGrL4m9czrStXyzCwAUB8CL0CGNWL1NclnXleqlmdmAYDa04cXIMMasfpajz6xAADlEHgBWlg+X4jjJ6fjm8cej+MnpyOfL1T0+cXV11JqsfpaPPO6+LV6uzpaqiURANBabGkGaFHlthIq1V+3kRWHnXkFABpN4AVoQeW2EionFDey4rAzrwBAIwm8AC2m3FZC+ULEpx8or79ukldfS61Qt9JrAACNJ/ACtJhyWwl9/mujJe/50788Hpetbo9tm3oil2tL5Oprudu2k/4aAEBzKFoF0GLKbRE0+9QzJT8+d+Zs3PWlb8d7P/23MTI6WYuh1VRx2/bicF9coa7FmBvxGgBA8wi8AC1mJS2CLiaJ4a7sbdsVVqVu9GsAAM0l8AK0mHJaCXVd9ryKv26Swl2527bHJmYS/RoAQHMJvAAtpthKqJSbfmHrsqF4sSSFu3K3bZd7X7NeAwBoLoEXoAUVWwktDrW9XR2xb2h77Np25bKh+GKaFe7y+UIcPzkd3zz2eBw/OR1rL1td1uetZHt3uZ9b6y3kAEDjqNIM0KKWayV0qf66pTQj3F2qSnLnmvaYO3P2kp/X23X++61WcWt4qfdmpa8BADSXwAvQwsppJVQolHcutxnhrlglebFyAvqewf4V9cotbg2/2OvX6jUAgOaypRkgpYphcubJp8u6v9Hhrpwqyc+/7HnR/fyF25uL27Zr0SN3ua3h+vACQGuzwguQQuWEyaLero7YM9jf8HBXTpXkJ596Jt7zH6+LXFvbRbdt18JyW8MBgNYl8AKkUDlhMiLiP95wTQxev7Ep4a7cAlmnf/p07L52Q13HUs7WcACg9djSDJBC5YbJtc9f3bSVTFWSAYB6E3gBUijpYTKfL0S+UIjONaU3GqmSDACshC3NACmU5JY7F2tDdCmqJAMAK2GFFyCFii13SmlGmCxWjl4u7KqSDADUghVegATI5ws1rxJcbLmzeDW1WVWZy6kc3bmmPW75xe2xbVOPlV0AYMUEXoAmu9gW356ujthbg1CapJY75VSOnjtzNnK5NmEXAKgJgRegiYpbfBebnp2P/YeP1mRbb1Ja7pRbObrc+wAAluMML0CTlLPF9+DweOTzhQaNqL6SXjkaAEgfgRegScrZ4js1Ox9jEzONGVCdFStHl6INEQBQSwIvQJNkbYtvUitHAwDpJfACNEkWt/gWK0cvXunVhggAqAdFq4CGq0cLnlZU3OJbaltzGrf4JqlyNACQbgIv0FD1bMHTaopbfC9WpbmokVt8G/kgIimVowGAdBN4gYZpRAueVlPc4rv4IUBvV0fsaeBDAA8iAIA0EniBhii3Bc+O/vWZ29ra7C2+HkQAAGkl8AINUUkLnixudW3WFl8PIgCANFOlGWiIrLXgaRVZ6wUMAGSLwAs0RBZb8LQCDyIAgDQTeIGGKLbgKSWNLXiSzoMIACDNBF6gIYoteEoptwVPPl+I4yen45vHHo/jJ6cjny/UapiZ40EEAJBmilYBDVOLFjza59RW0noBAwDUksALNNRKWvBon1MfO/rXxy+9dnM8eGQi5s6cvXC90b2AAQBqTeAFGq6aFjza59THxVbMO9e0x5uuvyr+7Ws2ey8BgJbmDC/QErTPqb3iivni93XuzNl44K+/H98a/3GTRgYAUBsCL9AStM+prXJXzBUEAwBamcALtATtc2rLijkAkAUCL9AStM+pLSvmAEAWCLxAS6hlH1+smAMA2SDwAi2j2Md38Upvb1eHlkQVuuZFV0TbMs8G2trO3wcA0Kq0JQISL58vLOjb+wc3vzoe/eETFffx5VmP/vCJKCxTj6pQOH9fpS2kAACSQuAFEu1ifWJ7ujpi72B/7L52QxNH1tqc4QUAssCWZiCxLtUndnp2PvYfPhojo5NLPiefL8Txk9PxzWOPx/GT09rqXIIzvABAFljhBRKp3D6xO/rXX9jOXGo12PnehYpVr0u1JlL1GgBodVZ4gUSqtE9sNavBWVZO1eudA+tjbGLGKjkA0LIEXiCRKjljWu5qcCsGt3pu0b5U1eti9eYHj/xT/OHBb8V7P/23HhgAAC3JlmYgkSo5Y1rJavDiisOLK0CXU/G5ms+pRiO2aO8c6Isd/edXcr81/uN48Mg/LaneXFwl1/oJAGg1Ai+QSJWcMf374z8q62suXjWuJlA26pxwcYv2YvUIn7lcW2zd2B33fPVYyfsWn5kGAEg6W5qBRCrnjOmewf7I5dqqqjhczZnfh4835pxwM7ZoV3pmGgCgFQi8QGJd6oxpb1fHghXO4mpwKc+tOFxNoDyXL8QXvjZa0edUqxnhU19eACCNbGkGEu25Z0wvdWa2uBp8sS3ARcXV4IjKAmXxzO+xfzwVU1WeE65UM8KnvrwAQBoJvEDi5XJty4bI4mrw4vO1vV0dsWfR+dpqAuXU6TMVf0616hU+SxXb0pcXAEgjgRdIjXJWgyOqC5S9a9dU/DnVqkf4XK7YVqWr5AAArcAZXiBViqvBu6/dENs29Vw0oFV65jci4tqXrIveCj9nOZfqsVtJwa5ylFugq9wz0wAArcIKL5A51axmrsq1xVt/YSA+8ZXvlP05pSy34lrJFu1Syi3QVWw3VO4qOQBAK2grFAq162tRB+fO5WNqaq7Zw8i89vZc9PR0xvT0XJw9m2/2cKAmLhY6LxYonzv//+67j684hF6qx27Rc1dTS527Lcfxk9Pxhwe/tex9t+3ZseJiW6SPP/vJMvOfLGuF+d/b2xmrVi2/YdkKL5BZ1axmrnQFtNIV13IKdpWi3RAAkGUCL5Bp1QTKlYTQaloirYR2QwBAlgm8QKatdMtwpRq94qrdEACQZQIvkFnLFY6qh0avuGo3BABkmbZEQKYUWwEdHB4rq1VPrZXTEqnrsufFNS+6omavWWm7oUu1SwIAaDVWeCHhGr3lNs0utqJ7Kc8tHFVL5ay4zj71TLzvMw/VdKW53GJbzVj1BgCoF22JKEsrlCZPI+GjdpZrBXQxxVY99Zj/5Ybvi63A1ksl7ZLIBn/2k2XmP1nWCvO/3LZEtjRDQhXDR6O33KZROa2ALqaerXp2DvTFH9z86ui67Hkl7zs4PN6QLcXltkuyvRkAaCUCLySQ8FFb5bQCuphKC0dVevb10R8+EbNPPVPynmKLonqrpF0SAECrcIYXEqjRvVrTrpqV2kpb9VSz/bzRLYpq8RqNGAsAQK1Y4YUEEj5qq5oWP5W06ql2+3ktWxSttLJyo9slAQA0ghVeSCDho7aKrYDK2dbc29UReyooClbu9vOLVXwuZ1zlrDTXorhZrcYCAJAkVnghgcrp1Sp8lK/YCqiUN11/Vdy2Z0f84S2vqagS8UrOvpYzruVWmmtV3KwWYwEASBqBFxJI+Ki9nQN9sW9o+5IHCb1dHbFvaHvsGdwa2zb1VPyernT7+XLjKhW+a13cbCVjAQBIIluaIaGK4WPxVtVKt9zyrJ0DfbGjf32MTczEzNx8dHeeXyVfyYODWmw/r3Zc9ShuVo/3CACgWQReSDDho/ZyubaaVrau1dnXasZVr+JmtX6PAACaxZZmSLhi+Nh97YaqttxSX83cfq64GQBAaQIvwAo16+yr4mYAAKXZ0gxQA83Yfl5cXd5/+Ogl71HcDADIMoEXoEaacfZVcTMAgEsTeAFanOJmAAAXJ/ACNZHPFzIXuOrxPVf7NVVWBgBYSuAFVmxkdHLJltqero7Ym+IttfX4nrP4PgIA1JMqzcCKjIxOxv7DR5f0oZ2enY/9h4/GyOhkk0ZWP/X4nrP4PgIA1JvAC1Qtny/EgeHxkvccHB6PfL7QoBHVXz2+5yy+jwAAjSDwAlUbm5hZsiK52NTsfIxNzDRmQCuQzxfi+Mnp+Oaxx+P4yelLhst6fM9peh8BAJLEGV5aQhYLIrWCmbnSIa3S+5qlkrOz9fie0/I+AgAkjcBL4rVCIZ+sBvLuzo6a3tcMxbOzixXPzu4b2h6vetmGC9fr8T2n4X0EAEgigZdEKyeMNDv0tkIgr5etG7ujp6uj5Hbc3q7zDwCSKJ8vxBceHCt5z8Hh8dj10isv/Loe33Orv48AAEnlDC+J1QqFfLJUWfdiZ1xzubbYO9hf8vP2DPYndrX7q3/7/Zh58umS90zNzsfoD6Yv/Loe33Orv48AAEllhZfEqqSQz7ZNPQ0a1bPKDeQ7+te3fFBZbhV739D2JR/v7eqIPQle5R4ZnYwH/vpEWfcuDsX1+J5b9X0EAEiyigLvzMxM3H333fFXf/VX8eSTT8bAwEC8+93vjuuvvz4iIh555JG488474+jRo9Hd3R1ve9vb4p3vfGddBk76Jb2QT9IDea2Uu618R//6ljnHXM7Diufqfv7qJdfq8T232vtIaVk92w8ASVJR4P3t3/7tOHXqVNx9993R29sbBw4ciHe+851x//33R29vb7zjHe+IwcHB+OAHPxjf/va344Mf/GB0d3fHjTfeWK/xk2JJL+ST9EBeC5WuYrdKsC/nYUVRb1dHDLz44t9XPb7nVnofubQsn+0HgCQpO/CePHky/uZv/iYOHjwYr3zlKyMi4vbbb4+vf/3r8dWvfjXWrFkTq1evjjvuuCPa29tjy5YtcfLkybjnnnsEXqqS9EI+SQ/ktZDWVexKHkI4O0ulWqHYHgBkRdlFq3p6euKzn/1sbN++/cK1tra2KBQK8cQTT8SRI0di165d0d7+bIbevXt3nDhxIk6dOlXbUZMJSS/kUwzkpbR6Zd20rmKX+xDil157tWBCRSoptnexQnAAQG2VvcK7du3aeP3rX7/g2l/+5V/GD37wg3jta18bH/3oR2Pr1q0LPt7Xd/4vio899lisW7eu+kG2KybdbKtW5Rb8u1Fe9bINkVuViy98bTSmnlvIZ21HvPXNA7FrW3PDyE2/MBCf+Mp3LvnxPW/eGt977ImYefLp6H7+6hh4cU9LrRauW7um7Pta6ffptZt7o7erY8GcWqx3bUf80uu2RC7X1rT5T+t55PtTZe2K+Itvfj/+6luPLfxzrasj3voLzf9z7bnMfbLM/CfL0jT/q67SPDIyEu9///vjjW98Y9xwww3x4Q9/OFavXljYpaPj/CrK/Hz1qz+5XFv09HRW/fnU1tq1lzX8Nd/86s3xxlddHcf+8VRMnT4TvWvXxLUvWRerEhAc3/zqzfH8zo747AP/N049cebC9Z/pvixed90L44vD4wuur7tiTfzGL/1svOblL2zGcCv2qisuj3V/fmzB97DYz3RfFq96xVWJ+HlU4uZffnl8+L6HL/3xoZfHunXPX3CtGfOf1vLMienlb4qI+7++tEL41Ox8fOIr34n/51d3Je7PCHOfLDP/ybI0zP+qAu/w8HC85z3viVe84hVx9913R0TEmjVr4umnF7buKAbdyy+/vOoB5vOFOH36p1V/PrWxalUu1q69LE6ffirOncs3ZQxXrbssrlp3/jfd6SeSMydeuvGK+ON9PxejP5i+sJI7+9Nn4pP3/98l95564kx8+L6H49ZfeXmiVnFK2fumraVXsQf7E/XzKNdLN14Rt/7Kyy+5e+ClG6+I6em5iEjG/Kc1PK9t5duSP3P4OzHworWJ2A1i7pNl5j9Z1grzf+3ay8paga448H7+85+PO++8M970pjfFXXfddWFVd8OGDTE5Obng3uKvr7zyykpfZoGzZ5P5JmfRuXN5P49L6L+qOyLOP6R576f/tuS9X/jaaLziJesS8Rfa5ey45mdK9ofdcc3PtOyc2HHNz8QrXrLuoq1jLvY9mf8sZ8sLr1i22N5ypk7Px7ETU4kqBGfuk2XmP1mWhvlfUeA9cOBAfOhDH4q3ve1t8f73vz9yuWcT9a5du+KLX/xinDt3LlatWhUREQ899FBs3rx5Red3odWksbJxmvvDagNELRWL7V2sSnMlWq0QHAAkVdmnkE+cOBG///u/H29605vi5ptvjlOnTsWPf/zj+PGPfxyzs7Nx4403xpNPPhm33357PProo3H//ffHfffdFzfffHM9xw+Jk9bKxsVguPvaDbFt0/LFt2pZgVY1W1rJzoG+2De0fUkV996ujvil115d1tdo5XZmAJAkZa/wfu1rX4tnnnkmHnzwwXjwwQcXfGxoaCg+8pGPxOc+97m48847Y2hoKNavXx+33XZbDA0N1XzQkGRZ6M+7nJHRySVboHu6OmLvYH/FbX5q+bWgUS61KyIi4v/8wz8ntr84AKRNW6FQSPRSyblz+Ziammv2MDKvvT0XPT2dMT091/L7+OuteIZ3ub/Q/uEtr0nFluDFRkYnS27n3De0veygWsuvtRLmP7WUlHldDnOfLDP/ybJWmP+9vZ1lFa1q/cZKkDDFM3yl7Bnsb5mwW8l24ny+EAeGx0t+vYPD42VtSa7l14IkKbXlOUlhFwDSoOo+vMClFf9Cu3grbtdlz4ubfmFry/yFttLtxLUs2JXG4l9QlOZCcACQJAIv1MnOgb7IFyI+/7XRmH3qmYiImH3qmfji/340cm1tiQ+9l9p2OT07H/sPH73oSlQtC3altfgXFKkQDgD1Z0sz1MnI6GR8+oGjF8JuUTEwjoxOXuIzm6/a7cS1LNil+BcAACsl8EIdtPr500q2Ez/X1o3dS84lLlZuBdpafi0AALJJ4IU6qDYwJkW124lrWbArbcW/AABoPIEX6qDVz5+uZDtxLSvQqmYLAMBKKFoFddDq50+L24mX6yV8qe3EtaxAq5otAADVEnihDlYaGJutuJ34YlWai5bbTlzLCrSq2QIAUA1bmqEO0nD+1HZiAABanRVeqJNiYDwwPL5gpbe3qyP2DPa3RGC0nRgAgFYm8EKcbyNUj1CXhsBoOzEAAK1K4CXzRkYnl6zC9nR1xN4arcIKjAAA0BzO8JJpI6OTsf/w0SXFpaZn52P/4aMxMjrZpJEBAAArJfCSWfl8IQ4Mj5e85+DweOTzhQaNCAAAqCVbmsmc4nndYyenSrYNioiYmp2PsYkZW5JTrF7ntwEAaD6Bl0y52Hnd5czMlX8vraXa89tCMgBAaxB4yYzied1KdXd2LH8TLedS86F4fvtSvYbrXeSsVoRyAACBl4wo57zuxfR2nQ8KpEu557d39K9fEBIfPl5dSG60VgnlAAD1pmgVmTA2MVPRNuaiPYP9VsVSqJz5UDy/XXQuX4gvfG205OckociZyuMAAM8SeMmESs/h9nZ1JGa1jtordz48975j/3gqpioMyY2m8jgAwEK2NJMJ5Z7D/bev3hTXXt3rvGOK5fOFOP3k02Xd+9x5M3X6TFmf08wiZ5WsXKs8DgBkgcBLJmzd2B09XR0lw0BvV0f80s+/RNBNsUqqdC8+v927dk1Zr9HMImfVrFwDAKSZLc1kQi7XFnsH+0ve47xufeTzhTh+cjq+eezxOH5yumnbaS91tvVSFs+Ha1+yLnq7SofZZhc5KzdsqzwOAGSFFV4yY+dAX+wb2r5kha+3qyP2qF5bF0mpFlxJle5LzYdVubZ46y8MxCe+8p1Lfm6zH5qUu5NB5XEAICsEXjJl50Bf7Ohfrz9pA1Tb57Yeyq3S/R9vuCYGr994yfmwa1uyH5oUdzKU6jfd7FAOANBIAi+Zk8u1KdhTZ9X2ua2Xcs+srn3+6mXHc7GHJte86Ip49IdPxDePPd70hyh2MgAAPEvgBWouadWCa3229bkPTUZGJ+N9n3mo6du2n8tOBgCA8xStAmouadWCi2dbS6nmbOulCmEVt22PjE5WOtSaKYby3dduiG2beoRdACCTBF6g5pJWLbgeVbrL3bbdrKrUAAAIvEAd1GtFdSWKZ1sXj6u3q6OqAlqVbNsGAKA5nOEFai6p1YJrebY1adu2AQBYygovUBe1XlFNmqRt2wYAYCkrvJAi+XwhUZV5k1YteGR0ckm7nmorKhe3bZfa1tzobdsAACwk8EJK1DLM1VJS+h4XKyovVqyoXOmqc1K3bQMA8CxbmiEFktweJwnqVVE57du2AQBanRVeMidp235Xqtwwt6N//ZLvM23vxaVUUlG50tXopG3bBgDgWQIvmZLUbb8rUW2YS+N7cSn1rqiclG3bAAAsZEszmZHWbb/VhLm0vheXoqIyAEA2CbxkQr3OcCZBpWEuze/FpRQrKpeiojIAQPoIvGRCJdt+W02lYS7N78WlFCsql6KiMgBA+gi8ZEK9z3A2U6VhLs3vRSkqKgMAZI+iVWRCrc5wJrWqcTHMLS5C1dvVEXsWFaHK8nlWFZUBALJF4CUTitt+S23lXe4MZ9KrGpcb5mrxXrQyFZUBALLDlmYyYaVnOFulqnExzO2+dkNs29Rz0e/HeVYAALJC4CUzqj3Dmcaqxs6zAgCQBbY0kynVnOGspKpxK22VdZ4VAIC0E3jJnErPcKa5qrHzrAAApJnAC8vIclVjmi+plcEBAFqBwAvLyHpVY5on6ZXBAQCSTtEqWIaqxjRDq1QGBwBIMoEXyqCqMY2UxsrgAADNYEszPEep85KqGtMoaa0MDgDQaAIv/ItyzkuqakwjpLkyOABAI9nSDOG8JMmiMjgAQG0IvGSe85IkTbEyeCkqgwMALE/gJfMqOS8JjaAyOABAbQi8ZJ7zkiSRyuAAACunaBWZ57wkSaUyOADAygi8ZF7xvGSpbc3OS9IsKoMDAFTPlmYyz3lJAABIJ4EXwnlJAABII1ua4V84LwkAAOki8MJzOC8JAADpYUszAAAAqSTwAgAAkEoCLwAAAKkk8AIAAJBKAi8AAACpJPACAACQSgIvAAAAqSTwAgAAkEoCLwAAAKkk8AIAAJBKAi8AAACp1N7sAUAa5fOFGJuYiZm5+eju7IitG7sjl2tr9rAAACBTBF6osZHRyTgwPB7Ts/MXrvV0dcTewf7YOdDXxJEBAEC22NIMNTQyOhn7Dx9dEHYjIqZn52P/4aMxMjrZpJEBAED2CLxQI/l8IQ4Mj5e85+DweOTzhQaNCAAAsk3ghRoZm5hZsrK72NTsfIxNzDRmQAAAkHECL9TIzFzpsFvpfQAAwMoIvFAj3Z0dNb0PAABYGYEXamTrxu7o6SodZnu7zrcoAgAA6k/gTbh8vhDHT07HN489HsdPTit4lGC5XFvsHewvec+ewX79eAEAoEH04U0w/Vxbz86Bvtg3tH3Jz623qyP21OHnls8XYmxiJmbm5qO78/zqsUANAADnCbwJVeznulixn+u+oe1Cb0LtHOiLHf3r6x5EPRABAIDSbGlOIP1cW18u1xbbNvXE7ms3xLZNPXUJu/sPH13SBqn4QGRkdLKmrwcAAK1I4E0g/VwpxQMRAAAoj8CbQPq5UooHIgAAUB6BN4H0c6UUD0QAAKA8Am8C6edKKR6IAABAeQTeBEpTP1d9hGvPAxEAACiPtkQJ1eh+rvWgbU59FB+IXKxtVVGrPBABAIB6aisUColecjt3Lh9TU3PNHkbT5POFuvdzLUd7ey56ejpjenouzp7NL3v/pfoIF+kjvHIXe6DQSg9EWkml8x/Swtwny8x/sqwV5n9vb2esWrX8hmUrvNRcuW1zdvSvtwq5AjsH+mJH//pEPBBJg6Q8XAIAoHYE3gRr1S3BlbTN2bapp0GjSqdcrs17WAOt+nsNAIDSFK1KqOKW4MXBcXp2PvYfPhojo5NNGtnytM2hlbTy7zUAAEoTeBOo3C3BSa14rG0OraLVf68BAFCawJtAlWwJTiJtc2gV5f5eG/3BdINGBABALQm8CdTqW4LT1EeYdCv799qTT9d5JAAA1IPAm0Bp2BJc7CO8eKW3t6tDSyISo+zfa89fXeeRAABQD6o0J1BxS3CprZatsCVY2xySrtzfawMvVgkbAKAVWeFNoDRtCS62zdl97YbYtqmnJcZMdqTp9xoAAEsJvAllSzA0ht9rAADpZUtzgtkSDI3h9xoAQDoJvAlX3BIM1JffawAA6WNLMwAAAKlkhReoqXy+YGswAACJIPACNTMyOhkHhscXtPnp6eqIvYP9ij8BANBwtjQDNTEyOhn7Dx9d0tN2enY+9h8+GiOjk00aGQAAWSXwAiuWzxfiwPB4yXsODo9HPl9o0IgAAEDgBWpgbGJmycruYlOz8zE2MdOYAQEAQAi8QA3MzJUOu5XeBwAAtSDwAivW3dlR0/sAAKAWBF5gxbZu7I6ertJhtrfrfIsiAABoFIEXWLFcri32DvaXvGfPYL9+vAAANJTAC9TEzoG+2De0fclKb29XR+wb2q4PLwAADdfe7AEA6bFzoC929K+PsYmZmJmbj+7O89uYrewCANAMAi9QU7lcW2zb1NPsYQAAgC3NAAAApJPACwAAQCrZ0rwC+XzBWUUAAICEEnirNDI6GQeGx2N6dv7CtZ6ujtg72K8aLQAAQALY0lyFkdHJ2H/46IKwGxExPTsf+w8fjZHRySaNDAAAgCKBt0L5fCEODI+XvOfg8Hjk84UGjQgAAICLEXgrNDYxs2Rld7Gp2fkYm5hpzIAAAAC4KIG3QjNzpcNupfcBAABQHysKvJ/61KfibW9724JrjzzySNx0001x3XXXxRve8Ia49957VzTApOnu7KjpfQAAANRH1YH3T//0T+PjH//4gmvT09Pxjne8I66++uo4dOhQ3HrrrfGxj30sDh06tOKBJsXWjd3R01U6zPZ2nW9RBAAAQPNU3JboRz/6Udx+++0xMjISmzdvXvCxL3/5y7F69eq44447or29PbZs2RInT56Me+65J2688caaDbqZcrm22DvYH/sPH73kPXsG+/XjBQAAaLKKA+93v/vduOKKK+LP/uzPYv/+/fHDH/7wwseOHDkSu3btivb2Z7/s7t274zOf+UycOnUq1q1bV90g25N11PhVL9sQuVW5+MLXRmPqOQWsetd2xFvfPBC7tqWvD++qVbkF/4YsMf/JKnOfLDP/ybI0zf+KA+8NN9wQN9xww0U/9vjjj8fWrVsXXOvrOx/+HnvssaoCby7XFj09nRV/Xr29+dWb442vujqO/eOpmDp9JnrXrolrX7IuVqV8ZXft2suaPQRoGvOfrDL3yTLznyxLw/yvOPCWcubMmVi9evWCax0d58+7zs9XV7U4ny/E6dM/XfHY6uWqdZfFVevOT4TTTyR3nCu1alUu1q69LE6ffirOncs3ezjQUOY/WWXuk2XmP1nWCvN/7drLylqBrmngXbNmTTz99NMLrhWD7uWXX1711z17NplvchadO5f38yCzzH+yytwny8x/siwN87+mm7I3bNgQk5OTC64Vf33llVfW8qUAAACgpJoG3l27dsXIyEicO3fuwrWHHnooNm/eXHXBKgAAAKhGTQPvjTfeGE8++WTcfvvt8eijj8b9998f9913X9x88821fBkAAABYVk0D77p16+Jzn/tcnDhxIoaGhuKTn/xk3HbbbTE0NFTLlwEAAIBltRUKhUKzB1HKuXP5mJqaa/YwMq+9PRc9PZ0xPT3X8gfXoVLmP1ll7pNl5j9Z1grzv7e3s6wqza3fSRgAAAAuQuAFAAAglQReAAAAUkngBQAAIJUEXgAAAFJJ4AUAACCVBF4AAABSSeAFAAAglQReAAAAUkngBQAAIJUEXgAAAFJJ4AUAACCVBF4AAABSSeAFAAAglQReAAAAUqm92QOg9eXzhRibmImZufno7uyIrRu7I5dra/awAACAjBN4WZGR0ck4MDwe07PzF671dHXE3sH+2DnQ18SRAQAAWWdLM1UbGZ2M/YePLgi7ERHTs/Ox//DRGBmdbNLIAAAABF6qlM8X4sDweMl7Dg6PRz5faNCIAAAAFhJ4qcrYxMySld3FpmbnY2xipjEDAgAAWETgpSozc6XDbqX3AQAA1JrAS1W6Oztqeh8AAECtCbxUZevG7ujpKh1me7vOtygCAABoBoGXC/L5Qhw/OR3fPPZ4HD85XbLgVC7XFnsH+0t+vT2D/frxAgAATaMPLxFRXT/dnQN9sW9o+5LP6+3qiD368AIAAE0m8HKhn+5ixX66+4a2x6tetuGin7tzoC929K+PsYmZmJmbj+7O89uYrewCAADNJvBmXLn9dHe99MpLfjyXa4ttm3pqPTQAAIAVcYY348rtpzv6g+kGjQgAAKA2BN6MK7uf7pNP13kkAAAAtSXwZlzZ/XSfv7rOIwEAAKgtgTfjyu2nO/BiZ3QBAIDWIvBmnH66AABAWgm8XOinu3ilt7erI/YNbddPFwAAaEnaEhER+ukCAADpI/BygX66AABAmtjSDAAAQCoJvAAAAKSSwAsAAEAqCbwAAACkksALAABAKgm8AAAApJLACwAAQCoJvAAAAKSSwAsAAEAqCbwAAACkksALAABAKgm8AAAApJLACwAAQCoJvAAAAKSSwAsAAEAqCbwAAACkksALAABAKgm8AAAApJLACwAAQCoJvAAAAKSSwAsAAEAqCbwAAACkksALAABAKgm8AAAApFJ7swfAQvl8IcYmZmJmbj66Ozti68buyOXamj0sAACAliPwJsjI6GQcGB6P6dn5C9d6ujpi72B/7Bzoa+LIAAAAWo8tzQkxMjoZ+w8fXRB2IyKmZ+dj/+GjMTI62aSRAQAAtCaBNwHy+UIcGB4vec/B4fHI5wsNGhEAAEDrE3gTYGxiZsnK7mJTs/MxNjHTmAEBAACkgMCbADNzpcNupfcBAAAg8CZCd2dHTe8DAABA4E2ErRu7o6erdJjt7TrfoggAAIDyCLwJkMu1xd7B/pL37Bns148XAACgAgJvQuwc6It9Q9uXrPT2dnXEvqHt+vACAABUqL3ZA+BZOwf6Ykf/+hibmImZufno7jy/jdnKLgAAQOUE3oTJ5dpi26aeZg8DAACg5dnSDAAAQCoJvAAAAKSSwAsAAEAqCbwAAACkksALAABAKgm8AAAApJLACwAAQCoJvAAAAKSSwAsAAEAqCbwAAACkksALAABAKgm8AAAApJLACwAAQCoJvAAAAKSSwAsAAEAqCbwAAACkksALAABAKgm8AAAApJLACwAAQCoJvAAAAKSSwAsAAEAqCbwAAACkksALAABAKgm8AAAApJLACwAAQCoJvAAAAKSSwAsAAEAqCbwAAACkksALAABAKgm8AAAApJLACwAAQCoJvAAAAKSSwAsAAEAqCbwAAACkksALAABAKgm8AAAApJLACwAAQCoJvAAAAKSSwAsAAEAqCbwAAACkUnuzBwBZk88XYmxiJmbm5qO7syO2buyOXK6t2cMCAIDUEXihgUZGJ+PA8HhMz85fuNbT1RF7B/tj50BfE0cGAADpY0szNMjI6GTsP3x0QdiNiJienY/9h4/GyOhkk0YGAADpJPBCA+TzhTgwPF7ynoPD45HPFxo0IgAASD+BFxpgbGJmycruYlOz8zE2MdOYAQEAQAYIvNAAM3Olw26l9wEAAMsTeKEBujs7anofAACwPIEXGmDrxu7o6SodZnu7zrcoAgAAakPghQbI5dpi72B/yXv2DPbrxwsAADUk8EKD7Bzoi31D25es9PZ2dcS+oe368AIAQI21N3sAkAb5fCHGJmZiZm4+ujvPb02+2GrtzoG+2NG/vqx7AQCAlRF4YYVGRifjwPD4grZDPV0dsXew/6KrtrlcW2zb1NPIIQIAQCbZ0gwrMDI6GfsPH13SY3d6dj72Hz4aI6OTTRoZAAAg8EKV8vlCHBgeL3nPweHxyOcLDRoRAADwXAIvVGlsYmbJyu5iU7PzMTYx05gBAQAAC9Q88Obz+fj4xz8eP//zPx+veMUr4td+7dfi5MmTtX4ZaLqZudJht9L7AACA2qp54P3Upz4VX/ziF+O//Jf/El/60peira0tfv3Xfz2efvrpWr8UNFV3Z8fyN1VwHwAAUFs1DbxPP/10/Lf/9t/i1ltvjde//vWxbdu2+OhHPxo/+tGP4sEHH6zlS0HTbd3YvaSn7mK9XefbDgEAAI1X08B7/PjxmJubi927d1+4tnbt2rj22mvj4YcfruVLQdPlcm2xd7C/5D17Bvv12AUAgCapaR/exx9/PCIiXvCCFyy43tfXF//8z/9c9ddtb1dbq9lWrcot+DfnveplGyK3Khdf+NpoTD2ngFXv2o5465sHYte2pX14aT3mP1ll7pNl5j9Zlqb5X9PA+9RTT0VExOrVqxdc7+joiCeeeKKqr5nLtUVPT+eKx0ZtrF17WbOHkDhvfvXmeOOrro5j/3gqpk6fid61a+Lal6yLVVZ2U8f8J6vMfbLM/CfL0jD/axp416xZExHnz/IW/zsiYn5+Pi67rLo3K58vxOnTP63J+KjeqlW5WLv2sjh9+qk4dy7f7OEk0lXrLour1p2f56efMGfTxPwnq8x9ssz8J8taYf6vXXtZWSvQNQ28xa3Mk5OT8eIXv/jC9cnJydi2bVvVX/fs2WS+yVl07lzez4PMMv/JKnOfLDP/ybI0zP+absretm1bPP/5z4+/+7u/u3Dt9OnTcezYsbj++utr+VIAAABQUk1XeFevXh033XRT3HXXXdHb2xsvetGL4o/+6I9iw4YN8aY3vamWLwWkQD5fiLGJmZiZm4/uzvMtnFS1BgCgVmoaeCMi3vWud8XZs2fjAx/4QJw5cyZ27doV995775JCVkC2jYxOxoHh8Zh+TnXrnq6O2DvYHzsHVLcGAGDl2gqFQqHZgyjl3Ll8TE3NNXsYmdfenouens6Ynp5r+X38NN/I6GTsP3z0kh/fN7Q9UaHX/CerzH2yzPwny1ph/vf2dpZVtKr1GysBLSWfL8SB4fGS9xwcHo98PtHP4gAAaAECL9BQYxMzC7YxX8zU7HyMTcw0ZkAAAKSWwAs01Mxc6bBb6X0AAHApAi/QUN2dHTW9DwAALkXgBRpq68bu6OkqHWZ7u863KAIAgJUQeIGGyuXaYu9gf8l79gz268cLAMCKCbxAw+0c6It9Q9uXrPT2dnUkriURAACtq73ZAwCyaedAX+zoXx9jEzMxMzcf3Z3ntzFb2QUAoFYEXqBpcrm22Lapp9nDAAAgpWxpBgAAIJUEXgAAAFJJ4AUAACCVBF4AAABSSeAFAAAglQReAAAAUkngBQAAIJUEXgAAAFJJ4AUAACCVBF4AAABSSeAFAAAglQReAAAAUkngBQAAIJUEXgAAAFJJ4AUAACCVBF4AAABSSeAFAAAglQReAAAAUkngBQAAIJUEXgAAAFJJ4AUAACCV2ps9gFaWzxdibGImZubmo7uzI7Zu7I5crq3ZwwIAACAE3qqNjE7GgeHxmJ6dv3Ctp6sj9g72x86BviaODAAAgAhbmqsyMjoZ+w8fXRB2IyKmZ+dj/+GjMTI62aSRAQAAUCTwViifL8SB4fGS9xwcHo98vtCgEQEAAHAxAm+FxiZmlqzsLjY1Ox9jEzONGRAAAAAXJfBWaGaudNit9D4AAADqQ+CtUHdnR03vAwAAoD4E3gpt3dgdPV2lw2xv1/kWRQAAADSPwFuhXK4t9g72l7xnz2C/frwAAABNJvBWYedAX+wb2r5kpbe3qyP2DW3XhxcAACAB2ps9gFa1c6AvdvSvj7GJmZiZm4/uzvPbmK3sAgAAJIPAuwK5XFts29TT7GEAAABwEbY0AwAAkEoCLwAAAKkk8AIAAJBKAi8AAACpJPACAACQSgIvAAAAqSTwAgAAkEoCLwAAAKkk8AIAAJBKAi8AAACpJPACAACQSgIvAAAAqSTwAgAAkEoCLwAAAKkk8AIAAJBKAi8AAACpJPACAACQSgIvAAAAqSTwAgAAkEoCLwAAAKkk8AIAAJBKbYVCodDsQZRSKBQin0/0EDNj1apcnDuXb/YwoCnMf7LK3CfLzH+yLOnzP5dri7a2tmXvS3zgBQAAgGrY0gwAAEAqCbwAAACkksALAABAKgm8AAAApJLACwAAQCoJvAAAAKSSwAsAAEAqCbwAAACkksALAABAKgm8AAAApJLACwAAQCoJvAAAAKSSwAsAAEAqCbxc0qc+9al429vetuDaI488EjfddFNcd9118YY3vCHuvffeJo0Oam9mZib+83/+z/G6170uXvnKV8aePXviyJEjFz5u/pNWp06dive+972xe/fu2LFjR/zGb/xGPProoxc+bu6TFSdOnIgdO3bE/ffff+Ga+U+a/fCHP4yBgYEl//yP//E/IiId81/g5aL+9E//ND7+8Y8vuDY9PR3veMc74uqrr45Dhw7FrbfeGh/72Mfi0KFDTRol1NZv//Zvxz/8wz/E3XffHV/5ylfiZS97Wbzzne+M733ve+Y/qXbLLbfExMRE3HPPPfGVr3wl1qxZE29/+9vjqaeeMvfJjGeeeSbe8573xE9/+tML18x/0m50dDQ6OjriG9/4Rvz1X//1hX/e8pa3pGb+tzd7ACTLj370o7j99ttjZGQkNm/evOBjX/7yl2P16tVxxx13RHt7e2zZsiVOnjwZ99xzT9x4441NGjHUxsmTJ+Nv/uZv4uDBg/HKV74yIiJuv/32+PrXvx5f/epXY82aNeY/qTQ9PR1XXXVV3HLLLdHf3x8REb/5m78Zv/iLvxjj4+Px0EMPmftkwic+8Yno7OxccM3ffUi7sbGx2Lx5c/T19S352H333ZeK+W+FlwW++93vxhVXXBF/9md/Fq94xSsWfOzIkSOxa9euaG9/9jnJ7t2748SJE3Hq1KlGDxVqqqenJz772c/G9u3bL1xra2uLQqEQTzzxhPlPavX09MTdd999Iez+5Cc/iXvvvTc2bNgQ11xzjblPJjz88MPxpS99Kf7gD/5gwXXzn7QbHR2Na6655qIfS8v8F3hZ4IYbbog//uM/jo0bNy752OOPPx4bNmxYcK34NOixxx5ryPigXtauXRuvf/3rY/Xq1Reu/eVf/mX84Ac/iNe+9rXmP5nwu7/7u/FzP/dz8b/+1/+KO++8My6//HJzn9Q7ffp03HbbbfGBD3wgXvCCFyz4mPlP2o2NjcWpU6di79698ZrXvCb27NkT3/jGNyIiPfNf4KVsZ86cWRAGIiI6OjoiImJ+fr4ZQ4K6GRkZife///3xxje+MW644Qbzn0z41V/91Th06FD8u3/372Lfvn3x3e9+19wn9e6444647rrr4i1vecuSj5n/pNnTTz8d3//+9+PJJ5+M3/qt34rPfvaz8bM/+7Px67/+6/HQQw+lZv47w0vZ1qxZE08//fSCa8XJfvnllzdjSFAXw8PD8Z73vCde8YpXxN133x0R5j/ZUNzW9qEPfSi+/e1vx+c//3lzn1R74IEH4siRI/Hnf/7nF/24+U+arV69Oh5++OFob2+/EGy3b98e3/ve9+Lee+9Nzfy3wkvZNmzYEJOTkwuuFX995ZVXNmNIUHOf//zn49Zbb43Xve51cc8998SaNWsiwvwnvU6dOhVf/epX49y5cxeu5XK52LJlS0xOTpr7pNqhQ4fi1KlT8YY3vCF27NgRO3bsiIiI3/u934t/82/+jflP6l1++eVLVnG3bt0aP/rRj1Iz/wVeyrZr164YGRlZ8Jeihx56KDZv3hzr1q1r4sigNg4cOBAf+tCH4q1vfWv8yZ/8yYL/AZj/pNXk5GS8+93vjr//+7+/cO2ZZ56JY8eOxZYtW8x9Uu2uu+6Kv/iLv4gHHnjgwj8REe9617vis5/9rPlPqh0/fjx27NgRR44cWXD96NGjcc0116Rm/gu8lO3GG2+MJ598Mm6//fZ49NFH4/7774/77rsvbr755mYPDVbsxIkT8fu///vxpje9KW6++eY4depU/PjHP44f//jHMTs7a/6TWtu2bYvXvva18cEPfjCOHDkSY2Nj8b73vS9Onz4db3/72819Uu3KK6+MTZs2LfgnImLdunXxohe9yPwn1bZu3Rr9/f0X/vz/3ve+Fx/+8Ifj29/+dvyn//SfUjP/2wqFQqHZgyCZfud3fid++MMfxn//7//9wrXvfOc7ceedd8axY8di/fr18Wu/9mtx0003NXGUUBv/9b/+1/joRz960Y8NDQ3FRz7yEfOf1JqdnY0//uM/juHh4ZidnY3rr78+fud3fudCqyJznywZGBiID3/4w/HLv/zLEWH+k25TU1Nx1113xde//vU4ffp0XHvttfGe97wnrr/++ohIx/wXeAEAAEglW5oBAABIJYEXAACAVBJ4AQAASCWBFwAAgFQSeAEAAEglgRcAAIBUEngBAABIJYEXAACAVBJ4AQAASCWBFwAAgFQSeAEAAEil/x+AVJx45dBfRwAAAABJRU5ErkJggg==\n", - "text/plain": [ - "
    " - ] - }, - "metadata": { - "filenames": { - "image/png": "/Users/mhjensen/Teaching/MachineLearning/doc/LectureNotes/_build/jupyter_execute/week35_210_0.png" - } - }, - "output_type": "display_data" - } - ], + "outputs": [], "source": [ "# plotting the y_test vs y_pred\n", "# ideally should have been a straight line\n", @@ -3866,7 +3689,7 @@ }, { "cell_type": "markdown", - "id": "cd590eba", + "id": "cb088f7a", "metadata": { "editable": true }, @@ -3876,7 +3699,7 @@ }, { "cell_type": "markdown", - "id": "9968e6df", + "id": "a452bf26", "metadata": { "editable": true }, @@ -3890,7 +3713,7 @@ }, { "cell_type": "markdown", - "id": "6e0b933c", + "id": "603ea987", "metadata": { "editable": true }, @@ -3902,7 +3725,7 @@ }, { "cell_type": "markdown", - "id": "e3019867", + "id": "61b65c66", "metadata": { "editable": true }, @@ -3914,7 +3737,7 @@ }, { "cell_type": "markdown", - "id": "84b218f8", + "id": "d08fd064", "metadata": { "editable": true }, @@ -3926,7 +3749,7 @@ }, { "cell_type": "markdown", - "id": "19a7596b", + "id": "e8f62983", "metadata": { "editable": true }, @@ -3936,7 +3759,7 @@ }, { "cell_type": "markdown", - "id": "bd703e67", + "id": "d68a9415", "metadata": { "editable": true }, @@ -3948,7 +3771,7 @@ }, { "cell_type": "markdown", - "id": "123c9939", + "id": "3307fed7", "metadata": { "editable": true }, @@ -3958,7 +3781,7 @@ }, { "cell_type": "markdown", - "id": "e25cd9d9", + "id": "8a910e57", "metadata": { "editable": true }, @@ -3970,7 +3793,7 @@ }, { "cell_type": "markdown", - "id": "7a90c314", + "id": "218a6b48", "metadata": { "editable": true }, @@ -3981,7 +3804,7 @@ }, { "cell_type": "markdown", - "id": "342cbb0e", + "id": "8f3748ba", "metadata": { "editable": true }, @@ -3993,7 +3816,7 @@ }, { "cell_type": "markdown", - "id": "8174f656", + "id": "d0385420", "metadata": { "editable": true }, @@ -4005,7 +3828,7 @@ }, { "cell_type": "markdown", - "id": "9d4a6e02", + "id": "4644a05e", "metadata": { "editable": true }, @@ -4015,7 +3838,7 @@ }, { "cell_type": "markdown", - "id": "6165636b", + "id": "bfb350df", "metadata": { "editable": true }, @@ -4027,7 +3850,7 @@ }, { "cell_type": "markdown", - "id": "cd5ead70", + "id": "508acac7", "metadata": { "editable": true }, @@ -4039,7 +3862,7 @@ }, { "cell_type": "markdown", - "id": "ea18f6fe", + "id": "1cde0c41", "metadata": { "editable": true }, @@ -4049,7 +3872,7 @@ }, { "cell_type": "markdown", - "id": "9b42e1cf", + "id": "683baaea", "metadata": { "editable": true }, @@ -4061,7 +3884,7 @@ }, { "cell_type": "markdown", - "id": "ddc58b22", + "id": "ec9c67ea", "metadata": { "editable": true }, @@ -4071,7 +3894,7 @@ }, { "cell_type": "markdown", - "id": "288e8e6a", + "id": "cdc9c6fc", "metadata": { "editable": true }, @@ -4083,7 +3906,7 @@ }, { "cell_type": "markdown", - "id": "4fd80694", + "id": "c7590b65", "metadata": { "editable": true }, @@ -4093,7 +3916,7 @@ }, { "cell_type": "markdown", - "id": "b006a8c2", + "id": "f2d7afb2", "metadata": { "editable": true }, @@ -4133,7 +3956,7 @@ }, { "cell_type": "markdown", - "id": "725d878b", + "id": "69fd907d", "metadata": { "editable": true }, @@ -4150,7 +3973,7 @@ }, { "cell_type": "markdown", - "id": "fd5e5178", + "id": "33b93521", "metadata": { "editable": true }, @@ -4173,7 +3996,7 @@ }, { "cell_type": "markdown", - "id": "153ac58e", + "id": "600d8db6", "metadata": { "editable": true }, @@ -4190,7 +4013,7 @@ }, { "cell_type": "markdown", - "id": "3a4c4a00", + "id": "22fc0a80", "metadata": { "editable": true }, @@ -4209,7 +4032,7 @@ }, { "cell_type": "markdown", - "id": "c102eee7", + "id": "bd71990f", "metadata": { "editable": true }, @@ -4220,7 +4043,7 @@ }, { "cell_type": "markdown", - "id": "7005d428", + "id": "587d44ae", "metadata": { "editable": true }, @@ -4232,7 +4055,7 @@ }, { "cell_type": "markdown", - "id": "ebdbde59", + "id": "2158156f", "metadata": { "editable": true }, @@ -4250,7 +4073,7 @@ }, { "cell_type": "markdown", - "id": "8757437b", + "id": "10eb0b7c", "metadata": { "editable": true }, @@ -4266,7 +4089,7 @@ }, { "cell_type": "markdown", - "id": "dba77cf1", + "id": "2aceb644", "metadata": { "editable": true }, @@ -4278,7 +4101,7 @@ }, { "cell_type": "markdown", - "id": "2f275695", + "id": "1465b8be", "metadata": { "editable": true }, @@ -4288,7 +4111,7 @@ }, { "cell_type": "markdown", - "id": "32c17033", + "id": "b3afc822", "metadata": { "editable": true }, @@ -4303,7 +4126,7 @@ }, { "cell_type": "markdown", - "id": "13d50641", + "id": "4357f67d", "metadata": { "editable": true }, @@ -4315,7 +4138,7 @@ }, { "cell_type": "markdown", - "id": "e32d182b", + "id": "b2ed8199", "metadata": { "editable": true }, @@ -4325,7 +4148,7 @@ }, { "cell_type": "markdown", - "id": "566185cc", + "id": "a28f5e2a", "metadata": { "editable": true }, @@ -4337,7 +4160,7 @@ }, { "cell_type": "markdown", - "id": "69cc07d3", + "id": "dda00171", "metadata": { "editable": true }, @@ -4347,7 +4170,7 @@ }, { "cell_type": "markdown", - "id": "5a62e55b", + "id": "99e49156", "metadata": { "editable": true }, @@ -4359,7 +4182,7 @@ }, { "cell_type": "markdown", - "id": "185a7b6c", + "id": "3de354b0", "metadata": { "editable": true }, @@ -4371,7 +4194,7 @@ }, { "cell_type": "markdown", - "id": "b63994c4", + "id": "9b719377", "metadata": { "editable": true }, @@ -4386,7 +4209,7 @@ }, { "cell_type": "markdown", - "id": "1b5e5ea8", + "id": "f46453c7", "metadata": { "editable": true }, @@ -4397,7 +4220,7 @@ }, { "cell_type": "markdown", - "id": "c7cba8d9", + "id": "0255efb1", "metadata": { "editable": true }, @@ -4417,7 +4240,7 @@ }, { "cell_type": "markdown", - "id": "34a321a1", + "id": "61df6aad", "metadata": { "editable": true }, @@ -4429,7 +4252,7 @@ }, { "cell_type": "markdown", - "id": "adeb4e2a", + "id": "ac44e8fa", "metadata": { "editable": true }, @@ -4439,7 +4262,7 @@ }, { "cell_type": "markdown", - "id": "983c4d05", + "id": "a73ed285", "metadata": { "editable": true }, @@ -4451,7 +4274,7 @@ }, { "cell_type": "markdown", - "id": "30746d8f", + "id": "4809c104", "metadata": { "editable": true }, @@ -4480,7 +4303,7 @@ }, { "cell_type": "markdown", - "id": "15b1904e", + "id": "9ff4078a", "metadata": { "editable": true }, @@ -4507,7 +4330,7 @@ }, { "cell_type": "markdown", - "id": "825d56c0", + "id": "78a8b113", "metadata": { "editable": true }, @@ -4518,34 +4341,12 @@ { "cell_type": "code", "execution_count": 26, - "id": "83389e7a", + "id": "47f6d805", "metadata": { "collapsed": false, "editable": true }, - "outputs": [ - { - "name": "stdout", - "output_type": "stream", - "text": [ - "[[ 1. -1.]\n", - " [ 1. -1.]]\n", - "test U\n", - "[[0. 0.]\n", - " [0. 0.]]\n", - "test VT\n", - "[[0. 0.]\n", - " [0. 0.]]\n", - "[[-0.70710678 -0.70710678]\n", - " [-0.70710678 0.70710678]]\n", - "[2.00000000e+00 3.35470445e-17]\n", - "[[-0.70710678 0.70710678]\n", - " [ 0.70710678 0.70710678]]\n", - "[[-3.33066907e-16 4.44089210e-16]\n", - " [ 0.00000000e+00 2.22044605e-16]]\n" - ] - } - ], + "outputs": [], "source": [ "import numpy as np\n", "# SVD inversion\n", @@ -4580,7 +4381,7 @@ }, { "cell_type": "markdown", - "id": "6c1d5c64", + "id": "5d841c14", "metadata": { "editable": true }, @@ -4597,7 +4398,7 @@ }, { "cell_type": "markdown", - "id": "092d08fb", + "id": "579b46a4", "metadata": { "editable": true }, @@ -4620,7 +4421,7 @@ }, { "cell_type": "markdown", - "id": "680ca861", + "id": "1bb48e3c", "metadata": { "editable": true }, @@ -4634,7 +4435,7 @@ }, { "cell_type": "markdown", - "id": "d9109bdb", + "id": "a872fcf9", "metadata": { "editable": true }, @@ -4653,7 +4454,7 @@ }, { "cell_type": "markdown", - "id": "1bc782ad", + "id": "f0565ccd", "metadata": { "editable": true }, @@ -4663,7 +4464,7 @@ }, { "cell_type": "markdown", - "id": "fd98474c", + "id": "a659e96f", "metadata": { "editable": true }, @@ -4675,7 +4476,7 @@ }, { "cell_type": "markdown", - "id": "27505b56", + "id": "fcfcf6b0", "metadata": { "editable": true }, @@ -4689,7 +4490,7 @@ }, { "cell_type": "markdown", - "id": "97458ec0", + "id": "ea39064c", "metadata": { "editable": true }, @@ -4701,7 +4502,7 @@ }, { "cell_type": "markdown", - "id": "6a940c34", + "id": "0096e499", "metadata": { "editable": true }, @@ -4711,7 +4512,7 @@ }, { "cell_type": "markdown", - "id": "beb7c9c1", + "id": "bf32dfa9", "metadata": { "editable": true }, @@ -4723,7 +4524,7 @@ }, { "cell_type": "markdown", - "id": "892eca8e", + "id": "e0d6fee2", "metadata": { "editable": true }, @@ -4740,7 +4541,7 @@ }, { "cell_type": "markdown", - "id": "d716176c", + "id": "0cb15d9d", "metadata": { "editable": true }, @@ -4750,7 +4551,7 @@ }, { "cell_type": "markdown", - "id": "d6f76ea3", + "id": "754f4312", "metadata": { "editable": true }, @@ -4766,7 +4567,7 @@ }, { "cell_type": "markdown", - "id": "6cd96381", + "id": "5bd1e9b0", "metadata": { "editable": true }, @@ -4776,7 +4577,7 @@ }, { "cell_type": "markdown", - "id": "3235bb2a", + "id": "2a839ac1", "metadata": { "editable": true }, @@ -4792,7 +4593,7 @@ }, { "cell_type": "markdown", - "id": "cfb5e5fa", + "id": "69e34c64", "metadata": { "editable": true }, @@ -4802,7 +4603,7 @@ }, { "cell_type": "markdown", - "id": "30c811c8", + "id": "b32ae1de", "metadata": { "editable": true }, @@ -4818,7 +4619,7 @@ }, { "cell_type": "markdown", - "id": "b64ff89b", + "id": "00c3ff66", "metadata": { "editable": true }, @@ -4828,7 +4629,7 @@ }, { "cell_type": "markdown", - "id": "d2d214b1", + "id": "92f1238d", "metadata": { "editable": true }, @@ -4845,7 +4646,7 @@ }, { "cell_type": "markdown", - "id": "1734cbea", + "id": "71f43637", "metadata": { "editable": true }, @@ -4857,7 +4658,7 @@ }, { "cell_type": "markdown", - "id": "18b87d79", + "id": "4bac0a15", "metadata": { "editable": true }, @@ -4869,7 +4670,7 @@ }, { "cell_type": "markdown", - "id": "7424dbeb", + "id": "b523b964", "metadata": { "editable": true }, @@ -4881,7 +4682,7 @@ }, { "cell_type": "markdown", - "id": "8bfde7d9", + "id": "3d7f8195", "metadata": { "editable": true }, @@ -4891,7 +4692,7 @@ }, { "cell_type": "markdown", - "id": "d7fae153", + "id": "f308dd0a", "metadata": { "editable": true }, @@ -4903,7 +4704,7 @@ }, { "cell_type": "markdown", - "id": "a5fe659e", + "id": "929784cf", "metadata": { "editable": true }, @@ -4915,7 +4716,7 @@ }, { "cell_type": "markdown", - "id": "0494a740", + "id": "09dccee1", "metadata": { "editable": true }, @@ -4927,7 +4728,7 @@ }, { "cell_type": "markdown", - "id": "cd9e9a2d", + "id": "165b3f17", "metadata": { "editable": true }, @@ -4937,7 +4738,7 @@ }, { "cell_type": "markdown", - "id": "a36f09cb", + "id": "24a8dd50", "metadata": { "editable": true }, @@ -4949,7 +4750,7 @@ }, { "cell_type": "markdown", - "id": "c595c4ab", + "id": "2597dc03", "metadata": { "editable": true }, @@ -4959,7 +4760,7 @@ }, { "cell_type": "markdown", - "id": "54ea720c", + "id": "4d40ddce", "metadata": { "editable": true }, @@ -4971,7 +4772,7 @@ }, { "cell_type": "markdown", - "id": "3b8cb8cc", + "id": "41d0e0cb", "metadata": { "editable": true }, @@ -4987,7 +4788,7 @@ }, { "cell_type": "markdown", - "id": "e825b356", + "id": "e4bafe51", "metadata": { "editable": true }, @@ -4999,7 +4800,7 @@ }, { "cell_type": "markdown", - "id": "2cbc23f9", + "id": "aab4d56f", "metadata": { "editable": true }, @@ -5011,7 +4812,7 @@ }, { "cell_type": "markdown", - "id": "8665bb8b", + "id": "861395ef", "metadata": { "editable": true }, @@ -5021,7 +4822,7 @@ }, { "cell_type": "markdown", - "id": "2aedf32c", + "id": "299b8198", "metadata": { "editable": true }, @@ -5033,7 +4834,7 @@ }, { "cell_type": "markdown", - "id": "e64ed163", + "id": "2096c2e7", "metadata": { "editable": true }, @@ -5044,7 +4845,7 @@ }, { "cell_type": "markdown", - "id": "b060bb08", + "id": "4ad3b043", "metadata": { "editable": true }, @@ -5056,7 +4857,7 @@ }, { "cell_type": "markdown", - "id": "0e9f682e", + "id": "66bf91e3", "metadata": { "editable": true }, @@ -5066,7 +4867,7 @@ }, { "cell_type": "markdown", - "id": "084d10ae", + "id": "95afc99c", "metadata": { "editable": true }, @@ -5078,7 +4879,7 @@ }, { "cell_type": "markdown", - "id": "322ae2b5", + "id": "73334115", "metadata": { "editable": true }, @@ -5088,7 +4889,7 @@ }, { "cell_type": "markdown", - "id": "2b934378", + "id": "fb6f936e", "metadata": { "editable": true }, @@ -5100,7 +4901,7 @@ }, { "cell_type": "markdown", - "id": "76fa0775", + "id": "f9093b47", "metadata": { "editable": true }, @@ -5111,7 +4912,7 @@ }, { "cell_type": "markdown", - "id": "4ab1ab5e", + "id": "fe539ee1", "metadata": { "editable": true }, @@ -5123,7 +4924,7 @@ }, { "cell_type": "markdown", - "id": "5c3528cd", + "id": "d130c8c1", "metadata": { "editable": true }, @@ -5141,7 +4942,7 @@ }, { "cell_type": "markdown", - "id": "99446c56", + "id": "6787b5c2", "metadata": { "editable": true }, @@ -5157,7 +4958,7 @@ }, { "cell_type": "markdown", - "id": "52b4ef86", + "id": "b2e599e5", "metadata": { "editable": true }, @@ -5169,7 +4970,7 @@ }, { "cell_type": "markdown", - "id": "14d03f17", + "id": "854ff040", "metadata": { "editable": true }, @@ -5181,7 +4982,7 @@ }, { "cell_type": "markdown", - "id": "08983b4e", + "id": "aaf5e54e", "metadata": { "editable": true }, @@ -5193,7 +4994,7 @@ }, { "cell_type": "markdown", - "id": "bf4aff1c", + "id": "444a68be", "metadata": { "editable": true }, @@ -5206,7 +5007,7 @@ }, { "cell_type": "markdown", - "id": "d1a70450", + "id": "56e0f274", "metadata": { "editable": true }, @@ -5222,7 +5023,7 @@ }, { "cell_type": "markdown", - "id": "4441a82e", + "id": "a55a54c3", "metadata": { "editable": true }, @@ -5236,7 +5037,7 @@ }, { "cell_type": "markdown", - "id": "985fe9f4", + "id": "b614c964", "metadata": { "editable": true }, @@ -5246,7 +5047,7 @@ }, { "cell_type": "markdown", - "id": "7d0b48ad", + "id": "624b1c18", "metadata": { "editable": true }, @@ -5258,7 +5059,7 @@ }, { "cell_type": "markdown", - "id": "927a1cc9", + "id": "63dc085a", "metadata": { "editable": true }, @@ -5268,7 +5069,7 @@ }, { "cell_type": "markdown", - "id": "28fe8612", + "id": "28db2f6a", "metadata": { "editable": true }, @@ -5280,7 +5081,7 @@ }, { "cell_type": "markdown", - "id": "643c5c24", + "id": "a9f1ebdd", "metadata": { "editable": true }, @@ -5290,7 +5091,7 @@ }, { "cell_type": "markdown", - "id": "31eb5551", + "id": "0b8bf07b", "metadata": { "editable": true }, @@ -5304,7 +5105,7 @@ }, { "cell_type": "markdown", - "id": "ee97772f", + "id": "5f237448", "metadata": { "editable": true }, @@ -5321,7 +5122,7 @@ }, { "cell_type": "markdown", - "id": "fdef2a70", + "id": "75b7044c", "metadata": { "editable": true }, @@ -5337,7 +5138,7 @@ }, { "cell_type": "markdown", - "id": "68211a1f", + "id": "51268862", "metadata": { "editable": true }, @@ -5349,7 +5150,7 @@ }, { "cell_type": "markdown", - "id": "9a8a18e2", + "id": "608b9dff", "metadata": { "editable": true }, @@ -5362,7 +5163,7 @@ }, { "cell_type": "markdown", - "id": "e7d94e46", + "id": "b06c316f", "metadata": { "editable": true }, @@ -5376,7 +5177,7 @@ }, { "cell_type": "markdown", - "id": "0c9c0c07", + "id": "e82ba709", "metadata": { "editable": true }, @@ -5386,7 +5187,7 @@ }, { "cell_type": "markdown", - "id": "3fc933af", + "id": "92d739a1", "metadata": { "editable": true }, @@ -5399,7 +5200,7 @@ }, { "cell_type": "markdown", - "id": "e97cce9c", + "id": "14ce5cea", "metadata": { "editable": true }, @@ -5418,7 +5219,7 @@ }, { "cell_type": "markdown", - "id": "d1be42f8", + "id": "f7e1f2b1", "metadata": { "editable": true }, @@ -5430,7 +5231,7 @@ }, { "cell_type": "markdown", - "id": "e957492f", + "id": "71910404", "metadata": { "editable": true }, @@ -5442,7 +5243,7 @@ }, { "cell_type": "markdown", - "id": "6f4bd14c", + "id": "cbd60268", "metadata": { "editable": true }, @@ -5452,7 +5253,7 @@ }, { "cell_type": "markdown", - "id": "ba1b4c89", + "id": "e6c94e3d", "metadata": { "editable": true }, @@ -5464,7 +5265,7 @@ }, { "cell_type": "markdown", - "id": "c9563317", + "id": "20cf812e", "metadata": { "editable": true }, @@ -5477,7 +5278,7 @@ }, { "cell_type": "markdown", - "id": "ed451710", + "id": "dd1cb8be", "metadata": { "editable": true }, @@ -5496,7 +5297,7 @@ }, { "cell_type": "markdown", - "id": "4eabcccb", + "id": "98a4e944", "metadata": { "editable": true }, @@ -5506,7 +5307,7 @@ }, { "cell_type": "markdown", - "id": "78678f6f", + "id": "8c6e3845", "metadata": { "editable": true }, @@ -5525,7 +5326,7 @@ }, { "cell_type": "markdown", - "id": "5840e451", + "id": "bc13a77d", "metadata": { "editable": true }, @@ -5543,7 +5344,7 @@ }, { "cell_type": "markdown", - "id": "75f212b9", + "id": "19d6cd9e", "metadata": { "editable": true }, @@ -5557,7 +5358,7 @@ }, { "cell_type": "markdown", - "id": "af4b97f1", + "id": "c5c7eee1", "metadata": { "editable": true }, @@ -5572,23 +5373,12 @@ { "cell_type": "code", "execution_count": 27, - "id": "bceeb8a6", + "id": "6ab6bcc3", "metadata": { "collapsed": false, "editable": true }, - "outputs": [ - { - "name": "stdout", - "output_type": "stream", - "text": [ - "0.10790125813226321\n", - "4.340071371496255\n", - "[[ 1.04193203 3.08165104]\n", - " [ 3.08165104 10.18383522]]\n" - ] - } - ], + "outputs": [], "source": [ "# Importing various packages\n", "import numpy as np\n", @@ -5604,7 +5394,7 @@ }, { "cell_type": "markdown", - "id": "e438fa73", + "id": "839a512c", "metadata": { "editable": true }, @@ -5621,23 +5411,12 @@ { "cell_type": "code", "execution_count": 28, - "id": "01ec3279", + "id": "bad7396d", "metadata": { "collapsed": false, "editable": true }, - "outputs": [ - { - "name": "stdout", - "output_type": "stream", - "text": [ - "0.08881497884574564\n", - "1.7086067479626619\n", - "[[1. 0.66080313]\n", - " [0.66080313 1. ]]\n" - ] - } - ], + "outputs": [], "source": [ "import numpy as np\n", "n = 100\n", @@ -5664,7 +5443,7 @@ }, { "cell_type": "markdown", - "id": "fb6ba409", + "id": "365c6ef8", "metadata": { "editable": true }, @@ -5678,7 +5457,7 @@ }, { "cell_type": "markdown", - "id": "6c5bfe67", + "id": "6fd82fe9", "metadata": { "editable": true }, @@ -5691,43 +5470,12 @@ { "cell_type": "code", "execution_count": 29, - "id": "b2b07565", + "id": "80ba738c", "metadata": { "collapsed": false, "editable": true }, - "outputs": [ - { - "name": "stdout", - "output_type": "stream", - "text": [ - "[[-0.40620066 -2.01265755]\n", - " [ 0.01458611 0.37737221]\n", - " [-1.0895387 -3.65442354]\n", - " [ 0.2338675 1.12044974]\n", - " [ 0.4676059 1.54393936]\n", - " [-0.65891389 -3.16304863]\n", - " [-0.1715252 0.39197698]\n", - " [ 0.71142161 2.95511792]\n", - " [ 0.39214397 0.13069442]\n", - " [ 0.50655336 2.3105791 ]]\n", - " 0 1\n", - "0 -0.406201 -2.012658\n", - "1 0.014586 0.377372\n", - "2 -1.089539 -3.654424\n", - "3 0.233868 1.120450\n", - "4 0.467606 1.543939\n", - "5 -0.658914 -3.163049\n", - "6 -0.171525 0.391977\n", - "7 0.711422 2.955118\n", - "8 0.392144 0.130694\n", - "9 0.506553 2.310579\n", - " 0 1\n", - "0 1.000000 0.952387\n", - "1 0.952387 1.000000\n" - ] - } - ], + "outputs": [], "source": [ "import numpy as np\n", "import pandas as pd\n", @@ -5747,7 +5495,7 @@ }, { "cell_type": "markdown", - "id": "e26d9b42", + "id": "4f390c8f", "metadata": { "editable": true }, @@ -5757,7 +5505,7 @@ }, { "cell_type": "markdown", - "id": "6200c4da", + "id": "4bceabcb", "metadata": { "editable": true }, @@ -5768,52 +5516,12 @@ { "cell_type": "code", "execution_count": 30, - "id": "1a0f5c54", + "id": "0146e7c8", "metadata": { "collapsed": false, "editable": true }, - "outputs": [ - { - "name": "stdout", - "output_type": "stream", - "text": [ - " 0 1 2 3 4 5 6 7 \\\n", - "0 0.0 0.000000 0.000000 0.000000 0.000000 0.000000 0.000000 0.000000 \n", - "1 0.0 0.078974 0.081276 0.075889 0.077168 0.078540 0.065410 0.066474 \n", - "2 0.0 0.081276 0.084076 0.078336 0.079946 0.081655 0.067707 0.069028 \n", - "3 0.0 0.075889 0.078336 0.077460 0.078986 0.080616 0.069452 0.070737 \n", - "4 0.0 0.077168 0.079946 0.078986 0.080764 0.082653 0.070986 0.072476 \n", - "5 0.0 0.078540 0.081655 0.080616 0.082653 0.084809 0.072621 0.074323 \n", - "6 0.0 0.065410 0.067707 0.069452 0.070986 0.072621 0.064074 0.065378 \n", - "7 0.0 0.066474 0.069028 0.070737 0.072476 0.074323 0.065378 0.066854 \n", - "8 0.0 0.067637 0.070457 0.072132 0.074084 0.076150 0.066787 0.068441 \n", - "9 0.0 0.068906 0.072000 0.073644 0.075816 0.078110 0.068307 0.070146 \n", - "10 0.0 0.055734 0.057835 0.060872 0.062337 0.063894 0.057393 0.058645 \n", - "11 0.0 0.056683 0.058996 0.062016 0.063653 0.065390 0.058552 0.059951 \n", - "12 0.0 0.057722 0.060254 0.063260 0.065077 0.066999 0.059807 0.061359 \n", - "13 0.0 0.058854 0.061614 0.064609 0.066612 0.068727 0.061163 0.062874 \n", - "14 0.0 0.060083 0.063080 0.066066 0.068264 0.070582 0.062624 0.064501 \n", - "\n", - " 8 9 10 11 12 13 14 \n", - "0 0.000000 0.000000 0.000000 0.000000 0.000000 0.000000 0.000000 \n", - "1 0.067637 0.068906 0.055734 0.056683 0.057722 0.058854 0.060083 \n", - "2 0.070457 0.072000 0.057835 0.058996 0.060254 0.061614 0.063080 \n", - "3 0.072132 0.073644 0.060872 0.062016 0.063260 0.064609 0.066066 \n", - "4 0.074084 0.075816 0.062337 0.063653 0.065077 0.066612 0.068264 \n", - "5 0.076150 0.078110 0.063894 0.065390 0.066999 0.068727 0.070582 \n", - "6 0.066787 0.068307 0.057393 0.058552 0.059807 0.061163 0.062624 \n", - "7 0.068441 0.070146 0.058645 0.059951 0.061359 0.062874 0.064501 \n", - "8 0.070213 0.072111 0.059993 0.061452 0.063019 0.064699 0.066500 \n", - "9 0.072111 0.074210 0.061443 0.063061 0.064793 0.066647 0.068629 \n", - "10 0.059993 0.061443 0.052305 0.053417 0.054617 0.055910 0.057300 \n", - "11 0.061452 0.063061 0.053417 0.054655 0.055987 0.057418 0.058952 \n", - "12 0.063019 0.064793 0.054617 0.055987 0.057457 0.059031 0.060716 \n", - "13 0.064699 0.066647 0.055910 0.057418 0.059031 0.060756 0.062599 \n", - "14 0.066500 0.068629 0.057300 0.058952 0.060716 0.062599 0.064606 \n" - ] - } - ], + "outputs": [], "source": [ "# Common imports\n", "import numpy as np\n", @@ -5862,7 +5570,7 @@ }, { "cell_type": "markdown", - "id": "be666eb5", + "id": "6e15d041", "metadata": { "editable": true }, @@ -5879,7 +5587,7 @@ }, { "cell_type": "markdown", - "id": "cc79dbf1", + "id": "107d5b46", "metadata": { "editable": true }, @@ -5891,7 +5599,7 @@ }, { "cell_type": "markdown", - "id": "7aaa9582", + "id": "e47d0e76", "metadata": { "editable": true }, @@ -5903,7 +5611,7 @@ }, { "cell_type": "markdown", - "id": "3c9ca18c", + "id": "86b8daf6", "metadata": { "editable": true }, @@ -5913,7 +5621,7 @@ }, { "cell_type": "markdown", - "id": "7450e1de", + "id": "934cc6c5", "metadata": { "editable": true }, @@ -5930,7 +5638,7 @@ }, { "cell_type": "markdown", - "id": "c190057c", + "id": "2a384ee9", "metadata": { "editable": true }, @@ -5940,7 +5648,7 @@ }, { "cell_type": "markdown", - "id": "20f4c172", + "id": "e9a632a7", "metadata": { "editable": true }, @@ -5955,7 +5663,7 @@ }, { "cell_type": "markdown", - "id": "746607df", + "id": "8cbf4cb8", "metadata": { "editable": true }, @@ -5965,7 +5673,7 @@ }, { "cell_type": "markdown", - "id": "d2419f36", + "id": "b29a7909", "metadata": { "editable": true }, @@ -5979,7 +5687,7 @@ }, { "cell_type": "markdown", - "id": "0c4d5713", + "id": "31b9c6a9", "metadata": { "editable": true }, @@ -5991,7 +5699,7 @@ }, { "cell_type": "markdown", - "id": "c51b1e85", + "id": "cdc2f810", "metadata": { "editable": true }, @@ -6003,7 +5711,7 @@ }, { "cell_type": "markdown", - "id": "df3d6e17", + "id": "0b7d368d", "metadata": { "editable": true }, @@ -6015,7 +5723,7 @@ }, { "cell_type": "markdown", - "id": "bda15ad2", + "id": "6d5ddd28", "metadata": { "editable": true }, @@ -6025,7 +5733,7 @@ }, { "cell_type": "markdown", - "id": "40ad7cbc", + "id": "a18622fc", "metadata": { "editable": true }, @@ -6037,7 +5745,7 @@ }, { "cell_type": "markdown", - "id": "305bd308", + "id": "b5a8893c", "metadata": { "editable": true }, @@ -6047,7 +5755,7 @@ }, { "cell_type": "markdown", - "id": "bb83e451", + "id": "50a0a62a", "metadata": { "editable": true }, @@ -6064,7 +5772,7 @@ }, { "cell_type": "markdown", - "id": "64d007a7", + "id": "20380d89", "metadata": { "editable": true }, @@ -6074,7 +5782,7 @@ }, { "cell_type": "markdown", - "id": "c0fe2564", + "id": "10805b50", "metadata": { "editable": true }, @@ -6086,7 +5794,7 @@ }, { "cell_type": "markdown", - "id": "630c43cb", + "id": "b9c31a46", "metadata": { "editable": true }, @@ -6096,7 +5804,7 @@ }, { "cell_type": "markdown", - "id": "1e412f4c", + "id": "1f48b48e", "metadata": { "editable": true }, @@ -6108,7 +5816,7 @@ }, { "cell_type": "markdown", - "id": "2294efa0", + "id": "ad8f7a8c", "metadata": { "editable": true }, @@ -6122,7 +5830,7 @@ }, { "cell_type": "markdown", - "id": "ec2d9133", + "id": "9e0dec01", "metadata": { "editable": true }, @@ -6134,7 +5842,7 @@ }, { "cell_type": "markdown", - "id": "be85e557", + "id": "46fd0b6d", "metadata": { "editable": true }, @@ -6156,7 +5864,7 @@ }, { "cell_type": "markdown", - "id": "61531c33", + "id": "3d2047ca", "metadata": { "editable": true }, @@ -6168,7 +5876,7 @@ }, { "cell_type": "markdown", - "id": "549a9854", + "id": "4a5f5016", "metadata": { "editable": true }, @@ -6183,7 +5891,7 @@ }, { "cell_type": "markdown", - "id": "ace8d1d3", + "id": "52651fc6", "metadata": { "editable": true }, @@ -6195,7 +5903,7 @@ }, { "cell_type": "markdown", - "id": "4624e6fc", + "id": "fea09344", "metadata": { "editable": true }, @@ -6207,7 +5915,7 @@ }, { "cell_type": "markdown", - "id": "4b8a8b55", + "id": "bcfd303f", "metadata": { "editable": true }, @@ -6217,7 +5925,7 @@ }, { "cell_type": "markdown", - "id": "e8a41480", + "id": "f684d942", "metadata": { "editable": true }, @@ -6229,7 +5937,7 @@ }, { "cell_type": "markdown", - "id": "6a36c786", + "id": "1e54bd36", "metadata": { "editable": true }, @@ -6239,7 +5947,7 @@ }, { "cell_type": "markdown", - "id": "462349df", + "id": "4cdcdef2", "metadata": { "editable": true }, @@ -6251,7 +5959,7 @@ }, { "cell_type": "markdown", - "id": "f3e432cb", + "id": "a6d5bd03", "metadata": { "editable": true }, @@ -6261,7 +5969,7 @@ }, { "cell_type": "markdown", - "id": "20a1bdac", + "id": "a4d9fc21", "metadata": { "editable": true }, @@ -6273,7 +5981,7 @@ }, { "cell_type": "markdown", - "id": "43ac5bba", + "id": "119bc56e", "metadata": { "editable": true }, @@ -6290,7 +5998,7 @@ }, { "cell_type": "markdown", - "id": "ff1f6546", + "id": "d15cad60", "metadata": { "editable": true }, @@ -6303,7 +6011,7 @@ }, { "cell_type": "markdown", - "id": "cf2d5142", + "id": "f725d905", "metadata": { "editable": true }, @@ -6315,7 +6023,7 @@ }, { "cell_type": "markdown", - "id": "0e74ad82", + "id": "a2a5b25f", "metadata": { "editable": true }, @@ -6325,7 +6033,7 @@ }, { "cell_type": "markdown", - "id": "f0e17a56", + "id": "a9f43162", "metadata": { "editable": true }, @@ -6338,7 +6046,7 @@ }, { "cell_type": "markdown", - "id": "b11ffbe6", + "id": "debb0a19", "metadata": { "editable": true }, @@ -6348,7 +6056,7 @@ }, { "cell_type": "markdown", - "id": "3f4e49db", + "id": "2764c014", "metadata": { "editable": true }, @@ -6360,7 +6068,7 @@ }, { "cell_type": "markdown", - "id": "e22c2482", + "id": "ad141726", "metadata": { "editable": true }, @@ -6373,7 +6081,7 @@ }, { "cell_type": "markdown", - "id": "a7e7dfe5", + "id": "d194482f", "metadata": { "editable": true }, @@ -6386,7 +6094,7 @@ }, { "cell_type": "markdown", - "id": "94414ad1", + "id": "7ccf56c7", "metadata": { "editable": true }, @@ -6398,7 +6106,7 @@ }, { "cell_type": "markdown", - "id": "cbb571a8", + "id": "41939010", "metadata": { "editable": true }, @@ -6410,7 +6118,7 @@ }, { "cell_type": "markdown", - "id": "08d69de8", + "id": "93d38078", "metadata": { "editable": true }, @@ -6420,7 +6128,7 @@ }, { "cell_type": "markdown", - "id": "17827d0b", + "id": "9c6d063a", "metadata": { "editable": true }, @@ -6433,7 +6141,7 @@ }, { "cell_type": "markdown", - "id": "a2606f59", + "id": "90d9a525", "metadata": { "editable": true }, @@ -6445,7 +6153,7 @@ }, { "cell_type": "markdown", - "id": "1a261469", + "id": "d1c9d3ea", "metadata": { "editable": true }, @@ -6457,7 +6165,7 @@ }, { "cell_type": "markdown", - "id": "2c25d0ff", + "id": "6a03fd03", "metadata": { "editable": true }, @@ -6469,7 +6177,7 @@ }, { "cell_type": "markdown", - "id": "1cbbda83", + "id": "12f9e2f4", "metadata": { "editable": true }, @@ -6481,7 +6189,7 @@ }, { "cell_type": "markdown", - "id": "10e5cd79", + "id": "0bd449c0", "metadata": { "editable": true }, @@ -6495,7 +6203,7 @@ }, { "cell_type": "markdown", - "id": "8149c527", + "id": "528f4c54", "metadata": { "editable": true }, @@ -6507,7 +6215,7 @@ }, { "cell_type": "markdown", - "id": "86370c66", + "id": "a4e89b45", "metadata": { "editable": true }, @@ -6517,7 +6225,7 @@ }, { "cell_type": "markdown", - "id": "ca970c01", + "id": "af51b23c", "metadata": { "editable": true }, @@ -6529,7 +6237,7 @@ }, { "cell_type": "markdown", - "id": "0a6651d6", + "id": "26945717", "metadata": { "editable": true }, @@ -6541,7 +6249,7 @@ }, { "cell_type": "markdown", - "id": "feb46caa", + "id": "70a85186", "metadata": { "editable": true }, @@ -6553,7 +6261,7 @@ }, { "cell_type": "markdown", - "id": "ba2ccc4c", + "id": "86de1af1", "metadata": { "editable": true }, @@ -6565,7 +6273,7 @@ }, { "cell_type": "markdown", - "id": "99bd5e5f", + "id": "a7eaaac6", "metadata": { "editable": true }, @@ -6577,7 +6285,7 @@ }, { "cell_type": "markdown", - "id": "122ac3fa", + "id": "732d4020", "metadata": { "editable": true }, @@ -6596,7 +6304,7 @@ }, { "cell_type": "markdown", - "id": "2ed2f1af", + "id": "06f71f9c", "metadata": { "editable": true }, @@ -6608,7 +6316,7 @@ }, { "cell_type": "markdown", - "id": "ab6d373f", + "id": "04266404", "metadata": { "editable": true }, @@ -6618,7 +6326,7 @@ }, { "cell_type": "markdown", - "id": "12e89aa0", + "id": "753d4bf0", "metadata": { "editable": true }, @@ -6630,7 +6338,7 @@ }, { "cell_type": "markdown", - "id": "f5ad1a22", + "id": "ea8b1f8f", "metadata": { "editable": true }, @@ -6640,7 +6348,7 @@ }, { "cell_type": "markdown", - "id": "972a591b", + "id": "12703a7e", "metadata": { "editable": true }, @@ -6652,7 +6360,7 @@ }, { "cell_type": "markdown", - "id": "29b0a40c", + "id": "90522189", "metadata": { "editable": true }, @@ -6664,7 +6372,7 @@ }, { "cell_type": "markdown", - "id": "974b89b6", + "id": "b81abc7b", "metadata": { "editable": true }, @@ -6680,7 +6388,7 @@ }, { "cell_type": "markdown", - "id": "d32b5a75", + "id": "115018b1", "metadata": { "editable": true }, @@ -6692,7 +6400,7 @@ }, { "cell_type": "markdown", - "id": "b7b0e4a9", + "id": "8741b7a9", "metadata": { "editable": true }, @@ -6704,7 +6412,7 @@ }, { "cell_type": "markdown", - "id": "00480506", + "id": "5fe75d98", "metadata": { "editable": true }, @@ -6714,7 +6422,7 @@ }, { "cell_type": "markdown", - "id": "e478d349", + "id": "522e6278", "metadata": { "editable": true }, @@ -6726,7 +6434,7 @@ }, { "cell_type": "markdown", - "id": "9941badc", + "id": "eaa39cca", "metadata": { "editable": true }, @@ -6736,7 +6444,7 @@ }, { "cell_type": "markdown", - "id": "d78d129f", + "id": "230a8059", "metadata": { "editable": true }, @@ -6748,7 +6456,7 @@ }, { "cell_type": "markdown", - "id": "81e43d35", + "id": "698a93f7", "metadata": { "editable": true }, @@ -6765,7 +6473,7 @@ }, { "cell_type": "markdown", - "id": "ab030d9f", + "id": "96e49fbc", "metadata": { "editable": true }, @@ -6777,7 +6485,7 @@ }, { "cell_type": "markdown", - "id": "5c1a039a", + "id": "f2043d81", "metadata": { "editable": true }, @@ -6789,7 +6497,7 @@ }, { "cell_type": "markdown", - "id": "64005abb", + "id": "f2dd8e44", "metadata": { "editable": true }, @@ -6799,7 +6507,7 @@ }, { "cell_type": "markdown", - "id": "dd03458c", + "id": "0ab90bb2", "metadata": { "editable": true }, @@ -6811,7 +6519,7 @@ }, { "cell_type": "markdown", - "id": "c1845e9a", + "id": "1090467c", "metadata": { "editable": true }, @@ -6821,7 +6529,7 @@ }, { "cell_type": "markdown", - "id": "9daa3df6", + "id": "8bc71963", "metadata": { "editable": true }, @@ -6833,7 +6541,7 @@ }, { "cell_type": "markdown", - "id": "add636f0", + "id": "918da4ad", "metadata": { "editable": true }, @@ -6843,7 +6551,7 @@ }, { "cell_type": "markdown", - "id": "79c36fde", + "id": "ee673e3d", "metadata": { "editable": true }, @@ -6855,7 +6563,7 @@ }, { "cell_type": "markdown", - "id": "d4b4abb2", + "id": "03352030", "metadata": { "editable": true }, @@ -6865,7 +6573,7 @@ }, { "cell_type": "markdown", - "id": "93a6f35c", + "id": "1b29a63e", "metadata": { "editable": true }, @@ -6877,7 +6585,7 @@ }, { "cell_type": "markdown", - "id": "62647fc5", + "id": "206bcec2", "metadata": { "editable": true }, @@ -6897,7 +6605,7 @@ "name": "python", "nbconvert_exporter": "python", "pygments_lexer": "ipython3", - "version": "3.9.10" + "version": "3.9.18" } }, "nbformat": 4, diff --git a/doc/LectureNotes/_build/jupyter_execute/week35.py b/doc/LectureNotes/_build/jupyter_execute/week35.py index 06bfeb41a..b962e32d6 100644 --- a/doc/LectureNotes/_build/jupyter_execute/week35.py +++ b/doc/LectureNotes/_build/jupyter_execute/week35.py @@ -8,7 +8,7 @@ # # Week 35: From Ordinary Linear Regression to Ridge and Lasso Regression # **Morten Hjorth-Jensen**, Department of Physics, University of Oslo and Department of Physics and Astronomy and National Superconducting Cyclotron Laboratory, Michigan State University # -# Date: **August 28-September 1** +# Date: **August 26-30** # ## Plans for week 35 # @@ -20,21 +20,15 @@ # # 3. Discussion on how to prepare data and examples of applications of linear regression # -# 4. Material for the lecture on Thursday: Mathematical interpretations of linear regression +# 4. Material for the lecture on Monday: Mathematical interpretations of linear regression # -# 5. Thursday: Ridge and Lasso regression and Singular Value Decomposition -# -# 6. [Video of lecture](https://youtu.be/qBNm-HGSxL4) -# -# 7. [Whiteboard notes](https://github.com/CompPhysics/MachineLearning/blob/master/doc/HandWrittenNotes/2023/NotesAug31.pdf) +# 5. Monday: Ridge and Lasso regression and Singular Value Decomposition # ### Reading recommendations: # # 1. See lecture notes for week 35 at # # 2. Goodfellow, Bengio and Courville, Deep Learning, chapter 2 on linear algebra and sections 3.1-3.10 on elements of statistics (background) -# -# 3. Hastie, Tibshirani and Friedman, The elements of statistical learning, sections 3.1-3.4 (on relevance for the discussion of linear regression). # ## Why Linear Regression (aka Ordinary Least Squares and family), repeat from last week # diff --git a/doc/LectureNotes/_build/jupyter_execute/week35_146_0.png b/doc/LectureNotes/_build/jupyter_execute/week35_146_0.png index 02d1feef089f04c92b20e3b868327097f2491900..7ef2784f5b4c18c17c0c40d386bd0a3446bf0550 100644 GIT binary patch delta 45 zcmdn7i*d&;#tCi;7J3Fc3K=CO1;tkS`nicE1v&X8Ihjd%`9\n", + "" + ] + }, + { + "cell_type": "markdown", + "id": "919216dd", + "metadata": { + "editable": true + }, + "source": [ + "# Week 34: Introduction to the course, Logistics and Practicalities\n", + "**Morten Hjorth-Jensen**, Department of Physics and Center for Computing in Science Education, University of Oslo, Norway and Department of Physics and Astronomy and Facility for Rare Isotope Beams, Michigan State University, USA\n", + "\n", + "Date: **Week 34, August 19-23, 2024**" + ] + }, + { + "cell_type": "markdown", + "id": "d990119b", + "metadata": { + "editable": true + }, + "source": [ + "## Overview of first week\n", + "\n", + "1. The sessions on Tuesdays and Wednesdays last four hours for each group (four groups in total) and will include lectures in a flipped mode (promoting active learning) and work on exercices and projects.\n", + "\n", + "2. The sessions will begin with lectures, discussions, questions and answers about the material to be covered every week. Videos and teaching material will be announced in due time.\n", + "\n", + "3. There are four groups:\n", + "\n", + " * Tuesdays 815am-12pm and 1215pm-4pm\n", + "\n", + " * Wednesdays 815am-12pm and 1215pm-4pm.\n", + "\n", + "4. On Mondays we have a regular lecture which will be organized as a mix of active learning sessions and regular lectures. These lectures/active learning sessions start at 1015am and end at 12pm and serve the aims of giving an overview over various topics as well as solving specific problems. These lectures will also be recorded.\n", + "\n", + " * [Link to recording of lecture TBA](https://youtu.be/)\n", + "\n", + "The labs are also available till 6pm Tuesdays and Wednesdays. Videos and learning material with reading suggestions will be made available before each week starts." + ] + }, + { + "cell_type": "markdown", + "id": "12fb6433", + "metadata": { + "editable": true + }, + "source": [ + "## Schedule first week\n", + "\n", + " * August 19: Lecture: Presentation of course, Linear regression, examples and theory \n", + "\n", + " * August 20: Introduction to software and repetition of Python Programming, linear algebra and basic elements of statistics. Please select group.\n", + "\n", + " * August 23: Introduction to software and repetition of Python Programming, linear algebra and basic elements of statistics. Please select group." + ] + }, + { + "cell_type": "markdown", + "id": "fc7733d1", + "metadata": { + "editable": true + }, + "source": [ + "## Lectures and ComputerLab\n", + "\n", + " * Mondays: regular lectures/active learning sessions (10.15am-12pm) \n", + "\n", + " * The sessions on Tuesdays and Wednesdays last four hours and will include partly lectures and discussions in the beginning.\n", + "\n", + " * Weekly reading assignments and videos needed to solve projects and exercises.\n", + "\n", + " * Weekly exercises. You can hand in exercises if you want and get an extra score, see below.\n", + "\n", + " * Detailed lecture notes, exercises, all programs presented, projects etc can be found at the homepage of the course.\n", + "\n", + " * Weekly plans and all other information are on the official website. This info will also be conveyed via weekly emails.\n", + "\n", + " * No final exam, three projects that are graded and have to be approved." + ] + }, + { + "cell_type": "markdown", + "id": "7b62d5a2", + "metadata": { + "editable": true + }, + "source": [ + "## Communication channels\n", + "\n", + "* Communications (email and more) via \n", + "\n", + "* **Discord** channel at " + ] + }, + { + "cell_type": "markdown", + "id": "6b3a4a81", + "metadata": { + "editable": true + }, + "source": [ + "## Course Format\n", + "\n", + " * Three compulsory projects. Electronic reports only using [Canvas](https://www.uio.no/english/services/it/education/canvas/) to hand in projects and [git](https://git-scm.com/) as version control software and [GitHub](https://github.com/) for repository (or [GitLab](https://about.gitlab.com/)) of all your material.\n", + "\n", + " * Evaluation and grading: The three projects are graded and each counts 1/3 of the final mark. No final written or oral exam.\n", + "\n", + "a. For the last project each group/participant submits a proposal or works with suggested (by us) proposals for the project.\n", + "\n", + "b. If possible, we would like to organize the last project as a workshop where each group presents this to all other participants of the course\n", + "\n", + "c. Based on feedback etc, each group finalizes the report and submits for grading. \n", + "\n", + " * Python is the default programming language, but feel free to use C/C++, Julia and/or Fortran or other programming languages. All source codes discussed during the lectures can be found at the webpage and [github address](https://github.com/CompPhysics/MachineLearning/tree/master/doc/Programs) of the course." + ] + }, + { + "cell_type": "markdown", + "id": "afc67709", + "metadata": { + "editable": true + }, + "source": [ + "## Teachers\n", + "\n", + "* Morten Hjorth-Jensen, morten.hjorth-jensen@fys.uio.no\n", + "\n", + " * **Phone**: +47-48257387\n", + "\n", + " * **Office**: Department of Physics, University of Oslo, Eastern wing, room FØ470 \n", + "\n", + " * **Office hours**: *Anytime*! Individual or group office hours can be arranged either in person or via zoom. Feel free to send an email for planning. \n", + "\n", + "* Ida Torkjellsdatter Storehaug, i.t.storehaug@fys.uio.no\n", + "\n", + "* Fahimeh Najafi, fahimeh.najafi@fys.uio.no\n", + "\n", + "* Mia-Katrin Ose Kvalsund, m.k.o.kvalsund@fys.uio.no\n", + "\n", + "* Karl Henrik Fredly, k.h.fredly@fys.uio.no\n", + "\n", + "* Sigurd k. Huse, s.k.huse@fys.uio.no\n", + "\n", + "* Odin Johansen, odin.johansen@fys.uio.no" + ] + }, + { + "cell_type": "markdown", + "id": "bbd60b9c", + "metadata": { + "editable": true + }, + "source": [ + "## Deadlines for projects (tentative)\n", + "\n", + "1. Project 1: October 7 (available September 2) graded with feedback)\n", + "\n", + "2. Project 2: November 4 (available October 8, graded with feedback)\n", + "\n", + "3. Project 3: December 9 (available November 5, graded with feedback)\n", + "\n", + "Extra Credit (not mandatory), weekly exercise assignments, 10 in total (due Friday same week), 10% additional score. The extra credit assignments are due each Sunday and can be uploaed to **Canvas** in your preferred format (although we prefer jupyter-notebooks). First assignment is for week 35. Each weekly exercise set counts 1%." + ] + }, + { + "cell_type": "markdown", + "id": "5c4e0b8c", + "metadata": { + "editable": true + }, + "source": [ + "## Grading\n", + "\n", + "Grades are awarded on a scale from A to F, where A is the best grade and F is a fail. There are three projects which are graded and each project counts 1/3 of the final grade. The total score is thus the average from all three projects.\n", + "\n", + "The final number of points is based on the average of all projects and the grade follows the following table:\n", + "\n", + " * 92-100 points: A\n", + "\n", + " * 77-91 points: B\n", + "\n", + " * 58-76 points: C\n", + "\n", + " * 46-57 points: D\n", + "\n", + " * 40-45 points: E\n", + "\n", + " * 0-39 points: F-failed\n", + "\n", + "In addition you can get an extra 10% score for weekly assignments (10 in total and due each Friday). Each weekly assignment counts 1%." + ] + }, + { + "cell_type": "markdown", + "id": "cabba75a", + "metadata": { + "editable": true + }, + "source": [ + "## Reading material\n", + "\n", + "The lecture notes are collected as a jupyter-book at .\n", + "The lecture notes can also be retrieved as a standard PDF file at .\n", + "\n", + "In addition to the lecture notes, we recommend the books of Rasckha et\n", + "al and Goodfellow et al. We will follow these texts closely and the\n", + "weekly reading assignments refer to these texts. The text by Hastie et\n", + "al is also widely used in the Machine Learning community. See next slide for link to textbooks." + ] + }, + { + "cell_type": "markdown", + "id": "2240bbaf", + "metadata": { + "editable": true + }, + "source": [ + "## Main textbooks\n", + "\n", + "* Goodfellow, Bengio, and Courville (GBC), Deep Learning \n", + "\n", + "* Sebastian Raschka, Yuxi Lie, and Vahid Mirjalili (RLM), Machine Learning with PyTorch and Scikit-Learn at , see also \n", + "\n", + "The weekly reading suggestions are all from these two texts. The text by GBC can be accessed chapter by chapter from the abovementioned URL.\n", + "Each chapter of RLM gives access to the pertinent notebooks. These notebooks are highly recommended." + ] + }, + { + "cell_type": "markdown", + "id": "e11266d3", + "metadata": { + "editable": true + }, + "source": [ + "## Other popular texts\n", + "\n", + "**Other texts.**\n", + "\n", + "* Christopher M. Bishop (CB), Pattern Recognition and Machine Learning\n", + "\n", + "* [Hastie, Tibshirani, and Friedman (HTF), The Elements of Statistical Learning, Springer](https://www.springer.com/gp/book/9780387848570).\n", + "\n", + "* [Aurelien Geron (AG), Hands‑On Machine Learning with Scikit‑Learn and TensorFlow, O'Reilly](https://www.oreilly.com/library/view/hands-on-machine-learning/9781492032632/). This text is very useful since it contains many code examples and hands-on applications of all algorithms discussed in this course.\n", + "\n", + "* [Kevin Murphy (KM), Probabilistic Machine Learning, an Introduction](https://probml.github.io/pml-book/book1.html)\n", + "\n", + "* David Foster (DF), Generative Deep Learning, \n", + "\n", + "* Babcock and Gavras (BG), Generative AI with Python and TensorFlow, " + ] + }, + { + "cell_type": "markdown", + "id": "2f254181", + "metadata": { + "editable": true + }, + "source": [ + "## Reading suggestions week 34\n", + "\n", + "This week: Refresh linear algebra, GBC chapter 2. Install scikit-learn. See lecture notes for week 34 at (these notes)." + ] + }, + { + "cell_type": "markdown", + "id": "a482f843", + "metadata": { + "editable": true + }, + "source": [ + "## Prerequisites\n", + "\n", + "Basic knowledge in programming and mathematics, with an emphasis on\n", + "linear algebra. Knowledge of Python or/and C++ as programming\n", + "languages is strongly recommended and experience with Jupiter notebook\n", + "is recommended. Required courses are the equivalents to the University\n", + "of Oslo mathematics courses MAT1100, MAT1110, MAT1120 and at least one\n", + "of the corresponding computing and programming courses INF1000/INF1110\n", + "or MAT-INF1100/MAT-INF1100L/BIOS1100/KJM-INF1100. Most universities\n", + "offer nowadays a basic programming course (often compulsory) where\n", + "Python is the recurring programming language." + ] + }, + { + "cell_type": "markdown", + "id": "1bfd35e8", + "metadata": { + "editable": true + }, + "source": [ + "## Topics covered in this course: Statistical analysis and optimization of data\n", + "\n", + "The course has two central parts\n", + "\n", + "1. Statistical analysis and optimization of data\n", + "\n", + "2. Machine learning\n", + "\n", + "These topics will be scattered thorughout the course and may not necessarily be taught separately. Rather, we will often take an approach (during the lectures and project/exercise sessions) where say elements from statistical data analysis are mixed with specific Machine Learning algorithms." + ] + }, + { + "cell_type": "markdown", + "id": "d28f3b65", + "metadata": { + "editable": true + }, + "source": [ + "## Statistical analysis and optimization of data\n", + "\n", + "We plan to cover the following topics:\n", + "* Basic concepts, expectation values, variance, covariance, correlation functions and errors;\n", + "\n", + "* Simpler models, binomial distribution, the Poisson distribution, simple and multivariate normal distributions;\n", + "\n", + "* Central elements of Bayesian statistics and modeling;\n", + "\n", + "* Gradient methods for data optimization;\n", + "\n", + "* Monte Carlo methods, Markov chains, Gibbs sampling and Metropolis-Hastings sampling (tentative);\n", + "\n", + "* Estimation of errors and resampling techniques such as the cross-validation, blocking, bootstrapping and jackknife methods;\n", + "\n", + "* Principal Component Analysis (PCA) and its mathematical foundation;" + ] + }, + { + "cell_type": "markdown", + "id": "1dd7eba4", + "metadata": { + "editable": true + }, + "source": [ + "## Machine Learning\n", + "\n", + "* Pre deep-learning revolution (2008 approx)\n", + "\n", + " * Linear Regression and Logistic Regression, classification and regression problems;\n", + "\n", + " * Bayesian linear and logistic regression, kernel regression;\n", + "\n", + " * Decisions trees, Random Forests, Bagging and Boosting methods;\n", + "\n", + " * Support vector machines (only survey);\n", + "\n", + " * Unsupervised learning and dimensionality reduction, from PCA to clustering;" + ] + }, + { + "cell_type": "markdown", + "id": "f65d481e", + "metadata": { + "editable": true + }, + "source": [ + "## Deep learning methods\n", + "\n", + "* Deep learning \n", + "\n", + " * Neural networks and deep learning;\n", + "\n", + " * Convolutional neural networks;\n", + "\n", + " * Recurrent neural networks;\n", + "\n", + " * Autoencoders\n", + "\n", + " * Generative methods with an emphasis on Boltzmann Machines, Variational Autoencoders and Generalized Adversarial Networks(covered by FYS5429);\n", + "\n", + "Hands-on demonstrations, exercises and projects aim at deepening your understanding of these topics." + ] + }, + { + "cell_type": "markdown", + "id": "860d45f1", + "metadata": { + "editable": true + }, + "source": [ + "## Extremely useful tools, strongly recommended\n", + "\n", + "**and discussed at the lab sessions.**\n", + "\n", + " * GIT for version control, and GitHub or GitLab as repositories, highly recommended. This will be discussed during the first exercise session\n", + "\n", + " * Anaconda and other Python environments, see intro slides and links to programming resources at " + ] + }, + { + "cell_type": "markdown", + "id": "8643a8e4", + "metadata": { + "editable": true + }, + "source": [ + "## Other courses on Data science and Machine Learning at UiO\n", + "\n", + "* [FYS5419 Quantum Computing and Quantum Machine Learning](https://www.uio.no/studier/emner/matnat/fys/FYS5419/index-eng.html)\n", + "\n", + "* [FYS5429 Advanced Machine Learning for the Physical Sciences](https://www.uio.no/studier/emner/matnat/fys/FYS5429/index-eng.html)\n", + "\n", + "* [STK2100 Machine learning and statistical methods for prediction and classification](http://www.uio.no/studier/emner/matnat/math/STK2100/index-eng.html). \n", + "\n", + "* [IN3050/4050 Introduction to Artificial Intelligence and Machine Learning](https://www.uio.no/studier/emner/matnat/ifi/IN3050/index-eng.html). Introductory course in machine learning and AI with an algorithmic approach. \n", + "\n", + "* [STK-INF3000/4000 Selected Topics in Data Science](http://www.uio.no/studier/emner/matnat/math/STK-INF3000/index-eng.html). The course provides insight into selected contemporary relevant topics within Data Science. \n", + "\n", + "* [IN4080 Natural Language Processing](https://www.uio.no/studier/emner/matnat/ifi/IN4080/index.html). Probabilistic and machine learning techniques applied to natural language processing." + ] + }, + { + "cell_type": "markdown", + "id": "883a32ab", + "metadata": { + "editable": true + }, + "source": [ + "## Other courses on Data science and Machine Learning at UiO, contn\n", + "\n", + "* [STK-IN4300 Statistical learning methods in Data Science](https://www.uio.no/studier/emner/matnat/math/STK-IN4300/index-eng.html). An advanced introduction to statistical and machine learning. For students with a good mathematics and statistics background.\n", + "\n", + "* [IN3310/4310 Deep Learnig for Image Analysis](https://www.uio.no/studier/emner/matnat/ifi/IN4310/index.html)\n", + "\n", + "* [STK4051 Computational Statistics](https://www.uio.no/studier/emner/matnat/math/STK4051/index-eng.html)\n", + "\n", + "* [STK4021 Applied Bayesian Analysis and Numerical Methods](https://www.uio.no/studier/emner/matnat/math/STK4021/index-eng.html)" + ] + }, + { + "cell_type": "markdown", + "id": "c36dca74", + "metadata": { + "editable": true + }, + "source": [ + "## Learning outcomes\n", + "\n", + "* Learn about basic data analysis, statistical analysis, Bayesian statistics, Monte Carlo sampling, data optimization and machine learning;\n", + "\n", + "* Be capable of extending the acquired knowledge to other systems and cases;\n", + "\n", + "* Have an understanding of central algorithms used in data analysis and machine learning;\n", + "\n", + "* Understand linear methods for regression and classification, from ordinary least squares, via Lasso and Ridge to Logistic regression;\n", + "\n", + "* Learn about neural networks and deep learning methods for supervised and unsupervised learning. Emphasis on feed forward neural networks, convolutional and recurrent neural networks; \n", + "\n", + "* Learn about about decision trees, random forests, bagging and boosting methods;\n", + "\n", + "* Learn about support vector machines and kernel transformations;\n", + "\n", + "* Reduction of data sets, from PCA to clustering;\n", + "\n", + "* Generative models\n", + "\n", + "* Work on numerical projects to illustrate the theory. The projects play a central role and you are expected to know modern programming languages like Python or C++ and/or Fortran (Fortran2003 or later) or Julia or other." + ] + }, + { + "cell_type": "markdown", + "id": "3331f004", + "metadata": { + "editable": true + }, + "source": [ + "## Types of Machine Learning\n", + "\n", + "The approaches to machine learning are many, but are often split into\n", + "two main categories. In *supervised learning* we know the answer to a\n", + "problem, and let the computer deduce the logic behind it. On the other\n", + "hand, *unsupervised learning* is a method for finding patterns and\n", + "relationship in data sets without any prior knowledge of the system.\n", + "Some authours also operate with a third category, namely\n", + "*reinforcement learning*. This is a paradigm of learning inspired by\n", + "behavioral psychology, where learning is achieved by trial-and-error,\n", + "solely from rewards and punishment.\n", + "\n", + "Another way to categorize machine learning tasks is to consider the\n", + "desired output of a system. Some of the most common tasks are:\n", + "\n", + " * Classification: Outputs are divided into two or more classes. The goal is to produce a model that assigns inputs into one of these classes. An example is to identify digits based on pictures of hand-written ones. Classification is typically supervised learning.\n", + "\n", + " * Regression: Finding a functional relationship between an input data set and a reference data set. The goal is to construct a function that maps input data to continuous output values.\n", + "\n", + " * Clustering: Data are divided into groups with certain common traits, without knowing the different groups beforehand. It is thus a form of unsupervised learning." + ] + }, + { + "cell_type": "markdown", + "id": "9805129a", + "metadata": { + "editable": true + }, + "source": [ + "## Essential elements of ML\n", + "\n", + "The methods we cover have three main topics in common, irrespective of\n", + "whether we deal with supervised or unsupervised learning.\n", + "* The first ingredient is normally our data set (which can be subdivided into training, validation and test data). Many find the most difficult part of using Machine Learning to be the set up of your data in a meaningful way. \n", + "\n", + "* The second item is a model which is normally a function of some parameters. The model reflects our knowledge of the system (or lack thereof). As an example, if we know that our data show a behavior similar to what would be predicted by a polynomial, fitting our data to a polynomial of some degree would then determin our model. \n", + "\n", + "* The last ingredient is a so-called **cost/loss** function (or error or risk function) which allows us to present an estimate on how good our model is in reproducing the data it is supposed to train." + ] + }, + { + "cell_type": "markdown", + "id": "b6ce1fec", + "metadata": { + "editable": true + }, + "source": [ + "## An optimization/minimization problem\n", + "\n", + "At the heart of basically all Machine Learning algorithms we will encounter so-called minimization or optimization algorithms. A large family of such methods are so-called **gradient methods**." + ] + }, + { + "cell_type": "markdown", + "id": "c3f855e6", + "metadata": { + "editable": true + }, + "source": [ + "## A Frequentist approach to data analysis\n", + "\n", + "When you hear phrases like **predictions and estimations** and\n", + "**correlations and causations**, what do you think of? May be you think\n", + "of the difference between classifying new data points and generating\n", + "new data points.\n", + "Or perhaps you consider that correlations represent some kind of symmetric statements like\n", + "if $A$ is correlated with $B$, then $B$ is correlated with\n", + "$A$. Causation on the other hand is directional, that is if $A$ causes $B$, $B$ does not\n", + "necessarily cause $A$.\n", + "\n", + "These concepts are in some sense the difference between machine\n", + "learning and statistics. In machine learning and prediction based\n", + "tasks, we are often interested in developing algorithms that are\n", + "capable of learning patterns from given data in an automated fashion,\n", + "and then using these learned patterns to make predictions or\n", + "assessments of newly given data. In many cases, our primary concern\n", + "is the quality of the predictions or assessments, and we are less\n", + "concerned about the underlying patterns that were learned in order\n", + "to make these predictions.\n", + "\n", + "In machine learning we normally use [a so-called frequentist approach](https://en.wikipedia.org/wiki/Frequentist_inference),\n", + "where the aim is to make predictions and find correlations. We focus\n", + "less on for example extracting a probability distribution function (PDF). The PDF can be\n", + "used in turn to make estimations and find causations such as given $A$\n", + "what is the likelihood of finding $B$." + ] + }, + { + "cell_type": "markdown", + "id": "db7df58f", + "metadata": { + "editable": true + }, + "source": [ + "## What is a good model?\n", + "\n", + "In science and engineering we often end up in situations where we want to infer (or learn) a\n", + "quantitative model $M$ for a given set of sample points $\\boldsymbol{X} \\in [x_1, x_2,\\dots x_N]$.\n", + "\n", + "As we will see repeatedely in these lectures, we could try to fit these data points to a model given by a\n", + "straight line, or if we wish to be more sophisticated to a more complex\n", + "function.\n", + "\n", + "The reason for inferring such a model is that it\n", + "serves many useful purposes. On the one hand, the model can reveal information\n", + "encoded in the data or underlying mechanisms from which the data were generated. For instance, we could discover important\n", + "corelations that relate interesting physics interpretations.\n", + "\n", + "In addition, it can simplify the representation of the given data set and help\n", + "us in making predictions about future data samples.\n", + "\n", + "A first important consideration to keep in mind is that inferring the *correct* model\n", + "for a given data set is an elusive, if not impossible, task. The fundamental difficulty\n", + "is that if we are not specific about what we mean by a *correct* model, there\n", + "could easily be many different models that fit the given data set *equally well*." + ] + }, + { + "cell_type": "markdown", + "id": "eae43d45", + "metadata": { + "editable": true + }, + "source": [ + "## What is a good model? Can we define it?\n", + "\n", + "The central question is this: what leads us to say that a model is correct or\n", + "optimal for a given data set? To make the model inference problem well posed, i.e.,\n", + "to guarantee that there is a unique optimal model for the given data, we need to\n", + "impose additional assumptions or restrictions on the class of models considered. To\n", + "this end, we should not be looking for just any model that can describe the data.\n", + "Instead, we should look for a **model** $M$ that is the best among a restricted class\n", + "of models. In addition, to make the model inference problem computationally\n", + "tractable, we need to specify how restricted the class of models needs to be. A\n", + "common strategy is to start \n", + "with the simplest possible class of models that is just necessary to describe the data\n", + "or solve the problem at hand. More precisely, the model class should be rich enough\n", + "to contain at least one model that can fit the data to a desired accuracy and yet be\n", + "restricted enough that it is relatively simple to find the best model for the given data.\n", + "\n", + "Thus, the most popular strategy is to start from the\n", + "simplest class of models and increase the complexity of the models only when the\n", + "simpler models become inadequate. For instance, if we work with a regression problem to fit a set of sample points, one\n", + "may first try the simplest class of models, namely linear models, followed obviously by more complex models.\n", + "\n", + "How to evaluate which model fits best the data is something we will come back to over and over again in these sets of lectures." + ] + }, + { + "cell_type": "markdown", + "id": "a14136b8", + "metadata": { + "editable": true + }, + "source": [ + "## Software and needed installations\n", + "\n", + "We will make extensive use of Python as programming language and its\n", + "myriad of available libraries. You will find\n", + "Jupyter notebooks invaluable in your work. You can run **R**\n", + "codes in the Jupyter/IPython notebooks, with the immediate benefit of\n", + "visualizing your data. You can also use compiled languages like C++,\n", + "Rust, Julia, Fortran etc if you prefer. The focus in these lectures will be\n", + "on Python.\n", + "\n", + "If you have Python installed (we strongly recommend Python3) and you feel\n", + "pretty familiar with installing different packages, we recommend that\n", + "you install the following Python packages via **pip** as \n", + "\n", + "1. pip install numpy scipy matplotlib ipython scikit-learn mglearn sympy pandas pillow \n", + "\n", + "For Python3, replace **pip** with **pip3**.\n", + "\n", + "For OSX users we recommend, after having installed Xcode, to\n", + "install **brew**. Brew allows for a seamless installation of additional\n", + "software via for example \n", + "\n", + "1. brew install python3\n", + "\n", + "For Linux users, with its variety of distributions like for example the widely popular Ubuntu distribution,\n", + "you can use **pip** as well and simply install Python as \n", + "\n", + "1. sudo apt-get install python3 (or python for pyhton2.7)\n", + "\n", + "etc etc." + ] + }, + { + "cell_type": "markdown", + "id": "43ad2d3a", + "metadata": { + "editable": true + }, + "source": [ + "## Python installers\n", + "\n", + "If you don't want to perform these operations separately and venture\n", + "into the hassle of exploring how to set up dependencies and paths, we\n", + "recommend two widely used distrubutions which set up all relevant\n", + "dependencies for Python, namely \n", + "\n", + "* [Anaconda](https://docs.anaconda.com/), \n", + "\n", + "which is an open source\n", + "distribution of the Python and R programming languages for large-scale\n", + "data processing, predictive analytics, and scientific computing, that\n", + "aims to simplify package management and deployment. Package versions\n", + "are managed by the package management system **conda**. \n", + "\n", + "* [Enthought canopy](https://www.enthought.com/product/canopy/) \n", + "\n", + "is a Python\n", + "distribution for scientific and analytic computing distribution and\n", + "analysis environment, available for free and under a commercial\n", + "license.\n", + "\n", + "Furthermore, [Google's Colab](https://colab.research.google.com/notebooks/welcome.ipynb) is a free Jupyter notebook environment that requires \n", + "no setup and runs entirely in the cloud. Try it out!" + ] + }, + { + "cell_type": "markdown", + "id": "260fc4f1", + "metadata": { + "editable": true + }, + "source": [ + "## Useful Python libraries\n", + "Here we list several useful Python libraries we strongly recommend (if you use anaconda many of these are already there)\n", + "\n", + "* [NumPy](https://www.numpy.org/) is a highly popular library for large, multi-dimensional arrays and matrices, along with a large collection of high-level mathematical functions to operate on these arrays\n", + "\n", + "* [The pandas](https://pandas.pydata.org/) library provides high-performance, easy-to-use data structures and data analysis tools \n", + "\n", + "* [Xarray](http://xarray.pydata.org/en/stable/) is a Python package that makes working with labelled multi-dimensional arrays simple, efficient, and fun!\n", + "\n", + "* [Scipy](https://www.scipy.org/) (pronounced “Sigh Pie”) is a Python-based ecosystem of open-source software for mathematics, science, and engineering. \n", + "\n", + "* [Matplotlib](https://matplotlib.org/) is a Python 2D plotting library which produces publication quality figures in a variety of hardcopy formats and interactive environments across platforms.\n", + "\n", + "* [Autograd](https://github.com/HIPS/autograd) can automatically differentiate native Python and Numpy code. It can handle a large subset of Python's features, including loops, ifs, recursion and closures, and it can even take derivatives of derivatives of derivatives\n", + "\n", + "* [JAX](https://jax.readthedocs.io/en/latest/index.html) has now more or less replaced **Autograd**. JAX is Autograd and XLA, brought together for high-performance numerical computing and machine learning research. It provides composable transformations of Python+NumPy programs: differentiate, vectorize, parallelize, Just-In-Time compile to GPU/TPU, and more.\n", + "\n", + "* [SymPy](https://www.sympy.org/en/index.html) is a Python library for symbolic mathematics. \n", + "\n", + "* [scikit-learn](https://scikit-learn.org/stable/) has simple and efficient tools for machine learning, data mining and data analysis\n", + "\n", + "* [TensorFlow](https://www.tensorflow.org/) is a Python library for fast numerical computing created and released by Google\n", + "\n", + "* [Keras](https://keras.io/) is a high-level neural networks API, written in Python and capable of running on top of TensorFlow, CNTK, or Theano\n", + "\n", + "* [Pytorch](https://pytorch.org/), highly recommened\n", + "\n", + "* [Theano](https://pypi.org/project/Theano/) and many other" + ] + }, + { + "cell_type": "markdown", + "id": "d79f5c48", + "metadata": { + "editable": true + }, + "source": [ + "## Installing R, C++, cython or Julia\n", + "\n", + "You will also find it convenient to utilize **R**. We will mainly\n", + "use Python during our lectures and in various projects and exercises.\n", + "Those of you\n", + "already familiar with **R** should feel free to continue using **R**, keeping\n", + "however an eye on the parallel Python set ups. Similarly, if you are a\n", + "Python afecionado, feel free to explore **R** as well. Jupyter(Julia, Python and R) /Ipython\n", + "notebook allows you to run **R** codes and **Julia** codes interactively in your\n", + "browser. The software library **R** is really tailored for statistical data analysis\n", + "and allows for an easy usage of the tools and algorithms we will discuss in these\n", + "lectures.\n", + "\n", + "To install **R** with Jupyter notebook \n", + "[follow the link here](https://mpacer.org/maths/r-kernel-for-ipython-notebook)" + ] + }, + { + "cell_type": "markdown", + "id": "14668766", + "metadata": { + "editable": true + }, + "source": [ + "## Installing R, C++, cython, Numba etc\n", + "\n", + "For the C++ aficionados, Jupyter/IPython notebook allows you also to\n", + "install C++ and run codes written in this language interactively in\n", + "the browser. Since we will emphasize writing many of the algorithms\n", + "yourself, you can thus opt for either Python or C++ (or Fortran or other compiled languages) as programming\n", + "languages.\n", + "\n", + "To add more entropy, **cython** can also be used when running your\n", + "notebooks. It means that Python with the jupyter notebook\n", + "setup allows you to integrate widely popular softwares and tools for\n", + "scientific computing. Similarly, the \n", + "[Numba Python package](https://numba.pydata.org/) delivers increased performance\n", + "capabilities with minimal rewrites of your codes. With its\n", + "versatility, including symbolic operations, Python offers a unique\n", + "computational environment. Your jupyter notebook can easily be\n", + "converted into a nicely rendered **PDF** file or a Latex file for\n", + "further processing. For example, convert to latex as" + ] + }, + { + "cell_type": "markdown", + "id": "158a0a2b", + "metadata": { + "editable": true + }, + "source": [ + " pycod jupyter nbconvert filename.ipynb --to latex \n" + ] + }, + { + "cell_type": "markdown", + "id": "8ff2bfbf", + "metadata": { + "editable": true + }, + "source": [ + "And to add more versatility, the Python package [SymPy](http://www.sympy.org/en/index.html) is a Python library for symbolic mathematics. It aims to become a full-featured computer algebra system (CAS) and is entirely written in Python. \n", + "\n", + "Finally, we recommend strongly using Autograd or JAX for automatic differentiation." + ] + }, + { + "cell_type": "markdown", + "id": "336a64f4", + "metadata": { + "editable": true + }, + "source": [ + "## Numpy examples and Important Matrix and vector handling packages\n", + "\n", + "There are several central software libraries for linear algebra and eigenvalue problems. Several of the more\n", + "popular ones have been wrapped into ofter software packages like those from the widely used text **Numerical Recipes**. The original source codes in many of the available packages are often taken from the widely used\n", + "software package LAPACK, which follows two other popular packages\n", + "developed in the 1970s, namely EISPACK and LINPACK. We describe them shortly here.\n", + "\n", + " * LINPACK: package for linear equations and least square problems.\n", + "\n", + " * LAPACK:package for solving symmetric, unsymmetric and generalized eigenvalue problems. From LAPACK's website it is possible to download for free all source codes from this library. Both C/C++ and Fortran versions are available.\n", + "\n", + " * BLAS (I, II and III): (Basic Linear Algebra Subprograms) are routines that provide standard building blocks for performing basic vector and matrix operations. Blas I is vector operations, II vector-matrix operations and III matrix-matrix operations. Highly parallelized and efficient codes, all available for download from ." + ] + }, + { + "cell_type": "markdown", + "id": "53d76bcf", + "metadata": { + "editable": true + }, + "source": [ + "## Numpy and arrays\n", + "[Numpy](http://www.numpy.org/) provides an easy way to handle arrays in Python. The standard way to import this library is as" + ] + }, + { + "cell_type": "code", + "execution_count": 1, + "id": "c8cbf8e5", + "metadata": { + "collapsed": false, + "editable": true + }, + "outputs": [], + "source": [ + "import numpy as np" + ] + }, + { + "cell_type": "markdown", + "id": "2544ec17", + "metadata": { + "editable": true + }, + "source": [ + "Here follows a simple example where we set up an array of ten elements, all determined by random numbers drawn according to the normal distribution," + ] + }, + { + "cell_type": "code", + "execution_count": 2, + "id": "e6fed93a", + "metadata": { + "collapsed": false, + "editable": true + }, + "outputs": [], + "source": [ + "n = 10\n", + "x = np.random.normal(size=n)\n", + "print(x)" + ] + }, + { + "cell_type": "markdown", + "id": "671ec8e4", + "metadata": { + "editable": true + }, + "source": [ + "We defined a vector $x$ with $n=10$ elements with its values given by the Normal distribution $N(0,1)$.\n", + "Another alternative is to declare a vector as follows" + ] + }, + { + "cell_type": "code", + "execution_count": 3, + "id": "03351553", + "metadata": { + "collapsed": false, + "editable": true + }, + "outputs": [], + "source": [ + "import numpy as np\n", + "x = np.array([1, 2, 3])\n", + "print(x)" + ] + }, + { + "cell_type": "markdown", + "id": "ab7b4a4f", + "metadata": { + "editable": true + }, + "source": [ + "Here we have defined a vector with three elements, with $x_0=1$, $x_1=2$ and $x_2=3$. Note that both Python and C++\n", + "start numbering array elements from $0$ and on. This means that a vector with $n$ elements has a sequence of entities $x_0, x_1, x_2, \\dots, x_{n-1}$. We could also let (recommended) Numpy to compute the logarithms of a specific array as" + ] + }, + { + "cell_type": "code", + "execution_count": 4, + "id": "7d547fee", + "metadata": { + "collapsed": false, + "editable": true + }, + "outputs": [], + "source": [ + "import numpy as np\n", + "x = np.log(np.array([4, 7, 8]))\n", + "print(x)" + ] + }, + { + "cell_type": "markdown", + "id": "fa3d6630", + "metadata": { + "editable": true + }, + "source": [ + "In the last example we used Numpy's unary function $np.log$. This function is\n", + "highly tuned to compute array elements since the code is vectorized\n", + "and does not require looping. We normaly recommend that you use the\n", + "Numpy intrinsic functions instead of the corresponding **log** function\n", + "from Python's **math** module. The looping is done explicitely by the\n", + "**np.log** function. The alternative, and slower way to compute the\n", + "logarithms of a vector would be to write" + ] + }, + { + "cell_type": "code", + "execution_count": 5, + "id": "a1410010", + "metadata": { + "collapsed": false, + "editable": true + }, + "outputs": [], + "source": [ + "import numpy as np\n", + "from math import log\n", + "x = np.array([4, 7, 8])\n", + "for i in range(0, len(x)):\n", + " x[i] = log(x[i])\n", + "print(x)" + ] + }, + { + "cell_type": "markdown", + "id": "1fcdba92", + "metadata": { + "editable": true + }, + "source": [ + "We note that our code is much longer already and we need to import the **log** function from the **math** module. \n", + "The attentive reader will also notice that the output is $[1, 1, 2]$. Python interprets automagically our numbers as integers (like the **automatic** keyword in C++). To change this we could define our array elements to be double precision numbers as" + ] + }, + { + "cell_type": "code", + "execution_count": 6, + "id": "b2baed9c", + "metadata": { + "collapsed": false, + "editable": true + }, + "outputs": [], + "source": [ + "import numpy as np\n", + "x = np.log(np.array([4, 7, 8], dtype = np.float64))\n", + "print(x)" + ] + }, + { + "cell_type": "markdown", + "id": "341fe975", + "metadata": { + "editable": true + }, + "source": [ + "or simply write them as double precision numbers (Python uses 64 bits as default for floating point type variables), that is" + ] + }, + { + "cell_type": "code", + "execution_count": 7, + "id": "4c81d6d8", + "metadata": { + "collapsed": false, + "editable": true + }, + "outputs": [], + "source": [ + "import numpy as np\n", + "x = np.log(np.array([4.0, 7.0, 8.0]))\n", + "print(x)" + ] + }, + { + "cell_type": "markdown", + "id": "b606be11", + "metadata": { + "editable": true + }, + "source": [ + "To check the number of bytes (remember that one byte contains eight bits for double precision variables), you can use simple use the **itemsize** functionality (the array $x$ is actually an object which inherits the functionalities defined in Numpy) as" + ] + }, + { + "cell_type": "code", + "execution_count": 8, + "id": "dc5f484b", + "metadata": { + "collapsed": false, + "editable": true + }, + "outputs": [], + "source": [ + "import numpy as np\n", + "x = np.log(np.array([4.0, 7.0, 8.0]))\n", + "print(x.itemsize)" + ] + }, + { + "cell_type": "markdown", + "id": "2ee4fd88", + "metadata": { + "editable": true + }, + "source": [ + "## Matrices in Python\n", + "\n", + "Having defined vectors, we are now ready to try out matrices. We can\n", + "define a $3 \\times 3 $ real matrix $\\boldsymbol{A}$ as (recall that we user\n", + "lowercase letters for vectors and uppercase letters for matrices)" + ] + }, + { + "cell_type": "code", + "execution_count": 9, + "id": "f54969e9", + "metadata": { + "collapsed": false, + "editable": true + }, + "outputs": [], + "source": [ + "import numpy as np\n", + "A = np.log(np.array([ [4.0, 7.0, 8.0], [3.0, 10.0, 11.0], [4.0, 5.0, 7.0] ]))\n", + "print(A)" + ] + }, + { + "cell_type": "markdown", + "id": "3ffdc5bb", + "metadata": { + "editable": true + }, + "source": [ + "If we use the **shape** function we would get $(3, 3)$ as output, that is verifying that our matrix is a $3\\times 3$ matrix. We can slice the matrix and print for example the first column (Python organized matrix elements in a row-major order, see below) as" + ] + }, + { + "cell_type": "code", + "execution_count": 10, + "id": "c517dc95", + "metadata": { + "collapsed": false, + "editable": true + }, + "outputs": [], + "source": [ + "import numpy as np\n", + "A = np.log(np.array([ [4.0, 7.0, 8.0], [3.0, 10.0, 11.0], [4.0, 5.0, 7.0] ]))\n", + "# print the first column, row-major order and elements start with 0\n", + "print(A[:,0])" + ] + }, + { + "cell_type": "markdown", + "id": "1aced303", + "metadata": { + "editable": true + }, + "source": [ + "We can continue this was by printing out other columns or rows. The example here prints out the second column" + ] + }, + { + "cell_type": "code", + "execution_count": 11, + "id": "32efbfb2", + "metadata": { + "collapsed": false, + "editable": true + }, + "outputs": [], + "source": [ + "import numpy as np\n", + "A = np.log(np.array([ [4.0, 7.0, 8.0], [3.0, 10.0, 11.0], [4.0, 5.0, 7.0] ]))\n", + "# print the first column, row-major order and elements start with 0\n", + "print(A[1,:])" + ] + }, + { + "cell_type": "markdown", + "id": "a95e02fd", + "metadata": { + "editable": true + }, + "source": [ + "Numpy contains many other functionalities that allow us to slice, subdivide etc etc arrays. We strongly recommend that you look up the [Numpy website for more details](http://www.numpy.org/). Useful functions when defining a matrix are the **np.zeros** function which declares a matrix of a given dimension and sets all elements to zero" + ] + }, + { + "cell_type": "code", + "execution_count": 12, + "id": "fcebfe97", + "metadata": { + "collapsed": false, + "editable": true + }, + "outputs": [], + "source": [ + "import numpy as np\n", + "n = 10\n", + "# define a matrix of dimension 10 x 10 and set all elements to zero\n", + "A = np.zeros( (n, n) )\n", + "print(A)" + ] + }, + { + "cell_type": "markdown", + "id": "5d767b5d", + "metadata": { + "editable": true + }, + "source": [ + "or initializing all elements to" + ] + }, + { + "cell_type": "code", + "execution_count": 13, + "id": "8c8edcaf", + "metadata": { + "collapsed": false, + "editable": true + }, + "outputs": [], + "source": [ + "import numpy as np\n", + "n = 10\n", + "# define a matrix of dimension 10 x 10 and set all elements to one\n", + "A = np.ones( (n, n) )\n", + "print(A)" + ] + }, + { + "cell_type": "markdown", + "id": "1365ca9a", + "metadata": { + "editable": true + }, + "source": [ + "or as unitarily distributed random numbers (see the material on random number generators in the statistics part)" + ] + }, + { + "cell_type": "code", + "execution_count": 14, + "id": "85c9a904", + "metadata": { + "collapsed": false, + "editable": true + }, + "outputs": [], + "source": [ + "import numpy as np\n", + "n = 10\n", + "# define a matrix of dimension 10 x 10 and set all elements to random numbers with x \\in [0, 1]\n", + "A = np.random.rand(n, n)\n", + "print(A)" + ] + }, + { + "cell_type": "markdown", + "id": "15700c5c", + "metadata": { + "editable": true + }, + "source": [ + "As we will see throughout these lectures, there are several extremely useful functionalities in Numpy.\n", + "As an example, consider the discussion of the covariance matrix. Suppose we have defined three vectors\n", + "$\\boldsymbol{x}, \\boldsymbol{y}, \\boldsymbol{z}$ with $n$ elements each. The covariance matrix is defined as" + ] + }, + { + "cell_type": "markdown", + "id": "d5d413f6", + "metadata": { + "editable": true + }, + "source": [ + "$$\n", + "\\boldsymbol{\\Sigma} = \\begin{bmatrix} \\sigma_{xx} & \\sigma_{xy} & \\sigma_{xz} \\\\\n", + " \\sigma_{yx} & \\sigma_{yy} & \\sigma_{yz} \\\\\n", + " \\sigma_{zx} & \\sigma_{zy} & \\sigma_{zz} \n", + " \\end{bmatrix},\n", + "$$" + ] + }, + { + "cell_type": "markdown", + "id": "81f680dd", + "metadata": { + "editable": true + }, + "source": [ + "where for example" + ] + }, + { + "cell_type": "markdown", + "id": "17c5a1bf", + "metadata": { + "editable": true + }, + "source": [ + "$$\n", + "\\sigma_{xy} =\\frac{1}{n} \\sum_{i=0}^{n-1}(x_i- \\overline{x})(y_i- \\overline{y}).\n", + "$$" + ] + }, + { + "cell_type": "markdown", + "id": "55a9b83d", + "metadata": { + "editable": true + }, + "source": [ + "The Numpy function **np.cov** calculates the covariance elements using the factor $1/(n-1)$ instead of $1/n$ since it assumes we do not have the exact mean values. \n", + "The following simple function uses the **np.vstack** function which takes each vector of dimension $1\\times n$ and produces a $3\\times n$ matrix $\\boldsymbol{W}$" + ] + }, + { + "cell_type": "markdown", + "id": "0929cae0", + "metadata": { + "editable": true + }, + "source": [ + "$$\n", + "\\boldsymbol{W} = \\begin{bmatrix} x_0 & x_1 & x_2 & \\dots & x_{n-2} & x_{n-1} \\\\\n", + " y_0 & y_1 & y_2 & \\dots & y_{n-2} & y_{n-1} \\\\\n", + "\t\t\t z_0 & z_1 & z_2 & \\dots & z_{n-2} & z_{n-1} \\\\\n", + " \\end{bmatrix},\n", + "$$" + ] + }, + { + "cell_type": "markdown", + "id": "f3181ff4", + "metadata": { + "editable": true + }, + "source": [ + "which in turn is converted into into the $3\\times 3$ covariance matrix\n", + "$\\boldsymbol{\\Sigma}$ via the Numpy function **np.cov()**. We note that we can also calculate\n", + "the mean value of each set of samples $\\boldsymbol{x}$ etc using the Numpy\n", + "function **np.mean(x)**. We can also extract the eigenvalues of the\n", + "covariance matrix through the **np.linalg.eig()** function." + ] + }, + { + "cell_type": "code", + "execution_count": 15, + "id": "6c2c0ee5", + "metadata": { + "collapsed": false, + "editable": true + }, + "outputs": [], + "source": [ + "# Importing various packages\n", + "import numpy as np\n", + "\n", + "n = 100\n", + "x = np.random.normal(size=n)\n", + "print(np.mean(x))\n", + "y = 4+3*x+np.random.normal(size=n)\n", + "print(np.mean(y))\n", + "z = x**3+np.random.normal(size=n)\n", + "print(np.mean(z))\n", + "W = np.vstack((x, y, z))\n", + "Sigma = np.cov(W)\n", + "print(Sigma)\n", + "Eigvals, Eigvecs = np.linalg.eig(Sigma)\n", + "print(Eigvals)" + ] + }, + { + "cell_type": "code", + "execution_count": 16, + "id": "cbe79e57", + "metadata": { + "collapsed": false, + "editable": true + }, + "outputs": [], + "source": [ + "%matplotlib inline\n", + "\n", + "import numpy as np\n", + "import matplotlib.pyplot as plt\n", + "from scipy import sparse\n", + "eye = np.eye(4)\n", + "print(eye)\n", + "sparse_mtx = sparse.csr_matrix(eye)\n", + "print(sparse_mtx)\n", + "x = np.linspace(-10,10,100)\n", + "y = np.sin(x)\n", + "plt.plot(x,y,marker='x')\n", + "plt.show()" + ] + }, + { + "cell_type": "markdown", + "id": "f23e1ca6", + "metadata": { + "editable": true + }, + "source": [ + "## Meet the Pandas\n", + "\n", + "\n", + "\n", + "\n", + "

    Figure 1:

    \n", + "\n", + "\n", + "Another useful Python package is\n", + "[pandas](https://pandas.pydata.org/), which is an open source library\n", + "providing high-performance, easy-to-use data structures and data\n", + "analysis tools for Python. **pandas** stands for panel data, a term borrowed from econometrics and is an efficient library for data analysis with an emphasis on tabular data.\n", + "**pandas** has two major classes, the **DataFrame** class with two-dimensional data objects and tabular data organized in columns and the class **Series** with a focus on one-dimensional data objects. Both classes allow you to index data easily as we will see in the examples below. \n", + "**pandas** allows you also to perform mathematical operations on the data, spanning from simple reshapings of vectors and matrices to statistical operations. \n", + "\n", + "The following simple example shows how we can, in an easy way make tables of our data. Here we define a data set which includes names, place of birth and date of birth, and displays the data in an easy to read way. We will see repeated use of **pandas**, in particular in connection with classification of data." + ] + }, + { + "cell_type": "code", + "execution_count": 17, + "id": "8789f2ba", + "metadata": { + "collapsed": false, + "editable": true + }, + "outputs": [], + "source": [ + "import pandas as pd\n", + "from IPython.display import display\n", + "data = {'First Name': [\"Frodo\", \"Bilbo\", \"Aragorn II\", \"Samwise\"],\n", + " 'Last Name': [\"Baggins\", \"Baggins\",\"Elessar\",\"Gamgee\"],\n", + " 'Place of birth': [\"Shire\", \"Shire\", \"Eriador\", \"Shire\"],\n", + " 'Date of Birth T.A.': [2968, 2890, 2931, 2980]\n", + " }\n", + "data_pandas = pd.DataFrame(data)\n", + "display(data_pandas)" + ] + }, + { + "cell_type": "markdown", + "id": "e9f51a5f", + "metadata": { + "editable": true + }, + "source": [ + "In the above we have imported **pandas** with the shorthand **pd**, the latter has become the standard way we import **pandas**. We make then a list of various variables\n", + "and reorganize the aboves lists into a **DataFrame** and then print out a neat table with specific column labels as *Name*, *place of birth* and *date of birth*.\n", + "Displaying these results, we see that the indices are given by the default numbers from zero to three.\n", + "**pandas** is extremely flexible and we can easily change the above indices by defining a new type of indexing as" + ] + }, + { + "cell_type": "code", + "execution_count": 18, + "id": "16b329b9", + "metadata": { + "collapsed": false, + "editable": true + }, + "outputs": [], + "source": [ + "data_pandas = pd.DataFrame(data,index=['Frodo','Bilbo','Aragorn','Sam'])\n", + "display(data_pandas)" + ] + }, + { + "cell_type": "markdown", + "id": "cd1876fb", + "metadata": { + "editable": true + }, + "source": [ + "Thereafter we display the content of the row which begins with the index **Aragorn**" + ] + }, + { + "cell_type": "code", + "execution_count": 19, + "id": "5b7e1c04", + "metadata": { + "collapsed": false, + "editable": true + }, + "outputs": [], + "source": [ + "display(data_pandas.loc['Aragorn'])" + ] + }, + { + "cell_type": "markdown", + "id": "10f0bb9d", + "metadata": { + "editable": true + }, + "source": [ + "We can easily append data to this, for example" + ] + }, + { + "cell_type": "code", + "execution_count": 20, + "id": "190b1a89", + "metadata": { + "collapsed": false, + "editable": true + }, + "outputs": [], + "source": [ + "new_hobbit = {'First Name': [\"Peregrin\"],\n", + " 'Last Name': [\"Took\"],\n", + " 'Place of birth': [\"Shire\"],\n", + " 'Date of Birth T.A.': [2990]\n", + " }\n", + "data_pandas=data_pandas.append(pd.DataFrame(new_hobbit, index=['Pippin']))\n", + "display(data_pandas)" + ] + }, + { + "cell_type": "markdown", + "id": "579fb43e", + "metadata": { + "editable": true + }, + "source": [ + "Here are other examples where we use the **DataFrame** functionality to handle arrays, now with more interesting features for us, namely numbers. We set up a matrix \n", + "of dimensionality $10\\times 5$ and compute the mean value and standard deviation of each column. Similarly, we can perform mathematial operations like squaring the matrix elements and many other operations." + ] + }, + { + "cell_type": "code", + "execution_count": 21, + "id": "cb5f7e36", + "metadata": { + "collapsed": false, + "editable": true + }, + "outputs": [], + "source": [ + "import numpy as np\n", + "import pandas as pd\n", + "from IPython.display import display\n", + "np.random.seed(100)\n", + "# setting up a 10 x 5 matrix\n", + "rows = 10\n", + "cols = 5\n", + "a = np.random.randn(rows,cols)\n", + "df = pd.DataFrame(a)\n", + "display(df)\n", + "print(df.mean())\n", + "print(df.std())\n", + "display(df**2)" + ] + }, + { + "cell_type": "markdown", + "id": "51e35da5", + "metadata": { + "editable": true + }, + "source": [ + "Thereafter we can select specific columns only and plot final results" + ] + }, + { + "cell_type": "code", + "execution_count": 22, + "id": "6754efdc", + "metadata": { + "collapsed": false, + "editable": true + }, + "outputs": [], + "source": [ + "df.columns = ['First', 'Second', 'Third', 'Fourth', 'Fifth']\n", + "df.index = np.arange(10)\n", + "\n", + "display(df)\n", + "print(df['Second'].mean() )\n", + "print(df.info())\n", + "print(df.describe())\n", + "\n", + "from pylab import plt, mpl\n", + "plt.style.use('seaborn')\n", + "mpl.rcParams['font.family'] = 'serif'\n", + "\n", + "df.cumsum().plot(lw=2.0, figsize=(10,6))\n", + "plt.show()\n", + "\n", + "\n", + "df.plot.bar(figsize=(10,6), rot=15)\n", + "plt.show()" + ] + }, + { + "cell_type": "markdown", + "id": "f1750baf", + "metadata": { + "editable": true + }, + "source": [ + "We can produce a $4\\times 4$ matrix" + ] + }, + { + "cell_type": "code", + "execution_count": 23, + "id": "4069afcc", + "metadata": { + "collapsed": false, + "editable": true + }, + "outputs": [], + "source": [ + "b = np.arange(16).reshape((4,4))\n", + "print(b)\n", + "df1 = pd.DataFrame(b)\n", + "print(df1)" + ] + }, + { + "cell_type": "markdown", + "id": "dc04e1ff", + "metadata": { + "editable": true + }, + "source": [ + "and many other operations. \n", + "\n", + "The **Series** class is another important class included in\n", + "**pandas**. You can view it as a specialization of **DataFrame** but where\n", + "we have just a single column of data. It shares many of the same features as **DataFrame**. As with **DataFrame**,\n", + "most operations are vectorized, achieving thereby a high performance when dealing with computations of arrays, in particular labeled arrays.\n", + "As we will see below it leads also to a very concice code close to the mathematical operations we may be interested in.\n", + "For multidimensional arrays, we recommend strongly [xarray](http://xarray.pydata.org/en/stable/). **xarray** has much of the same flexibility as **pandas**, but allows for the extension to higher dimensions than two. We will see examples later of the usage of both **pandas** and **xarray**." + ] + }, + { + "cell_type": "markdown", + "id": "ff884c05", + "metadata": { + "editable": true + }, + "source": [ + "### Simple linear regression model using **scikit-learn**\n", + "\n", + "We start with perhaps our simplest possible example, using **Scikit-Learn** to perform linear regression analysis on a data set produced by us. \n", + "\n", + "What follows is a simple Python code where we have defined a function\n", + "$y$ in terms of the variable $x$. Both are defined as vectors with $100$ entries. \n", + "The numbers in the vector $\\boldsymbol{x}$ are given\n", + "by random numbers generated with a uniform distribution with entries\n", + "$x_i \\in [0,1]$ (more about probability distribution functions\n", + "later). These values are then used to define a function $y(x)$\n", + "(tabulated again as a vector) with a linear dependence on $x$ plus a\n", + "random noise added via the normal distribution.\n", + "\n", + "The Numpy functions are imported used the **import numpy as np**\n", + "statement and the random number generator for the uniform distribution\n", + "is called using the function **np.random.rand()**, where we specificy\n", + "that we want $100$ random variables. Using Numpy we define\n", + "automatically an array with the specified number of elements, $100$ in\n", + "our case. With the Numpy function **randn()** we can compute random\n", + "numbers with the normal distribution (mean value $\\mu$ equal to zero and\n", + "variance $\\sigma^2$ set to one) and produce the values of $y$ assuming a linear\n", + "dependence as function of $x$" + ] + }, + { + "cell_type": "markdown", + "id": "10424430", + "metadata": { + "editable": true + }, + "source": [ + "$$\n", + "y = 2x+N(0,1),\n", + "$$" + ] + }, + { + "cell_type": "markdown", + "id": "d4456d18", + "metadata": { + "editable": true + }, + "source": [ + "where $N(0,1)$ represents random numbers generated by the normal\n", + "distribution. From **Scikit-Learn** we import then the\n", + "**LinearRegression** functionality and make a prediction $\\tilde{y} =\n", + "\\alpha + \\beta x$ using the function **fit(x,y)**. We call the set of\n", + "data $(\\boldsymbol{x},\\boldsymbol{y})$ for our training data. The Python package\n", + "**scikit-learn** has also a functionality which extracts the above\n", + "fitting parameters $\\alpha$ and $\\beta$ (see below). Later we will\n", + "distinguish between training data and test data.\n", + "\n", + "For plotting we use the Python package\n", + "[matplotlib](https://matplotlib.org/) which produces publication\n", + "quality figures. Feel free to explore the extensive\n", + "[gallery](https://matplotlib.org/gallery/index.html) of examples. In\n", + "this example we plot our original values of $x$ and $y$ as well as the\n", + "prediction **ypredict** ($\\tilde{y}$), which attempts at fitting our\n", + "data with a straight line.\n", + "\n", + "The Python code follows here." + ] + }, + { + "cell_type": "code", + "execution_count": 24, + "id": "570b320d", + "metadata": { + "collapsed": false, + "editable": true + }, + "outputs": [], + "source": [ + "# Importing various packages\n", + "import numpy as np\n", + "import matplotlib.pyplot as plt\n", + "from sklearn.linear_model import LinearRegression\n", + "\n", + "x = np.random.rand(100,1)\n", + "y = 2*x+np.random.randn(100,1)\n", + "linreg = LinearRegression()\n", + "linreg.fit(x,y)\n", + "xnew = np.array([[0],[1]])\n", + "ypredict = linreg.predict(xnew)\n", + "\n", + "plt.plot(xnew, ypredict, \"r-\")\n", + "plt.plot(x, y ,'ro')\n", + "plt.axis([0,1.0,0, 5.0])\n", + "plt.xlabel(r'$x$')\n", + "plt.ylabel(r'$y$')\n", + "plt.title(r'Simple Linear Regression')\n", + "plt.show()" + ] + }, + { + "cell_type": "markdown", + "id": "a6e493ad", + "metadata": { + "editable": true + }, + "source": [ + "This example serves several aims. It allows us to demonstrate several\n", + "aspects of data analysis and later machine learning algorithms. The\n", + "immediate visualization shows that our linear fit is not\n", + "impressive. It goes through the data points, but there are many\n", + "outliers which are not reproduced by our linear regression. We could\n", + "now play around with this small program and change for example the\n", + "factor in front of $x$ and the normal distribution. Try to change the\n", + "function $y$ to" + ] + }, + { + "cell_type": "markdown", + "id": "8f1725d2", + "metadata": { + "editable": true + }, + "source": [ + "$$\n", + "y = 10x+0.01 \\times N(0,1),\n", + "$$" + ] + }, + { + "cell_type": "markdown", + "id": "8df5914b", + "metadata": { + "editable": true + }, + "source": [ + "where $x$ is defined as before. Does the fit look better? Indeed, by\n", + "reducing the role of the noise given by the normal distribution we see immediately that\n", + "our linear prediction seemingly reproduces better the training\n", + "set. However, this testing 'by the eye' is obviouly not satisfactory in the\n", + "long run. Here we have only defined the training data and our model, and \n", + "have not discussed a more rigorous approach to the **cost** function.\n", + "\n", + "We need more rigorous criteria in defining whether we have succeeded or\n", + "not in modeling our training data. You will be surprised to see that\n", + "many scientists seldomly venture beyond this 'by the eye' approach. A\n", + "standard approach for the *cost* function is the so-called $\\chi^2$\n", + "function (a variant of the mean-squared error (MSE))" + ] + }, + { + "cell_type": "markdown", + "id": "7648e110", + "metadata": { + "editable": true + }, + "source": [ + "$$\n", + "\\chi^2 = \\frac{1}{n}\n", + "\\sum_{i=0}^{n-1}\\frac{(y_i-\\tilde{y}_i)^2}{\\sigma_i^2},\n", + "$$" + ] + }, + { + "cell_type": "markdown", + "id": "17c3f9d8", + "metadata": { + "editable": true + }, + "source": [ + "where $\\sigma_i^2$ is the variance (to be defined later) of the entry\n", + "$y_i$. We may not know the explicit value of $\\sigma_i^2$, it serves\n", + "however the aim of scaling the equations and make the cost function\n", + "dimensionless. \n", + "\n", + "Minimizing the cost function is a central aspect of\n", + "our discussions to come. Finding its minima as function of the model\n", + "parameters ($\\alpha$ and $\\beta$ in our case) will be a recurring\n", + "theme in these series of lectures. Essentially all machine learning\n", + "algorithms we will discuss center around the minimization of the\n", + "chosen cost function. This depends in turn on our specific\n", + "model for describing the data, a typical situation in supervised\n", + "learning. Automatizing the search for the minima of the cost function is a\n", + "central ingredient in all algorithms. Typical methods which are\n", + "employed are various variants of **gradient** methods. These will be\n", + "discussed in more detail later. Again, you'll be surprised to hear that\n", + "many practitioners minimize the above function ''by the eye', popularly dubbed as \n", + "'chi by the eye'. That is, change a parameter and see (visually and numerically) that \n", + "the $\\chi^2$ function becomes smaller. \n", + "\n", + "There are many ways to define the cost function. A simpler approach is to look at the relative difference between the training data and the predicted data, that is we define \n", + "the relative error (why would we prefer the MSE instead of the relative error?) as" + ] + }, + { + "cell_type": "markdown", + "id": "0cb0e3fa", + "metadata": { + "editable": true + }, + "source": [ + "$$\n", + "\\epsilon_{\\mathrm{relative}}= \\frac{\\vert \\boldsymbol{y} -\\boldsymbol{\\tilde{y}}\\vert}{\\vert \\boldsymbol{y}\\vert}.\n", + "$$" + ] + }, + { + "cell_type": "markdown", + "id": "00fe7e8c", + "metadata": { + "editable": true + }, + "source": [ + "The squared cost function results in an arithmetic mean-unbiased\n", + "estimator, and the absolute-value cost function results in a\n", + "median-unbiased estimator (in the one-dimensional case, and a\n", + "geometric median-unbiased estimator for the multi-dimensional\n", + "case). The squared cost function has the disadvantage that it has the tendency\n", + "to be dominated by outliers.\n", + "\n", + "We can modify easily the above Python code and plot the relative error instead" + ] + }, + { + "cell_type": "code", + "execution_count": 25, + "id": "7a17d6fe", + "metadata": { + "collapsed": false, + "editable": true + }, + "outputs": [], + "source": [ + "import numpy as np\n", + "import matplotlib.pyplot as plt\n", + "from sklearn.linear_model import LinearRegression\n", + "\n", + "x = np.random.rand(100,1)\n", + "y = 5*x+0.01*np.random.randn(100,1)\n", + "linreg = LinearRegression()\n", + "linreg.fit(x,y)\n", + "ypredict = linreg.predict(x)\n", + "\n", + "plt.plot(x, np.abs(ypredict-y)/abs(y), \"ro\")\n", + "plt.axis([0,1.0,0.0, 0.5])\n", + "plt.xlabel(r'$x$')\n", + "plt.ylabel(r'$\\epsilon_{\\mathrm{relative}}$')\n", + "plt.title(r'Relative error')\n", + "plt.show()" + ] + }, + { + "cell_type": "markdown", + "id": "8f557979", + "metadata": { + "editable": true + }, + "source": [ + "Depending on the parameter in front of the normal distribution, we may\n", + "have a small or larger relative error. Try to play around with\n", + "different training data sets and study (graphically) the value of the\n", + "relative error.\n", + "\n", + "As mentioned above, **Scikit-Learn** has an impressive functionality.\n", + "We can for example extract the values of $\\alpha$ and $\\beta$ and\n", + "their error estimates, or the variance and standard deviation and many\n", + "other properties from the statistical data analysis. \n", + "\n", + "Here we show an\n", + "example of the functionality of **Scikit-Learn**." + ] + }, + { + "cell_type": "code", + "execution_count": 26, + "id": "a5e9ee5a", + "metadata": { + "collapsed": false, + "editable": true + }, + "outputs": [], + "source": [ + "import numpy as np \n", + "import matplotlib.pyplot as plt \n", + "from sklearn.linear_model import LinearRegression \n", + "from sklearn.metrics import mean_squared_error, r2_score, mean_squared_log_error, mean_absolute_error\n", + "\n", + "x = np.random.rand(100,1)\n", + "y = 2.0+ 5*x+0.5*np.random.randn(100,1)\n", + "linreg = LinearRegression()\n", + "linreg.fit(x,y)\n", + "ypredict = linreg.predict(x)\n", + "print('The intercept alpha: \\n', linreg.intercept_)\n", + "print('Coefficient beta : \\n', linreg.coef_)\n", + "# The mean squared error \n", + "print(\"Mean squared error: %.2f\" % mean_squared_error(y, ypredict))\n", + "# Explained variance score: 1 is perfect prediction \n", + "print('Variance score: %.2f' % r2_score(y, ypredict))\n", + "# Mean squared log error \n", + "print('Mean squared log error: %.2f' % mean_squared_log_error(y, ypredict) )\n", + "# Mean absolute error \n", + "print('Mean absolute error: %.2f' % mean_absolute_error(y, ypredict))\n", + "plt.plot(x, ypredict, \"r-\")\n", + "plt.plot(x, y ,'ro')\n", + "plt.axis([0.0,1.0,1.5, 7.0])\n", + "plt.xlabel(r'$x$')\n", + "plt.ylabel(r'$y$')\n", + "plt.title(r'Linear Regression fit ')\n", + "plt.show()" + ] + }, + { + "cell_type": "markdown", + "id": "a2b45b0b", + "metadata": { + "editable": true + }, + "source": [ + "The function **coef** gives us the parameter $\\beta$ of our fit while **intercept** yields \n", + "$\\alpha$. Depending on the constant in front of the normal distribution, we get values near or far from $\\alpha =2$ and $\\beta =5$. Try to play around with different parameters in front of the normal distribution. The function **meansquarederror** gives us the mean square error, a risk metric corresponding to the expected value of the squared (quadratic) error or loss defined as" + ] + }, + { + "cell_type": "markdown", + "id": "97da0991", + "metadata": { + "editable": true + }, + "source": [ + "$$\n", + "MSE(\\boldsymbol{y},\\boldsymbol{\\tilde{y}}) = \\frac{1}{n}\n", + "\\sum_{i=0}^{n-1}(y_i-\\tilde{y}_i)^2,\n", + "$$" + ] + }, + { + "cell_type": "markdown", + "id": "6664f912", + "metadata": { + "editable": true + }, + "source": [ + "The smaller the value, the better the fit. Ideally we would like to\n", + "have an MSE equal zero. The attentive reader has probably recognized\n", + "this function as being similar to the $\\chi^2$ function defined above.\n", + "\n", + "The **r2score** function computes $R^2$, the coefficient of\n", + "determination. It provides a measure of how well future samples are\n", + "likely to be predicted by the model. Best possible score is 1.0 and it\n", + "can be negative (because the model can be arbitrarily worse). A\n", + "constant model that always predicts the expected value of $\\boldsymbol{y}$,\n", + "disregarding the input features, would get a $R^2$ score of $0.0$.\n", + "\n", + "If $\\tilde{\\boldsymbol{y}}_i$ is the predicted value of the $i-th$ sample and $y_i$ is the corresponding true value, then the score $R^2$ is defined as" + ] + }, + { + "cell_type": "markdown", + "id": "4ca74414", + "metadata": { + "editable": true + }, + "source": [ + "$$\n", + "R^2(\\boldsymbol{y}, \\tilde{\\boldsymbol{y}}) = 1 - \\frac{\\sum_{i=0}^{n - 1} (y_i - \\tilde{y}_i)^2}{\\sum_{i=0}^{n - 1} (y_i - \\bar{y})^2},\n", + "$$" + ] + }, + { + "cell_type": "markdown", + "id": "9e1d8766", + "metadata": { + "editable": true + }, + "source": [ + "where we have defined the mean value of $\\boldsymbol{y}$ as" + ] + }, + { + "cell_type": "markdown", + "id": "4605a6c5", + "metadata": { + "editable": true + }, + "source": [ + "$$\n", + "\\bar{y} = \\frac{1}{n} \\sum_{i=0}^{n - 1} y_i.\n", + "$$" + ] + }, + { + "cell_type": "markdown", + "id": "882cab00", + "metadata": { + "editable": true + }, + "source": [ + "Another quantity taht we will meet again in our discussions of regression analysis is \n", + " the mean absolute error (MAE), a risk metric corresponding to the expected value of the absolute error loss or what we call the $l1$-norm loss. In our discussion above we presented the relative error.\n", + "The MAE is defined as follows" + ] + }, + { + "cell_type": "markdown", + "id": "7d365176", + "metadata": { + "editable": true + }, + "source": [ + "$$\n", + "\\text{MAE}(\\boldsymbol{y}, \\boldsymbol{\\tilde{y}}) = \\frac{1}{n} \\sum_{i=0}^{n-1} \\left| y_i - \\tilde{y}_i \\right|.\n", + "$$" + ] + }, + { + "cell_type": "markdown", + "id": "ed69759f", + "metadata": { + "editable": true + }, + "source": [ + "We present the \n", + "squared logarithmic (quadratic) error" + ] + }, + { + "cell_type": "markdown", + "id": "33745626", + "metadata": { + "editable": true + }, + "source": [ + "$$\n", + "\\text{MSLE}(\\boldsymbol{y}, \\boldsymbol{\\tilde{y}}) = \\frac{1}{n} \\sum_{i=0}^{n - 1} (\\log_e (1 + y_i) - \\log_e (1 + \\tilde{y}_i) )^2,\n", + "$$" + ] + }, + { + "cell_type": "markdown", + "id": "049e0384", + "metadata": { + "editable": true + }, + "source": [ + "where $\\log_e (x)$ stands for the natural logarithm of $x$. This error\n", + "estimate is best to use when targets having exponential growth, such\n", + "as population counts, average sales of a commodity over a span of\n", + "years etc. \n", + "\n", + "Finally, another cost function is the Huber cost function used in robust regression.\n", + "\n", + "The rationale behind this possible cost function is its reduced\n", + "sensitivity to outliers in the data set. In our discussions on\n", + "dimensionality reduction and normalization of data we will meet other\n", + "ways of dealing with outliers.\n", + "\n", + "The Huber cost function is defined as" + ] + }, + { + "cell_type": "markdown", + "id": "5a9fe56d", + "metadata": { + "editable": true + }, + "source": [ + "$$\n", + "H_{\\delta}(\\boldsymbol{a})=\\left\\{\\begin{array}{cc}\\frac{1}{2} \\boldsymbol{a}^{2}& \\text{for }|\\boldsymbol{a}|\\leq \\delta\\\\ \\delta (|\\boldsymbol{a}|-\\frac{1}{2}\\delta ),&\\text{otherwise}.\\end{array}\\right.\n", + "$$" + ] + }, + { + "cell_type": "markdown", + "id": "be3f1edc", + "metadata": { + "editable": true + }, + "source": [ + "Here $\\boldsymbol{a}=\\boldsymbol{y} - \\boldsymbol{\\tilde{y}}$.\n", + "\n", + "We will discuss in more detail these and other functions in the\n", + "various lectures and lab sessions." + ] + }, + { + "cell_type": "markdown", + "id": "39a78b9e", + "metadata": { + "editable": true + }, + "source": [ + "### To our real data: nuclear binding energies. Brief reminder on masses and binding energies\n", + "\n", + "Let us now dive into nuclear physics and remind ourselves briefly about some basic features about binding\n", + "energies. A basic quantity which can be measured for the ground\n", + "states of nuclei is the atomic mass $M(N, Z)$ of the neutral atom with\n", + "atomic mass number $A$ and charge $Z$. The number of neutrons is $N$. There are indeed several sophisticated experiments worldwide which allow us to measure this quantity to high precision (parts per million even). \n", + "\n", + "Atomic masses are usually tabulated in terms of the mass excess defined by" + ] + }, + { + "cell_type": "markdown", + "id": "8c035b2b", + "metadata": { + "editable": true + }, + "source": [ + "$$\n", + "\\Delta M(N, Z) = M(N, Z) - uA,\n", + "$$" + ] + }, + { + "cell_type": "markdown", + "id": "12c6c509", + "metadata": { + "editable": true + }, + "source": [ + "where $u$ is the Atomic Mass Unit" + ] + }, + { + "cell_type": "markdown", + "id": "81cb4b33", + "metadata": { + "editable": true + }, + "source": [ + "$$\n", + "u = M(^{12}\\mathrm{C})/12 = 931.4940954(57) \\hspace{0.1cm} \\mathrm{MeV}/c^2.\n", + "$$" + ] + }, + { + "cell_type": "markdown", + "id": "f1aec311", + "metadata": { + "editable": true + }, + "source": [ + "The nucleon masses are" + ] + }, + { + "cell_type": "markdown", + "id": "3f4f90ea", + "metadata": { + "editable": true + }, + "source": [ + "$$\n", + "m_p = 1.00727646693(9)u,\n", + "$$" + ] + }, + { + "cell_type": "markdown", + "id": "5535c1ab", + "metadata": { + "editable": true + }, + "source": [ + "and" + ] + }, + { + "cell_type": "markdown", + "id": "b3efd5ad", + "metadata": { + "editable": true + }, + "source": [ + "$$\n", + "m_n = 939.56536(8)\\hspace{0.1cm} \\mathrm{MeV}/c^2 = 1.0086649156(6)u.\n", + "$$" + ] + }, + { + "cell_type": "markdown", + "id": "a6d81840", + "metadata": { + "editable": true + }, + "source": [ + "In the [2016 mass evaluation of by W.J.Huang, G.Audi, M.Wang, F.G.Kondev, S.Naimi and X.Xu](http://nuclearmasses.org/resources_folder/Wang_2017_Chinese_Phys_C_41_030003.pdf)\n", + "there are data on masses and decays of 3437 nuclei.\n", + "\n", + "The nuclear binding energy is defined as the energy required to break\n", + "up a given nucleus into its constituent parts of $N$ neutrons and $Z$\n", + "protons. In terms of the atomic masses $M(N, Z)$ the binding energy is\n", + "defined by" + ] + }, + { + "cell_type": "markdown", + "id": "f69f2188", + "metadata": { + "editable": true + }, + "source": [ + "$$\n", + "BE(N, Z) = ZM_H c^2 + Nm_n c^2 - M(N, Z)c^2 ,\n", + "$$" + ] + }, + { + "cell_type": "markdown", + "id": "cf70b128", + "metadata": { + "editable": true + }, + "source": [ + "where $M_H$ is the mass of the hydrogen atom and $m_n$ is the mass of the neutron.\n", + "In terms of the mass excess the binding energy is given by" + ] + }, + { + "cell_type": "markdown", + "id": "4bfa00ef", + "metadata": { + "editable": true + }, + "source": [ + "$$\n", + "BE(N, Z) = Z\\Delta_H c^2 + N\\Delta_n c^2 -\\Delta(N, Z)c^2 ,\n", + "$$" + ] + }, + { + "cell_type": "markdown", + "id": "4750b7cb", + "metadata": { + "editable": true + }, + "source": [ + "where $\\Delta_H c^2 = 7.2890$ MeV and $\\Delta_n c^2 = 8.0713$ MeV.\n", + "\n", + "A popular and physically intuitive model which can be used to parametrize \n", + "the experimental binding energies as function of $A$, is the so-called \n", + "**liquid drop model**. The ansatz is based on the following expression" + ] + }, + { + "cell_type": "markdown", + "id": "cc94773e", + "metadata": { + "editable": true + }, + "source": [ + "$$\n", + "BE(N,Z) = a_1A-a_2A^{2/3}-a_3\\frac{Z^2}{A^{1/3}}-a_4\\frac{(N-Z)^2}{A},\n", + "$$" + ] + }, + { + "cell_type": "markdown", + "id": "48a29815", + "metadata": { + "editable": true + }, + "source": [ + "where $A$ stands for the number of nucleons and the $a_i$s are parameters which are determined by a fit \n", + "to the experimental data. \n", + "\n", + "To arrive at the above expression we have assumed that we can make the following assumptions:\n", + "\n", + " * There is a volume term $a_1A$ proportional with the number of nucleons (the energy is also an extensive quantity). When an assembly of nucleons of the same size is packed together into the smallest volume, each interior nucleon has a certain number of other nucleons in contact with it. This contribution is proportional to the volume.\n", + "\n", + " * There is a surface energy term $a_2A^{2/3}$. The assumption here is that a nucleon at the surface of a nucleus interacts with fewer other nucleons than one in the interior of the nucleus and hence its binding energy is less. This surface energy term takes that into account and is therefore negative and is proportional to the surface area.\n", + "\n", + " * There is a Coulomb energy term $a_3\\frac{Z^2}{A^{1/3}}$. The electric repulsion between each pair of protons in a nucleus yields less binding. \n", + "\n", + " * There is an asymmetry term $a_4\\frac{(N-Z)^2}{A}$. This term is associated with the Pauli exclusion principle and reflects the fact that the proton-neutron interaction is more attractive on the average than the neutron-neutron and proton-proton interactions.\n", + "\n", + "We could also add a so-called pairing term, which is a correction term that\n", + "arises from the tendency of proton pairs and neutron pairs to\n", + "occur. An even number of particles is more stable than an odd number." + ] + }, + { + "cell_type": "markdown", + "id": "2be22cb2", + "metadata": { + "editable": true + }, + "source": [ + "### Organizing our data\n", + "\n", + "Let us start with reading and organizing our data. \n", + "We start with the compilation of masses and binding energies from 2016.\n", + "After having downloaded this file to our own computer, we are now ready to read the file and start structuring our data.\n", + "\n", + "We start with preparing folders for storing our calculations and the data file over masses and binding energies. We import also various modules that we will find useful in order to present various Machine Learning methods. Here we focus mainly on the functionality of **scikit-learn**." + ] + }, + { + "cell_type": "code", + "execution_count": 27, + "id": "57ce58c1", + "metadata": { + "collapsed": false, + "editable": true + }, + "outputs": [], + "source": [ + "# Common imports\n", + "import numpy as np\n", + "import pandas as pd\n", + "import matplotlib.pyplot as plt\n", + "import sklearn.linear_model as skl\n", + "from sklearn.model_selection import train_test_split\n", + "from sklearn.metrics import mean_squared_error, r2_score, mean_absolute_error\n", + "import os\n", + "\n", + "# Where to save the figures and data files\n", + "PROJECT_ROOT_DIR = \"Results\"\n", + "FIGURE_ID = \"Results/FigureFiles\"\n", + "DATA_ID = \"DataFiles/\"\n", + "\n", + "if not os.path.exists(PROJECT_ROOT_DIR):\n", + " os.mkdir(PROJECT_ROOT_DIR)\n", + "\n", + "if not os.path.exists(FIGURE_ID):\n", + " os.makedirs(FIGURE_ID)\n", + "\n", + "if not os.path.exists(DATA_ID):\n", + " os.makedirs(DATA_ID)\n", + "\n", + "def image_path(fig_id):\n", + " return os.path.join(FIGURE_ID, fig_id)\n", + "\n", + "def data_path(dat_id):\n", + " return os.path.join(DATA_ID, dat_id)\n", + "\n", + "def save_fig(fig_id):\n", + " plt.savefig(image_path(fig_id) + \".png\", format='png')\n", + "\n", + "infile = open(data_path(\"MassEval2016.dat\"),'r')" + ] + }, + { + "cell_type": "markdown", + "id": "856d936e", + "metadata": { + "editable": true + }, + "source": [ + "Before we proceed, we define also a function for making our plots. You can obviously avoid this and simply set up various **matplotlib** commands every time you need them. You may however find it convenient to collect all such commands in one function and simply call this function." + ] + }, + { + "cell_type": "code", + "execution_count": 28, + "id": "f00c1cc8", + "metadata": { + "collapsed": false, + "editable": true + }, + "outputs": [], + "source": [ + "from pylab import plt, mpl\n", + "plt.style.use('seaborn')\n", + "mpl.rcParams['font.family'] = 'serif'\n", + "\n", + "def MakePlot(x,y, styles, labels, axlabels):\n", + " plt.figure(figsize=(10,6))\n", + " for i in range(len(x)):\n", + " plt.plot(x[i], y[i], styles[i], label = labels[i])\n", + " plt.xlabel(axlabels[0])\n", + " plt.ylabel(axlabels[1])\n", + " plt.legend(loc=0)" + ] + }, + { + "cell_type": "markdown", + "id": "01f32685", + "metadata": { + "editable": true + }, + "source": [ + "Our next step is to read the data on experimental binding energies and\n", + "reorganize them as functions of the mass number $A$, the number of\n", + "protons $Z$ and neutrons $N$ using **pandas**. Before we do this it is\n", + "always useful (unless you have a binary file or other types of compressed\n", + "data) to actually open the file and simply take a look at it!\n", + "\n", + "In particular, the program that outputs the final nuclear masses is written in Fortran with a specific format. It means that we need to figure out the format and which columns contain the data we are interested in. Pandas comes with a function that reads formatted output. After having admired the file, we are now ready to start massaging it with **pandas**. The file begins with some basic format information." + ] + }, + { + "cell_type": "code", + "execution_count": 29, + "id": "c00626c0", + "metadata": { + "collapsed": false, + "editable": true + }, + "outputs": [], + "source": [ + "\"\"\" \n", + "This is taken from the data file of the mass 2016 evaluation. \n", + "All files are 3436 lines long with 124 character per line. \n", + " Headers are 39 lines long. \n", + " col 1 : Fortran character control: 1 = page feed 0 = line feed \n", + " format : a1,i3,i5,i5,i5,1x,a3,a4,1x,f13.5,f11.5,f11.3,f9.3,1x,a2,f11.3,f9.3,1x,i3,1x,f12.5,f11.5 \n", + " These formats are reflected in the pandas widths variable below, see the statement \n", + " widths=(1,3,5,5,5,1,3,4,1,13,11,11,9,1,2,11,9,1,3,1,12,11,1), \n", + " Pandas has also a variable header, with length 39 in this case. \n", + "\"\"\"" + ] + }, + { + "cell_type": "markdown", + "id": "e3ac89b4", + "metadata": { + "editable": true + }, + "source": [ + "The data we are interested in are in columns 2, 3, 4 and 11, giving us\n", + "the number of neutrons, protons, mass numbers and binding energies,\n", + "respectively. We add also for the sake of completeness the element name. The data are in fixed-width formatted lines and we will\n", + "covert them into the **pandas** DataFrame structure." + ] + }, + { + "cell_type": "code", + "execution_count": 30, + "id": "292ced26", + "metadata": { + "collapsed": false, + "editable": true + }, + "outputs": [], + "source": [ + "# Read the experimental data with Pandas\n", + "Masses = pd.read_fwf(infile, usecols=(2,3,4,6,11),\n", + " names=('N', 'Z', 'A', 'Element', 'Ebinding'),\n", + " widths=(1,3,5,5,5,1,3,4,1,13,11,11,9,1,2,11,9,1,3,1,12,11,1),\n", + " header=39,\n", + " index_col=False)\n", + "\n", + "# Extrapolated values are indicated by '#' in place of the decimal place, so\n", + "# the Ebinding column won't be numeric. Coerce to float and drop these entries.\n", + "Masses['Ebinding'] = pd.to_numeric(Masses['Ebinding'], errors='coerce')\n", + "Masses = Masses.dropna()\n", + "# Convert from keV to MeV.\n", + "Masses['Ebinding'] /= 1000\n", + "\n", + "# Group the DataFrame by nucleon number, A.\n", + "Masses = Masses.groupby('A')\n", + "# Find the rows of the grouped DataFrame with the maximum binding energy.\n", + "Masses = Masses.apply(lambda t: t[t.Ebinding==t.Ebinding.max()])" + ] + }, + { + "cell_type": "markdown", + "id": "b21b5f18", + "metadata": { + "editable": true + }, + "source": [ + "We have now read in the data, grouped them according to the variables we are interested in. \n", + "We see how easy it is to reorganize the data using **pandas**. If we\n", + "were to do these operations in C/C++ or Fortran, we would have had to\n", + "write various functions/subroutines which perform the above\n", + "reorganizations for us. Having reorganized the data, we can now start\n", + "to make some simple fits using both the functionalities in **numpy** and\n", + "**Scikit-Learn** afterwards. \n", + "\n", + "Now we define five variables which contain\n", + "the number of nucleons $A$, the number of protons $Z$ and the number of neutrons $N$, the element name and finally the energies themselves." + ] + }, + { + "cell_type": "code", + "execution_count": 31, + "id": "18c931f7", + "metadata": { + "collapsed": false, + "editable": true + }, + "outputs": [], + "source": [ + "A = Masses['A']\n", + "Z = Masses['Z']\n", + "N = Masses['N']\n", + "Element = Masses['Element']\n", + "Energies = Masses['Ebinding']\n", + "print(Masses)" + ] + }, + { + "cell_type": "markdown", + "id": "bf1a1139", + "metadata": { + "editable": true + }, + "source": [ + "The next step, and we will define this mathematically later, is to set up the so-called **design matrix**. We will throughout call this matrix $\\boldsymbol{X}$.\n", + "It has dimensionality $p\\times n$, where $n$ is the number of data points and $p$ are the so-called predictors. In our case here they are given by the number of polynomials in $A$ we wish to include in the fit." + ] + }, + { + "cell_type": "code", + "execution_count": 32, + "id": "0c1a4a2d", + "metadata": { + "collapsed": false, + "editable": true + }, + "outputs": [], + "source": [ + "# Now we set up the design matrix X\n", + "X = np.zeros((len(A),5))\n", + "X[:,0] = 1\n", + "X[:,1] = A\n", + "X[:,2] = A**(2.0/3.0)\n", + "X[:,3] = A**(-1.0/3.0)\n", + "X[:,4] = A**(-1.0)" + ] + }, + { + "cell_type": "markdown", + "id": "b1b537e6", + "metadata": { + "editable": true + }, + "source": [ + "With **scikitlearn** we are now ready to use linear regression and fit our data." + ] + }, + { + "cell_type": "code", + "execution_count": 33, + "id": "ef679107", + "metadata": { + "collapsed": false, + "editable": true + }, + "outputs": [], + "source": [ + "clf = skl.LinearRegression().fit(X, Energies)\n", + "fity = clf.predict(X)" + ] + }, + { + "cell_type": "markdown", + "id": "718927c7", + "metadata": { + "editable": true + }, + "source": [ + "Pretty simple! \n", + "Now we can print measures of how our fit is doing, the coefficients from the fits and plot the final fit together with our data." + ] + }, + { + "cell_type": "code", + "execution_count": 34, + "id": "ea124a61", + "metadata": { + "collapsed": false, + "editable": true + }, + "outputs": [], + "source": [ + "# The mean squared error \n", + "print(\"Mean squared error: %.2f\" % mean_squared_error(Energies, fity))\n", + "# Explained variance score: 1 is perfect prediction \n", + "print('Variance score: %.2f' % r2_score(Energies, fity))\n", + "# Mean absolute error \n", + "print('Mean absolute error: %.2f' % mean_absolute_error(Energies, fity))\n", + "print(clf.coef_, clf.intercept_)\n", + "\n", + "Masses['Eapprox'] = fity\n", + "# Generate a plot comparing the experimental with the fitted values values.\n", + "fig, ax = plt.subplots()\n", + "ax.set_xlabel(r'$A = N + Z$')\n", + "ax.set_ylabel(r'$E_\\mathrm{bind}\\,/\\mathrm{MeV}$')\n", + "ax.plot(Masses['A'], Masses['Ebinding'], alpha=0.7, lw=2,\n", + " label='Ame2016')\n", + "ax.plot(Masses['A'], Masses['Eapprox'], alpha=0.7, lw=2, c='m',\n", + " label='Fit')\n", + "ax.legend()\n", + "save_fig(\"Masses2016\")\n", + "plt.show()" + ] + }, + { + "cell_type": "markdown", + "id": "9b3a0eeb", + "metadata": { + "editable": true + }, + "source": [ + "### And what about using neural networks?\n", + "\n", + "The **seaborn** package allows us to visualize data in an efficient way. Note that we use **scikit-learn**'s multi-layer perceptron (or feed forward neural network) \n", + "functionality." + ] + }, + { + "cell_type": "code", + "execution_count": 35, + "id": "1994899a", + "metadata": { + "collapsed": false, + "editable": true + }, + "outputs": [], + "source": [ + "from sklearn.neural_network import MLPRegressor\n", + "from sklearn.metrics import accuracy_score\n", + "import seaborn as sns\n", + "\n", + "\n", + "X_train = X\n", + "Y_train = Energies\n", + "n_hidden_neurons = 50\n", + "epochs = 100\n", + "# store models for later use\n", + "eta_vals = np.logspace(-3, 0, 4)\n", + "lmbd_vals = np.logspace(-3, 0, 4)\n", + "# store the models for later use\n", + "DNN_scikit = np.zeros((len(eta_vals), len(lmbd_vals)), dtype=object)\n", + "train_accuracy = np.zeros((len(eta_vals), len(lmbd_vals)))\n", + "sns.set()\n", + "for i, eta in enumerate(eta_vals):\n", + " for j, lmbd in enumerate(lmbd_vals):\n", + " dnn = MLPRegressor(hidden_layer_sizes=(n_hidden_neurons), activation='relu', solver='adam',\n", + " alpha=lmbd, learning_rate_init=eta, max_iter=epochs)\n", + " dnn.fit(X_train, Y_train)\n", + " DNN_scikit[i][j] = dnn\n", + " train_accuracy[i][j] = dnn.score(X_train, Y_train)\n", + " fity = dnn.predict(X_train)\n", + " MSE = mean_squared_error(Y_train, fity)\n", + " print(\"Mean squared error: %.2f\" % mean_squared_error(Y_train, fity))\n", + " train_accuracy[i][j] = MSE\n", + "fig, ax = plt.subplots(figsize = (10, 10))\n", + "sns.heatmap(train_accuracy, annot=True, ax=ax, cmap=\"viridis\")\n", + "ax.set_title(\"Training Accuracy\")\n", + "ax.set_ylabel(\"$\\eta$\")\n", + "ax.set_xlabel(\"$\\lambda$\")\n", + "plt.show()\n", + "print(train_accuracy)" + ] + }, + { + "cell_type": "markdown", + "id": "7373ec03", + "metadata": { + "editable": true + }, + "source": [ + "## A first summary\n", + "\n", + "The aim behind these introductory words was to present to you various\n", + "Python libraries and their functionalities, in particular libraries like\n", + "**numpy**, **pandas**, **xarray** and **matplotlib** and other that make our life much easier\n", + "in handling various data sets and visualizing data. \n", + "\n", + "Furthermore,\n", + "**Scikit-Learn** allows us with few lines of code to implement popular\n", + "Machine Learning algorithms for supervised learning. Later we will meet **Tensorflow**, a powerful library for deep learning. \n", + "Now it is time to dive more into the details of various methods. We will start with linear regression and try to take a deeper look at what it entails." + ] + }, + { + "cell_type": "markdown", + "id": "d6bf1bf5", + "metadata": { + "editable": true + }, + "source": [ + "## Why Linear Regression (aka Ordinary Least Squares and family)\n", + "\n", + "Fitting a continuous function with linear parameterization in terms of the parameters $\\boldsymbol{\\beta}$.\n", + "* Method of choice for fitting a continuous function!\n", + "\n", + "* Gives an excellent introduction to central Machine Learning features with **understandable pedagogical** links to other methods like **Neural Networks**, **Support Vector Machines** etc\n", + "\n", + "* Analytical expression for the fitting parameters $\\boldsymbol{\\beta}$\n", + "\n", + "* Analytical expressions for statistical propertiers like mean values, variances, confidence intervals and more\n", + "\n", + "* Analytical relation with probabilistic interpretations \n", + "\n", + "* Easy to introduce basic concepts like bias-variance tradeoff, cross-validation, resampling and regularization techniques and many other ML topics\n", + "\n", + "* Easy to code! And links well with classification problems and logistic regression and neural networks\n", + "\n", + "* Allows for **easy** hands-on understanding of gradient descent methods\n", + "\n", + "* and many more features\n", + "\n", + "For more discussions of Ridge and Lasso regression, [Wessel van Wieringen's](https://arxiv.org/abs/1509.09169) article is highly recommended.\n", + "Similarly, [Mehta et al's article](https://arxiv.org/abs/1803.08823) is also recommended." + ] + }, + { + "cell_type": "markdown", + "id": "accb159e", + "metadata": { + "editable": true + }, + "source": [ + "## Regression analysis, overarching aims\n", + "\n", + "Regression modeling deals with the description of the sampling distribution of a given random variable $y$ and how it varies as function of another variable or a set of such variables $\\boldsymbol{x} =[x_0, x_1,\\dots, x_{n-1}]^T$. \n", + "The first variable is called the **dependent**, the **outcome** or the **response** variable while the set of variables $\\boldsymbol{x}$ is called the independent variable, or the predictor variable or the explanatory variable, or simply just the **inputs**. \n", + "\n", + "A regression model aims at finding a likelihood function $p(\\boldsymbol{y}\\vert \\boldsymbol{x})$ or in the more traditional sense a function $\\boldsymbol{y}(\\boldsymbol{x})$, that is the conditional distribution for $\\boldsymbol{y}$ with a given $\\boldsymbol{x}$. The estimation of $p(\\boldsymbol{y}\\vert \\boldsymbol{x})$ is made using a data set with \n", + "* $n$ cases $i = 0, 1, 2, \\dots, n-1$ \n", + "\n", + "* Response (target, dependent or outcome) variable $y_i$ with $i = 0, 1, 2, \\dots, n-1$ \n", + "\n", + "* $p$ so-called explanatory (independent or predictor or feature) variables $\\boldsymbol{x}_i=[x_{i0}, x_{i1}, \\dots, x_{ip-1}]$ with $i = 0, 1, 2, \\dots, n-1$ and explanatory variables running from $0$ to $p-1$. See below for more explicit examples. \n", + "\n", + " The goal of the regression analysis is to extract/exploit relationship between $\\boldsymbol{y}$ and $\\boldsymbol{x}$ in order to infer specific dependencies, approximations to the likelihood functions, functional relationships and to make predictions, making fits and many other things." + ] + }, + { + "cell_type": "markdown", + "id": "a92a5e51", + "metadata": { + "editable": true + }, + "source": [ + "## Regression analysis, overarching aims II\n", + "\n", + "Consider an experiment in which $p$ characteristics/features of $n$ samples are\n", + "measured. The data from this experiment, for various explanatory variables $p$ are normally represented by a matrix \n", + "$\\mathbf{X}$.\n", + "\n", + "The matrix $\\mathbf{X}$ is called the *design\n", + "matrix*. Additional information of the samples is available in the\n", + "form of $\\boldsymbol{y}$ (also as above). The variable $\\boldsymbol{y}$ is\n", + "generally referred to as the *response variable*. The aim of\n", + "regression analysis is to explain $\\boldsymbol{y}$ in terms of\n", + "$\\boldsymbol{X}$ through a functional relationship like $y_i =\n", + "f(\\mathbf{X}_{i,\\ast})$. When no prior knowledge on the form of\n", + "$f(\\cdot)$ is available, it is common to assume a linear relationship\n", + "between $\\boldsymbol{X}$ and $\\boldsymbol{y}$. This assumption gives rise to\n", + "the *linear regression model* where $\\boldsymbol{\\beta} = [\\beta_0, \\ldots,\n", + "\\beta_{p-1}]^{T}$ are the *regression parameters*. \n", + "\n", + "Linear regression gives us a set of analytical equations for the parameters $\\beta_j$." + ] + }, + { + "cell_type": "markdown", + "id": "5ae65ed4", + "metadata": { + "editable": true + }, + "source": [ + "## Examples\n", + "In order to understand the relation among the predictors (or features or properties) $p$, the set of data $n$ and the target (outcome, output etc) $\\boldsymbol{y}$,\n", + "consider the model we discussed for describing nuclear binding energies. \n", + "\n", + "There we assumed that we could parametrize the data using a polynomial approximation based on the liquid drop model.\n", + "Assuming" + ] + }, + { + "cell_type": "markdown", + "id": "687ef539", + "metadata": { + "editable": true + }, + "source": [ + "$$\n", + "BE(A) = a_0+a_1A+a_2A^{2/3}+a_3A^{-1/3}+a_4A^{-1},\n", + "$$" + ] + }, + { + "cell_type": "markdown", + "id": "9aeee4e8", + "metadata": { + "editable": true + }, + "source": [ + "we have five predictors, that is the intercept, the $A$ dependent term, the $A^{2/3}$ term and the $A^{-1/3}$ and $A^{-1}$ terms.\n", + "This gives $p=0,1,2,3,4$. Furthermore we have $n$ entries for each predictor. It means that our design matrix is a \n", + "$p\\times n$ matrix $\\boldsymbol{X}$.\n", + "\n", + "Here the predictors are based on a model we have made. A popular data set which is widely encountered in ML applications is the\n", + "so-called [credit card default data from Taiwan](https://www.sciencedirect.com/science/article/pii/S0957417407006719?via%3Dihub). The data set contains data on $n=30000$ credit card holders with predictors like gender, marital status, age, profession, education, etc. In total there are $24$ such predictors or attributes leading to a design matrix of dimensionality $24 \\times 30000$. This is however a classification problem and we will come back to it when we discuss Logistic Regression." + ] + }, + { + "cell_type": "markdown", + "id": "b387637a", + "metadata": { + "editable": true + }, + "source": [ + "## General linear models and linear algebra\n", + "Before we proceed let us study a case where we aim at fitting a set of data $\\boldsymbol{y}=[y_0,y_1,\\dots,y_{n-1}]$. We could think of these data as a result of an experiment or a complicated numerical experiment. These data are functions of a series of variables $\\boldsymbol{x}=[x_0,x_1,\\dots,x_{n-1}]$, that is $y_i = y(x_i)$ with $i=0,1,2,\\dots,n-1$. The variables $x_i$ could represent physical quantities like time, temperature, position etc. We assume that $y(x)$ is a smooth function. \n", + "\n", + "Since obtaining these data points may not be trivial, we want to use these data to fit a function which can allow us to make predictions for values of $y$ which are not in the present set. The perhaps simplest approach is to assume we can parametrize our function in terms of a polynomial of degree $n-1$ with $n$ points, that is" + ] + }, + { + "cell_type": "markdown", + "id": "ea565ad3", + "metadata": { + "editable": true + }, + "source": [ + "$$\n", + "y=y(x) \\rightarrow y(x_i)=\\tilde{y}_i+\\epsilon_i=\\sum_{j=0}^{n-1} \\beta_j x_i^j+\\epsilon_i,\n", + "$$" + ] + }, + { + "cell_type": "markdown", + "id": "3dc47fc2", + "metadata": { + "editable": true + }, + "source": [ + "where $\\epsilon_i$ is the error in our approximation." + ] + }, + { + "cell_type": "markdown", + "id": "00ea18d8", + "metadata": { + "editable": true + }, + "source": [ + "## Rewriting the fitting procedure as a linear algebra problem\n", + "For every set of values $y_i,x_i$ we have thus the corresponding set of equations" + ] + }, + { + "cell_type": "markdown", + "id": "7a125f42", + "metadata": { + "editable": true + }, + "source": [ + "$$\n", + "\\begin{align*}\n", + "y_0&=\\beta_0+\\beta_1x_0^1+\\beta_2x_0^2+\\dots+\\beta_{n-1}x_0^{n-1}+\\epsilon_0\\\\\n", + "y_1&=\\beta_0+\\beta_1x_1^1+\\beta_2x_1^2+\\dots+\\beta_{n-1}x_1^{n-1}+\\epsilon_1\\\\\n", + "y_2&=\\beta_0+\\beta_1x_2^1+\\beta_2x_2^2+\\dots+\\beta_{n-1}x_2^{n-1}+\\epsilon_2\\\\\n", + "\\dots & \\dots \\\\\n", + "y_{n-1}&=\\beta_0+\\beta_1x_{n-1}^1+\\beta_2x_{n-1}^2+\\dots+\\beta_{n-1}x_{n-1}^{n-1}+\\epsilon_{n-1}.\\\\\n", + "\\end{align*}\n", + "$$" + ] + }, + { + "cell_type": "markdown", + "id": "6709a1b0", + "metadata": { + "editable": true + }, + "source": [ + "## Rewriting the fitting procedure as a linear algebra problem, more details\n", + "Defining the vectors" + ] + }, + { + "cell_type": "markdown", + "id": "3428c3a8", + "metadata": { + "editable": true + }, + "source": [ + "$$\n", + "\\boldsymbol{y} = [y_0,y_1, y_2,\\dots, y_{n-1}]^T,\n", + "$$" + ] + }, + { + "cell_type": "markdown", + "id": "95c50e90", + "metadata": { + "editable": true + }, + "source": [ + "and" + ] + }, + { + "cell_type": "markdown", + "id": "3da4b4ce", + "metadata": { + "editable": true + }, + "source": [ + "$$\n", + "\\boldsymbol{\\beta} = [\\beta_0,\\beta_1, \\beta_2,\\dots, \\beta_{n-1}]^T,\n", + "$$" + ] + }, + { + "cell_type": "markdown", + "id": "4ba0a0a9", + "metadata": { + "editable": true + }, + "source": [ + "and" + ] + }, + { + "cell_type": "markdown", + "id": "aafd46bd", + "metadata": { + "editable": true + }, + "source": [ + "$$\n", + "\\boldsymbol{\\epsilon} = [\\epsilon_0,\\epsilon_1, \\epsilon_2,\\dots, \\epsilon_{n-1}]^T,\n", + "$$" + ] + }, + { + "cell_type": "markdown", + "id": "c45d88f2", + "metadata": { + "editable": true + }, + "source": [ + "and the design matrix" + ] + }, + { + "cell_type": "markdown", + "id": "652c12db", + "metadata": { + "editable": true + }, + "source": [ + "$$\n", + "\\boldsymbol{X}=\n", + "\\begin{bmatrix} \n", + "1& x_{0}^1 &x_{0}^2& \\dots & \\dots &x_{0}^{n-1}\\\\\n", + "1& x_{1}^1 &x_{1}^2& \\dots & \\dots &x_{1}^{n-1}\\\\\n", + "1& x_{2}^1 &x_{2}^2& \\dots & \\dots &x_{2}^{n-1}\\\\ \n", + "\\dots& \\dots &\\dots& \\dots & \\dots &\\dots\\\\\n", + "1& x_{n-1}^1 &x_{n-1}^2& \\dots & \\dots &x_{n-1}^{n-1}\\\\\n", + "\\end{bmatrix}\n", + "$$" + ] + }, + { + "cell_type": "markdown", + "id": "287eebdf", + "metadata": { + "editable": true + }, + "source": [ + "we can rewrite our equations as" + ] + }, + { + "cell_type": "markdown", + "id": "37400e70", + "metadata": { + "editable": true + }, + "source": [ + "$$\n", + "\\boldsymbol{y} = \\boldsymbol{X}\\boldsymbol{\\beta}+\\boldsymbol{\\epsilon}.\n", + "$$" + ] + }, + { + "cell_type": "markdown", + "id": "bcef14c0", + "metadata": { + "editable": true + }, + "source": [ + "The above design matrix is called a [Vandermonde matrix](https://en.wikipedia.org/wiki/Vandermonde_matrix)." + ] + }, + { + "cell_type": "markdown", + "id": "8e755bfd", + "metadata": { + "editable": true + }, + "source": [ + "## Generalizing the fitting procedure as a linear algebra problem\n", + "\n", + "We are obviously not limited to the above polynomial expansions. We\n", + "could replace the various powers of $x$ with elements of Fourier\n", + "series or instead of $x_i^j$ we could have $\\cos{(j x_i)}$ or $\\sin{(j\n", + "x_i)}$, or time series or other orthogonal functions. For every set\n", + "of values $y_i,x_i$ we can then generalize the equations to" + ] + }, + { + "cell_type": "markdown", + "id": "bf603c75", + "metadata": { + "editable": true + }, + "source": [ + "$$\n", + "\\begin{align*}\n", + "y_0&=\\beta_0x_{00}+\\beta_1x_{01}+\\beta_2x_{02}+\\dots+\\beta_{n-1}x_{0n-1}+\\epsilon_0\\\\\n", + "y_1&=\\beta_0x_{10}+\\beta_1x_{11}+\\beta_2x_{12}+\\dots+\\beta_{n-1}x_{1n-1}+\\epsilon_1\\\\\n", + "y_2&=\\beta_0x_{20}+\\beta_1x_{21}+\\beta_2x_{22}+\\dots+\\beta_{n-1}x_{2n-1}+\\epsilon_2\\\\\n", + "\\dots & \\dots \\\\\n", + "y_{i}&=\\beta_0x_{i0}+\\beta_1x_{i1}+\\beta_2x_{i2}+\\dots+\\beta_{n-1}x_{in-1}+\\epsilon_i\\\\\n", + "\\dots & \\dots \\\\\n", + "y_{n-1}&=\\beta_0x_{n-1,0}+\\beta_1x_{n-1,2}+\\beta_2x_{n-1,2}+\\dots+\\beta_{n-1}x_{n-1,n-1}+\\epsilon_{n-1}.\\\\\n", + "\\end{align*}\n", + "$$" + ] + }, + { + "cell_type": "markdown", + "id": "42abb005", + "metadata": { + "editable": true + }, + "source": [ + "**Note that we have $p=n$ here. The matrix is symmetric. This is generally not the case!**" + ] + }, + { + "cell_type": "markdown", + "id": "f79e2da7", + "metadata": { + "editable": true + }, + "source": [ + "## Generalizing the fitting procedure as a linear algebra problem\n", + "We redefine in turn the matrix $\\boldsymbol{X}$ as" + ] + }, + { + "cell_type": "markdown", + "id": "7a0b3900", + "metadata": { + "editable": true + }, + "source": [ + "$$\n", + "\\boldsymbol{X}=\n", + "\\begin{bmatrix} \n", + "x_{00}& x_{01} &x_{02}& \\dots & \\dots &x_{0,n-1}\\\\\n", + "x_{10}& x_{11} &x_{12}& \\dots & \\dots &x_{1,n-1}\\\\\n", + "x_{20}& x_{21} &x_{22}& \\dots & \\dots &x_{2,n-1}\\\\ \n", + "\\dots& \\dots &\\dots& \\dots & \\dots &\\dots\\\\\n", + "x_{n-1,0}& x_{n-1,1} &x_{n-1,2}& \\dots & \\dots &x_{n-1,n-1}\\\\\n", + "\\end{bmatrix}\n", + "$$" + ] + }, + { + "cell_type": "markdown", + "id": "7322cacc", + "metadata": { + "editable": true + }, + "source": [ + "and without loss of generality we rewrite again our equations as" + ] + }, + { + "cell_type": "markdown", + "id": "1a10a334", + "metadata": { + "editable": true + }, + "source": [ + "$$\n", + "\\boldsymbol{y} = \\boldsymbol{X}\\boldsymbol{\\beta}+\\boldsymbol{\\epsilon}.\n", + "$$" + ] + }, + { + "cell_type": "markdown", + "id": "ec1915c1", + "metadata": { + "editable": true + }, + "source": [ + "The left-hand side of this equation is kwown. Our error vector $\\boldsymbol{\\epsilon}$ and the parameter vector $\\boldsymbol{\\beta}$ are our unknow quantities. How can we obtain the optimal set of $\\beta_i$ values?" + ] + }, + { + "cell_type": "markdown", + "id": "c4fe6000", + "metadata": { + "editable": true + }, + "source": [ + "## Optimizing our parameters\n", + "We have defined the matrix $\\boldsymbol{X}$ via the equations" + ] + }, + { + "cell_type": "markdown", + "id": "41a78ecd", + "metadata": { + "editable": true + }, + "source": [ + "$$\n", + "\\begin{align*}\n", + "y_0&=\\beta_0x_{00}+\\beta_1x_{01}+\\beta_2x_{02}+\\dots+\\beta_{n-1}x_{0n-1}+\\epsilon_0\\\\\n", + "y_1&=\\beta_0x_{10}+\\beta_1x_{11}+\\beta_2x_{12}+\\dots+\\beta_{n-1}x_{1n-1}+\\epsilon_1\\\\\n", + "y_2&=\\beta_0x_{20}+\\beta_1x_{21}+\\beta_2x_{22}+\\dots+\\beta_{n-1}x_{2n-1}+\\epsilon_1\\\\\n", + "\\dots & \\dots \\\\\n", + "y_{i}&=\\beta_0x_{i0}+\\beta_1x_{i1}+\\beta_2x_{i2}+\\dots+\\beta_{n-1}x_{in-1}+\\epsilon_1\\\\\n", + "\\dots & \\dots \\\\\n", + "y_{n-1}&=\\beta_0x_{n-1,0}+\\beta_1x_{n-1,2}+\\beta_2x_{n-1,2}+\\dots+\\beta_{n-1}x_{n-1,n-1}+\\epsilon_{n-1}.\\\\\n", + "\\end{align*}\n", + "$$" + ] + }, + { + "cell_type": "markdown", + "id": "d9184930", + "metadata": { + "editable": true + }, + "source": [ + "As we noted above, we stayed with a system with the design matrix \n", + " $\\boldsymbol{X}\\in {\\mathbb{R}}^{n\\times n}$, that is we have $p=n$. For reasons to come later (algorithmic arguments) we will hereafter define \n", + "our matrix as $\\boldsymbol{X}\\in {\\mathbb{R}}^{n\\times p}$, with the predictors refering to the column numbers and the entries $n$ being the row elements." + ] + }, + { + "cell_type": "markdown", + "id": "336efd0e", + "metadata": { + "editable": true + }, + "source": [ + "## Our model for the nuclear binding energies\n", + "\n", + "In our [introductory notes](https://compphysics.github.io/MachineLearning/doc/pub/How2ReadData/html/How2ReadData.html) we looked at the so-called [liquid drop model](https://en.wikipedia.org/wiki/Semi-empirical_mass_formula). Let us remind ourselves about what we did by looking at the code.\n", + "\n", + "We restate the parts of the code we are most interested in." + ] + }, + { + "cell_type": "code", + "execution_count": 36, + "id": "d7f7ee11", + "metadata": { + "collapsed": false, + "editable": true + }, + "outputs": [], + "source": [ + "# Common imports\n", + "import numpy as np\n", + "import pandas as pd\n", + "import matplotlib.pyplot as plt\n", + "from IPython.display import display\n", + "import os\n", + "\n", + "# Where to save the figures and data files\n", + "PROJECT_ROOT_DIR = \"Results\"\n", + "FIGURE_ID = \"Results/FigureFiles\"\n", + "DATA_ID = \"DataFiles/\"\n", + "\n", + "if not os.path.exists(PROJECT_ROOT_DIR):\n", + " os.mkdir(PROJECT_ROOT_DIR)\n", + "\n", + "if not os.path.exists(FIGURE_ID):\n", + " os.makedirs(FIGURE_ID)\n", + "\n", + "if not os.path.exists(DATA_ID):\n", + " os.makedirs(DATA_ID)\n", + "\n", + "def image_path(fig_id):\n", + " return os.path.join(FIGURE_ID, fig_id)\n", + "\n", + "def data_path(dat_id):\n", + " return os.path.join(DATA_ID, dat_id)\n", + "\n", + "def save_fig(fig_id):\n", + " plt.savefig(image_path(fig_id) + \".png\", format='png')\n", + "\n", + "infile = open(data_path(\"MassEval2016.dat\"),'r')\n", + "\n", + "\n", + "# Read the experimental data with Pandas\n", + "Masses = pd.read_fwf(infile, usecols=(2,3,4,6,11),\n", + " names=('N', 'Z', 'A', 'Element', 'Ebinding'),\n", + " widths=(1,3,5,5,5,1,3,4,1,13,11,11,9,1,2,11,9,1,3,1,12,11,1),\n", + " header=39,\n", + " index_col=False)\n", + "\n", + "# Extrapolated values are indicated by '#' in place of the decimal place, so\n", + "# the Ebinding column won't be numeric. Coerce to float and drop these entries.\n", + "Masses['Ebinding'] = pd.to_numeric(Masses['Ebinding'], errors='coerce')\n", + "Masses = Masses.dropna()\n", + "# Convert from keV to MeV.\n", + "Masses['Ebinding'] /= 1000\n", + "\n", + "# Group the DataFrame by nucleon number, A.\n", + "Masses = Masses.groupby('A')\n", + "# Find the rows of the grouped DataFrame with the maximum binding energy.\n", + "Masses = Masses.apply(lambda t: t[t.Ebinding==t.Ebinding.max()])\n", + "A = Masses['A']\n", + "Z = Masses['Z']\n", + "N = Masses['N']\n", + "Element = Masses['Element']\n", + "Energies = Masses['Ebinding']\n", + "\n", + "# Now we set up the design matrix X\n", + "X = np.zeros((len(A),5))\n", + "X[:,0] = 1\n", + "X[:,1] = A\n", + "X[:,2] = A**(2.0/3.0)\n", + "X[:,3] = A**(-1.0/3.0)\n", + "X[:,4] = A**(-1.0)\n", + "# Then nice printout using pandas\n", + "DesignMatrix = pd.DataFrame(X)\n", + "DesignMatrix.index = A\n", + "DesignMatrix.columns = ['1', 'A', 'A^(2/3)', 'A^(-1/3)', '1/A']\n", + "display(DesignMatrix)" + ] + }, + { + "cell_type": "markdown", + "id": "06b3c778", + "metadata": { + "editable": true + }, + "source": [ + "With $\\boldsymbol{\\beta}\\in {\\mathbb{R}}^{p\\times 1}$, it means that we will hereafter write our equations for the approximation as" + ] + }, + { + "cell_type": "markdown", + "id": "7fd7f1a9", + "metadata": { + "editable": true + }, + "source": [ + "$$\n", + "\\boldsymbol{\\tilde{y}}= \\boldsymbol{X}\\boldsymbol{\\beta},\n", + "$$" + ] + }, + { + "cell_type": "markdown", + "id": "7a7d6f60", + "metadata": { + "editable": true + }, + "source": [ + "throughout these lectures." + ] + }, + { + "cell_type": "markdown", + "id": "dcf4259b", + "metadata": { + "editable": true + }, + "source": [ + "## Optimizing our parameters, more details\n", + "With the above we use the design matrix to define the approximation $\\boldsymbol{\\tilde{y}}$ via the unknown quantity $\\boldsymbol{\\beta}$ as" + ] + }, + { + "cell_type": "markdown", + "id": "56e2c7b1", + "metadata": { + "editable": true + }, + "source": [ + "$$\n", + "\\boldsymbol{\\tilde{y}}= \\boldsymbol{X}\\boldsymbol{\\beta},\n", + "$$" + ] + }, + { + "cell_type": "markdown", + "id": "83f24da1", + "metadata": { + "editable": true + }, + "source": [ + "and in order to find the optimal parameters $\\beta_i$ instead of solving the above linear algebra problem, we define a function which gives a measure of the spread between the values $y_i$ (which represent hopefully the exact values) and the parameterized values $\\tilde{y}_i$, namely" + ] + }, + { + "cell_type": "markdown", + "id": "3e072e07", + "metadata": { + "editable": true + }, + "source": [ + "$$\n", + "C(\\boldsymbol{\\beta})=\\frac{1}{n}\\sum_{i=0}^{n-1}\\left(y_i-\\tilde{y}_i\\right)^2=\\frac{1}{n}\\left\\{\\left(\\boldsymbol{y}-\\boldsymbol{\\tilde{y}}\\right)^T\\left(\\boldsymbol{y}-\\boldsymbol{\\tilde{y}}\\right)\\right\\},\n", + "$$" + ] + }, + { + "cell_type": "markdown", + "id": "ebb98625", + "metadata": { + "editable": true + }, + "source": [ + "or using the matrix $\\boldsymbol{X}$ and in a more compact matrix-vector notation as" + ] + }, + { + "cell_type": "markdown", + "id": "2208961c", + "metadata": { + "editable": true + }, + "source": [ + "$$\n", + "C(\\boldsymbol{\\beta})=\\frac{1}{n}\\left\\{\\left(\\boldsymbol{y}-\\boldsymbol{X}\\boldsymbol{\\beta}\\right)^T\\left(\\boldsymbol{y}-\\boldsymbol{X}\\boldsymbol{\\beta}\\right)\\right\\}.\n", + "$$" + ] + }, + { + "cell_type": "markdown", + "id": "9fe2fec2", + "metadata": { + "editable": true + }, + "source": [ + "This function is one possible way to define the so-called cost function.\n", + "\n", + "It is also common to define\n", + "the function $C$ as" + ] + }, + { + "cell_type": "markdown", + "id": "2469ff5a", + "metadata": { + "editable": true + }, + "source": [ + "$$\n", + "C(\\boldsymbol{\\beta})=\\frac{1}{2n}\\sum_{i=0}^{n-1}\\left(y_i-\\tilde{y}_i\\right)^2,\n", + "$$" + ] + }, + { + "cell_type": "markdown", + "id": "78c3608b", + "metadata": { + "editable": true + }, + "source": [ + "since when taking the first derivative with respect to the unknown parameters $\\beta$, the factor of $2$ cancels out." + ] + }, + { + "cell_type": "markdown", + "id": "724d699f", + "metadata": { + "editable": true + }, + "source": [ + "## Interpretations and optimizing our parameters\n", + "\n", + "The function" + ] + }, + { + "cell_type": "markdown", + "id": "c81e30d6", + "metadata": { + "editable": true + }, + "source": [ + "$$\n", + "C(\\boldsymbol{\\beta})=\\frac{1}{n}\\left\\{\\left(\\boldsymbol{y}-\\boldsymbol{X}\\boldsymbol{\\beta}\\right)^T\\left(\\boldsymbol{y}-\\boldsymbol{X}\\boldsymbol{\\beta}\\right)\\right\\},\n", + "$$" + ] + }, + { + "cell_type": "markdown", + "id": "b7539680", + "metadata": { + "editable": true + }, + "source": [ + "can be linked to the variance of the quantity $y_i$ if we interpret the latter as the mean value. \n", + "When linking (see the discussion below) with the maximum likelihood approach below, we will indeed interpret $y_i$ as a mean value" + ] + }, + { + "cell_type": "markdown", + "id": "35bef2fb", + "metadata": { + "editable": true + }, + "source": [ + "$$\n", + "y_{i}=\\langle y_i \\rangle = \\beta_0x_{i,0}+\\beta_1x_{i,1}+\\beta_2x_{i,2}+\\dots+\\beta_{n-1}x_{i,n-1}+\\epsilon_i,\n", + "$$" + ] + }, + { + "cell_type": "markdown", + "id": "c9ba75f2", + "metadata": { + "editable": true + }, + "source": [ + "where $\\langle y_i \\rangle$ is the mean value. Keep in mind also that\n", + "till now we have treated $y_i$ as the exact value. Normally, the\n", + "response (dependent or outcome) variable $y_i$ the outcome of a\n", + "numerical experiment or another type of experiment and is thus only an\n", + "approximation to the true value. It is then always accompanied by an\n", + "error estimate, often limited to a statistical error estimate given by\n", + "the standard deviation discussed earlier. In the discussion here we\n", + "will treat $y_i$ as our exact value for the response variable.\n", + "\n", + "In order to find the parameters $\\beta_i$ we will then minimize the spread of $C(\\boldsymbol{\\beta})$, that is we are going to solve the problem" + ] + }, + { + "cell_type": "markdown", + "id": "0de9cf54", + "metadata": { + "editable": true + }, + "source": [ + "$$\n", + "{\\displaystyle \\min_{\\boldsymbol{\\beta}\\in\n", + "{\\mathbb{R}}^{p}}}\\frac{1}{n}\\left\\{\\left(\\boldsymbol{y}-\\boldsymbol{X}\\boldsymbol{\\beta}\\right)^T\\left(\\boldsymbol{y}-\\boldsymbol{X}\\boldsymbol{\\beta}\\right)\\right\\}.\n", + "$$" + ] + }, + { + "cell_type": "markdown", + "id": "c29fc4c3", + "metadata": { + "editable": true + }, + "source": [ + "In practical terms it means we will require" + ] + }, + { + "cell_type": "markdown", + "id": "806f82d4", + "metadata": { + "editable": true + }, + "source": [ + "$$\n", + "\\frac{\\partial C(\\boldsymbol{\\beta})}{\\partial \\beta_j} = \\frac{\\partial }{\\partial \\beta_j}\\left[ \\frac{1}{n}\\sum_{i=0}^{n-1}\\left(y_i-\\beta_0x_{i,0}-\\beta_1x_{i,1}-\\beta_2x_{i,2}-\\dots-\\beta_{n-1}x_{i,n-1}\\right)^2\\right]=0,\n", + "$$" + ] + }, + { + "cell_type": "markdown", + "id": "7101ec03", + "metadata": { + "editable": true + }, + "source": [ + "which results in" + ] + }, + { + "cell_type": "markdown", + "id": "e3c91e71", + "metadata": { + "editable": true + }, + "source": [ + "$$\n", + "\\frac{\\partial C(\\boldsymbol{\\beta})}{\\partial \\beta_j} = -\\frac{2}{n}\\left[ \\sum_{i=0}^{n-1}x_{ij}\\left(y_i-\\beta_0x_{i,0}-\\beta_1x_{i,1}-\\beta_2x_{i,2}-\\dots-\\beta_{n-1}x_{i,n-1}\\right)\\right]=0,\n", + "$$" + ] + }, + { + "cell_type": "markdown", + "id": "28859238", + "metadata": { + "editable": true + }, + "source": [ + "or in a matrix-vector form as" + ] + }, + { + "cell_type": "markdown", + "id": "412d7d97", + "metadata": { + "editable": true + }, + "source": [ + "$$\n", + "\\frac{\\partial C(\\boldsymbol{\\beta})}{\\partial \\boldsymbol{\\beta}} = 0 = \\boldsymbol{X}^T\\left( \\boldsymbol{y}-\\boldsymbol{X}\\boldsymbol{\\beta}\\right).\n", + "$$" + ] + }, + { + "cell_type": "markdown", + "id": "a2d6e61f", + "metadata": { + "editable": true + }, + "source": [ + "## Interpretations and optimizing our parameters\n", + "We can rewrite" + ] + }, + { + "cell_type": "markdown", + "id": "3aab18ca", + "metadata": { + "editable": true + }, + "source": [ + "$$\n", + "\\frac{\\partial C(\\boldsymbol{\\beta})}{\\partial \\boldsymbol{\\beta}} = 0 = \\boldsymbol{X}^T\\left( \\boldsymbol{y}-\\boldsymbol{X}\\boldsymbol{\\beta}\\right),\n", + "$$" + ] + }, + { + "cell_type": "markdown", + "id": "a5d3d3d4", + "metadata": { + "editable": true + }, + "source": [ + "as" + ] + }, + { + "cell_type": "markdown", + "id": "6bc87ffc", + "metadata": { + "editable": true + }, + "source": [ + "$$\n", + "\\boldsymbol{X}^T\\boldsymbol{y} = \\boldsymbol{X}^T\\boldsymbol{X}\\boldsymbol{\\beta},\n", + "$$" + ] + }, + { + "cell_type": "markdown", + "id": "e6d26432", + "metadata": { + "editable": true + }, + "source": [ + "and if the matrix $\\boldsymbol{X}^T\\boldsymbol{X}$ is invertible we have the solution" + ] + }, + { + "cell_type": "markdown", + "id": "68315dcb", + "metadata": { + "editable": true + }, + "source": [ + "$$\n", + "\\boldsymbol{\\beta} =\\left(\\boldsymbol{X}^T\\boldsymbol{X}\\right)^{-1}\\boldsymbol{X}^T\\boldsymbol{y}.\n", + "$$" + ] + }, + { + "cell_type": "markdown", + "id": "251e4b2e", + "metadata": { + "editable": true + }, + "source": [ + "We note also that since our design matrix is defined as $\\boldsymbol{X}\\in\n", + "{\\mathbb{R}}^{n\\times p}$, the product $\\boldsymbol{X}^T\\boldsymbol{X} \\in\n", + "{\\mathbb{R}}^{p\\times p}$. In the above case we have that $p \\ll n$,\n", + "in our case $p=5$ meaning that we end up with inverting a small\n", + "$5\\times 5$ matrix. This is a rather common situation, in many cases we end up with low-dimensional\n", + "matrices to invert. The methods discussed here and for many other\n", + "supervised learning algorithms like classification with logistic\n", + "regression or support vector machines, exhibit dimensionalities which\n", + "allow for the usage of direct linear algebra methods such as **LU** decomposition or **Singular Value Decomposition** (SVD) for finding the inverse of the matrix\n", + "$\\boldsymbol{X}^T\\boldsymbol{X}$.\n", + "\n", + "**Small question**: Do you think the example we have at hand here (the nuclear binding energies) can lead to problems in inverting the matrix $\\boldsymbol{X}^T\\boldsymbol{X}$? What kind of problems can we expect?" + ] + }, + { + "cell_type": "markdown", + "id": "485307ed", + "metadata": { + "editable": true + }, + "source": [ + "## Some useful matrix and vector expressions\n", + "\n", + "See the handwritten notes at \n", + "\n", + "These notes will be discussed during one of the lectures." + ] + }, + { + "cell_type": "markdown", + "id": "9a1d8612", + "metadata": { + "editable": true + }, + "source": [ + "## Interpretations and optimizing our parameters\n", + "The residuals $\\boldsymbol{\\epsilon}$ are in turn given by" + ] + }, + { + "cell_type": "markdown", + "id": "b053306a", + "metadata": { + "editable": true + }, + "source": [ + "$$\n", + "\\boldsymbol{\\epsilon} = \\boldsymbol{y}-\\boldsymbol{\\tilde{y}} = \\boldsymbol{y}-\\boldsymbol{X}\\boldsymbol{\\beta},\n", + "$$" + ] + }, + { + "cell_type": "markdown", + "id": "6509f810", + "metadata": { + "editable": true + }, + "source": [ + "and with" + ] + }, + { + "cell_type": "markdown", + "id": "5f2b6cfb", + "metadata": { + "editable": true + }, + "source": [ + "$$\n", + "\\boldsymbol{X}^T\\left( \\boldsymbol{y}-\\boldsymbol{X}\\boldsymbol{\\beta}\\right)= 0,\n", + "$$" + ] + }, + { + "cell_type": "markdown", + "id": "d68edc03", + "metadata": { + "editable": true + }, + "source": [ + "we have" + ] + }, + { + "cell_type": "markdown", + "id": "e592d409", + "metadata": { + "editable": true + }, + "source": [ + "$$\n", + "\\boldsymbol{X}^T\\boldsymbol{\\epsilon}=\\boldsymbol{X}^T\\left( \\boldsymbol{y}-\\boldsymbol{X}\\boldsymbol{\\beta}\\right)= 0,\n", + "$$" + ] + }, + { + "cell_type": "markdown", + "id": "402a8712", + "metadata": { + "editable": true + }, + "source": [ + "meaning that the solution for $\\boldsymbol{\\beta}$ is the one which minimizes the residuals. Later we will link this with the maximum likelihood approach.\n", + "\n", + "Let us now return to our nuclear binding energies and simply code the above equations." + ] + }, + { + "cell_type": "markdown", + "id": "3297371d", + "metadata": { + "editable": true + }, + "source": [ + "## Own code for Ordinary Least Squares\n", + "\n", + "It is rather straightforward to implement the matrix inversion and obtain the parameters $\\boldsymbol{\\beta}$. After having defined the matrix $\\boldsymbol{X}$ we simply need to \n", + "write" + ] + }, + { + "cell_type": "code", + "execution_count": 37, + "id": "87fb9b2a", + "metadata": { + "collapsed": false, + "editable": true + }, + "outputs": [], + "source": [ + "# matrix inversion to find beta\n", + "beta = np.linalg.inv(X.T.dot(X)).dot(X.T).dot(Energies)\n", + "# and then make the prediction\n", + "ytilde = X @ beta" + ] + }, + { + "cell_type": "markdown", + "id": "ee24edc8", + "metadata": { + "editable": true + }, + "source": [ + "Alternatively, you can use the least squares functionality in **Numpy** as" + ] + }, + { + "cell_type": "code", + "execution_count": 38, + "id": "f3f9658c", + "metadata": { + "collapsed": false, + "editable": true + }, + "outputs": [], + "source": [ + "fit = np.linalg.lstsq(X, Energies, rcond =None)[0]\n", + "ytildenp = np.dot(fit,X.T)" + ] + }, + { + "cell_type": "markdown", + "id": "b4ed34de", + "metadata": { + "editable": true + }, + "source": [ + "And finally we plot our fit with and compare with data" + ] + }, + { + "cell_type": "code", + "execution_count": 39, + "id": "609abf77", + "metadata": { + "collapsed": false, + "editable": true + }, + "outputs": [], + "source": [ + "Masses['Eapprox'] = ytilde\n", + "# Generate a plot comparing the experimental with the fitted values values.\n", + "fig, ax = plt.subplots()\n", + "ax.set_xlabel(r'$A = N + Z$')\n", + "ax.set_ylabel(r'$E_\\mathrm{bind}\\,/\\mathrm{MeV}$')\n", + "ax.plot(Masses['A'], Masses['Ebinding'], alpha=0.7, lw=2,\n", + " label='Ame2016')\n", + "ax.plot(Masses['A'], Masses['Eapprox'], alpha=0.7, lw=2, c='m',\n", + " label='Fit')\n", + "ax.legend()\n", + "save_fig(\"Masses2016OLS\")\n", + "plt.show()" + ] + }, + { + "cell_type": "markdown", + "id": "7f3cfe27", + "metadata": { + "editable": true + }, + "source": [ + "## Adding error analysis and training set up\n", + "\n", + "We can easily test our fit by computing the $R2$ score that we discussed in connection with the functionality of **Scikit-Learn** in the introductory slides.\n", + "Since we are not using **Scikit-Learn** here we can define our own $R2$ function as" + ] + }, + { + "cell_type": "code", + "execution_count": 40, + "id": "c825f110", + "metadata": { + "collapsed": false, + "editable": true + }, + "outputs": [], + "source": [ + "def R2(y_data, y_model):\n", + " return 1 - np.sum((y_data - y_model) ** 2) / np.sum((y_data - np.mean(y_data)) ** 2)" + ] + }, + { + "cell_type": "markdown", + "id": "127f753b", + "metadata": { + "editable": true + }, + "source": [ + "and we would be using it as" + ] + }, + { + "cell_type": "code", + "execution_count": 41, + "id": "9002643d", + "metadata": { + "collapsed": false, + "editable": true + }, + "outputs": [], + "source": [ + "print(R2(Energies,ytilde))" + ] + }, + { + "cell_type": "markdown", + "id": "3c10d523", + "metadata": { + "editable": true + }, + "source": [ + "We can easily add our **MSE** score as" + ] + }, + { + "cell_type": "code", + "execution_count": 42, + "id": "b0be976a", + "metadata": { + "collapsed": false, + "editable": true + }, + "outputs": [], + "source": [ + "def MSE(y_data,y_model):\n", + " n = np.size(y_model)\n", + " return np.sum((y_data-y_model)**2)/n\n", + "\n", + "print(MSE(Energies,ytilde))" + ] + }, + { + "cell_type": "markdown", + "id": "a3c853fd", + "metadata": { + "editable": true + }, + "source": [ + "and finally the relative error as" + ] + }, + { + "cell_type": "code", + "execution_count": 43, + "id": "3e876e46", + "metadata": { + "collapsed": false, + "editable": true + }, + "outputs": [], + "source": [ + "def RelativeError(y_data,y_model):\n", + " return abs((y_data-y_model)/y_data)\n", + "print(RelativeError(Energies, ytilde))" + ] + }, + { + "cell_type": "markdown", + "id": "8bae9ae0", + "metadata": { + "editable": true + }, + "source": [ + "## The $\\chi^2$ function\n", + "\n", + "Normally, the response (dependent or outcome) variable $y_i$ is the\n", + "outcome of a numerical experiment or another type of experiment and is\n", + "thus only an approximation to the true value. It is then always\n", + "accompanied by an error estimate, often limited to a statistical error\n", + "estimate given by the standard deviation discussed earlier. In the\n", + "discussion here we will treat $y_i$ as our exact value for the\n", + "response variable.\n", + "\n", + "Introducing the standard deviation $\\sigma_i$ for each measurement\n", + "$y_i$, we define now the $\\chi^2$ function (omitting the $1/n$ term)\n", + "as" + ] + }, + { + "cell_type": "markdown", + "id": "e268fe32", + "metadata": { + "editable": true + }, + "source": [ + "$$\n", + "\\chi^2(\\boldsymbol{\\beta})=\\frac{1}{n}\\sum_{i=0}^{n-1}\\frac{\\left(y_i-\\tilde{y}_i\\right)^2}{\\sigma_i^2}=\\frac{1}{n}\\left\\{\\left(\\boldsymbol{y}-\\boldsymbol{\\tilde{y}}\\right)^T\\frac{1}{\\boldsymbol{\\Sigma^2}}\\left(\\boldsymbol{y}-\\boldsymbol{\\tilde{y}}\\right)\\right\\},\n", + "$$" + ] + }, + { + "cell_type": "markdown", + "id": "0eb0a0b8", + "metadata": { + "editable": true + }, + "source": [ + "where the matrix $\\boldsymbol{\\Sigma}$ is a diagonal matrix with $\\sigma_i$ as matrix elements." + ] + }, + { + "cell_type": "markdown", + "id": "48244140", + "metadata": { + "editable": true + }, + "source": [ + "## The $\\chi^2$ function\n", + "\n", + "In order to find the parameters $\\beta_i$ we will then minimize the spread of $\\chi^2(\\boldsymbol{\\beta})$ by requiring" + ] + }, + { + "cell_type": "markdown", + "id": "d285acf3", + "metadata": { + "editable": true + }, + "source": [ + "$$\n", + "\\frac{\\partial \\chi^2(\\boldsymbol{\\beta})}{\\partial \\beta_j} = \\frac{\\partial }{\\partial \\beta_j}\\left[ \\frac{1}{n}\\sum_{i=0}^{n-1}\\left(\\frac{y_i-\\beta_0x_{i,0}-\\beta_1x_{i,1}-\\beta_2x_{i,2}-\\dots-\\beta_{n-1}x_{i,n-1}}{\\sigma_i}\\right)^2\\right]=0,\n", + "$$" + ] + }, + { + "cell_type": "markdown", + "id": "291407cc", + "metadata": { + "editable": true + }, + "source": [ + "which results in" + ] + }, + { + "cell_type": "markdown", + "id": "b80bef46", + "metadata": { + "editable": true + }, + "source": [ + "$$\n", + "\\frac{\\partial \\chi^2(\\boldsymbol{\\beta})}{\\partial \\beta_j} = -\\frac{2}{n}\\left[ \\sum_{i=0}^{n-1}\\frac{x_{ij}}{\\sigma_i}\\left(\\frac{y_i-\\beta_0x_{i,0}-\\beta_1x_{i,1}-\\beta_2x_{i,2}-\\dots-\\beta_{n-1}x_{i,n-1}}{\\sigma_i}\\right)\\right]=0,\n", + "$$" + ] + }, + { + "cell_type": "markdown", + "id": "ad91b94e", + "metadata": { + "editable": true + }, + "source": [ + "or in a matrix-vector form as" + ] + }, + { + "cell_type": "markdown", + "id": "59d64474", + "metadata": { + "editable": true + }, + "source": [ + "$$\n", + "\\frac{\\partial \\chi^2(\\boldsymbol{\\beta})}{\\partial \\boldsymbol{\\beta}} = 0 = \\boldsymbol{A}^T\\left( \\boldsymbol{b}-\\boldsymbol{A}\\boldsymbol{\\beta}\\right).\n", + "$$" + ] + }, + { + "cell_type": "markdown", + "id": "f0f79d1c", + "metadata": { + "editable": true + }, + "source": [ + "where we have defined the matrix $\\boldsymbol{A} =\\boldsymbol{X}/\\boldsymbol{\\Sigma}$ with matrix elements $a_{ij} = x_{ij}/\\sigma_i$ and the vector $\\boldsymbol{b}$ with elements $b_i = y_i/\\sigma_i$." + ] + }, + { + "cell_type": "markdown", + "id": "a2c1adbd", + "metadata": { + "editable": true + }, + "source": [ + "## The $\\chi^2$ function\n", + "\n", + "We can rewrite" + ] + }, + { + "cell_type": "markdown", + "id": "77c55331", + "metadata": { + "editable": true + }, + "source": [ + "$$\n", + "\\frac{\\partial \\chi^2(\\boldsymbol{\\beta})}{\\partial \\boldsymbol{\\beta}} = 0 = \\boldsymbol{A}^T\\left( \\boldsymbol{b}-\\boldsymbol{A}\\boldsymbol{\\beta}\\right),\n", + "$$" + ] + }, + { + "cell_type": "markdown", + "id": "464518fe", + "metadata": { + "editable": true + }, + "source": [ + "as" + ] + }, + { + "cell_type": "markdown", + "id": "7722ff6a", + "metadata": { + "editable": true + }, + "source": [ + "$$\n", + "\\boldsymbol{A}^T\\boldsymbol{b} = \\boldsymbol{A}^T\\boldsymbol{A}\\boldsymbol{\\beta},\n", + "$$" + ] + }, + { + "cell_type": "markdown", + "id": "17a0a0bf", + "metadata": { + "editable": true + }, + "source": [ + "and if the matrix $\\boldsymbol{A}^T\\boldsymbol{A}$ is invertible we have the solution" + ] + }, + { + "cell_type": "markdown", + "id": "db0729e5", + "metadata": { + "editable": true + }, + "source": [ + "$$\n", + "\\boldsymbol{\\beta} =\\left(\\boldsymbol{A}^T\\boldsymbol{A}\\right)^{-1}\\boldsymbol{A}^T\\boldsymbol{b}.\n", + "$$" + ] + }, + { + "cell_type": "markdown", + "id": "a3342e4d", + "metadata": { + "editable": true + }, + "source": [ + "## The $\\chi^2$ function\n", + "\n", + "If we then introduce the matrix" + ] + }, + { + "cell_type": "markdown", + "id": "32797264", + "metadata": { + "editable": true + }, + "source": [ + "$$\n", + "\\boldsymbol{H} = \\left(\\boldsymbol{A}^T\\boldsymbol{A}\\right)^{-1},\n", + "$$" + ] + }, + { + "cell_type": "markdown", + "id": "6b4fa2ed", + "metadata": { + "editable": true + }, + "source": [ + "we have then the following expression for the parameters $\\beta_j$ (the matrix elements of $\\boldsymbol{H}$ are $h_{ij}$)" + ] + }, + { + "cell_type": "markdown", + "id": "91b0f90c", + "metadata": { + "editable": true + }, + "source": [ + "$$\n", + "\\beta_j = \\sum_{k=0}^{p-1}h_{jk}\\sum_{i=0}^{n-1}\\frac{y_i}{\\sigma_i}\\frac{x_{ik}}{\\sigma_i} = \\sum_{k=0}^{p-1}h_{jk}\\sum_{i=0}^{n-1}b_ia_{ik}\n", + "$$" + ] + }, + { + "cell_type": "markdown", + "id": "1788b899", + "metadata": { + "editable": true + }, + "source": [ + "We state without proof the expression for the uncertainty in the parameters $\\beta_j$ as (we leave this as an exercise)" + ] + }, + { + "cell_type": "markdown", + "id": "fbedd864", + "metadata": { + "editable": true + }, + "source": [ + "$$\n", + "\\sigma^2(\\beta_j) = \\sum_{i=0}^{n-1}\\sigma_i^2\\left( \\frac{\\partial \\beta_j}{\\partial y_i}\\right)^2,\n", + "$$" + ] + }, + { + "cell_type": "markdown", + "id": "46ced7fc", + "metadata": { + "editable": true + }, + "source": [ + "resulting in" + ] + }, + { + "cell_type": "markdown", + "id": "126581f2", + "metadata": { + "editable": true + }, + "source": [ + "$$\n", + "\\sigma^2(\\beta_j) = \\left(\\sum_{k=0}^{p-1}h_{jk}\\sum_{i=0}^{n-1}a_{ik}\\right)\\left(\\sum_{l=0}^{p-1}h_{jl}\\sum_{m=0}^{n-1}a_{ml}\\right) = h_{jj}!\n", + "$$" + ] + }, + { + "cell_type": "markdown", + "id": "22263ac1", + "metadata": { + "editable": true + }, + "source": [ + "## The $\\chi^2$ function\n", + "The first step here is to approximate the function $y$ with a first-order polynomial, that is we write" + ] + }, + { + "cell_type": "markdown", + "id": "d2f1c4bf", + "metadata": { + "editable": true + }, + "source": [ + "$$\n", + "y=y(x) \\rightarrow y(x_i) \\approx \\beta_0+\\beta_1 x_i.\n", + "$$" + ] + }, + { + "cell_type": "markdown", + "id": "3c150c12", + "metadata": { + "editable": true + }, + "source": [ + "By computing the derivatives of $\\chi^2$ with respect to $\\beta_0$ and $\\beta_1$ show that these are given by" + ] + }, + { + "cell_type": "markdown", + "id": "54c4bd59", + "metadata": { + "editable": true + }, + "source": [ + "$$\n", + "\\frac{\\partial \\chi^2(\\boldsymbol{\\beta})}{\\partial \\beta_0} = -2\\left[ \\frac{1}{n}\\sum_{i=0}^{n-1}\\left(\\frac{y_i-\\beta_0-\\beta_1x_{i}}{\\sigma_i^2}\\right)\\right]=0,\n", + "$$" + ] + }, + { + "cell_type": "markdown", + "id": "85450044", + "metadata": { + "editable": true + }, + "source": [ + "and" + ] + }, + { + "cell_type": "markdown", + "id": "f62678e4", + "metadata": { + "editable": true + }, + "source": [ + "$$\n", + "\\frac{\\partial \\chi^2(\\boldsymbol{\\beta})}{\\partial \\beta_1} = -\\frac{2}{n}\\left[ \\sum_{i=0}^{n-1}x_i\\left(\\frac{y_i-\\beta_0-\\beta_1x_{i}}{\\sigma_i^2}\\right)\\right]=0.\n", + "$$" + ] + }, + { + "cell_type": "markdown", + "id": "06216620", + "metadata": { + "editable": true + }, + "source": [ + "## The $\\chi^2$ function\n", + "\n", + "For a linear fit (a first-order polynomial) we don't need to invert a matrix!! \n", + "Defining" + ] + }, + { + "cell_type": "markdown", + "id": "48b4d612", + "metadata": { + "editable": true + }, + "source": [ + "$$\n", + "\\gamma = \\sum_{i=0}^{n-1}\\frac{1}{\\sigma_i^2},\n", + "$$" + ] + }, + { + "cell_type": "markdown", + "id": "44fe7e7a", + "metadata": { + "editable": true + }, + "source": [ + "$$\n", + "\\gamma_x = \\sum_{i=0}^{n-1}\\frac{x_{i}}{\\sigma_i^2},\n", + "$$" + ] + }, + { + "cell_type": "markdown", + "id": "989f2952", + "metadata": { + "editable": true + }, + "source": [ + "$$\n", + "\\gamma_y = \\sum_{i=0}^{n-1}\\left(\\frac{y_i}{\\sigma_i^2}\\right),\n", + "$$" + ] + }, + { + "cell_type": "markdown", + "id": "0425932f", + "metadata": { + "editable": true + }, + "source": [ + "$$\n", + "\\gamma_{xx} = \\sum_{i=0}^{n-1}\\frac{x_ix_{i}}{\\sigma_i^2},\n", + "$$" + ] + }, + { + "cell_type": "markdown", + "id": "7f095428", + "metadata": { + "editable": true + }, + "source": [ + "$$\n", + "\\gamma_{xy} = \\sum_{i=0}^{n-1}\\frac{y_ix_{i}}{\\sigma_i^2},\n", + "$$" + ] + }, + { + "cell_type": "markdown", + "id": "a37ec316", + "metadata": { + "editable": true + }, + "source": [ + "we obtain" + ] + }, + { + "cell_type": "markdown", + "id": "05921282", + "metadata": { + "editable": true + }, + "source": [ + "$$\n", + "\\beta_0 = \\frac{\\gamma_{xx}\\gamma_y-\\gamma_x\\gamma_y}{\\gamma\\gamma_{xx}-\\gamma_x^2},\n", + "$$" + ] + }, + { + "cell_type": "markdown", + "id": "147b5033", + "metadata": { + "editable": true + }, + "source": [ + "$$\n", + "\\beta_1 = \\frac{\\gamma_{xy}\\gamma-\\gamma_x\\gamma_y}{\\gamma\\gamma_{xx}-\\gamma_x^2}.\n", + "$$" + ] + }, + { + "cell_type": "markdown", + "id": "fe77ebfe", + "metadata": { + "editable": true + }, + "source": [ + "This approach (different linear and non-linear regression) suffers\n", + "often from both being underdetermined and overdetermined in the\n", + "unknown coefficients $\\beta_i$. A better approach is to use the\n", + "Singular Value Decomposition (SVD) method discussed next week." + ] + }, + { + "cell_type": "markdown", + "id": "2a2e48f9", + "metadata": { + "editable": true + }, + "source": [ + "## Fitting an Equation of State for Dense Nuclear Matter\n", + "\n", + "Before we continue, let us introduce yet another example. We are going to fit the\n", + "nuclear equation of state using results from many-body calculations.\n", + "The equation of state we have made available here, as function of\n", + "density, has been derived using modern nucleon-nucleon potentials with\n", + "[the addition of three-body\n", + "forces](https://www.sciencedirect.com/science/article/pii/S0370157399001106). This\n", + "time the file is presented as a standard **csv** file.\n", + "\n", + "The beginning of the Python code here is similar to what you have seen\n", + "before, with the same initializations and declarations. We use also\n", + "**pandas** again, rather extensively in order to organize our data.\n", + "\n", + "The difference now is that we use **Scikit-Learn's** regression tools\n", + "instead of our own matrix inversion implementation. Furthermore, we\n", + "sneak in **Ridge** regression (to be discussed below) which includes a\n", + "hyperparameter $\\lambda$, also to be explained below." + ] + }, + { + "cell_type": "markdown", + "id": "6c8cf2ea", + "metadata": { + "editable": true + }, + "source": [ + "## The code" + ] + }, + { + "cell_type": "code", + "execution_count": 44, + "id": "4b4b43d0", + "metadata": { + "collapsed": false, + "editable": true + }, + "outputs": [], + "source": [ + "# Common imports\n", + "import os\n", + "import numpy as np\n", + "import pandas as pd\n", + "import matplotlib.pyplot as plt\n", + "import matplotlib.pyplot as plt\n", + "import sklearn.linear_model as skl\n", + "from sklearn.metrics import mean_squared_error, r2_score, mean_absolute_error\n", + "\n", + "# Where to save the figures and data files\n", + "PROJECT_ROOT_DIR = \"Results\"\n", + "FIGURE_ID = \"Results/FigureFiles\"\n", + "DATA_ID = \"DataFiles/\"\n", + "\n", + "if not os.path.exists(PROJECT_ROOT_DIR):\n", + " os.mkdir(PROJECT_ROOT_DIR)\n", + "\n", + "if not os.path.exists(FIGURE_ID):\n", + " os.makedirs(FIGURE_ID)\n", + "\n", + "if not os.path.exists(DATA_ID):\n", + " os.makedirs(DATA_ID)\n", + "\n", + "def image_path(fig_id):\n", + " return os.path.join(FIGURE_ID, fig_id)\n", + "\n", + "def data_path(dat_id):\n", + " return os.path.join(DATA_ID, dat_id)\n", + "\n", + "def save_fig(fig_id):\n", + " plt.savefig(image_path(fig_id) + \".png\", format='png')\n", + "\n", + "infile = open(data_path(\"EoS.csv\"),'r')\n", + "\n", + "# Read the EoS data as csv file and organize the data into two arrays with density and energies\n", + "EoS = pd.read_csv(infile, names=('Density', 'Energy'))\n", + "EoS['Energy'] = pd.to_numeric(EoS['Energy'], errors='coerce')\n", + "EoS = EoS.dropna()\n", + "Energies = EoS['Energy']\n", + "Density = EoS['Density']\n", + "# The design matrix now as function of various polytrops\n", + "X = np.zeros((len(Density),4))\n", + "X[:,3] = Density**(4.0/3.0)\n", + "X[:,2] = Density\n", + "X[:,1] = Density**(2.0/3.0)\n", + "X[:,0] = 1\n", + "\n", + "# We use now Scikit-Learn's linear regressor and ridge regressor\n", + "# OLS part\n", + "clf = skl.LinearRegression().fit(X, Energies)\n", + "ytilde = clf.predict(X)\n", + "EoS['Eols'] = ytilde\n", + "# The mean squared error \n", + "print(\"Mean squared error: %.2f\" % mean_squared_error(Energies, ytilde))\n", + "# Explained variance score: 1 is perfect prediction \n", + "print('Variance score: %.2f' % r2_score(Energies, ytilde))\n", + "# Mean absolute error \n", + "print('Mean absolute error: %.2f' % mean_absolute_error(Energies, ytilde))\n", + "print(clf.coef_, clf.intercept_)\n", + "\n", + "# The Ridge regression with a hyperparameter lambda = 0.1\n", + "_lambda = 0.1\n", + "clf_ridge = skl.Ridge(alpha=_lambda).fit(X, Energies)\n", + "yridge = clf_ridge.predict(X)\n", + "EoS['Eridge'] = yridge\n", + "# The mean squared error \n", + "print(\"Mean squared error: %.2f\" % mean_squared_error(Energies, yridge))\n", + "# Explained variance score: 1 is perfect prediction \n", + "print('Variance score: %.2f' % r2_score(Energies, yridge))\n", + "# Mean absolute error \n", + "print('Mean absolute error: %.2f' % mean_absolute_error(Energies, yridge))\n", + "print(clf_ridge.coef_, clf_ridge.intercept_)\n", + "\n", + "fig, ax = plt.subplots()\n", + "ax.set_xlabel(r'$\\rho[\\mathrm{fm}^{-3}]$')\n", + "ax.set_ylabel(r'Energy per particle')\n", + "ax.plot(EoS['Density'], EoS['Energy'], alpha=0.7, lw=2,\n", + " label='Theoretical data')\n", + "ax.plot(EoS['Density'], EoS['Eols'], alpha=0.7, lw=2, c='m',\n", + " label='OLS')\n", + "ax.plot(EoS['Density'], EoS['Eridge'], alpha=0.7, lw=2, c='g',\n", + " label='Ridge $\\lambda = 0.1$')\n", + "ax.legend()\n", + "save_fig(\"EoSfitting\")\n", + "plt.show()" + ] + }, + { + "cell_type": "markdown", + "id": "e2a451c5", + "metadata": { + "editable": true + }, + "source": [ + "The above simple polynomial in density $\\rho$ gives an excellent fit\n", + "to the data. \n", + "\n", + "We note also that there is a small deviation between the\n", + "standard OLS and the Ridge regression at higher densities. We discuss this in more detail\n", + "below." + ] + }, + { + "cell_type": "markdown", + "id": "b59392e2", + "metadata": { + "editable": true + }, + "source": [ + "## Splitting our Data in Training and Test data\n", + "\n", + "It is normal in essentially all Machine Learning studies to split the\n", + "data in a training set and a test set (sometimes also an additional\n", + "validation set). **Scikit-Learn** has an own function for this. There\n", + "is no explicit recipe for how much data should be included as training\n", + "data and say test data. An accepted rule of thumb is to use\n", + "approximately $2/3$ to $4/5$ of the data as training data. We will\n", + "postpone a discussion of this splitting to the end of these notes and\n", + "our discussion of the so-called **bias-variance** tradeoff. Here we\n", + "limit ourselves to repeat the above equation of state fitting example\n", + "but now splitting the data into a training set and a test set." + ] + }, + { + "cell_type": "code", + "execution_count": 45, + "id": "7b909eeb", + "metadata": { + "collapsed": false, + "editable": true + }, + "outputs": [], + "source": [ + "import os\n", + "import numpy as np\n", + "import pandas as pd\n", + "import matplotlib.pyplot as plt\n", + "from sklearn.model_selection import train_test_split\n", + "# Where to save the figures and data files\n", + "PROJECT_ROOT_DIR = \"Results\"\n", + "FIGURE_ID = \"Results/FigureFiles\"\n", + "DATA_ID = \"DataFiles/\"\n", + "\n", + "if not os.path.exists(PROJECT_ROOT_DIR):\n", + " os.mkdir(PROJECT_ROOT_DIR)\n", + "\n", + "if not os.path.exists(FIGURE_ID):\n", + " os.makedirs(FIGURE_ID)\n", + "\n", + "if not os.path.exists(DATA_ID):\n", + " os.makedirs(DATA_ID)\n", + "\n", + "def image_path(fig_id):\n", + " return os.path.join(FIGURE_ID, fig_id)\n", + "\n", + "def data_path(dat_id):\n", + " return os.path.join(DATA_ID, dat_id)\n", + "\n", + "def save_fig(fig_id):\n", + " plt.savefig(image_path(fig_id) + \".png\", format='png')\n", + "\n", + "def R2(y_data, y_model):\n", + " return 1 - np.sum((y_data - y_model) ** 2) / np.sum((y_data - np.mean(y_data)) ** 2)\n", + "def MSE(y_data,y_model):\n", + " n = np.size(y_model)\n", + " return np.sum((y_data-y_model)**2)/n\n", + "\n", + "infile = open(data_path(\"EoS.csv\"),'r')\n", + "\n", + "# Read the EoS data as csv file and organized into two arrays with density and energies\n", + "EoS = pd.read_csv(infile, names=('Density', 'Energy'))\n", + "EoS['Energy'] = pd.to_numeric(EoS['Energy'], errors='coerce')\n", + "EoS = EoS.dropna()\n", + "Energies = EoS['Energy']\n", + "Density = EoS['Density']\n", + "# The design matrix now as function of various polytrops\n", + "X = np.zeros((len(Density),5))\n", + "X[:,0] = 1\n", + "X[:,1] = Density**(2.0/3.0)\n", + "X[:,2] = Density\n", + "X[:,3] = Density**(4.0/3.0)\n", + "X[:,4] = Density**(5.0/3.0)\n", + "# We split the data in test and training data\n", + "X_train, X_test, y_train, y_test = train_test_split(X, Energies, test_size=0.2)\n", + "# matrix inversion to find beta\n", + "beta = np.linalg.inv(X_train.T.dot(X_train)).dot(X_train.T).dot(y_train)\n", + "# and then make the prediction\n", + "ytilde = X_train @ beta\n", + "print(\"Training R2\")\n", + "print(R2(y_train,ytilde))\n", + "print(\"Training MSE\")\n", + "print(MSE(y_train,ytilde))\n", + "ypredict = X_test @ beta\n", + "print(\"Test R2\")\n", + "print(R2(y_test,ypredict))\n", + "print(\"Test MSE\")\n", + "print(MSE(y_test,ypredict))" + ] + }, + { + "cell_type": "markdown", + "id": "bec3ce40", + "metadata": { + "editable": true + }, + "source": [ + "## Exercises\n", + "\n", + "Here are three possible exercises for week 34" + ] + }, + { + "cell_type": "markdown", + "id": "a321d502", + "metadata": { + "editable": true + }, + "source": [ + "## Exercise 1: Setting up various Python environments\n", + "\n", + "The first exercise here is of a mere technical art. We want you to have \n", + "* git as a version control software and to establish a user account on a provider like GitHub. Other providers like GitLab etc are equally fine. You can also use the University of Oslo [GitHub facilities](https://www.uio.no/tjenester/it/maskin/filer/versjonskontroll/github.html). \n", + "\n", + "* Install various Python packages\n", + "\n", + "We will make extensive use of Python as programming language and its\n", + "myriad of available libraries. You will find\n", + "IPython/Jupyter notebooks invaluable in your work. You can run **R**\n", + "codes in the Jupyter/IPython notebooks, with the immediate benefit of\n", + "visualizing your data. You can also use compiled languages like C++,\n", + "Rust, Fortran etc if you prefer. The focus in these lectures will be\n", + "on Python.\n", + "\n", + "If you have Python installed (we recommend Python3) and you feel\n", + "pretty familiar with installing different packages, we recommend that\n", + "you install the following Python packages via **pip** as \n", + "\n", + "1. pip install numpy scipy matplotlib ipython scikit-learn sympy pandas pillow \n", + "\n", + "For **Tensorflow**, we recommend following the instructions in the text of \n", + "[Aurelien Geron, Hands‑On Machine Learning with Scikit‑Learn and TensorFlow, O'Reilly](http://shop.oreilly.com/product/0636920052289.do)\n", + "\n", + "We will come back to **tensorflow** later. \n", + "\n", + "For Python3, replace **pip** with **pip3**.\n", + "\n", + "For OSX users we recommend, after having installed Xcode, to\n", + "install **brew**. Brew allows for a seamless installation of additional\n", + "software via for example \n", + "\n", + "1. brew install python3\n", + "\n", + "For Linux users, with its variety of distributions like for example the widely popular Ubuntu distribution,\n", + "you can use **pip** as well and simply install Python as \n", + "\n", + "1. sudo apt-get install python3 (or python for Python2.7)\n", + "\n", + "If you don't want to perform these operations separately and venture\n", + "into the hassle of exploring how to set up dependencies and paths, we\n", + "recommend two widely used distrubutions which set up all relevant\n", + "dependencies for Python, namely \n", + "\n", + "* [Anaconda](https://docs.anaconda.com/), \n", + "\n", + "which is an open source\n", + "distribution of the Python and R programming languages for large-scale\n", + "data processing, predictive analytics, and scientific computing, that\n", + "aims to simplify package management and deployment. Package versions\n", + "are managed by the package management system **conda**. \n", + "\n", + "* [Enthought canopy](https://www.enthought.com/product/canopy/) \n", + "\n", + "is a Python\n", + "distribution for scientific and analytic computing distribution and\n", + "analysis environment, available for free and under a commercial\n", + "license.\n", + "\n", + "We recommend using **Anaconda** if you are not too familiar with setting paths in a terminal environment." + ] + }, + { + "cell_type": "markdown", + "id": "759fda61", + "metadata": { + "editable": true + }, + "source": [ + "## Exercise 2: making your own data and exploring scikit-learn\n", + "\n", + "We will generate our own dataset for a function $y(x)$ where $x \\in [0,1]$ and defined by random numbers computed with the uniform distribution. The function $y$ is a quadratic polynomial in $x$ with added stochastic noise according to the normal distribution $\\cal {N}(0,1)$.\n", + "The following simple Python instructions define our $x$ and $y$ values (with 100 data points)." + ] + }, + { + "cell_type": "code", + "execution_count": 46, + "id": "93284b25", + "metadata": { + "collapsed": false, + "editable": true + }, + "outputs": [], + "source": [ + "x = np.random.rand(100,1)\n", + "y = 2.0+5*x*x+0.1*np.random.randn(100,1)" + ] + }, + { + "cell_type": "markdown", + "id": "a3388ab9", + "metadata": { + "editable": true + }, + "source": [ + "1. Write your own code (following the examples under the [regression notes](https://compphysics.github.io/MachineLearning/doc/LectureNotes/_build/html/chapter1.html)) for computing the parametrization of the data set fitting a second-order polynomial. \n", + "\n", + "2. Use thereafter **scikit-learn** (see again the examples in the regression slides) and compare with your own code. \n", + "\n", + "3. Using scikit-learn, compute also the mean square error, a risk metric corresponding to the expected value of the squared (quadratic) error defined as" + ] + }, + { + "cell_type": "markdown", + "id": "985f07fa", + "metadata": { + "editable": true + }, + "source": [ + "$$\n", + "MSE(\\boldsymbol{y},\\boldsymbol{\\tilde{y}}) = \\frac{1}{n}\n", + "\\sum_{i=0}^{n-1}(y_i-\\tilde{y}_i)^2,\n", + "$$" + ] + }, + { + "cell_type": "markdown", + "id": "65ca73e3", + "metadata": { + "editable": true + }, + "source": [ + "and the $R^2$ score function.\n", + "If $\\tilde{\\boldsymbol{y}}_i$ is the predicted value of the $i-th$ sample and $y_i$ is the corresponding true value, then the score $R^2$ is defined as" + ] + }, + { + "cell_type": "markdown", + "id": "97ccbc96", + "metadata": { + "editable": true + }, + "source": [ + "$$\n", + "R^2(\\boldsymbol{y}, \\tilde{\\boldsymbol{y}}) = 1 - \\frac{\\sum_{i=0}^{n - 1} (y_i - \\tilde{y}_i)^2}{\\sum_{i=0}^{n - 1} (y_i - \\bar{y})^2},\n", + "$$" + ] + }, + { + "cell_type": "markdown", + "id": "0e7404ee", + "metadata": { + "editable": true + }, + "source": [ + "where we have defined the mean value of $\\boldsymbol{y}$ as" + ] + }, + { + "cell_type": "markdown", + "id": "64aed9c5", + "metadata": { + "editable": true + }, + "source": [ + "$$\n", + "\\bar{y} = \\frac{1}{n} \\sum_{i=0}^{n - 1} y_i.\n", + "$$" + ] + }, + { + "cell_type": "markdown", + "id": "e0a3bdb2", + "metadata": { + "editable": true + }, + "source": [ + "You can use the functionality included in scikit-learn. If you feel for it, you can use your own program and define functions which compute the above two functions. \n", + "Discuss the meaning of these results. Try also to vary the coefficient in front of the added stochastic noise term and discuss the quality of the fits." + ] + }, + { + "cell_type": "markdown", + "id": "4ef8be54", + "metadata": { + "editable": true + }, + "source": [ + "## Exercise 3: Split data in test and training data\n", + "\n", + "In this exercise we want you to to compute the MSE for the training\n", + "data and the test data as function of the complexity of a polynomial,\n", + "that is the degree of a given polynomial.\n", + "\n", + "The aim is to reproduce Figure 2.11 of [Hastie et al](https://github.com/CompPhysics/MLErasmus/blob/master/doc/Textbooks/elementsstat.pdf).\n", + "\n", + "Our data is defined by $x\\in [-3,3]$ with a total of for example $n=100$ data points. You should try to vary the number of data points $n$ in your analysis." + ] + }, + { + "cell_type": "code", + "execution_count": 47, + "id": "5283ee66", + "metadata": { + "collapsed": false, + "editable": true + }, + "outputs": [], + "source": [ + "np.random.seed()\n", + "n = 100\n", + "# Make data set.\n", + "x = np.linspace(-3, 3, n).reshape(-1, 1)\n", + "y = np.exp(-x**2) + 1.5 * np.exp(-(x-2)**2)+ np.random.normal(0, 0.1, x.shape)" + ] + }, + { + "cell_type": "markdown", + "id": "f275d73e", + "metadata": { + "editable": true + }, + "source": [ + "where $y$ is the function we want to fit with a given polynomial." + ] + }, + { + "cell_type": "markdown", + "id": "e2f0b55f", + "metadata": { + "editable": true + }, + "source": [ + "**a)**\n", + "Write a first code which sets up a design matrix $X$ defined by a fifth-order polynomial and split your data set in training and test data." + ] + }, + { + "cell_type": "markdown", + "id": "5b01468f", + "metadata": { + "editable": true + }, + "source": [ + "**b)**\n", + "Write thereafter (using either **scikit-learn** or your matrix inversion code using for example **numpy**)\n", + "and perform an ordinary least squares fitting and compute the mean squared error for the training data and the test data. These calculations should apply to a model given by a fifth-order polynomial." + ] + }, + { + "cell_type": "markdown", + "id": "5af2c631", + "metadata": { + "editable": true + }, + "source": [ + "**c)**\n", + "Add now a model which allows you to make polynomials up to degree $15$. Perform a standard OLS fitting of the training data and compute the MSE for the training and test data and plot both test and training data MSE as functions of the polynomial degree. Compare what you see with Figure 2.11 of Hastie et al. Comment your results. For which polynomial degree do you find an optimal MSE (smallest value)?" + ] + } + ], + "metadata": {}, + "nbformat": 4, + "nbformat_minor": 5 +} diff --git a/doc/LectureNotes/week35.ipynb b/doc/LectureNotes/week35.ipynb new file mode 100644 index 000000000..40b6c66a9 --- /dev/null +++ b/doc/LectureNotes/week35.ipynb @@ -0,0 +1,6038 @@ +{ + "cells": [ + { + "cell_type": "markdown", + "id": "ea977b24", + "metadata": { + "editable": true + }, + "source": [ + "\n", + "" + ] + }, + { + "cell_type": "markdown", + "id": "a247218b", + "metadata": { + "editable": true + }, + "source": [ + "# Week 35: From Ordinary Linear Regression to Ridge and Lasso Regression\n", + "**Morten Hjorth-Jensen**, Department of Physics, University of Oslo and Department of Physics and Astronomy and National Superconducting Cyclotron Laboratory, Michigan State University\n", + "\n", + "Date: **August 26-30**" + ] + }, + { + "cell_type": "markdown", + "id": "f234b76d", + "metadata": { + "editable": true + }, + "source": [ + "## Plans for week 35\n", + "\n", + "The main topics are:\n", + "\n", + "1. Brief repetition from last week\n", + "\n", + "2. Derivation of the equations for ordinary least squares\n", + "\n", + "3. Discussion on how to prepare data and examples of applications of linear regression\n", + "\n", + "4. Material for the lecture on Monday: Mathematical interpretations of linear regression\n", + "\n", + "5. Monday: Ridge and Lasso regression and Singular Value Decomposition" + ] + }, + { + "cell_type": "markdown", + "id": "86d0671f", + "metadata": { + "editable": true + }, + "source": [ + "### Reading recommendations:\n", + "\n", + "1. See lecture notes for week 35 at \n", + "\n", + "2. Goodfellow, Bengio and Courville, Deep Learning, chapter 2 on linear algebra and sections 3.1-3.10 on elements of statistics (background)" + ] + }, + { + "cell_type": "markdown", + "id": "0b0bc0ec", + "metadata": { + "editable": true + }, + "source": [ + "## Why Linear Regression (aka Ordinary Least Squares and family), repeat from last week\n", + "\n", + "We need first a reminder from last week about linear regression. \n", + "\n", + "Fitting a continuous function with linear parameterization in terms of the parameters $\\boldsymbol{\\beta}$.\n", + "* Method of choice for fitting a continuous function!\n", + "\n", + "* Gives an excellent introduction to central Machine Learning features with **understandable pedagogical** links to other methods like **Neural Networks**, **Support Vector Machines** etc\n", + "\n", + "* Analytical expression for the fitting parameters $\\boldsymbol{\\beta}$\n", + "\n", + "* Analytical expressions for statistical propertiers like mean values, variances, confidence intervals and more\n", + "\n", + "* Analytical relation with probabilistic interpretations \n", + "\n", + "* Easy to introduce basic concepts like bias-variance tradeoff, cross-validation, resampling and regularization techniques and many other ML topics\n", + "\n", + "* Easy to code! And links well with classification problems and logistic regression and neural networks\n", + "\n", + "* Allows for **easy** hands-on understanding of gradient descent methods\n", + "\n", + "* and many more features\n", + "\n", + "For more discussions of Ridge and Lasso regression, [Wessel van Wieringen's](https://arxiv.org/abs/1509.09169) article is highly recommended.\n", + "Similarly, [Mehta et al's article](https://arxiv.org/abs/1803.08823) is also recommended." + ] + }, + { + "cell_type": "markdown", + "id": "c30cfd06", + "metadata": { + "editable": true + }, + "source": [ + "## The equations for ordinary least squares\n", + "\n", + "Our data which we want to apply a machine learning method on, consist\n", + "of a set of inputs $\\boldsymbol{x}^T=[x_0,x_1,x_2,\\dots,x_{n-1}]$ and the\n", + "outputs we want to model $\\boldsymbol{y}^T=[y_0,y_1,y_2,\\dots,y_{n-1}]$.\n", + "We assume that the output data can be represented (for a regression case) by a continuous function $f$\n", + "through" + ] + }, + { + "cell_type": "markdown", + "id": "59d6452b", + "metadata": { + "editable": true + }, + "source": [ + "$$\n", + "y_i=f(x_i)+\\epsilon_i,\n", + "$$" + ] + }, + { + "cell_type": "markdown", + "id": "8649d84d", + "metadata": { + "editable": true + }, + "source": [ + "or in general" + ] + }, + { + "cell_type": "markdown", + "id": "aaa65f06", + "metadata": { + "editable": true + }, + "source": [ + "$$\n", + "\\boldsymbol{y}=f(\\boldsymbol{x})+\\boldsymbol{\\epsilon},\n", + "$$" + ] + }, + { + "cell_type": "markdown", + "id": "cc43802e", + "metadata": { + "editable": true + }, + "source": [ + "where $\\boldsymbol{\\epsilon}$ represents some noise which is normally assumed to\n", + "be distributed via a normal probability distribution with zero mean\n", + "value and a variance $\\sigma^2$.\n", + "\n", + "In linear regression we approximate the unknown function with another\n", + "continuous function $\\tilde{\\boldsymbol{y}}(\\boldsymbol{x})$ which depends linearly on\n", + "some unknown parameters\n", + "$\\boldsymbol{\\beta}^T=[\\beta_0,\\beta_1,\\beta_2,\\dots,\\beta_{p-1}]$.\n", + "\n", + "Last week we introduced the so-called design matrix in order to define\n", + "the approximation $\\boldsymbol{\\tilde{y}}$ via the unknown quantity\n", + "$\\boldsymbol{\\beta}$ as" + ] + }, + { + "cell_type": "markdown", + "id": "53877600", + "metadata": { + "editable": true + }, + "source": [ + "$$\n", + "\\boldsymbol{\\tilde{y}}= \\boldsymbol{X}\\boldsymbol{\\beta},\n", + "$$" + ] + }, + { + "cell_type": "markdown", + "id": "bc4478fc", + "metadata": { + "editable": true + }, + "source": [ + "and in order to find the optimal parameters $\\beta_i$ we defined a function which\n", + "gives a measure of the spread between the values $y_i$ (which\n", + "represent the output values we want to reproduce) and the parametrized\n", + "values $\\tilde{y}_i$, namely the so-called cost/loss function." + ] + }, + { + "cell_type": "markdown", + "id": "64bc2ac2", + "metadata": { + "editable": true + }, + "source": [ + "## The cost/loss function\n", + "\n", + "We used the mean squared error to define the way we measure the quality of our model" + ] + }, + { + "cell_type": "markdown", + "id": "d7b7d1d1", + "metadata": { + "editable": true + }, + "source": [ + "$$\n", + "C(\\boldsymbol{\\beta})=\\frac{1}{n}\\sum_{i=0}^{n-1}\\left(y_i-\\tilde{y}_i\\right)^2=\\frac{1}{n}\\left\\{\\left(\\boldsymbol{y}-\\boldsymbol{\\tilde{y}}\\right)^T\\left(\\boldsymbol{y}-\\boldsymbol{\\tilde{y}}\\right)\\right\\},\n", + "$$" + ] + }, + { + "cell_type": "markdown", + "id": "f34563f6", + "metadata": { + "editable": true + }, + "source": [ + "or using the matrix $\\boldsymbol{X}$ and in a more compact matrix-vector notation as" + ] + }, + { + "cell_type": "markdown", + "id": "1dbad69a", + "metadata": { + "editable": true + }, + "source": [ + "$$\n", + "C(\\boldsymbol{\\beta})=\\frac{1}{n}\\left\\{\\left(\\boldsymbol{y}-\\boldsymbol{X}\\boldsymbol{\\beta}\\right)^T\\left(\\boldsymbol{y}-\\boldsymbol{X}\\boldsymbol{\\beta}\\right)\\right\\}.\n", + "$$" + ] + }, + { + "cell_type": "markdown", + "id": "2a16de00", + "metadata": { + "editable": true + }, + "source": [ + "This function represents one of many possible ways to define the so-called cost function.\n", + "\n", + "It is also common to define\n", + "the function $C$ as" + ] + }, + { + "cell_type": "markdown", + "id": "07115e56", + "metadata": { + "editable": true + }, + "source": [ + "$$\n", + "C(\\boldsymbol{\\beta})=\\frac{1}{2n}\\sum_{i=0}^{n-1}\\left(y_i-\\tilde{y}_i\\right)^2,\n", + "$$" + ] + }, + { + "cell_type": "markdown", + "id": "b90655a4", + "metadata": { + "editable": true + }, + "source": [ + "since when taking the first derivative with respect to the unknown parameters $\\beta$, the factor of $2$ cancels out." + ] + }, + { + "cell_type": "markdown", + "id": "2ac208f1", + "metadata": { + "editable": true + }, + "source": [ + "## Interpretations and optimizing our parameters\n", + "\n", + "The function" + ] + }, + { + "cell_type": "markdown", + "id": "a8197640", + "metadata": { + "editable": true + }, + "source": [ + "$$\n", + "C(\\boldsymbol{\\beta})=\\frac{1}{n}\\left\\{\\left(\\boldsymbol{y}-\\boldsymbol{X}\\boldsymbol{\\beta}\\right)^T\\left(\\boldsymbol{y}-\\boldsymbol{X}\\boldsymbol{\\beta}\\right)\\right\\},\n", + "$$" + ] + }, + { + "cell_type": "markdown", + "id": "7c72baae", + "metadata": { + "editable": true + }, + "source": [ + "can be linked to the variance of the quantity $y_i$ if we interpret the latter as the mean value. \n", + "When linking (see the discussions next week) with the maximum likelihood approach below, we will indeed interpret $y_i$ as a mean value" + ] + }, + { + "cell_type": "markdown", + "id": "3c595093", + "metadata": { + "editable": true + }, + "source": [ + "$$\n", + "y_{i}=\\langle y_i \\rangle = \\beta_0x_{i,0}+\\beta_1x_{i,1}+\\beta_2x_{i,2}+\\dots+\\beta_{n-1}x_{i,n-1}+\\epsilon_i,\n", + "$$" + ] + }, + { + "cell_type": "markdown", + "id": "4dab1f87", + "metadata": { + "editable": true + }, + "source": [ + "where $\\langle y_i \\rangle$ is the mean value. Keep in mind also that\n", + "till now we have treated $y_i$ as the exact value. Normally, the\n", + "response (dependent or outcome) variable $y_i$ is the outcome of a\n", + "numerical experiment or another type of experiment and could thus be treated itself as an\n", + "approximation to the true value. It is then always accompanied by an\n", + "error estimate, often limited to a statistical error estimate given by\n", + "the standard deviation discussed earlier. In the discussion here we\n", + "will treat $y_i$ as our exact value for the response variable.\n", + "\n", + "In order to find the parameters $\\beta_i$ we will then minimize the spread of $C(\\boldsymbol{\\beta})$, that is we are going to solve the problem" + ] + }, + { + "cell_type": "markdown", + "id": "2a85bd46", + "metadata": { + "editable": true + }, + "source": [ + "$$\n", + "{\\displaystyle \\min_{\\boldsymbol{\\beta}\\in\n", + "{\\mathbb{R}}^{p}}}\\frac{1}{n}\\left\\{\\left(\\boldsymbol{y}-\\boldsymbol{X}\\boldsymbol{\\beta}\\right)^T\\left(\\boldsymbol{y}-\\boldsymbol{X}\\boldsymbol{\\beta}\\right)\\right\\}.\n", + "$$" + ] + }, + { + "cell_type": "markdown", + "id": "5500dd61", + "metadata": { + "editable": true + }, + "source": [ + "In practical terms it means we will require" + ] + }, + { + "cell_type": "markdown", + "id": "0072db82", + "metadata": { + "editable": true + }, + "source": [ + "$$\n", + "\\frac{\\partial C(\\boldsymbol{\\beta})}{\\partial \\beta_j} = \\frac{\\partial }{\\partial \\beta_j}\\left[ \\frac{1}{n}\\sum_{i=0}^{n-1}\\left(y_i-\\beta_0x_{i,0}-\\beta_1x_{i,1}-\\beta_2x_{i,2}-\\dots-\\beta_{n-1}x_{i,n-1}\\right)^2\\right]=0,\n", + "$$" + ] + }, + { + "cell_type": "markdown", + "id": "078ec23d", + "metadata": { + "editable": true + }, + "source": [ + "which results in" + ] + }, + { + "cell_type": "markdown", + "id": "cc1760bc", + "metadata": { + "editable": true + }, + "source": [ + "$$\n", + "\\frac{\\partial C(\\boldsymbol{\\beta})}{\\partial \\beta_j} = -\\frac{2}{n}\\left[ \\sum_{i=0}^{n-1}x_{ij}\\left(y_i-\\beta_0x_{i,0}-\\beta_1x_{i,1}-\\beta_2x_{i,2}-\\dots-\\beta_{n-1}x_{i,n-1}\\right)\\right]=0,\n", + "$$" + ] + }, + { + "cell_type": "markdown", + "id": "73d00905", + "metadata": { + "editable": true + }, + "source": [ + "or in a matrix-vector form as (multiplying away the factor $-2/n$, see derivation below)" + ] + }, + { + "cell_type": "markdown", + "id": "50dff40b", + "metadata": { + "editable": true + }, + "source": [ + "$$\n", + "\\frac{\\partial C(\\boldsymbol{\\beta})}{\\partial \\boldsymbol{\\beta}^T} = 0 = \\boldsymbol{X}^T\\left( \\boldsymbol{y}-\\boldsymbol{X}\\boldsymbol{\\beta}\\right).\n", + "$$" + ] + }, + { + "cell_type": "markdown", + "id": "622bf5f5", + "metadata": { + "editable": true + }, + "source": [ + "## Interpretations and optimizing our parameters\n", + "We can rewrite, see the derivations below," + ] + }, + { + "cell_type": "markdown", + "id": "48bfcf85", + "metadata": { + "editable": true + }, + "source": [ + "$$\n", + "\\frac{\\partial C(\\boldsymbol{\\beta})}{\\partial \\boldsymbol{\\beta}^T} = 0 = \\boldsymbol{X}^T\\left( \\boldsymbol{y}-\\boldsymbol{X}\\boldsymbol{\\beta}\\right),\n", + "$$" + ] + }, + { + "cell_type": "markdown", + "id": "07c395fe", + "metadata": { + "editable": true + }, + "source": [ + "as" + ] + }, + { + "cell_type": "markdown", + "id": "d3ccdcb0", + "metadata": { + "editable": true + }, + "source": [ + "$$\n", + "\\boldsymbol{X}^T\\boldsymbol{y} = \\boldsymbol{X}^T\\boldsymbol{X}\\boldsymbol{\\beta},\n", + "$$" + ] + }, + { + "cell_type": "markdown", + "id": "c1ef9741", + "metadata": { + "editable": true + }, + "source": [ + "and if the matrix $\\boldsymbol{X}^T\\boldsymbol{X}$ is invertible we have the solution" + ] + }, + { + "cell_type": "markdown", + "id": "1646a521", + "metadata": { + "editable": true + }, + "source": [ + "$$\n", + "\\boldsymbol{\\beta} =\\left(\\boldsymbol{X}^T\\boldsymbol{X}\\right)^{-1}\\boldsymbol{X}^T\\boldsymbol{y}.\n", + "$$" + ] + }, + { + "cell_type": "markdown", + "id": "daa11d84", + "metadata": { + "editable": true + }, + "source": [ + "We note also that since our design matrix is defined as $\\boldsymbol{X}\\in\n", + "{\\mathbb{R}}^{n\\times p}$, the product $\\boldsymbol{X}^T\\boldsymbol{X} \\in\n", + "{\\mathbb{R}}^{p\\times p}$. In most cases we have that $p \\ll n$. In our example case below we have $p=5$ meaning. We end up with inverting a small\n", + "$5\\times 5$ matrix. This is a rather common situation, in many cases we end up with low-dimensional\n", + "matrices to invert. The methods discussed here and for many other\n", + "supervised learning algorithms like classification with logistic\n", + "regression or support vector machines, exhibit dimensionalities which\n", + "allow for the usage of direct linear algebra methods such as **LU** decomposition or **Singular Value Decomposition** (SVD) for finding the inverse of the matrix\n", + "$\\boldsymbol{X}^T\\boldsymbol{X}$. This is discussed on Thursday this week.\n", + "\n", + "**Small question**: Do you think the example we have at hand here (the nuclear binding energies) can lead to problems in inverting the matrix $\\boldsymbol{X}^T\\boldsymbol{X}$? What kind of problems can we expect?" + ] + }, + { + "cell_type": "markdown", + "id": "78b271ce", + "metadata": { + "editable": true + }, + "source": [ + "## Some useful matrix and vector expressions\n", + "\n", + "The following matrix and vector relation will be useful here and for\n", + "the rest of the course. Vectors are always written as boldfaced lower\n", + "case letters and matrices as upper case boldfaced letters. In the\n", + "following we will discuss how to calculate derivatives of various\n", + "matrices relevant for machine learning. We will often represent our\n", + "data in terms of matrices and vectors.\n", + "\n", + "Let us introduce first some conventions. We assume that $\\boldsymbol{y}$ is a\n", + "vector of length $m$, that is it has $m$ elements $y_0,y_1,\\dots,\n", + "y_{m-1}$. By convention we start labeling vectors with the zeroth\n", + "element, as are arrays in Python and C++/C, for example. Similarly, we\n", + "have a vector $\\boldsymbol{x}$ of length $n$, that is\n", + "$\\boldsymbol{x}^T=[x_0,x_1,\\dots, x_{n-1}]$.\n", + "\n", + "We assume also that $\\boldsymbol{y}$ is a function of $\\boldsymbol{x}$ through some\n", + "given function $f$" + ] + }, + { + "cell_type": "markdown", + "id": "9482d4e6", + "metadata": { + "editable": true + }, + "source": [ + "$$\n", + "\\boldsymbol{y}=f(\\boldsymbol{x}).\n", + "$$" + ] + }, + { + "cell_type": "markdown", + "id": "c7787334", + "metadata": { + "editable": true + }, + "source": [ + "## The Jacobian\n", + "\n", + "We define the partial derivatives of the various components of $\\boldsymbol{y}$ as functions of $x_i$ in terms of the so-called [Jacobian matrix](https://en.wikipedia.org/wiki/Jacobian_matrix_and_determinant)" + ] + }, + { + "cell_type": "markdown", + "id": "a7c6c6e4", + "metadata": { + "editable": true + }, + "source": [ + "$$\n", + "\\boldsymbol{J}=\\frac{\\partial \\boldsymbol{y}}{\\partial \\boldsymbol{x}}=\\begin{bmatrix} \\frac{\\partial y_0}{\\partial x_0} & \\frac{\\partial y_0}{\\partial x_1} & \\frac{\\partial y_0}{\\partial x_2} & \\dots & \\dots & \\frac{\\partial y_0}{\\partial x_{n-1}} \\\\ \\frac{\\partial y_1}{\\partial x_0} & \\frac{\\partial y_1}{\\partial x_1} & \\frac{\\partial y_1}{\\partial x_2} & \\dots & \\dots & \\frac{\\partial y_1}{\\partial x_{n-1}} \\\\\n", + "\\frac{\\partial y_2}{\\partial x_0} & \\frac{\\partial y_2}{\\partial x_1} & \\frac{\\partial y_2}{\\partial x_2} & \\dots & \\dots & \\frac{\\partial y_2}{\\partial x_{n-1}} \\\\\n", + "\\dots & \\dots & \\dots & \\dots & \\dots & \\dots \\\\\n", + "\\dots & \\dots & \\dots & \\dots & \\dots & \\dots \\\\\n", + "\\frac{\\partial y_{m-1}}{\\partial x_0} & \\frac{\\partial y_{m-1}}{\\partial x_1} & \\frac{\\partial y_{m-1}}{\\partial x_2} & \\dots & \\dots & \\frac{\\partial y_{m-1}}{\\partial x_{n-1}} \\end{bmatrix},\n", + "$$" + ] + }, + { + "cell_type": "markdown", + "id": "dc9f4b6f", + "metadata": { + "editable": true + }, + "source": [ + "which is an $m\\times n$ matrix. If $\\boldsymbol{x}$ is a scalar, then the\n", + "Jacobian is only a single-column vector, or an $m\\times 1$ matrix. If\n", + "on the other hand $\\boldsymbol{y}$ is a scalar, the Jacobian becomes a\n", + "$1\\times n$ matrix.\n", + "\n", + "When this matrix is a square matrix $m=n$, its determinant is often referred to as the Jacobian\n", + "determinant. Both the matrix and (if $m=n$) the determinant are\n", + "often referred to simply as the Jacobian. The Jacobian matrix represents the differential of $\\boldsymbol{y}$ at every point where the\n", + "vector is differentiable." + ] + }, + { + "cell_type": "markdown", + "id": "dbb092e9", + "metadata": { + "editable": true + }, + "source": [ + "## Derivatives, example 1\n", + "\n", + "Let now $\\boldsymbol{y}=\\boldsymbol{A}\\boldsymbol{x}$, where $\\boldsymbol{A}$ is an $m\\times n$ matrix and the matrix does not depend on $\\boldsymbol{x}$. If we write out the vector $\\boldsymbol{y}$ compoment by component we have" + ] + }, + { + "cell_type": "markdown", + "id": "47f695d0", + "metadata": { + "editable": true + }, + "source": [ + "$$\n", + "y_i = \\sum_{j=0}^{n-1}a_{ij}x_j,\n", + "$$" + ] + }, + { + "cell_type": "markdown", + "id": "6ff6f849", + "metadata": { + "editable": true + }, + "source": [ + "with $\\forall i=0,1,2,\\dots,m-1$. The individual matrix elements of $\\boldsymbol{A}$ are given by the symbol $a_{ij}$.\n", + "It follows that the partial derivatives of $y_i$ with respect to $x_k$" + ] + }, + { + "cell_type": "markdown", + "id": "3fab9d8e", + "metadata": { + "editable": true + }, + "source": [ + "$$\n", + "\\frac{\\partial y_i }{\\partial x_k}= a_{ik} \\forall i=0,1,2,\\dots,m-1.\n", + "$$" + ] + }, + { + "cell_type": "markdown", + "id": "230d417b", + "metadata": { + "editable": true + }, + "source": [ + "From this we have, using the definition of the Jacobian" + ] + }, + { + "cell_type": "markdown", + "id": "ae3eea03", + "metadata": { + "editable": true + }, + "source": [ + "$$\n", + "\\frac{\\partial \\boldsymbol{y} }{\\partial \\boldsymbol{x}}= \\boldsymbol{A}.\n", + "$$" + ] + }, + { + "cell_type": "markdown", + "id": "97d7d08a", + "metadata": { + "editable": true + }, + "source": [ + "## Example 2\n", + "\n", + "We define a scalar (our cost/loss functions are in general also scalars,\n", + "just think of the mean squared error) as the result of some matrix vector\n", + "multiplications" + ] + }, + { + "cell_type": "markdown", + "id": "dbcabc11", + "metadata": { + "editable": true + }, + "source": [ + "$$\n", + "\\alpha = \\boldsymbol{y}^T\\boldsymbol{A}\\boldsymbol{x},\n", + "$$" + ] + }, + { + "cell_type": "markdown", + "id": "7278dcbd", + "metadata": { + "editable": true + }, + "source": [ + "with $\\boldsymbol{y}$ a vector of length $m$, $\\boldsymbol{A}$ an $m\\times n$ matrix and $\\boldsymbol{x}$ a vector of length $n$. We assume also that $\\boldsymbol{A}$ does not depend on any of the two vectors.\n", + "In order to find the derivative of $\\alpha$ with respect to the two vectors, we define an intermediate vector $\\boldsymbol{z}$. We define first\n", + "$\\boldsymbol{z}^T=\\boldsymbol{y}^T\\boldsymbol{A}$, a vector of length $n$. We have then, using the definition of the Jacobian," + ] + }, + { + "cell_type": "markdown", + "id": "c16d222a", + "metadata": { + "editable": true + }, + "source": [ + "$$\n", + "\\alpha = \\boldsymbol{z}^T\\boldsymbol{x},\n", + "$$" + ] + }, + { + "cell_type": "markdown", + "id": "0d85444e", + "metadata": { + "editable": true + }, + "source": [ + "which means that (using our previous example) we have" + ] + }, + { + "cell_type": "markdown", + "id": "4d26bab6", + "metadata": { + "editable": true + }, + "source": [ + "$$\n", + "\\frac{\\partial \\alpha}{\\partial \\boldsymbol{x}} = \\boldsymbol{z}=bm{A}^T\\boldsymbol{y}.\n", + "$$" + ] + }, + { + "cell_type": "markdown", + "id": "b6d57fdf", + "metadata": { + "editable": true + }, + "source": [ + "Note that the resulting vector elements are the same for $\\boldsymbol{z}^T$ and $\\boldsymbol{z}$, the only difference is that one if just the transpose of the other.\n", + "\n", + "Since $\\alpha$ is a scalar we have $\\alpha =\\alpha^T=\\boldsymbol{x}^T\\boldsymbol{A}^T\\boldsymbol{y}$. Defining now $\\boldsymbol{z}=\\boldsymbol{x}^T\\boldsymbol{A}^T$ we find that" + ] + }, + { + "cell_type": "markdown", + "id": "7a78e5dc", + "metadata": { + "editable": true + }, + "source": [ + "$$\n", + "\\frac{\\partial \\alpha}{\\partial \\boldsymbol{y}} = \\boldsymbol{z}^T=\\boldsymbol{x}^T\\boldsymbol{A}^T.\n", + "$$" + ] + }, + { + "cell_type": "markdown", + "id": "6231367b", + "metadata": { + "editable": true + }, + "source": [ + "## Example 3\n", + "\n", + "We start with a new scalar but where now the vector $\\boldsymbol{y}$ is\n", + "replaced by a vector $\\boldsymbol{x}$ and the matrix $\\boldsymbol{A}$ is a square\n", + "matrix with dimension $n\\times n$." + ] + }, + { + "cell_type": "markdown", + "id": "ab068594", + "metadata": { + "editable": true + }, + "source": [ + "$$\n", + "\\alpha = \\boldsymbol{x}^T\\boldsymbol{A}\\boldsymbol{x},\n", + "$$" + ] + }, + { + "cell_type": "markdown", + "id": "07d2f06b", + "metadata": { + "editable": true + }, + "source": [ + "with $\\boldsymbol{x}$ a vector of length $n$.\n", + "\n", + "We write out the specific sums involved in the calculation of $\\alpha$" + ] + }, + { + "cell_type": "markdown", + "id": "d2382139", + "metadata": { + "editable": true + }, + "source": [ + "$$\n", + "\\alpha = \\sum_{i=0}^{n-1}\\sum_{j=0}^{n-1}x_i a_{ij}x_j,\n", + "$$" + ] + }, + { + "cell_type": "markdown", + "id": "7d063f00", + "metadata": { + "editable": true + }, + "source": [ + "taking the derivative of $\\alpha$ with respect to a given component $x_k$ we get the two sums" + ] + }, + { + "cell_type": "markdown", + "id": "5e119075", + "metadata": { + "editable": true + }, + "source": [ + "$$\n", + "\\frac{\\partial \\alpha}{\\partial x_k} = \\sum_{i=0}^{n-1}a_{ik}x_i+\\sum_{j=0}^{n-1}a_{kj}x_j,\n", + "$$" + ] + }, + { + "cell_type": "markdown", + "id": "700eaedb", + "metadata": { + "editable": true + }, + "source": [ + "for $\\forall k =0,1,2,\\dots,n-1$. We identify these sums as" + ] + }, + { + "cell_type": "markdown", + "id": "51e05fca", + "metadata": { + "editable": true + }, + "source": [ + "$$\n", + "\\frac{\\partial \\alpha}{\\partial \\boldsymbol{x}} = \\boldsymbol{x}^T\\left(\\boldsymbol{A}^T+\\boldsymbol{A}\\right).\n", + "$$" + ] + }, + { + "cell_type": "markdown", + "id": "bba7f463", + "metadata": { + "editable": true + }, + "source": [ + "If the matrix $\\boldsymbol{A}$ is symmetric, that is $\\boldsymbol{A}=\\boldsymbol{A}^T$, we have" + ] + }, + { + "cell_type": "markdown", + "id": "601577cc", + "metadata": { + "editable": true + }, + "source": [ + "$$\n", + "\\frac{\\partial \\alpha}{\\partial \\boldsymbol{x}} = 2\\boldsymbol{x}^T\\boldsymbol{A}.\n", + "$$" + ] + }, + { + "cell_type": "markdown", + "id": "ea31952c", + "metadata": { + "editable": true + }, + "source": [ + "## Example 4\n", + "\n", + "We let the scalar $\\alpha$ be defined by" + ] + }, + { + "cell_type": "markdown", + "id": "fc6c86a7", + "metadata": { + "editable": true + }, + "source": [ + "$$\n", + "\\alpha = \\boldsymbol{y}^T\\boldsymbol{x},\n", + "$$" + ] + }, + { + "cell_type": "markdown", + "id": "ffe09390", + "metadata": { + "editable": true + }, + "source": [ + "where both $\\boldsymbol{y}$ and $\\boldsymbol{x}$ have the same length $n$, or if we\n", + "wish to think of them as column vectors, they have dimensions $n\\times\n", + "1$. We assume that both $\\boldsymbol{y}$ and $\\boldsymbol{x}$ depend on a vector\n", + "$\\boldsymbol{z}$ of the same length. To calculate the derivative of $\\alpha$\n", + "with respect to a given component $z_k$ we need first to write out the\n", + "inner product that defines $\\alpha$ as" + ] + }, + { + "cell_type": "markdown", + "id": "22f4970c", + "metadata": { + "editable": true + }, + "source": [ + "$$\n", + "\\alpha = \\sum_{i=0}^{n-1}y_ix_i,\n", + "$$" + ] + }, + { + "cell_type": "markdown", + "id": "4ba751cb", + "metadata": { + "editable": true + }, + "source": [ + "and the partial derivative" + ] + }, + { + "cell_type": "markdown", + "id": "87052e13", + "metadata": { + "editable": true + }, + "source": [ + "$$\n", + "\\frac{\\partial \\alpha}{\\partial z_k} = \\sum_{i=0}^{n-1}\\left(x_i\\frac{\\partial y_i}{\\partial z_k}+y_i\\frac{\\partial x_i}{\\partial z_k}\\right),\n", + "$$" + ] + }, + { + "cell_type": "markdown", + "id": "e24dea19", + "metadata": { + "editable": true + }, + "source": [ + "for $\\forall k =0,1,2,\\dots,n-1$. We can rewrite the partial derivative in a more compact form as" + ] + }, + { + "cell_type": "markdown", + "id": "6b52c737", + "metadata": { + "editable": true + }, + "source": [ + "$$\n", + "\\frac{\\partial \\alpha}{\\partial \\boldsymbol{z}} = \\boldsymbol{x}^T\\frac{\\partial \\boldsymbol{y}}{\\partial \\boldsymbol{z}}+\\boldsymbol{y}^T\\frac{\\partial \\boldsymbol{x}}{\\partial \\boldsymbol{z}},\n", + "$$" + ] + }, + { + "cell_type": "markdown", + "id": "904b93aa", + "metadata": { + "editable": true + }, + "source": [ + "and if $\\boldsymbol{y}=\\boldsymbol{x}$ we have" + ] + }, + { + "cell_type": "markdown", + "id": "439e197d", + "metadata": { + "editable": true + }, + "source": [ + "$$\n", + "\\frac{\\partial \\alpha}{\\partial \\boldsymbol{z}} = 2\\boldsymbol{x}^T\\frac{\\partial \\boldsymbol{x}}{\\partial \\boldsymbol{z}}.\n", + "$$" + ] + }, + { + "cell_type": "markdown", + "id": "f5658ed9", + "metadata": { + "editable": true + }, + "source": [ + "## The mean squared error and its derivative\n", + "\n", + "We defined earlier a possible cost function using the mean squared error" + ] + }, + { + "cell_type": "markdown", + "id": "6f99984d", + "metadata": { + "editable": true + }, + "source": [ + "$$\n", + "C(\\boldsymbol{\\beta})=\\frac{1}{n}\\sum_{i=0}^{n-1}\\left(y_i-\\tilde{y}_i\\right)^2=\\frac{1}{n}\\left\\{\\left(\\boldsymbol{y}-\\boldsymbol{\\tilde{y}}\\right)^T\\left(\\boldsymbol{y}-\\boldsymbol{\\tilde{y}}\\right)\\right\\},\n", + "$$" + ] + }, + { + "cell_type": "markdown", + "id": "eeb1373c", + "metadata": { + "editable": true + }, + "source": [ + "or using the design/feature matrix $\\boldsymbol{X}$ we have the more compact matrix-vector" + ] + }, + { + "cell_type": "markdown", + "id": "f3c557ba", + "metadata": { + "editable": true + }, + "source": [ + "$$\n", + "C(\\boldsymbol{\\beta})=\\frac{1}{n}\\left\\{\\left(\\boldsymbol{y}-\\boldsymbol{X}\\boldsymbol{\\beta}\\right)^T\\left(\\boldsymbol{y}-\\boldsymbol{X}\\boldsymbol{\\beta}\\right)\\right\\}.\n", + "$$" + ] + }, + { + "cell_type": "markdown", + "id": "412789d5", + "metadata": { + "editable": true + }, + "source": [ + "We note that the design matrix $\\boldsymbol{X}$ does not depend on the unknown parameters defined by the vector $\\boldsymbol{\\beta}$.\n", + "We are now interested in minimizing the cost function with respect to the unknown parameters $\\boldsymbol{\\beta}$.\n", + "\n", + "The mean squared error is a scalar and if we use the results from example three above, we can define a new vector" + ] + }, + { + "cell_type": "markdown", + "id": "65fbbb29", + "metadata": { + "editable": true + }, + "source": [ + "$$\n", + "\\boldsymbol{w}=\\boldsymbol{y}-\\boldsymbol{X}\\boldsymbol{\\beta},\n", + "$$" + ] + }, + { + "cell_type": "markdown", + "id": "f4cd65e4", + "metadata": { + "editable": true + }, + "source": [ + "which depends on $\\boldsymbol{\\beta}$. We rewrite the cost function as" + ] + }, + { + "cell_type": "markdown", + "id": "9ee329c3", + "metadata": { + "editable": true + }, + "source": [ + "$$\n", + "C(\\boldsymbol{\\beta})=\\frac{1}{n}\\boldsymbol{w}^T\\boldsymbol{w},\n", + "$$" + ] + }, + { + "cell_type": "markdown", + "id": "47023d81", + "metadata": { + "editable": true + }, + "source": [ + "with partial derivative" + ] + }, + { + "cell_type": "markdown", + "id": "40d4cc36", + "metadata": { + "editable": true + }, + "source": [ + "$$\n", + "\\frac{\\partial C(\\boldsymbol{\\beta})}{\\partial \\boldsymbol{\\beta}}=\\frac{2}{n}\\boldsymbol{w}^T\\frac{\\partial \\boldsymbol{w}}{\\partial \\boldsymbol{\\beta}},\n", + "$$" + ] + }, + { + "cell_type": "markdown", + "id": "e266851f", + "metadata": { + "editable": true + }, + "source": [ + "and using that" + ] + }, + { + "cell_type": "markdown", + "id": "f4d0941c", + "metadata": { + "editable": true + }, + "source": [ + "$$\n", + "\\frac{\\partial \\boldsymbol{w}}{\\partial \\boldsymbol{\\beta}}=-\\boldsymbol{X},\n", + "$$" + ] + }, + { + "cell_type": "markdown", + "id": "6f4b2a9d", + "metadata": { + "editable": true + }, + "source": [ + "where we used the result from example two above. Inserting the last expression we obtain" + ] + }, + { + "cell_type": "markdown", + "id": "62cab30b", + "metadata": { + "editable": true + }, + "source": [ + "$$\n", + "\\frac{\\partial C(\\boldsymbol{\\beta})}{\\partial \\boldsymbol{\\beta}}=-\\frac{2}{n}\\left(\\boldsymbol{y}-\\boldsymbol{X}\\boldsymbol{\\beta}\\right)^T\\boldsymbol{X},\n", + "$$" + ] + }, + { + "cell_type": "markdown", + "id": "4c8c6398", + "metadata": { + "editable": true + }, + "source": [ + "or as" + ] + }, + { + "cell_type": "markdown", + "id": "f9c6ab8a", + "metadata": { + "editable": true + }, + "source": [ + "$$\n", + "\\frac{\\partial C(\\boldsymbol{\\beta})}{\\partial \\boldsymbol{\\beta}^T}=-\\frac{2}{n}\\boldsymbol{X}^T\\left(\\boldsymbol{y}-\\boldsymbol{X}\\boldsymbol{\\beta}\\right).\n", + "$$" + ] + }, + { + "cell_type": "markdown", + "id": "b7945d33", + "metadata": { + "editable": true + }, + "source": [ + "## Other useful relations\n", + "\n", + "We list here some other useful relations we may encounter (recall that vectors are defined by boldfaced low-key letters)" + ] + }, + { + "cell_type": "markdown", + "id": "80421efe", + "metadata": { + "editable": true + }, + "source": [ + "$$\n", + "\\frac{\\partial (\\boldsymbol{b}^T\\boldsymbol{a})}{\\partial \\boldsymbol{a}} = \\boldsymbol{b},\n", + "$$" + ] + }, + { + "cell_type": "markdown", + "id": "cc1fb4bf", + "metadata": { + "editable": true + }, + "source": [ + "$$\n", + "\\frac{\\partial tr(\\boldsymbol{B}\\boldsymbol{A})}{\\partial \\boldsymbol{A}} = \\boldsymbol{B}^T,\n", + "$$" + ] + }, + { + "cell_type": "markdown", + "id": "c149bd15", + "metadata": { + "editable": true + }, + "source": [ + "$$\n", + "\\frac{\\partial \\log{\\vert\\boldsymbol{A}\\vert}}{\\partial \\boldsymbol{A}} = (\\boldsymbol{A}^{-1})^T.\n", + "$$" + ] + }, + { + "cell_type": "markdown", + "id": "4aeb6fad", + "metadata": { + "editable": true + }, + "source": [ + "## Meet the Hessian Matrix\n", + "\n", + "A very important matrix we will meet again and again in machine\n", + "learning is the Hessian. It is given by the second derivative of the\n", + "cost function with respect to the parameters $\\boldsymbol{\\beta}$. Using the above\n", + "expression for derivatives of vectors and matrices, we find that the\n", + "second derivative of the mean squared error as cost function is," + ] + }, + { + "cell_type": "markdown", + "id": "fecdf631", + "metadata": { + "editable": true + }, + "source": [ + "$$\n", + "\\frac{\\partial}{\\partial \\boldsymbol{\\beta}}\\frac{\\partial C(\\boldsymbol{\\beta})}{\\partial \\boldsymbol{\\beta}^T} =\\frac{\\partial}{\\partial \\boldsymbol{\\beta}}\\left[-\\frac{2}{n}\\boldsymbol{X}^T\\left( \\boldsymbol{y}-\\boldsymbol{X}\\boldsymbol{\\beta}\\right)\\right]=\\frac{2}{n}\\boldsymbol{X}^T\\boldsymbol{X}.\n", + "$$" + ] + }, + { + "cell_type": "markdown", + "id": "7ffbaccd", + "metadata": { + "editable": true + }, + "source": [ + "The Hessian matrix plays an important role and is defined here as" + ] + }, + { + "cell_type": "markdown", + "id": "ba12c9f2", + "metadata": { + "editable": true + }, + "source": [ + "$$\n", + "\\boldsymbol{H}=\\boldsymbol{X}^T\\boldsymbol{X}.\n", + "$$" + ] + }, + { + "cell_type": "markdown", + "id": "871cfd8e", + "metadata": { + "editable": true + }, + "source": [ + "For ordinary least squares, it is inversely proportional (derivation\n", + "next week) with the variance of the optimal parameters\n", + "$\\hat{\\boldsymbol{\\beta}}$. Furthermore, we will see later this week that it is\n", + "(aside the factor $1/n$) equal to the covariance matrix. It plays also a very\n", + "important role in optmization algorithms and Principal Component\n", + "Analysis as a way to reduce the dimensionality of a machine learning/data analysis\n", + "problem.\n", + "\n", + "**Linear algebra question:** Can we use the Hessian matrix to say something about properties of the cost function (our optmization problem)? (hint: think about convex or concave problems and how to relate these to a matrix!)." + ] + }, + { + "cell_type": "markdown", + "id": "0ad332cd", + "metadata": { + "editable": true + }, + "source": [ + "## Interpretations and optimizing our parameters\n", + "\n", + "The residuals $\\boldsymbol{\\epsilon}$ are in turn given by" + ] + }, + { + "cell_type": "markdown", + "id": "5e7042e9", + "metadata": { + "editable": true + }, + "source": [ + "$$\n", + "\\boldsymbol{\\epsilon} = \\boldsymbol{y}-\\boldsymbol{\\tilde{y}} = \\boldsymbol{y}-\\boldsymbol{X}\\boldsymbol{\\beta},\n", + "$$" + ] + }, + { + "cell_type": "markdown", + "id": "43b825ce", + "metadata": { + "editable": true + }, + "source": [ + "and with" + ] + }, + { + "cell_type": "markdown", + "id": "58a4ed44", + "metadata": { + "editable": true + }, + "source": [ + "$$\n", + "\\boldsymbol{X}^T\\left( \\boldsymbol{y}-\\boldsymbol{X}\\boldsymbol{\\beta}\\right)= 0,\n", + "$$" + ] + }, + { + "cell_type": "markdown", + "id": "202c5775", + "metadata": { + "editable": true + }, + "source": [ + "we have" + ] + }, + { + "cell_type": "markdown", + "id": "0eab64e4", + "metadata": { + "editable": true + }, + "source": [ + "$$\n", + "\\boldsymbol{X}^T\\boldsymbol{\\epsilon}=\\boldsymbol{X}^T\\left( \\boldsymbol{y}-\\boldsymbol{X}\\boldsymbol{\\beta}\\right)= 0,\n", + "$$" + ] + }, + { + "cell_type": "markdown", + "id": "d17063fa", + "metadata": { + "editable": true + }, + "source": [ + "meaning that the solution for $\\boldsymbol{\\beta}$ is the one which minimizes the residuals." + ] + }, + { + "cell_type": "markdown", + "id": "02cca57e", + "metadata": { + "editable": true + }, + "source": [ + "## Example relevant for the exercises\n", + "\n", + "In order to understand the relation among the predictors $p$, the set of data $n$ and the target (outcome, output etc) $\\boldsymbol{y}$,\n", + "we condiser a simple polynomial fit.\n", + "We assume our data can represented by a fourth-order polynomial. For the $i$th component we have" + ] + }, + { + "cell_type": "markdown", + "id": "d5a0e65b", + "metadata": { + "editable": true + }, + "source": [ + "$$\n", + "\\tilde{y}_i = \\beta_0+\\beta_1x_i+\\beta_2x_i^2+\\beta_3x_i^3+\\beta_4x_i^4.\n", + "$$" + ] + }, + { + "cell_type": "markdown", + "id": "03f47788", + "metadata": { + "editable": true + }, + "source": [ + "we have five predictors/features. The first is the intercept $\\beta_0$. The other terms are $\\beta_i$ with $i=1,2,3,4$. Furthermore we have $n$ entries for each predictor. It means that our design matrix is an \n", + "$n\\times p$ matrix $\\boldsymbol{X}$." + ] + }, + { + "cell_type": "markdown", + "id": "ab07b7cf", + "metadata": { + "editable": true + }, + "source": [ + "## Own code for Ordinary Least Squares\n", + "\n", + "It is rather straightforward to implement the matrix inversion and obtain the parameters $\\boldsymbol{\\beta}$. After having defined the matrix $\\boldsymbol{X}$ and the outputs $\\boldsymbol{y}$ we have" + ] + }, + { + "cell_type": "code", + "execution_count": 1, + "id": "f51e672d", + "metadata": { + "collapsed": false, + "editable": true + }, + "outputs": [], + "source": [ + "# matrix inversion to find beta\n", + "# First we set up the data\n", + "import numpy as np\n", + "x = np.random.rand(100)\n", + "y = 2.0+5*x*x+0.1*np.random.randn(100)\n", + "# and then the design matrix X including the intercept\n", + "# The design matrix now as function of a fourth-order polynomial\n", + "X = np.zeros((len(x),5))\n", + "X[:,0] = 1.0\n", + "X[:,1] = x\n", + "X[:,2] = x**2\n", + "X[:,3] = x**3\n", + "X[:,4] = x**4\n", + "beta = (np.linalg.inv(X.T @ X) @ X.T ) @ y\n", + "# and then make the prediction\n", + "ytilde = X @ beta" + ] + }, + { + "cell_type": "markdown", + "id": "e44be45e", + "metadata": { + "editable": true + }, + "source": [ + "Alternatively, you can use the least squares functionality in **Numpy** as" + ] + }, + { + "cell_type": "code", + "execution_count": 2, + "id": "b4786589", + "metadata": { + "collapsed": false, + "editable": true + }, + "outputs": [], + "source": [ + "fit = np.linalg.lstsq(X, y, rcond =None)[0]\n", + "ytildenp = np.dot(fit,X.T)" + ] + }, + { + "cell_type": "markdown", + "id": "af2dcc52", + "metadata": { + "editable": true + }, + "source": [ + "## Adding error analysis and training set up\n", + "\n", + "We can easily test our fit by computing the $R2$ score that we discussed in connection with the functionality of **Scikit-Learn** in the introductory slides.\n", + "Since we are not using **Scikit-Learn** here we can define our own $R2$ function as" + ] + }, + { + "cell_type": "code", + "execution_count": 3, + "id": "2bc65bc5", + "metadata": { + "collapsed": false, + "editable": true + }, + "outputs": [], + "source": [ + "def R2(y_data, y_model):\n", + " return 1 - np.sum((y_data - y_model) ** 2) / np.sum((y_data - np.mean(y_data)) ** 2)" + ] + }, + { + "cell_type": "markdown", + "id": "46bda600", + "metadata": { + "editable": true + }, + "source": [ + "and we would be using it as" + ] + }, + { + "cell_type": "code", + "execution_count": 4, + "id": "9bdae7bf", + "metadata": { + "collapsed": false, + "editable": true + }, + "outputs": [], + "source": [ + "print(R2(y,ytilde))" + ] + }, + { + "cell_type": "markdown", + "id": "64eeaaef", + "metadata": { + "editable": true + }, + "source": [ + "We can easily add our **MSE** score as" + ] + }, + { + "cell_type": "code", + "execution_count": 5, + "id": "cafbda91", + "metadata": { + "collapsed": false, + "editable": true + }, + "outputs": [], + "source": [ + "def MSE(y_data,y_model):\n", + " n = np.size(y_model)\n", + " return np.sum((y_data-y_model)**2)/n\n", + "\n", + "print(MSE(y,ytilde))" + ] + }, + { + "cell_type": "markdown", + "id": "831a5888", + "metadata": { + "editable": true + }, + "source": [ + "and finally the relative error as" + ] + }, + { + "cell_type": "code", + "execution_count": 6, + "id": "90f6a538", + "metadata": { + "collapsed": false, + "editable": true + }, + "outputs": [], + "source": [ + "def RelativeError(y_data,y_model):\n", + " return abs((y_data-y_model)/y_data)\n", + "print(RelativeError(y, ytilde))" + ] + }, + { + "cell_type": "markdown", + "id": "dc364c27", + "metadata": { + "editable": true + }, + "source": [ + "## Splitting our Data in Training and Test data\n", + "\n", + "It is normal in essentially all Machine Learning studies to split the\n", + "data in a training set and a test set (sometimes also an additional\n", + "validation set). **Scikit-Learn** has an own function for this. There\n", + "is no explicit recipe for how much data should be included as training\n", + "data and say test data. An accepted rule of thumb is to use\n", + "approximately $2/3$ to $4/5$ of the data as training data. We will\n", + "postpone a discussion of this splitting to the end of these notes and\n", + "our discussion of the so-called **bias-variance** tradeoff. Here we\n", + "limit ourselves to repeat the above equation of state fitting example\n", + "but now splitting the data into a training set and a test set." + ] + }, + { + "cell_type": "markdown", + "id": "1598259c", + "metadata": { + "editable": true + }, + "source": [ + "## The complete code with a simple data set" + ] + }, + { + "cell_type": "code", + "execution_count": 7, + "id": "ca994e68", + "metadata": { + "collapsed": false, + "editable": true + }, + "outputs": [], + "source": [ + "%matplotlib inline\n", + "\n", + "import os\n", + "import numpy as np\n", + "import pandas as pd\n", + "import matplotlib.pyplot as plt\n", + "from sklearn.model_selection import train_test_split\n", + "\n", + "\n", + "def R2(y_data, y_model):\n", + " return 1 - np.sum((y_data - y_model) ** 2) / np.sum((y_data - np.mean(y_data)) ** 2)\n", + "def MSE(y_data,y_model):\n", + " n = np.size(y_model)\n", + " return np.sum((y_data-y_model)**2)/n\n", + "\n", + "x = np.random.rand(100)\n", + "y = 2.0+5*x*x+0.1*np.random.randn(100)\n", + "\n", + "\n", + "# The design matrix now as function of a fourth-order polynomial\n", + "X = np.zeros((len(x),5))\n", + "X[:,0] = 1.0\n", + "X[:,1] = x\n", + "X[:,2] = x**2\n", + "X[:,3] = x**3\n", + "X[:,4] = x**4\n", + "# We split the data in test and training data\n", + "X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2)\n", + "# matrix inversion to find beta\n", + "beta = np.linalg.inv(X_train.T @ X_train) @ X_train.T @ y_train\n", + "print(beta)\n", + "# and then make the prediction\n", + "ytilde = X_train @ beta\n", + "print(\"Training R2\")\n", + "print(R2(y_train,ytilde))\n", + "print(\"Training MSE\")\n", + "print(MSE(y_train,ytilde))\n", + "ypredict = X_test @ beta\n", + "print(\"Test R2\")\n", + "print(R2(y_test,ypredict))\n", + "print(\"Test MSE\")\n", + "print(MSE(y_test,ypredict))" + ] + }, + { + "cell_type": "markdown", + "id": "7353f2e7", + "metadata": { + "editable": true + }, + "source": [ + "## Making your own test-train splitting" + ] + }, + { + "cell_type": "code", + "execution_count": 8, + "id": "05a066db", + "metadata": { + "collapsed": false, + "editable": true + }, + "outputs": [], + "source": [ + "# equivalently in numpy\n", + "def train_test_split_numpy(inputs, labels, train_size, test_size):\n", + " n_inputs = len(inputs)\n", + " inputs_shuffled = inputs.copy()\n", + " labels_shuffled = labels.copy()\n", + "\n", + " np.random.shuffle(inputs_shuffled)\n", + " np.random.shuffle(labels_shuffled)\n", + "\n", + " train_end = int(n_inputs*train_size)\n", + " X_train, X_test = inputs_shuffled[:train_end], inputs_shuffled[train_end:]\n", + " Y_train, Y_test = labels_shuffled[:train_end], labels_shuffled[train_end:]\n", + "\n", + " return X_train, X_test, Y_train, Y_test" + ] + }, + { + "cell_type": "markdown", + "id": "1f30de64", + "metadata": { + "editable": true + }, + "source": [ + "But since **scikit-learn** has its own function for doing this and since\n", + "it interfaces easily with **tensorflow** and other libraries, we\n", + "normally recommend using the latter functionality." + ] + }, + { + "cell_type": "markdown", + "id": "80fa8b7d", + "metadata": { + "editable": true + }, + "source": [ + "## Reducing the number of degrees of freedom, overarching view\n", + "\n", + "Many Machine Learning problems involve thousands or even millions of\n", + "features for each training instance. Not only does this make training\n", + "extremely slow, it can also make it much harder to find a good\n", + "solution, as we will see. This problem is often referred to as the\n", + "curse of dimensionality. Fortunately, in real-world problems, it is\n", + "often possible to reduce the number of features considerably, turning\n", + "an intractable problem into a tractable one.\n", + "\n", + "Later we will discuss some of the most popular dimensionality reduction\n", + "techniques: the principal component analysis (PCA), Kernel PCA, and\n", + "Locally Linear Embedding (LLE). \n", + "\n", + "Principal component analysis and its various variants deal with the\n", + "problem of fitting a low-dimensional [affine\n", + "subspace](https://en.wikipedia.org/wiki/Affine_space) to a set of of\n", + "data points in a high-dimensional space. With its family of methods it\n", + "is one of the most used tools in data modeling, compression and\n", + "visualization." + ] + }, + { + "cell_type": "markdown", + "id": "7e92be20", + "metadata": { + "editable": true + }, + "source": [ + "## Preprocessing our data\n", + "\n", + "Before we proceed however, we will discuss how to preprocess our\n", + "data. Till now and in connection with our previous examples we have\n", + "not met so many cases where we are too sensitive to the scaling of our\n", + "data. Normally the data may need a rescaling and/or may be sensitive\n", + "to extreme values. Scaling the data renders our inputs much more\n", + "suitable for the algorithms we want to employ.\n", + "\n", + "For data sets gathered for real world applications, it is rather normal that\n", + "different features have very different units and\n", + "numerical scales. For example, a data set detailing health habits may include\n", + "features such as **age** in the range $0-80$, and **caloric intake** of order $2000$.\n", + "Many machine learning methods sensitive to the scales of the features and may perform poorly if they\n", + "are very different scales. Therefore, it is typical to scale\n", + "the features in a way to avoid such outlier values." + ] + }, + { + "cell_type": "markdown", + "id": "052e8c0c", + "metadata": { + "editable": true + }, + "source": [ + "## Functionality in Scikit-Learn\n", + "\n", + "**Scikit-Learn** has several functions which allow us to rescale the\n", + "data, normally resulting in much better results in terms of various\n", + "accuracy scores. The **StandardScaler** function in **Scikit-Learn**\n", + "ensures that for each feature/predictor we study the mean value is\n", + "zero and the variance is one (every column in the design/feature\n", + "matrix). This scaling has the drawback that it does not ensure that\n", + "we have a particular maximum or minimum in our data set. Another\n", + "function included in **Scikit-Learn** is the **MinMaxScaler** which\n", + "ensures that all features are exactly between $0$ and $1$. The" + ] + }, + { + "cell_type": "markdown", + "id": "d752c7f4", + "metadata": { + "editable": true + }, + "source": [ + "## More preprocessing\n", + "\n", + "The **Normalizer** scales each data\n", + "point such that the feature vector has a euclidean length of one. In other words, it\n", + "projects a data point on the circle (or sphere in the case of higher dimensions) with a\n", + "radius of 1. This means every data point is scaled by a different number (by the\n", + "inverse of it’s length).\n", + "This normalization is often used when only the direction (or angle) of the data matters,\n", + "not the length of the feature vector.\n", + "\n", + "The **RobustScaler** works similarly to the StandardScaler in that it\n", + "ensures statistical properties for each feature that guarantee that\n", + "they are on the same scale. However, the RobustScaler uses the median\n", + "and quartiles, instead of mean and variance. This makes the\n", + "RobustScaler ignore data points that are very different from the rest\n", + "(like measurement errors). These odd data points are also called\n", + "outliers, and might often lead to trouble for other scaling\n", + "techniques." + ] + }, + { + "cell_type": "markdown", + "id": "4b40d092", + "metadata": { + "editable": true + }, + "source": [ + "## Frequently used scaling functions\n", + "\n", + "Many features are often scaled using standardization to improve performance. In **Scikit-Learn** this is given by the **StandardScaler** function as discussed above. It is easy however to write your own. \n", + "Mathematically, this involves subtracting the mean and divide by the standard deviation over the data set, for each feature:" + ] + }, + { + "cell_type": "markdown", + "id": "f8526e57", + "metadata": { + "editable": true + }, + "source": [ + "$$\n", + "x_j^{(i)} \\rightarrow \\frac{x_j^{(i)} - \\overline{x}_j}{\\sigma(x_j)},\n", + "$$" + ] + }, + { + "cell_type": "markdown", + "id": "5cfb3455", + "metadata": { + "editable": true + }, + "source": [ + "where $\\overline{x}_j$ and $\\sigma(x_j)$ are the mean and standard deviation, respectively, of the feature $x_j$.\n", + "This ensures that each feature has zero mean and unit standard deviation. For data sets where we do not have the standard deviation or don't wish to calculate it, it is then common to simply set it to one." + ] + }, + { + "cell_type": "markdown", + "id": "363e0117", + "metadata": { + "editable": true + }, + "source": [ + "## Example of own Standard scaling\n", + "\n", + "Let us consider the following vanilla example where we use both\n", + "**Scikit-Learn** and write our own function as well. We produce a\n", + "simple test design matrix with random numbers. Each column could then\n", + "represent a specific feature whose mean value is subracted." + ] + }, + { + "cell_type": "code", + "execution_count": 9, + "id": "4c7ecfc5", + "metadata": { + "collapsed": false, + "editable": true + }, + "outputs": [], + "source": [ + "import sklearn.linear_model as skl\n", + "from sklearn.metrics import mean_squared_error\n", + "from sklearn.model_selection import train_test_split\n", + "from sklearn.preprocessing import MinMaxScaler, StandardScaler, Normalizer\n", + "import numpy as np\n", + "import pandas as pd\n", + "from IPython.display import display\n", + "np.random.seed(100)\n", + "# setting up a 10 x 5 matrix\n", + "rows = 10\n", + "cols = 5\n", + "X = np.random.randn(rows,cols)\n", + "XPandas = pd.DataFrame(X)\n", + "display(XPandas)\n", + "print(XPandas.mean())\n", + "print(XPandas.std())\n", + "XPandas = (XPandas -XPandas.mean())\n", + "display(XPandas)\n", + "# This option does not include the standard deviation\n", + "scaler = StandardScaler(with_std=False)\n", + "scaler.fit(X)\n", + "Xscaled = scaler.transform(X)\n", + "display(XPandas-Xscaled)" + ] + }, + { + "cell_type": "markdown", + "id": "981f65fb", + "metadata": { + "editable": true + }, + "source": [ + "Small exercise: perform the standard scaling by including the standard deviation and compare with what Scikit-Learn gives." + ] + }, + { + "cell_type": "markdown", + "id": "9ddcca79", + "metadata": { + "editable": true + }, + "source": [ + "## Min-Max Scaling\n", + "\n", + "Another commonly used scaling method is min-max scaling. This is very\n", + "useful for when we want the features to lie in a certain interval. To\n", + "scale the feature $x_j$ to the interval $[a, b]$, we can apply the\n", + "transformation" + ] + }, + { + "cell_type": "markdown", + "id": "02bed8b3", + "metadata": { + "editable": true + }, + "source": [ + "$$\n", + "x_j^{(i)} \\rightarrow (b-a)\\frac{x_j^{(i)} - \\min(x_j)}{\\max(x_j) - \\min(x_j)} - a\n", + "$$" + ] + }, + { + "cell_type": "markdown", + "id": "64033f1d", + "metadata": { + "editable": true + }, + "source": [ + "where $\\min(x_j)$ and $\\max(x_j)$ return the minimum and maximum value of $x_j$ over the data set, respectively." + ] + }, + { + "cell_type": "markdown", + "id": "1cfc52cc", + "metadata": { + "editable": true + }, + "source": [ + "## Testing the Means Squared Error as function of Complexity\n", + "\n", + "One of \n", + "the aims is to reproduce Figure 2.11 of [Hastie et al](https://github.com/CompPhysics/MLErasmus/blob/master/doc/Textbooks/elementsstat.pdf).\n", + "\n", + "Our data is defined by $x\\in [-3,3]$ with a total of for example $100$ data points." + ] + }, + { + "cell_type": "code", + "execution_count": 10, + "id": "06b67f41", + "metadata": { + "collapsed": false, + "editable": true + }, + "outputs": [], + "source": [ + "np.random.seed()\n", + "n = 100\n", + "maxdegree = 14\n", + "# Make data set.\n", + "x = np.linspace(-3, 3, n).reshape(-1, 1)\n", + "y = np.exp(-x**2) + 1.5 * np.exp(-(x-2)**2)+ np.random.normal(0, 0.1, x.shape)" + ] + }, + { + "cell_type": "markdown", + "id": "773210a0", + "metadata": { + "editable": true + }, + "source": [ + "where $y$ is the function we want to fit with a given polynomial.\n", + "\n", + "Write a first code which sets up a design matrix $X$ defined by a fourth-order polynomial. Scale your data and split it in training and test data." + ] + }, + { + "cell_type": "code", + "execution_count": 11, + "id": "34cb4217", + "metadata": { + "collapsed": false, + "editable": true + }, + "outputs": [], + "source": [ + "import matplotlib.pyplot as plt\n", + "import numpy as np\n", + "from sklearn.linear_model import LinearRegression\n", + "from sklearn.preprocessing import PolynomialFeatures\n", + "from sklearn.model_selection import train_test_split\n", + "from sklearn.pipeline import make_pipeline\n", + "\n", + "\n", + "np.random.seed(2018)\n", + "n = 50\n", + "maxdegree = 5\n", + "# Make data set.\n", + "x = np.linspace(-3, 3, n).reshape(-1, 1)\n", + "y = np.exp(-x**2) + 1.5 * np.exp(-(x-2)**2)+ np.random.normal(0, 0.1, x.shape)\n", + "TestError = np.zeros(maxdegree)\n", + "TrainError = np.zeros(maxdegree)\n", + "polydegree = np.zeros(maxdegree)\n", + "x_train, x_test, y_train, y_test = train_test_split(x, y, test_size=0.2)\n", + "scaler = StandardScaler()\n", + "scaler.fit(x_train)\n", + "x_train_scaled = scaler.transform(x_train)\n", + "x_test_scaled = scaler.transform(x_test)\n", + "\n", + "for degree in range(maxdegree):\n", + " model = make_pipeline(PolynomialFeatures(degree=degree), LinearRegression(fit_intercept=False))\n", + " clf = model.fit(x_train_scaled,y_train)\n", + " y_fit = clf.predict(x_train_scaled)\n", + " y_pred = clf.predict(x_test_scaled) \n", + " polydegree[degree] = degree\n", + " TestError[degree] = np.mean( np.mean((y_test - y_pred)**2) )\n", + " TrainError[degree] = np.mean( np.mean((y_train - y_fit)**2) )\n", + "\n", + "plt.plot(polydegree, TestError, label='Test Error')\n", + "plt.plot(polydegree, TrainError, label='Train Error')\n", + "plt.legend()\n", + "plt.show()" + ] + }, + { + "cell_type": "markdown", + "id": "4ae9cee9", + "metadata": { + "editable": true + }, + "source": [ + "## More preprocessing examples, two-dimensional example, the Franke function" + ] + }, + { + "cell_type": "code", + "execution_count": 12, + "id": "9be1964e", + "metadata": { + "collapsed": false, + "editable": true + }, + "outputs": [], + "source": [ + "# Common imports\n", + "import os\n", + "import numpy as np\n", + "import pandas as pd\n", + "import matplotlib.pyplot as plt\n", + "import sklearn.linear_model as skl\n", + "from sklearn.metrics import mean_squared_error\n", + "from sklearn.model_selection import train_test_split\n", + "from sklearn.preprocessing import MinMaxScaler, StandardScaler, Normalizer\n", + "\n", + "# Where to save the figures and data files\n", + "PROJECT_ROOT_DIR = \"Results\"\n", + "FIGURE_ID = \"Results/FigureFiles\"\n", + "DATA_ID = \"DataFiles/\"\n", + "\n", + "if not os.path.exists(PROJECT_ROOT_DIR):\n", + " os.mkdir(PROJECT_ROOT_DIR)\n", + "\n", + "if not os.path.exists(FIGURE_ID):\n", + " os.makedirs(FIGURE_ID)\n", + "\n", + "if not os.path.exists(DATA_ID):\n", + " os.makedirs(DATA_ID)\n", + "\n", + "def image_path(fig_id):\n", + " return os.path.join(FIGURE_ID, fig_id)\n", + "\n", + "def data_path(dat_id):\n", + " return os.path.join(DATA_ID, dat_id)\n", + "\n", + "def save_fig(fig_id):\n", + " plt.savefig(image_path(fig_id) + \".png\", format='png')\n", + "\n", + "\n", + "def FrankeFunction(x,y):\n", + "\tterm1 = 0.75*np.exp(-(0.25*(9*x-2)**2) - 0.25*((9*y-2)**2))\n", + "\tterm2 = 0.75*np.exp(-((9*x+1)**2)/49.0 - 0.1*(9*y+1))\n", + "\tterm3 = 0.5*np.exp(-(9*x-7)**2/4.0 - 0.25*((9*y-3)**2))\n", + "\tterm4 = -0.2*np.exp(-(9*x-4)**2 - (9*y-7)**2)\n", + "\treturn term1 + term2 + term3 + term4\n", + "\n", + "\n", + "def create_X(x, y, n ):\n", + "\tif len(x.shape) > 1:\n", + "\t\tx = np.ravel(x)\n", + "\t\ty = np.ravel(y)\n", + "\n", + "\tN = len(x)\n", + "\tl = int((n+1)*(n+2)/2)\t\t# Number of elements in beta\n", + "\tX = np.ones((N,l))\n", + "\n", + "\tfor i in range(1,n+1):\n", + "\t\tq = int((i)*(i+1)/2)\n", + "\t\tfor k in range(i+1):\n", + "\t\t\tX[:,q+k] = (x**(i-k))*(y**k)\n", + "\n", + "\treturn X\n", + "\n", + "\n", + "# Making meshgrid of datapoints and compute Franke's function\n", + "n = 5\n", + "N = 1000\n", + "x = np.sort(np.random.uniform(0, 1, N))\n", + "y = np.sort(np.random.uniform(0, 1, N))\n", + "z = FrankeFunction(x, y)\n", + "X = create_X(x, y, n=n) \n", + "# split in training and test data\n", + "X_train, X_test, y_train, y_test = train_test_split(X,z,test_size=0.2)\n", + "\n", + "\n", + "clf = skl.LinearRegression().fit(X_train, y_train)\n", + "\n", + "# The mean squared error and R2 score\n", + "print(\"MSE before scaling: {:.2f}\".format(mean_squared_error(clf.predict(X_test), y_test)))\n", + "print(\"R2 score before scaling {:.2f}\".format(clf.score(X_test,y_test)))\n", + "\n", + "scaler = StandardScaler()\n", + "scaler.fit(X_train)\n", + "X_train_scaled = scaler.transform(X_train)\n", + "X_test_scaled = scaler.transform(X_test)\n", + "\n", + "print(\"Feature min values before scaling:\\n {}\".format(X_train.min(axis=0)))\n", + "print(\"Feature max values before scaling:\\n {}\".format(X_train.max(axis=0)))\n", + "\n", + "print(\"Feature min values after scaling:\\n {}\".format(X_train_scaled.min(axis=0)))\n", + "print(\"Feature max values after scaling:\\n {}\".format(X_train_scaled.max(axis=0)))\n", + "\n", + "clf = skl.LinearRegression().fit(X_train_scaled, y_train)\n", + "\n", + "\n", + "print(\"MSE after scaling: {:.2f}\".format(mean_squared_error(clf.predict(X_test_scaled), y_test)))\n", + "print(\"R2 score for scaled data: {:.2f}\".format(clf.score(X_test_scaled,y_test)))" + ] + }, + { + "cell_type": "markdown", + "id": "f0fe5870", + "metadata": { + "editable": true + }, + "source": [ + "## To think about, first part\n", + "\n", + "When you are comparing your own code with for example **Scikit-Learn**'s\n", + "library, there are some technicalities to keep in mind. The examples\n", + "here demonstrate some of these aspects with potential pitfalls.\n", + "\n", + "The discussion here focuses on the role of the intercept, how we can\n", + "set up the design matrix, what scaling we should use and other topics\n", + "which tend confuse us.\n", + "\n", + "The intercept can be interpreted as the expected value of our\n", + "target/output variables when all other predictors are set to zero.\n", + "Thus, if we cannot assume that the expected outputs/targets are zero\n", + "when all predictors are zero (the columns in the design matrix), it\n", + "may be a bad idea to implement a model which penalizes the intercept.\n", + "Furthermore, in for example Ridge and Lasso regression (to be discussed in moe detail next week), the default solutions\n", + "from the library **Scikit-Learn** (when not shrinking $\\beta_0$) for the unknown parameters\n", + "$\\boldsymbol{\\beta}$, are derived under the assumption that both $\\boldsymbol{y}$ and\n", + "$\\boldsymbol{X}$ are zero centered, that is we subtract the mean values." + ] + }, + { + "cell_type": "markdown", + "id": "9b60a7bd", + "metadata": { + "editable": true + }, + "source": [ + "## More thinking\n", + "\n", + "If our predictors represent different scales, then it is important to\n", + "standardize the design matrix $\\boldsymbol{X}$ by subtracting the mean of each\n", + "column from the corresponding column and dividing the column with its\n", + "standard deviation. Most machine learning libraries do this as a default. This means that if you compare your code with the results from a given library,\n", + "the results may differ. \n", + "\n", + "The\n", + "[Standadscaler](https://scikit-learn.org/stable/modules/generated/sklearn.preprocessing.StandardScaler.html)\n", + "function in **Scikit-Learn** does this for us. For the data sets we\n", + "have been studying in our various examples, the data are in many cases\n", + "already scaled and there is no need to scale them. You as a user of different machine learning algorithms, should always perform a\n", + "survey of your data, with a critical assessment of them in case you need to scale the data.\n", + "\n", + "If you need to scale the data, not doing so will give an *unfair*\n", + "penalization of the parameters since their magnitude depends on the\n", + "scale of their corresponding predictor.\n", + "\n", + "Suppose as an example that you \n", + "you have an input variable given by the heights of different persons.\n", + "Human height might be measured in inches or meters or\n", + "kilometers. If measured in kilometers, a standard linear regression\n", + "model with this predictor would probably give a much bigger\n", + "coefficient term, than if measured in millimeters.\n", + "This can clearly lead to problems in evaluating the cost/loss functions." + ] + }, + { + "cell_type": "markdown", + "id": "a31dcc5d", + "metadata": { + "editable": true + }, + "source": [ + "## Still thinking\n", + "\n", + "Keep in mind that when you transform your data set before training a model, the same transformation needs to be done\n", + "on your eventual new data set before making a prediction. If we translate this into a Python code, it would could be implemented as follows\n", + "(note that the lines are commented since the model function has not been defined)" + ] + }, + { + "cell_type": "code", + "execution_count": 13, + "id": "225671c5", + "metadata": { + "collapsed": false, + "editable": true + }, + "outputs": [], + "source": [ + "#Model training, we compute the mean value of y and X\n", + "y_train_mean = np.mean(y_train)\n", + "X_train_mean = np.mean(X_train,axis=0)\n", + "X_train = X_train - X_train_mean\n", + "y_train = y_train - y_train_mean\n", + "\n", + "# The we fit our model with the training data\n", + "#trained_model = some_model.fit(X_train,y_train)\n", + "\n", + "\n", + "#Model prediction, we need also to transform our data set used for the prediction.\n", + "X_test = X_test - X_train_mean #Use mean from training data\n", + "#y_pred = trained_model(X_test)\n", + "y_pred = y_pred + y_train_mean" + ] + }, + { + "cell_type": "markdown", + "id": "ac1448c8", + "metadata": { + "editable": true + }, + "source": [ + "## What does centering (subtracting the mean values) mean mathematically?\n", + "\n", + "Let us try to understand what this may imply mathematically when we\n", + "subtract the mean values, also known as *zero centering*. For\n", + "simplicity, we will focus on ordinary regression, as done in the above example.\n", + "\n", + "The cost/loss function for regression is" + ] + }, + { + "cell_type": "markdown", + "id": "c6e308a3", + "metadata": { + "editable": true + }, + "source": [ + "$$\n", + "C(\\beta_0, \\beta_1, ... , \\beta_{p-1}) = \\frac{1}{n}\\sum_{i=0}^{n} \\left(y_i - \\beta_0 - \\sum_{j=1}^{p-1} X_{ij}\\beta_j\\right)^2,.\n", + "$$" + ] + }, + { + "cell_type": "markdown", + "id": "a2f2dab5", + "metadata": { + "editable": true + }, + "source": [ + "Recall also that we use the squared value since this leads to an increase of the penalty for higher differences between predicted and output/target values.\n", + "\n", + "What we have done is to single out the $\\beta_0$ term in the definition of the mean squared error (MSE).\n", + "The design matrix\n", + "$X$ does in this case not contain any intercept column.\n", + "When we take the derivative with respect to $\\beta_0$, we want the derivative to obey" + ] + }, + { + "cell_type": "markdown", + "id": "8a7df606", + "metadata": { + "editable": true + }, + "source": [ + "$$\n", + "\\frac{\\partial C}{\\partial \\beta_j} = 0,\n", + "$$" + ] + }, + { + "cell_type": "markdown", + "id": "31e595c9", + "metadata": { + "editable": true + }, + "source": [ + "for all $j$. For $\\beta_0$ we have" + ] + }, + { + "cell_type": "markdown", + "id": "f5f389db", + "metadata": { + "editable": true + }, + "source": [ + "$$\n", + "\\frac{\\partial C}{\\partial \\beta_0} = -\\frac{2}{n}\\sum_{i=0}^{n-1} \\left(y_i - \\beta_0 - \\sum_{j=1}^{p-1} X_{ij} \\beta_j\\right).\n", + "$$" + ] + }, + { + "cell_type": "markdown", + "id": "1dd4b34d", + "metadata": { + "editable": true + }, + "source": [ + "Multiplying away the constant $2/n$, we obtain" + ] + }, + { + "cell_type": "markdown", + "id": "f931e286", + "metadata": { + "editable": true + }, + "source": [ + "$$\n", + "\\sum_{i=0}^{n-1} \\beta_0 = \\sum_{i=0}^{n-1}y_i - \\sum_{i=0}^{n-1} \\sum_{j=1}^{p-1} X_{ij} \\beta_j.\n", + "$$" + ] + }, + { + "cell_type": "markdown", + "id": "4cbda41b", + "metadata": { + "editable": true + }, + "source": [ + "## Further Manipulations\n", + "\n", + "Let us special first to the case where we have only two parameters $\\beta_0$ and $\\beta_1$.\n", + "Our result for $\\beta_0$ simplifies then to" + ] + }, + { + "cell_type": "markdown", + "id": "6657a435", + "metadata": { + "editable": true + }, + "source": [ + "$$\n", + "n\\beta_0 = \\sum_{i=0}^{n-1}y_i - \\sum_{i=0}^{n-1} X_{i1} \\beta_1.\n", + "$$" + ] + }, + { + "cell_type": "markdown", + "id": "91f7475b", + "metadata": { + "editable": true + }, + "source": [ + "We obtain then" + ] + }, + { + "cell_type": "markdown", + "id": "98482060", + "metadata": { + "editable": true + }, + "source": [ + "$$\n", + "\\beta_0 = \\frac{1}{n}\\sum_{i=0}^{n-1}y_i - \\beta_1\\frac{1}{n}\\sum_{i=0}^{n-1} X_{i1}.\n", + "$$" + ] + }, + { + "cell_type": "markdown", + "id": "01e12c29", + "metadata": { + "editable": true + }, + "source": [ + "If we define" + ] + }, + { + "cell_type": "markdown", + "id": "38fa32e4", + "metadata": { + "editable": true + }, + "source": [ + "$$\n", + "\\mu_1=\\frac{1}{n}\\sum_{i=0}^{n-1} (X_{i1},\n", + "$$" + ] + }, + { + "cell_type": "markdown", + "id": "ea483f66", + "metadata": { + "editable": true + }, + "source": [ + "and if we define the mean value of the outputs as" + ] + }, + { + "cell_type": "markdown", + "id": "d5862089", + "metadata": { + "editable": true + }, + "source": [ + "$$\n", + "\\mu_y=\\frac{1}{n}\\sum_{i=0}^{n-1}y_i,\n", + "$$" + ] + }, + { + "cell_type": "markdown", + "id": "0456f62e", + "metadata": { + "editable": true + }, + "source": [ + "we have" + ] + }, + { + "cell_type": "markdown", + "id": "1ed14941", + "metadata": { + "editable": true + }, + "source": [ + "$$\n", + "\\beta_0 = \\mu_y - \\beta_1\\mu_{1}.\n", + "$$" + ] + }, + { + "cell_type": "markdown", + "id": "43387b69", + "metadata": { + "editable": true + }, + "source": [ + "In the general case, that is we have more parameters than $\\beta_0$ and $\\beta_1$, we have" + ] + }, + { + "cell_type": "markdown", + "id": "06bd01bf", + "metadata": { + "editable": true + }, + "source": [ + "$$\n", + "\\beta_0 = \\frac{1}{n}\\sum_{i=0}^{n-1}y_i - \\frac{1}{n}\\sum_{i=0}^{n-1}\\sum_{j=1}^{p-1} X_{ij}\\beta_j.\n", + "$$" + ] + }, + { + "cell_type": "markdown", + "id": "9cad411e", + "metadata": { + "editable": true + }, + "source": [ + "Replacing $y_i$ with $y_i - y_i - \\overline{\\boldsymbol{y}}$ and centering also our design matrix results in a cost function (in vector-matrix disguise)" + ] + }, + { + "cell_type": "markdown", + "id": "c37f7792", + "metadata": { + "editable": true + }, + "source": [ + "$$\n", + "C(\\boldsymbol{\\beta}) = (\\boldsymbol{\\tilde{y}} - \\tilde{X}\\boldsymbol{\\beta})^T(\\boldsymbol{\\tilde{y}} - \\tilde{X}\\boldsymbol{\\beta}).\n", + "$$" + ] + }, + { + "cell_type": "markdown", + "id": "8a7f23f8", + "metadata": { + "editable": true + }, + "source": [ + "## Wrapping it up\n", + "\n", + "If we minimize with respect to $\\boldsymbol{\\beta}$ we have then" + ] + }, + { + "cell_type": "markdown", + "id": "a7fdf6e8", + "metadata": { + "editable": true + }, + "source": [ + "$$\n", + "\\hat{\\boldsymbol{\\beta}} = (\\tilde{X}^T\\tilde{X})^{-1}\\tilde{X}^T\\boldsymbol{\\tilde{y}},\n", + "$$" + ] + }, + { + "cell_type": "markdown", + "id": "3ac73282", + "metadata": { + "editable": true + }, + "source": [ + "where $\\boldsymbol{\\tilde{y}} = \\boldsymbol{y} - \\overline{\\boldsymbol{y}}$\n", + "and $\\tilde{X}_{ij} = X_{ij} - \\frac{1}{n}\\sum_{k=0}^{n-1}X_{kj}$.\n", + "\n", + "For Ridge regression we need to add $\\lambda \\boldsymbol{\\beta}^T\\boldsymbol{\\beta}$ to the cost function and get then" + ] + }, + { + "cell_type": "markdown", + "id": "e55db5a0", + "metadata": { + "editable": true + }, + "source": [ + "$$\n", + "\\hat{\\boldsymbol{\\beta}} = (\\tilde{X}^T\\tilde{X} + \\lambda I)^{-1}\\tilde{X}^T\\boldsymbol{\\tilde{y}}.\n", + "$$" + ] + }, + { + "cell_type": "markdown", + "id": "966cd383", + "metadata": { + "editable": true + }, + "source": [ + "What does this mean? And why do we insist on all this? Let us look at some examples." + ] + }, + { + "cell_type": "markdown", + "id": "360cb45f", + "metadata": { + "editable": true + }, + "source": [ + "## Linear Regression code, Intercept handling first\n", + "\n", + "This code shows a simple first-order fit to a data set using the above transformed data, where we consider the role of the intercept first, by either excluding it or including it (*code example thanks to Øyvind Sigmundson Schøyen*). Here our scaling of the data is done by subtracting the mean values only.\n", + "Note also that we do not split the data into training and test." + ] + }, + { + "cell_type": "code", + "execution_count": 14, + "id": "2099267d", + "metadata": { + "collapsed": false, + "editable": true + }, + "outputs": [], + "source": [ + "import numpy as np\n", + "import matplotlib.pyplot as plt\n", + "\n", + "from sklearn.linear_model import LinearRegression\n", + "\n", + "\n", + "np.random.seed(2021)\n", + "\n", + "def MSE(y_data,y_model):\n", + " n = np.size(y_model)\n", + " return np.sum((y_data-y_model)**2)/n\n", + "\n", + "\n", + "def fit_beta(X, y):\n", + " return np.linalg.pinv(X.T @ X) @ X.T @ y\n", + "\n", + "\n", + "true_beta = [2, 0.5, 3.7]\n", + "\n", + "x = np.linspace(0, 1, 11)\n", + "y = np.sum(\n", + " np.asarray([x ** p * b for p, b in enumerate(true_beta)]), axis=0\n", + ") + 0.1 * np.random.normal(size=len(x))\n", + "\n", + "degree = 3\n", + "X = np.zeros((len(x), degree))\n", + "\n", + "# Include the intercept in the design matrix\n", + "for p in range(degree):\n", + " X[:, p] = x ** p\n", + "\n", + "beta = fit_beta(X, y)\n", + "\n", + "# Intercept is included in the design matrix\n", + "skl = LinearRegression(fit_intercept=False).fit(X, y)\n", + "\n", + "print(f\"True beta: {true_beta}\")\n", + "print(f\"Fitted beta: {beta}\")\n", + "print(f\"Sklearn fitted beta: {skl.coef_}\")\n", + "ypredictOwn = X @ beta\n", + "ypredictSKL = skl.predict(X)\n", + "print(f\"MSE with intercept column\")\n", + "print(MSE(y,ypredictOwn))\n", + "print(f\"MSE with intercept column from SKL\")\n", + "print(MSE(y,ypredictSKL))\n", + "\n", + "\n", + "plt.figure()\n", + "plt.scatter(x, y, label=\"Data\")\n", + "plt.plot(x, X @ beta, label=\"Fit\")\n", + "plt.plot(x, skl.predict(X), label=\"Sklearn (fit_intercept=False)\")\n", + "\n", + "\n", + "# Do not include the intercept in the design matrix\n", + "X = np.zeros((len(x), degree - 1))\n", + "\n", + "for p in range(degree - 1):\n", + " X[:, p] = x ** (p + 1)\n", + "\n", + "# Intercept is not included in the design matrix\n", + "skl = LinearRegression(fit_intercept=True).fit(X, y)\n", + "\n", + "# Use centered values for X and y when computing coefficients\n", + "y_offset = np.average(y, axis=0)\n", + "X_offset = np.average(X, axis=0)\n", + "\n", + "beta = fit_beta(X - X_offset, y - y_offset)\n", + "intercept = np.mean(y_offset - X_offset @ beta)\n", + "\n", + "print(f\"Manual intercept: {intercept}\")\n", + "print(f\"Fitted beta (wiothout intercept): {beta}\")\n", + "print(f\"Sklearn intercept: {skl.intercept_}\")\n", + "print(f\"Sklearn fitted beta (without intercept): {skl.coef_}\")\n", + "ypredictOwn = X @ beta\n", + "ypredictSKL = skl.predict(X)\n", + "print(f\"MSE with Manual intercept\")\n", + "print(MSE(y,ypredictOwn+intercept))\n", + "print(f\"MSE with Sklearn intercept\")\n", + "print(MSE(y,ypredictSKL))\n", + "\n", + "plt.plot(x, X @ beta + intercept, \"--\", label=\"Fit (manual intercept)\")\n", + "plt.plot(x, skl.predict(X), \"--\", label=\"Sklearn (fit_intercept=True)\")\n", + "plt.grid()\n", + "plt.legend()\n", + "\n", + "plt.show()" + ] + }, + { + "cell_type": "markdown", + "id": "9ba9afe9", + "metadata": { + "editable": true + }, + "source": [ + "The intercept is the value of our output/target variable\n", + "when all our features are zero and our function crosses the $y$-axis (for a one-dimensional case). \n", + "\n", + "Printing the MSE, we see first that both methods give the same MSE, as\n", + "they should. However, when we move to for example Ridge regression (discussed next week),\n", + "the way we treat the intercept may give a larger or smaller MSE,\n", + "meaning that the MSE can be penalized by the value of the\n", + "intercept. Not including the intercept in the fit, means that the\n", + "regularization term does not include $\\beta_0$. For different values\n", + "of $\\lambda$, this may lead to differing MSE values. \n", + "\n", + "To remind the reader, the regularization term, with the intercept in Ridge regression is given by" + ] + }, + { + "cell_type": "markdown", + "id": "ea4bf6fe", + "metadata": { + "editable": true + }, + "source": [ + "$$\n", + "\\lambda \\vert\\vert \\boldsymbol{\\beta} \\vert\\vert_2^2 = \\lambda \\sum_{j=0}^{p-1}\\beta_j^2,\n", + "$$" + ] + }, + { + "cell_type": "markdown", + "id": "98ca9b28", + "metadata": { + "editable": true + }, + "source": [ + "but when we take out the intercept, this equation becomes" + ] + }, + { + "cell_type": "markdown", + "id": "996fc4f6", + "metadata": { + "editable": true + }, + "source": [ + "$$\n", + "\\lambda \\vert\\vert \\boldsymbol{\\beta} \\vert\\vert_2^2 = \\lambda \\sum_{j=1}^{p-1}\\beta_j^2.\n", + "$$" + ] + }, + { + "cell_type": "markdown", + "id": "b5db8128", + "metadata": { + "editable": true + }, + "source": [ + "For Lasso regression we have" + ] + }, + { + "cell_type": "markdown", + "id": "745d6bff", + "metadata": { + "editable": true + }, + "source": [ + "$$\n", + "\\lambda \\vert\\vert \\boldsymbol{\\beta} \\vert\\vert_1 = \\lambda \\sum_{j=1}^{p-1}\\vert\\beta_j\\vert.\n", + "$$" + ] + }, + { + "cell_type": "markdown", + "id": "2ecb048e", + "metadata": { + "editable": true + }, + "source": [ + "It means that, when scaling the design matrix and the outputs/targets,\n", + "by subtracting the mean values, we have an optimization problem which\n", + "is not penalized by the intercept. The MSE value can then be smaller\n", + "since it focuses only on the remaining quantities. If we however bring\n", + "back the intercept, we will get an MSE which then contains the\n", + "intercept. This becomes more important when we discuss Ridge and Lasso\n", + "regression next week." + ] + }, + { + "cell_type": "markdown", + "id": "73eb2f08", + "metadata": { + "editable": true + }, + "source": [ + "## The Boston housing data example\n", + "\n", + "The Boston housing \n", + "data set was originally a part of UCI Machine Learning Repository\n", + "and has been removed now. The data set is now included in **Scikit-Learn**'s \n", + "library. There are 506 samples and 13 feature (predictor) variables\n", + "in this data set. The objective is to predict the value of prices of\n", + "the house using the features (predictors) listed here.\n", + "\n", + "The features/predictors are\n", + "1. CRIM: Per capita crime rate by town\n", + "\n", + "2. ZN: Proportion of residential land zoned for lots over 25000 square feet\n", + "\n", + "3. INDUS: Proportion of non-retail business acres per town\n", + "\n", + "4. CHAS: Charles River dummy variable (= 1 if tract bounds river; 0 otherwise)\n", + "\n", + "5. NOX: Nitric oxide concentration (parts per 10 million)\n", + "\n", + "6. RM: Average number of rooms per dwelling\n", + "\n", + "7. AGE: Proportion of owner-occupied units built prior to 1940\n", + "\n", + "8. DIS: Weighted distances to five Boston employment centers\n", + "\n", + "9. RAD: Index of accessibility to radial highways\n", + "\n", + "10. TAX: Full-value property tax rate per USD10000\n", + "\n", + "11. B: $1000(Bk - 0.63)^2$, where $Bk$ is the proportion of [people of African American descent] by town\n", + "\n", + "12. LSTAT: Percentage of lower status of the population\n", + "\n", + "13. MEDV: Median value of owner-occupied homes in USD 1000s" + ] + }, + { + "cell_type": "markdown", + "id": "41d9c008", + "metadata": { + "editable": true + }, + "source": [ + "## Housing data, the code\n", + "We start by importing the libraries" + ] + }, + { + "cell_type": "code", + "execution_count": 15, + "id": "0af3b38a", + "metadata": { + "collapsed": false, + "editable": true + }, + "outputs": [], + "source": [ + "import numpy as np\n", + "import matplotlib.pyplot as plt \n", + "\n", + "import pandas as pd \n", + "import seaborn as sns" + ] + }, + { + "cell_type": "markdown", + "id": "41771944", + "metadata": { + "editable": true + }, + "source": [ + "and load the Boston Housing DataSet from **Scikit-Learn**" + ] + }, + { + "cell_type": "code", + "execution_count": 16, + "id": "c0ad90ff", + "metadata": { + "collapsed": false, + "editable": true + }, + "outputs": [], + "source": [ + "from sklearn.datasets import load_boston\n", + "\n", + "boston_dataset = load_boston()\n", + "\n", + "# boston_dataset is a dictionary\n", + "# let's check what it contains\n", + "boston_dataset.keys()" + ] + }, + { + "cell_type": "markdown", + "id": "ef2f9bce", + "metadata": { + "editable": true + }, + "source": [ + "Then we invoke Pandas" + ] + }, + { + "cell_type": "code", + "execution_count": 17, + "id": "150d1433", + "metadata": { + "collapsed": false, + "editable": true + }, + "outputs": [], + "source": [ + "boston = pd.DataFrame(boston_dataset.data, columns=boston_dataset.feature_names)\n", + "boston.head()\n", + "boston['MEDV'] = boston_dataset.target" + ] + }, + { + "cell_type": "markdown", + "id": "1be017ef", + "metadata": { + "editable": true + }, + "source": [ + "and preprocess the data" + ] + }, + { + "cell_type": "code", + "execution_count": 18, + "id": "01ef8953", + "metadata": { + "collapsed": false, + "editable": true + }, + "outputs": [], + "source": [ + "# check for missing values in all the columns\n", + "boston.isnull().sum()" + ] + }, + { + "cell_type": "markdown", + "id": "adc486b5", + "metadata": { + "editable": true + }, + "source": [ + "We can then visualize the data" + ] + }, + { + "cell_type": "code", + "execution_count": 19, + "id": "2471fc63", + "metadata": { + "collapsed": false, + "editable": true + }, + "outputs": [], + "source": [ + "# set the size of the figure\n", + "sns.set(rc={'figure.figsize':(11.7,8.27)})\n", + "\n", + "# plot a histogram showing the distribution of the target values\n", + "sns.distplot(boston['MEDV'], bins=30)\n", + "plt.show()" + ] + }, + { + "cell_type": "markdown", + "id": "e26d39f7", + "metadata": { + "editable": true + }, + "source": [ + "It is now useful to look at the correlation matrix" + ] + }, + { + "cell_type": "code", + "execution_count": 20, + "id": "6bb60001", + "metadata": { + "collapsed": false, + "editable": true + }, + "outputs": [], + "source": [ + "# compute the pair wise correlation for all columns \n", + "correlation_matrix = boston.corr().round(2)\n", + "# use the heatmap function from seaborn to plot the correlation matrix\n", + "# annot = True to print the values inside the square\n", + "sns.heatmap(data=correlation_matrix, annot=True)" + ] + }, + { + "cell_type": "markdown", + "id": "90f47dc1", + "metadata": { + "editable": true + }, + "source": [ + "From the above coorelation plot we can see that **MEDV** is strongly correlated to **LSTAT** and **RM**. We see also that **RAD** and **TAX** are stronly correlated, but we don't include this in our features together to avoid multi-colinearity" + ] + }, + { + "cell_type": "code", + "execution_count": 21, + "id": "a1f980e4", + "metadata": { + "collapsed": false, + "editable": true + }, + "outputs": [], + "source": [ + "plt.figure(figsize=(20, 5))\n", + "\n", + "features = ['LSTAT', 'RM']\n", + "target = boston['MEDV']\n", + "\n", + "for i, col in enumerate(features):\n", + " plt.subplot(1, len(features) , i+1)\n", + " x = boston[col]\n", + " y = target\n", + " plt.scatter(x, y, marker='o')\n", + " plt.title(col)\n", + " plt.xlabel(col)\n", + " plt.ylabel('MEDV')" + ] + }, + { + "cell_type": "markdown", + "id": "9efdaaaa", + "metadata": { + "editable": true + }, + "source": [ + "Now we start training our model" + ] + }, + { + "cell_type": "code", + "execution_count": 22, + "id": "01e9afe5", + "metadata": { + "collapsed": false, + "editable": true + }, + "outputs": [], + "source": [ + "X = pd.DataFrame(np.c_[boston['LSTAT'], boston['RM']], columns = ['LSTAT','RM'])\n", + "Y = boston['MEDV']" + ] + }, + { + "cell_type": "markdown", + "id": "73335565", + "metadata": { + "editable": true + }, + "source": [ + "We split the data into training and test sets" + ] + }, + { + "cell_type": "code", + "execution_count": 23, + "id": "f865febb", + "metadata": { + "collapsed": false, + "editable": true + }, + "outputs": [], + "source": [ + "from sklearn.model_selection import train_test_split\n", + "\n", + "# splits the training and test data set in 80% : 20%\n", + "# assign random_state to any value.This ensures consistency.\n", + "X_train, X_test, Y_train, Y_test = train_test_split(X, Y, test_size = 0.2, random_state=5)\n", + "print(X_train.shape)\n", + "print(X_test.shape)\n", + "print(Y_train.shape)\n", + "print(Y_test.shape)" + ] + }, + { + "cell_type": "markdown", + "id": "88f5a339", + "metadata": { + "editable": true + }, + "source": [ + "Then we use the linear regression functionality from **Scikit-Learn**" + ] + }, + { + "cell_type": "code", + "execution_count": 24, + "id": "bacdbf9b", + "metadata": { + "collapsed": false, + "editable": true + }, + "outputs": [], + "source": [ + "from sklearn.linear_model import LinearRegression\n", + "from sklearn.metrics import mean_squared_error, r2_score\n", + "\n", + "lin_model = LinearRegression()\n", + "lin_model.fit(X_train, Y_train)\n", + "\n", + "# model evaluation for training set\n", + "\n", + "y_train_predict = lin_model.predict(X_train)\n", + "rmse = (np.sqrt(mean_squared_error(Y_train, y_train_predict)))\n", + "r2 = r2_score(Y_train, y_train_predict)\n", + "\n", + "print(\"The model performance for training set\")\n", + "print(\"--------------------------------------\")\n", + "print('RMSE is {}'.format(rmse))\n", + "print('R2 score is {}'.format(r2))\n", + "print(\"\\n\")\n", + "\n", + "# model evaluation for testing set\n", + "\n", + "y_test_predict = lin_model.predict(X_test)\n", + "# root mean square error of the model\n", + "rmse = (np.sqrt(mean_squared_error(Y_test, y_test_predict)))\n", + "\n", + "# r-squared score of the model\n", + "r2 = r2_score(Y_test, y_test_predict)\n", + "\n", + "print(\"The model performance for testing set\")\n", + "print(\"--------------------------------------\")\n", + "print('RMSE is {}'.format(rmse))\n", + "print('R2 score is {}'.format(r2))" + ] + }, + { + "cell_type": "code", + "execution_count": 25, + "id": "09aa7ac9", + "metadata": { + "collapsed": false, + "editable": true + }, + "outputs": [], + "source": [ + "# plotting the y_test vs y_pred\n", + "# ideally should have been a straight line\n", + "plt.scatter(Y_test, y_test_predict)\n", + "plt.show()" + ] + }, + { + "cell_type": "markdown", + "id": "cb088f7a", + "metadata": { + "editable": true + }, + "source": [ + "## Material for lecture Thursday, August 31" + ] + }, + { + "cell_type": "markdown", + "id": "a452bf26", + "metadata": { + "editable": true + }, + "source": [ + "## Mathematical Interpretation of Ordinary Least Squares\n", + "\n", + "What is presented here is a mathematical analysis of various regression algorithms (ordinary least squares, Ridge and Lasso Regression). The analysis is based on an important algorithm in linear algebra, the so-called Singular Value Decomposition (SVD). \n", + "\n", + "We have shown that in ordinary least squares the optimal parameters $\\beta$ are given by" + ] + }, + { + "cell_type": "markdown", + "id": "603ea987", + "metadata": { + "editable": true + }, + "source": [ + "$$\n", + "\\hat{\\boldsymbol{\\beta}} = \\left(\\boldsymbol{X}^T\\boldsymbol{X}\\right)^{-1}\\boldsymbol{X}^T\\boldsymbol{y}.\n", + "$$" + ] + }, + { + "cell_type": "markdown", + "id": "61b65c66", + "metadata": { + "editable": true + }, + "source": [ + "The **hat** over $\\boldsymbol{\\beta}$ means we have the optimal parameters after minimization of the cost function.\n", + "\n", + "This means that our best model is defined as" + ] + }, + { + "cell_type": "markdown", + "id": "d08fd064", + "metadata": { + "editable": true + }, + "source": [ + "$$\n", + "\\tilde{\\boldsymbol{y}}=\\boldsymbol{X}\\hat{\\boldsymbol{\\beta}} = \\boldsymbol{X}\\left(\\boldsymbol{X}^T\\boldsymbol{X}\\right)^{-1}\\boldsymbol{X}^T\\boldsymbol{y}.\n", + "$$" + ] + }, + { + "cell_type": "markdown", + "id": "e8f62983", + "metadata": { + "editable": true + }, + "source": [ + "We now define a matrix" + ] + }, + { + "cell_type": "markdown", + "id": "d68a9415", + "metadata": { + "editable": true + }, + "source": [ + "$$\n", + "\\boldsymbol{A}=\\boldsymbol{X}\\left(\\boldsymbol{X}^T\\boldsymbol{X}\\right)^{-1}\\boldsymbol{X}^T.\n", + "$$" + ] + }, + { + "cell_type": "markdown", + "id": "3307fed7", + "metadata": { + "editable": true + }, + "source": [ + "We can rewrite" + ] + }, + { + "cell_type": "markdown", + "id": "8a910e57", + "metadata": { + "editable": true + }, + "source": [ + "$$\n", + "\\tilde{\\boldsymbol{y}}=\\boldsymbol{X}\\hat{\\boldsymbol{\\beta}} = \\boldsymbol{A}\\boldsymbol{y}.\n", + "$$" + ] + }, + { + "cell_type": "markdown", + "id": "218a6b48", + "metadata": { + "editable": true + }, + "source": [ + "The matrix $\\boldsymbol{A}$ has the important property that $\\boldsymbol{A}^2=\\boldsymbol{A}$. This is the definition of a projection matrix.\n", + "We can then interpret our optimal model $\\tilde{\\boldsymbol{y}}$ as being represented by an orthogonal projection of $\\boldsymbol{y}$ onto a space defined by the column vectors of $\\boldsymbol{X}$. In our case here the matrix $\\boldsymbol{A}$ is a square matrix. If it is a general rectangular matrix we have an oblique projection matrix." + ] + }, + { + "cell_type": "markdown", + "id": "8f3748ba", + "metadata": { + "editable": true + }, + "source": [ + "## Residual Error\n", + "\n", + "We have defined the residual error as" + ] + }, + { + "cell_type": "markdown", + "id": "d0385420", + "metadata": { + "editable": true + }, + "source": [ + "$$\n", + "\\boldsymbol{\\epsilon}=\\boldsymbol{y}-\\tilde{\\boldsymbol{y}}=\\left[\\boldsymbol{I}-\\boldsymbol{X}\\left(\\boldsymbol{X}^T\\boldsymbol{X}\\right)^{-1}\\boldsymbol{X}^T\\right]\\boldsymbol{y}.\n", + "$$" + ] + }, + { + "cell_type": "markdown", + "id": "4644a05e", + "metadata": { + "editable": true + }, + "source": [ + "The residual errors are then the projections of $\\boldsymbol{y}$ onto the orthogonal component of the space defined by the column vectors of $\\boldsymbol{X}$." + ] + }, + { + "cell_type": "markdown", + "id": "bfb350df", + "metadata": { + "editable": true + }, + "source": [ + "## Simple case\n", + "\n", + "If the matrix $\\boldsymbol{X}$ is an orthogonal (or unitary in case of complex values) matrix, we have" + ] + }, + { + "cell_type": "markdown", + "id": "508acac7", + "metadata": { + "editable": true + }, + "source": [ + "$$\n", + "\\boldsymbol{X}^T\\boldsymbol{X}=\\boldsymbol{X}\\boldsymbol{X}^T = \\boldsymbol{I}.\n", + "$$" + ] + }, + { + "cell_type": "markdown", + "id": "1cde0c41", + "metadata": { + "editable": true + }, + "source": [ + "In this case the matrix $\\boldsymbol{A}$ becomes" + ] + }, + { + "cell_type": "markdown", + "id": "683baaea", + "metadata": { + "editable": true + }, + "source": [ + "$$\n", + "\\boldsymbol{A}=\\boldsymbol{X}\\left(\\boldsymbol{X}^T\\boldsymbol{X}\\right)^{-1}\\boldsymbol{X}^T)=\\boldsymbol{I},\n", + "$$" + ] + }, + { + "cell_type": "markdown", + "id": "ec9c67ea", + "metadata": { + "editable": true + }, + "source": [ + "and we have the obvious case" + ] + }, + { + "cell_type": "markdown", + "id": "cdc9c6fc", + "metadata": { + "editable": true + }, + "source": [ + "$$\n", + "\\boldsymbol{\\epsilon}=\\boldsymbol{y}-\\tilde{\\boldsymbol{y}}=0.\n", + "$$" + ] + }, + { + "cell_type": "markdown", + "id": "c7590b65", + "metadata": { + "editable": true + }, + "source": [ + "This serves also as a useful test of our codes." + ] + }, + { + "cell_type": "markdown", + "id": "f2d7afb2", + "metadata": { + "editable": true + }, + "source": [ + "## The singular value decomposition\n", + "\n", + "The examples we have looked at so far are cases where we normally can\n", + "invert the matrix $\\boldsymbol{X}^T\\boldsymbol{X}$. Using a polynomial expansion where we fit of various functions leads to\n", + "row vectors of the design matrix which are essentially orthogonal due\n", + "to the polynomial character of our model. Obtaining the inverse of the\n", + "design matrix is then often done via a so-called LU, QR or Cholesky\n", + "decomposition.\n", + "\n", + "As we will also see in the first project, \n", + "this may\n", + "however not the be case in general and a standard matrix inversion\n", + "algorithm based on say LU, QR or Cholesky decomposition may lead to singularities. We will see examples of this below.\n", + "\n", + "There is however a way to circumvent this problem and also\n", + "gain some insights about the ordinary least squares approach, and\n", + "later shrinkage methods like Ridge and Lasso regressions.\n", + "\n", + "This is given by the **Singular Value Decomposition** (SVD) algorithm,\n", + "perhaps the most powerful linear algebra algorithm. The SVD provides\n", + "a numerically stable matrix decomposition that is used in a large\n", + "swath oc applications and the decomposition is always stable\n", + "numerically.\n", + "\n", + "In machine learning it plays a central role in dealing with for\n", + "example design matrices that may be near singular or singular.\n", + "Furthermore, as we will see here, the singular values can be related\n", + "to the covariance matrix (and thereby the correlation matrix) and in\n", + "turn the variance of a given quantity. It plays also an important role\n", + "in the principal component analysis where high-dimensional data can be\n", + "reduced to the statistically relevant features." + ] + }, + { + "cell_type": "markdown", + "id": "69fd907d", + "metadata": { + "editable": true + }, + "source": [ + "## Linear Regression Problems\n", + "\n", + "One of the typical problems we encounter with linear regression, in particular \n", + "when the matrix $\\boldsymbol{X}$ (our so-called design matrix) is high-dimensional, \n", + "are problems with near singular or singular matrices. The column vectors of $\\boldsymbol{X}$ \n", + "may be linearly dependent, normally referred to as super-collinearity. \n", + "This means that the matrix may be rank deficient and it is basically impossible to \n", + "to model the data using linear regression. As an example, consider the matrix" + ] + }, + { + "cell_type": "markdown", + "id": "33b93521", + "metadata": { + "editable": true + }, + "source": [ + "$$\n", + "\\begin{align*}\n", + "\\mathbf{X} & = \\left[\n", + "\\begin{array}{rrr}\n", + "1 & -1 & 2\n", + "\\\\\n", + "1 & 0 & 1\n", + "\\\\\n", + "1 & 2 & -1\n", + "\\\\\n", + "1 & 1 & 0\n", + "\\end{array} \\right]\n", + "\\end{align*}\n", + "$$" + ] + }, + { + "cell_type": "markdown", + "id": "600d8db6", + "metadata": { + "editable": true + }, + "source": [ + "The columns of $\\boldsymbol{X}$ are linearly dependent. We see this easily since the \n", + "the first column is the row-wise sum of the other two columns. The rank (more correct,\n", + "the column rank) of a matrix is the dimension of the space spanned by the\n", + "column vectors. Hence, the rank of $\\mathbf{X}$ is equal to the number\n", + "of linearly independent columns. In this particular case the matrix has rank 2.\n", + "\n", + "Super-collinearity of an $(n \\times p)$-dimensional design matrix $\\mathbf{X}$ implies\n", + "that the inverse of the matrix $\\boldsymbol{X}^T\\boldsymbol{X}$ (the matrix we need to invert to solve the linear regression equations) is non-invertible. If we have a square matrix that does not have an inverse, we say this matrix singular. The example here demonstrates this" + ] + }, + { + "cell_type": "markdown", + "id": "22fc0a80", + "metadata": { + "editable": true + }, + "source": [ + "$$\n", + "\\begin{align*}\n", + "\\boldsymbol{X} & = \\left[\n", + "\\begin{array}{rr}\n", + "1 & -1\n", + "\\\\\n", + "1 & -1\n", + "\\end{array} \\right].\n", + "\\end{align*}\n", + "$$" + ] + }, + { + "cell_type": "markdown", + "id": "bd71990f", + "metadata": { + "editable": true + }, + "source": [ + "We see easily that $\\mbox{det}(\\boldsymbol{X}) = x_{11} x_{22} - x_{12} x_{21} = 1 \\times (-1) - 1 \\times (-1) = 0$. Hence, $\\mathbf{X}$ is singular and its inverse is undefined.\n", + "This is equivalent to saying that the matrix $\\boldsymbol{X}$ has at least an eigenvalue which is zero." + ] + }, + { + "cell_type": "markdown", + "id": "587d44ae", + "metadata": { + "editable": true + }, + "source": [ + "## Fixing the singularity\n", + "\n", + "If our design matrix $\\boldsymbol{X}$ which enters the linear regression problem" + ] + }, + { + "cell_type": "markdown", + "id": "2158156f", + "metadata": { + "editable": true + }, + "source": [ + "\n", + "
    \n", + "\n", + "$$\n", + "\\begin{equation}\n", + "\\boldsymbol{\\beta} = (\\boldsymbol{X}^{T} \\boldsymbol{X})^{-1} \\boldsymbol{X}^{T} \\boldsymbol{y},\n", + "\\label{_auto1} \\tag{1}\n", + "\\end{equation}\n", + "$$" + ] + }, + { + "cell_type": "markdown", + "id": "10eb0b7c", + "metadata": { + "editable": true + }, + "source": [ + "has linearly dependent column vectors, we will not be able to compute the inverse\n", + "of $\\boldsymbol{X}^T\\boldsymbol{X}$ and we cannot find the parameters (estimators) $\\beta_i$. \n", + "The estimators are only well-defined if $(\\boldsymbol{X}^{T}\\boldsymbol{X})^{-1}$ exits. \n", + "This is more likely to happen when the matrix $\\boldsymbol{X}$ is high-dimensional. In this case it is likely to encounter a situation where \n", + "the regression parameters $\\beta_i$ cannot be estimated.\n", + "\n", + "A cheap *ad hoc* approach is simply to add a small diagonal component to the matrix to invert, that is we change" + ] + }, + { + "cell_type": "markdown", + "id": "2aceb644", + "metadata": { + "editable": true + }, + "source": [ + "$$\n", + "\\boldsymbol{X}^{T} \\boldsymbol{X} \\rightarrow \\boldsymbol{X}^{T} \\boldsymbol{X}+\\lambda \\boldsymbol{I},\n", + "$$" + ] + }, + { + "cell_type": "markdown", + "id": "1465b8be", + "metadata": { + "editable": true + }, + "source": [ + "where $\\boldsymbol{I}$ is the identity matrix. When we discuss **Ridge** regression this is actually what we end up evaluating. The parameter $\\lambda$ is called a hyperparameter. More about this later." + ] + }, + { + "cell_type": "markdown", + "id": "b3afc822", + "metadata": { + "editable": true + }, + "source": [ + "## Basic math of the SVD\n", + "\n", + "From standard linear algebra we know that a square matrix $\\boldsymbol{X}$ can be diagonalized if and only it is \n", + "a so-called [normal matrix](https://en.wikipedia.org/wiki/Normal_matrix), that is if $\\boldsymbol{X}\\in {\\mathbb{R}}^{n\\times n}$\n", + "we have $\\boldsymbol{X}\\boldsymbol{X}^T=\\boldsymbol{X}^T\\boldsymbol{X}$ or if $\\boldsymbol{X}\\in {\\mathbb{C}}^{n\\times n}$ we have $\\boldsymbol{X}\\boldsymbol{X}^{\\dagger}=\\boldsymbol{X}^{\\dagger}\\boldsymbol{X}$.\n", + "The matrix has then a set of eigenpairs" + ] + }, + { + "cell_type": "markdown", + "id": "4357f67d", + "metadata": { + "editable": true + }, + "source": [ + "$$\n", + "(\\lambda_1,\\boldsymbol{u}_1),\\dots, (\\lambda_n,\\boldsymbol{u}_n),\n", + "$$" + ] + }, + { + "cell_type": "markdown", + "id": "b2ed8199", + "metadata": { + "editable": true + }, + "source": [ + "and the eigenvalues are given by the diagonal matrix" + ] + }, + { + "cell_type": "markdown", + "id": "a28f5e2a", + "metadata": { + "editable": true + }, + "source": [ + "$$\n", + "\\boldsymbol{\\Sigma}=\\mathrm{Diag}(\\lambda_1, \\dots,\\lambda_n).\n", + "$$" + ] + }, + { + "cell_type": "markdown", + "id": "dda00171", + "metadata": { + "editable": true + }, + "source": [ + "The matrix $\\boldsymbol{X}$ can be written in terms of an orthogonal/unitary transformation $\\boldsymbol{U}$" + ] + }, + { + "cell_type": "markdown", + "id": "99e49156", + "metadata": { + "editable": true + }, + "source": [ + "$$\n", + "\\boldsymbol{X} = \\boldsymbol{U}\\boldsymbol{\\Sigma}\\boldsymbol{V}^T,\n", + "$$" + ] + }, + { + "cell_type": "markdown", + "id": "3de354b0", + "metadata": { + "editable": true + }, + "source": [ + "with $\\boldsymbol{U}\\boldsymbol{U}^T=\\boldsymbol{I}$ or $\\boldsymbol{U}\\boldsymbol{U}^{\\dagger}=\\boldsymbol{I}$.\n", + "\n", + "Not all square matrices are diagonalizable. A matrix like the one discussed above" + ] + }, + { + "cell_type": "markdown", + "id": "9b719377", + "metadata": { + "editable": true + }, + "source": [ + "$$\n", + "\\boldsymbol{X} = \\begin{bmatrix} \n", + "1& -1 \\\\\n", + "1& -1\\\\\n", + "\\end{bmatrix}\n", + "$$" + ] + }, + { + "cell_type": "markdown", + "id": "f46453c7", + "metadata": { + "editable": true + }, + "source": [ + "is not diagonalizable, it is a so-called [defective matrix](https://en.wikipedia.org/wiki/Defective_matrix). It is easy to see that the condition\n", + "$\\boldsymbol{X}\\boldsymbol{X}^T=\\boldsymbol{X}^T\\boldsymbol{X}$ is not fulfilled." + ] + }, + { + "cell_type": "markdown", + "id": "0255efb1", + "metadata": { + "editable": true + }, + "source": [ + "## The SVD, a Fantastic Algorithm\n", + "\n", + "However, and this is the strength of the SVD algorithm, any general\n", + "matrix $\\boldsymbol{X}$ can be decomposed in terms of a diagonal matrix and\n", + "two orthogonal/unitary matrices. The [Singular Value Decompostion\n", + "(SVD) theorem](https://en.wikipedia.org/wiki/Singular_value_decomposition)\n", + "states that a general $m\\times n$ matrix $\\boldsymbol{X}$ can be written in\n", + "terms of a diagonal matrix $\\boldsymbol{\\Sigma}$ of dimensionality $m\\times n$\n", + "and two orthognal matrices $\\boldsymbol{U}$ and $\\boldsymbol{V}$, where the first has\n", + "dimensionality $m \\times m$ and the last dimensionality $n\\times n$.\n", + "We have then" + ] + }, + { + "cell_type": "markdown", + "id": "61df6aad", + "metadata": { + "editable": true + }, + "source": [ + "$$\n", + "\\boldsymbol{X} = \\boldsymbol{U}\\boldsymbol{\\Sigma}\\boldsymbol{V}^T\n", + "$$" + ] + }, + { + "cell_type": "markdown", + "id": "ac44e8fa", + "metadata": { + "editable": true + }, + "source": [ + "As an example, the above defective matrix can be decomposed as" + ] + }, + { + "cell_type": "markdown", + "id": "a73ed285", + "metadata": { + "editable": true + }, + "source": [ + "$$\n", + "\\boldsymbol{X} = \\frac{1}{\\sqrt{2}}\\begin{bmatrix} 1& 1 \\\\ 1& -1\\\\ \\end{bmatrix} \\begin{bmatrix} 2& 0 \\\\ 0& 0\\\\ \\end{bmatrix} \\frac{1}{\\sqrt{2}}\\begin{bmatrix} 1& -1 \\\\ 1& 1\\\\ \\end{bmatrix}=\\boldsymbol{U}\\boldsymbol{\\Sigma}\\boldsymbol{V}^T,\n", + "$$" + ] + }, + { + "cell_type": "markdown", + "id": "4809c104", + "metadata": { + "editable": true + }, + "source": [ + "with eigenvalues $\\sigma_1=2$ and $\\sigma_2=0$. \n", + "The SVD exits always! \n", + "\n", + "The SVD\n", + "decomposition (singular values) gives eigenvalues \n", + "$\\sigma_i\\geq\\sigma_{i+1}$ for all $i$ and for dimensions larger than $i=p$, the\n", + "eigenvalues (singular values) are zero.\n", + "\n", + "In the general case, where our design matrix $\\boldsymbol{X}$ has dimension\n", + "$n\\times p$, the matrix is thus decomposed into an $n\\times n$\n", + "orthogonal matrix $\\boldsymbol{U}$, a $p\\times p$ orthogonal matrix $\\boldsymbol{V}$\n", + "and a diagonal matrix $\\boldsymbol{\\Sigma}$ with $r=\\mathrm{min}(n,p)$\n", + "singular values $\\sigma_i\\geq 0$ on the main diagonal and zeros filling\n", + "the rest of the matrix. There are at most $p$ singular values\n", + "assuming that $n > p$. In our regression examples for the nuclear\n", + "masses and the equation of state this is indeed the case, while for\n", + "the Ising model we have $p > n$. These are often cases that lead to\n", + "near singular or singular matrices.\n", + "\n", + "The columns of $\\boldsymbol{U}$ are called the left singular vectors while the columns of $\\boldsymbol{V}$ are the right singular vectors." + ] + }, + { + "cell_type": "markdown", + "id": "9ff4078a", + "metadata": { + "editable": true + }, + "source": [ + "## Economy-size SVD\n", + "\n", + "If we assume that $n > p$, then our matrix $\\boldsymbol{U}$ has dimension $n\n", + "\\times n$. The last $n-p$ columns of $\\boldsymbol{U}$ become however\n", + "irrelevant in our calculations since they are multiplied with the\n", + "zeros in $\\boldsymbol{\\Sigma}$.\n", + "\n", + "The economy-size decomposition removes extra rows or columns of zeros\n", + "from the diagonal matrix of singular values, $\\boldsymbol{\\Sigma}$, along with the columns\n", + "in either $\\boldsymbol{U}$ or $\\boldsymbol{V}$ that multiply those zeros in the expression. \n", + "Removing these zeros and columns can improve execution time\n", + "and reduce storage requirements without compromising the accuracy of\n", + "the decomposition.\n", + "\n", + "If $n > p$, we keep only the first $p$ columns of $\\boldsymbol{U}$ and $\\boldsymbol{\\Sigma}$ has dimension $p\\times p$. \n", + "If $p > n$, then only the first $n$ columns of $\\boldsymbol{V}$ are computed and $\\boldsymbol{\\Sigma}$ has dimension $n\\times n$.\n", + "The $n=p$ case is obvious, we retain the full SVD. \n", + "In general the economy-size SVD leads to less FLOPS and still conserving the desired accuracy." + ] + }, + { + "cell_type": "markdown", + "id": "78a8b113", + "metadata": { + "editable": true + }, + "source": [ + "## Codes for the SVD" + ] + }, + { + "cell_type": "code", + "execution_count": 26, + "id": "47f6d805", + "metadata": { + "collapsed": false, + "editable": true + }, + "outputs": [], + "source": [ + "import numpy as np\n", + "# SVD inversion\n", + "def SVD(A):\n", + " ''' Takes as input a numpy matrix A and returns inv(A) based on singular value decomposition (SVD).\n", + " SVD is numerically more stable than the inversion algorithms provided by\n", + " numpy and scipy.linalg at the cost of being slower.\n", + " '''\n", + " U, S, VT = np.linalg.svd(A,full_matrices=True)\n", + " print('test U')\n", + " print( (np.transpose(U) @ U - U @np.transpose(U)))\n", + " print('test VT')\n", + " print( (np.transpose(VT) @ VT - VT @np.transpose(VT)))\n", + " print(U)\n", + " print(S)\n", + " print(VT)\n", + "\n", + " D = np.zeros((len(U),len(VT)))\n", + " for i in range(0,len(VT)):\n", + " D[i,i]=S[i]\n", + " return U @ D @ VT\n", + "\n", + "\n", + "X = np.array([ [1.0,-1.0], [1.0,-1.0]])\n", + "#X = np.array([[1, 2], [3, 4], [5, 6]])\n", + "\n", + "print(X)\n", + "C = SVD(X)\n", + "# Print the difference between the original matrix and the SVD one\n", + "print(C-X)" + ] + }, + { + "cell_type": "markdown", + "id": "5d841c14", + "metadata": { + "editable": true + }, + "source": [ + "The matrix $\\boldsymbol{X}$ has columns that are linearly dependent. The first\n", + "column is the row-wise sum of the other two columns. The rank of a\n", + "matrix (the column rank) is the dimension of space spanned by the\n", + "column vectors. The rank of the matrix is the number of linearly\n", + "independent columns, in this case just $2$. We see this from the\n", + "singular values when running the above code. Running the standard\n", + "inversion algorithm for matrix inversion with $\\boldsymbol{X}^T\\boldsymbol{X}$ results\n", + "in the program terminating due to a singular matrix." + ] + }, + { + "cell_type": "markdown", + "id": "579b46a4", + "metadata": { + "editable": true + }, + "source": [ + "## Note about SVD Calculations\n", + "\n", + "The $U$, $S$, and $V$ matrices returned from the **svd()** function\n", + "cannot be multiplied directly.\n", + "\n", + "As you can see from the code, the $S$ vector must be converted into a\n", + "diagonal matrix. This may cause a problem as the size of the matrices\n", + "do not fit the rules of matrix multiplication, where the number of\n", + "columns in a matrix must match the number of rows in the subsequent\n", + "matrix.\n", + "\n", + "If you wish to include the zero singular values, you will need to\n", + "resize the matrices and set up a diagonal matrix as done in the above\n", + "example" + ] + }, + { + "cell_type": "markdown", + "id": "1bb48e3c", + "metadata": { + "editable": true + }, + "source": [ + "## Mathematics of the SVD and implications\n", + "\n", + "Let us take a closer look at the mathematics of the SVD and the various implications for machine learning studies.\n", + "\n", + "Our starting point is our design matrix $\\boldsymbol{X}$ of dimension $n\\times p$" + ] + }, + { + "cell_type": "markdown", + "id": "a872fcf9", + "metadata": { + "editable": true + }, + "source": [ + "$$\n", + "\\boldsymbol{X}=\\begin{bmatrix}\n", + "x_{0,0} & x_{0,1} & x_{0,2}& \\dots & \\dots x_{0,p-1}\\\\\n", + "x_{1,0} & x_{1,1} & x_{1,2}& \\dots & \\dots x_{1,p-1}\\\\\n", + "x_{2,0} & x_{2,1} & x_{2,2}& \\dots & \\dots x_{2,p-1}\\\\\n", + "\\dots & \\dots & \\dots & \\dots \\dots & \\dots \\\\\n", + "x_{n-2,0} & x_{n-2,1} & x_{n-2,2}& \\dots & \\dots x_{n-2,p-1}\\\\\n", + "x_{n-1,0} & x_{n-1,1} & x_{n-1,2}& \\dots & \\dots x_{n-1,p-1}\\\\\n", + "\\end{bmatrix}.\n", + "$$" + ] + }, + { + "cell_type": "markdown", + "id": "f0565ccd", + "metadata": { + "editable": true + }, + "source": [ + "We can SVD decompose our matrix as" + ] + }, + { + "cell_type": "markdown", + "id": "a659e96f", + "metadata": { + "editable": true + }, + "source": [ + "$$\n", + "\\boldsymbol{X}=\\boldsymbol{U}\\boldsymbol{\\Sigma}\\boldsymbol{V}^T,\n", + "$$" + ] + }, + { + "cell_type": "markdown", + "id": "fcfcf6b0", + "metadata": { + "editable": true + }, + "source": [ + "where $\\boldsymbol{U}$ is an orthogonal matrix of dimension $n\\times n$, meaning that $\\boldsymbol{U}\\boldsymbol{U}^T=\\boldsymbol{U}^T\\boldsymbol{U}=\\boldsymbol{I}_n$. Here $\\boldsymbol{I}_n$ is the unit matrix of dimension $n \\times n$.\n", + "\n", + "Similarly, $\\boldsymbol{V}$ is an orthogonal matrix of dimension $p\\times p$, meaning that $\\boldsymbol{V}\\boldsymbol{V}^T=\\boldsymbol{V}^T\\boldsymbol{V}=\\boldsymbol{I}_p$. Here $\\boldsymbol{I}_n$ is the unit matrix of dimension $p \\times p$.\n", + "\n", + "Finally $\\boldsymbol{\\Sigma}$ contains the singular values $\\sigma_i$. This matrix has dimension $n\\times p$ and the singular values $\\sigma_i$ are all positive. The non-zero values are ordered in descending order, that is" + ] + }, + { + "cell_type": "markdown", + "id": "ea39064c", + "metadata": { + "editable": true + }, + "source": [ + "$$\n", + "\\sigma_0 > \\sigma_1 > \\sigma_2 > \\dots > \\sigma_{p-1} > 0.\n", + "$$" + ] + }, + { + "cell_type": "markdown", + "id": "0096e499", + "metadata": { + "editable": true + }, + "source": [ + "All values beyond $p-1$ are all zero." + ] + }, + { + "cell_type": "markdown", + "id": "bf32dfa9", + "metadata": { + "editable": true + }, + "source": [ + "## Example Matrix\n", + "\n", + "As an example, consider the following $3\\times 2$ example for the matrix $\\boldsymbol{\\Sigma}$" + ] + }, + { + "cell_type": "markdown", + "id": "e0d6fee2", + "metadata": { + "editable": true + }, + "source": [ + "$$\n", + "\\boldsymbol{\\Sigma}=\n", + "\\begin{bmatrix}\n", + "2& 0 \\\\\n", + "0 & 1 \\\\\n", + "0 & 0 \\\\\n", + "\\end{bmatrix}\n", + "$$" + ] + }, + { + "cell_type": "markdown", + "id": "0cb15d9d", + "metadata": { + "editable": true + }, + "source": [ + "The singular values are $\\sigma_0=2$ and $\\sigma_1=1$. It is common to rewrite the matrix $\\boldsymbol{\\Sigma}$ as" + ] + }, + { + "cell_type": "markdown", + "id": "754f4312", + "metadata": { + "editable": true + }, + "source": [ + "$$\n", + "\\boldsymbol{\\Sigma}=\n", + "\\begin{bmatrix}\n", + "\\boldsymbol{\\tilde{\\Sigma}}\\\\\n", + "\\boldsymbol{0}\\\\\n", + "\\end{bmatrix},\n", + "$$" + ] + }, + { + "cell_type": "markdown", + "id": "5bd1e9b0", + "metadata": { + "editable": true + }, + "source": [ + "where" + ] + }, + { + "cell_type": "markdown", + "id": "2a839ac1", + "metadata": { + "editable": true + }, + "source": [ + "$$\n", + "\\boldsymbol{\\tilde{\\Sigma}}=\n", + "\\begin{bmatrix}\n", + "2& 0 \\\\\n", + "0 & 1 \\\\\n", + "\\end{bmatrix},\n", + "$$" + ] + }, + { + "cell_type": "markdown", + "id": "69e34c64", + "metadata": { + "editable": true + }, + "source": [ + "contains only the singular values. Note also (and we will use this below) that" + ] + }, + { + "cell_type": "markdown", + "id": "b32ae1de", + "metadata": { + "editable": true + }, + "source": [ + "$$\n", + "\\boldsymbol{\\Sigma}^T\\boldsymbol{\\Sigma}=\n", + "\\begin{bmatrix}\n", + "4& 0 \\\\\n", + "0 & 1 \\\\\n", + "\\end{bmatrix},\n", + "$$" + ] + }, + { + "cell_type": "markdown", + "id": "00c3ff66", + "metadata": { + "editable": true + }, + "source": [ + "which is a $2\\times 2 $ matrix while" + ] + }, + { + "cell_type": "markdown", + "id": "92f1238d", + "metadata": { + "editable": true + }, + "source": [ + "$$\n", + "\\boldsymbol{\\Sigma}\\boldsymbol{\\Sigma}^T=\n", + "\\begin{bmatrix}\n", + "4& 0 & 0\\\\\n", + "0 & 1 & 0\\\\\n", + "0 & 0 & 0\\\\\n", + "\\end{bmatrix},\n", + "$$" + ] + }, + { + "cell_type": "markdown", + "id": "71f43637", + "metadata": { + "editable": true + }, + "source": [ + "is a $3\\times 3 $ matrix. The last row and column of this last matrix\n", + "contain only zeros. This will have important consequences for our SVD\n", + "decomposition of the design matrix." + ] + }, + { + "cell_type": "markdown", + "id": "4bac0a15", + "metadata": { + "editable": true + }, + "source": [ + "## Setting up the Matrix to be inverted\n", + "\n", + "The matrix that may cause problems for us is $\\boldsymbol{X}^T\\boldsymbol{X}$. Using the SVD we can rewrite this matrix as" + ] + }, + { + "cell_type": "markdown", + "id": "b523b964", + "metadata": { + "editable": true + }, + "source": [ + "$$\n", + "\\boldsymbol{X}^T\\boldsymbol{X}=\\boldsymbol{V}\\boldsymbol{\\Sigma}^T\\boldsymbol{U}^T\\boldsymbol{U}\\boldsymbol{\\Sigma}\\boldsymbol{V}^T,\n", + "$$" + ] + }, + { + "cell_type": "markdown", + "id": "3d7f8195", + "metadata": { + "editable": true + }, + "source": [ + "and using the orthogonality of the matrix $\\boldsymbol{U}$ we have" + ] + }, + { + "cell_type": "markdown", + "id": "f308dd0a", + "metadata": { + "editable": true + }, + "source": [ + "$$\n", + "\\boldsymbol{X}^T\\boldsymbol{X}=\\boldsymbol{V}\\boldsymbol{\\Sigma}^T\\boldsymbol{\\Sigma}\\boldsymbol{V}^T.\n", + "$$" + ] + }, + { + "cell_type": "markdown", + "id": "929784cf", + "metadata": { + "editable": true + }, + "source": [ + "We define $\\boldsymbol{\\Sigma}^T\\boldsymbol{\\Sigma}=\\tilde{\\boldsymbol{\\Sigma}}^2$ which is a diagonal matrix containing only the singular values squared. It has dimensionality $p \\times p$.\n", + "\n", + "We can now insert the result for the matrix $\\boldsymbol{X}^T\\boldsymbol{X}$ into our equation for ordinary least squares where" + ] + }, + { + "cell_type": "markdown", + "id": "09dccee1", + "metadata": { + "editable": true + }, + "source": [ + "$$\n", + "\\tilde{y}_{\\mathrm{OLS}}=\\boldsymbol{X}\\left(\\boldsymbol{X}^T\\boldsymbol{X}\\right)^{-1}\\boldsymbol{X}^T\\boldsymbol{y},\n", + "$$" + ] + }, + { + "cell_type": "markdown", + "id": "165b3f17", + "metadata": { + "editable": true + }, + "source": [ + "and using our SVD decomposition of $\\boldsymbol{X}$ we have" + ] + }, + { + "cell_type": "markdown", + "id": "24a8dd50", + "metadata": { + "editable": true + }, + "source": [ + "$$\n", + "\\tilde{y}_{\\mathrm{OLS}}=\\boldsymbol{U}\\boldsymbol{\\Sigma}\\boldsymbol{V}^T\\left(\\boldsymbol{V}\\tilde{\\boldsymbol{\\Sigma}}^{2}(\\boldsymbol{V}^T\\right)^{-1}\\boldsymbol{V}\\boldsymbol{\\Sigma}^T\\boldsymbol{U}^T\\boldsymbol{y},\n", + "$$" + ] + }, + { + "cell_type": "markdown", + "id": "2597dc03", + "metadata": { + "editable": true + }, + "source": [ + "which gives us, using the orthogonality of the matrix $\\boldsymbol{V}$," + ] + }, + { + "cell_type": "markdown", + "id": "4d40ddce", + "metadata": { + "editable": true + }, + "source": [ + "$$\n", + "\\tilde{y}_{\\mathrm{OLS}}=\\boldsymbol{U}\\boldsymbol{U}^T\\boldsymbol{y}=\\sum_{i=0}^{p-1}\\boldsymbol{u}_i\\boldsymbol{u}^T_i\\boldsymbol{y},\n", + "$$" + ] + }, + { + "cell_type": "markdown", + "id": "41d0e0cb", + "metadata": { + "editable": true + }, + "source": [ + "It means that the ordinary least square model (with the optimal\n", + "parameters) $\\boldsymbol{\\tilde{y}}$, corresponds to an orthogonal\n", + "transformation of the output (or target) vector $\\boldsymbol{y}$ by the\n", + "vectors of the matrix $\\boldsymbol{U}$. **Note that the summation ends at**\n", + "$p-1$, that is $\\boldsymbol{\\tilde{y}}\\ne \\boldsymbol{y}$. We can thus not use the\n", + "orthogonality relation for the matrix $\\boldsymbol{U}$. This can already be\n", + "when we multiply the matrices $\\boldsymbol{\\Sigma}^T\\boldsymbol{U}^T$." + ] + }, + { + "cell_type": "markdown", + "id": "e4bafe51", + "metadata": { + "editable": true + }, + "source": [ + "## Further properties (important for our analyses later)\n", + "\n", + "Let us study again $\\boldsymbol{X}^T\\boldsymbol{X}$ in terms of our SVD," + ] + }, + { + "cell_type": "markdown", + "id": "aab4d56f", + "metadata": { + "editable": true + }, + "source": [ + "$$\n", + "\\boldsymbol{X}^T\\boldsymbol{X}=\\boldsymbol{V}\\boldsymbol{\\Sigma}^T\\boldsymbol{U}^T\\boldsymbol{U}\\boldsymbol{\\Sigma}\\boldsymbol{V}^T=\\boldsymbol{V}\\boldsymbol{\\Sigma}^T\\boldsymbol{\\Sigma}\\boldsymbol{V}^T.\n", + "$$" + ] + }, + { + "cell_type": "markdown", + "id": "861395ef", + "metadata": { + "editable": true + }, + "source": [ + "If we now multiply from the right with $\\boldsymbol{V}$ (using the orthogonality of $\\boldsymbol{V}$) we get" + ] + }, + { + "cell_type": "markdown", + "id": "299b8198", + "metadata": { + "editable": true + }, + "source": [ + "$$\n", + "\\left(\\boldsymbol{X}^T\\boldsymbol{X}\\right)\\boldsymbol{V}=\\boldsymbol{V}\\boldsymbol{\\Sigma}^T\\boldsymbol{\\Sigma}.\n", + "$$" + ] + }, + { + "cell_type": "markdown", + "id": "2096c2e7", + "metadata": { + "editable": true + }, + "source": [ + "This means the vectors $\\boldsymbol{v}_i$ of the orthogonal matrix $\\boldsymbol{V}$ are the eigenvectors of the matrix $\\boldsymbol{X}^T\\boldsymbol{X}$\n", + "with eigenvalues given by the singular values squared, that is" + ] + }, + { + "cell_type": "markdown", + "id": "4ad3b043", + "metadata": { + "editable": true + }, + "source": [ + "$$\n", + "\\left(\\boldsymbol{X}^T\\boldsymbol{X}\\right)\\boldsymbol{v}_i=\\boldsymbol{v}_i\\sigma_i^2.\n", + "$$" + ] + }, + { + "cell_type": "markdown", + "id": "66bf91e3", + "metadata": { + "editable": true + }, + "source": [ + "Similarly, if we use the SVD decomposition for the matrix $\\boldsymbol{X}\\boldsymbol{X}^T$, we have" + ] + }, + { + "cell_type": "markdown", + "id": "95afc99c", + "metadata": { + "editable": true + }, + "source": [ + "$$\n", + "\\boldsymbol{X}\\boldsymbol{X}^T=\\boldsymbol{U}\\boldsymbol{\\Sigma}\\boldsymbol{V}^T\\boldsymbol{V}\\boldsymbol{\\Sigma}^T\\boldsymbol{U}^T=\\boldsymbol{U}\\boldsymbol{\\Sigma}\\boldsymbol{\\Sigma}^T\\boldsymbol{U}^T.\n", + "$$" + ] + }, + { + "cell_type": "markdown", + "id": "73334115", + "metadata": { + "editable": true + }, + "source": [ + "If we now multiply from the right with $\\boldsymbol{U}$ (using the orthogonality of $\\boldsymbol{U}$) we get" + ] + }, + { + "cell_type": "markdown", + "id": "fb6f936e", + "metadata": { + "editable": true + }, + "source": [ + "$$\n", + "\\left(\\boldsymbol{X}\\boldsymbol{X}^T\\right)\\boldsymbol{U}=\\boldsymbol{U}\\boldsymbol{\\Sigma}\\boldsymbol{\\Sigma}^T.\n", + "$$" + ] + }, + { + "cell_type": "markdown", + "id": "f9093b47", + "metadata": { + "editable": true + }, + "source": [ + "This means the vectors $\\boldsymbol{u}_i$ of the orthogonal matrix $\\boldsymbol{U}$ are the eigenvectors of the matrix $\\boldsymbol{X}\\boldsymbol{X}^T$\n", + "with eigenvalues given by the singular values squared, that is" + ] + }, + { + "cell_type": "markdown", + "id": "fe539ee1", + "metadata": { + "editable": true + }, + "source": [ + "$$\n", + "\\left(\\boldsymbol{X}\\boldsymbol{X}^T\\right)\\boldsymbol{u}_i=\\boldsymbol{u}_i\\sigma_i^2.\n", + "$$" + ] + }, + { + "cell_type": "markdown", + "id": "d130c8c1", + "metadata": { + "editable": true + }, + "source": [ + "**Important note**: we have defined our design matrix $\\boldsymbol{X}$ to be an\n", + "$n\\times p$ matrix. In most supervised learning cases we have that $n\n", + "\\ge p$, and quite often we have $n >> p$. For linear algebra based methods like ordinary least squares or Ridge regression, this leads to a matrix $\\boldsymbol{X}^T\\boldsymbol{X}$ which is small and thereby easier to handle from a computational point of view (in terms of number of floating point operations).\n", + "\n", + "In our lectures, the number of columns will\n", + "always refer to the number of features in our data set, while the\n", + "number of rows represents the number of data inputs. Note that in\n", + "other texts you may find the opposite notation. This has consequences\n", + "for the definition of for example the covariance matrix and its relation to the SVD." + ] + }, + { + "cell_type": "markdown", + "id": "6787b5c2", + "metadata": { + "editable": true + }, + "source": [ + "## Meet the Covariance Matrix\n", + "\n", + "Before we move on to a discussion of Ridge and Lasso regression, we want to show an important example of the above.\n", + "\n", + "We have already noted that the matrix $\\boldsymbol{X}^T\\boldsymbol{X}$ in ordinary\n", + "least squares is proportional to the second derivative of the cost\n", + "function, that is we have" + ] + }, + { + "cell_type": "markdown", + "id": "b2e599e5", + "metadata": { + "editable": true + }, + "source": [ + "$$\n", + "\\frac{\\partial^2 C(\\boldsymbol{\\beta})}{\\partial \\boldsymbol{\\beta}\\partial \\boldsymbol{\\beta}^T} =\\frac{2}{n}\\boldsymbol{X}^T\\boldsymbol{X}.\n", + "$$" + ] + }, + { + "cell_type": "markdown", + "id": "854ff040", + "metadata": { + "editable": true + }, + "source": [ + "This quantity defines was what is called the Hessian matrix (the second derivative of a function we want to optimize).\n", + "\n", + "The Hessian matrix plays an important role and is defined in this course as" + ] + }, + { + "cell_type": "markdown", + "id": "aaf5e54e", + "metadata": { + "editable": true + }, + "source": [ + "$$\n", + "\\boldsymbol{H}=\\boldsymbol{X}^T\\boldsymbol{X}.\n", + "$$" + ] + }, + { + "cell_type": "markdown", + "id": "444a68be", + "metadata": { + "editable": true + }, + "source": [ + "The Hessian matrix for ordinary least squares is also proportional to\n", + "the covariance matrix. This means also that we can use the SVD to find\n", + "the eigenvalues of the covariance matrix and the Hessian matrix in\n", + "terms of the singular values. Let us develop these arguments, as they will play an important role in our machine learning studies." + ] + }, + { + "cell_type": "markdown", + "id": "56e0f274", + "metadata": { + "editable": true + }, + "source": [ + "## Introducing the Covariance and Correlation functions\n", + "\n", + "Before we discuss the link between for example Ridge regression and the singular value decomposition, we need to remind ourselves about\n", + "the definition of the covariance and the correlation function. These are quantities that play a central role in machine learning methods.\n", + "\n", + "Suppose we have defined two vectors\n", + "$\\hat{x}$ and $\\hat{y}$ with $n$ elements each. The covariance matrix $\\boldsymbol{C}$ is defined as" + ] + }, + { + "cell_type": "markdown", + "id": "a55a54c3", + "metadata": { + "editable": true + }, + "source": [ + "$$\n", + "\\boldsymbol{C}[\\boldsymbol{x},\\boldsymbol{y}] = \\begin{bmatrix} \\mathrm{cov}[\\boldsymbol{x},\\boldsymbol{x}] & \\mathrm{cov}[\\boldsymbol{x},\\boldsymbol{y}] \\\\\n", + " \\mathrm{cov}[\\boldsymbol{y},\\boldsymbol{x}] & \\mathrm{cov}[\\boldsymbol{y},\\boldsymbol{y}] \\\\\n", + " \\end{bmatrix},\n", + "$$" + ] + }, + { + "cell_type": "markdown", + "id": "b614c964", + "metadata": { + "editable": true + }, + "source": [ + "where for example" + ] + }, + { + "cell_type": "markdown", + "id": "624b1c18", + "metadata": { + "editable": true + }, + "source": [ + "$$\n", + "\\mathrm{cov}[\\boldsymbol{x},\\boldsymbol{y}] =\\frac{1}{n} \\sum_{i=0}^{n-1}(x_i- \\overline{x})(y_i- \\overline{y}).\n", + "$$" + ] + }, + { + "cell_type": "markdown", + "id": "63dc085a", + "metadata": { + "editable": true + }, + "source": [ + "With this definition and recalling that the variance is defined as" + ] + }, + { + "cell_type": "markdown", + "id": "28db2f6a", + "metadata": { + "editable": true + }, + "source": [ + "$$\n", + "\\mathrm{var}[\\boldsymbol{x}]=\\frac{1}{n} \\sum_{i=0}^{n-1}(x_i- \\overline{x})^2,\n", + "$$" + ] + }, + { + "cell_type": "markdown", + "id": "a9f1ebdd", + "metadata": { + "editable": true + }, + "source": [ + "we can rewrite the covariance matrix as" + ] + }, + { + "cell_type": "markdown", + "id": "0b8bf07b", + "metadata": { + "editable": true + }, + "source": [ + "$$\n", + "\\boldsymbol{C}[\\boldsymbol{x},\\boldsymbol{y}] = \\begin{bmatrix} \\mathrm{var}[\\boldsymbol{x}] & \\mathrm{cov}[\\boldsymbol{x},\\boldsymbol{y}] \\\\\n", + " \\mathrm{cov}[\\boldsymbol{x},\\boldsymbol{y}] & \\mathrm{var}[\\boldsymbol{y}] \\\\\n", + " \\end{bmatrix}.\n", + "$$" + ] + }, + { + "cell_type": "markdown", + "id": "5f237448", + "metadata": { + "editable": true + }, + "source": [ + "**Note:** we have used $1/n$ in the above definitions of the *sample* variance and covariance. We assume then that we can calculate the exact mean value. \n", + "What you will find in essentially all statistics texts are equations\n", + "with a factor $1/(n-1)$. This is called [Bessel's correction](https://mathworld.wolfram.com/BesselsCorrection.html). This\n", + "method corrects the bias in the estimation of the population variance\n", + "and covariance. It also partially corrects the bias in the estimation\n", + "of the population standard deviation. If you use a library like\n", + "**Scikit-Learn** or **nunmpy's** function to calculate the covariance, this\n", + "quantity will be computed with a factor $1/(n-1)$." + ] + }, + { + "cell_type": "markdown", + "id": "75b7044c", + "metadata": { + "editable": true + }, + "source": [ + "## Covariance and Correlation Matrix\n", + "\n", + "The covariance takes values between zero and infinity and may thus\n", + "lead to problems with loss of numerical precision for particularly\n", + "large values. It is common to scale the covariance matrix by\n", + "introducing instead the correlation matrix defined via the so-called\n", + "correlation function" + ] + }, + { + "cell_type": "markdown", + "id": "51268862", + "metadata": { + "editable": true + }, + "source": [ + "$$\n", + "\\mathrm{corr}[\\boldsymbol{x},\\boldsymbol{y}]=\\frac{\\mathrm{cov}[\\boldsymbol{x},\\boldsymbol{y}]}{\\sqrt{\\mathrm{var}[\\boldsymbol{x}] \\mathrm{var}[\\boldsymbol{y}]}}.\n", + "$$" + ] + }, + { + "cell_type": "markdown", + "id": "608b9dff", + "metadata": { + "editable": true + }, + "source": [ + "The correlation function is then given by values $\\mathrm{corr}[\\boldsymbol{x},\\boldsymbol{y}]\n", + "\\in [-1,1]$. This avoids eventual problems with too large values. We\n", + "can then define the correlation matrix for the two vectors $\\boldsymbol{x}$\n", + "and $\\boldsymbol{y}$ as" + ] + }, + { + "cell_type": "markdown", + "id": "b06c316f", + "metadata": { + "editable": true + }, + "source": [ + "$$\n", + "\\boldsymbol{K}[\\boldsymbol{x},\\boldsymbol{y}] = \\begin{bmatrix} 1 & \\mathrm{corr}[\\boldsymbol{x},\\boldsymbol{y}] \\\\\n", + " \\mathrm{corr}[\\boldsymbol{y},\\boldsymbol{x}] & 1 \\\\\n", + " \\end{bmatrix},\n", + "$$" + ] + }, + { + "cell_type": "markdown", + "id": "e82ba709", + "metadata": { + "editable": true + }, + "source": [ + "In the above example this is the function we constructed using **pandas**." + ] + }, + { + "cell_type": "markdown", + "id": "92d739a1", + "metadata": { + "editable": true + }, + "source": [ + "## Correlation Function and Design/Feature Matrix\n", + "\n", + "In our derivation of the various regression algorithms like **Ordinary Least Squares** or **Ridge regression**\n", + "we defined the design/feature matrix $\\boldsymbol{X}$ as" + ] + }, + { + "cell_type": "markdown", + "id": "14ce5cea", + "metadata": { + "editable": true + }, + "source": [ + "$$\n", + "\\boldsymbol{X}=\\begin{bmatrix}\n", + "x_{0,0} & x_{0,1} & x_{0,2}& \\dots & \\dots x_{0,p-1}\\\\\n", + "x_{1,0} & x_{1,1} & x_{1,2}& \\dots & \\dots x_{1,p-1}\\\\\n", + "x_{2,0} & x_{2,1} & x_{2,2}& \\dots & \\dots x_{2,p-1}\\\\\n", + "\\dots & \\dots & \\dots & \\dots \\dots & \\dots \\\\\n", + "x_{n-2,0} & x_{n-2,1} & x_{n-2,2}& \\dots & \\dots x_{n-2,p-1}\\\\\n", + "x_{n-1,0} & x_{n-1,1} & x_{n-1,2}& \\dots & \\dots x_{n-1,p-1}\\\\\n", + "\\end{bmatrix},\n", + "$$" + ] + }, + { + "cell_type": "markdown", + "id": "f7e1f2b1", + "metadata": { + "editable": true + }, + "source": [ + "with $\\boldsymbol{X}\\in {\\mathbb{R}}^{n\\times p}$, with the predictors/features $p$ refering to the column numbers and the\n", + "entries $n$ being the row elements.\n", + "We can rewrite the design/feature matrix in terms of its column vectors as" + ] + }, + { + "cell_type": "markdown", + "id": "71910404", + "metadata": { + "editable": true + }, + "source": [ + "$$\n", + "\\boldsymbol{X}=\\begin{bmatrix} \\boldsymbol{x}_0 & \\boldsymbol{x}_1 & \\boldsymbol{x}_2 & \\dots & \\dots & \\boldsymbol{x}_{p-1}\\end{bmatrix},\n", + "$$" + ] + }, + { + "cell_type": "markdown", + "id": "cbd60268", + "metadata": { + "editable": true + }, + "source": [ + "with a given vector" + ] + }, + { + "cell_type": "markdown", + "id": "e6c94e3d", + "metadata": { + "editable": true + }, + "source": [ + "$$\n", + "\\boldsymbol{x}_i^T = \\begin{bmatrix}x_{0,i} & x_{1,i} & x_{2,i}& \\dots & \\dots x_{n-1,i}\\end{bmatrix}.\n", + "$$" + ] + }, + { + "cell_type": "markdown", + "id": "20cf812e", + "metadata": { + "editable": true + }, + "source": [ + "With these definitions, we can now rewrite our $2\\times 2$\n", + "correlation/covariance matrix in terms of a moe general design/feature\n", + "matrix $\\boldsymbol{X}\\in {\\mathbb{R}}^{n\\times p}$. This leads to a $p\\times p$\n", + "covariance matrix for the vectors $\\boldsymbol{x}_i$ with $i=0,1,\\dots,p-1$" + ] + }, + { + "cell_type": "markdown", + "id": "dd1cb8be", + "metadata": { + "editable": true + }, + "source": [ + "$$\n", + "\\boldsymbol{C}[\\boldsymbol{x}] = \\begin{bmatrix}\n", + "\\mathrm{var}[\\boldsymbol{x}_0] & \\mathrm{cov}[\\boldsymbol{x}_0,\\boldsymbol{x}_1] & \\mathrm{cov}[\\boldsymbol{x}_0,\\boldsymbol{x}_2] & \\dots & \\dots & \\mathrm{cov}[\\boldsymbol{x}_0,\\boldsymbol{x}_{p-1}]\\\\\n", + "\\mathrm{cov}[\\boldsymbol{x}_1,\\boldsymbol{x}_0] & \\mathrm{var}[\\boldsymbol{x}_1] & \\mathrm{cov}[\\boldsymbol{x}_1,\\boldsymbol{x}_2] & \\dots & \\dots & \\mathrm{cov}[\\boldsymbol{x}_1,\\boldsymbol{x}_{p-1}]\\\\\n", + "\\mathrm{cov}[\\boldsymbol{x}_2,\\boldsymbol{x}_0] & \\mathrm{cov}[\\boldsymbol{x}_2,\\boldsymbol{x}_1] & \\mathrm{var}[\\boldsymbol{x}_2] & \\dots & \\dots & \\mathrm{cov}[\\boldsymbol{x}_2,\\boldsymbol{x}_{p-1}]\\\\\n", + "\\dots & \\dots & \\dots & \\dots & \\dots & \\dots \\\\\n", + "\\dots & \\dots & \\dots & \\dots & \\dots & \\dots \\\\\n", + "\\mathrm{cov}[\\boldsymbol{x}_{p-1},\\boldsymbol{x}_0] & \\mathrm{cov}[\\boldsymbol{x}_{p-1},\\boldsymbol{x}_1] & \\mathrm{cov}[\\boldsymbol{x}_{p-1},\\boldsymbol{x}_{2}] & \\dots & \\dots & \\mathrm{var}[\\boldsymbol{x}_{p-1}]\\\\\n", + "\\end{bmatrix},\n", + "$$" + ] + }, + { + "cell_type": "markdown", + "id": "98a4e944", + "metadata": { + "editable": true + }, + "source": [ + "and the correlation matrix" + ] + }, + { + "cell_type": "markdown", + "id": "8c6e3845", + "metadata": { + "editable": true + }, + "source": [ + "$$\n", + "\\boldsymbol{K}[\\boldsymbol{x}] = \\begin{bmatrix}\n", + "1 & \\mathrm{corr}[\\boldsymbol{x}_0,\\boldsymbol{x}_1] & \\mathrm{corr}[\\boldsymbol{x}_0,\\boldsymbol{x}_2] & \\dots & \\dots & \\mathrm{corr}[\\boldsymbol{x}_0,\\boldsymbol{x}_{p-1}]\\\\\n", + "\\mathrm{corr}[\\boldsymbol{x}_1,\\boldsymbol{x}_0] & 1 & \\mathrm{corr}[\\boldsymbol{x}_1,\\boldsymbol{x}_2] & \\dots & \\dots & \\mathrm{corr}[\\boldsymbol{x}_1,\\boldsymbol{x}_{p-1}]\\\\\n", + "\\mathrm{corr}[\\boldsymbol{x}_2,\\boldsymbol{x}_0] & \\mathrm{corr}[\\boldsymbol{x}_2,\\boldsymbol{x}_1] & 1 & \\dots & \\dots & \\mathrm{corr}[\\boldsymbol{x}_2,\\boldsymbol{x}_{p-1}]\\\\\n", + "\\dots & \\dots & \\dots & \\dots & \\dots & \\dots \\\\\n", + "\\dots & \\dots & \\dots & \\dots & \\dots & \\dots \\\\\n", + "\\mathrm{corr}[\\boldsymbol{x}_{p-1},\\boldsymbol{x}_0] & \\mathrm{corr}[\\boldsymbol{x}_{p-1},\\boldsymbol{x}_1] & \\mathrm{corr}[\\boldsymbol{x}_{p-1},\\boldsymbol{x}_{2}] & \\dots & \\dots & 1\\\\\n", + "\\end{bmatrix},\n", + "$$" + ] + }, + { + "cell_type": "markdown", + "id": "bc13a77d", + "metadata": { + "editable": true + }, + "source": [ + "## Covariance Matrix Examples\n", + "\n", + "The Numpy function **np.cov** calculates the covariance elements using\n", + "the factor $1/(n-1)$ instead of $1/n$ since it assumes we do not have\n", + "the exact mean values. The following simple function uses the\n", + "**np.vstack** function which takes each vector of dimension $1\\times n$\n", + "and produces a $2\\times n$ matrix $\\boldsymbol{W}$\n", + "\n", + "Note that this assumes you have the features as the rows, and the inputs as columns, that is" + ] + }, + { + "cell_type": "markdown", + "id": "19d6cd9e", + "metadata": { + "editable": true + }, + "source": [ + "$$\n", + "\\boldsymbol{W} = \\begin{bmatrix} x_0 & x_1 & x_2 & \\dots & x_{n-2} & x_{n-1} \\\\\n", + " y_0 & y_1 & y_2 & \\dots & y_{n-2} & y_{n-1} \\\\\n", + " \\end{bmatrix},\n", + "$$" + ] + }, + { + "cell_type": "markdown", + "id": "c5c7eee1", + "metadata": { + "editable": true + }, + "source": [ + "which in turn is converted into into the $2\\times 2$ covariance matrix\n", + "$\\boldsymbol{C}$ via the Numpy function **np.cov()**. We note that we can also calculate\n", + "the mean value of each set of samples $\\boldsymbol{x}$ etc using the Numpy\n", + "function **np.mean(x)**. We can also extract the eigenvalues of the\n", + "covariance matrix through the **np.linalg.eig()** function." + ] + }, + { + "cell_type": "code", + "execution_count": 27, + "id": "6ab6bcc3", + "metadata": { + "collapsed": false, + "editable": true + }, + "outputs": [], + "source": [ + "# Importing various packages\n", + "import numpy as np\n", + "n = 100\n", + "x = np.random.normal(size=n)\n", + "print(np.mean(x))\n", + "y = 4+3*x+np.random.normal(size=n)\n", + "print(np.mean(y))\n", + "W = np.vstack((x, y))\n", + "C = np.cov(W)\n", + "print(C)" + ] + }, + { + "cell_type": "markdown", + "id": "839a512c", + "metadata": { + "editable": true + }, + "source": [ + "## Correlation Matrix\n", + "\n", + "The previous example can be converted into the correlation matrix by\n", + "simply scaling the matrix elements with the variances. We should also\n", + "subtract the mean values for each column. This leads to the following\n", + "code which sets up the correlations matrix for the previous example in\n", + "a more brute force way. Here we scale the mean values for each column of the design matrix, calculate the relevant mean values and variances and then finally set up the $2\\times 2$ correlation matrix (since we have only two vectors)." + ] + }, + { + "cell_type": "code", + "execution_count": 28, + "id": "bad7396d", + "metadata": { + "collapsed": false, + "editable": true + }, + "outputs": [], + "source": [ + "import numpy as np\n", + "n = 100\n", + "# define two vectors \n", + "x = np.random.random(size=n)\n", + "y = 4+3*x+np.random.normal(size=n)\n", + "#scaling the x and y vectors \n", + "x = x - np.mean(x)\n", + "y = y - np.mean(y)\n", + "variance_x = np.sum(x@x)/n\n", + "variance_y = np.sum(y@y)/n\n", + "print(variance_x)\n", + "print(variance_y)\n", + "cov_xy = np.sum(x@y)/n\n", + "cov_xx = np.sum(x@x)/n\n", + "cov_yy = np.sum(y@y)/n\n", + "C = np.zeros((2,2))\n", + "C[0,0]= cov_xx/variance_x\n", + "C[1,1]= cov_yy/variance_y\n", + "C[0,1]= cov_xy/np.sqrt(variance_y*variance_x)\n", + "C[1,0]= C[0,1]\n", + "print(C)" + ] + }, + { + "cell_type": "markdown", + "id": "365c6ef8", + "metadata": { + "editable": true + }, + "source": [ + "We see that the matrix elements along the diagonal are one as they\n", + "should be and that the matrix is symmetric. Furthermore, diagonalizing\n", + "this matrix we easily see that it is a positive definite matrix.\n", + "\n", + "The above procedure with **numpy** can be made more compact if we use **pandas**." + ] + }, + { + "cell_type": "markdown", + "id": "6fd82fe9", + "metadata": { + "editable": true + }, + "source": [ + "## Correlation Matrix with Pandas\n", + "\n", + "We whow here how we can set up the correlation matrix using **pandas**, as done in this simple code" + ] + }, + { + "cell_type": "code", + "execution_count": 29, + "id": "80ba738c", + "metadata": { + "collapsed": false, + "editable": true + }, + "outputs": [], + "source": [ + "import numpy as np\n", + "import pandas as pd\n", + "n = 10\n", + "x = np.random.normal(size=n)\n", + "x = x - np.mean(x)\n", + "y = 4+3*x+np.random.normal(size=n)\n", + "y = y - np.mean(y)\n", + "# Note that we transpose the matrix in order to stay with our ordering n x p\n", + "X = (np.vstack((x, y))).T\n", + "print(X)\n", + "Xpd = pd.DataFrame(X)\n", + "print(Xpd)\n", + "correlation_matrix = Xpd.corr()\n", + "print(correlation_matrix)" + ] + }, + { + "cell_type": "markdown", + "id": "4f390c8f", + "metadata": { + "editable": true + }, + "source": [ + "We expand this model to the Franke function discussed above." + ] + }, + { + "cell_type": "markdown", + "id": "4bceabcb", + "metadata": { + "editable": true + }, + "source": [ + "## Correlation Matrix with Pandas and the Franke function" + ] + }, + { + "cell_type": "code", + "execution_count": 30, + "id": "0146e7c8", + "metadata": { + "collapsed": false, + "editable": true + }, + "outputs": [], + "source": [ + "# Common imports\n", + "import numpy as np\n", + "import pandas as pd\n", + "\n", + "\n", + "def FrankeFunction(x,y):\n", + "\tterm1 = 0.75*np.exp(-(0.25*(9*x-2)**2) - 0.25*((9*y-2)**2))\n", + "\tterm2 = 0.75*np.exp(-((9*x+1)**2)/49.0 - 0.1*(9*y+1))\n", + "\tterm3 = 0.5*np.exp(-(9*x-7)**2/4.0 - 0.25*((9*y-3)**2))\n", + "\tterm4 = -0.2*np.exp(-(9*x-4)**2 - (9*y-7)**2)\n", + "\treturn term1 + term2 + term3 + term4\n", + "\n", + "\n", + "def create_X(x, y, n ):\n", + "\tif len(x.shape) > 1:\n", + "\t\tx = np.ravel(x)\n", + "\t\ty = np.ravel(y)\n", + "\n", + "\tN = len(x)\n", + "\tl = int((n+1)*(n+2)/2)\t\t# Number of elements in beta\n", + "\tX = np.ones((N,l))\n", + "\n", + "\tfor i in range(1,n+1):\n", + "\t\tq = int((i)*(i+1)/2)\n", + "\t\tfor k in range(i+1):\n", + "\t\t\tX[:,q+k] = (x**(i-k))*(y**k)\n", + "\n", + "\treturn X\n", + "\n", + "\n", + "# Making meshgrid of datapoints and compute Franke's function\n", + "n = 4\n", + "N = 100\n", + "x = np.sort(np.random.uniform(0, 1, N))\n", + "y = np.sort(np.random.uniform(0, 1, N))\n", + "z = FrankeFunction(x, y)\n", + "X = create_X(x, y, n=n) \n", + "\n", + "Xpd = pd.DataFrame(X)\n", + "# subtract the mean values and set up the covariance matrix\n", + "Xpd = Xpd - Xpd.mean()\n", + "covariance_matrix = Xpd.cov()\n", + "print(covariance_matrix)" + ] + }, + { + "cell_type": "markdown", + "id": "6e15d041", + "metadata": { + "editable": true + }, + "source": [ + "We note here that the covariance is zero for the first rows and\n", + "columns since all matrix elements in the design matrix were set to one\n", + "(we are fitting the function in terms of a polynomial of degree $n$).\n", + "\n", + "This means that the variance for these elements will be zero and will\n", + "cause problems when we set up the correlation matrix. We can simply\n", + "drop these elements and construct a correlation\n", + "matrix without these elements." + ] + }, + { + "cell_type": "markdown", + "id": "107d5b46", + "metadata": { + "editable": true + }, + "source": [ + "## Rewriting the Covariance and/or Correlation Matrix\n", + "\n", + "We can rewrite the covariance matrix in a more compact form in terms of the design/feature matrix $\\boldsymbol{X}$ as" + ] + }, + { + "cell_type": "markdown", + "id": "e47d0e76", + "metadata": { + "editable": true + }, + "source": [ + "$$\n", + "\\boldsymbol{C}[\\boldsymbol{x}] = \\frac{1}{n}\\boldsymbol{X}^T\\boldsymbol{X}= \\mathbb{E}[\\boldsymbol{X}^T\\boldsymbol{X}].\n", + "$$" + ] + }, + { + "cell_type": "markdown", + "id": "86b8daf6", + "metadata": { + "editable": true + }, + "source": [ + "To see this let us simply look at a design matrix $\\boldsymbol{X}\\in {\\mathbb{R}}^{2\\times 2}$" + ] + }, + { + "cell_type": "markdown", + "id": "934cc6c5", + "metadata": { + "editable": true + }, + "source": [ + "$$\n", + "\\boldsymbol{X}=\\begin{bmatrix}\n", + "x_{00} & x_{01}\\\\\n", + "x_{10} & x_{11}\\\\\n", + "\\end{bmatrix}=\\begin{bmatrix}\n", + "\\boldsymbol{x}_{0} & \\boldsymbol{x}_{1}\\\\\n", + "\\end{bmatrix}.\n", + "$$" + ] + }, + { + "cell_type": "markdown", + "id": "2a384ee9", + "metadata": { + "editable": true + }, + "source": [ + "If we then compute the expectation value (note the $1/n$ factor instead of $1/(n-1)$)" + ] + }, + { + "cell_type": "markdown", + "id": "e9a632a7", + "metadata": { + "editable": true + }, + "source": [ + "$$\n", + "\\mathbb{E}[\\boldsymbol{X}^T\\boldsymbol{X}] = \\frac{1}{n}\\boldsymbol{X}^T\\boldsymbol{X}=\\frac{1}{n}\\begin{bmatrix}\n", + "x_{00}^2+x_{10}^2 & x_{00}x_{01}+x_{10}x_{11}\\\\\n", + "x_{01}x_{00}+x_{11}x_{10} & x_{01}^2+x_{11}^2\\\\\n", + "\\end{bmatrix},\n", + "$$" + ] + }, + { + "cell_type": "markdown", + "id": "8cbf4cb8", + "metadata": { + "editable": true + }, + "source": [ + "which is just" + ] + }, + { + "cell_type": "markdown", + "id": "b29a7909", + "metadata": { + "editable": true + }, + "source": [ + "$$\n", + "\\boldsymbol{C}[\\boldsymbol{x}_0,\\boldsymbol{x}_1] = \\boldsymbol{C}[\\boldsymbol{x}]=\\begin{bmatrix} \\mathrm{var}[\\boldsymbol{x}_0] & \\mathrm{cov}[\\boldsymbol{x}_0,\\boldsymbol{x}_1] \\\\\n", + " \\mathrm{cov}[\\boldsymbol{x}_1,\\boldsymbol{x}_0] & \\mathrm{var}[\\boldsymbol{x}_1] \\\\\n", + " \\end{bmatrix},\n", + "$$" + ] + }, + { + "cell_type": "markdown", + "id": "31b9c6a9", + "metadata": { + "editable": true + }, + "source": [ + "where we wrote $$\\boldsymbol{C}[\\boldsymbol{x}_0,\\boldsymbol{x}_1] = \\boldsymbol{C}[\\boldsymbol{x}]$$ to indicate that this is the covariance of the vectors $\\boldsymbol{x}$ of the design/feature matrix $\\boldsymbol{X}$.\n", + "\n", + "It is easy to generalize this to a matrix $\\boldsymbol{X}\\in {\\mathbb{R}}^{n\\times p}$." + ] + }, + { + "cell_type": "markdown", + "id": "cdc2f810", + "metadata": { + "editable": true + }, + "source": [ + "## Linking with the SVD\n", + "\n", + "We saw earlier that" + ] + }, + { + "cell_type": "markdown", + "id": "0b7d368d", + "metadata": { + "editable": true + }, + "source": [ + "$$\n", + "\\boldsymbol{X}^T\\boldsymbol{X}=\\boldsymbol{V}\\boldsymbol{\\Sigma}^T\\boldsymbol{U}^T\\boldsymbol{U}\\boldsymbol{\\Sigma}\\boldsymbol{V}^T=\\boldsymbol{V}\\boldsymbol{\\Sigma}^T\\boldsymbol{\\Sigma}\\boldsymbol{V}^T.\n", + "$$" + ] + }, + { + "cell_type": "markdown", + "id": "6d5ddd28", + "metadata": { + "editable": true + }, + "source": [ + "Since the matrices here have dimension $p\\times p$, with $p$ corresponding to the singular values, we defined earlier the matrix" + ] + }, + { + "cell_type": "markdown", + "id": "a18622fc", + "metadata": { + "editable": true + }, + "source": [ + "$$\n", + "\\boldsymbol{\\Sigma}^T\\boldsymbol{\\Sigma} = \\begin{bmatrix} \\tilde{\\boldsymbol{\\Sigma}} & \\boldsymbol{0}\\\\ \\end{bmatrix}\\begin{bmatrix} \\tilde{\\boldsymbol{\\Sigma}} \\\\ \\boldsymbol{0}\\\\ \\end{bmatrix},\n", + "$$" + ] + }, + { + "cell_type": "markdown", + "id": "b5a8893c", + "metadata": { + "editable": true + }, + "source": [ + "where the tilde-matrix $\\tilde{\\boldsymbol{\\Sigma}}$ is a matrix of dimension $p\\times p$ containing only the singular values $\\sigma_i$, that is" + ] + }, + { + "cell_type": "markdown", + "id": "50a0a62a", + "metadata": { + "editable": true + }, + "source": [ + "$$\n", + "\\tilde{\\boldsymbol{\\Sigma}}=\\begin{bmatrix} \\sigma_0 & 0 & 0 & \\dots & 0 & 0 \\\\\n", + " 0 & \\sigma_1 & 0 & \\dots & 0 & 0 \\\\\n", + "\t\t\t\t 0 & 0 & \\sigma_2 & \\dots & 0 & 0 \\\\\n", + "\t\t\t\t 0 & 0 & 0 & \\dots & \\sigma_{p-2} & 0 \\\\\n", + "\t\t\t\t 0 & 0 & 0 & \\dots & 0 & \\sigma_{p-1} \\\\\n", + "\\end{bmatrix},\n", + "$$" + ] + }, + { + "cell_type": "markdown", + "id": "20380d89", + "metadata": { + "editable": true + }, + "source": [ + "meaning we can write" + ] + }, + { + "cell_type": "markdown", + "id": "10805b50", + "metadata": { + "editable": true + }, + "source": [ + "$$\n", + "\\boldsymbol{X}^T\\boldsymbol{X}=\\boldsymbol{V}\\tilde{\\boldsymbol{\\Sigma}}^2\\boldsymbol{V}^T.\n", + "$$" + ] + }, + { + "cell_type": "markdown", + "id": "b9c31a46", + "metadata": { + "editable": true + }, + "source": [ + "Multiplying from the right with $\\boldsymbol{V}$ (using the orthogonality of $\\boldsymbol{V}$) we get" + ] + }, + { + "cell_type": "markdown", + "id": "1f48b48e", + "metadata": { + "editable": true + }, + "source": [ + "$$\n", + "\\left(\\boldsymbol{X}^T\\boldsymbol{X}\\right)\\boldsymbol{V}=\\boldsymbol{V}\\tilde{\\boldsymbol{\\Sigma}}^2.\n", + "$$" + ] + }, + { + "cell_type": "markdown", + "id": "ad8f7a8c", + "metadata": { + "editable": true + }, + "source": [ + "## What does it mean?\n", + "\n", + "This means the vectors $\\boldsymbol{v}_i$ of the orthogonal matrix $\\boldsymbol{V}$\n", + "are the eigenvectors of the matrix $\\boldsymbol{X}^T\\boldsymbol{X}$ with eigenvalues\n", + "given by the singular values squared, that is" + ] + }, + { + "cell_type": "markdown", + "id": "9e0dec01", + "metadata": { + "editable": true + }, + "source": [ + "$$\n", + "\\left(\\boldsymbol{X}^T\\boldsymbol{X}\\right)\\boldsymbol{v}_i=\\boldsymbol{v}_i\\sigma_i^2.\n", + "$$" + ] + }, + { + "cell_type": "markdown", + "id": "46fd0b6d", + "metadata": { + "editable": true + }, + "source": [ + "In other words, each non-zero singular value of $\\boldsymbol{X}$ is a positive\n", + "square root of an eigenvalue of $\\boldsymbol{X}^T\\boldsymbol{X}$. It means also that\n", + "the columns of $\\boldsymbol{V}$ are the eigenvectors of\n", + "$\\boldsymbol{X}^T\\boldsymbol{X}$. Since we have ordered the singular values of\n", + "$\\boldsymbol{X}$ in a descending order, it means that the column vectors\n", + "$\\boldsymbol{v}_i$ are hierarchically ordered by how much correlation they\n", + "encode from the columns of $\\boldsymbol{X}$. \n", + "\n", + "Note that these are also the eigenvectors and eigenvalues of the\n", + "Hessian matrix. Note also that the Hessian matrix we are discussing here is from a cost function defined by the mean squared error only.\n", + "\n", + "If we now recall the definition of the covariance matrix (not using\n", + "Bessel's correction) we have" + ] + }, + { + "cell_type": "markdown", + "id": "3d2047ca", + "metadata": { + "editable": true + }, + "source": [ + "$$\n", + "\\boldsymbol{C}[\\boldsymbol{X}]=\\frac{1}{n}\\boldsymbol{X}^T\\boldsymbol{X},\n", + "$$" + ] + }, + { + "cell_type": "markdown", + "id": "4a5f5016", + "metadata": { + "editable": true + }, + "source": [ + "meaning that every squared non-singular value of $\\boldsymbol{X}$ divided by $n$ (\n", + "the number of samples) are the eigenvalues of the covariance\n", + "matrix. Every singular value of $\\boldsymbol{X}$ is thus a positive square\n", + "root of an eigenvalue of $\\boldsymbol{X}^T\\boldsymbol{X}$. If the matrix $\\boldsymbol{X}$ is\n", + "self-adjoint, the singular values of $\\boldsymbol{X}$ are equal to the\n", + "absolute value of the eigenvalues of $\\boldsymbol{X}$." + ] + }, + { + "cell_type": "markdown", + "id": "52651fc6", + "metadata": { + "editable": true + }, + "source": [ + "## And finally $\\boldsymbol{X}\\boldsymbol{X}^T$\n", + "\n", + "For $\\boldsymbol{X}\\boldsymbol{X}^T$ we found" + ] + }, + { + "cell_type": "markdown", + "id": "fea09344", + "metadata": { + "editable": true + }, + "source": [ + "$$\n", + "\\boldsymbol{X}\\boldsymbol{X}^T=\\boldsymbol{U}\\boldsymbol{\\Sigma}\\boldsymbol{V}^T\\boldsymbol{V}\\boldsymbol{\\Sigma}^T\\boldsymbol{U}^T=\\boldsymbol{U}\\boldsymbol{\\Sigma}^T\\boldsymbol{\\Sigma}\\boldsymbol{U}^T.\n", + "$$" + ] + }, + { + "cell_type": "markdown", + "id": "bcfd303f", + "metadata": { + "editable": true + }, + "source": [ + "Since the matrices here have dimension $n\\times n$, we have" + ] + }, + { + "cell_type": "markdown", + "id": "f684d942", + "metadata": { + "editable": true + }, + "source": [ + "$$\n", + "\\boldsymbol{\\Sigma}\\boldsymbol{\\Sigma}^T = \\begin{bmatrix} \\tilde{\\boldsymbol{\\Sigma}} \\\\ \\boldsymbol{0}\\\\ \\end{bmatrix}\\begin{bmatrix} \\tilde{\\boldsymbol{\\Sigma}} \\boldsymbol{0}\\\\ \\end{bmatrix}=\\begin{bmatrix} \\tilde{\\boldsymbol{\\Sigma}} & \\boldsymbol{0} \\\\ \\boldsymbol{0} & \\boldsymbol{0}\\\\ \\end{bmatrix},\n", + "$$" + ] + }, + { + "cell_type": "markdown", + "id": "1e54bd36", + "metadata": { + "editable": true + }, + "source": [ + "leading to" + ] + }, + { + "cell_type": "markdown", + "id": "4cdcdef2", + "metadata": { + "editable": true + }, + "source": [ + "$$\n", + "\\boldsymbol{X}\\boldsymbol{X}^T=\\boldsymbol{U}\\begin{bmatrix} \\tilde{\\boldsymbol{\\Sigma}} & \\boldsymbol{0} \\\\ \\boldsymbol{0} & \\boldsymbol{0}\\\\ \\end{bmatrix}\\boldsymbol{U}^T.\n", + "$$" + ] + }, + { + "cell_type": "markdown", + "id": "a6d5bd03", + "metadata": { + "editable": true + }, + "source": [ + "Multiplying with $\\boldsymbol{U}$ from the right gives us the eigenvalue problem" + ] + }, + { + "cell_type": "markdown", + "id": "a4d9fc21", + "metadata": { + "editable": true + }, + "source": [ + "$$\n", + "(\\boldsymbol{X}\\boldsymbol{X}^T)\\boldsymbol{U}=\\boldsymbol{U}\\begin{bmatrix} \\tilde{\\boldsymbol{\\Sigma}} & \\boldsymbol{0} \\\\ \\boldsymbol{0} & \\boldsymbol{0}\\\\ \\end{bmatrix}.\n", + "$$" + ] + }, + { + "cell_type": "markdown", + "id": "119bc56e", + "metadata": { + "editable": true + }, + "source": [ + "It means that the eigenvalues of $\\boldsymbol{X}\\boldsymbol{X}^T$ are again given by\n", + "the non-zero singular values plus now a series of zeros. The column\n", + "vectors of $\\boldsymbol{U}$ are the eigenvectors of $\\boldsymbol{X}\\boldsymbol{X}^T$ and\n", + "measure how much correlations are contained in the rows of $\\boldsymbol{X}$.\n", + "\n", + "Since we will mainly be interested in the correlations among the features\n", + "of our data (the columns of $\\boldsymbol{X}$, the quantity of interest for us are the non-zero singular\n", + "values and the column vectors of $\\boldsymbol{V}$." + ] + }, + { + "cell_type": "markdown", + "id": "d15cad60", + "metadata": { + "editable": true + }, + "source": [ + "## Ridge and LASSO Regression\n", + "\n", + "Let us remind ourselves about the expression for the standard Mean Squared Error (MSE) which we used to define our cost function and the equations for the ordinary least squares (OLS) method, that is \n", + "our optimization problem is" + ] + }, + { + "cell_type": "markdown", + "id": "f725d905", + "metadata": { + "editable": true + }, + "source": [ + "$$\n", + "{\\displaystyle \\min_{\\boldsymbol{\\beta}\\in {\\mathbb{R}}^{p}}}\\frac{1}{n}\\left\\{\\left(\\boldsymbol{y}-\\boldsymbol{X}\\boldsymbol{\\beta}\\right)^T\\left(\\boldsymbol{y}-\\boldsymbol{X}\\boldsymbol{\\beta}\\right)\\right\\}.\n", + "$$" + ] + }, + { + "cell_type": "markdown", + "id": "a2a5b25f", + "metadata": { + "editable": true + }, + "source": [ + "or we can state it as" + ] + }, + { + "cell_type": "markdown", + "id": "a9f43162", + "metadata": { + "editable": true + }, + "source": [ + "$$\n", + "{\\displaystyle \\min_{\\boldsymbol{\\beta}\\in\n", + "{\\mathbb{R}}^{p}}}\\frac{1}{n}\\sum_{i=0}^{n-1}\\left(y_i-\\tilde{y}_i\\right)^2=\\frac{1}{n}\\vert\\vert \\boldsymbol{y}-\\boldsymbol{X}\\boldsymbol{\\beta}\\vert\\vert_2^2,\n", + "$$" + ] + }, + { + "cell_type": "markdown", + "id": "debb0a19", + "metadata": { + "editable": true + }, + "source": [ + "where we have used the definition of a norm-2 vector, that is" + ] + }, + { + "cell_type": "markdown", + "id": "2764c014", + "metadata": { + "editable": true + }, + "source": [ + "$$\n", + "\\vert\\vert \\boldsymbol{x}\\vert\\vert_2 = \\sqrt{\\sum_i x_i^2}.\n", + "$$" + ] + }, + { + "cell_type": "markdown", + "id": "ad141726", + "metadata": { + "editable": true + }, + "source": [ + "By minimizing the above equation with respect to the parameters\n", + "$\\boldsymbol{\\beta}$ we could then obtain an analytical expression for the\n", + "parameters $\\boldsymbol{\\beta}$. We can add a regularization parameter $\\lambda$ by\n", + "defining a new cost function to be optimized, that is" + ] + }, + { + "cell_type": "markdown", + "id": "d194482f", + "metadata": { + "editable": true + }, + "source": [ + "$$\n", + "{\\displaystyle \\min_{\\boldsymbol{\\beta}\\in\n", + "{\\mathbb{R}}^{p}}}\\frac{1}{n}\\vert\\vert \\boldsymbol{y}-\\boldsymbol{X}\\boldsymbol{\\beta}\\vert\\vert_2^2+\\lambda\\vert\\vert \\boldsymbol{\\beta}\\vert\\vert_2^2\n", + "$$" + ] + }, + { + "cell_type": "markdown", + "id": "7ccf56c7", + "metadata": { + "editable": true + }, + "source": [ + "which leads to the Ridge regression minimization problem where we\n", + "require that $\\vert\\vert \\boldsymbol{\\beta}\\vert\\vert_2^2\\le t$, where $t$ is\n", + "a finite number larger than zero. By defining" + ] + }, + { + "cell_type": "markdown", + "id": "41939010", + "metadata": { + "editable": true + }, + "source": [ + "$$\n", + "C(\\boldsymbol{X},\\boldsymbol{\\beta})=\\frac{1}{n}\\vert\\vert \\boldsymbol{y}-\\boldsymbol{X}\\boldsymbol{\\beta}\\vert\\vert_2^2+\\lambda\\vert\\vert \\boldsymbol{\\beta}\\vert\\vert_1,\n", + "$$" + ] + }, + { + "cell_type": "markdown", + "id": "93d38078", + "metadata": { + "editable": true + }, + "source": [ + "we have a new optimization equation" + ] + }, + { + "cell_type": "markdown", + "id": "9c6d063a", + "metadata": { + "editable": true + }, + "source": [ + "$$\n", + "{\\displaystyle \\min_{\\boldsymbol{\\beta}\\in\n", + "{\\mathbb{R}}^{p}}}\\frac{1}{n}\\vert\\vert \\boldsymbol{y}-\\boldsymbol{X}\\boldsymbol{\\beta}\\vert\\vert_2^2+\\lambda\\vert\\vert \\boldsymbol{\\beta}\\vert\\vert_1\n", + "$$" + ] + }, + { + "cell_type": "markdown", + "id": "90d9a525", + "metadata": { + "editable": true + }, + "source": [ + "which leads to Lasso regression. Lasso stands for least absolute shrinkage and selection operator. \n", + "\n", + "Here we have defined the norm-1 as" + ] + }, + { + "cell_type": "markdown", + "id": "d1c9d3ea", + "metadata": { + "editable": true + }, + "source": [ + "$$\n", + "\\vert\\vert \\boldsymbol{x}\\vert\\vert_1 = \\sum_i \\vert x_i\\vert.\n", + "$$" + ] + }, + { + "cell_type": "markdown", + "id": "6a03fd03", + "metadata": { + "editable": true + }, + "source": [ + "## Deriving the Ridge Regression Equations\n", + "\n", + "Using the matrix-vector expression for Ridge regression and dropping the parameter $1/n$ in front of the standard means squared error equation, we have" + ] + }, + { + "cell_type": "markdown", + "id": "12f9e2f4", + "metadata": { + "editable": true + }, + "source": [ + "$$\n", + "C(\\boldsymbol{X},\\boldsymbol{\\beta})=\\left\\{(\\boldsymbol{y}-\\boldsymbol{X}\\boldsymbol{\\beta})^T(\\boldsymbol{y}-\\boldsymbol{X}\\boldsymbol{\\beta})\\right\\}+\\lambda\\boldsymbol{\\beta}^T\\boldsymbol{\\beta},\n", + "$$" + ] + }, + { + "cell_type": "markdown", + "id": "0bd449c0", + "metadata": { + "editable": true + }, + "source": [ + "and \n", + "taking the derivatives with respect to $\\boldsymbol{\\beta}$ we obtain then\n", + "a slightly modified matrix inversion problem which for finite values\n", + "of $\\lambda$ does not suffer from singularity problems. We obtain\n", + "the optimal parameters" + ] + }, + { + "cell_type": "markdown", + "id": "528f4c54", + "metadata": { + "editable": true + }, + "source": [ + "$$\n", + "\\hat{\\boldsymbol{\\beta}}_{\\mathrm{Ridge}} = \\left(\\boldsymbol{X}^T\\boldsymbol{X}+\\lambda\\boldsymbol{I}\\right)^{-1}\\boldsymbol{X}^T\\boldsymbol{y},\n", + "$$" + ] + }, + { + "cell_type": "markdown", + "id": "a4e89b45", + "metadata": { + "editable": true + }, + "source": [ + "with $\\boldsymbol{I}$ being a $p\\times p$ identity matrix with the constraint that" + ] + }, + { + "cell_type": "markdown", + "id": "af51b23c", + "metadata": { + "editable": true + }, + "source": [ + "$$\n", + "\\sum_{i=0}^{p-1} \\beta_i^2 \\leq t,\n", + "$$" + ] + }, + { + "cell_type": "markdown", + "id": "26945717", + "metadata": { + "editable": true + }, + "source": [ + "with $t$ a finite positive number. \n", + "\n", + "If we keep the $1/n$ factor, the equation for the optimal $\\beta$ changes to" + ] + }, + { + "cell_type": "markdown", + "id": "70a85186", + "metadata": { + "editable": true + }, + "source": [ + "$$\n", + "\\hat{\\boldsymbol{\\beta}}_{\\mathrm{Ridge}} = \\left(\\boldsymbol{X}^T\\boldsymbol{X}+n\\lambda\\boldsymbol{I}\\right)^{-1}\\boldsymbol{X}^T\\boldsymbol{y}.\n", + "$$" + ] + }, + { + "cell_type": "markdown", + "id": "86de1af1", + "metadata": { + "editable": true + }, + "source": [ + "In many textbooks the $1/n$ term is often omitted. Note that a library like **Scikit-Learn** does not include the $1/n$ factor in the setup of the cost function.\n", + "\n", + "When we compare this with the ordinary least squares result we have" + ] + }, + { + "cell_type": "markdown", + "id": "a7eaaac6", + "metadata": { + "editable": true + }, + "source": [ + "$$\n", + "\\hat{\\boldsymbol{\\beta}}_{\\mathrm{OLS}} = \\left(\\boldsymbol{X}^T\\boldsymbol{X}\\right)^{-1}\\boldsymbol{X}^T\\boldsymbol{y},\n", + "$$" + ] + }, + { + "cell_type": "markdown", + "id": "732d4020", + "metadata": { + "editable": true + }, + "source": [ + "which can lead to singular matrices. However, with the SVD, we can always compute the inverse of the matrix $\\boldsymbol{X}^T\\boldsymbol{X}$.\n", + "\n", + "We see that Ridge regression is nothing but the standard OLS with a\n", + "modified diagonal term added to $\\boldsymbol{X}^T\\boldsymbol{X}$. The consequences, in\n", + "particular for our discussion of the bias-variance tradeoff are rather\n", + "interesting. We will see that for specific values of $\\lambda$, we may\n", + "even reduce the variance of the optimal parameters $\\boldsymbol{\\beta}$. These topics and other related ones, will be discussed after the more linear algebra oriented analysis here.\n", + "\n", + "Using our insights about the SVD of the design matrix $\\boldsymbol{X}$ \n", + "We have already analyzed the OLS solutions in terms of the eigenvectors (the columns) of the right singular value matrix $\\boldsymbol{U}$ as" + ] + }, + { + "cell_type": "markdown", + "id": "06f71f9c", + "metadata": { + "editable": true + }, + "source": [ + "$$\n", + "\\tilde{\\boldsymbol{y}}_{\\mathrm{OLS}}=\\boldsymbol{X}\\boldsymbol{\\beta} =\\boldsymbol{U}\\boldsymbol{U}^T\\boldsymbol{y}.\n", + "$$" + ] + }, + { + "cell_type": "markdown", + "id": "04266404", + "metadata": { + "editable": true + }, + "source": [ + "For Ridge regression this becomes" + ] + }, + { + "cell_type": "markdown", + "id": "753d4bf0", + "metadata": { + "editable": true + }, + "source": [ + "$$\n", + "\\tilde{\\boldsymbol{y}}_{\\mathrm{Ridge}}=\\boldsymbol{X}\\boldsymbol{\\beta}_{\\mathrm{Ridge}} = \\boldsymbol{U\\Sigma V^T}\\left(\\boldsymbol{V}\\boldsymbol{\\Sigma}^2\\boldsymbol{V}^T+\\lambda\\boldsymbol{I} \\right)^{-1}(\\boldsymbol{U\\Sigma V^T})^T\\boldsymbol{y}=\\sum_{j=0}^{p-1}\\boldsymbol{u}_j\\boldsymbol{u}_j^T\\frac{\\sigma_j^2}{\\sigma_j^2+\\lambda}\\boldsymbol{y},\n", + "$$" + ] + }, + { + "cell_type": "markdown", + "id": "ea8b1f8f", + "metadata": { + "editable": true + }, + "source": [ + "with the vectors $\\boldsymbol{u}_j$ being the columns of $\\boldsymbol{U}$ from the SVD of the matrix $\\boldsymbol{X}$." + ] + }, + { + "cell_type": "markdown", + "id": "12703a7e", + "metadata": { + "editable": true + }, + "source": [ + "## Interpreting the Ridge results\n", + "\n", + "Since $\\lambda \\geq 0$, it means that compared to OLS, we have" + ] + }, + { + "cell_type": "markdown", + "id": "90522189", + "metadata": { + "editable": true + }, + "source": [ + "$$\n", + "\\frac{\\sigma_j^2}{\\sigma_j^2+\\lambda} \\leq 1.\n", + "$$" + ] + }, + { + "cell_type": "markdown", + "id": "b81abc7b", + "metadata": { + "editable": true + }, + "source": [ + "Ridge regression finds the coordinates of $\\boldsymbol{y}$ with respect to the\n", + "orthonormal basis $\\boldsymbol{U}$, it then shrinks the coordinates by\n", + "$\\frac{\\sigma_j^2}{\\sigma_j^2+\\lambda}$. Recall that the SVD has\n", + "eigenvalues ordered in a descending way, that is $\\sigma_i \\geq\n", + "\\sigma_{i+1}$.\n", + "\n", + "For small eigenvalues $\\sigma_i$ it means that their contributions become less important, a fact which can be used to reduce the number of degrees of freedom. More about this when we have covered the material on a statistical interpretation of various linear regression methods." + ] + }, + { + "cell_type": "markdown", + "id": "115018b1", + "metadata": { + "editable": true + }, + "source": [ + "## More interpretations\n", + "\n", + "For the sake of simplicity, let us assume that the design matrix is orthonormal, that is" + ] + }, + { + "cell_type": "markdown", + "id": "8741b7a9", + "metadata": { + "editable": true + }, + "source": [ + "$$\n", + "\\boldsymbol{X}^T\\boldsymbol{X}=(\\boldsymbol{X}^T\\boldsymbol{X})^{-1} =\\boldsymbol{I}.\n", + "$$" + ] + }, + { + "cell_type": "markdown", + "id": "5fe75d98", + "metadata": { + "editable": true + }, + "source": [ + "In this case the standard OLS results in" + ] + }, + { + "cell_type": "markdown", + "id": "522e6278", + "metadata": { + "editable": true + }, + "source": [ + "$$\n", + "\\boldsymbol{\\beta}^{\\mathrm{OLS}} = \\boldsymbol{X}^T\\boldsymbol{y}=\\sum_{i=0}^{n-1}\\boldsymbol{u}_i\\boldsymbol{u}_i^T\\boldsymbol{y},\n", + "$$" + ] + }, + { + "cell_type": "markdown", + "id": "eaa39cca", + "metadata": { + "editable": true + }, + "source": [ + "and" + ] + }, + { + "cell_type": "markdown", + "id": "230a8059", + "metadata": { + "editable": true + }, + "source": [ + "$$\n", + "\\boldsymbol{\\beta}^{\\mathrm{Ridge}} = \\left(\\boldsymbol{I}+\\lambda\\boldsymbol{I}\\right)^{-1}\\boldsymbol{X}^T\\boldsymbol{y}=\\left(1+\\lambda\\right)^{-1}\\boldsymbol{\\beta}^{\\mathrm{OLS}},\n", + "$$" + ] + }, + { + "cell_type": "markdown", + "id": "698a93f7", + "metadata": { + "editable": true + }, + "source": [ + "that is the Ridge estimator scales the OLS estimator by the inverse of a factor $1+\\lambda$, and\n", + "the Ridge estimator converges to zero when the hyperparameter goes to\n", + "infinity.\n", + "\n", + "We will come back to more interpreations after we have gone through some of the statistical analysis part. \n", + "\n", + "For more discussions of Ridge and Lasso regression, [Wessel van Wieringen's](https://arxiv.org/abs/1509.09169) article is highly recommended.\n", + "Similarly, [Mehta et al's article](https://arxiv.org/abs/1803.08823) is also recommended." + ] + }, + { + "cell_type": "markdown", + "id": "96e49fbc", + "metadata": { + "editable": true + }, + "source": [ + "## Deriving the Lasso Regression Equations\n", + "\n", + "Using the matrix-vector expression for Lasso regression, we have the following **cost** function" + ] + }, + { + "cell_type": "markdown", + "id": "f2043d81", + "metadata": { + "editable": true + }, + "source": [ + "$$\n", + "C(\\boldsymbol{X},\\boldsymbol{\\beta})=\\frac{1}{n}\\left\\{(\\boldsymbol{y}-\\boldsymbol{X}\\boldsymbol{\\beta})^T(\\boldsymbol{y}-\\boldsymbol{X}\\boldsymbol{\\beta})\\right\\}+\\lambda\\vert\\vert\\boldsymbol{\\beta}\\vert\\vert_1,\n", + "$$" + ] + }, + { + "cell_type": "markdown", + "id": "f2dd8e44", + "metadata": { + "editable": true + }, + "source": [ + "Taking the derivative with respect to $\\boldsymbol{\\beta}$ and recalling that the derivative of the absolute value is (we drop the boldfaced vector symbol for simplicty)" + ] + }, + { + "cell_type": "markdown", + "id": "0ab90bb2", + "metadata": { + "editable": true + }, + "source": [ + "$$\n", + "\\frac{d \\vert \\beta\\vert}{d \\beta}=\\mathrm{sgn}(\\beta)=\\left\\{\\begin{array}{cc} 1 & \\beta > 0 \\\\-1 & \\beta < 0, \\end{array}\\right.\n", + "$$" + ] + }, + { + "cell_type": "markdown", + "id": "1090467c", + "metadata": { + "editable": true + }, + "source": [ + "we have that the derivative of the cost function is" + ] + }, + { + "cell_type": "markdown", + "id": "8bc71963", + "metadata": { + "editable": true + }, + "source": [ + "$$\n", + "\\frac{\\partial C(\\boldsymbol{X},\\boldsymbol{\\beta})}{\\partial \\boldsymbol{\\beta}}=-\\frac{2}{n}\\boldsymbol{X}^T(\\boldsymbol{y}-\\boldsymbol{X}\\boldsymbol{\\beta})+\\lambda sgn(\\boldsymbol{\\beta})=0,\n", + "$$" + ] + }, + { + "cell_type": "markdown", + "id": "918da4ad", + "metadata": { + "editable": true + }, + "source": [ + "and reordering we have" + ] + }, + { + "cell_type": "markdown", + "id": "ee673e3d", + "metadata": { + "editable": true + }, + "source": [ + "$$\n", + "\\boldsymbol{X}^T\\boldsymbol{X}\\boldsymbol{\\beta}+\\frac{n}{2}\\lambda sgn(\\boldsymbol{\\beta})=2\\boldsymbol{X}^T\\boldsymbol{y}.\n", + "$$" + ] + }, + { + "cell_type": "markdown", + "id": "03352030", + "metadata": { + "editable": true + }, + "source": [ + "We can redefine $\\lambda$ to absorb the constant $n/2$ and we rewrite the last equation as" + ] + }, + { + "cell_type": "markdown", + "id": "1b29a63e", + "metadata": { + "editable": true + }, + "source": [ + "$$\n", + "\\boldsymbol{X}^T\\boldsymbol{X}\\boldsymbol{\\beta}+\\lambda sgn(\\boldsymbol{\\beta})=2\\boldsymbol{X}^T\\boldsymbol{y}.\n", + "$$" + ] + }, + { + "cell_type": "markdown", + "id": "206bcec2", + "metadata": { + "editable": true + }, + "source": [ + "This equation does not lead to a nice analytical equation as in either Ridge regression or ordinary least squares. This equation can however be solved by using standard convex optimization algorithms using for example the Python package [CVXOPT](https://cvxopt.org/). We will discuss this later." + ] + } + ], + "metadata": {}, + "nbformat": 4, + "nbformat_minor": 5 +}

    ($i2F3Ef_cZn zko?H~8DD;~E*en456*Ud^&U(ekZYdWy*AjrYLlJ--|R$@gU19k^fn(Lh}xpB<;!P6 z4^v_*%sd8WgW)|{vYwHpShoB6R(-HWLbIi@K%BcB20F?$J}@NjfH}d?Y;1?GsPxiS zgLdlo9L=)}*(!AIrFZGwN&9TGuey<1PUCGE5arca;uN4kBFzBJsXRMYXgx`gxa3A7TK z?hohC2QXEUfx^Wo%oX#<^Iy1p_lqCuIT~4;UG)0OHQBbFeSV^01aD{CdUnt?ZhHUh zV|`foC%(E?r1o}kN3Bw?dci2;lWe|zFFd_{f>H-7cf3{l>OTEFat#C#OCsa<>*3^P zHoER@D-0C4jStcgqg8%b{D%X;l$ZB@hxFYV z8Sml!sUyJqOR}URpF%dcfxJU(@(vd#kLd3@#(UUM*H}zH3X}aytjav~vr#$Yhq&(^ zg??24i}e+}?IE3M#rTvFx`P)xsppaWdhV$wb$Af{wcg^>`pe|IA?~TC^`ikb8b>|d z%=7V~S;eF9YU;u%3(eiwkvZVFLivm@_39)%hrjowUbR6)j%k6j$kS0?0P)jG9WANZ zc|Afvi)AKm)FiM8M&Z z&9zVjFa~(S^+^2sO#C_^g7^RkdWayo7z7C-s8<4lCq>{E!445Df)l1(^F>f02!aq1 zY!|^65gefqd@h1O20<~F2jO_}bDRjSiQtL|cIy!A6hUrD2u6q?Iv9edM6gu^n?$g? z6a+g(FrqXB!$dHy3LT~9Ipz&5fQvq4T7a2xDpA$B@wKC5`vW? zNN*28st9VefFM!?$Maf4ctix};B#HB(;`R|d7L6>*#UxPBDmcVf?FbJ+y#P$B4`pT zE=BNFHwey&;3ga>=lWg*&3Zu4L4#^!dCi9u$6Ncvw4IejbNH|~q z18r2@>2k(Ho}MBo0|zL$f<-VMcC@<2LBO}Bv&N9AEbKRNl@h_O6bQD9;BQ#a>G}f# z-uM~|&2zd=!rK?uF%k5E>1J1o2-?GZrK_z7hKe9t1gA0~I3WTJJeunfj67U!VTU^) zcy1QW%^W#o+>4{ZR-t{kgqb?gM4f1!PBcv?nxzv>(kaX_4>Ac`bfO(P(FUDpe@?VL zC)%A8P0oqt=0sC-qM13-#GGhekPcSmM6+_DNjcG+oM=i=Bv_CWO~{GX<3!5=`Gwgy z(PW%xE>1KRCz^>9O~i@j;Y8DLqFFf6Bp?qMf)g#liB{l53vgoXJF(`SSnE!#aVOTc z6KmRuwd~Au^~@0vqB@;el^`qBpwktH>7oXmSbI*aIZz;`i%N51g*maZoLEs#tRzr4 zR1oM@RKat@DvIh54r5pw^cKSwOINW}gSyK@Ur~&}PxKX^i(lv~5`^nOUy&+Y2l|SJ zP*c)Zd?0?IuXrO6exa|ZBpe3%ie2JYG2s@D3)g|Jf{9CX6%)iSbQL$youIGyP`D2C z70(LSfxhBt;V{rw>=3`uS9~a32l|R!;X2S)j2Es0eZ{N7b)c`PEF1>9id69nT}30| zInY(a3C|&1MV>20xDNCcKML1@zM{5p9q22@REA&ZE7l3ufxhAk;X2S)tgHsV&{tfG zgkR_@-W9F`eZ{>7@C#i<9pO6ARfsPnN>?Gi_UCGrCwxUe;X2S)v=Nu+EAFA|5Wb>G z7YNW-h*O-UuMh`wN?#!kq(oog5{Easz89`T95d%y8V7+mGEI63ad4LO65>=J^b#&O zaU>65V5g`{Y}R)jPJ%$}y_P=Xgt+`ncn`4!QhE=uPYS(@;;GH{8dX0COxjKw7u0lBvKg+Q#tkS-@?kGMvkBi;f_pCev-NuSe6 bI3DylF7XR}j(9*ppW}k3gviT!EA9UQW9uU5 literal 778588 zcmeFa3z#I=RVJusOG;a|+LFtXWm_S+B~_IwtNNu^OO{mqD0NHSt#)?_wcQqSRAy9V zW@l!k^3l~L8(V;34VyE7X^hQl7+^p!wudn=e87MKvtAFc9T?BRF3aMT8I~Qq>@F_@ z_U`O|&V8MXjLeLvh*C>l^C4Gf#JxA}IrrRi&-*@q<@a22$)%Uj|Mg$nX;rGt^YebW z+ziV>=R*JLa#-p$f@b%^cVC$K#tYwYVY+`!+h6a5y>=sJXdVRxN3z|XO?*?UW zwH-FRgJJ23W-0L0=e+4kx7+IMTUc1Db}PM=`BKyZS5~(5 zx3zp=yL+MX>fVaqFZkVVySmcrVzp>>F0Yn5Sc(2srMlng;358fWz%n{e_dVfwcL*t zzjU@8ta6)e3SAfaR}jK3^shPJsPF5vd|KtJTkW6|w9f?>di|@q{u+&Np;G8?Gi0!| z@Fd=M78;dW(Ch@wh2_8pSv1!cj`82%XyCV-^c#z_a5N}&d+p$Oh&eClm8rHink)Et zz1j>e9DCiJm8r_*l}js^_f{&eQgjE}d6H?T95(hXA6Y(nXrK2Kmet#{cb|8p*=>jA zUa4CRn_f5cx|P5yfkr#QoOd)_t9C$O9nWu;y%TL8tw3$nZZ+r-0jTxgzEz`(r2|lR zVa+OUz(Q4S0@2-!|K5!MZoz-IVxi0;RCZKuuiVkA+*v79rYkd**<&|Ij9k;dsskJX zR*LC9BjtKE7aUiB9kI9^D&1mc&Yd-rf_PJ zmvXwYy|T@&1ZZcfa+3C2W%_t!_Bi8c8-H|7BIt%V^cd2Je`&wbkAII3pOGIPy*p?r z-+`rkt655(Fs8b_|2tn@3*>P2RR&m;%7T%skQV!dT;haL6@JFsq&$?}MK(4Tq&eC%8`SSLQVT5SXA z>o|%HMn=81$f$fj0RCtazP-Dr`SypIC%rakLKEWzCA%`??*&=`7M zapd#wmLVfRKYtFKx?r`vwpSsEg1Ih0`3TPpTf3j~h}~R3*sflLKVKE4&h{VcplElh{R`^UBpusi%l*&U+T5MIwM&IKSCh zhZx}bD`Bt8qAK*1pk4LrB)YDU2>)GDLa;q16T%b-0iqX)UxEYdGn;YL zYYR|+R13iQC+Xn4&%pUVCxz4Y&~T1F9)3b@kq@hHK!|?TO0QlIx}zBJ=sk3sWwrP1 zy4!CQckOO9n5FI7z3c8)qqw)#FlbED)S)y<>&jH^GMGEkVR)ax@PAE;VcX*?8egN) zal1HdMk2)S;)JaoQWACmUf!4*FAr+G)ZU=GPCC&0w;R~=Qbbh>w#DCalZOqJ6P-0{kGxQ^JoMchxys@I$h{{9_&YoCYd|~oVs{o zsFh73%)k9=10uw#w^ltz+8;D8;^0a^!auxoe!Cj>I$-ZDsEtG4V)pIVJIwssK`CsP zgR))lS1<&Y2y1U6`k1Ockeb3CG8A@S3JSBG?oQZ=IGpKJF+}EM#UG_ZzwWQ#{3Vu8 zE9IZ_t9SwnCaj%x?;db4%hgCab9;K=>^6d(Ji8$`v;)6Pl+)?0tr=0l9O?}pBBJ}; zN&r(s;IRZsLbsw+Ck4JD=IRLJDMc7hrY4L>3`^F_<+w&{9}v;?E=wO4h9XKcKXt+F9;U z`SKt;oE{^;{<2Y$ckhEO6fCa^8xcfPLPS?sO_`+;A;Y{5i&%Gl$i~_USG()HAJD2D zv;vqN^*|>!x)lt0q8-A<)@XpT=RC6Pg5Ub}wP2;~Ge2GNVMX(TdO&tHW}x7@U1hAD z_fBB1fFpPCzSLF9mgR}Ba477;_g~?FfTe#^>YaPgQ1AP7*GVK#LWAw}UfU@NmGAkg zpz>EH6fso($^-;d{(Y&be92Jx_gaFTY>2R(5>fd+!^`0T(@r(~L-AS2x8Uw%+?s>k z$Zxdj+H3?SAGSA)ewAeix4v0M0dhZ?8o7rJa{pBdqJb0uNcFIMhmKmM z%DGPc>pS|$j~6rSYbg;7$r$D|uOyH$Zq)0nEJ4cQ6ts`}D`r7QH?Yf9`=1DusoEdn z&m`7M(#FY8YiZ*@a)&h1#!r#pycr`aNggZ!8}li--w+_M^;XnZ(v;nj{-s*dFVY|3 z#v9LZ$XL2;7WaSGT_;fl9mclPpV>}h4&xcCfA5Q`-5qaw*Y0^X`ar9mF+`lAhebg@ zMJEvd<(H+!)YlnIU81`t!IbTk2vf(%-2^H(>L4OGs%uRp9n+3Dr;NbOAb^2@jK!U> z4r_+-1Slf~I|;DotgxK(s21b3HxnYJYB#4w#w zO0dmT2$e99+gDz7)!V?!bsz41dbt+RUo_}KQ|Z7SgD{d#5WqHH57#YTxAGGX$$J%& zcc(`3I}MT-QXtuON`&Oj!JrE>2xw9BWv@v=JtT3ErwUk~gThxQ0wqPTgMYBb8IySaHB*cIi}G!^ERU;YIg)x=-es0$DaEqbPKlP~ zoTmL&9j+!OXj+62NNt1eRiGDX>ZH8m4 z=74j-23GuB)o0ff*j3N~5jcKxu|Dq>XGJZ}yHhXD*PF$8I>qAHPKg$0>39ffunAO? zSUv~rx4~H~3-4Ay{#S?^(dj-${!?=4hiKq8X>U=?j&7j^fa?PmM4*5T%kpBbtGfBK4(R}5{jd zcXRIW#(ogzZfQi;+DXDp>n`1fwEi>MA|1SttA3t&n{L?EG($kw&i#ZAS|KTQ!I`lVHT(JPr!? z>9Nf)9W$mO%E^mmr}M`a@8e;h#j>5;VvYY2St9HT(_SB9dQ$_txM(?#V|jxu48A&G ziV=oqm`W0cckKa=vi6oZ*xoF9f^`}p$fCv?+ZT*r;&L*CJ|E7^BcwvS?ur23^Y=l{(_KVm8#^=@Frq;?3pZRI2&NY~- z-5nWe^j@v~Cce?X&!n8BUH=R2taz;J$k;%_OzWnRG$JrJrqM*qT#j`%XyJc5oTyh* zwZ~E-gbzlYgJTId39z?LByIt8g2oep-=_A8f#3XeC@@bj(laTsaJ?Z5AlU4`BuKa+ zZjTDM1HF<_5BB_TY?y*8sE zopjRRM3&v|u-(Q8Q13Z(&ad~Bl+P9;Xlpn(_E8v7RHch(a~!#WvvJ70UG&8VuB_Sl4#_d&EddG_=Y~G{@4*ZeDIJKCRZ` z*HW*=a}(C$WNF^pkJz3vSsz#7%%DV64|ZS}j$L8}GeoQh;Wf}QIt$Qd1Hh2URx(;17%kJ`Q!jVAwX%{Lpytoh(8> z&{^0e$_zL84Oqi63?|T+Xi~=T7HiLkWtq+SbX<}S1i6V!4HTu|)Dt03!Iak0iIziY z#9e^3(7+xI+MH5+LOU2(+Mt=JO{U0#l$hWCYQmln?7q6-0_XoiWN!_sdaoIz8^c7S zkL`}_N8jKJUyOWV^x2|Rz(8Jt~5eBbP~-=k*KHmeh+u6O}LwB{5Q6&E*JS zS26VB9$5U=yenApcnkha!U&nBz6tT@+B9`DcbRCKniewO-EoQ3bI1my?DP4G%05@M z6dqaKFm`yJK5?_D`0j!)jA{X**-e0sG^X5=WDc0Z#C8_5lbd2v4@4$4X;a=oF2`=T zZ_;dq73KqO#S991D~=fBd`+}tM7IS!No>`~(LFBW`VF(QClC!C%+Buf?%I2AaqoS* z@4k1>efOHxjO6Xso{FGC7}u}lfeaPvUk=gc^;GTaBV&w4Cn+~Dt3URw4m)N7%#mIb znY8;_^bJ0MpDgIlTxl-)9$oJa&j)M7Kor@?k?SD(9QF?(AZ7gVJedZ}pH0 zQAVa$xu;Zbl?Tod6cn{WIpS~|QX;S4hHSkC899Ks%fT033&#+&9*ExTXnhVO1@&Kw z>PX2Tx4(+2V0$6OaZvRfE6zq)#=ne^i=et!E2>lTGPF1N&@JuYb1cv&BLk1eG|}O= zJ32J8VmiERpC^td`i0?53$y-6D!n>rv?|C8=|~swRT}qZ{`R+Cop=y@6I zuIQGC5@weC3XX${cigY}tJOJgRsEiC^6$8{zb@KEEcWm_VE2{?b_ZAYrtx3I@{VcY z)^|)JOkp}Qh0%yq3k(M`3+AKeCRX^Lx)nB{CRt(8?M-@mNjQt>mS}}{AFKMs$9}D z!=j3R$F2Ddab3i6$G-=f!w8xOSNip%zlv2J@z$;Ihz9uV`N(G{t?rxj){dW#SlJJ` zl{KIxSy|Doo?>N1w?r#@=VIA!c#om{=L$q^1gPWZd`;mymv1|W;vH1oKzY}-(-@g;R5k$=crLJcZAqHi)vkSs5I0r( zTl|?M-jGH5L(f=?^j~q8N~B88I3wkLc+jYtoVRPA_e7~1u0XB1-rBW?xmNwET=n_GeLoEt@#b40Q10iu*#-`~Mfv zj&44r=;k}=j|f2-n&{n#J{MdgHkV;R_2A@ryaPHGC0np$C%PCZZsD$Oafl8dC% zp3HV*8lv~S&e&ab6njw1s{YMUj#To|7WsXNziRRLl7l-{`=QiJ_T#ZjmLhQGy8Cw* zckSG%mvNt`Zmz)Y8Ghj~GyD#G>St0<{slMrpVplxF*?#iM7NLIZez5+*WP0=g!1smJ z@O{j|_xTj?iEhc@+j~#(?t3kK2Q7Tj=K{XyE5P^V)bM@6!T0wm;1k^v!nd=y_ihW{ zAqQXNxr8tB3h-TjRa$=k(+GJ$ zccq5-lMdqP6cCGU4q_);#zi%f#Z)jVlE{Y6({DWj5lrjETpNir+kvu3q%|u6$f%%D zI-PDxmA!=SP0DdZVTM90^;Or^3Se4W1;>B6Ovf$#%VkEOwWZXw_Op)G-0C}`>0d=6 z5X2p!cZf$3Yq=BdlPDM0oz$hS&E*wlvkkwn$gZsrgj2P5o?O&8cPr1L@bh-J6=0u!3xI0ARHlA)i5y)stHSxmolr8r@P3U2Ilc zj{rDY%(3-fY8ym1w%W^MKkF#UpogSox@{H5i%GW;gA=(%dGTqgJSy2S zbYW6c28fvR8R_bP2C4J&7|KI( zs+G=2K!qXDXZsCs@)deo`odu&XB6Ys1oWA-()zr<*_oAzs%e~B><9oKTqu79282t|9)JKwu`XRFOX(1=JC?hH>NRa`@N_cFsXCyRJu39I&Tf)Zip z#N5Z+!%85M9P#U)vvR}>+$Bxg&zUohtX2)=n_sV^v3``|f!&*r{n(6!m_7PtM)j)3*}bYkLDF{ZZ~ znPen}WUl3JxK;d={?Mewr&C#U`?m?Zk%dHb`vu!=j0Nc6fl3=UUW6^m4>^Xscs{JX z=>z*g7$-Qsyy>09!M@g1*J}_3MUO+Xiunv?*R=Mh1i@78MGc5a(-o&2;Gd! z7mdK-YlMn9?^KIY*@O1r9_;9+TrO*^wLtrD;r@H?+leH;`}W><_q{u3v>-pYCBJTK zCTA9VtA@AB-`}b)fTaGP#3ZG*JoF`X^*e3($qOR)|7RU7{)44O*c7DfUi)@>GgUJU z45hpCY?SaWM*llI`eaHM-I7rH={?W^&Me~A^g3>pRwAr7z4$07`!LD3FFyZWPc(S|5yJ*35&L_|^?zIlvOAz?yyeIBF8Q?J57^Hb5w9rE)`Fa%>_Ov$^=svRr zBTnO3ryJgbqB)&tN9@{r|L&c8cHgsS_X4atTtS$nZg^ne7^7M=D6feK3l#MaJOp!4 zjXS@J8pYVD8~6n|eBiDM^Dz%)Z|l0KD%VjV*BWjT3Q-=Zg0j;3vQ48e;BzK_p6^5- z+?G#oDH_f0d}eFD^5XL!Rm&yx&aDP$sMV*2r8 zB=WSw6@LZy+rw5-8scblxDQ-J=C~HzxGRmiFv_(W^&%hD^gp}U;1(x1@6SF7v*+^| z%27}rqha}vrrf)8X746JsN9;r?Y8FOgj7Rvw&->!VK*W+(ajOtc+w`nhY-(6rBk*x z*R6jIomWIKGE{uvVMI@LI${z%^=4!J9=Pa{!}s6qgnaKS=KSh^&es>>Nh2Lq= zGO9Tykc3%Xd!mhM{Ll8PbRmeXofLU$@lyMF0%NN7bA;do#ZN3SI4w3@25z%KJ92O|0=x@ciROBN$Ip{f3iuo>7?c;f}iS!}V1MhAWFykjW z^^i=a2539NvBl+Gh?Ig;hyFqN3jB}VJ9&oiUqVSks3eLI(J=Hal>P^sZ-ppi(p_2R5^{96{;K04bN@vcR)H z`ysIy@+VcPVh@2gdSZE zTafQ?_Cs(OGVtz0?Iq{P@ev5Jfzn|t#e^+XYpXtow}|}!gF(WeZ#0p72X*U`@3>gD z+pkF`O#c<`A=K4KZ{sdbnC`RhOUatJkOm12>!DYIkV*FmPp{uhP)fo{c1}&$7EMUqd_L|85?sWWi70Mm@ zc2UQzf~YXuJ=*rW2t7Cj-U^mY`CD3Pqt#US)>aj@SA9~C@28; zSgOUxKgvaUuoc7AA|Gt-_&utI9eH4iaRpIfL&$OMfjMMCawkoa(>o>G)mhFdd%3l` zpw{X`_%n&ul1==wXYHx^9o$8nns*=smg=rj_$sdu^AC{-$ctw)0h2bjbL}VXfm8N} zQ`6oRgOF*?nIiY@j53kHL0>}Q7rxOMjE0yJq$#@kh^}@%2d3$x!5m>o{2QjFx@x)F zYnG^s63I~XAZ&LYFelWOe#0WV_VbD;el9f}XN8_Gq(;v*4n3bwfgaH<5qj=?l#+vhBCioZyeg|2BrK%J zBg7&kaeIe?uP7A!V`>z<%Aw#(DNrD~B|^cwk0Edg7wVuyBn#i@UA=kVSfb>%WDgYYQ>D=k=!W8zCEghvm<%TYuA9kL|qR8dQ`ia(PW7%3;O`-oLeO59~)@`=1)XcoSElobkEHa-_l z=yPG6Wl3*(_s*U7DZ|BiTemSy7YkKCO)n7WbDGACk8`~AM)6@cI6SQD&Ttu~P-RXY zRiR8LgEhKqju<>`(xc&;iZOK0p~v9f#}1iO)ImV)+O8YC%BcR*a5D5(3~fIH?WA5V>{8y%{C)WSR&RiaxWR6T?ulL(_BMVPKGgmickv_-cGAv(H4`t^Q)ZOups z`$NP^(2uBqkaZY`uumz3{c>uAz0o1;7gHcibW4P=J5KdlE!>8Nya80BrEBRq+W=K1 z!Y1sr9c0i28#9)Sk~Vh;_)iJ}pG%E^H#r3SUJ3+=Zix_Z^vPzYhsdIHRjOQNjQh;F zp#39{iKqz@XO|+9%00HS;0_9^mIgV5tyc9O-H!=6vS`Y8P>0O_Lm~4oQX}&%4w-+R z0-2(lL#7iWMoAxn!MUSkd^h5Y;som2Nk;jiJbbU^gif<&MmC5%b=bS^Rm|sKLw{2F z(maQ~SLx2_j>g-L2R(8FHUl^X>HcUs@JMQ~1ZPPnNmB>X4h7O}sX@BUfpm)nX)-?+ z-QHxoMVCleci(a#Y#M2Z;U7SQ1$t652k-+5;QLbpyu$%}kDd8sfJL`N0KX9_q==0p zg{3*T<`&p-O&p*n6`&_l1A2!8^jHc&MYlwNzIw6O4H1nATdKS7bMT=9rmBEhOAXAl z1E!n;7||^eFdL5sO%#-*8uCUKh>LUe_J{TEbI75yDS!|tzK)H+d`Nf_C%nhixOLpF zUG^5s6p~4;>)vtA2rN-t#2L6{dR{Hl`%*8{tXrn{q*x}=%`MaTbApsx!Gs(;9^Z|Q z7s18d@iM*}eNCK7q#s6|2j%O>Qq$a=qdB)OZaMqc zMH6R5G{1RgkKf_C7|tw^#85GJ2({CZ^{&e4Q0{Fv49Uk77tU@3m2{o#qSSs>ZPQ=D zpCks3+dgFt9KXa}#QA*3>@15S)lR9`ApsbKN&c_8zkF; zYNDX_ZIj0}cu3OJLf=o)8U*zpB2ycG)Kih}9S%c0?B^5R+|13{6Xr z-c9`9K6+%C)3`XQAH0S#y4xYjOA(qMt#%LhR_Lx%{Oc%|4)*eP&uf-BXv z%3w}~&f_(aJT9|a1lO!`9el&a3_+M>ds)rN(nsyD3Bgmf|2x(C(<0sB*8eZql;o=#pa2D6FQK zTmC7~$JMVM)B*>S@oZwf%Glu(ee*~(J0|B*EzNVr%Jv9Aqbb)V>0OULB1v!B?Er(G zBzI7WZdd9_Ogfin=*1rph#p)<7sxlZwK8oSEP>E$lkt8NW zf;rpGRL>Z9f)9mjxkEOIxUlaD-u5Oj4gCBd#UAQS%8bE;n;OrDM|=Cp>Jx^RvJ7Df zr}i+d*HrCoLSh=Vo5g-*AJ*ogK*(17B$04HG6?=GxvbQbhCz{1MG`68-;jVwrT&*r9M7GSg8 zE%N)D9RUmWq~2$f-8-sK$bOStym=JL5(Il49lTx7WD@z%2`joCPuPtZh3NLU?Kb9w z{YFJ-yYDBJo8sn%3wg0DMS|`Lt}zRZ9MyX$x3sefYTJE(0&07Jscmy}G9;I23`cjF zh5_-N-*Vy`!l)#^dmQm~Ejf%n?I<>$h);BTHeoj+KG7`^@qP5nspZFa({&1lj~V+k zvvnKQ29ncWC#FRt`IM{dT;OJd{!vAf`xX`^?OqCoSkT{((xgty9h7rU=090OtXna( zqv5R>9i;vJn<4FN3nNMUK1bT$YiX3ylSTPsQ$o!&Fh_tBfktVeV)P4k^zj>qc7W)X zXb1e!nIp&d?7VyD!e0E(KoKF*TNc}0^81q!^ax`6>h6i9^_08B79^R(zeX;j+$8(lCixXh#@Hmsb6#qPyu3#S3eC)u?_L4+FIliB z?_SX@(eC{NI=`rz#2zX`u^0b?fHC6Q{!7Xow?y)OigRhilE`iMpxbtTX6X;x?rE|lQlXQrSvH5bE&dR&Y~V`1DFsr# zV39I;Q;KehHsvqkNZq^hzMbB2zsnxFe^9FLv9njMo)t4vOKj_*mt)YBxATTM~2P;^xhXlv3F2HqCa+VI)g&wIy2EsoFvOnPeTJKLZ@P~B#AobQF?GElCrbdIj7ODaa__@hE!}MDd09QZF6GZ zjgA;3E-6+2IOd8QR^Y)S!zQAKI$96$)^KNxNODkKAUhP@xLG>8)~39NSXO)QCUIg2 zV$=OC8T2r(Y`bdahW*6af*cUM|DXb?GaQ!Tko^}Jog@oP^uT+!_t z5_TgCmgts!wI_)Nr-NVNaB5pBzEue7U_xv=sh+m$M6m| zARg~EkP3hs)xBdX=`=Y~y1%2VO%DNb`^~KH(l8rYg9aHuxP&5efGgg)=YuAmqgV$A{_xs1DBQQC`K>g??)U|EPNekQuVdY{C@*(~}uk zMn^L<)m59=$XI~I7nSvZ5&S>&Yae-7DCSHbLCs_1q(Mw%9rZE@J-Dfo$LYdIjJZRS%Z1@*8+*e@WI2<{|Y5`;L}Hl#;Nf>6~t zNPF8LVkuXt=rU&Jm9S_S7GZw&w!wl~XugV5pC?`1TE`bZm!9pRumxR_%ky+KqgVYB z?(4wSqD+1TJ2kq!2bbKbxj3X7vH{i?l^QAD5g0h2_@ts}M8HFn(Fmq=1x;du72T-3 zbUP@R+Ft5DP#;C3+h~vedgmBY?;u%K=p9OBU6Brd8jOKJd*Y37Jy_QD+?qC^N=9~H2I8| z1)@i?3N!+m>|R|okePU)dUJE9jdwEc2OP@XUZM;`J zrKPFMPuMl*>ylEGrUx4z-Gm1v$UU_t9{U;!kSs}O3YN_&SD!4)$7)*C-)GZ(Uq&;s z%UJs$NyAgMZ;c4Wlg+X#Zh^j8cb=q+lTk!;d){^%W66JPKLks^XPD-CH)kL-D^+DE`^hC|-3a{?{o`EV?B^@wYr_^SR9x zf5x)03NNp#(4>fRpd6MiFB7(r3Qpl|I2U2w=)f!h`4-iHtG;&><+DQWda_EFc7fDw zoh>)ECG(fbY~1qwj#|FoO1*p)w|t*Xv3#OiqUHN}d16Egc`(|!c#Df2mTNoCy2T<6 z>_hY3A!Evd9cwj!y#-{k?zhX)vLS3;6(v-NhpGFw$hZ`lnqBZ$?ED>x{HY?57gLi+ z&5_8Tq#zN|EfI-4AxT7u7G+(0%+wxhW3f;t3M;E>kFAK>W2jdeUwbU~aUDv(tWf$7 zsZm;YDE+$>C>7ljq4Z&iQf#Bx!eq1obe%ht+GuuwU3ku@occw;3%b{dP3Y3U$ ziBPg#7W3g!@5bdB^TvVohyv@O)L^w8SPvuv>wB)Ca5elNU*|3QCxY*foo`8Pb2qdr>jk#y3P4E^NSiVx&D3l2CWGklh|a2H&+=A`b+{BYB!j z=C=ng1~tLH9mqGhpvB(u=^daOKAYtQh&fBBEQmeoP3wQ49O@n_Q&Gq4+B5X8$9i>$ zGx!Hf>MDc{HtDZw7%k0xb%P02^2yYjsp~e=$z+>}_mJr3_Rx6C0{Pd421?%GA^-Yz zBd-;$Puh9R?Mvsd9&&*@cXJXK_^WNI8jdr=v<4qq+Npg5p=YZ09{ibfuuydE${FkU zKF?j8IMAT}NbH7!SkzU) zWJw`g5<*$w6L_u0RQ_dqh#4ac3)@jMijH&zpIAsab75ag-4)3GHcgV&U-&9> zM^^u;2UptO!b1hKZ1%TZF|N|_p~wiMmHYlSCD~l4?5Nycxr4$V3jzJo!bRmH-iI|Dj3kd=uwuB=b!VdsLq8x9bAtFjWL+_aD@^q zl!&_gj%6S*j^12n-yp^+Mx#zYW@PP1b% z6K6L6#ndZgPSRl@Wsg6IU>5>`E7(!$o`?}KcGdxdQUO5-d;?PKh8K6NA$kS-f-#0$ zeDGZi9x}EBV<8@dRKarrVjq^lT!Qm-vjl}<=ztKKo^q;UJk*1xI(%#e1`-*6>Z+dt z?hx5fmjr3NYL%{u`+*=bmCHey(a%vP8fGmD70mkJ^2gFy3Nk)(s#HB&?G{-*SK5Va{vi1CdnE#ru3h39hg5QNje}XpGHcdohJ&97xh#j8b>r=V)hkg;gaA=(>Hx_z zErLK1BIuk#uW%}%_c$!!ZizaQEI1eov}C?qn4OgiG&}2#nPRGaE4XXQj^H~#7dar} zLQ-Pd9Lj}Ph?(a!U}}iOsYZo0bKzV9to+8z0@)qOSgDwI(jHl6wU_XnmT`+YZmxfp z882o&HN^CD7%U4cr?%ky63}hQ@LAw}Aj8=z;L0>imiccVI^V^tVqV64YcTcW)$;T) zYQ*3}C-DwG$JpDhOKPE1nR2)23IU_U4;d?8agwb$dRXYcf`l~zwfY?c==eiSu>7}W zl6S;ZG7gjlhDW4CvKgsMfRTNyERb|BhWIC-zc}B|g0X$etn+L}b`@}E870f?AIu^? zi}`08Cj$i0TFr)AS$oYpt-U6~K(BiG0+`g`!!g|UiNxHN>^4+gdK3?hEA17X_GH_G z7@e$pL$-%~_6B#S3R5ZwYf0wZ|^(4jyhfftuIGm8EPrKxNY|F7absd;^d0VcC0yZ*zw_ z-a*z6*%8*-expIg4ik%3(1m@JLV&{RCR2m{b}HdIHD(ZCUx6=S)h5Phw?v^{T|ucJ z(l$xs8`cgX`2toO12$lraC+dLW!~PYa47c0rn+N0R3g+Ccbvww!A+Yvte%*EP6MWf zNC*gvnQ2MDlfz(HV0kzrRSQTm50wRuw`JR0j?HEqCr{7nC^IgnJGHCuxZ+=6Kd`fMN*K(%+TMuT;UPE=E?FSA3D~1ep)!tBZ6s9u=~yHo zaE{8;TGJs(-Gyb`Ocu6R+3E)4toJzXufeTtogjcklb#ZvQ`O>wZfR!Ta2@PZB zF!_*qU)&+%y7gaeh==0XL{fhAd8A61^XVsvE;zJ!WZ~FRX2C3Ile~*7i>THV@#+R# zI()cQ;G`*g(AoJO;Ful*_U$En(j_>&}_q5VxZp5afp zOXUTl+riNeb#8i0Cc*D51=S+{^Nv>OJmwlexRPz3H#^(#TNKZs&PXJdldCao*Kt$J zsu!;CsXsgGO`m}#pxjPSc+lEJBEqYL8p3d&aUQ)Z{!#Kvjd}WyJbcYyy|b`;*ZueI z++D<3tcuOiI7Kl|(XZmF3N;Q_pwrIc4er8oTEIn9^)B)tX4JA!ruB`ZKogsBbQ>(d z-$lyncH+WACb|)w8u^C~d~0(0=KRz&d`!Al)&>QKiGg;D4mL|FYf2u!&Edq)X9At_3eV9^#JRH61ljZF{Y-)kDbzkMpFzElhZ zY#rSxY6|}EuHQNP0Lo8rbVa)d54Mj0DqJ~szre1}O zAwbNAKVRz1uLSM02-4V?M^NyBU<&i;01+#cwkMYJ-UxAuOW_{LiXgMMvJd38UG}j6 z^dk|VC-bFqjxQOEjpj?Hg)w9f@}=42Bx4Ymri(*WnqEN4a$=+?pVXVQPb!w2C36{t zJIP#Xchc8~$#F7w5u@+b5G3I)qFW;F^7BujwC9GmzaEr3Az5D`h=Dt>6?LWFYj*1! z#8Y&bQayxD-R?EP29BusEEsC}igtBz4Y7`Adm#mFqsIxq0V}KT9V;C`8d=?4!57g7atHbduCgNu0D_k!YmX&c zkI;?aAa^E2hoSSt?H!RP?t+;~i$?~T!&!7H=|1zg#(u$R94GRg zp&<4A#|E|jVuV@;_r{$G@nbg3%s~4Wpa1Acj0(7te`Kom>Bw|P^BA?c-YhrQ(7MTe z^qk{G1}91GdlcPbN%os&XAdKSbf2=}D#C;zoP=S>(V*RsWn!2*h|=^CGn`AS;+PTc zDKcfHkIv*~uyj7)up510@&6dXr8rsMcX8)z$mwEF!}0oyJrnHI&qtPPH0c{{|Gkc+ z&05p(8Vw9E?<&*AL_MBUQ+&S|+L68M*540NOE?wBsRmFo+9fO(gC!<;Bo9a+&d2& zdL7fkl2Yx;*Rd#mIsQzNq$yYFn|{*T_AcQrE?4RFb(dXo$tmNhN1iKhd<3!COT>ow z3642rH0V@{u1hqcqLixIC1gsiS?ht|ErY3N14SP@IA~EX6Cnn4_%h33e$(*J1_cpO zuTEZ?%$$r(u--5gCjnDI+owv4W;RHBXhSDf`OCUMP0L(K3GWx(qQc(;iKuL=I+vHM z`|Es6H$t))!-1!(KPqe>0a)cdU|_`Z&mk5A6)E{L3eF9N{eS}TP4P@vBC5>-z63D< z_p*^;0yYnF^HovmxJfl9SgxQsVE$!D9w92{m@6~qyyc)&X@>Q1ZDX!*%qD=Ti63er zy&^yg8Ppe@;{`+>t*!>H|4|>Z3FR>}9_+d(N9Exj>Z;nRmu#0k1@XpxzvEnkOZiZS zIH>a)5zK5mZ32-)9v8(C(+1{=Y-B2+$v#$UI1GOUwEMH~7XeEiqh*2SP%c|n0F={! zSzvEOVQK=Tyhh9d)&A@}RzQ@;Xj!1yW%yfic5elX{w6xd%+(2T zqZ|$&7?en&TKegqLvH7hE|haz$P-ZUayH{}CM4VQ@Tft7KNJrWK;zaN9VfhsBf>j- zMq>|B?2Zo5;cDWM15amDoj+jWWEPeD^TK2Jf)X)y~O?P_LFf#A0^f5mmKC0FYnbpaR_F5gC%SOxh@;fTm>% zOc30z7&uK&UHeXg7tO>J7pGC_Z2(OXq7Q$ia~76N6-bKaB!j5dg*e@j25?{EvGfJ= z@Z+M8gq1Cj=+hod%J*;|2sn`Y921(l^BQakJ62Anfel%o8@W{67c zL4iW4Si~c2HGd3&_#{5k1gag19HS-Y82~H-lA8wS zOOSkkNHrO9)_WnB#ew693W3iR5P^o~RDK)sD#e`xNh?*DeMszuJXM19Rwrpoi?(x~ zk}n}XLIOmAF(7)51W5X5t6e<@s-ai>v$p~=0?E?dxr7E<_#SGjx0%u_usn4ro!PG= zP*`7EMPP6km$}9Y#%8uztprHTtZ<1wWpRR>sS4WD#;63><$sJWad!e?L-mjDNy91xZzb^1H&yB8mP=PJpIl6(N$s(X3QQ(jzN_FqcCW zgtDsIvNakS1ZjC(w20JWs0jhe@t#9NYZT{OpYV->R>PrLm%=sD(4g92CnF0F*M+jp zT15m_*VtV#y?A8CYT@u3U_Q_j3k|sw>c5DbEITLf8*Q5bAP^7MgQVA45b1 zMeksTc4_WlSAs(;fR$d(40kz^#%uIVsF5KhZ0d|91rsThoV!GKUa`*XwL=qRq$=sV zif>9^H|nLaE;tnnmL`rSa<1OgizGHp9;1OAznDOUi)pi;y*8PsMZ%K9XsKb53S2IP zD*!r_&w!a=%4Hi#nDQAg3rxpy-P8iMoCnSV#vMypMv0mIwwbP=Gs(-5BACL0|oYh@*1YvFk^ z|5gz|YP0Dnho4K~RWS#gdKiY%R$w`#R8YD;5l0f;Tnl!;7Q&EO!F?I)xF4{>CD-5r zM`0*F8(}j0ZrL@n(ee;0Hk^06kF#sS;~&J8L;eeW{WqD z2bwUd-!+uc)y@SY!6m)Yt0EDHYuh2k7XIdHsUS^={AIxT4x}@oDnJj7;kYLYC7@a- z%kSABXwiv`>H+`;D8ON>B3${9wBN%~2E<^#zV?T~)=tJ(eG4Qo0fTXcJk!cN3_NtI zYZWXX9pdf^5}c-N{8aVfA&{UTDv1J~x{?IO*nvvS1+K&leFiIv^dfWRr0X_hSGF^D z$Lzs8$V~8te8$73n!bLr13ae9677iW6fYpkYsAzri6a+t$YTQzLY2#iS)kgtd43=u z$udfo*&j07GZRY^faEk_7MLE+$RGtYnTN^($5K9wT7Z++h?$_u=iHD`8swf}z9Elp87P)sJ7LnY7Ku}aw zLNQ<^-=GpL;`jM}Xe}rpJfP{7dmJuD=N@D#64P*jH^hMw3=|0PH6TJJxAi2vPa-6C&9;X7BMhzMsrN9A~7>TreIu`A z+kUHBuHy=e6FTEET6ht~M<7)~J|lGNf=|kw9x*r2MHK~8g_$iyHiHrpcYGD*xx$%c zTWV!6Cjwv8C0IDCdj?HUY%GVkKiv-7+JNW0R8j94urpk!#SMh3Z2ZoAHC&j10jORt zASjcF$d&n4XF3v2p&(E>eI$%}k5;>fdn+CV4#2$+TN02B;hX59p(6uW5LW^u;uHuo zL{4-sdI#&u-hYZr!QJ322_rh9*FgFxx?vR9pNyo7zC;Js92MdLNzpVU6EBu%9?7w| ze;pD!zEQ9usp@G+jVd=ojetIbh4QgWpk}Cg*675M3J4>p;p!5SkD0XL&u;}(nOm26 zZU+#$6&=C|1^tAT23v)i8e*yin9X3cqe%ztHo_6;UqoBf+Xhq+oykoBaa%;03sUs$u1{uC;BeSrDuePvmgI6(N$`njOF)|~T!`S(B zH6N!w#M{+UF*tD?bB|m4JII(BBU&! zm^7QghfYQwe2y9XdW2JsPMJzy2l^9EJT}ahbC)lj6DY%voDd;u+!-{;M-B<{DZc$j zDN%5jwjHtE+(q;klB9UjvQ)BG58z&0{$V16Nix8mXG+-8(9?GWE2w<{~lm&_hM#%C> zR4V~OreU(o|3D7voq!{k;j+N9Kf9_az{z8@EYK`w)_MgnISiHwmdyIMgeCi6SztMs zhb2IOlh1frAev2KmT=NRnqD!pn{53R@*Sm}t0XVit$!ou>sLEStcWDt8IdOGeSSle-ram$`s@f=MjY}2`(tzM5mGIgq%(f8*0^?|j?Su|-NcM@7Jk^17Vif3@|japMej=A}~;7 zd*&QjQpudnp_1(Y*HyywOsms^nYvRUGp4gV9$KdL%t}mx)8#ZEw#$bj`beBQ5Yy(S zk%TQ~Ii^v}muvq$d{Cy+ZU6ch5;g1~_MK$}Bf3u2UWkA?TJ=KBmD*=88&vGL;Mjyg z16u}e9JN;k{G;2%fIlAbLf2l(hZ%@@<~3p#sJ1EIBxYrv#Ed#fDzA^_XNFitymjO< zq5(epyLl4K?TR~1;I9JygdJkglbDna=E2Ryl=B%c3q<#A_Gl4MY<`SQ&wP-er{YgJ zL(!vNJCYvN0`vR(JZX9^&ABTuoUY%dv5I|gD3`-tOg*Oov%vJ$B%+5ShD6O{=Hv8( zQMDt)*+?REw01=Qn-@`0fMOpIp-OVBk%6C!xy4vzfIxtwc1R3CG%u&>7Z4c2f*XQ> z5q3dB9fD0aP}%^Iv`Ec{AgP5*t}8$mKE!LN(IAoU<4r^5;}7I889@iR3C(WA+!KRbsmK|up;Gi(KL$rK!^%`VGW5&`pO_4 z4p+Wus>7vn934*MEm9}}U+b+$#P?BgV|ByBWY#E1%0?`1ZBK_yx7|bSLiZuH^KmDL-u9}$I+;+lrbp3T`aC-4*AZW6 zc3}S%41qflUco?sy5E_ax_{JB_fwWk$8QRvZqY3fb^pkLI)VVXVB|jUAQi0~I;YkU zI0&L+BUmYDciD2NMVhvcBLo-kRVmc5%f>ab&XHZMTwP^KN3N3^U?qT&3}&t-B}XB# zmrl3}h!!MHHA8Xg#OlnJj9&>;b@cj5m@NpiotiNJg(J)`1!0PAjxfiIWdAtGt({2b zy7h1BlAXR7u8wsRa3i9ysJVRDP2f!MN!$cC9x`=YJsT&A&m22y^y1MCEUDDKkI*<( z`w0F_I>4x2?~i=RItjjqyErF7|9LX%nvg#j?n_ilMJ2_luy(fl>zh!?1Hk(jk@KjF zYvY{}lx&K8a9$jaINtn1%7ffGX0wuNvy{(FoWzvdh(Ps^Yr-9;;Ka1KfAeUutKH8q zNX*RLRv4ua|JWe8XoWbrQq%uDt>kJI<@X@bKolyY`ZIIyCe^&70>*q#sV;czO%LR; zq9(+k(t{I&yl8W{Ga6Cf?6&b(G(vDaGCna1ZcjZ%{u)kwrIUn}XgW@+B?N-Q_0wjR zyVs$kChDFeT^)h%)K6cAiv5U05O}0$h8)CA#lO)P_qmZ3z#cGP{eW63tbIoDoZpCS zgz*9fN!>s0$m!Q~=SfV9CS8TV@Qupa2>I!wLh8VKfFhEstk`?%BTb(P72bKnf zpo|6QBJSjL125#Fk}P4XzL3D_k}#5%N4f*OX>ho@Uph;K)DFT`5alBI(u_6@mbogt zEzrp=iO~(|n5Z%GA#VibD(UJnzorxeu#x?h4hz)^%4XL>z)orFfR-5UMQg5ag+-CYi zyDP@;LE22BTawMx|I9MDA?LP%rUV10sDzOI} zqFwErwXbIMCPeoT6bg}IN37xgEk~2InL(peiGl1}MC-(| z6_4iA1=0rY;Ka;8`ly3nZ7MP*+2XAU;1PmDqUJbT|0=S6;<}P+EOLxsC!SbB=!=IK z@5_<##xLwUu&_Vn=)p{e9lIa4Sbupfh=cs)I>VS{oh&kmW%xf+Y)jG2ZOidrBNay+ zjU>+x2SVAh>P4etu)b3lflxQvHUoM{gW5#mpq%=UM8Vks19I5HPOd)3vf2Vp7W>1L z4>5ZpSz}8ywfQMleCF_Hk_< z4NHk4w%6q5QDP_V0ffHfxZ(h`;D8bpBG(VXflig=+SFX;tJ6bbvQfpzsNzPQokg8* zB}VH8v$Kx7ee9J4ieR&^ta*bm>?87%SA@8`m#>R1kRkEm7nYp+!|(8s1CftRJ_LT& zk-3?n%KH)SgW9)W#aqWTFpBJWZbS0B7@aoJ5VzUkH;aG~+-7Wb@OG{X6EAii3Z}G$^1S+>{1QBzF?%%G*z7XX;}w zUmz`ueW@gfs&5j8u}J(K`b0UzFGLFfe!3Y7`RA~8a3h+cW7s#3S!}@{$2J4$_4IZ$ zds&E|H;Rnch2!2g8`7~m%xxZvu5oPyy2dpFEFaAcU8qQra8nDMrs$L!@gltQU>9ucA zBCt7T#-4VQ2;ylMu<(@p}dD)ztA^plU zw?lc(?HVh83hEFKV`iFccc9hlh9z3@k+`=pUrSC~@6Ho1m&T~UQCV=Z8Y~V2(%-aK z^zDXwpPo_Kb`(k(B3P?MwPs<%fytWPE+`(1S0gkl9b{0jXDW>Xk~|kGEVpO3Mk-WYZo}MwPR}G zk*WzT%6(O11ODC;smQ282Cp1$M#GI_ctp5w6)jkY?TqRJYNg!!uCz_fH+#7mXcb3m|%4hXjJ0m)$-f!_rKAG!j3@o}dKKD^BD zHcc{O6J{O?J9a&?@8bAFOq)eZDw`!-0Y?slrG~`F0f6_BtXoKcl6|Z!kQ~ZoFAH#T z8ZZk?4-$cGma_;@vW=4kf&+r<5MSC1dlP`3u_0Gs(15|B71>8YnzAMri zH0Re*AGU=^GoNd@(ys;K0C)!Z_9}=TRbUa5htrzQbHBijNp8IS&(qdpE$ULC?QAy9{vSsh6=D2 z_#Ov{5Xh{-|7ZzG*!#uIjNuwL=923WSJ)~k3ASbc3B$VHnq(%gS1TM&vC2_$G({M! zogA_w$%+WtPSzgu^Scp=VzA&C@Z_AFacgWWB9j|Bik{pS^ZJ9xyhiKsst(^CQ^70+ zt;rf^f8ch7L5cFwiQ0UoIGt%=Yz%QySWKIPc@VZ(<9x=8p@H%62wCj(R_!tY<<@;8 z3*-lKU;_fkT!xE*C%Hzy?Z!>m%|>pTf`g6CyKXlK>bY$)4|K!yleC_QfpK=IH|2_f z7@LMef=a@jd{hhkx}(~4>)+`Y1ye2>FM6>X7D@j{AsKbuyzuVdiLlz3vwGO^KIGtc z4)P=p{?|XH4>(`N33A-(!{)dc@z$OZwMS?%rfLu2PZH<-@7JyK{sHddocH}t;pj9M zLXmb7G;y(czzI@hhf&3p0=(#PsUZ}F?xrPCs}nHnk~FkRz_z;405co;MGPv|f%l($gjxJcDkMg)xVeW6>A_Sy>b?8=;cG%FF3^Xt|Mu|gQoucC3=qkr0+K0%< z_u)ej`xOXvIK3{_GxDnY#k zQz1zcaG^4jpfoKmFapQ(3e{GCrIE_>C=R8x1Hm(n=Q|led3leFwfI~DeiPGX@1`*1 zXlQf&W9B=Vc0NCzc1|C|F}VoIkdvy-=|S#pt}&*_1ybF>1-kaYB;&WevQ7nxm%6j+ zOf29SgkTw=F?0oO1}OCb6_Zm}5!UR{v4y%eDB_C{GF*1AjMtDF%1E1Sc5$lOr0Wgk zf~Vt}(_SeYfrca}=amcn~=Gd_AbwMfS{6K4=viAg>WYNMDQ){$Pp4tJpbF>KYBp{&pm6A7QY+ zjSMzk;nbyLzu*YdOokQCZHjyZ*yc&hwBrP8Gn!Gm(B`QvqD3*uE&D`jsD;FEuidHX z_KJXO(?i6}I}?%Jd{Y`j?*t;dRuP$I0s`E~ix?orlbk?4+_a>7XJIX3VtI@f1I^%) zyjrp{v-t-fIu0=S9An>?=L*FcRH8e3^64j-j8hU_xBd-uP83nv-!D>Dc#+w?usXlq znED5;!9zA?XU9!qW4<%i#*Bm^ef>N9!%)<^*6N(NyQ6p+W@Dsk$A1;1|vt2?!Jus4yX)2O!oXCROcZ6K*9^;j(QlfxJ|R7>vA9_ZRm+I zG$hias%Z)CejV-!N6CEQ2#f(hyd025(x{!C<#`~Lk8Jxq4xb2=dqZOl7z;0(MV+2a^c0tqYuUa1A?*gx!P5 zQsq=doOaEP(8=Z?^zn%bxa6;2D)oR{$hOeiHsGs4kcU8}`ix$54%tu!p>t#`R_LMi zw6%?xBGku+cZRdx9$Tg*f>2HuL}X?K;(*I}U@*U0~ONP$^@7r@fZv?bkFnAVN-!lFr6ceA+GHwKy*rG}AK9;ZZZ2O)gW21xV8?ZZTpq?;Jh^V|zSDF-A;3*I~23_e9R3m4Gq#p|ik= zB>IsepP2L5W?8=fbz37pzBN}3Jy2fDxJ*5AUuEzymTVbn5Wiw+{PWIZPX~AloQT>(F zvud+MZgizU>d+XGKd6*#sDDt+5WL5>1U(>K%YpbF+>U|zqqxqc+Vsn0rRzc&Ucwf2 z(E!RHvL3e2swy?4*PHtStkTLFAK7K%g8LBW(+mm?7;lt6h{J}YG93ZUTs+7zLO_t3 zDQbp>REZJRgm48n3HCbVSs`Nv)MO32ZtB#^y~`-To)+g~cWtgeDCkvh95gG(DTy&{ zPUOAZ0+#&8P7SA!qSh6pW_4dOIur=GXj907xB5%Ej~v5&X}=qTp~*b>ubiS2$AkOt zKa47^;8X!!9|BINqoSC-kQbJiA*^M@pxG=26CmZnQ}wYm8z0Hsa)k>g<8~t|K2MBT z{bLP9Tq(o>BY-D^6~dsq3LBgXoK##1jNqcr!>(%WUSd;IwYwwSYP?cORrbCVhikV) z{oCU_ASlJ#EUpK|azL(#Vznz=B6r5RL^$LG_FdJ3ofkt+66a({;v~8C6e8SlaV$*m zST`~P<3Qolu3l&Ba>pp)30gWto=}K9jz38pBY*Xa)-m!pcM*<}4?$FTN=M^zy@B9- z7u6Ujpq}y!K~X0*a2p9?b2@bXqL5<)B@EY4pR);j+nNFl)Ldw6w5vW>qw~-CsL%~# zIgZqoHtM`l+@bdlRJP-oUozGf9_zI>s5U4Z2f+$#{S>Uj8-==os8I(GcgjHw&^^g> z(C*<*<=K<7voN2-eynNV(?cyB(G#^p!kBF+~(tcv=0NPomGTtOTnnWJ$l18!!f z3JA{;IQ%`@hx0s9`W)X`OgNz9zDh-%4a~ao;DNjDnk$@yn_~`hs8{_tl4YRIA~d91 zqR0*^<_D8H;!AWa2qj1AX=7ZoRTWxb_y(303{Iptn8(_PQz)PDu!-Ll*~D=oM@*Yy zDl!ohPuVf`427_8-)4zZOn38R#Le7U?k+uP7zX}j8A6{Pqd-MuO~x};vex~L;|yl8 z$XZv~W{2iv4D-%d>c%g&K;@xacB%k0rvc-T9AlAla0{3Y=D{}vNcoJH1)|4uWMTra zT!+m9pJc3-u>109%;-+M7^Q`a%|pj(R15Ea_J}$Ha1}k0*wrbj&wd;x(-1VEjKg^i z%@TfBm^A(M17tM_>II5xN2MMvhh2q|$_JYsi;gcB>(_#?h+~;<5u=D% zGc37c3pAYW#HXTCajCzao$2hIt0LBLwpDFW0bM1dP$>P8+#nKUlH;IQ#-EAsz&KVF z)8Y z>}R^1=v91x$#Kv z>R}hMv4@{5TjRyqYPZORqP)hM`it~bv~Gb9km!wUxp3WJaZAQ_NZXR(K_h>eYL!Xx zyX2Rw=JFSo#f~Qqy3s{+`}2g|eqykjSaP?dcag19Gw3-m*A}ic;sWH%Cz&TR)7&HP zA9#IiCqbek8USC{+#E6MrP@=ki}W6kHj)M}bJ#YY*3rxio0#)9bpl=Zo|`U({)qn@ zKiey?7xoz9RX-fH>6cTrJ93+FT->FB$jGphIeVp2dypw#gNQTT6KS zLlB;NIaPamWMY$d$`x*>m>Kg9J-+DCC)^?AjEw8e{z%jd}Mriy#Y0$bX2CHMqu0_(WP9%_hj z5nP=QiCSi_YAG`W?)AbW} zhyigjHxZK*J0&?cxwq59^)G&_TUVQ`RV7Atty|SkC*(-P$V9haP1ubXndl~#$1$?2$zqQGtk=ptun4Msfj&4@ z`(IPT`dSC8`?{m4{;lTpL(QggQF&>KQsn9g*O6^J+NCq(G;$7@Bu=C4nsw?KK(;hg z7W2lT=PL?5|A;@6jwHJN?XnlGYV{@V;+#VLFKRnaIc(mE8&-7zCfrekbEBahjv;<3 z7Z$`+x*N7jCkU~Ea|oO97FceXM4EPY_a`=unTKO>qfFRW3^D<2!j9Z#KE}v(=b6Q(j|`x)@9NE#!%}A+ z#qap>JT~vb%$(X|gXK-HHeC&Oa}ONY?it{FFtQ6q%Py)c=^IU1(%~t|>Z8{$}H4#x~3#^@mM(}$S@WV~?>|_Tgr}pftK=omj6K5)bXx{|YHh_PFDk|_0*g^Gh zgMQ9?CzS642T;31362E{yio1S6ud_O#SGKgK>A?=It^2-wB5a71gZoF8QBE%x)Pz+ zI87j?%~C!KAtssEh^b)`eEU!?bRmGsX}~Nn9n6DD1xWdfmj$9?sx2d?p0Z=y9GxC} zCGSLYF6dwGP%y8jYTpsrVdMEK*|=Zjn7!G0irL51j5Q6CGkY<*V86-F)3=>D)PzR} zskL1HC~R%Gb9H@veI9I1z2$Qi@mRR*y}JOb0a`97Wpwb6y)HVQLF(`ehu`6MSgubd zMzuP8XUyR{ao+MQ-tLy?6A6z!(q=`sf0?iw9kQa^3kkc?AuGCxRd(9!N9b(TN9W+F zN@pdP!&QeKoq^^^bSL0|-Hi@8+!&-v2_x7dlobDWCh}Sw_jto!l##dZHQfM%A1(;&O921@NVDP@eYKD5Out* zL_g<|%7e`|c$RGXzR(O&mfrM!UluN?qJtZL*1F!}#R zcFrJIe$5~rEKgRCVSLaC5}z3AGF7|k&4WgP(TAVn$oCtLoEqDbL*M9D+yKc3=-r!I z5dq;Q2Z%v-9Gfz8HD@{6?A;VGxUI9f{xS2Nyv+pC-8OUG`rDOp+88a#Wat~6-@G(d zZT0dN1h3rsG%ajpAC5F<4NPL8e8ZEftgO}!ZJ4(qc zPbtFmn4?smwjs@_E2zUQJdBED5YcFi2XkJdSMOGfJLD0?u1 zrcif=!W#WL)%)Rq6kpjLAnDX8mY&KvVYTQ>2&F=a7z(wj1XRWth6#JM5Sta0^&0sN zCVxhKOR@SvW_=}tXGmNBvWV}S*9eJEjC;k8rwl(P3E3e`GTYa?#W}4$za{=C&zOQd#wmgO8ZGH*^_q3#&1JXMMSrgw%eFp_x>}>Y|WzRKqp73 zXurHj!lG+3HH&VEsQLTO zoT6}T$6M)?<_K;r)=Yz;q6!`^F(`X4KK}!!Aa-~ss=^7gta+0TonBq4qOC zL?N$BQF&e9e9;-ABnml!1(FUMis*_2(pAO9N!pAvNYGdEYz;l@Uv5>+YuI#BQuBb6 z;^3DAe6u6qe{WX=1pFTFBI3xweo?0Z5;r(WPT~Tgzhe`W?DnTm>2iICOm8VeJ!vG_7HvEsMO zCD^V>55RYow81xd&{d&u7z%?YUY6RZu#O4%U21RY^$%`@f`iHI2KmU5g?x%t`bx@u z@dhKkNAM*##+%*7_TJUv?8IJp;U!Wz@RiP-`j6Tju|2+I5ei;TVj$W#U3s9bL@}X$V0xD<(=jSWk zMtz2YD^W#bT~($cYZ~3Xt#i}L2x>7KjWUez1v+`mBi`kwk1o!6D{bX-2FF4L8YC`} zFv^BBVJGllqr#piTN)fOEsoaVAsT)ORcolA1@7e}o?;z2#G0(#fjWg9E(}6dGCJza zSCz<3nUTBL*k&S)P?mjw56&U9r_@CN>2r{ZDdrS9Aqsfl$73kNQ9RNtF2j7tvqQlS ziZ6Zi#FGolC!SO?G&!MSh3CtG7{iG8-)>i^SGYDaCHq-0>?h$uN^W$k<3@)q(Lrpu zWx`?$XUfE;;HYM7vl}Wd07GzIRf5$$aHw(5FqoehKV*2ONQ@Csp5BJN@HJ9pQnk4L z8d69E(ffCpawl751+g8nTWT^N7u}NZ@%}r{oZ1-jg>WJ_>r&w0l66Z9m{F#P@v4i7 z5flk=Q2Q_9b)75uYld^_UzTY4=JizVgNb*i5}w$E)qxF*jUJSUK0JTPvEJ%9)(0$l z!LjBC6rIU1y1A$A2^M6&Z1~w^su0uuMmz1vR3W-0qKa=m1G|Y$@ONjte9HK>woy9N zl|@q-e~eKRM;dJJd^$%D-8p5sM{zDXfoZ!8SncD4@K?(T7%Cck=oVz~Ine#nDQU_I z5jUW{`ON@V#ne$nu}i)os4*vwAmO=P?SfP( zdP|!qiQGzli}eiH+7aZ%9FaWzVT%F;9Ffg=2aYd4&KHBjb%`k2IHJ6gXK3hA|8nbP zUQg97xh0*2V!NS23$vuX8Ap3xu?qm&<6Cfi8RhU&;KjjvalQ{4Hdshb!vcl>U{N@k zhDEnTG`zYx zz+OOZtfEa&z*PMAg!VV81+cgyLZpLcxvTUP4Yk|fZvE{e3|5Q`HX64|th~Wcyu^eg z`nw#_n~Aa=?s8yDz{fu)0<%r*X`s#gbfB0g7-@e>NUSi^+K6AWBv4(!%j)K%e#gKy zS&|iqyH$fSDXfm7PDD3H>f^sg0q`PNg`)9P%$V!ee}f9XD`J^ZI<~0fex&w_phVq7 z7w&MCV$nnd)KF-m3;jzHnt0n0Reyqn;FI9*sL|?`RFy5rDqN@45Oa50NbYTm3y3XO*M6G(OEhsacEMV5LCA(iyLtq<$(*%2S^BZb=(EegXenxJT#AZ_|1ZJa5bqBZ&>ZjicYjiOEh6pi8b zTck))`)Kd8U+3Hj?2B{Hp~%I>wZ8SO@4ddyhP=HHsk4B7fNMf}inB2M@i-5m|M~NM zfjE?|FgS|<1BBs%rx1!3LZxI_55M6vzYH_{JcA?PC{`2X!*k6GL-8WBUdYaa6Wx$O zxS`J>t+0iP)9r&b{fNx7YOuP>2x`|s*x+yhx%=aT2+o}Ep%mt#>J%-3Sp_Z}P+^qe5=Jww`*xVjP1U@!_*v(U;ymqg|Ff02oEF(6shwAY@vw9M; zp4V}(*tl>0&Z&{z6ytyI!LS0qE#r;N_4ezjU4O6r08M?M_YWrU>w3*Gp)z zF}$wjsZrb%4ZikZ5G9eZ@^<26Y>sz%`_#N|3jNxHOR}-ayn)W|GuKB48T+uQVmD9p zeNeKmI)4(AXpv%hIRnhawz&vT0tO0M5MlqyA=M+yI={YJzf3Q`}A(INI zG3bm5a#Pv~>jSW3n%e9Ga0+|?k<-5F9}?5xtQ<;5``Os{V@q>%8z!z_!v7oV0M?}! zU#|ls4mv>iRbK~q?=)m$gTAW8sqvrK0O8j{ec;#@_XDTkAKETXKRjU3>E|%6U%WAR z0+SsZn(S`3-f{ESN%+1Vkz=nN5c%-h#gFat7WXE`C$bY6 zpMKSUC1!j|L-`E2~+-eFxOpi9RVlQT4kh#fZ|Xcep#dxM2GUxJq$nZHnX$h_p6;P$}{FkAx`TYLy$#%RvN^asfD*Dp~580)9c4j=Lh|D0%(-fyM=IqtTu zhp${bNO!lMO-!duKLC!!=kpNV-Df`2w}|htdB4@q-UmMMJ$fLq@w+E_Kd_yv#4h@n zq+S-gx^uAUgX9B=`-4bbFyUKp@Z}lEU;*PoW@DgDKJ^^<#rK9m8QsuZRpp{$?p zw6RbmjGvBGIX5Ab0X(u$%3EaHfB*fen1%Hpp`c}8H_CY#*2E2dgEW0M3XsUGrLjqQ}aB*3d3=P!aA@^KGbe*y&Gd=yhkUu z9(j!Ii4Q>!V$*n-{_ZoQ$2TEPu@T>_{hdd2NtruE62r~&11BFIw$kb6FtR52M8zkhw$>%k*9Pjlm~9l8Oo+O|J( zrCbr4(lw1vP32nt7~?YZog|k7H178Pi4nhEfRBL>*+ljN{G*HS0m%_16nin4E!64D zfAeKn@$Vve4*xAZuxT75z(FX9Az98;!gPh_A3%B?$X10!v$JsJ@BDrQA74lRIlz?b zj6N6dhE|D}7oRZ~ruK63<;hP1));>l;n@4d)W3FQ4Z5tlT>P#8T0RUv(p`?|7n1mo zCH?dGA(-pWkX#*A9?9qNGcZW!2~#c)AfpDH^@Eycn;F=ggOkk=`RmK-D5_{S)}Z=0 z9H#NJdp}7Fji={+oDR4{kP_o3eTcOCX6KBCsgS-#P8}{0JU}Gu3*=TExD(y%p)gfr`Ky-uC&T!-j5<4IZ z_uiBe)dRYJM+fNtW&r*F0sgs;n;@8@_|?JRjmW@n_^-rV2*34duyrACp`SA|Ovni- zsKK5-J0v`c!h(JDg9*a%@rZ1r>1+BJj4jFx0!YE~0a?Q!<;!_vpWkzD=tpNl&%(NO zz}z6c9V)jy(BMpnV=2pJXm)`#OTZOE!&U@Jh&+Z|7T~LdDA$p-@T(hz)-Z_81IDMh zYp~G3lI_pF*CEbyso5yv7A6Vy8hwnm+`fv&-o*itwMXuVC{=g3gg$7{n1XB?=E;vA zihJ%~J1+}WAq^*1f}A^nhY&1)P#G!kQG}2PKLf>&AQ2|mxcp#W#H$HDiGwEx$tGZf z$`l%?Lm%79g$lYx#xs=N!&WUF43Y589EGb{YiN!Z^}r!#Z*!4j-1Y5#7f8}SM0+Ea zRrQps zNa0fWa>?M$Z`0T+yp6A&T80w}SqO!rLa)MQ0(fhR5}WJ;batP)G~NVlJ0Rv8>Hfrg z4}!{7zNHvyBVM~#&@NRKxh_TXPwz?lS3|ZJ=eUp?-*;^UatJ!63rV!$9xMh| z{v93Qd;h)wm|y#yJQGi#HDhKX+CLh8S&{zxhwc;E!rFes~ELkJa}d zJh?*QzPjRRv{`&ZPxjIWuEzC?cPvPLZ|N_MJiLQUJ%9Z>V4u8SoF0%r9InqKp^)|` zgDKGrFFvs$oLIWoljIm6zq((Rn^2M1Yd4`H-H$+%N|lAi`4c$mUMTn^qEIM2{p$IX z6!@1_RQwxhO~T&T)z}PxW}|Q<8)B1SQ$k)Zh>ZfR$PW^LXD9_Y6hHv=3Q}*L4>tPD z&jRQhH-p3?d&fJ{Hz9Q`d}FVLB8?1;aY#2k_{@Pc%peA;fXK|g-Ql4>bxlK-oey0cHpC<5RW+nM3sQ3i22csxAt8`y)8t8_oy% z`$rJ%WFhx5q@igSdTo?c%4w5V-U{2+emN0Ac(9s+0!iyFDHAZ|+H7XukU( zG|I&6jX__>rogDLklZ55yC<$;U!fq6j?`ZYTs~OlZeol4-oO@#J`pQ{0tSv(A4I&` z_^W6U-ZOp$;lSW(Yzb|J)<21Cg@4(99V@F3Ir-inh|EKot0r58$O`(M%A{dzCx z@q5Ov?@=+twr5ci3B3 zX}~eSAPfpL;EV5>gKzJJIe2cOGx#qr-c3W1hzeZCytE)WgU8JHd+^r9_n_wm6Jq&J zH~Mp+Tu0vBFYJ-VM@AIqZ7xHcIQ1xkpf9Tb&+xhHb_Vjm#{IJI?$66mJ~sG%+4qe9 zaX-_80p}RQF3uo~aP~q+69O{uC!nI&ffN|OiQay{__IIyPFOhWTl@Yl5A5PIsGs8= zE*|-Puf3%PUSp&e`Xl=d)Wv&7xCV!j#dh?|JhJ?UrfG1%0w6*6+>=Wb(+ZElITa*! z05LGw#D10nu!cjTFjU?WOw>rK8){&+hhR@ohaqzqWQ`qyI0s8IKmnRVOL5?BRb5!V z5DR1hS-4G;|}OUS7cOAvA#B$TRiw;+r3x z6VG{`OR_k_oWnKA@-$5o5M4q%$2o%GafUqq0Dn&K1VQsGjjmao#*-w=ou9)sgR>-^ zWY7GUp%o5~&^1MK1WmC1%Ou6}B*FMEFeFD(L^An}vzMEXUtTl3=5k7F8$I{G4d?L8yJkORRx=2^x+y^Lx1AfW%Y?|y@nKS1=LT85wT`uwr` zIEZ|IY<@`Kk0UY}+=M`P$m9c#Qu}-if%Ilr?Y{CVDLj8%d4fM9o<4qlCIB)5H3mWp zM0Q_d03;-2CDc?%wS%H-_MZp-x2NbnB}E50f8f+G4;tVV&jFa7{ZfR)&G^=P2P$>( zX*ZP@WtW$p46K$BgZG>oY z7kBL71XPd7$|aQc8GQ_&@5$(?S0&t#>HBKclaGjJ=j5|<>Km`}`#ZfG0nBIn{~=(* zWl=OfVI(7;Wcz;hFJO^w&?JzoPy=gkQgCd=377FwPg7=HG;V z1BL0BUK%BM@QQS_XLuoO-Uh?#Dqwx}l?KoX{OBE!8jiW&{#Y9-aevSc{F{&67x;(7 z<7dDiUl1RXkA1T;T$3MCkDs3-@hUKV50D3IAE%0p9pK7312X}fnF_QCWbXE{KKeiq zk@FaMEou*8a1ibT+%b0MF5-^CNX!^lMhUz@^#R|ih7K)5uo4P6_0O-N5kEVJ(W1X# zdwqSlK-!M`;+y6N#K$mb;Hx0Z%z*jNYzP|G*5^;6Kt65wbYJ=hxb!~O)mM6Ei!o&K z^HaLP$KcaT2vb7m^nyvn&VzAx1$B&>+`SK=dH-mSkRg>m=KtU2FKEa}_P>rP$M0V1 z;25vtG$bYmeCvOSHhwq&Uk><=XYtIU=+{k#2&fhtBKmba#7{jAHeEQ!dkyisd<;B% z;bMQ|CIf|i5F04^bv)4Tf5?IU_-l6D;oBFlZF*vIr`UP8mLZ^_&EuQw>)23k*8aqJ zjuH3Mkw^$v$3RXzB#^&yLwa-=!^MqXdHp2K5Su=29zNjn^VCC5^2-M@d<`i*jNsyi zFT8ewf8tu|98Uf_}(fAMcSB(1$9)R9x*a_pFaj<2Al?Q(wADJ`?`IG>bgNJ_j-d2OffO? zlK2ZLn?Z6#-$myCLx2a0P4n{&4;Nr=0uvG(Gg)omIF(;Y669!~LIw6>l;i-UR50kn zmr$Atlz0NAyoGMh{E?%a2w+P_aVFsyQ5Fa|vjs6~`xt+)??Xko<-+u>{O`XH^FrAY z_ESCcF0E~h?NP7o;8oN>0`7khQIN_6&Nd8=MVWU3P=wqr{CP~he*IDx#~bJhDg5`a zi1>s<@TKrCyo#r>S)O`&ViKq1!|*FH`7r$e8z45g2kGwCvk3`5%sGwp(|c~l_5^&SwOyc0pe7xfOS5YXEg1VieIcmnL^@MrXXbO(m>qhG#-S>amj;v?+3EtiWy z^d6nu1GX1WZp>#7K)m@oCr0*q9VNDj@2R7>Cv+5lN1}~(zJCY+xMZr2G?p`T(m)3h z3PnqdHSqO;3DE>s{nM|4hxh#4{Yd`?c=n-(C+PB31?Q6+K(t!^mPrGy-$^_A>1dOL z6z^Cxxi&1|I~tLI^5MRphu4mfe*ioLpP&j9n`S4P<|Qy)=N|}R^Hx-#IjBHj6bDsf zZ_G!9Y(k}EzELND&4B92kqs`Hq30XOz?WcZfr7K&G)R@XtUMf!-M*qXK_80xWd!_H=u8ld2}=DSmGLl&NI%Iv5ZGfp9-l?&k5H&-X#B?qG&YLJUkb87;V&uoF?xSe0hC*!Y&M`y!_1i!@3_rOFWyFV| z3^5ozOn)c96_ZpSMRX{F)!|MAtBZKE_l&=D8>n5o%e1#c`wkO%OCLM|^w$fVF}%8` zz$u>)IQOxiNJxCuC=QjTQD|Zi9ts75l{HJBFqA)dztO_@;^F@Wcy%Z7@E=78c?a?E zi+?5J0RM2`&%=v{-`2+S7zF-#1c77Ld9Cq01l!w?954P=bm|)L8{{lMPcX9d&XJgP zrSKCLRstineGb900~A_`UI+qNgJaVO=aD&ixd3tP+}{kSjv^{KY(IS#h=h8SrRS3! zM6_#+^PdFc!F$G!p?_k@Ope#?ve<);%#;6Zg!K2MHNuT)&2!LOljtw*Iey9w_W(Ub zkn!mW31GPsJxN6HyaPQ+{a+DipY8kkLq<T-&eLYb&3ed zUSUFBs)2`ckVBZ(Tti1w0t$c}P3QsWVT%R`}<>Euat+e!ooy1jJR3h`}ow>AT^gg~IdU zMns7&4)>rl>r!XOyW%pX?g6E)zxQtF+Yd+LE2uwuw7^Gb5(DFPtxnACNRcuIC@3#5 zVZRc%|8uvQNT@koHJ8c*WAy>}58d+#n7v-Gk4^iY%(i%6X8SzE*yxzoLv|U#-Dkgl z6;R|(?DwxkxOE5iJNPi#FaOTIpND6^-@$!yap18D{%6qykLk#@+%<&Co8zvB9dYr! zV1a~#_27U0z-M9cdhx+C-?AG$JDhf%phEG7W9BzG`2Gb6VoeCknz zt;X*lIKF56WBBJfgoV&!KT)PNj8N=<^r2Pt9pqOKJc_^^8&vG(iJp%b&h!oD_^6lfP{K!L2<%h4r-Po+IZgXOS zr=o^J;2p>wv=Z*WIU=|`L}w@Fav-LckI5o(gmn2Bh9Ghj91ObCIdT1jcp(Hv!DGAO z`A77THvjDWBMRLhaQ|;OrTh)J<+ow>4Zm@I(D{W(`gn_9j26n@ivl3lr8_z4B)G@tr>J@7+ER!BI(ZRsNqnJfJWT;y-|xwY%-Q6Myg zGQ;Ej{ZOztw;@Ird6l*B1r!E2n~Je^LJpw-AQix+tE(FgWU8h|5HSb|K`4*hnJf!`Di2Q z=pY1rg3?Y50>2eO;FyhFYxN1ic92evx9meoI~Vf~cu2rGfxINT3AH|gFg9Q{a5Bf2 zHjwOsEFVF(nn1_^Mr5H424;{Z2q>W}0xk^{(gto>pHun5iw#GRKyV4(3pdwW{%W)@ zj88rB%}0L_VR#^@9IwtPn)qv-;2apfI9ChQ8tk`qXAH)cu6tP~_?y{U4aleFYEF*FexT z1jd{=p$W$&r{_>D9EmhRepb+5f=UC(Z;fg$q0EemKC^?e-mfNZeSY4uAqV{|8Y~nm zm_TAO--?O|x)Lds&>8xWe*kl*Sqmtw6uq_gRqykWfj2vR%TIC=O99Fr2Qhu#>k(+t@1JzjMHs~lTm_5f8`*@1VZWLFPr&n7c8#M;XcUiu;GUw@$0yXyeLmGM z?SpELXxM>v5%{?aCh?Glog`srd;7YN5>L*bm{7;<>3MjB>tHDVghvsru`lraJYeLV z1fD+|q4FIBp5NX?JN!@Y`+0DIr&|Ix{n1DGbI784)gNRSzxpY>^+yc?(0!8Lff%y< zr3hJ$xy-e)VTfUGLpHqlage}t6TEIKTPE2q%PLp6%%-s>65<+5AMu5Uqw!G`|H)aVMhr_o6kt1JV4Bza1^- z-`)4~rido-96WGUW61K4BV@S+(F`%{tq@J9&Vrm*8=#wT zPy@8ys5$@~5x!Jb;0f|WB8?Qhmf$;uC@N4bkJ_9EW%||&h>rqSCTa`j{52FD&{Zh6 z2U$fUBmUd}a70Lq&p!3Z`Xltutqy#A;s1!}z&*+OUwUI?{b)hJxB$6NL4f``EXPME zw&WXUdzv4#^UD|n@^a{GiI(WwdW_L(`fTA(z*63cE&OPN19xBxU;M&ZXnFpjeLoM+ z7C!z=AWP#(BFQC52BboqV|j+9&?U#yEXm+WxJ)u|kE79D3TIiCW?0mgi7k;5i)N;DeP;aun;&jD&jtD<8rDe;P&w zo$zQxEE~*{hr2w_qZe6*!=Y{j0u&23Nhmr2mn22QCwVTICBZ?U5ajwp-N48>+8=BZ z5&*KOssunA0*YuhiIxvlrbx07E(Fk~V7@%D|0E0L$|-+z$(HY`CwH4C^* z@(e6I5BnVf7V-+>I1P0$&>FKeKpA}}$v~Gl6t930(oiOYr_n57`0#xWeUe6yA}HPm zEI<>$$)WiWIA9k;`7mYx!MG%9odm3)lJp+1unK?${sN+f0u1v3%Ta*3{$K%#aRNpR zZ{j!!IT3wO(MgI%BMCkUa|FCY%SuorPLMom%>%qycoTh+;b;y96U-9UG0DNC;Q>bw zupek2QD~B)2nt=o+92%pHvkQJ7jX);#bH_qrTtF={^QWQKTFgfybMiv*e>ugngPMn zXvTZMl1U1X)<;O#iVO|Igf>tGgu^+1?gStKY##I`AQIpdff|rhlA)6%<$n@E6(E3` zFwhmr`$$dk97!f2H6&mXj2R}npCzm%jX(|$VDnKFnM9DlDUw3F6kP%$k$`e=3Drm# z_~Rp0680L$1%L$*vTz@D4meE^u)*MxVi_t4z=ul`Cd`tsFF!$VZH&AU5qZ6ZAQjT& zw;@P%zX~P~0Tmt&GNA;b5>y!-PmqTeBq2X^9L}6U#zqu_hWxQ8l-<@K4h=*ps9A$f z$$2JV}fp*#uL@u41+tDyQ(&yXj?hT^5@a2XY7r~CujD(GS5Z;MgAt&0P5x#{5zXX%F@x@!i zBoxw)BmSPpG4u798XAIb``WR{XjQ19o8KG+RP*EWuiNO!i*LH_$LBwJ_~jk_+CjUo16RN9 zzpx|ks3Y&FBkwjH?T$Ly9d)#Wj*iFkbx1lK&Fa}%xEubkgCW9HU!nYquyd|cC?Wae z!m*Sk)MtCg^vf>3tf12l;5jpX8ST3Fi>aT9_IeBrYhgK^i|-36KBB;ZJueTJ;>43^ zbjH7rdVkOO)!S@s|Ab5Z=TD5s_zTcaG^F}jh?_1T(T86jS&I5i;^S|c2>Unl7vI!B z#6SL5{CX@;+!y)>=U-od^fH4}cHeYAe)_~azU6)V^m&9{Z=&l6DE^ZDCoq$HF4^Ee zIsu~C0fa0Fc}9r)Yg}K0jSk=sor1_V^i%8wk{jv;kOy)Xpz=HWQg_eK z{S?|b_WvW!7uxm*q@JpVFu?P zAg?$&Hj2($9v%hM^ZZDd?0o$A_Vao6CKLOa7NOJNq?1TUM(msd<380Lz zumIt%3V%je<0p{y8@y-y_m{f4mYe(G0oHFuxDt-RXXVVDa3D6*J9cma7Ds}@#dq(~ zEQCk&I|7Kmjeh$!kO<|PtAO#jI7-Lnczpl0L;p_L4B@c->*FE+vxgjV@{XG>HoH4_ zaRLyhPGN@l7CWi?6|{S9u;XK+yzwiiMs>*j{RnnhKtjS5irtCU=^}O$`uo23VdLM} z^p2u&uEMayH-8TXQG4rhJ3Lb%S1Leuoi;Iz6S3uoCR3~e<3L{lG&)o(B_h{?${Q%SCJo| zZ*|3&W3Ld0pFDm4{e8`wFhMnlujojNpC>vJmCw-k5Av&D6cS0D5V4G|ZQsrb*`woX zx(oJ36u5m5ru{*jMKZ20+M-S&!~1?1(U*~}70Jx#yO4TJGxsH;1B>a|E7OODz9rXx zA*hF=o62nb99~9~j9AcfpXQ)g>Zdmbe2i4z;w2!4i%XR25-SQRc2wr@%HyBzrH-zZ zeM46COJDkI==%%@;)}mucolnMGd%V5#8gfRJ>geEq33wI-ycVgJ%WY|;N-L8-T3Dp z5(Gbd)y9Yc;_5c1z;TeaP)sx6=aa}uf4C9N=;Ck>I{TH|OwHG9u3B11+TMw0n?Jdk zV{^P&`&08hVHZCve`o^+B>BmkQI6P{Zu-WFQ5_@PkyPQH7B=8^v?#vN_g~&-Enc_N ze&7@VJbdut^z#!FyMDLD!2KwquCdR=Zl3D+%Zyi5RvY3UcUP;gD~}_^THhB*8CL5NJ3h`sj?;5 z&XlocpPdNkItxxX;9*IceaKZ%0`LjSQ~IG99#S}Lj;CiHcpqqtdf&z1?oD3uAkFv= zUUJ`mpStNgJ9wuPq$LW}_a{%>XXoCtbM(M>f&>o{x9NnV^zT1C%jjbenZS>YE;I=3 z`|$i2q4w?k1IJJHtwWaeN1#NXMd#_iGW|& z_w(T4Zx{dI0~9y|K{OCU#3gYERe{K?GYW#jPy`Z%0?^Icn0E(P+S&7W!M~`?25QC5~6lz3}&ms2857hCS z9o~vRI;SWIluAO>5XVBe%tsXe975%AnnWK$(Krwb1VKXRqY$_U&3OJ3462DO+OufU zjwSwUk9349{pNyd?n0g~{@}}CI$F*a>zO_Pr53rQ&Q6i!J(WH*e!le3YbXeMIa>!c zQ*BjWdSOX18^V@t?M(Cbg&pAH2_4cy`0?~CXz^mcM%5vLAJ0|WdJ!12p7?D7N_c4b zG~@{|Qn;&XPd*^luveIT|C-XYbiuv8I~!;aA+R1P|=V!Z~OI zf7rorOcq;rC5!d@ki}nHMPyNqc9`*{FCF}>K(irW!*~+iGBCJ=%C|-$xb?&!;Ns#P zIE$_+^Opv-{{@NB*DnnQ{aT^?bUI{V}^whyTlEDiFOi6Shck9_szTO;=eSAn}y?!lK>2>SQ zAjji_+)OXz`!m(7EC(dLD;uqi)Nsa1zK*MTi7k8lI^MQC=e@p{==DY=9`&8>rV5>| z1Xuh7{;KwBxkZ&7F5yXQ(VAsy?K*ABB(HTREoMk15<7Y~Z*;AGg&XI*oLy5}i%i zW{b$yt%@i1ly+^UZmb2nEOln7uH8#zGPP7DD~*dQB{%hkvf0fjL~W_23r4}o6cTv0 z-fCx4`7x2o2=!DZCr|98)KogNC2i1HX0>R^lCwsw>a|k7An55ru9@pd#d1l~d;V|1 z$kxJVZ|ItCYblPKnkFW8IwYS}=8KhFNQxSU@fB=o@tfpOPkLN6rB~`xZ%`SN+ikU6 zTI4q5V7ST2-Rj)Q2~JO9Re7jmqk%oDPqBrmlp3}--c)J{rkl?#bFJ2_??_x>Q5dIl zB^%3j$9%Pk)0JYm%yr6Th#p^VY^$U%9URB0o;q(78)K`)N!!sjQ_iM(o!%P0sTGKn zL#s{};-7o%_KFxxuxj4ul-sLpTiJ9AGjZZ1A@*OYm8Knw9*JruT{1V7hQ#2OTw84> z&22N&%Zz&&OwKY3H^JrX?P}7p+H*0hPuj+I%eLDDlhVuuTbWZzN=WyrU7Hjq9A;D! ziNsc;6QjXEsHF$+JZ;arWjmJ_Q)5w>jPZe;A8otyow62Y+iij*cRNm8wCPfsDhPsv zFiHQQsTe2;Fj3(++4Ub8)@ zR)uk`(%YII#H~vdl^4XyJfVr@?ND42^2Cwy;#?eV%#LWybGnk&?Y6$L+p8_Dl0$Qe zC-Tk47D3o4MqoHeIzceLJyo1ffjk?NYy29BLBN zPg==*C7o6CI>w8RFgN68tzAsHW4t1^CZ)!<$d=R7WxB@Z1&*rh8Wj!a#hN7Vl7qEJ zXBtYgG4N(frOS-A=}d1nSMxPhP^$$_$cYK8-s2Jq*6gme8cACYBV{dnndxNc#jwkF z%JjG=$fgC9BHgLw3bjeC#cc93Ej>#n*C}V4Y|`7Rl}wC83A0FjCO4&2G1mp+q);_^ zG@R3xN#m8FM3gOFz+wGF9@}>H9Rt8=)IB|uaqOgM(q?YD8dFpvH*-dnk!2EHy_TPr zyR$Ws8YtbalFm+CaiZ1P1XZQmAcC@~9Z6|zF5BH=wqQ8bxsGMBm^Rp0d9x|YW7okt zYqC6BIjVpcoqm}qG-SyvdOgXOdSu0@jf?44R_#{20^xW#Yff}2H5tSIT$N0vTeTfN zcCq!qu29{bU6}JyR>&JuY%^Q1R#9hNl@JQ4Cf_D{+y-cQx#_Hmok_i#FKb-V$m7G6 z+vkbSm?4WahR?HNYhCT6nO%NS=`~n(&|*@Pz3nO!z%3ql@HT`Q?%cSCl0M{ug-cH|}( zw7O8X&Pq*g0ByuIDN350uSw%&Av2Pxo?Pxx| zDl}p5I~-TQ?QNA{_(sa5scA*$?9@b}R-%gybECR8sg~WW)Jjl^-Yl`TM_t;gmQ_}E z_(Z3ivhewG?9c;|3#b&#S1WRy+yt8}BWYQBSHM@&#Wh0Ze z(h`yCEwK*g3ivoxFg8^lOV^#X$K{xQxwBNXL_Y0e+88IT!gN(hr^jormzQZyE^kz< zXkf#NUhighQni{Ll{4i;V&#pNsqzeVf;pKrjW*Fq$Q8#Jja8LuRZX!XXKBpF#8j)2 z-8lU&*Y4S6T+7#%%N|>u%((2%>UO)jolDme*_loZQU*cpn%yof8})@JV@VfyO(By^ zS`)*zB}30-d-)ceH);uOA)NwdZ=`g5TdA@AWp)C%o>@wze3IOGTz$2!Hu|f!j?ast zJF?kwPoqZ6c$?U`IM=4#j1()haCC>dcwZEH8D$;dp@+XmLG~G8L!R z<%bl#P#8}u?%Fvk zCGplw#hN?DX_>9zsF9*+LCmqqJfZWey49TzMmxEh@|KF-?dv>6bNzMRt`1Ft&(4?4 zlBQ*`1@N7TBuyIClsibw?NoN_lG)udneQ7EQy4m}!90~|WXj?+M=P4O5{x3eRkJmmPq9Ghd|8Pn(nW(w8y@fkrIb{3 z*BzBc7Dm_=W7zc;M880%gv=yU9FY7jOKMDiF0vcK?R6MQ%yPVrdo--aSS#k-w%chh z@Uqx5X}e5p@@!{FS=&yTN$k9uH0LYXInyes5u3#rO< zP%j(OX5O)Y)whOT5pUGhX{CS*o6@w@7SkTdk1)*2R7}&UG<$f_-2zPO8k6m@p51LO z#bIXXE~Iv@JlYLSt(;7bX3d4b^!Nj z_RPATq8jT)uZwAYXD}U?+(Et9T;cp$chsz<+F~xPEQV^kP+M^gmLz(b$C~|xoD)Zz ze&5|NDpz6GiM)b|n?Yt!#yCb~D{_PBsi|hpN%Hk%zYfH+nxiXeT*)(x?G)H83n@b- zO=CKBax;+HmdVr&9-HM7)ui0ux@Nl5^#-7Fr$OLNq^Cw@G1YW=q~h}_(Gh#e^oXNd zi_NfzSuPqs5W-q;MYCJob(X*>cDl1|FW5nT!qLmlT!-d_)a#PQ)>ZRf8)Wh|*00XnwIwi) z-E`bZsYxUxIc(OoN@U8(Y?N`KJ*qmxVKs|+nWj=)Fm^RHavI)bMG@i>69!90rqyjq zN+gn5ej+&)sxPjvY)xA&-PSZe>x{|#cs)yx^W`Gp4tcp#PYb5bIy{#cjx&Otn<(XS zZ@B6ctx|7pEp63sCh4@!5FJVDs9d3E%Z0`Y8*!MNHnm~W$eC1u;p94@br*QElubAL zo~3SzZoi}0JFZ_!6|q#?!X|L24+N$5Zo17=PO?k0xteHN6Jlpg)GXb=xxTZrwJZxV z^Hl0I8^aza71~R+>e=uo`uGILD2o6+Q*)UdPmMyRb;9hxXOl;|w^CCd)yTDmDn zT+ONt0EnOzh#3K}5=hRrQ7^ezEs?9Rqm08EjRlJtqBpQ)yv++=L6h9=*UZ7&t=liCwYuJ% zn}9Wiv0QRBnt`m%v~UM&YHO`J)e4kXN-gl6R&7`riX0PW)@Z5C;-XS_HLN;Tm(yO^ z)SN^WL}Xl%NNGgWM1h?&*1h$d&WkgJpttLWG#7;-vuff5EBBJpbR|!{>bBtYM%iRt zUlV4|%x*`U-n5Rd3&No9GNpcwZq?jcX;6+?H*q81V7xw(6e)Z?~&K-l29Q$+6eT-J)vJ?M`8;17}`k8`_+Z zXW0%V)Wua}G;UbEfjHX|ZK=>*fsD#>l_^te8Fi(-!}6lD?NkYG$&72tu*vXcyqu=W z&X@&}u4Z)VbwC%;)9r~_+vG>eq-|>bMkU7@IMGHjL`NvLGxR7mz^zohKu^*Zv#<*7 zp{`ZiMX5g57^yT%q;?WF1b#0#l4jQl^b>X6RnY?q-r{ys0;= zW|&&a?TOu7?XdbpDdt6WstS{~z2=6!{H{H$@^)Jg9TH1O87yI~^EG9*vk9x-2VCW| zUO}XDL?TsLxwE9ztF*{UT2U$up`flNJ5H z)j^s|HJxfRgGse)sf9PN#2C2rj2-4-Piz{yD#D++Er>?F%Q#JHuDL4}1U|8mDHOGh zTPZVM6Sc|7MNi|JBP`ikQ*~uf)3K$~@2^KA8dD2`EiY=T5>=U%k&UFcB?qpST)6{A zrba!^=!|j`tg;x^XLNpE9;WG(Oj9M1p{8nC#~& z?cAtBj2aqi)tF3fDmkUyY{jRB(%9ZMQ@!ktnHRd7tz}p3gg5mnQ>T$_joSlJulHKJ z#DYppjUjJ%l^u?iQ@UUeMU2xXtD!q@mxhX+9o7jR&&`=}zP>g$3C)sLD^{#+`a5=; zskqJbu4p9Mv{o?kCB5A2wW6G;Emf1stIm|BrL8iwJje~PtJ;js zH8CU`7V24+$v0@OQp9YQZPqr0owpw8ZjxP>mUzu*P7*rbOILP-I=e0|GDhD)j%BXX zubSPe+ATC_KGp2lTXCk5x=IX)n(MD`E34PWE=biiK`tyJee3xVD$_EXiYV(4%lUi z?6wCDy=Q6-io(0JIK?cAnU}kou~;`Ml7+XSK5ktgt>#o34(G$>MlH{h1Z>XYcq%V+ zF!|&hp|AuE6n8r{t28K6rIFj)wei)mFhKZ*l`uFnCEuyEbpq$|$yAA%ttxb?oFFQmRN&j|d9k{pIA^_TNu7MA(9RY$#qP|z zy%Js|I#ajY$flDibCygj@K&n_@Rc*581#mN?PxSkO!5haT?i{7Qygohl06c{EaU;1 ztYxyRc|8NgFnbjwZ9DFAf|>#& zf<2YNPBTlVavg6lhm01fexfF(C{jEY7$ z)4@8GH71~K^b-YV-I+MZE~NGw{fr>YM}&~DhV5K;N-k>^5O?OId>R}Gsj*iBWvYcC zpGG6Ol?!QJ71`7%H*QSUg-n;r&Fi+!&%kCru2-wzP$6I!5g3-QZmFaT-c@p^ZBw)I z%ww|ksRCkLbw~{<@PO$8j+vQ$e>j|M6T4A@t}-?@s$%tIr$ltn|C}}gdmiJCCdD+^ z!PIJoWpkt>uVo=KUe1csn$cE<+1U`>Nv++`ql)&d(55;_7&9BAmEE0b_-Uv>w{*Cs(^f4F0`;7-|5SZ zNj<%mvc>$WQF6Csqn;vmiqpeDTtc|znFzP)vQo5)4A^<7vFn2E*U7bY3M3;kpQ&!a zi{BgS*>S?%NLGKGsil{ToNQ0}jjhqH*IT2!gRQ}nR_Ls&JyJ9ZD?_T8n~{rcHd`3P zsy!4f9(+S9KD$umPP^?emIH1%Q51Tss#2J5=c|foxImDd+={o7PRo&tw4O<|WxY3Z z?J4WfpoTk^(`R!u4UUzZ6b}At1TYPso&2c-rq!P`^2(0)m zLfaCav@O^0Sy3O3jAEk&vwivaY8zaMwr;g|IY^ph3%!_yd z{5D|sm!^YxO|acTRcx2)TdmlT=p{MtXIB}kRBB_jdCJ=rI^f3K_RB8#sVuu=wM#SC zb?e>2jsr6ei}90;Id~=hV5e(}MxzU6XCbdP{RZELfeIdAX9yUNCm#%BGTD`Ge zcT%O?M$x>C2ZpA#nj6%;YIf5Y^Vzylt8UCpUCvw0mYvX*nk`hD*u1sFEA^S%=BjNy z!*cG-lnHtzYWMjY1Kxy0nD+3!Id5<)v$}c8?$J78%frVEr;qZ;^7RnVP%6nwE|g`Sx_)2Y)e+^;b-# z2b!(KrcD9tep|6qP%>$rHQDlZHv>0hhT+?pT7Frtj+(U^Wh@pwEjP*~%QKx6^M>4S zmQ%g5Bx7BOFv#>)B^|hWHB$yN?5LGY3%Q&qW7D0Q-C;B*c%v##&QyBb1UXYE6cdGR z)nN0;PC)7|N#&DFHrvr$xt+E+vdG~?TBrNtU20pE%gO#=ylp7mp)^fdW;)T)3zJ&4 zln}b*s@5u!>Nc%+DY@1lEjQzimg8*E9h<5u4yb;5gnYB}VoS{q#k8t6X}Lnx(si}! zX4Kv^1;T=4u@WQcPB$y`0N2Yys)M(&aShp53YJ--rv+06yyj^uN$Od@%mDlB?L zX<;=965QtIs0EuTDVZBK*U{)P!%LNJEeCQ}NfLK?tUfLdw~|yTsCofB$uKXQ$V`N8 zww1}G88G1BGcq&g)8)F9lWB6>VOC;-C%R*W#!|#UYS8_T!{p1gUdaLTlu;ggb6ieO zF>?hxtTzWQ%C@=F7NB*EQ-og9L~%G@CZ)!LN%wnpc8M*L>adGrIiXs_(!PFCsdUy^ zv)<1S(|JXzYc)G3m}+m-Z7xKKrwlnG0}RbHJ;%}jJ-U?Dm5l{^g12yIrQzo?H|+=#~{CNoy8xh1l_-e#1l z;JKx$7qL}(km&CEIq*A4Wddf?GfNYjRr7dV2Ih>+P)oIkr#AKmES`2oG+K%7Dp}?W z;KWX=%{0}da!XR#h?{Jq#M(qDX^qC23P_4Vr&DWmDn@H%&`mJ@3_+ezW=(4Ch$~Lc zs_;2*EEg;G&Kt62z$ zRa%vVDrB-wr8S?=!2Zaj=iPR)X$y^;XT?L>JSU zMP<9H<-zag8s%ku;D2{&m(qDKjL#Rc0`glEG}qR`Yi7in;1;lcTJta#crnE0;3+M; z<>!Ug)a^7gl*6AT9D6%7^?aTc41b(R|z>I*qfQNu!NP8By|-Ja&MWqpCdlv*in z)0rD1aBy&&VJ?+xt?HmqW@?E_-EJ@Cd|5Oay|uitNujORolVy)RmvT8R%c7t!okd( zwRGw*M!TRHz{9$;yj-bmu_Y@CJopK#4b}2oc9+fWHfu#D-9odk=CN8G3{*%LE{)x8 zTcT?Pd}o^tZ9E30U)KzYFN90EE*AQ^D&flVQc=8d4*V?BU4GTf)Kz(b(*vfGk#@>%S^_s2 zYv=ltDWgiBG$Ex*y`p+6o|hAOh*M$8y5B8<_5T#oc5x zY%i*IDwnmHQm+JZfeOMGo$(lLRovn_vz|A&)!J*9`%Dt-jj~cssD!fYH%m!9SR1Ca z8;lLf05UnqYQj*-IGH??G~Et_4hUv7x9gaR)}qL)2NFn0qL8bZlPMUe?Oa`-ZJNtL zaa(5B*-e&)uu3`0ZNOo$!RpP1r336 zx|*(J9j~B6+>+B_nNe1l_N(A5Fjk{xxitYxSYkD!TICr_=Zj*tEJ#d?cRS#P0Dj#B zox#>BnK9Pzwj(EH0mY#=DJDPH`YSx2E++Cg3A7Fvfg`uQg<`cb+D>0hxb_+(+N)=^I0DsClT&wE2>ykBJ zjmfUgjhN!b%nzEGZgDI+)igwYrf>+55^B0F+4F@r%TWoD67a4}xAYM?QU#^@|8sR_ z%c^qOwtgTlKm^1~YEYyu#5)0{QmHGS{fae` zT^VSl0e>=vpF@;_BGM=oh}?K}{KVx+K<*_;GQjO$t@qEUp2uO$^bU z^1ATHHOgKN(^#UWN0)Aq;sJ{Jdae{namz4l1t$L~#$AMOronR;zi)>%v#aynz8q`3 z6L!usA3C0{<-fn{c_!rcx$iLF(jXj0NBW8XztRj)MuHAJ*<1Y}Ai`WxvGLH-FXi?% z2cK5y`tsERNvfAYwp%VZX7z417@6%P8eY!Fa#(Dgm<{Mv5&i7gzFp(I3>C@+by0zTZ7b-o9IkS!f}gp9&6^p<&CvpuxY3qpa23zLO8@z!!ppdbP}9Ya z0)~5mi+?W^XFow}&o42~6=oORZX}ez0#$KoZ`^DwfBl^FoyTvrKQ5Y;@F<4%c_{*G)#e7b97P+qRhVJjieSo58=BHjrz+$2o`H8t3r;u!Zu@XN*Ib6)%)k2wD2KiMiz!V zER4o782LD*{_A?qm6llsOI8F4_Ku=Hn|)0Y+Wz@`?r5f0*pr%rYYwx2Y+4`xRV~Xx ztm}{1$u4^S;zwoi=Um36RTal=`qMH$+Mh-o4=Th+Rg#MQ5Ko76{_{8&(9B=sjDA@r zi!bzO%X^Bs_k6rMXs!l9;@%(X-v2VOQ_aRlYn?;(v^w^s30lK;GH+ea8C%AlG@yG+ zlfcqehw(q+QP=nStr>8*Nh7D5b%)}8>z12#@9knc%kXY9C>~$c#-#H~98WtkKsW4}Vtw> zqUBS?lr)LY2Cf&h#*Kz%BXV`R4Yp^5heZTx<`G==wG4Ol}A!cIBq+3i(x(pCNvuW`0s`7(8$3Tyz> zoS(0Fk<+h!`if_nR;4xLYPV>d``yD8{ZnAM!$8EakNIzV*sI}Su!1}8I6MXBH40UA zu77vRz`OS?f5eyBJ<7IAwfRMyjyDY?dDmor%m4VJZ?tbk8Y^GCM|G)sRyLV*AvXAL zc02zd$Mz$AI8L76Xllt3Z<2fpxZq6uZ1_fM9$~kM?rs@Fg`b@>Ys7pVyQ(z3<IunSLYqHxexs$ zHNpw9iO!Q{v?Pq>%y~Aq2Y+atEsaLesZ>6R=`GSdXNq92`=}lRW&)+;oxF^ha4vnZlQO ziu0{NJ+WKtKz!}|_exiX_L)Shl~b2JPs8AEYtQvS>y>#-KlEAd4qXNKxOq@cH}-@{ z@na0So2DsBTG?<~_x+Jl*{SVpyUKIqY)&Ut5!cs(0Tw63qNCrV`zQV|>Fy=|y_-M( z^;(VlNF9Zd`X#IFV$}iuwATv?h4r}K3CTUcSclfoK>oMW1K9>echCwD3QrB_e?ibGo*-hSFpDmk5B>joE+&{)^X z>YXo{?A;J|DNJyrPKM_dX|aOMVzO}B)x_^+5t6MRBMfnu_7EFYMk~L+^SMFbMhG~9 z@cj-=KQz$E(EO3o#cRbc0_H%(9Ks;~_xlcM`dsM1P*(n-Hr?OnP$DU{Gbw13Ub23M z$WSP|-**Rk|2XZ65dY=)(tiW0jNOjQ|NdE`$KYi-U+>oCS`6aSx9{s-+D<_@P~lGL zb$99a`Cxe@ORlhlAm78(WPTB0nkVcF{4dB`un#Go%}X+OH2e7k0xV3kf4@D7mR)Z* zZP1Co{{8R6XkHb(`h4ykWU0ora&frRN#LK)sVww6kqn>6*mE4QJ3&q|FcXP>!Rh#` zs%l(T_?ma>nYNqE{0f6|mh#BijZ(MbeffnK1bJy`~l&J`Du$dfwGnQhlsROb2c zQF4qBA2hqqK3~0p10%3XN`qSNpPY7*HtV%wT;ssETMPBA=&!fwpzb<%Y>$<}74|95 z0&%0K+wrwK+?kJ65BW=Gl+PjI3F@+TU=G5^fif#pcCE-|ZWcjNw zzS*F(Hbo4Jm~fjS%DIhB&w29qcMb07H?<|%o<~4HOl=NosFzpgN(jbE6!blJ3j>V9 zBqt@+aNk_Mi8}p?i$F&hRHyeTIx1%!XCS|f)P3rZ?8EQ!ovGEtFX#wh53B>96CpZdE?abfgjhJTJbq>DIiW8ua?+-U}iOxS=UTxxZ+cj@pP($ZR#%E~=$DO;> zk!EUHEr`NjzyDQ<&IuXS;HCHEPBniXe%A>8#t;WLdNPCqXf87*jzV0ZY`p_7)XPgw z$Vg#Vqat{*awvmq^dL&FF)6yaC6ZiJQ8;N0#rm8NYJNB!oFoY(_RJl;uXFHtIU3nW z9-j}Ku=)Ft6K<+EzPa#c&EU$Zd;j%);eDcF%)^ypiLNkBJz_0%NYuVzBvpPw)294|EIUBjQQS1~)h zNR=o)JJWiGyHxXDMu^#!u4|QhyfoMDfc|@0n}>P3UI~NBU>3GmwR!J9g)qrak%~_B zJPG5jQWOor!tGZ>c;=-qAAhCVRyoeN!OBMt0)O#h=MyGBDy`9UA%oUq*U%0kPaoc8 zD6Yj^lNc{DupC8h|Nf=DiT;Sf-JS4__oe&q$f=*lAeT<^Wh18nuFb4N*LvE$vwuH^QUq~U3!(6{kSy7qRa&T=g>hs^GEYu zSO=1Nfj>1KuhTyd=znKBq4J?5hG)OGJvACtFI~U)e6pC+PwX@11^|W9!d*RB8q44P zzw>Bd`;&2G)PAue!})T*EMSi5@Z&SylFBVR_j~Edn(-+-itm- zrQ2`gc|N7pi`Lq|Ub~}ixpaEG-rJhZ84Wq#+-Cpa3d3%s9^B{9Sd5@I%W;)&4UY~? zL%Hq+dVGC*!gZAdpUXHTrtl0oCLYu3YHqFi=O<0z##O$j-OlJ+Mm;W9KZNrL{)#Ie z&eB!Y24%AREshbBbFMGC_3gJJNIIuuoyn{vqMU8^Xzyl~38edXI7ieS45T)ARq ztUtuxeY^->^6#G3IcWA3Zw&FEB_Y3KK4+BO{pf%4y>>~|&B$VvGW85D{9&C$FOEd9 zHd#G?T*r5xHweb3j2AuAG=A7`U!J@Y7ujIi$8i^0%luqKy0po^XW;tS+{dj&MAd!l zqIsV`SvCIM#=p;sC(!7h9p77IzRMJ~P;(ld_{r3K3Wk3C-LC5)*a63=;x(VhCcd*+ zoDt1x-gX#&_vOLVLrl!rw-a3Y*}00{` z-REU;J;H2!aZK{Z^vQMdTScR8XEB@X>&&PYD#TfGX~hd_A%3HWvvY`AAq)mv`S^jnrAZgwer>nF3HbN; z=G(1*amnxKUfE)1D1oe9%Y85L-1m+HBc=B=+WoLX=+Svo12N&Xud=xN5i$(H7(p(q zW*_Tw1;YWR*Y{i^zZ55Jcy`keXYZ-ZU5mGQk~pdpJ@{y8QGcJPNWSA^KXiXyOv87LKpkfDfvG?=`Dm4{Bk6QOG6Grfq4HC zoaz@s92q~6A)|$ZB;Kw)gT|I$BroP{#p_R(?x)s!#YEhI53ZXw1-W@S>z2$t{Iwbf zk0?&QkHH3J0GIMKh`TAf{>|I%@UGSJtFlOZ87M6LW~@)-=c2SQY)8#?4PxDQ&-dBQ z-(zJuk4bn9b|tygOWrN?t>5zXsDC_f$7v#hp#AH3*^?a(eVq>=i~qznARF~^Qyf7r zuZU$(8QkjK5DB|yy)DINCXr4RD&6e(r!ZdM$)mi(3oEkZDK$Q+EWe!T3EBFbK86_K zK2Flb-={n7+%_l==UNB{jS`?2{G7*QxqV-I%eg~IOEKnEiibtIQ`6gM&AQFq!*y=T z=OUcAwdQ`T)r|>Pjmr64N__5LcE}v#qM@p%FSr!jA4l@-@JoG}LZq{3RTF|pYKcG+ znW6f=Ba+X>Q*W(KpX9=OofpNmM2@fxW4rd3d{i1&VV+urWq76uFC+eSd#;IDZ)ee| zbrI8Om{NBCw6`7f%nz6z16>s($?oPJ$sg_GOKn_jN?P9SK}9{-L6d1ND$mBvbdmG* zpa%I9MUyiAzCEUouYm|3=R_t%idMvKXJN>A&4rYVTPvas4$hSeX4AXiLs;C%hu0-xz?f}kJ%*YD1zuCBFw2ZjU#&*`s=Ts zIt+A8Xq<;RtK_7;W0D=X7(N}7yH7(0PJRhgFq2WfUs#|I5dp{*-ep!fe7vw7F8}%# z^M`vWQP8(+=l+{9q*Bwx1rMsXFV9Ul)G7KY} z*&NtZ&^%m#2H@?^Ngq}J$^82J0JgikDk{elBw<_(i0f{s?QO z+b>eE{pEyA`qJ9fz2BGXKqb1O9exXvN4p(G#ua+e465|?JZayrlRyKJH#k8O3g`yc zCIaDFlOwe%56R!DUaQDNxsAJKvyHF1TP+1%u9IUd*;{UvdvmC1TS+_$LyBj9*nuEp zlw;FgemmO|yc%Pg74F(%VD=IU!J2mxV?hPU@AGpDyp^Q*Pj^XWYMkR?>uH&+Q&@bvZN$1iwD50>Mg ze!=>t=8LR4gmfa$Q2hMjaqwuUl)B$={rGrGlIJhXmKUdzkEvprQHSjHfY!pTI0etJ zI+@Zr>#wP#J?@;tgqQvrND=c!_I;F7&;IVUl8C+%`K%6@&77U!ZIq{5arT@VLJ`d! zt@-(y$MJyAl6Y0gfne1S^=IMsUkh>NDx4ujiziC{*wlTecTXMp<*Q)|WHge;A9BJjE_S@z}#jJ4?Op@Pf6WDg z=RqmYg{`P@^fNQseFs1Dw)8u5PopZ@eb{96m}5vyVcf++b#6kb>VL`mM!_NO_7CZ}WwG6a827h;#bZSD;H zPIfs0(dFY{LH7pd!a9t{S5-)donADt`jHoC`Y?uKYblrGJ5{RuNOQl-zu)T{6MO0- z)=W^zKbNatB7zBepFfn}I@&|#lCus2Z_djoxOxnidH7L2gTPjOJ{{225E^6<6`}Y*1)&MtRv0u|?yWpMK z)mQ$k3qS3YzKYry3+L^1>z|*%e5I6@pwQrpz)qN3l!o$axq0V~?GpszO<`F~bT=uN zpsigZK#R^S@$c^i7vb7PBDh~6p}k4AfzEz|?dJ3iiM^n{FWz5-$yomKcI9B*brUn| z3l6jfy2}mDNOkGV)c&LwrFk=7`R5l!x+O|$BgYU(#N)L^Pw$J;nFx`0sow^m8*Zs5 zHHp;Y0MqoL9YEeWWc-^L5Bf8u8-hJ$dM}Z_ujKm+5D{HCR}G1t=xTlgL)*z)DA=U1 zD4o3quU3l>r#u9igjeXjcVtNab_bIT^S9@z+u(dvzt87YM=IP9FMkaMpGQ8W?kJwh z35|_mBC;OiV1x;N#>STM$G6vp=7MR@g_uLI%CE)_?uNvO z^e{2rB457vM9Ej=SP*T|x%HMiej0bF6z~W5XH6Xr>>YcTVx$TDa1jPwhUWoVKrM>* z;rH;BqRWSur^5#k$I@>4>-9tEI#lWf^3>(hZy8?S)gGzyMjX9X6`&tij{Gl9Zf;Nv~GTDSa}grVAhutnsavAF6lwMBoYRi%r*mFi}U{ zzOj(EbiMab{5>{!N1t@t-9<;_kC?HPT^j4~+KR_;oE<56y1Gr$X>JcXZiU69NzFV$ zmux4PLx^5b8I6eBW&|(OmS)-jdMEhz9DD_89Gc4Xu!$T3_H>s=O8f zi*I3n6Jxco;O2~2Sirtf7(bUO{*YW)#+lH>RvoIeW{NAHs zpV6C0o@UeVD|{E_-=7mV$)ec#rp>PCxt)=`W)IquKUqRPlf++x4pK+^H>#$u(2w!+ zQRi!Q)`0&})Gutk$5TvG-AQi$dZFv#+=kg^l+k%v^9NWVI!x77F9Ue>$-%R{LXUU$TauV|UnD8ez96iM{R1P_W_Itv>DIs!s?JErGgzMaV9ew-^cYv5>1oJ^H)gq8!4&Z^T+jM$7$Tk;Rg z9>|?$m*vB);MV9D?(<`5T^Qmp6g277@}Hk{x-wY;8y60Tuq-A>GZE)aaXS-7dDwhq z5gPjOb$foMv=oM%z;l;8_kYK|F7$vojWITeIKA_cJORCt@t=N$|h*{)-Hi6^K5;@Fho2$1rE<@AInN>qlk=;{8h8 zW(K6BI{h6$5{>}h+0@Am#e>Q!CnR3U2i1lxOnZ~H;%{#`=;3BE?0JuG$$vHc{f|w> zo_Z#is0?rp{w%*~p*gzuDk#J4Z}B5%e5A{SKl`Wtu__vN`YuncY@R9)+Mk09=WtYF z#Ns-;NKz|wWZo23d1UVo5);UJ?Q7P(eAP34^ny+ba5$|U`T?gIWMvxf+4ZEt()c+9 z@tJ5b>|fNsOfx-(_SVV|V6sl0%`rgCeAE6thr0TY4>U(l@DF)nD&wT_yHPz`74v=n z`d&%K?-0P#k^|w?y6g)&oGY~y{|s+)VL*;4R8(c3P`(A}t9uV4-g7m_0SP5RkM3h& zQ^-gun5k_vw0|;cuTPau0PV^Zeh)9@u?|XHwK9-Eu~!7I>Tk9%^PGG+-gFEThYI|p zZ13z(s>TAlLa9;4>32x`pdIFa!m2N_Ul?jHhNacBv;?g;U(?MT_jq}(`^VSpmHzG1 zH0*K0^Y)n(jOQ*<$9Tox=h(Dfbh3{!`P(bEELAS5KxWr+WP?3d2n-(FJ+1YX1& z|KY1Wn~eRU!iQW{QV;|aM8Fs_a$A&40C3l0cydX}mZyPk1AEI4%qK*Egz}o-kMNMa zV};5;(6_(iX|L1~evI?w>!pSd%jMtv9m1o4+Y%m#;c>JSy+(G|f4g0=-;!p39mDQw zO2k=j`RjfskoWBKpL;?EvZsnsZ({uL0#D&Dk5Qi~nh$U(3(=pqJ9t=X?flK|A~j2t z_e;HAst3m9E5Dxq@=AX_c^s}5`pQ}EVV7Ovj7cz&NpBRm{e;{s{Y8V4}A}Bx8hCy5J;rlC=SmKlG z$G>XSF`G{(w6#uij6=PeFKUrsAV1jfeSyoSr*nkQ-{lVvwgM5K5<9KN;o_%q^oCt?>&0HB7&cGr zW<Xl^z`Z?tz4!yn+mVTQ_p@=;dj8!=HzBcSS8uXYfL(|tOG5xY>2HC`W!K5G( zYOod<98nEife{(XwAC)*gLd`TKYf3hvgVL)DkdlhBcL&7@$T})uW0IIO6rv0>rk;H zL`PJn3uQjP-tK8~=>>~9xr}cg}w-TT~;^V5<7`*rDI- zJ@RC&kL-#bls>7z9CEyXT;BCX+sGpx!G(O>&CgL7DE~ZA29N)cm`ekVW-mB_E}&cd z^AFjycI|4lWj_Yu;YSf(XcZ;)+Kp5R9u9bec10iVkdD(T)p2g#eQ>#?`Pg@06D?=3 z3_KU8DAW@E?#a)UI;AyVoC|kK0PcItfKI$IFEwiM48PXyh$u8-(MJV>16|w>_`G#R z*q=`DRFe3x^W~@|NBH=zCx(eS__M$FJy3aX{*n;VLNInv|DH%fp)kB2C}9=3JP&hyT>h|cbZs(f$I~cFhwp1RB*QplaJ^P*#9}tq{+-E!EWbghz;es!^>7{pHjei+q z>Z5Dz=X9%+BA36Zr!j4GVz}Ee>r%%jHHbDM?sS?e4N z5YCVOYD<8-VOZK1e;r!&OgYfSz>Z)AVK%``rq_H?8=vy^g$F?LNrB*&{O` zTknCf1YY8H81?*deo8||Z-0_MNK2KgOdZ$xdmiS?{wd6nxF!h#y>$>@eETW)31@z9 z)P}U;(g6gB=irHEfU4E#JtWEsW{_In0Xek%z3$0HsZWMVs1G_j`v1bkXW{uW71~sC(0{r4-ckb;o#Xg4yl+(4j-)s@wmZ@8;ed6A)04>6EBdL|bjTT50+V{;o zy}Z4=6n4INwV)3-V?Ayr=-4}mNyHAG!GokIVaB&7%Y=rt9JhBENt;5t`#weN3n98uiuDwvvQdfO8_J{M^2Dr<1s8U_Vy4*vOpicNr* z>HLZpdS{R0iHi<|?Yb+W037nFBKVe_Yy`@OOU%Y2rAl-^ZyPd}&R!%z^#gg<>An0CMd_O~irL7v_Q)z%~sa>j+8=a&PK z6HhbPgO!PK?4IK8vsSKI$!6Y&JpTBiGn{Evv<*jl{ec=CTbfwFyKYJBcMy4P$6==U zvMxB(xZehE=~<+CJkSV1}%@-*r`?QRgFG!@%-XWt=`{Vo| z@Kxm%iapC*Ce$9jUpTeTKh^#lJ+|vNyYsDq!|ab+3}%-3Gr^WrV2PUBW4f0Qtfjgv zYg9gFpOwy}{?6VtJzGitpLVa{cT~>o8nNq8u4s2$Q;sC?D!YIo)nT6+1${UJWp+#6 z19Yoh>S`#s($!BCe?yFK|9+XXHzIIbAUC=4^T%fIp%p2Ap*Xwrhu{_aSB zJ*%k0oNJ7v&^_3W$|4BfhgV|j&dCiWzdVDE1E{q3S}(P4I|4{k7z!a1;9QWn@Fe5= z%j%OmWM4!B_G$%5BKjhOv05_7lF%c}{P*^Ks`JNF4VMUzYd9p3Q0uv+Xo?+GCK-x8 z%o;cI!nk2f-M4ePrXQV-Kl$&{&ft4pfB*CaaPc~$1FN-%5-+{(=%>ArFZ4o(bPDG79}Ku-KPj60ef~VORN^d%AOdN2lQXUI@&Wzp5F)(DK>;*7>t9 zp>y2;&to$LjKkZ%KKM^}XeZcY%GE0P3DIYa z6qK`YF|Cqy8hD|ZOXR*5*!-@HUZOr!h~(e&jQ#Py&5B|CrIZr}Uo_{2KPS$2B0o!{{$PTF$rma!HE#R{e$^4kyA zQ7z#UA9`vY^X%A(_PK{bDHH8qZBk}-{LKT`e160{vhJrXy3_o+M&PB7>qU~Q*V;MY zD;pB0z26`aUIF zeAqTBD9V&tY3?f25-#oM)?ZfXDrFQv?MhQ2VvbQfd?sFS>sZ_KEgrTngq;iHG|ap;04KFhyDyIF|l$ zU>0I{y3Tzpt-O3(-u(N_gapA&=op}KA+#|aZlB0GMG4%^4=;Vc$=9`JPweLiKs7h+ z#~-5Y2laejoTV!Dlb7vnA>G{XIuE9jhGXSKEIclF_jvfKqzuOid^dkWo~}zBb3XrE z*zNm1?i4`LpC8`+J+2$H-kR1-_4ppbo~{2lRP+dEv(7KGn_#|jhif~IW9{@B{Y#tI z`1VKxqMQRHO?XCMFtY)XwEDj54I~baZTQ8Q{CPjlnD-VjiV4bC-H5IQrGM@F*9UHC z_i%Wa#(mE-Wu+pg8U>*n4&wLX$e7#c9wN4vS7-g*frExPcaejHlZP0*$lgnJ+ZKj| zd>;3w>6 zxh=fHjkf3U2UUS|c^YqKH9qiI%C$LV&Ykle3TdCrj6O?a@yBNH|J@J9>C21KG^pRG zxhT=l$Oygd`v`+rrsq`kLid<-o&r1V>qJjbYJ1V59KX`;a;u=@DHM9Ir~lU_dSJ1 z7>8oG?7G>lJ8ZBvq~I3;X9uok|EbG;<^p(m9X(tUr5B>Ese6sV=Hg2f`uSEMpdzwfB{0*1O~x!Q4GP+iD___5eFTDy!XBeY`eX6TDlSX&cc?tP52c&k zXK>bZ<%{bo>xPHLkndDuFT(GMJpl#vEBe;JZN)jxTf*-nxuME2?Am_~Nw5=%h z?psihUFqM&O))5pMjl$i=8|@DU-}sb+RbXGT^7NeltjfFvDQJUuYdpkXkqsbn}h<2 z=Gz?)G5Z2|>Ww8e=)VRHl9D7BljL!fp z!vo*~&Use)yv4gI_OXx6Ny*Cj1ulYnR}?MC9!3PE=)&^P=}ajR*9K`g->Vp+Fos61 z>mCorIX8|^YM#bU?SJdBCY{Z`EjJ6>EYh5^wd#W|7OAl5cK!bIul)T^`TjVkuy1B+ zO|94GbQkDn^+12Ddf6N5b;VfZ?*L2hGU?EmA1cd7q$ zAa#~d1nBU~RpJ6`%DyCU2$ybrH0j`cDt-gnAKxleHG%Q@GGIuhLEPSh*6Ura7ABsQ z^@dn6HOTKpZNNU4beCE9oM@ScCIID=u-@=)onbdTT3;;r`S|8n`gZ09*0>jZ&U@;L z-Aufwl*leyV1jktx1}e$pd&^1Ys4-IN!q&S2cwKL@*ZK2Elm8OT26L`Y48*(eR3ZV zaG*Tnw;|_L#l}s-glq(ODb<~$rNQgO8CB8b9dnvDJqJH+vL&=QcmS;{5+JabmF6;A zxpUQG>2h~9WQ}zM=VIf0$1Iz8A@?cK8Pc6O?lzaqlxKA$_WSpwS2Ur4;EbqZQB|zk zcieaby16^b&d%BbkJp4SYkwtRyxi|(l~+>6Oq~RK@Buc4TcX)`PwT*y$Iv|I06#Ps6&{kQL_Scunmb53zqjA4s^gEELPpaqu2!+~iA*9U(PyEz|P z5@51vQJj0;ekVZ9`-;ZqCOz?&heb0y()@`pg;aw`6qxRyRUCxvK{V?4#zc_tc;@g` zN;0~fh^u+DcknKL*yUTLN(*%5Vch~#e}AAEu++*Biuj~8oKy^a=maFoZx#&q5qRCZik~v)ELuJTXgKcmynUd-|zVc4M5GrKR>H& z9uj!6xz`-XLwwjoEwq(2I`HtGRYic5@wK{Qln9mpr1&+S0M;102b9oYgkS0SN-*JM z(lUU0-Y;C5zMlK{TujEcZ9C2Ho)Q)Puu&#^*;B=USVYA(R>VFH`+KLdx^Nh<#$>GS z**s&!@8H9I@>9*OyiyuJU)FeiRR-=!GyGn9cbDHK2=;CJ244pZ>OcQJ)>MQlM+C_& z()ETGVNylX7SYjdzu=XtVABFWv)%8YdM_53qqm2K<-1Q^aPs@2a;aI@0t>3u=)~qcmbWN8Trgl=WL=a`~enU`V_poW0 zZUF|Mc6Y}QJ8otqG&=1qRKPiBcCPB8ve{9mPTf{o@2?bCW-A4_Ep@+sc=i*h(b&bR zI{5(i6TNdkWY`aLdnTl&4%EwD8}e{ya>QPfoW6oir&Wt?g7X@i$l`yM3vG6LY?q=8 z=49dggL^Wss(D&)f)#{@-ExG$-n_DT$b#gM=3v(H{&v_ATK&%lXK6pc_?rImkN0;> z@%Cj{%|+N9vbSYRyzUzxFFm+BvHG}`ex7`vr}i`>Bh1~h>`Z?iUWrvvkp1oeR)+}b zQ?RGgH3_ypI7Fw{HT%oxxk96;^gHOmZ0KYAw||dwoUz<9#O^xjFD$#Wz>sF(B|Wiw zc)9^;U~*uc8b1<@Xb(FrvePFg+W$Rl>=8_t_VT=#_wd-BZe4(2dRY|Xv|MrA?3Fmu zE8tc$@R^y6RN*+@_^-pp7qgrH_`gdjF8k4~7G>L(>4GFs^YURrb$7^pPKRji77jko z0kIsmB?IglG0V|=h#(wx+itEcY*3OHIt)%*NsONk!MX#|Vn|?PPo8aZFY7$rKhN); z+v5j)gvIg1p6mjU**|6t_j0itL;-6AxwCzKIF^qn|IsCj7~X<0?K{u#dhC&9pMH&m z!EQu~4vwC40h3R@SBwFIw_7d`jnB-Thf41sgA+WoXCQK&c)#BJ9UPuU++J_Yc0)9P z+{scN#8sCNX@ z%H>_6Tl0JE1(UrEz-9MAiv1RVCYZzChc#GwU2H&QfYr{I@P364GZKAY;d;{VPk z5!tThtn9>xfv&`+1zJe|*FNJr)FbJb*UPGrl4gt)g|HUOc`YygDrUg3egA12AE8BAg-O6*VqR~f~j@E$K%;R3! z&VM(udG#LVk*@2ql4jX`R_=kqBA>YaZ(h>z|1$aomguYtd_arVDBL}$Kj%$3M`;0X z4}Ciy*7op?-X@ldB!H980RO3C{N-zW7{>}JfNklFpR3j6E61~`yvg93GFx@$YJkoF zq;684{%U_aKE%j_7{!qyT)_S+zsUV7|HtFoiRloA?^AO^td6($XDMCFb`0csZK&wR z*H!tx7Q1}WvS!TQ9`+OQ$FtYR4x!)Qvi7za7kC=jZ4?iR!>lB)&+|`T*Dmj_X1!zV zUv%uxkke~KHBL@`u?`}#BG^rhVXxgC@XK5ExdhoeB~KtS&pmI^X-LbT%3%;WTo&iuPiC ze0cfHXL^XIT>xDKTH{v4Y>8D@VVyNA{l{Sknuoc7uxIAej4Wb>&2n7U4r`uvh;_Rl z?G6rqiw=T^LCY|J1h@ZeX~gs{;rE0{Pp^&zi+eai`gglJ9jbr zw)tX3-2i#wqTT%`e8{(kHKMBP0}Y?0;)@M)|GmijFLZ=9ATHuhcY^RI9l`8NMeV#! zs2n`$c#X`%^DQR#*@@_}yxfp_g>^k(&1L9l@Y2ju3AJ`Su6IwxR0Mq;m#qiL+2;S_ zt44*v^J$Rg zkzG0JXZnU9am`>0!Dd+{AhIfArTl4XHq1AaOnuM6g`{OiegX}G1zzu;iu*h*l(Pfj z0j~~mSbkEAt(fBnw?hcY>T^+HjyysbqIQ5?FW)^-x32*6m$kclSIUr15mIbV`S>Px z?hJmvZwK$-x&CaEG^vOcf|C~TU{2nBG)|WDw|dCOQim-s0k4KDXgeKFd$jT3I`9Vt zZ+C4L;#naU!w)#@X}#U+_W!W=Zn3Z9`F+@U?X2q)r|BBT6i(ds@3G^Z9nKs|A|;aJ z*=;0I7fPad5hYP_1`CRJO1y{^Nr}M%E?NUgaNc?f^rb*v3KV&2i=seV6a|X9X@df( zgSKd28z5~S`jQrT3W|QH|Mi?Xb9Qb!cIq8q{^$SKg_j@s`|*4ET;}3*H)of7o3i=Q zs3(rvE2jnld(9mmn@)HZSCYZ>$0(pll;5o=^p;F`5qMY7}Y~@X&+KsClN1T+W6@G#IZpX{{;Y z?&l*%fa(?R!?Tf?=bll(X0yZ059u1v&D14&HJKlv+=Jhf`3QIfR335TIg>!jfNb7YB)`DHc4 z`oS-xWq7gRCceYR@Q~J)Wa#Ousv6$ zn)e8@hSV~R!iNscF)FRW&_CuwC3A>{zxRgFY4N+lc$QZvyg_o0gIM5%2j?|_?6(zW z(+%1aYeHLdeHNX)EqFLHFgGVBFvc(JN@1pEZ@)0B3%X2WppDTgfwmAhfh%NHVl{xq zOtxm&oQnYTA5FZ;M71|-MxvY2c}1*JK(x|*7oP0lWGA#^2tXf;^YTP)d$ndG`dD85 zTr*Km_7ijf5MHa>$ysnZE4$w~?N%PtVZmEGi1q(hyquNpTF{iM97I_qOjDS1j-tYe zO;e~a>;4|ugQA19C!&T)jX^lHy;Hhd2W@VEV$XP_j^LjOpg_0+3O;G6vTx5P726>r zp|?AP%XHWUAA4FsG+u{ZIz8+SkDY3F5d8@=_S)bzj;5Dfsq>>jzh$)*xmV{8Uwos~t9;oBk=3;Hw zolCg~OyCGbe-*~#v3&LL5f9B4I7;4(Ji#XQIEe1IP-)@}ZLgimrdmLm;b$9Atf8^Zb$lWk0<=i2`!_}sKAt#hhAd9ikuY7g9($s4CYlOjo><4;P-C2+ zyWHj*YpUNV9r;4YMZ+2uxg0fAci3wLr}|vyC|qdl783V0M{)zSWh|N+WRTPboL3kL z1Z_Z7Yu@ePyx)!tKR$~6!XcZfj`|3v!73VP(Vi>f>qoZJIh2R`Z5d|Vj_;XHAkqS;8%SG*xK&B_Gw*H4b#(UApqSlJ_(!F1Wl53v7{SV!lqaU z&vG|8ENN!v%5t>d(^B8PG9qF9o6Oo{GRotzDt=l6tP0EGwb@*&>@*> z+y>4H*1=?9lj^zBacNPknvX<_-`3thvqkeXo^YFW6pUywIIP4a-Mn}}up69EYrVn8 zVTOKvH_p9qLN7b|sy}Juk^^z>(`eS(Z>x}3c$SqC1oJKHfaf4$^UZn#Arw#8nEpPfJg2}W3ku=duZTK(Fu?> z$hI#$?!<-5Iq*5%0HpK%P%uFfgENLOH)G+2eo>g#pd6uadJ!d7@)D4Vwsl__GAUyhKy=h`0X|b1 zNZcG`^aWgDu_lS3cjZCUevd<`vCz9MyG%T(4Y!1KRMK(~?IwK;QG|XQoRLxh7xc+M zb%BhT)bkDk_#TXRz`^G0T7S)fss;_X0yZ+o%`UYLE=mJf$5B6pv}_Mc+BBET`g)D*cT97bmtZe-`>5BW z0^D?hq$0T~1WOmq;Tl~#yiYQ9uP#cwRibNqyB9+bcfO-XV3l|G@LtwetzM0Pphq!4g>2@!QpE-7Qq za2}NcYzuu?X$zb+-JZ=-sFjcu$v`p6=*T072$ccU_+qN=LYQNb#gWnIfYZ@>@_f+KN0&egOkOZP<68?c{(=18(8MF}yy z*cFAvi5Ye~TV<@y;zp&=qvn(ac;=gb)_N=~2`nU)erQ zO?TChp{6HitB4H8>*ms}#V=N9pU?njLUkDBywNh`TI&xbz;Jm%ft#I^gY*wS|W=p;lv~BuYX4 zSr>5(dZjLgxzAk;Y!iOV=XuUnzC0TFqprt}dl1@(KJQeAp*FZagY4AW)7g=o@nX+| zVf7ig$GpWh=I}11AwWM?cqJHjLuuM_v*S_S?&#z5T$u3!Ac<0v zyVU`q2@h5HjZrn)`=dRxEycjPa4dGI-eqz{?HtCPNO8>wsCY+E>}E*s{K&8%n|tZE z1tM5U-AvP9WHA{QA_*|Y)DjzgQk-tv1IpWkNT~>ONbu3ZkfG%mnnQ`^h|a9H>H?WO zOQ`93go5>a(eTE-QzJ5Gyo~rynE74*tQA5ouw%3k3ziL7XbS8RiWlOt%8(FD)3V1rL90(WIL>e zF!RN;w)Tehte&%mKaA1_Q=1j49V%Dmn6E5;CoO7!R6s&!jl;TEF+!KVETDriLyo=L zHT}-cwXIoYcYC!C8~P5rcnT=DDzHmp=`Oj5e5_~t?hLL+ldXSZP=FGEIU~+VB*A7n9%x&rNAo+PV=D~i ze@yFImBV^AS+7iR;(1AneHU6Y6QLWMCwetFCT{JoGEi`PdTDpw>7K8~6z zPCawA{OACjt^HY8j%%-q^ITqCy$ax%Iz(A?A1#}(f)Pi9{dw99)j?-^JWb+>J_rVuZywih&RN-D zfca?P1Q)+QLSDI<9a(YcY}}CnOlz%M9J3w}QH#FEDSWU6i?;;USlLtc8eN4IWjN<0 z02J$JY3I>}u@6*?>vV*!0>qt{aY=89)n$aWX_7+6!#Fn)B`dCKx1xqrF^2%Y-L4p( zy0Fh&c1EPCjIj9_mnOSxqs7?*=M7plX2R||%O%7yF15A^QuJz*Y{?0of-iO=F3{fN{t2Mh65DQbJ z%WB%lbqjokY}nhzvtHAy2AY%*TcC@l2UlFoEdd&UnHuKMsa{s_Ms1EK>(!#07ODEpo_^ZicbL`@|3()tbf$)NtRY)=#ppP(fAHD4g2nSXJpT~>^n8=(b6?m=n zGxy}L)pc{;$z*>mo(1(Bo-KRFEP2drmBD%dgUHk$&rt5~00-rfpJ)D4F1 zM1?#b?VH2Ckwc*Vpn_unr4VUIIS~F0CpGVMBpk8QI|n#t-L89|~L&NG*^RyW`jjQiCxnSm2RH<@To#`CM*J{cAK~pMxsH>2UrEXBa zf`9v*BM$;8SHW6q1A3`I)^`9Ep{fYOF@mQE_0kh`36?vu8*b;*rk5w853jVGfLZl) zEfc#n32!6<+=3jQ)!mV=?Omob=(cd#wSW;zPcO&dybI^b~&b$RTc z5%2_I+dg!??v%v$JyWzMus^K(MyiQiQu4!nHc7_ap44=qn0wSV2Z2>KvsxEC8(x}3 zDOt{j-=fa9^n(6;0yh=1fh>{t^R(Fqzvl#_E7j4jzOn)DdL%$w^PVJyXgPh=DJA{iHwMlo!a#iZGxuncd^PLHck}bF)PWubUP8Qf%mDF+O3<+$K!vduDqX1~%HvT5qZN6<|S>W0MTxhp7$q<;}L$!=U~2>f_g3e&2!mo6K!a+spL5f^PMqweD`jQ*HpkfTK*m5@8X)uFoN9I=F00jqK5MLa_!%22b6ZPKO*EG^j0Dw9Y3X->)U#qxD zhs6<|04P@x;PJ&YVr=jh$=tG9#(bT#X;d`9z2}J4V9z677iSLK)?*LKV;cq(zQzUV zvcCa)L~C;qc_op(FT1dm0cjZ%5LA#7Akfz>&1=56vf|N zMll?zN!%Ga7ei7;xq;om92_Mk$3ZOs>clAdz*7OH8;icZ zp}?}-3yZ^uJ0p|RB_OAB35Aa3832`vt`qit_iTa{)v2`v>%WC6kpWF^S1erQgat(+ zGKOt5tWc;TwzITf?k5)~I178NHG{7*UGwidaDEXyioL6GDg?{erRey_rc4GPr-U<( zJq{AIam~OMSj|RH(lzSX&WMzFTohx(%w}s|F8cG^SiHZ#=v_sg^$r(k8z32JLbqjm zYytkxc|iL{YQJYn38lhs3Gp}$<(77P*6)?lxkbo0uAYBc_Z*pRi8)>90M3zt&5_I) zItel71O{hhr8PY)+M``a=fG*xC}dWV%nZ{e_4#zHV=c&ItCod(%$IJZZ1Q-e#bs-D3p$22JgaqAIx&>?E0pEJNT$BX(1qWP~H@ z=~&B7o_d(<%Q0Pu+CE>L=N&m&LGi{pa80SczYMxbZ#VnQkTIvrRBI+m%12zSFd_L>5)xw6LmIOaakj0xV2l34a zgj}Kpw`t^oQS)dFH`!wp;>2q_60&7lWSnq&Md&s4H_=< zGF%mVa7XS6C~qy%D=W>b24g3Oe-qb%J9WwGn1P8ghalf!;Z?O3$4pvPS_Tv3GpFnN zdR0L9H<5=86ed++>(2wuYS5yi_cF#>4t+)Fz$w&UDfCv^jN7p8>LUjY2BH&FqMbu0w}~4370ZeG_Nc=! zngI>U=}bS_rUbbrTvAJqxf8XESF%V3IfvB)o<9imnp3nT&kjzLCUYk20Eejqc!ic4 zq><$A=(NgnlE2J7c|dep%3k&P=_sDbaB~oQR$!Ndb19dbgs1l#tY`H4ytmVqJG&4S z>~3JFL)&C)J8VR!sI4mOWCNiq89qbMhJhjt)auTMiag|0d6MHZ*HqUI?*iH}+;asPr z$oX3lKWR#Sm$XqDcQb@NG34wD4T7)66h4CadI8toGU~}?%PKaWsPMU0=kBtKyf$d= zDVT7L2Z2Hu5x8=vs&y)7-R^ok+BLhEehY10%3IGkU#dNS>0x;~FVS0WjB0)j8I>Sn z@*PHU^b0v6OHi@+3^aWZTeEWm*j8!fqGgDF3;`UvMzzg0H0|0gPM4(I;SSYgy@Tr* zYWVTI>GxYls8P&}z1UNQi8)?N-MXfO4Kd&+_G);rLKp zE*s;9os2Jn1G86eFoHN*2InSFtVzGqx>z=R_)6GRO5}D6>=r=hN;w?32({+k0T_=R zxa$-&$aIEumb4yRvdS}?P^B_5g7_&>?d3A>%?7}9 zxE($3pCCgQZzxpYkc>N(+)g}M@mvE{aXh%&b zUSVFYJWxW1<&58qi(|RcaslhaWSno0%Jd}rWos~PnlOR|V#KA$U5JE22IOwiR#vs& zxVJ_Ar+|Bv?bX$3fabAIUNI<=m&O}DQ#k9ezkp^K!)bgkOtwALRgI)2!B1nkZ^Bf& zG2xt|5XcMQ|I#F(h9tN!#k$&{DLQ~(Pv1A-R~Jst1bZC8&ji-04Dg`h1$e38n9&7N zs$|}0}|1+e8$_(B6v(VO$xS$kxWA@lhaRwzJi)cu!HVje>h)@ zBQh>WLQ;9kEW03cLx*uG5OobxFIxNYWIP(kT~;0Bxm?Bo`h!z=AWWDkr32LagIzG% zTWfiQ?71`&CD|{=Lblqg46d}erA%WAc#1Luz7P`%0 z!vQ@hMj?O^M-tKjMHt8MzDVj;A=4$L2n^O4;PpWhd(R> zRRqMAv!#S=Hyb{&Yue`0>4>xwdCl7Y3q+g9Sx$H;4;;fNcj-+xH7rJm@(GC2Nh?HH zKFoGVF=pKUq&Hf-h}a4nQ01D|SqhZda1d*f0$q#!5H^ZR8zi3%Wp`BB(P0-vdgJPx z!e=KSH4v$qV3k77?LlZF-)@Sut!wY$IXN|EK1n6A7V1+Uk~6S{d{aHpq>g z-c{>#e4v2H8dELBKrPC?#`0J@+!dsK0e-P_JkSc4En-uUr}8qM9KvlU0zTfeaPV_Hxu-8SlV62+|egRex{0YDtC+#CQ4V%QsTY)Q+&Cu#a z0VP0PHewoCJfbG*RMq5aouK#I-I0WBvu#jr^wXM;sK{@{&>+=w7MvzHgKXphY(D@7 z?kfD$IHhL_hAI2Y5k+zp8ru8qkV}}Q)jYaa40R9e9)hQ0h#~}CfE9XB6;IWK;FwZs z*=yM0otKMAwuB#8SNGehSzNkty`oUihi(q7+fBGzf<9d-f(U@8!0j7B<nM1zM2Zb=4C_RU0zJW7KQCIWhLP6?MsDV3S*%b&V_By6&^sW#x(* zs&M;*5qNr{>w77s+6&(8qYTtA8fU>T2JPKxv`>0813Prc5{_6RJT7*1tsV9SPE!%P zm1+*J&y@meENo0Q!Im(}P^E^JW;%}vwUI(^MMZQH9nX*?-UsecSU^i|bk&lTF-2^a z6G>!UmOO;96iR|Kx^n20mgafG8R`^{m_QFKYOL4I?wJSHy%Vv{FkAUmjJqJB4j^YM z$?!;wN@HtoVd)igr~HyKCteJ77xX1h1A@?+5dWV6c?eYR*j&MhBcEk5f53DGouFg5 z8Mrm5iH_G74wvsX=7CS+vgYj5Ds%?nw_{kqeA!Z&x6-D~n`r`?Uf2RDIBxS`s%*Nw z8N85GNEbNA9QD?58>$x*4QjducvOv8TId7Tsr=*swuEpvD=qYJuQA4@L%8tR5bbCb z4x7?wAT$(VqtnjWqB*+;mrIq{1J1biV>-0OF?z7V0Uniu_8A>ypPq$MVuG9QgA?MSX@p@U}Bh=ar6VYi&N_uUm567ZRt zZHeV(Ub^QkG~Z2dY|UlmrLtjF2f7#&;$rMFTu~)t(kui81;KUO<+tB8z?~{S*DGHNc zdSW)CSW@Tn5Do_sT+UA0-4ecafXmqZrp6u0cAPcE%!=BUE*W2R-QYyW}ahS3f@vKp#U3vyA8P8T`RC5L82r7WC z6CW`UCv1?=S0LI52Ee$uTgyV2eSm(=1 z)3Vv1iom55nk(q!NoOoqRxfTsP+V9J&e8~R;<1cSFbq3Qdcuu?=Yow%T<2!+wASbb z%#@Dha(p=y19+uS2R`29!^k>SuI5w+1zL8e!U;y)%vHNp14gWqGTt?GhAO@DoXlkF zBqHA)^0URo>|Mr?P4gspAb}5DoW;V)xhf?#gKZ=dt4Lgt+8zr$yv2orzW{_NEcT@d zZK}BL6VYvOhaAN#Pc~_6oo%N=L3&{UPXmh^hPBkCT`c9^JgFr?+Uj&P5436;Xz2P+ z_w&Q0m~MEE*fKqe>r_c@tlU$}UMb|{Faj_RI6ZgJh5CSeK&N$ZW}Q$RZr2k?#hmTE zudN!|Y1@Pjy*G(h4*CrRl)`tjVF!{iLrB11{lPVZ@@v&MS&q?|A3``W-uV!eEFc@E zO@P(PR>zYqEuiNIV>Z|vvSZ$~AdmnTj}t=pXxXJv6q8idYi4{lK5U^aQ)|I0Lo78` zRVDP?_StqpMvbY?ZCeP|a!8$w2+gFH=HN8c#7I>^8wPGy2R0DmUJ5fiU||ZfTqfof zH(qRDqaGh%_f%`_L+!?cy#Pa3S$pasI1T74Re&f%}x{T zL&lVAEM6|H*EPmRDk$g&XuWbi2jpuYHPeJd{9$&aOOvLH=_&`^gobUfKDc_YL8UQ8 zjg4Q~lQd0Q+v%*c2HmA&>srF|1C6<``(5%`j+J6e}q+9=Fc&KyMEbL=I%9P+)SSHUtQsAO!~}nmgCN%7|5u zog9`PC=Jzq%CxZA!CPhfAP^|u;0@0~$!xq?AD_~$751Hr*A>Au1X=%4c2O*W*O zEqKX84;*xhNgRygC49>}VOQ(>GlS$nG4<4_7?+?F0*@Sykpime6o!4g?zt#>2^vi{ zwlmbm1sbb_v}347Xj#FrLr%*S9!d0UM>4LnO06MLuSL+|hNAAmfoJiSub5Lu^-Xwq zO;2b72t0V&_6##pgcBGFj%X#}c>w*O+AphY5ly?^ z?VUW0_*tLKKsm^}Gf^LaleruoR=nHnDl^cx;e&Ms@D*ac@SU@qn1eOKSyaS4HaN%c zL6>#~DO8<>uP)$RNHqh!##7MtbO;8oJlr%BR+_>!y7p!&!I~78!FJ`Uom}HKl< zDd(W^LKjj32gVx=Ti}-TK@w+eHd-|X2Q%uzwK`})Q2qdg9ntQd7&M3BKo}?frY}h? zny;Xg4)dxJGiVX$6kW{bRA4IED=sp0<+BZ-(jo^ykv+3u zu|`4lx)0_l2yXCHl2OYnnH22~MDG`~65+Yx?m+=oqq5fh5Ee_6R9alN>n%=F7ESO( z+X9i08YH5PKxxfG%)e~K7dbKF)x30yCPu`Os(r0Oaq%G7h8h7RdqylsHavLvhPrB6 zXf`&$%2^G03B;jD8jYYW4gdJcpEjyGAGHr_xN9Hy+FqjHuAr?L)XO)sfsW!OOZsLc zTu|+wier*+y1oA7w1d8N0fGq1#$6t|*HgDaz<2WiHr?W+cU{a$;)G*WCJ2wR3?fr0 zTlWcuE-U8nm`OH6uLaA>3TOxv0S8(|qRAXAyaN3RG7n)k9ob(qZ9Hw5e*N4Fd}_ zPUW)eLBkiC;Y=R`M)-ik&k>eDt>vowYDV+wY&jIPVLf>CLJMz16=Y*x>|hYocjHpb zilRD)r?Yf`7R*3V`vbBU$fVa&q`+IaB@R;U4iwmpw5(lEQ2f5o_4{mh3GDps@5^5K zGx+^XFw5m(wF=H{$k0@NUxq#>xO9CXGiNPkH)uc@>`+S4vExp=qGRXRH@jY6s{QLs zXgr}U9xPCA*ny{T(pF7WX+%$epJ&uSgv~(hYki0fBlLh6OAia8b_bW)EoA;DNVI>E)ZWRl0?%6 z>p0`#kOjG?`yr{ff^frjkQow z-e}WeLkPxdYjv2cj6#oF=w)9J+ac(yAfjAV=kwI7mRai1Chln(A`kr%-hZ_{lkPPd z;AJ@D4%QqLT%oexFn|k`Ld_J@lqnbSWF$p&1A5Q1>9oTQwximJMAX3c0o?Bd&8-q* zhB{AfTQ+z{9c3!oQUkmU2wt0uO*ElNdK4TuhvgNcOvk1ZOdw@&Y0IkxblCAZMWdi@ zoG!h&rs!i+hsd&nM^Qq?cIrXT|5nGp7mGcU*okEwr%{d04m^9BRl|%JOANe&w9}zCnWm%P6a=eI0Xklwf@mP?9cUXR zNy?0g&cP-}1@6f<#|<+Ul)p1TmcyYVsiwB&+HaWR%0;l|>a??CpVtH6t{7Rs*& z5Yjv#T0nY8Y?Ag0$|;(Q(~KDCNxut4v{vH)18 z^L$SfRFji6x3SL(%%=j+cq*TYk~#`J(wwc#mltU`u^!DEyH%pcu!qGK5a z-4d3w;q^N>=NYC=OLBPLfI0^!YSIEYgA`KF1STQ_l|PPP+j(zfDf^2FcOC(Jlx)iu zW^tgQkh>=%6w2Ea9nSIiXt9^I=Hq67WDFrTWD__4rE-v-HRC{E$V*0_^*})*YfYh! ztkqte6;bP1jmcRjg1gU_ynrJlvA~O{KP57aXxPa@g=fS4IcE?P8op?Q+LpzGL zyK{2gL{Y$9wvvo$wz+tMjtl;$6J~VR3yn`GVFu@t;AFNtVY9NTE?tBP9pC^qTc?nA6kWx|5n3y?tQ0NlTx(g5#{7J4SprjJ z2C@)|&$Q7wZg(PUK`8BF?)md^5Cs6rqxqKWGmmVMa?Pun@+nkEyq;I%54={+HH!_o zT-Ck(F5eHCRzZ+5To{%Im{kmVR!-WCO?a9Lq1{b|yjk6YRO2y#RH)GPCw9Dk!Kh~3 zA+u$9J|{=~m^`~pX(u5&K{qjq?I18YBAv~*=wrs*m4}IVZUHU7Gw5+xY*z5EbT?eR zn5YPkpbiyW%mbXnnK0~Q;h2Zi7<||zsE6m`oO?^GS$*8|O#gi5$biS%r;s#_mJTx4 zW|N&CPs%nFq_gM{J$G9Xu#j(cEMo2+4$Vs+z-ahT;Xh-t+Ey;U;t-hXqm4gv zHb@%A>np$es(*I%TR}Ft+x5w^J=nnhkz2yhk;BSl%Yg@7HEfgfF>g7cNmC}V6{`vK zjqqu?Vx2jN#E6LthbHj6W(x<;Du&@P{6?SJ4fjd@{C!aLp_t} z(kf4H;?C5%dsvrAkouBY*WL96YK(Y$F}L@?X-Nk30QWFjhJ=69+O2zO zVaa>{WT(t%o1$rNP{4y(ENVII{c-v&RZ@j%HRd+3`c z%?_$fMGJb#De~LoM2sc}a4A^%%$(aSxcVz<#*uE{Js#sJLWfg{HK2h0U6V}@L>nl= zC-a<#tGI}CkMhxL-a^ikBiT08C({nA7X;$EA{OeH#)d_$!q6ccj$|omNEj77&kvW0 z(syewi%FwnmcR+gd9ImCb6-q|ZJP>N*4*rJ8JM`vSnHVecw&MadfJkZn?0f@PYTI8 zfZfwI5$v(l^a6CF8BE|l0-H9n&4R}OT>uifW)OyJGo0t$i8x_o^b7mF6?~0!guMs{ z>*qsv(+tTulPF_219Zk{rj7IiZ7=rTgstP%?mVMz0B@Cw1P57z8TE9%SdR=kgKMNBHYv@+lWdimV>^dR_2sbv}J{7m9@sD zt5&U}1WkxG0HA3UAw-9zeFv7$XR_UHQUn%o((MSRq zH*x~7_HspXSVIy^hQ=(omrh_~rtF|3*KsP80!g_E95`F(wIszH3OTIT#0`#E9y*jJCP2@tRTJa z-Yb^iUY)}P$yS~OY$S&5{}NS z?U_f1ZL=yQig`ZMgXz9jhJkA(AZj-8?x&{N#w`9xbDCh*x}#!1Hr*%Q{O z$e~f9ko}CDkSry&9ul#MNK5t}iYt)m*z`CCF$+tezCJ#AZTMg{nsl*7g8|1x z0yCt|+x2#rC~M%~KhfWDE8&5v({WO#5*7@#&J-FJJtU8C&+tdVBvPK8Nl7 z!{5CjUU}Syn8nW*oF5o&NsFGg}d|h zKDj+v@Aoja^~l`~woz2ZX3bhsR!iU z;6K1WuMgyFL+JhMIG+Fd-+dVWfB*Uw@6SK%{o_x5>!XiutT_C5D2$fs;NzR$cL3B& zu7~nGNZb!^O5ZwpKkPIbHx9_TKWsc_KfU?rqaQuHKhUqUiHCE-?e%W(pZ=5+dhuN+ zPH}x+dcWiS74LWJ@qTuD5hwpmeU9%2_4(Zm`Qtghdp*aU?c$o@LC5Ecf;?!KleVE zzwO?9%ccCgx5M>6z3Ec^=GzA1{@CCCp;wRi|M*!S@h{@?+#lHW_gDA-Pk%Q1|K5vd zkN3pOhh4t%DyGZ*7~fy7C-=)Q)pyeUf#3e|u$k**efHt~D*7|J*4XLYee8Yj#qA%j z9>H(?Opf5yXUpsBsf_jXdV}6R&)&G+{Q7mhu_NnEtIeC=eD%bhE&6H#$Zds7Wu~WUGJmBPOmF>WZECz z*hY5w=oEj1L%6B8iIpwQ%@da8dUMwGwP!|T94;AlaEjwYc7t!<9qaR(4?eg(#1B5e zH}Qqrck!BixPJG;8{-B=jPPa`r)gZ;xD06=-q-&4_{lIu#aDO_PCMj8v6QY zg8%$G*D(AVD!%yc?R|c~2;cwtuvR>N;N4*I+TLCbub-}B!QaC^Ui_ucpWfF{`9H&l zu+;s%dO5jW>h6y<-{DMt>!&UOk7xQtKK!M}3)#dq6Tq?j)vvqQJUP^_zpbxxCV%;1 z#rf>2_v9eo`ms0dfBO(_-rqxaImZ2;Z@i_BU-*`)1M$sU?v}s#r)HskGKznS4(d(U z?5(TCc2ja~cSym`w5@yX?Q`{&*?LXT(mD-Vy=`?d1PD-YxI z;>nBH-rxSlPVv*9>7)F~82yZQ^!7pi?rlVIKf?EaJ`V5wE7;6`@{Nt{AN)zjFHeU5 zPySfmbcMe5Lh-PeJWi{|cZw*lv$uK4ir{{B;WcyG8PetH7?B&vIo zz&;eEbmkY{c}GLg?ZkBgP{-SMq4r&Df0KD}ncd(=od7_e;ln!kuM;Gsb~mMQK{UU& z>lCTZ0}zxWIlN7jZpJpMZ}^gBLm}EmrgqJ=GE_kCQp(6Y-i)`ige+cr|)Qh&WZlgE7G|Nb*LfKS%SKa;1A$@q_7 zTMfTr{Pj;>+sx;ubN8|LA3tVl_s4L})IRL*;q@>Uo}b#+ z{oVgENFk9CV+%Nj>uXPs08#RFo$FnfQtf&7dA*eu*I_@rX|Y@bKRK#d|707VJ{tA;t{K3nA=bu^cT>rZbB7S}y9`1y1_c}aG z;%k2RYahM6v|RVqg8vg!D)`6vfyE{Gw=kJ7h5sVHSa;SQo2IX>Nx}bx&wr+a`#>lm7nC`+w`n z{EWK(b+;bXzu&Gb_n-OP17;g9U;N5-;Jj0Kc&Y!RUwr4CPb|Oq(X&skjmVqKM3L6| z(RG=4USAC~heO1CyV$zioKi$$AIH(*@=@%3RJY-8{`$j$QrLA|WgI>-4!#?Gd=vVX zb+CW$`uXmk6U3Xw-5`8|lfLWGes=rUPuGKvZ=gSmA9ur1|NVF~zW&a` zz4`hZuimP!zx&x6_wf_>ExjH(4&v_EKe=AC+atnRJUz6=;}`2=w|;cJ@$ur_N#DMB zcPqdC@^vn}{$f2B9$&+6cl$4$KRWRR>MU8l|C7r(-eF_Rv@|G7JEy}skenfLhZ z+r8gS!_T~Y`wV{l<$5|kzJ}l4eBu<|dF90K=I-NHZ+Ct>k6(ZFbB3IK!J`j>iwe-2{E_*o-{exZKY+#!aZJTHFt;d$}e^X6@cq5Fr-O_9|m{{KCj&+ub6dDO_oxI{*>w^z& zJA?=0gx2M?WV%DcvR+W@&(>{DBfX}u_15pA)W^+U^V-{-+e0(fKra))CUVlkfTRcd ze)YfCY#fbM3+eEE3-P-7>rrRd?_@}vkuMuKC@dlmt;+gKI1oUdQoN6J{&a)SM97|R zlla}6n>J=d~V>KcIU82HLfl!rST-N0+G z4`Tkc<#_T^+kT~Iihw&9NPW`pb zygJ*SHW2SK&j0-%Jp^_4$8gO!fBj82`IB>c^ZRc>qq%3UsIl({+IdIo6hj9(my%*pAf{WOb z1N*{XdDBrn7RH~pkZL&W_ntPD9`DMhAA2|W_r9@<(!H)pUuPwLG9=%?#@;Yk!QcI* z$E@zfFVzeG{mi}n<8hSk-h4OskG{+R1^+E}fSmI4mY?r@c=O~W>%V^LQT~gsK9=r} z_w|<_kNov_u!leTCePu|U9a<#)3|%#r=H1Qc;#7oe;3+W_wsPruGPukeEt=ylfQv4 ze&y=qKluy4dJl4Y_ij6XLe)wBwmNxRoqH?`eYqOteQok?D|M>^zkb1TV_m7duTb7@ z;Qp^KxPiJ}d0#U5%2i9;m$y5|&#zy*{HMS8^V(&W{h6y>-j^z0sixh(__MBG-j^$1 z+4=p8Uw!9atcH0v|4`U_W%u{fQV?D*8~#ixnV7h*AHm&Retq}&Im9-cx(JEV*Il>mTJQpW;#AWlP}8dGUtm_;L3Xah zI#2l?0P&LUTm8=uvHANCLFK1ExF4S{^x228yT*TifH8X;@#%BB(?59_?E8%I)!}|?cly`< z+QYb4ciZ{4;=fm#(=Yz^laTKr{(0K_efH20eDe17*Si(`*{hAgC!e}&5;f+-nvOm7LB_qAe9=q&M*x}!5Z|KR@diij*Uc1_F>kZvs;%{X= zeZGFBe*gi?nig0mZZ#+AquhI0r@fXsCWM9<_+*E8P6COousGusN1{nHI$SV$NM*Y=+&G2 z2^8uH+Uah4pS|60F;CnRgwyRuU%@&3@JVj{{PwE7{|fNw@dRsp9hh;*vt>U44GjtP zTQlmPkI(0g&%<4OeHQ$E+`?b!S@1tR-1}eQSrnD$2Y^gCef~qw5CXYe1l*M zeNU|BcQ^12$gf@u(rAWWWs=%JE~7VHw^FVY&RyMS4bi{8;yQ;bHG}jOr5Vgjh|Gbp`-S~>MXguw+u!P+pM#9!UIUt)(B1ht(Cp{Mnr{|C9fBY>Q&|S*FFdK_9nm|zWQZgZ{Mm=)|24lA3g*hUm~@+ zk66Bq)J8wy`FUk?)!?fbC838b2DPBNic}YnYGzekEqWDB2D8K~lL`Rf6YyFw@NN+x zz<_b3AaQ+o6Vxx;a$z*wg zsO2jEaK3p~bF&`BHR@gdPP6gXPIxK1Y5&eO0s_kGbnj|n>W#u5&X9I{HDwB26Vvv=-gKYQEvUU&))b?&f`t* zzF}X%KX~^Ep6A))#JR6kJbmfa437CSS3CG)?B^{P{6GBXZk|32#*2Ucj{OZc!cQ+V zKbfmvuY~mC|Gh&vV_8qGIzv(N?Czy6&EboZ=PB0lID8K1u=Rek(fGl$|Btzpn zvc$@$j&XqMy6XccjC-?~dH8;%D=$Dve2Ah*ilq1|6w-W3q)1BQOC-M`oBjjC9rp|v z@K?CyUva}tPf2I(b$=P&+~T8AD@@~&GQOCdvYlM9X#~gpt$_6VLL2P zVt-8YU!J<* zCH@ORLM!Q?xYwIgaQ|1^8HU5z*WED;+WC4j1_!JLz68|ad6wdSdew&x!r%))i+GNN zH+r^%q*)q+J3e~|(yuyzE3!EC`+&ZG^u<-{-$2;b%Uie%!h*W8~F3{3SX+E5BR!Y{g5Gel38`d&$+W z`Oo)!iP`T8KBVqv0i=H1zTXVlcQZbu^k?0V{I|^hnh&iY=%)z(LBU(1e=T@^^QV0O z%!kyETSr65?*Kj+wJ&|}S@+}9zO}>Ge30BPUGX&^TK!fXUkg4I$!9*Ke%v?)O1?A> z&UpaE^I7-TFZ-c~zAN}pOJ56K0}qtc_xYeGKxKXAL+Zz^W1-}Ct$PlamyY|a{PAVq z8t-fVQysk&;13Gk`tSz@Z}s?D0I46h?-@}1wSDwUpMF;UwfnGN-s<&h0eq{Mvi+J5 zZ~E4~Ukg4o@n=4ye%!q0==^>2Kq9|X_h;pA&3kL|uLU1^{cHX=HUG5$hRI9mf96B# z)jat99|M4Xal3u*)r4Tsw^#EY|L3Pk3LS>CU{_-A4G*AS!T2NC=N<;nG8l1i;OA>w z0{9E;AdY072Hneafpg_Z{-<9VCpny1*)vb;6@EZ&F+7~w^Knz2frHYx*G->gI0s|p zz1IOu1Mr_R?8i-c7?3>i^``%vj>SLUO#hjL*MzpeOl}-!De`Ti5@2Y*4MK)wiI=$v zW+e|y>zA1hXT5=){xV!CjwfDq;3R9FheZJNIN09U>y8*hV+8Z;G?23x&vNhQa6HMp zOmdRKKzBV$8PG{jbMraPL3xtTu7x|{7>~Vca|A&{`SY`2B=x=zkMm&eKTT8`W8Pnt z_=SOm!?Oa#IiB~xs%11I#8~=r)Nf<}Z zI&icUMZVt_ds^{tGaaLN>Ukvr?Oka5x9G;fW+Hg-kkc;ehY~)BpJv#PcPePlOJH-g>6+=QrhlZ>ImB5HD6KkknuEU*iho_V@X3DgJ#vXaYyO9} z_&y(GGU$%ad`SJcZ9lNg-@4|r?nl49HP6?4Sc<*$(D(Uot@M5VTStB7L+ZzE`_3+Z z&V{E=`>gwJ+lPkxn*X8izUF^uzwh(ky6`g}Qa^6ncQ*Nl?)Pb@;^XJp#z4x8|pv)^)JuQ|Hta__poLF7JhMho~rft z@IrsXJUw*J2f+@p1mA} z{~JuQKg&`0zkZvYe}<#5mA*~X|K->F{J-xgdum0jFgd@EEc@T)#^aK;|H|X&BPw%PvHTN}Zzh=H?@OQb-$^4lK zsSi{0FYd#?xDQ|Q{=XCTo(&%gYepRs3r0sjnpkG`Fi`N#g+!CQ-#`ES6Fl)_ ze|c~OVGzvF{B85R+4JYasrlmUec0sxFlNW&t>YFA1PhJE*ske;}zyGO= zUVhi^?>^f2M_AL=5D?nV5NH91!~WgR6bGLNcG&H+?kDJ??AI;K;g+8-{JWLLx5j_A z@O|xbvGF=6{@EIsI?tc~m?Sg|@SWc{n<4!%bbjMzekI>N=GO(lk$XCrfphz826*Y- zPUTnG+oSx>eYulgxo=NzTOKkUGR-!AC-Y3i9emhP)2a@ zO3-&tT@H+qC%X}nBu4;^=5+zZkQ{^m#J-;lHGpaf&YV{nL$et5eg<3vl*d0^dI7(s8X~X zZZK@yf5@gRfjA%Zk!2T>`Uj5r2jZ7obNU~;-)wC0?>Ro=AOD+w^XswNPpk;WE{08T zKKnaZ3IAD`vhGjdzb$H*FX;2W{{Qa(7yqJgSBCY#cJk>ez>jVp&*Jd}spSIyDfC(h z;P<)+^R);G!SF4~Q!FPYLM$buIXtZNz_%W;%ww@!60i} zqU;%M=KJ4XtJVA*&S((iJN|j^wZGbW{vJ~N8U8bagM2la^d<=KXt5Fxu0=J*lBVQ2 znc{}xGM&Uiforx1u*W%MvU56(->x94&lFjX0 zZ}v%?CN*MfyS{Z z+g+gWef?@Jcg5OLzFohyAKTkD`MCeV+N_H*J}Ay9y|YIglQ7}1!@Wy*3aq2PG3f1u zzi=*cL$*euj9xj>4(d471a!K8jUiDyG&8h2M6?vi)Mcl|0A55ZRSjrB;? zfrw7(q>iU}*6P(cvgnUKfZw7NikD))Jr%<1-=R8Lc0irh+wJ?GEJ^C7{%yaxm+bKE z`qO#kS?ad@cD<+u;;}Y9`}KUb>;wIA|I_P{%H`Yj+wH-<*!K3@w>hu9m86!xw&z(d zI36!X@N0XZUFVhCUpL(YgE2MGL(`DV`q8O@N#HW3 zvT3y3kSL`r;YfDHahIAD>+$G9QR&%PaD0P?1DTNJ!ZJCz(6oKq+1KkN-*t)({c1FQ zFDY3xU%4{m`ZMPzLzXR(F4|->EppU*`EiQ9xid{g@C5}$k!c@nR^ke6?Qh=~Q_!{6 zHQ}hE>lKf1HN~0)l76D_>U11#?mY!*3ezv)7$HD5` znBZ$9w|lKx*yh4g>c==bw1PIwPSa7ia^JBdXO3*!-vWF{E+JpfE(-ll9|c3j4PI&a zDCC#f_WY|GwR`KXqeh=QsM+_#_{j7Jrt1ewv2fkFP{W9lJ8(tTmIcwtK{LW^-EK4hX-#Qr#}u@{ESecC&3Zmj)x^=)tybs2?ud zV;PYBpcD3jbEsw$yo;MV+_-06?5qM~ox}DYk?HqDN3^azvJAeU6WR15hu98^MeQc; zQUCI*tlEoaqlJ;ScE_zUc7j%Ry?4ftgEF`oqIQUIND*thvlz3c#nM`&nO+ye*jz20 zN4R>oD-MrGthbYL9IS_-ude!9qhZj$Wu?gOXs;BGqs?4~l{gvJx!6;Byvv!LcBt`3 zqY$y)NDP7?~YP=QWzg(c{;`L?UnnWpzTIM8Kty(G%!qA zLCd8;rD~L{x`N&FqRf48PG8%PGvJsnxAE>Ml^=BHVc=p?NXp;poX2V79NQtQ`gW|+ULD-TmYsw; zZOB;*e}7M`ipVmG?k(-a>#$jh<28^HAwxoXo1A_fn}T&d8Rsi;NjHf7lwk#CBzB-a zqKAdzo8Ricy|4*9?0(&mn90eEBYQ?>*UPTluZa7NzY09DIwfVvXE0n=t#${{pK9?4m{$CMGr z!!+oSpluqKv7%jheJB*K8!l=bM|9?|muW7sq_l4dKP}F&7(Q&G!>Mv^ofM&9KkhHm z0XqG-+AR`g^{11`H-^n|Nf2vN@i?uAaa`?$mPL_zgddt;ogTrI8s!0PmiB7KY07gC z*fj`K6LD2`ljES}3-urT*=yfAfP1fRB+l1JkxBqTWN@m@ zQW{951pR?Dvha}c`$88Z%F(m8D^BcO!IEpaB>9+R)|PSiwX@UD6U*Gvol;&Y107r6 zWYuPwnYn9rfsSx%6UFrPhwUTh8b!35V|&<_Oy>$3HYvV|1eJ5=BxJ(w+>P9wtt-E} zk3OPmw@j08p1TCQwQvv3hG+748ZoU!x!o9dL~_)1e9>~0UAC9Zs6e}qtUR4UlxGEL z7={Z0#ucGjpr+R~g63gc6+G(r%|0ekcFpX{04>d&XHT`4W}&%Ig}-2!-@Wv%(y-Ja ziS}~RYuZefla={LSGAW7*dEqNNRTL5C>}*Of^dtD)pPunsJY+I$eavECDsSR@@w;U z?D8ACn;Y5J$YBe5t+1xNRhfKqSH(2jE$CC)< zxA0Pq?a{YYY;~t{eI+^KDJ7WEA4Y9=$Ig4luyNp5o{=oesk~_#Lb=S6$RWncl$~@i z4H)N3aN9-A9<;i1(#s%PGf1|fTDOHq$9cN+QD5^l9?cnw@K}z?cRtJRI6l(_9^Fh# zZr$9BLz;Jd53grhj4-bR<0eqrmPJ-RiZT*R--X03sttLJp4xsz?+)0WH&J#nleQ%IF~+hUx5T`?N7MkOjI~#^i>O<7c1rNA zE$=b}3@>W4n@epUmgbGI;|j5Lc_YfUYP9!zak|dypjJWuovzy?Jlqmrdh9R5p?KB@ zJwKB&MINZcyQr&&zOMCcak*XKDAxm<5Z4%$rb{3XrxEn2UO1!Bh#ms#G?!h(+O838 zt&=iV9gGuxJWi>urIu)i0{>W0REy7>S+_c4vsu_JSW4)^b>qm*V?KJVUlQXrl6hy| z)7+w&SDrkhw44m#Wr@70V|lm5)7-y=&c!(j#TL+FFbL{LJuj_tA zAldtN2h^MOGQ)S5-bj}W){Vm@4tqPNF4T#9q?~-{ z7PY(D6}=%N84Wg9eH+-TiW8Qo5yNgV_iUOq!+CTOr;+zQejnYaQRk#M4cfrs5mwmc z`jEm*N=T`6qJ0!uV|Hs;;tcahwYNpl#bVl{qv%t!(_3iUvpjzmlN=2Vn-MnRG^b}> z49|Pfwi_H3tO?;u-n_ZDT`+Zl?8CYxvuFg7@(X<+*AyxpVC=1|OHd0UtSS73=fgC~ za}TGDqfWIXN!}y856P`TQLn%&`UGCl_R z(UDrUq69LMc$z-=1vTx3mu+*`m6A|s?oQuh8R0nV=H1CGB2P!(7bp92t4XrD8ril( zUTfBZ;dy0iivalG4gz*ZQB^o=tR{pzapqacaGG6ki>j_~9A+&Bx|^a0d`z)}YVR%+ zjZcErSmwbzdA5CvEAoUmye>b2M5p+^YH9~(^^=h2Am#ZvnpR(wIoH3(Y#fPz-CX|P?IhX0 z=D@%N@p>xc&E`BFIRu&P;(9gqHJfB6i{03#+`OP(+!LErvG(r7^YO9se03=&&6ce? zbkv^EKwYDD$c!N)t*2~C45ffAAvNj9s?{PkYYjUG7xtk}(s*hSDdA?^+r$Ugtfi#v zZuERF#0EpV83yqln@0bZjB`M@EJ?^Wp5soSE3KQ#onpt#^W-`o_|cM$Cw9bdqc3>X znoPC?-H+E)S1taoPsXgxfoz%=!HljsdL-to@nP{zlK#Qbc^o?etZ=q}UE3AH-d^E4 zLR_v0R?teAFgxbqG#a%>uuvpYh$+dVHWpjj?atWE|T7)YOt$rXQxQ>_&d zb7iUb4$=$*xfJTsP73NS@~lk->~Gf_hwJ%4M0il(v{Kz3g0&Bft=%-qO*tvz{SR(8eJGsS$c(2y}#ynm5->f^p?o_ITb&Fj!NK=1Up9*Y|8ij+C z8IQwbgK18oso&Pn+rvq1n$Fwa@(CfXD{KYGjY?wzan&tx#a7LO=@T2fzOb@GTUcSx z_LW3*El%qv+gLMKH?gkHQ5>oPAh<(l`|4TqFHXf^Fgh{Fw%0Phxn57Ou0VwP1Mg&Z zCcg=Csx!~dTwPlO?+grJ0V<`Yo>81)cPUTBhB_A$d*7g(c4dhDX>+VEg}o+d;ZAX8 zyieCB@jRo(97R)ffTJwslWyKZ1I-rI>=Qa#&jN_0Rsae#phRq&y+O9a{xyAk@62r279tpUQV7~*h6&a`e0`kQ#9qQeBkml zW!6)%%E@sL20#ywDlktt4C_P*FJ2TQvzQ0oiCSMJ4X~m-Ijz~XVyv_C;fb9(0(SRJ z!Cj?(;yvv=qa;zTQ?P@eZ$$1%YTDlY-((f0~j}C7kT#48Z z1f6l*ySlK>&LOIOyEU5KovK4nY7M)jBztnNJwUC*+kAbvL-y*ju! zvTKuCBSwa44rJ?y4}L}E%A9XE>_dBSnK@bL&Ar2L-CtRaD^O8Vo8yg7IGxz<(krsz zsVlM?HtAs=U=3OXO$kmf67yGUi6ivEI4U`%BrA6Bkddy+RIguFtZQ7?Yutx}QsY!um8AtsGgvZG zu+Y_lFuzRVoY3apk`C+Mz2NJ^*@m?SY-N*bw+38pNnO2*XH>6%nTwnh zyKbi|YKTmCf(HB`N{ID5C>uN99_meQZjlNJ)02*uA%ra(wRQ3PhE-3IesblSa%egS z8GN{*ntz2$756e9B*Bs&E8D63;^ZhR>|mh}^$@6qrXq9Qz=hnN;&MjyOeJGIB4(a#FLR`aypR0qL}i2jsOYsws~M!;fx zG;Ny$8xi4$_318m@@6I3Q!=O}gOoRfXUF^~6;uhB(AEL$L);&wDWC9a)FQ8M!}N~H z>BMmezFTKC7$i!PbYt&IAZH9&VR_BNFSpgh5+B!j;bL=v3N(4@`={<{Z+NzBUJ)#G_%F3A)MyDz|5!u22Ej zZ8b96=_c-M)n&7ep8D!W2!P?oC5O-jzXYuETpkFA7BKMDjz1M;Z4Q(fof!0#_J`GV z+wZrLf0Ft`b5E&jx{+fT=D7-3^^MQg3}DO~;qk)J*K8If8$BF2rGE^SKB#SEF?Jm<_U4-TyuyYwQIzZ|!*4@)ps^VW@8 zbjya?9WQ<^W*#Y>HMckcj2id{Qd^a_2DpFnt3PuC-+$3!Egyo~pF;fHrN=wFK7(mi z1hWbFq*!Q$zz67fj1|+<2Rdlh^wQYJ3)6NK*7N}AJtp%hw~MW};l+!pq<+^s2u~G< zklpfNA%p&DxRjPt-54%%F9Jg1MZ1BQuq2L-!hPdewUEOc4o>5U@`vN(GmLwZv+Z$p zqO644p=V#)E8YoQW@h19(@o1z%j^TL=*C5xxA?Ab1=H!Xff+VAL9=dO!-}b~Cvoqv zh3k=QcasgVsEmCt3KSuYO43#->u8u*=-a3c_xK5~Lz>Wz)*-s4jCj6m#AaT$dT5~* z*$Nv$bt4P<(6NeQKax>N3MYJUz-~ANYZM&uu-@wN^?t}T&jw`C2V?1c-Sfn0EI9T& zW6Cm9&327zx)YHR#&vwZ01)R4m37Z24Bg-&;$I@)UQ0pykY;dW$MzD#G{}g9E{tp0 z2rsbYuZSj5m1zAOuicQe>SeRLvdp#;CY9@ECvRTXmQD%PBy>E%?skrIt|-riYVJ>Km1x_*k0B=u@yelQ7*6`-rK1!%y&{`!J_A{7+IjB648LG=_PmryQfd@$@@5!O&!Y=d*=ou^nE&A zPP}tJ^4>X@fKRj3syIm@#^~~RbG6U~)3{%F?cATl$F9BvDMcVR7X>@(B0sEYJbB?l zkk!Pq+YDRQ<5O31V8JxLEp|QY%__(~bhW|lIB8PAbfw+3O|xaq5$A%+sCjf`&n5T{!Lx6yP8wQ-fOD?NVEdpe#H#)5D4Ru}I^odz zUgJlov!9o{nWar5S{E5$8AGS@DKw-7-099BG-|+BIBg!!y4|`iCk8PmpXOBAV++XR zcGt_Nb#HedIHzFQdT!Ff%7PB15z*-TmZ685=kKm{uWuK$cnl9(6_3Uu-!k<2pgnYd zZr8_FFaVrcho-u)C92T;LP=|Nb3xP-D+5OI!n?KbTsXIFrT1w^)8@vjI7$t3yRD*I9bTE!pVru?!G87Nv>S!gG^(f3$oL?V6K)WBu9P6d-{O}&xIZJB48JeZbXp6a^uz^56G zEifGLh=_SKqF@z@z{x6HCu~yGXR`<3DC)AOvY^bR4YxbG`k5TC4aOypv$xR-u~iEl z+~Y=mjN&u70Sa*iw#@VhYX^`)sytfC>V{su6?H$ z!`OdDT2t2!thGlUU1?YCiKXS0?|_O{Ca|fm;8T6t)HT@D8obQ* zaFK-U76#(9m4k5uUIHBTxD6*aHy5+6Te<*RA0uRQOx0jJ6QS`2d_HeSx6A&?gfYRQXqI~j_lFrYs$F z6c^)_dQ2bQ?nb9!%o2`!zw$RQ&0VX8X)-3wepPUQf~K2t0DpCeN~J%~5h-dmU&IP=jP0BdcOGTLBfRZ-^r$|c47C$5@puWqJHOIAQ^dV< zjM=tGISA4xDAohr>;nF&fcEZ)4}M!_=c7w;W0!eucC~XO4F8S-I}JfBvH_w8yMTRs z-`)HeIGf>ovnk!{Jq`hm+ytH3jj)#y2*Wf_ZKY=oV37g;?uHGSks%x&;qk(f2GThqTa=L@Cr%^>|uwBdN?BXk60ohZ`pKdKqvKw&m@VkYl9*3iU zO;fg=4*q-3(UhC3c!#kvNGc8GZ zeD%bi`6{H*8&_PI>#&@GE)khc>Q)ggTkx4PeUShme-P#2jN#N_!R6IR8<$kWVcBr% zVZ&jW4ig7&)IDbu8-DMV*s|}ClD>o(e$M;gGR`b*-P;jB0#qQ!>t-W%!Ls*gZYq+? z3IRV+(1O3jNzqdexJ0&wo{t?zT{&5S2d+;i=>b42)fp5yxwUr#ysYho+Uaym8cB2W zoASgcHvWKNAOJu%S3xFCU2G9kr)?8cdgwf0O?z;b;5)lfZ{`w4TkyffBrk0_4?2l5 z1N1@#`F-&x23ZeLV*?(CM}6qVb-HGE^>H{Z=TcBk!B`zz$qn|yl+gsIkgf%|K6Ule znLUq-f$be@3L@HHgVV896ST{=O}(6DCz7z^)1J`nvuuxtNQsSQ8T_OK)bp;hdkM=B z@E0$+IU>`=?BZpChMhUBW73IVi>H&wR{7!Th0)bOw+LUwV;1&15tHV}fxK?EfGgdq zhpV3|BQxqya4)KyCzWP^g>m<)js*@80t1jBZwRWc4^($)9H3yG?`ewGd>(_r_{6}H zCx$KIKvmStdQY5~7Q55yDYdb}one59s+h|whFEWpyXxp~a%^{gWGlSCuSrRZZ*0mR zuBb95B?l^umP*)o0>=^Z459_r++0W1v*8Rf+9~!ScA}KNHRuhOz?8a7CE(u|y$?GI zHEkTMQu!gktajGdWNUMSJ`bCc%*EicIoF3dpt^ank2$sLBa0JuH_xNZrNxd}z0%Ij zp-G=}bT5PGr6<`X$CYp92setb)L6H>nd`UC5!+mMUR8&YCym;&dMKG_MZ%K=>DDG|lP~4^;yw^Y*6eHNs0RtT zy54P2S}Hhm`KoPiys^Oz2w$4S5>R%6w$^qhw!1NTZ0{RoK2_Jz1SNcC`5i7Y%zjO3 zhJ!ID+!2v{Qk^3Qi!Cj)mn|~@C*iO<>MD2M0saBpb7vL#^d2u=U3&x2ri`w1uE&8@q4>A?pO5Y2hb+l2Sfl070_RH*?@g6h6xzwNJH zHpnSgNXtL2k2EQ_p1kue4q|XO6Um6nvEQ=55>G;-<`Aturbtpe|a z1OBub=rV?bNobyItPZklD17j@-~jQk&;G~^0~&s+s&0Z z*Tdi?%i)@sG!7g;r&287dg(I9y*RMqd227@d0CTKlb-fI3J${njCZ#~cb5(gkJT7l z7mVNCj_s-<*YnOg3&?E;)R1|A1(D{@*<;2lVSk9J=1idqcCmsO0EadyNpYAHyv^|J zfye453I{*8Xn%8S^LF+MgzhdjGC$Z_av3*0_LWZ#YYv{}X$g|f&bSM%=DZK5eu;fQ zj@BjWX?1#0j<yJahhQ3c_}rJ!!E2{V?%DtCr$@wpv!u$%Xsb1D|&`hQ(%qg)>1vdjr!2;jrIs9 zeNlkl_Vj;OjM;XBY18MOZ`}8JR@6YEJRZR>Od`1iT)n%IQDP8M!&`5kTNB|C?aG_}rkui>(kHW9M9DL`I9 zXNu_qHnwK^Tq@P&q>P?PSYcQL)6We6{v*#-vFF)R2iJxK?=XX}fHI5PX&l)!@M^d3 zvxCm4vmw!YuFAoE#yQt?3s&4dS01B#(u4yLb^xD3k2TPV?V9vl87;b0^JaUw3;rE1 z<1wTg73d{5sSuYLjp75z1y4+^sPaZHIv|TS@J;UlwoUfDp-r=y9MfoSs(RuEZ0N5- zp-U2QrUQa2)J@JyOuX%qr~g=j_@(($dSX&pw)Hq9RB{7e=*9pi)?%o}F=ba_1e5`x zk{&Co$n-4`WltjT2LK2#O3E)E?r9qrV0kJW>n4-hb+$)bwum;u(Ca8C8dn|~-YxSA zhZ*FV74NYMteAWC*j`>^s6a?FFb@=jfy?Vu@B)}9~3JDS=Y=x zRt8gOJ;+VPUGTewCyZS+Fuv}5<@Ri;Piit~3xF zi(b0@wgig899%^jKbTxVgA~e0@Fl}p7;L2lAcLdF)3UoVMV0 zT`o-)AE@lmt-wk)IRi;su#-j)K+3MePcvr@SKq$+^FAUCfvI0dmGu4Xy;@&>Gzk8PyjNX-%Ox z)0+rGdI2UQb>KI#%H-LE8<)`fhpb!x9AMzUzlRa)(k=yYZ@m4U#nd1etHy2Bd1-?@`jlOCX=m>m?)v7Xw zk(2}tBGY{L8Jn=40$8ZXiUO>gg1nK|vG(Xlh=Y=g4Kg2SnTL42A=YcG&|vI!AR;BE zfUw6^I*{RnyRM&Pz-uHm2)In{Jc9%8cMGJS)9S>@0)db z0T`AH?rvXh=cnC>qYE*>B4aI*Y@7HT1$Li&H5M9ONgzU0T?|;>BrDkqyM`Q(ZZ-)ZpuBE8tsPLvg_7T%6cd#Pa?1oj zMlI5Yb$P}eP%eeuSO(F&Gx%=Ra!UYDIa8*_BoivCoC(z-KGS8jcI>z_+q-aL&&~o~ zqtKwdigPalSd7b4bp#3IG9gA>Z@6U=t;zFt%un}!^jjtbpJD50G0x=*D z`x*nL3~*(nhCDt_(2H5JUCr&SC)fUx^ln7&9BjyEk#9(mZtpm_+Eyjq%LiPUqF%VH zVO`YAK8GB8oz-u{*}VF@{e|#C-1BoTVOCXgyVC4Ne5CLx>YzwHtt3$P03_*x zLuHT3kdcgc2h1`Eo;;-UL^F30HGw1%+J}4A`VUU&s%AaI)ebvAh%L{c=!y+v3e6y~ z+axh71&MP{)pgcTO{gs@j~Wn%8)wZ_8_c-lMg`Vthq?g@7o|R24g4NH>})v=0h*QpGFDt-1*P1_4{jgQ=${m7BdtU)2 z12)NRe{al|@AvkOmL-rG%_pCb3qW@XNURh5WxiQA)QrfH$d&T4gZ14#7tCcyS$@^> zFwrs>Oz4HaKLn23uTnvW=Ydrrm#&;8WHsY_MR9?S1E!mBurmd@QNedaqyAnEF?Kf0 zH8pwa_{j4vE&<0>W;JVjazhn+W&@~~f;&fi~O_0DF35^u$SIwSiFQNgUXU zR7OJYB_m%siE>W>#%MNv?6EF*FrR_P=*+D-^)5HqqgYH4+@=qqVE1)mJ~3v%`Y+jy z%Tx=E9uPz7$i$u4ubWDF_VaPr0dcPl`S!jh>N_g!=q6mzdskMku(5>*K?2N}=KThI zHCy0wjd$QxFXs*5`qY9Sa?{jx7#AUMJm?v)=zmXqGR;d0idm6YUIq1Ls1O!SDYszA zGuV@VIX{98LXrUJR>e%$&-gTog>Ooci+aUZj4`E{&H;6lY7*G&f5(8;LB*kc#cikd z!IwF1+IbxVb#61GLw+M?{Bjk<(=w63LP!gZ?^bdyZcg_qxJd_w6)0bR+`S-<`(`te z8S=P7oba{;7-|CDj9&ZAInMl8*-gN4IAoj}?fi{4$Pr)>U~DWWyOI@-a98=BHi^WG zxYp;6a9jg_;?pM|xHfgSjNMq)*K-9{{|$U`m9vXnWE_1l2cQCI5B+qHjqU!34hzNo z-!z@avZGkHgdd23@Md`AKzJcQ5;Lp>!W&_p{-)~hJE-XB=;|^u?6p^Be)-y;4#?S+ z*yb}LUP?%+mrsoS8iXJA_wV?@b1o^!-|Xhwq&ZCPOx&kOC;1ohdj>tAqh47~($33u zzHTc8&oO0v+ur#ErY%clI(Vfr_@0oRlHJ4m^!Y3H_&gS2R6IK^Zk~up)n z#JkMxFXskoC+0=yUWp@QzP1!@_TjB@rUUs#Q~PioA5Vo9*J3(i-`#!|{+5VE5b>9) z(-~H=B;Q-Oygs$9P{Zf^CQcJx?;2{A^7A`?ZE2TV2l_5WFGwHEO1HerjHZ^us91AW zEYk$;$n}PMWof%bJe$|;xSEDA=;B8z&msAQ!xzkA@6JTdswC-MZpTgHF9`@}}c)wK0*5oAwB z8FV=FEK>aQQn?oG4lt3ww=m^xV#r+ zygNdLHRlUw)+6`5Y<1_c+vlh4+sNs;pHa67nH)B&^xx7BW;y$v-A<4CkCUssz2oja z&q9MJ;dblDdMVc6tvl__4vwX@+nv^=Q^>#|ySa6}TA{J6aB2rZDpZ-i?v<$D*E}Ui) z+kRTYgm>svr@Q}m9Y7}FSeW$-0_KzUh-S}!gKIJS?YCM1M=MP!@4m3(>NA40O zr&YbcNPYZUlh<3duH)(Tw&gh&RO1%H0gos{B{k!{xt%(-iR9U?x+Y>ABN!z-b--_U z?)MMkX(cQ254cZZB?!0a&EiNW$1_5FFU5>x)$@kd4~+lR&g^jl$qr^EgwR{8n!ZL}TY9zhFw{p!sjsN&4;}kw<5bwt`lO zckkJDA)(JIDhCd!YoYcBph4(^T7Vt0q_JYHZtW{CUcgEU&ktp#(!nQBw z7PI$1JMsiE3lsIP9Fo)1suJBX+z*11%t-~|!H(5{)(+X6>%}g+=Q6b1REZ)fo9EYe zhikI^KAQ_2ZeAI2iWG4*FBkEeoK6lda+d>EEbmW|eN>UIW|D3NL5BgEYmHU<qUFrVu9gEF0^e@}T!E zJ7kv=&54JAo>s@!7mn3Q+*|~5G!R1~p7bX@oGw_+E!;ZD?#yG!G${4OKRg4LEc~u- z2+QAVanRn=)!K9qo}|B&A4zj3PPpb((LTJ-cCwH6%w;PDi4ZD2OtVJc&$3h_9e1tN zFP{1^)jK1`jr80c?$sZkn00J?$^%n$-Gf+vUR0++_&Wot2KScwg#f=#_-0&Vto_Y&2-U6c!aZ9mjRzdIbD z{qS`;tdvDg{pOk?yA%YD95;R0pU*z0|Kh=k_y=bd)k7LGF9<>vOA%4VCZobt`#bI3 zJ{4qE!Tyb_U4|mKJN?@U$CP3zNBOLID~V?ZOqbPustqinAJHsLqxo8SO=jb7^LE+^ zSspAk)M2ZtGb_3ImHRqw^Ab+iw4D>vbzx^n$L^jj$LMjt$=hmbxGj;yli4p+)8=jv z)D>UcF_Unv(xvt~+~RT0O})ox*}Sfwv5SRl!8Or*MkaUAFL2z~<;+~bckws^M|aH4 z;bfJA1XUOjUTD|!Zi2ifD(^S5XP_YREs;zq#!a&$t}Jz|beHRtd*ul`buV>s;UcBV zKQu%oaHqi+@>q!S6x7E)?RVsrXo!(;_S9RF%U)a>pi`PT43zXM+Q7Ql0}=qb9~)1rH&l}O;k5I zKOtZAdtTfm+L1VSln-k0#@Rc~Pr)5=BR_Ca$2{9Yq%ZDd{j?>1j0jvcmj8JJha|K1 zl#;Fw)4WeOi?;6HXZ{Uma7#5LdnL9jtfKJ@2u(MaJ>oZnpFFhk7DBt2o?7#Uz$KCL z>2rYnJcnkC&`}*t;190A4}n{u&?d2 zYxBc?uOdXD;!gDr_S?w0&Z8F}>3v*_M`-ELT*?QKU0YFM)x=A=TiM;r^cZ61v5a9C zJGBP;)=!MB?N=41n5! z{S~qG-Gv|cvMo&8SSyV*S+3H)A$oq7#BK6)YNnZ#PweY(p-@W&x7JD&R{n{Z-$Rby zhDX!)gtXg}yP9aQ3jKq-?O_N&YoxXN2Q0}BA)|+!e-JXlvkMP%qWVh3==GG%Lcg#VZ$Reyzrzxvaj=B9^q{^ZA<+FNahnvWz+)L# zb-K@0_p&17%~|@zF=~;Nb}G31+q$>`^?RM3HO&r54y^;PC4ffcBXunz zb2|5StG@Dd$&GruN5qNMtsU#^;jenD)icD?SpeuM^oL zBlVs~czT(2prz7?cV77W-u>PuS+Z1j!@W?290EGaGER$6Tnb>-inXu1;*^~tTw`@& z;fstmAL;Pvmzk`0@PM&(`<2g!5*Q<`Cq7iv?(zEQ6=}x&FuV4b^A?~_oDKAe2yq*@ zMsDReMMp4)qB-?w=eA>DCV7G*2;FkI><}Yz$o1oIThgRF#r}<#;Pfob>ePB{S4y<& z3T~y?0WZk+@1>5sWEV8~f3WO)4;^Ir90pEjEIuy3D=k;;F5vDf8J28rfqW#{ncc>PeJb1~x1r%N&m}cw z9;Q|+#&wWsX^xeO>bn4 zDVg6QX(6{9eKusJzI$tFarXr}mHzx`-A88Bspa1Cn!Bj7ld`SVCMP^5b?CiGac}AO z3I}eQTm!r>0#|6sBe%?$Vd{{kYdB;cU3VyQ41#+lk#{ovf?q15941CfuXXhJMN-)HCCIgas)nD;J_ZOjD&_ISpocSeZJ&xun~WwNXhpJIgnOUlG! zHwsiOHF24BwQLmeX?jWjvJZB#D9ihE2T?O_4|l%zaI|@nFq-EImi79H1n%dC-2$$P zcg9$8^n23dF`oOoM$>X9FUV7*`6=*=Yso9C2qS0#-{oJV3q6X)r4hpZkgs zqZ@^ED%@kI#+tQ1HRrAN07}aw#GsXu>?2;-(9XAAA+BcpcQpO>?i?P-%(~d-|CP_@ zZ$8gG{A6fBsr2=&^PRAyS2rwou>qGxMrwL(_FsU}7M>mt1c6n;FDobPS>;a)FOKy) zz2nxY&CKqa>ms|V>oaXC<)H)yXm={K>De{QS+27?a?$mf9>JnL*1~0JyXkXNUFV=N zMY$XvEocn&_2z!&kA)~n_T7$fv?Ds)*s#29=N3+}A(5u${b5VpzHBNnoryZ#eL4=G zj-*rpAx1Wv9vexKpW+f0z?j0(Ivr~GJWW#czr*3(zAt~SdPWp;JM3b&X~bQZ#QxHM zQ_FoEc#==*r_Rwv95{_=c6s+2R(=b=+|_1AqaWM%BBByuOk4vhc-fs~@=SvT>4Lwe%1`LOz;XoE z1(zOgs>K&}fyY^%8wbzxpb&%tgc>F}?goCnr zPorX{pg^W&*WT$Nb#6@2zd&!PkO1%ZPIh4jH5BvEHVJ`pyXf{5-!ayiQ$z960`ZB( zUFz5qOMq$a-Vf^WN?Z`G{9bslZeZpnuJeny1pl3-)A^TV1~@Oed0!*Z`-xf@hF_1M z6^LwM)WPMd?G8lIS3m9{|7q{6g-K>?k$)Boz4Se>flFcWu}Nvxh%dd`?~zdCIhsyf zRdg2N>sY0=|LoF>Bf-B<|FOwp_xDPA*(Gz8a1qRtvE$S;=n+wWTK?Sy*5`KQr3ArO_n}7v_&BiHmAB1TEkC}N?kmLQ zuc9N40ghMzQ%tOlId~iy)~IFQelC~jJ>A*qp~(nH-y4Y|Z7@9SZ2TKQ`Lhi1(k$pN?A zIz2b@Lvt)zfhC^MwjS7nXE1|2$LyR2<~$=UGdTx(O8-JI3LkxHWmkvYGYXsjc2x(= zTo*8f2+QD;3coT&QFzvUWy+GzeK8)66xkW;5jup%;;`wX%%pGoE{%+Wy)nF#N+TVd zBy}wPEK+BsR(R>w?bUx5t2uy7CxJb(z$4s5;0cA1eT5eCo+$o1gxd==W7k?wHauD0 zsC5shaB}^P57wQH_g+|Gry5EHYnn_~>fi(qioX8awGv;|dEbt89QlRj^YTiB06Hjl zNB&C_!&EVLr+H3T@iPu{rYwOF)SlPr52zyd?!V{Cd4cR_{mXh0_6ZxD%RnYP0=2jc zGJk?x_i@YaH1!}*_Cd|}FaHdI-^;{1f{GJ)uZ3oCh_jww&hZYHaF{vIyQQCK@1YZ1 z+Lp`yD+>*UoN;CK$bK9Z&-mcM>2(&L}^r^oY;b#*Rv2Q91hxZ8vC&f}qP>3$-%NhK+L^plwr2zXhG* zC=v0;5FstbF3qj)Uh>%D*0ivRoS^UqFb8SD&(*ea*NnJc!-)@T<#ANce=r7uyT_b) z>HYo-nF}X}$W_mTIsEoS`FiJAEpq+wC7gXRWq;nm8W@q0C8WJPZM9zC`}s5N#HN_9dHpEd=+avM-RsSVbp6`=F}JVFI&lZ`}*~@bVoYW z(nNKAV&+XMBqLo!Q|Buw_!n&OdOV!$%D!Bycz1x23J0d_Z}7ijCtoabW@Elt`JJLg z1C}Sh@TPl@(Hia)aOfnND7C<8CAVlBfw)m}W=sR&Ewdl3_=CekTK{s~*KvpXo=0<- z*+_ppZzbvQE7zs_25_ z_@09x9?kogqwn;zTc&f%GyB;2kjcQ;pSMBj@1DzD<``iF-;FV{WFQ5eu2XpK&hFmi z;CPWsdbIT?)p;b1o!;kvT0V5+@3pS9;}RL~qBf)yzUMA0l!qwta|(`W?OyKO`fBwY z!4{lBQ%in2o|j7|uY95u@`)MP$G`oiNo)-nvOnuvmeqWwzpfO-0xq+LjWR3gOs;D) z+T5DuLhf$otSF@-%D!4H0Zst0$DxW0Lcdw(%xwY}`@P0J|=m}TG zL}XxWE}t#i^C>J|T6TMgFNw6|XIIQJrCv<0Whe#)Lry|8lc}3m57S*N@^hx}ux|RPsZ<6as3lSl&N$E4b zRg&s?nNQd1@whag6%ojFfU&y%YEsOOe!hl@^XbCnQ@lK!yf@`~JYSvxcoQ-9qM)vPz6Z-TO)hr$Kv)%DJVN{O2F!qjm-JXp?cUrZ>td33n2(05CB!r7fLrBoAI5{%!9Iau!(&Nl)XM6AYCO) zUCV`umuH7RuvOqL0#2Rew@5?eEqF`k2;X`-xjmQmQ#IQcR!j}om&uOmPC?|E6lcUL zV-bF1>5#CBFPvy`D%dZWB0ygK4d++^ujl7Cy_C1h*tP?37+DEls`hZ4%9tigHqLyk zzkbP**bl`nxNV-8m0r2--nwUFx@U2n2PkkW{fz0$gT>7Iz;No=tS_M21TNsesC8dfyI5y(`>Pb%>p61LfpaRb}S; z>3t}7QV&H3krU~`4nRR71JXH#+to0mxl8hmLXHL^ol{s$@B))K@jbuz$@-W=l3j#8 zDL^CeJD|4Dx9*Cwc8Qf;(&}^ky?Y-gS^clJYM0;lcH7k+@t|$!>h%kLUxrJ+Y@@vV zy2HiY_4yw+0M3sVAUfyO8=ud6&Q9Ry&z`bca!y4ZU{al;lwL6l-}qKy-;h>j_fq=$ z&dLVJb{n=t>RosbkL%E~l3tzEVZAPEjP?UX^@$mfzKAKOp8OvFroFgW2PM-9Q6ewW zrjp#OeB_L8C8&>P*JPO2=_2`RJ zL8=_H2VYN;u4c2G+F16|?IA<)Aa?cbpfesRga}LQ>Fd`$T~F@t^dy$*OpmVx0!}Sy z;XrNr>Pu~5WA;eQ8%%8Qg?I16rgX2G*!A*X`Fnk3;8T}Xk35P3wVXwZ}N<_p2_B+oB`gHz{<;54hzWXp2MNUo#Hz>YvB zGsePTeSYxwF7?&Y=`+~t{BB}z#uU3i(l;w49OCpAW>V-1X1>(1_qj}#g5i;q+dH4J zeY(famfQWYz!<+Ae*Fr4%YN>M3nzrmZF#|`#%HJB{mOj*0iSBCMme?;uA)xVJC*lt z+E{yv>V+-Us%Zve+weto_P;ak$8WbdT#a$YO~wn&1i3~MUoKHL{VIUKzMv&(2enhA z`)Y11@$1B`MR2aFC>ihk$VoB>s<0%6r61^U zD?Xqg?+gUcSr&$q^EUppLjiY1P)IXxkF8CvNZIdxg6OlUgi3N1zhDcQ==;(^mD`qZ z4}HA!RCZ;QFyq)+LAEC;iH&y-Zp5LY-w}!L_=9TM${H3>T(T7LwFH38XDAeodKDAil z^N%(@&;0stuLu~3t(B(0RgoE3%4`3?W?(y>Yn@>4)YM=o_}Y#YKY&iPbB}F%MvIEX z#5UrcVfemTOp?FN)57gp!g-wPEsjb*)Kwk*)<}T2StKY!g3MH?5xN^VhkHWu@O$&= z`t!Q=1eY{{Lp<6&I8iV%71(8sA@Ys(k8$QNGi|~2IFW8rP`ESC9cGWsd1NG|3-ET{ zDcniGq32%cARv{7#FqAYw#&2FkHFcTep(2h#UIne-SIDgBn`bYu;C>&HJU%ba>xE6 z#p)*`x5Nef=;kWRtV@gYYHW+O?l~ESx<7$w)O>vh4L2;7sh(_o>~Bxx=b<|2R+yRB zl2H#MvKSmYcE>CBOO%$F8vC-JJ@sSgz+1pmY8ehJknk3prMH_>4UgU7@qFUzxqnOt z630)&(XzYoRhZo$_Oo&MvwF*Qs_u;=y6V|Jhp%Dcq|(d>o$I3F1#U=?G0|| ze68reR0e$J$J%l68k6uCSh~CIGF>|lGxjgo=j$8U?YPmt_QCVI!DF|VJmX>H=Q27S z`Lo>q)2rv~cs|H+>TknXzNMy$Vb2XUF{(dr)tZ&cL(-hc z$%X1wDK3$Xj4m9L;WM`1?Op3F_!Y!$`$z)40EMIM%D+2Y0J+hx{v@pEF5=kC0naLI z`Fsp@S8SrkxgGEkLK7YnKHYtCnfnlv66aE1O&z2^a?vaC`pcNq*J@xF*Es+7`}gBs zGGa|#BwzmNn)KAsl9_wQ_8#(vv*jle0W}ix{ZTsb4!}`mAdUN{c=g95m>^&veTYcO zLG;z@BC@u}!(`3IZ~V4k--ItVh95oiWN$OY!2kXK*+KH~Xw7Tb@A#&X<|!P7Q5md} zHXAHS#B4k99&sD6s7zP8@0RSvQ@4Slt~_{3(CJY^0QcsgQiJ)` zT;r7N&lu6n>8ee(ltK21)1P-m&P#Y#?vz7Mmkoq5n#kTOYm+T~fzkiQM!(N`FT&qp zl=4YP&BsZlUHSQ!E>Zk%4=pP6a(z=#8TWnkfY1FKr6{&&))ODP>!KxwvNLr0c@a5* z*Bvm!5=NUTRn}1fHBXn~ZTF3)s;5ExVsn{{0jEjXnZMiEuw0eD0+nVGaMJJOV8!Rf zqQ<5#1@}pwq?ZW$h$wvynZkXO5Shu85dWlNSHyFF^RJzxx`lAa~)) zqveP?(Z83u;dhcd6QLnnyp4PO1jP{C?ds+2IxhAAi5?UXWzJ z<%PTyFeMf}cvx!j7g20FAAx}=LB#2Z{Gc%F3EzW01GEk6glin zH`%oeZX$>_m5bv}CXTR*%4tgVG;d>Jqkz@=aqVP!8e+@C`(K zr;;H4R!RQ*?e>E^{RVJIO_Mz(YwGC~Jc!F_Nco0G%^>YTEBe%j>2muzS(t6W^nacK zQO)8PiW_!ZLejfoUF0X34ZrP+y)t{#zLMmB-_M=lX?t3#y(+;J-$DXa2WY#)s;4lW z%t_c8w;00oX#|o`ug3?{wX9@Y>Mg)z-QUxBkGTbis$lZs{;o!t>?p0Uya)Z6^KhdX1p+2{xaTAZT7JP;hdK^Pc=AwF&-XSrFrULMmvyo z#(x^^EA-|6v?3JJ4K9jE3I)A=1v?SX%Rd$e-KiAlIApe$F@dQr&71$73&Qzu3|Ae@ zLW;2Pecyj=D2pu86(HNN+75rP^@)0&IRPq>ZA;^nQwI$Uj-u5CgjLw+xHPT<&Q%sv z&2x0kwr$6qoP8^t{T1wV!KVv%d@|Ihxmo-ro6cj{DFp_{yay!bs^$*uBH*~a90fAN zuw^J}Dm%n5lxy-#v?~kzWdEC~DpIxyeK z+p6TQ{l^a~_BG*g3|AOzek@?`#@w9sW}oPRTJD`J-O75k%H89KHWr{YT>tdsVl@RhlzTC2R?7jFeRwd+Rxd4ck{bSrYb%HQvyYyzt2|aH zC!28oj5zzJF9`IY;3e64W;b*uu+j9qk)8D?;$7GOJ=dV=$u{-l4T^n9J^uQg7DxbpchjtoenbBLzCr9r2EjLyh*9}K(RpEDm9e}J{wY1Adygyc z+hd2}!$?rBff>p`&@DE1Zr2KDXeWm=sJXVGry+?pB?L z^)fu^e_K{Yf9dTA^6)?1*IHBjb=v3Wl_oIOo|V0K`wX(IP5Qt5J@Pxk@{o?_X?=X( zcP+aQ59D&H@Z&DkY}~rv{X!paus{TAdBlo5L!!}Rt!>`M!_UwCeRKrX9-uT`&X4<5 zBZilEG!@iSc+M`_dU3C7Mw$&BwooZ@0D)jJ&=El)829r&jP|7lMsBr>{8AevOYqRC zN-}!_R)@-zTl1x$k?(x4rn||VxOvC&Yxmb&7~I@hi_XzuHX(8_BLCtY!auTN3z!w1 z54e3`Z1sBNW+oHzHQL-ru}^3Xv}hnr`yrn6YCGLWkr2rWhRc7iXLKJ>z1WS33PYfz z!kFdT$x}RpS(WsF@;@4LlxRWVk}zC<`%0!M;Ye!cgjH!wJllzJzM&>CI2hShkMB5^+`X8#_(GTiK9Z<8}O__fHXt6*H+ zR$6WEiBB@SXz_A#aEhI=A&q_-ZbXzz<#w(viB2&{GRwb> z5Dbu*PVST#0qA2t?<)72LvKHAf5p`=rOQ<+wOJX%;8IvKx1u=Gmw~2btqR3%zdbo1 z|E;8)KfgV*&|Exr|Fb2|zvr-Z#2qi+@qonpkNbCIUy!$tAj5dZ?XUmd*953oa4^T7 z7I^#pR^mYQ*iRe-N;5GaU7EIeM@|mBQ@832rACB<&uGhbqzTRwZob65F(f`5-mV3CQ zQM|>JhqT`J8hmm7szxfBR@EW#rO1?Kk=^*@pPXEu)X#2P$%^WDImLP*Yv{)@o!$sf z{w>|#aT}kLiiqRR_#OfFB4`e_A?3k=iD-2>IhVihE{xi*9SE(}Fs22M58~~fnpw+w zuXf@`n>QY!y5Mf#EzI4HRygy(o27;1b!m{V4`%FB&sT5{nj`Vgdv^N;RmIK@2K9Uf z)`cirSh)U7=!`4e>K=B|tLe4-Kdszc)a-_Tbk$GbV3aQT3G4h~Nj3ZUoA+>!KKyTT z{;}UDyE#Mayj;=#Sw9+d+a8ecC(wa=gU^AxN;Tl-$VUO+$DD}Oi1I0Xvppr-)BCRm zZ-Z5dKV4|(d0bq_&z=w6AE(jxe27xWL&ekqw#=3IK8w~bvPW|sGk~eD=E+qnHJr3} z_7P3oQ@}`=AMn1V9*^Z?cGaub`+Jq03m9hhixpf9(m!zKI(LQl`Cy~qNq_fhuJ4sK z0goGRJE;<0jRl&18%5Pjk1SAIrTIy19?#Yk&qb-<+3#b&hXF=f;pOj)QU89g;C>MY zV&(KephSvP3l&^ia+-J$=F-sh!jj?-+KqGuq2!^V-rdTe{2xCu44sr-{+h-7ks26zvRM2p*{>FjaFJX zd;Jw4tx14303BQ90QV!8{>L)FciU|GU%_Nwf`kFE{^z(gOLv&+eQy{E^q(B9TuH_B zhmBLTdcy_s@T89m2^Use8em2+>QVC z9wKJ(72MfO>rel<-rJ<$w-d>^0C&Vd*#Oc~jQa4 z;Yyz|*HEAP=M$)l4fj&|Jht?y*OluIw1Xc{|H!BK!ncXsp^M4U&j1KZ%nElO8eHr5 zW>M38&ZS3D#{Xs;K&;UAVEjIxe}e$g(8tl)>mStdez(K^_nL$GpYJqiR>&PBIiA^E zw35MAQsd78=<8a#f7;(b1>5^=0hR{;q?qjPsu$(mC&P+4RlDe`B}2Q8AI<vkCER=`#f*|Q*rv*frDd4QO7Z!%KLKU6K2^g6!V~W}vhwA0N6!e){U)cYQ*n^*2-Y_VAb~0R<-a&7}WGx3<}7i@GwJd~?N6tL6>aKz&_HQ8`-xbQ%_#U-7y|`DN{&c*O(h9`9y|m(f~bGlVar}5v1lTL9F{E%TDJi7)AR12c6i+!1g~TQMY{o zc5;16YzlzKIc`q~v)ybKrlBTarm}P?1`!TCPJ@=(vX7)R>^X)cuQz&Qp2uyr7s z?iE|nkK1LyN5j6^XQ8a^V}C@x!GNwK{YB(#$ABldA@aQlLfK@h(0!4HpQ77W?DKo* z>u-=3*n>|fq`^++3TFcF0`SeO*%zf{PvpVD=?Lzdxu*f0YnX_1{c^9~Lm3`?__}Kx zL)Cf_R-;?KeYh_e4u-KrDO7qNrU!;Ek9M?Q?-*_9yXy4FrBaUOqAbhba&ih~#?C}n z_ZUG#FOfaO`t1*%!Wel8!M_A|_D$(V9e()xY<&d;5Kt>K3C{G7UtYEfSRDioWiZ4J zar0?c^pK(hqPMb7Fh%Q(N;>1%QQ`Nf4j-so<)!1DyzH{S?0joLnHWwE_mmJ`#lGS4zOCG+SWNJ9 z{DI#swpD|O&wB7E{PF0l)lqYc9u=Vn?B5V?@ceT?Gs!-=vDaZ`+<|^RsNR9ce(liN zyl--3Ln)MnU$g*HH8|f1Z+-Aqa&7w!!!qau=lt7D8`-e>TL0>!2rPo%ckR{eD7f1^ zgtZdfd|`6m|Gtj{j|-4Khrrlp|7yQg$@;WC61Z<_JKmLjx9h|Bb_RE9ej18_UO6-a zdhw4{z$SpCnJ;Z6a;_)Q#&u1)6U8H_dE`G=31l+Vv84PxY;PxP-z1TFor+5?U5I^L z{K=wTgu|XA4s;^Clgk}dHOJ}bW_|tG%;+0!1xQrh$W=_r`*J{9KTi?4yXap4Eq+-+ zr$p6YT**+S#K!^CwJN1sJyCgd?Gp4KI(u-HHqZHz>WPbRZsa$BG>JzgcAg#jms=MB z6{Q;|rzGr^da=qNCLkWTeP`Fm>;mYo|2b5k-55|RM3GYZv`9vaEAsv(g}e}5?>67Y zBV>6g27(p4Y6HSi7(vu|M5Om|Z$=&}k_+#qp;CBmd+h)F5y4K6z`@>-^X;{nJ?iAe zSuvw4A4T^Ua4J#G40CMTr zGY-~{1_;?cG-toRoe1L&8_zY>YTv3nI(PH1({)r5%l3xUY8Qadk{FxLvrkp6~9zw5#Gw> z87VQ*xPRxGz90yoz8`4vGqTT+z%-p-&`mAa8SWiS&Yv3a8s<+)3~%Ir^a|O#Om5LO z&5$LXGG3o`9)V&sc)zTVd_@mX+vfo(?t=$U>Cy=GnR%LaI_x1OM@XOCNB4L>1??Zt zUDBm``~$|^7qLR^c8St4Xm0vz3*^6DSsh1L0PFBEem8R*#)-SpqxSNU$=?3B54Ln@ z3DEM>+vI)i3epsqhFo}LjnVfbO&8fy^O1-TL*mw8)LMa@u$3d3e6hZ_<#xRnC#y$A z?y)BRB2>yPU!K3X&ix!|eSGyPWyah~hJ}YNUOdbxI`YQ%)>rf4eRseL2K4VjJ}P>YGcWx}0+Q_HeJ z*|$STbyCtF2Q-;key&@E0E*COBJaKpTU!k?;eH7lsw)NNB z`Yp$V)!%zdX*acqj%}cYXX+ASstWQPH%U*NwIdmC;3e%2r+v)>zf@w8)P;Kwxm#o& z?=^Sk{?N*$y{tp*5})uM_~9cn#GaOR2Oj?CtEsgkv~nqLCfV6yED|ke#04%st)J3b zh_#B%Xy@8&w+^jhhif`N;VuH{QbA`Jw^- zfz4`I6R0ycHnt_M%^%8?b$89;1vz-udPj+H87=~*J@*sF$tQ}BLkMRTo!Yx0j=b~K zObLPwo;AXoa_h|R^tHn`g?U{FE)p8Q7gQCas$}Kg)aiDM%{dvPla6r;EIM*WTa|wL zD!X76k`eDSZ2V~9*vt*BkW7lE%!t% zp07J}lr*U9#M(#+vc@uRPQbcI9q1R?)L9#7iar_U%x(a|03_@p<$gm66!(v-QA`=jrsbQ-MM_# zcSDM|zeoMxzxAb9XF>!bsW|_P*8RCW1IKVk3KwSV3r!WQ{6TR;U? z?cvO!)3^`cz*F-H@J)1AK@K?ZJyc2YV;e)ozNciUD2MaT#?yTIOn#SFII+6$`Q(76 z*?-g*rK>sFPJ1IAc|*PJl>SzEQW=MTRwnY7PThWeGvC%M^Jlmg%!t==x>|ww6h-$h zi92OKc456Y7wpW@7{_}ihWz_hocPLOf0;Z0YLbUvve^tn2acT2bchxIbQFcje86kzRBXlJ{PK3H7^X_ zFn>=nEKD36sb^-0j*$MTTSQZqq*wq)pb75|L-$rcme@ut5oq; zqnTS^Twu;}@(mm^fgkUeL%u&(<8#F>ZjEmA6v&_AmaNYgEc(W4Sv^*LBR{tzaJM^( z*yfO)$z0vq2SD*wAxx=%SQ;=|x`C$XfP-iB2l2B&)22%*w6l8=@Q28FW~l9atsfru zj@l71u6yod?6t5F#m7^t0#e&vZQB1{|b5sz5^!pPt!tzm&8uz&4z{SRpgGmy%C zM!ZfST%%eb93gu1D7pPHQE(`*pHC}J*d@~9_>ISVKbgF-`_BgpGUe30{_UDwTY3)p ziWcuMf?4!2KM_t@XxE=bKFd;>=@fzpS^*;336r8rSz^=A6}kccUQ|- z@H(WEZ+=Yg+=ZfpyYH^}zO6*X>*hQutK|)ZwOm0>h?(>}@^n zFO0`}DM_OMYqEV#dm?U&6rqGbPJ5jn*8?kaUGrVO84L^Ba)~nn^*(%w!mtMpIW%`_ z-Bd??MdEq^A7A0Oau^)0lJ;y#oQ3V+W52#-FL>kNE6uQ)@@T_RTt7*#F%UPW*33)g z-G@4~=I6nOK8W|18?5v!1Zr2{MhjM?=2q`_%u{n&fVeIgH&8s@Zug>S>AR9{v(TYNUDVU z?jz}q3c^wg!UQ`)){1wyQX9{WX7gF+=L9A6@Hv-beV^*zY|KXR4DLGeC0svK_QzH~ z))IGXgEQrB`_A7a@1Zp)G ziJKgx;*KzX>RSPR>U)X#J5E^$Kgso>Jo5J;?yaCxXZF&wzn#krLN#4}X{2kG@L^pF z)Glg&(*84~s)TXGEy80xL_T(+=@V9xziD?6lzj|Nx7uEYACCLWkGlNK8)+5 z0=O)R4&2xtDLx%4}B;IXf>l%r~G#5 z^ed3q>c(3u^2CuKfq}v&HvAiS9Qc)5ZSJlUiRvlbXAY1!EkuN*kz3yTJK#%&-^bVQ z{6f69QT`kbLG{?5$^FqNi-p3j7Nb=>>;?CT$%IT!?irm&=s|od% z*LANzLnElj<#)TS-}%!PO67V+?`2;i#smFv1CQ=W{g_}JQv!EmxeeiFG_@;6-6A8n z7Ese-RE>IXcH`T$wXM2gEr0^vTd49bKk6p`m1jdCUha$jbCdwJxdc*_IZjvg-~?@_ zoRQ8;9F}N<5*N4R6)ymWT3po}4rI_muAOp^Oz?>}cxK`%^BEj>-!! zIC295ArJIsn+5@B$zfnBKwmUhMf2X8ux;d6=!CUyCoFPXlvlj4OVBwt`aG25Ki$v0 zMcLyUD}Js&hNSK05NXk zco8P^mtg6J49aGpam1ibl!Qwzt zdoYLF1R$1s=J23M9i$OLRDK{+ElRaqn<($r(cw-^y-6uvV(0%y*qdyt%C23u7es+P zE2;>n2#AtMjZ_2yNd>Mx#$4Yye?*j`w%cxdx4G6_3h(=o!XJlB@^2DfX70WddwqU-pl>R3zPv>dS4B_Z@bSg>?|#i9XW0X{BTcfwSknmB zuOfRfqaL=x3$e7P9q;mbe#-Y#$ne|pspxg*PknjGN_f(+86?^Zf=6!hKvVyCm||)1 zUncZQQZwXUHe4Ld$Ton@vCu-jDYCs~p|)dV;`&q_qKa-G$Hb&}^$uY`{wm;gFzwsd zd_7IwCnSAE%lh{To1oL~T|@pF zI4i}SqCh}m(49=Y=sA~fm6ui&_4S(rM+}b!tgS~=HA+=AD8-!1Xsv5;-pA`1=Y00& ztlAN=%4<1EG{cK7q6`5SZr8{*I(`*nzl~f7k5$op*)Je!_Z#QT$;4MdxfYgNV3c5 z|9S_s>x9&aig#j#;lisI^ZMhOyPOersKaG&%-6vf3H|Ro*J}+pi%ZSXnjl=HZ-mz- z9<*#O8AOBDO0%A((O|2CH_P{krrXyS0V%j6N-L^8a~M^#xnik^r*5A<#M1>!Ry`Z@OL{<6 z_8eB{<0;n)>=f0Oro8Sf-VmDm=H9L;gD#4*Buzs&y+V9h(`7zn_$3XiA=L(NaL}~YQYo&Yt&R;7kyW@L+LY#PnKWyKhTC?^) z9}>>M^G`pX%kgvN2U0mp+G3?!7GA*PxykSg6Q7Wls~;ab&%ycEPZgc~LgDIvKWH+9(hmuf>-YI= z<$y;NL#8=4wZBdO+#@6ctg^PmD+wzsr#-My=I?L0`QGFB?J>;k5IDr`LHP53cN`d=K*F=g(m-Q8q^Oz^CG&QxU(=gbV(B z!rNyCNTjy5*BnA>XJDZ+$|^hdYf|N3^Gs>D^VJpZHWt037%gLF?G5;v!~e%moB{SGwgDEYZOQL+iwJN~`XCsZE}0u>>0>b235?oVsjByj@6 zG&(RZ!mk?9o^6Pumi;mj{}xaJ;K$@u*X?nt>pxBD3k`hXImRYP4NF8cjZIo;vW#JIjy|?K1MdkckAtQ4lH&z61d#lu5&Nv4 z;E5X?x$aZEtOZiZk7ImmlAk8kdr7uPoXxF~b) zdfWMXe+~D)z4AtRHBO*TzYijFR_4aWrHpt33i~fB3VoCp`-fNLFRvvb*eZ3x{CXBS ziAsSX6uUl?#vmUnciZM$um;S0-$Lfhcwpe8!oP%@;7Nf*56Y z`}~ERZMSg$VmW_~PrNAp@_8@J8%-U#f)FMx%49O+P$K4B-eYthKO(SI$}KzG>;-XO zRsFKadlkt9nl4C|um&t9;IFi~!_i?LWxAykU4 za9v9$d>lLBerWPuHTL5fe6dTQUaF57sJL$`$H$}M+?W?EWdM!QfEh2;*&?Z2_Il+$5q!EaEm>WU|l(p(D3jch?(a}Ot!80%cp%94s=&QPg`x9BSdy;|^ST=G3e&P~k zj!N7(?i4;=rhy}_-gtHs1$fPJe`l7&N$vc%s-MqBh!DeAcq}u=+h655-pO{6d<4wxB^Nr2j!y zB%9^@1kBVkDH3gSqw3{cuCp*6@FObNS`I`Kpo9|M$#mUPYXe5*p+3(1VSO`fyFD@M zRhvnktp@JUe{=APlyg*n9X-J)0|M};C4(>ablP}0_~^oM817+1mZm(u?L&mQdhk1_ znkuo?Xsg!;KVG36A-79K`aI@8`6UB^Z_AX#EkP5N@LgAc$-2tvjaK2VX1*={?x@`U z9{Q<0Z$l)H_f6zp$|!dt!dtez`ij#WkA*9qc;@`;*zwD#>V=k7GJAK|PR%Nt#F(sR zf&eKLJp+QtX8+!0WLD?9>*N0X_O<*FO_WGv^Cp+7E|bWI{Cy7feAHa3kAwkyE_L|k z=V)mi=MUWUa$AoX11>*k&m6%CwlM#4XE06<#U1-8*t+$fkU%BJ3gvP8JLBzg_uGnE zx_I5jfII!;Ioq0!j?*T3xdBe*XueDjX z!u|(l^4#XX>W~nx_Se{hcDp~>DUjfV(FKK&jQL_CP_-(L>z{Xw%6(!zPJQZFrW#7$ z5q@?Q_7*|D{FrNQsFd+ZX`E^P`qb+CuQC~p3@Q>BCREwNApZG!h<{acLvI}GXV1Rw zGy?#dos`Kh*9_hE955n6A<^I6^5@}*cEW+V(&j@X^9!_bK!bl)=L8OK&;2(GVFg2NU+PcG9!9i^bDe(F>T`i`DD+XpWXO} zHLuCQKt-AP4J$~kI}wu}3=A&ZA3}7kpHv4|2xk?{X2~|?M zY}X6*-|sTI9xUN-j zUCn>rb^NBFAfLWj2CP9JQl9TFh)Ae-txPxPnriiU`|IMj9fKl$nEpLOtxO|~-2p14 z2fpLUvSDWVr(oQ9wr|SCTdcOzFl@!AJQJPSA5~1pnrr5_5EE&Bk}dh20@%V@Et1V; zC?$rggF@1=K`k=kvh-;oG5uwZka*jPT=ZP-B3 zwL@$^>*QE*y%*Evd^e0Emp#GmDOeYbjt6Lk-1Ba)Tww|8 zM&r*KtyrDMs0isAPZ0#=QXNd34g+0n{3S&+Y|XwE*5 zk|V)D0do7Ku#hXBM4dFd5A~mu$Q&eQ1lOCw1K)bIfitLY;c41JYP!1wfn3zKML0i0 zY^=1n-X{K48-OSReQHDR*}Xf=>3M%ZH4l89s0k55s>|t~~xmx5I8? zS=ry;!OgdeKXeB^HTeXOZL(!*C*S0uL!Y_Q7^#Sd_=+t3bzK?WN*ze3G^i_ySe>#n ziGwi5UL;pmugHfX`aG4d5^n8J==tD=cUy*C$}<)t!P4jK>ng`J!uS?@lI>F0&xi1= z&|m>tZtLCc@zj1t+{fO?bLWXV#t%Iqk4zFK-QmfFu|LkXvamQiusaNk0cxXgTR#Ic zOrUp7$tf3+8w5=YN(c3Bt#>a%&dK6_+{ROO>dj^KKo!s68%2by(!+K` ztZlij2z5pH#tWx~yn}-%4z%~Lm)L%7P0k7Zpy_|#bD_d)XOXf443R}tzhA^yH^Vt` zFATj5Ojynnr_oA}>BYedPnDJ}S6Yk%H&x$lgmxAMJbN0<@7fCh5ni{~Ob z2A$70y8bQvZ=Mb}P>E?MO9+6V7_;C6(Wag`APnx?UF?RsuT-#TBBQbl))9!jQAqW~e&s{&#;OOn+2n%< zjIg(6u-^yEn15X`yk-~6Ygq)qIFq+ca$@moMo+sxcGhBL#yve}>MePIUW;?hv+NL8 zW-qxpT#gJa1{q9kE`V9<>uo3cN#TN&KK;j|SAPYv7r>bG&0FDX0zB9eo;v@LPViWa zj14UVKj0jOpA-6TKkTyl$ALcsUDO21{l~FT*Z+R?YtmAzMSyu?o-gPT8!}Qx^Sj8P zZuB&wUQ?VnZARfB)A*FpIpNQE6rrRAe;d?|VRI)?&{IYAaa&HUmj8iNt)n$OfWt5_ za^qXxNWhv{?S)Su$sTW1iqGU3cC+3`o)4jYOm^DetJ^9{S-wgMbzx21DXQTck~pE= zaoSy<&Pf6RG=Z_^a+EKhIgFq8Mrd#6QrZp@6wcQoNukTt{un-*WoblLH?7aS$VkvG z|K{?q7Vqn5{(HQpNXz5KQydZ6q##Ah(?VAw=^+3r+`n5fR+zgMb=JB(aTc;JKUuo8 zxGQGJiar#}KDW-@wUnqM+~+<-H!(FTD9n1|_!5MH8Deu1S^e`{E&Av#7c_~#|MuKN zgRBVXHl)d)%i97~wL!dhg1h${HGWZL z3f^gJB!<2;M$gk1NEyv@yIPUxLYnQ(wHn=dt6*8~nft>FVa}G>BAT;A2MaVUae)%h zDXv+(Z2&o;XMDfOEJ64kJiwm+A@|<7`@@|vEcDqPho9k6@@{i=Irwojc2d8AHn^wU zpRlQ5<+CLS+oTSkTmLXIpPFpt%`Neb8CfO z4zH&>{_OF+#XX~}aFsf@6R?S^>JJ-TEMaru$8PMkzxNIHdT}WZ1cDK%K-4$r$5&*T zUn-r;#J*v(+p)PBQS0?=L0JC4*=gWD+jnN{fP}D=1z}psV>zfC^YOpz zal_*dz0U|RUNb9@$7{_MTk^=$(+a1UYaNw`5X0>skw2&1WeLmPK>pB`&r)G~UM&|j z^VBv%bWXk>-*>n4aiB*h6@$&^Do-nVQdk2J>S>R$H!Nwhc5QT$H{Zv?fzyX*LqB>FAnyLRp@L9cPV$9g}J!h z|K79DF8D1WSftGOMsIrbMr7lOiDUQv+Ib7I+tFN9_?wu?JwfxOrL)h)4BXE(!c%w_ z?k7jpoVAkwIwjJUMa&>VhyC}v66!B9HYxybC)g^ZTu2xi@h_L7xY6Ht3FOmh0i)WZ zP58{^F6(q-GlVGhwkdC+l9ipdU98d`D_rhvJp3Nub{QGi5DUi0*oC2!WQVto=k8=|B)b#v>m{1SJER{9!I|Cn>n1g_Z3|m}FxB$KU2L>rfBNePT}*&w zo^R0391Vzwv1Q6lS%3Vi#e%T&ZEM{oyF)DKD@#MBNJ69)KQBb)b7eL61FpLv*-(`k zV7L-D^R2>G=4_fmMD{DCX_2`u zhtlHNqsV-@;}N^1U(me;)xDNOjZm$5j_nE4Ut9)0@A{v5R;7b`N}>K{FDz1U-^2WX zk7T*(9DqXMw{GYUPEA3lUl$DboYZ2HJ*-Hd7tdHPnF;HgeGX#>y|0czQZ&W4P&g$H zU5C|c$45fvJ%Z47q9Axm2?Jz3mi$0F9;-){oni=F|FDey}f4hod>C6vMInCKaF@qKEN*MRNFkjb{eFQ=O zI31|B``N<_^70gw1uwTb#*an1>8+4d=|!8X#U&9S$`dm>$>C>rA8Bqa?V`Q?5Q8o@ z;{zt^UoK7!{v2Vh5Do1(E=M-upYv3F)_BLU8k}x0trutCrx%W#_)Dy%7cm8m>kcD> zmP-HoJwRlg@eJ&^%joM9POw#6&=vm#S3KdX1yN<{Tce|kP=zWJ6#KdNF9tIQDqE!2 z>5bZqg3_frquRSZNR+pc*8|IDQ+K0y2Y<5fXFaB2y!bRn7DgwF*e_;&{Vx8UY4Yvz zG7)iu?Q4TDvArS@C2(N=PWt&d@Lnh&I2B9B^l6kyGjcgW7xpN--(oo{sEpGRHFCzf z2(Fd}JKmj3Q8ObFGat}PUe4~D`gde=^!NTp4cDR91%Bev`EUWcxOe>0;z~#`cEukz zQ6OL?lGrdG7R;BV^+>JWrmed2F=$aWxw@xix31~>oF{jj9|wsP#+#Q{r`j%s%eXy+ zmm-1nV%pM{rcWT4i{RpU8fFksZCLG)rAI=^vH%>D@6S^ow4UGFzB;oOwaKs(1IjQy zY5LB_KH=;%BFA#&*;oV0Q^cYAehpe8AhSD(E{-yXg&jq4-;$PMS=P#-$a|KABNan8 zE^yrAG0Z=@?)gl4?rP&JK)%bT)RAeF-97$E07Axa)Y7F|g?)*O`D#@u`)wb*@W<#L zF3MjgR6II)X$jtT;_9mldy~IFRVkNJQXPlyC7gu%+|^nB`|#9VtBoc&X6qwQG{p%% z7}b|l3gl&Y8Ji^sT4ltuBenPSr#UV%EE##3S&0<2Dn`zSd`1!tp_LnK%zVemA z81@69((?z~nuWfx4(0OV5Nkn6=f`D^|J0?Y$2HFVZ->52Zjnz8_U0|?vX)L0OxN;% z_oN3aaahOXAHw(=dt#y^WQ_V{A1JTyLG&Q802`C!IAqm;B5&~*+TvGEVK{-v2U#0| zVEbgBM5eE)O{~}oT-aB|E4UMs~(zie0+L%c10~mWS3|#cg9b!_r zs@{l5(wQ$z56|Zdjmxl9WJPt&)D-%*>EOS zK(x7kMLZYq`^?x1u7DY)DF&KDh|5N%(~JpR(v#1kv;ZX3|3$j zPj{82xTYR&KMA2_h!!uMe`_4pZeE32VaBO2idBqc-y=hpG8KFV*rl`C!DQ1{c%^D! zYT!xAkI%my_v7ywFSv~c3W(rrspcI2v|#V`R@wh@-(k)gbqZ#f=M62Rf@*Tm z-?G=n-=qyye~3gFg>p9Je~{j*ds0-VA?{ZTQ6Kk6hnn*>7h%7F&+v-4l%$ok9~Td@ zavb>_*CD=QUZ}q{19qzKKC@FjlhSg&X(hnmAqdxIXMiWUHnM~|<8{DG`V3Cs`sFhU zKXwov>e;;*h&2BQgzP%qD~<^-a@xzrIb8HT{Q?oR&IkEG+&(By{p;Y*Ap2P!sz5yk zgyZ}7g>?Slrfl`CXrr|g`uu*`t;GMiB8naM^mh6D>!)%J3epZgB4oWvq{v4HA6K>; zSV%b*hd8}_F1>dKlcp*U=P=Xc({c3mN;>uvlU*_-6MA_#7l_)wwtOuVN4T#*Jey8F zc9+NJhR;L!zK`NLtjiUpj&nnt-mbIZ3qbg&>{()9kd@sR1>qt`&nR_+ktLZm`)$|E zbq;?5r!C+#;CKVt7iSp3?JZewz?=>_TFIk?@6V=7fXRU?Bv=wA+k{4-7R9od1HbQt zAe+=`2=Si?@WN-_6?^3RsGjWvMtk;n*qu+QvxBqhQNqH2(Xs5~|2uWKP7v5)2~u?z zPoIoUo0TBN34WxI&1i>=@jYp_Mz1qQMTh5(oq@Xo-(}+fQ%cRoLB9vGB7Cjr4ZX>E zXx!aXW3q2BF-4lYCP&2AyJ}|F(O%SjGnYP{Hm5c4F*^HE*pth@Ps8$<1lW!K2HoZG z3f}o#=F+t}jds&a=WFr$ee}EB{bcr5cHdcVSn1=~U$li_Y}O&-aws3T^u6;GOf1g@ z_n|%y;m3L33X?cH&9yOAeo*%#gf`+*!cS~Y5)XA8t+Tl^Tw)mr>vb|ASbvU!`F?0q z^r52j*`MxJSj9^0MHucj#;JWzWvhX-=D(tDO&iQoSa=wi!_VYT8_uOJPB^E?%bFlGO8tBwWCs zUXN`KS(39SF_e_u-XX}U;J9ykE1qE1#&!bwl$Of34x+;bd8qo%UJCBFLI9NSP6NbH z7Gs=l?O`e*u0I3c&Aes&^-=CLt|ysLJ!&1stHw_!m9TH(Xt(yI>a{UKxwHkCAbp%D z_WO*(1K}oMar>V;=B|*dbkTWUA!GlDe#XAv9O?&h6%Xvo7BLU3|FE`I(VC};Bw)D@ zjPQw`Y4SR}E?3=QZ?v37pbZuo$UY$JE?4+QB4#ieiV&OPS($rAOF`evN% zd{Oz7v*lxbP7Ekaz?zV0T0i{|NeCI^Wq^)DgNR+YiqOE9;4=$g&kpM`-)tJSUcQ|z> zasKgO|BP)?y)O#gX9TxdZ{;d{dMq|mDr@wT;D)s~t^mU)dUkMgk;t+)3Y?#^V$Ls| zkB?Wps@r_VvBsMF-kc65gH9VhHVo?uKAYcN(*mAt=qQuosc%q=*HB0g`lcJ3@(46mHz zPk2%1;}2IYso%Y-&7R8KXdcZvUA}l8;M~PZrt1^odI*N^XSfYhb(vT+{^V=CouiP+ zFVQkAzf292X;1pwiQOOHNzCRjjcy+nDrNr9OoM_ZkQY>Ok)+v(*Z%y4^q9`yrJ1?m#-Ue0B8 zJlvaNJuW7oW=dZi*e2&r>Nn424^klY(Jd-Zi`26=t1^CnT+HbK>l8o5Z1rG9>d9>}9F@MxM z{7Tm;?5!QCT}?|DUSYKq5Q>%X34u?J5O?zMEkB{^QN6KGzZ-xh@bq}s?g`Rp$Hb^? zP-S-2mrD!h(>`H<94+DW)^-cB@pCTNtN?%>le)j5Eo5o0a?AA*%f`7SE_u2+-)ksh zC--alQhpSoYoG5IEX9cOJ~Y~$s^~RV?Z%hVqb}Heb^0B4>@^9Hl>t)PMT$EeZ@%>7 z80d9Hj$pxPuDA`rEAH_U-0eghOE-qs6sF)EHzXQ?ehLS?-NBE7=4J6;E`tkB-4);z zwEE8UA(VfejY#eY-3eMPwW4p)WhQdhII`*T00tfX**zJ`?uI$WgD2aiOq(sDRl#B_ z7{yMIAK=XNTzApveL~G-5eP)n_hSn(;Idy9nvo7^fqkcsnM?EiQ4pYwihD&;?x}yJ zqa~1+7iNwjTwWLuRX*`PU6e0A150MN?(RCOpZ1>HH;rGw((qWo9Qx-TvliiS%M2g; zzW1(xgg5bV>GoOovq;tpeDVL|cd#xGAk`w0d`hY1edwCnul%#*1|G?qka)KmaY7G1 zzhR{^WXyM95|uO6i$tP}^mH8jVNR!_jj{p*C}n?@ckG&7N-D?8{#EF1(>`C-r5=~i zB}J`_be0Zph4Lw$Rqb`=TbZZZq^v+!CbnE#Ex?Lrd=63K^We5r%*W1Vx2g87#quM* zP}KdNIH}Hc|DwC6(1%~jl3fzDm~T3#ghV_GLP7x6;6Wi2o)F4|9=xMPY56W+NUMb- zKTHSN-#BqkeLjwYlNySetB6T|3D)O()3QjxyIrJNDyGYc^<$6y9iD|q7@tSMIcJUk zydNL|s>{oH@xJ#xoFIn!=1XwK8p?6h(a5P5b30(t&T1iKKRP`haq8lg!^@k`{d9>Q z+46&#K)^NJ&xQybDbmbY96XwSuuBOyl6Glu-(q|5b7SNdpYJjTxpS@;?GWm2$U=zC z4=OlhI35{nEepr3SFUPJdC)TP_S!ACxK?t>G9 z1Z@qkV|&C#tu;+}M!vBnKP(rQ*28$DeE354vBxCE8O~s2&ZAH+^)z4@#bM|8=e_(V z&SP~(a)(>1jE|e$Z1bZ&8spx&iti00J*BfA>Inf!YK?V83oe#XFowRLOPo*-n~J~0 zM(Px#2t~}W%fBh*XuCK!;@h$s%gnc0)H=a$amk6hptM|o$6y$;3VA{2N zUdoH5bpOul%Z$_^zuQDhJwlSRvizpPf%w|p_HOuo-g8nqkL3sMje19MY!PZAC$P`Q zrI@wS+SCHjrHMGQ8#%^KbI=>XyezA6Tyh}MoZ^O7C5uH~OXemS?YbQvWD52A$x5{q z3N!5{H$W7OjK}V%zzy@H^u_o4zM<&;ex8oKCB!$4Rzs!*p9e5NdUo~|N1=#gbsN6e z+Ub7e_lJ&_)}Q47a#aPUjOtTH2&d~=8g-{+6f&lNBpRvfnRA|B+di3jW!M9UDwNJ< z1oJcZuR3oW#OQ--O3EOkFsJx^SQ!~L!bpH5MS0+@s{AorQ6;_lE)@s8fNzCBwPRRGUzuxC+?FJ`>S*;r4 zN`M9TN(t_mSv|!uZ4E-z84;8{2pWrKgyu0s60~Uq>x3b)wml^{>uu$5fTi9%D+V8w z>w3?e&-aN(I0Boxnl1y-j|xk&=NG10>P~e8t2JEUPxdgsTkIY{g_ZezTL^1f6n5#y6t&oYJ#c`0y!0yeD_p~kuL+u_HMlb)43uV{;Kyvj{qyQiB zkGdKgc2cKDRq6-C$oLDzSbbw&tvXkHI4_cm_FiJF(vfP**6sSUxvOFD2(1zzD;)wg z(o3P__OJIn5Pr|Rn3;pKs7Gg~IE=Cr^GUu+G3JzAxG!)1lcR_AJZDN<_V!0tspPwU z*1uJKl1Q>l9AxyDlmwFqd)~lw*#KxKwU7r%r6kA$B|TQ0v&Y*<+p#?>9(B9n`2Av%N55 z+lF~8RK9ET)oF^u@ry+k;A&=!Pw=#LLDgJUydFo86O=MDXdDBh@uyKS)$iVCzQbDJ z$Zh@GK2k1(b_DclyaLGe)9IcMy^-$k_b2%r0B4jwY5iWwKMlS} zGKowS?d7m*Hay3YfZW$17 zj%zDLb;$<|jMgQX*s1G7V{qN8hp&|zjEn_KU$+EQCv)(Xiw{17Fm*)9l?^eX)m7jC z#*64-UN~&3sOLl~NYAt-MAFX)brZ9Sw>&^O@gWL7IR(0pAoKLuAi4e8g-V8GJFj3qq< zs+$7rsy}T`_}of)O4uj0W5+ig;h9%F!4rvlNjj_=ap`gcoC|@o4&UH*XCq#Ju;zL- z{n_ULif)FZ=g~{S=Asdh+gp54E1tVcj@1~98eA>Z>_)+Slil9 zkNPyDO;8-xXDna)=<#QB+{kWMe2V*(b)>nvzL&^;S-r`4yX5!TqUWm`qvFB zlecuZeA99nY4*?K2(E#cH?TE+)QCB)pw>SrT6b(T7s=g0uD158h3N2v-Tip$_+R5S zVxZD;1jim}Nsp%-QTG#NEIWCsx$M~OFz;TiwTwl8>TZPOPN#D<^d8`FGdG<^f2hi5 zT`zySgI3gknrFgx^(j0r!m;MhF`3VPIyaEYpJioTULG_*W`L@ z_OA5}wfUSLDa1J(XE~=jB(zggwYb_zWb$`*r}OL2dU|*7uu_-XH)-*CJ9(5S!`+BG z&+ew2K8OBF*p1DF6h)?CQdRu+Wjrdx%VD(&D>Qa&-Zc4XF4t!l8cEwZh)A-$si;>U z3TtKJ^bPQG3G4~@%#mJ<%IEHbya$!PER-dhi`PswR#>ceIn1GO-$~$HJc(LRFV4r= zO0T*!sHy@`LzRjqCX=k{Txi~wX9K*Rf z*80z;=gkA9d0j-sCYG!%zJOV)%k$;?`kBC@MRFL1j2nOOwyu_`Q7~(RvKDqogsJnx z-bavHqjaT-jyT8eZ~Xc9Z>Is<3f`anf%)Pe`L!tW?_~ehq@eD*U$8Pasui?aV^YMX zRfj$GPA10J=I|Q)aJa?`F;OfgaD)d!-EQBryz~BCy%WoVr>|y{O)6t#Xg<{9~tPJ0VDC-BiY=+bi{b^IkyBF{cozD6qRtSyE4 zmakY}9)ADN^ZrHM>cAH`FJhX?%@V*2U2Q{8gMH1S_^|8q}fUYNf~yM_wDt@I5D_Ivwz1AIOkd1H6Pp1=pU2>A`oB_3zHNubd;iQ2p!1K1TNTnec96CYS6A z8@&gs`8|4b#CvHEg2m6bv`^1ex1GXNIg;oSXQ*Yz6B6UX992U?G2$E z)L|6(2#3sL2U|Sm{Y(q1t?t^RO_mG#Y0GnB&IYqtY3`X%V4}{GeI$Z$cRFy1N+LST zsgioxWJGQTykM^$@+ZM?zfpr>HTigJ_yQ#!lq>aN%ltt~WOUyFoP8NCl}ajFZ{y?*st!FGsy>OZrvYk z_xxt>R?C5!v5T&+-HJT)zZqL*Q(AU)n};nb&FL;D5+_|x2meD7`(F-*-WJd0aXEr( zv%j3ILu~WB+d)V)Kx?_q8pbl6P8`(F-!pML(%#iLH79!?U1KqzA+Td?Tq4*kc=gHr zKBg-ZEz46zdfK-;!8jMEupwVg8r`bhPaC!4bS9;beez~QI&JgTha}qk#3D#TqSG*Jlr@oU>=Agt2p4V8$`=;?pitok`$qV$K^G~F>t2*87 zjF;K$6&>gr*DHSE%@6&e&++j08Nc!#?wx~i)m@Vm*>kvi^Eibb^T~|9Br6U(AG43; zQ4lz^G`qA=)yHGa;9t|#;`8A4{;MjFobWfh{>tR}Mm6Jlx%B?C!8;4jx6@6_rZ_*O zHOfJ9u;r}Wne2M!UxI;}$V&^1W8RoCslH!lE52B%^)Z5?U*xA)dETl8oG8!rsicVe z_0$S34ASQNc>%YX4fQjA@8=%?f_Yp_o6>%-x6j_!KY&3R2M5g0za1TF5VkSjQU>_8 z?=o)*f5X?ahz6*)Q20i|6|ZXxGgr*u+B(-iOhID)gN*HG{pQN%$ahw6mAT)qaen$M zn~UyqBmy{}1`#bHSExMSDBk<#w4TQkZg594R6&0o$G_-m0eBk?=CL!)xgW5+!dEx2W4WndvM*XSMzOf zL`(X3VL|QweI~YlpNU)HsCX4I+_2+&za}8j9?<)`e6HK?9ud{Sy$bT4l3tdGB&<3_ z4l*1UA6kwYpATkte(O%(lM0}Y0xzw~iz#>>TvA&P?$bbthC@3n%iX#{vFqRWsUAI7 zHS&VHfShgI%7M#NXD;4yhPmWvL!!b(Hj@~CETM(V=YGi?U|03ed)KcVrc>gTOUrJS z!3uj3nKb)*l%1cY$OYiBY^H%Fd+UDfPovhqQUlS`R|FuTj4VpnnG2=`Di_y#yj)j7 zut^DwI)w#i<;_7Og@E(>Tuh?RNPBmR~f)coJ`h`-=PO}rCkH(jIA!I-~?nZu0Hhqcox7RfETE> zh63_&_dJ>iT;Ma3lL1H1;j6mdMl}*V#POTm0bd%xALIEZC1OnXK>sNMxEDRika&D1 z8Kx;6@fpJG?@q0s>G36p5NdOspA7rD?cV3t9KcN>Klw3?XBT|6&1+|$CZU7R zY`r%JY6bp<97M%Ec`Nu+=fml;drg*U86Ai?ak-i@A8V(ZSJM}VhMH>q`7~6OxT<6p zBc$i%i$BzzNRa=6%Ld`w^6xYBGX6e8=QsTl3Q-tye;@TSuulhiceSUK#n&}qKj9XC zD?5j}CvPs~KtY*I@`&nIeNZ==h~pPIAO= z&W^}AE(Bu#mRYYK;0`%YUAN%5JF{;p1G5~Te6dP+d=ZijpOvVWC4H@A+yPo{T1ZxxwJ1Dhj!CwxUgaqlu8h|aJd zCueve=FleUlVWIqamD9&&-EaphEt+;<=%k58nCxnW@wbQ+##u#LEh&|q&Q`AJ?!S1 zOS68Y1&ek3oDh2|VS!hpyAzq+50+Q}mg=0(h|h(&OVX(xLTpXEcpoz50Hx z-Ql)?UDGqz4>IzEN?a37In-k%_}Z&-0_XLsmYP zQ7O(ZpPX`gJa))J3eA9l`MhvkwSR@;lYnRHS=dR>p0x_|08=6iux5_KeCR-r4^Une zU+zf;3X+aXpn?g|yb(H5|*ro~&}$ z`s=!{3G1Z&xK4hSythjH%VU_Mi?_r3qM4_#_)Xa<0Y8-UZn2nHH^HovuCBpIuG$5E``r;+@n4z8&P$_Pv4->kv7 znaGNz=g<9+%j$i_RQXhGvEA|1M(vNlC{S4PUWori)tR*`tF1@-2XO$>a|qI^w4xwq zib$uRbOOKrE9bkDZ|BNMvXiVe=TrvIsHf_#oJ@z3N4b%qz4nB-Dkt{#-AOMifohn# zI=1zD+tI9Jz(nWIJwHYrH7XTHc9OFp$Gx~WXQIX3mHh-E%m1DwMds2@f$;0N=~EbA zFXFdiv({E56DGqfuaU0&rkW=Q0yCdcM;Uy@{ zDvnC7TC%ssYWTWK%0LcE71QzM$uTr0YnO0X|I+1pr) z01({r{wDkKc;DLK`MTz-)jyfHsY!$yq2K9hGo{T99YY3#0=~m_(?=tH;ZU05Cl@_< zW%XZhfq{=o7|h(%=pZjD4iiwi9vNeJ*>vIoAmPbGT_* zMO?sZgt9qQo8SEr&0FjB2{(IJYz#&Zb z7oHeJj4)hjLd;AQo}v!&ii8oqH+1wmWU*Y6$ml4+t+D`c9LhR!DgZ0&HM%G=v*ED{ zTDgYLn~!n8#HGaRW``@lqYPAc_+0L^4sGfT|7Of8@w224;NlsPHd3tBAR-W*yW}@l zw%1}^8*OQ{H zJn@}xn9}oDbcTYj4>sFyz|XWLEF5Ch0!OLE?#b58pHEZd zMWi!z?czzW6x8)P9 zv2f!3JysNFzq^L#Nkg2@?+`8FJiex=sB<*BXa{O08x9&E7|r(UaXjCadlpKj(5IpJ zqQ5q3Sh19$q$Kx6v0z;PWfxn_L+r)gRqKY%VG4a#^xN+j3)KKlXg?Y8F6;|jyGCTN z347KSBTc`Oe-nvk*oJwPDrkuDUw$QDSGAZwO2UC1Y%rdt9TY0tnLml5q?Q0yKQbjy@7>nP% z&MEYO$j`1hg{nDQgAvCB? z#fEIP+)eBCRHIG%c>ayrf(Ym%f=xbtXW=W$*vemb-YRZ?^QP9O&nV-;uuG3z8cj^I zG0af43521imeD>sS?C#S#Q)5YLu`flJs5LDvNI82C+1OD2f^o8FPsD;(N>7H!(C7ZvzecQ3V#T<8U26COi`- zG7vdc(~c)jg+ah!KRg2u)k(YF4&0z3K;r~EGnomD#s_f1h>|1_GPC55RaiURS#ZqD$D`FQ?pmodDxZEpB{m{_gd=SrEh1 zbxrQaCZYYS0B{&E7)rlg+N-f~Y6ksyREjCU;QQxKAOGy~yWPO6x$LfKe)TqZw!{Z5 zwjlIo@Lp}&46z1V4Nnm#deK2UYS@`=Z?BlAX6)lR?Q{yx5t;ym{VKDTs*DxIuGn=S z>cI@Pz3&qTmT&wjp2kv@x48aH-!C^b7T}dgGHk>Y519JI>1;ow23X9;k4bUgkd*Ae zBXfWF{r%@*As?cs#2d7Zt8%irxR(iNVw95S7caRKBts7OGi_eKcrWGx?`?5ZkAYUo z84(S(>TB`o#QppZ)b4VE!Tq5K5G&^WgHX<=_NpK8W+-PV0mgtl*oC>(%#Tor*ItH; zDwfM+&Af15vGC#a^!xBW|K=ql>;-r@`j{Z}R-san`(IKY_{6Y z&_3=dyvXo7-6Es+B-44}^*_n=4Qn48zVObL9?_*nrz{TjGbj_Tps$@#H8-p}>&+^= zk;rxV!b=(f4>+Wcb0V0!SF?VguImj-#Al%^395h`SAEqy{r#C{F3K5DzYv2NeI-B05B@e9mahcEQ>340v+U z!E;8!h{xXv>Vhgmqwo*Jc20{s4E^ek5{viE8;~(N0X}MZpCXVdPdFZ~5eaqckt~B6 zdBU$@SZn(@8PP@cZ2=jDzZClZJ?M74dXA)ze0cVkYJ(j##c;5Rdi8OG;E#I+Xm7$f z{@zfy;okJ$`FE^qH-B!YZ$|*mv40%WiNI!3HeNJwJKSH=&AYx1$BpvkNK%%|NZ26c z2PYZE;}S2X1#;sRe!{l$DiBc7OAw75aVYpOU&k>7FaL#Rz+-Mv>f;0m$?1tJ!^uwq zPXrzT_vy*CLimL!;{yGJIqs=b`sXXmS2D?$a!>6dR3bbOJ6uv@AomU?LJ9!a3G1fe zlW~To`KNf{kp!U6y^)(jz39a$#(wlh725Ik9tl!5?%Em7Czhw7vC9`T!EuB;JHZ1f z+&mvG*T0b;(#etNGzGGm@^23Hu@{36VAAteH+S7sfoGGM(uN{Rbgvvo5;M(Eh{O!2 zLVU#M%E^Q@Kx{$m#!kV9b6Tyio>kwjQ2!riX*yOCL8Sh{U=s=XAq2A2_~wE!t>aLc zy9*6%=}=Jj?)aflu>{Bb>9*ai_6=|S1UV)Dv?vnfB<%e_^QrRjfJ8n(KDUk%-NcpX?2Gtd_><168wC^vk>L>j!F zceKCf2T_8`(@~>}B_C4$IkbDgi+|Z6L`73#KWJbZqtXeI=%}0_^x+{iy-UWz|8hX+nt@z;>5Z|($W!?oWei}I~;~8{*FF18QalhxU z9GJFJFcSFqwwv^IxnD)Y&Ko{69(#v?2Q(2$mkcl8&waf;96#D(<#XcaksCJ#!|l>V znn2@fWt7GO;%Z_(;O;`-UjTu}qKh1e=HxtE0&R209QHPvNYqPo7dBK-$rt;4PLR{; zj+Y!7kX}tv2qO9ZrQJ6z|2XUyHlY)|!^?JX@HpD0BPYjHn^dbVL9$ZQ*j-aY8Y8g5s&>ee;`Ou$i?tA850=-HrD z>`GPoD~Jvjt%N+m2?PlIFXHN_4&jvpMO0(2`1~~Skrr&21LB3x04*7!2e)vxl+y~o z|CWVCN5gA!%HU5NClHRj6ApY?xau`p8`|ggR>0)fIgg6{diqnorHqxx#+eJYPQ9${ z;q55);-Rc(UmZ^`J$5P7kMqmVuWL^0j!KHPsWnV3_{j+qh7TCAwl;J{*^2pv@MJfz z1CO~&*{?%{!O*2Kubgvl?^h7)$0*UM<4yZ=bpBB^U8b(}%k*eI>*w0|XuxG4OT zEPnwjuOuGI@Zk5QiNHM*vHP4O#t9j`>;5bEXKAg>iAtuO-Nfbbin47<0&7VM8TPvw zo6hkV1R2n7vs%@mY8!+ktbBFWqZ=y8@$3)EXUD*Q0Wv(wiC`DTwlZ7BPEG?o*=(V_52M{H8#Dz@ZO+>^us;zU2ld~#+~{- zD_I1-r%NHXprcOg#^s;QTjQSlX+#hP=l$kWY-fsa)>|gTyjB5((Grd~wSaBF|A?i9 z6-b2p@b}y?&bD_vM>KOt$gY$j~*jXavt+^6plOh^k}r)M`J{G11T5;I!L;5PIiZHuYy2v!@LSB z${JqrlG@=sA7m~@aTB2<_lo9K<~sTI&y(@`=gAOqOIG%Py+T%DhzL z#1ju+bA{x%ceAW1GWW;jD5x>IQL96*o)=|?FbEqRbXn|CWbqL6|1$ELP zRProEk<}ldoT5@18QWmLaAE*rf|+2|j(~Y^JrdKE4s;}dHdOKYd`=I7oPLNq1q))7 zx<{RZ{7sb>yho=I{^b)&+A|yNJXW54a`lX*j)pgXu{S>Utf1YadAxO1c2|(x-p}MY z4WIgHvu~K=|Ie8ne!6#OsqQKc#Tm>Nw2Bb>*USPzHg7YXcIOq`Sq+Pe5d}QWcElGH zJ1LAxIHa2luM#ym!0z(_&VO{7uoX{k$H8#LNluH;D}!5KfJYZOo|S=CUFLA%PC-j5 zyA>U%d-YyO%w^+WwnZP9IQjNeqvp@}hkEY1NP1?=G8-Lr&RN|r2x+PFhuq^w4J5-wZ zpf5&;cI82)?2dnhg-C+}bo)AnFy5Psa^$co-LtM2 zjl>J9@?^qUap>dx8NM<7_Oq{zHFXSM#;-Gv98yAAxoQ3dnlZEFs zHN>FANcVuhhw!;@#aHpQ%u}C#b2S0J0whfi|cOc>*#7_xq3JPNN@LBdRPQ zrSPKh%LzsX`BlE!Sk3$0d3Ze?mkfK30fZj-X6Kc(| zdxdTeScL79oclmK>vgx;f9FteH%`jfpUrxNMrCGnI6W_cW+{9_Bhg&%e0HWCG~>3U z7rI%9h9)zqRmCfFdK2Lru=53 zCvJXpL%!`gyhG*jnzMP(OZLUFeqr816mrW^^lbs>^VByQ)URv!MMOe zx;Yki=eQSF3-&HQJ5InAP z1A;5W_44QopBIjF*{>~p6uYG07X z;4gN!tHHD%9;@wwNbp~?(MS(X5MR>UH^Us>ow5TsY-ygp_ZvUyKG|=b)ZmTE@_hj= zLMPr9DZ&mZFK=RTR-v;s*L{bS%Kh>DxWZ+@PDX{vK1|2OQz=OrzS^;{%mk zThh!QOrz;f5qjN#L=trdd89yNyO@ri@#-Fq?HM<7@W^LtY}kCW?v!t|fUu6xxZiJWOI?VU_N`dJlxzz z62z65?_Ykk}a(rMKNA&im3*67i9jgcH4P^1NOiF35;5f~WhXu(FX6Ge0{h3Nrsq}aV z5RfDOd`0EHd?$#%CpV58c^#HG>uPqi;eR6zxtEP;&gB6tkx^?756RQD`0#!28ghMz zD2O7X!*z%C1RUY2_(sO|>eb}$zh_Wn=HripPniTyr+uWPMN+=3*~w^<&onw@4+DVR z{vtdcFsP^Zu&Ji@ZovQ=duGqE48fdc1G*C@Q%-{rC%O4~#*w>-+V%?CME|i4-hgIRwRnd{~KYoTP{SIA{5;ou`@TSRl*MN%icQj$H#QJ^dud&Y#Wgo^-bt`G(Ml zrdfLMEcF>o?(@3A#wQ$>O=59aU*jw=In2~ww%!gW>?Oi9fZPl>n4k{c0$U7<$;$LM zha?yLl1`U#eersClnFH3K5~xBRaIrR{&_4h%2y;uqOg?*xl^N-F}{?LrB*B@lx=6F79brcWqosBQg0U z=1emZj+8US6%&j1nb`O1g%{AWgJrNXZ9zVW*aY_)@d84!*UaOVR^|l#ZiJ&dL54OP zDP8#TQc~3!+z*P}UfrIX*(9)bZ?EWTDmf~}_>NXc*)YQ$JSrc6OEq zxB-5;b^3LUW0Ja89t2!=o~-&ed)!`gjHFgW8hbyZJr}lAY}f@+=&5j1MBi>hCxuP9 z@cSn~Q>X6pX#V1^*p!=Q{ytsvsJ!I1Z=&9t_wpS5M6A!(>BL#g@rsJ>d=l=PWB#Vc z`ske54^RuY&{_~MoqpNyYUoTPEfA3KfpA7gliEE-HI5;BgYkBUT;hB#@u_Jh&NJ)a zaw}t=sp++bl(%orm#`n+<$JllidK|{qWYI1VK%@-Ne}F2x&7;s5_~t}9e225gTTOb zo^QW9wLdZ>XACbNg zzkT6|d~Xy`dLb+ic7pjn68z8h%#ItIoECgGRHWjw5m8Wr(Y3y>9GJ61Yi}}-?Dp8> zc0XnoJXEEXzYi`dev_qKyypA;lJn*{O#YFNeSBJdpBJzE_JY6vXow8Utaq<{-B_mG zo@iMXvjO5TARoIx*R|UQTlIjs>Uy#PmJe1{XcNDC0*mz4K_vtEj>k}(7L^58U>s3M zsJQ+eZ7RE5I9HJbAE|)R2W4mPn$f67&!UuPf!3Hlgqx3i?I)ryl?`FL`rIKPxgQJl z&^+1en7{%##hFLkJmKAXhxu$$Hu=Q+9-xYi(8uBXG_9pBpyV1=AmzN2*GP3S1S;?a zm&oX_`1Q|T709{xn11$)-BP>3nBi|(!1XL5DiKM*K4UO+B$a&g0K3xxcw&PP=jEmL z3N-M}Wqf@@@_NLlSQ_aTdiU>adgyr0(u9cy>uLS8SfdB|1GG@*VEQ6*osZ{wR^QF{ z1v_C22A$nPWqUsZ!nvIzw5FNpK>Y+4?mnU%?EncW+>oAP1V{1-HdVBNaCzL5TghNt zl^Z0yVyE&x$ZEf%Ci=lEG)O%trlSQGcEVr$!j*d zonSu&tED4k=L>q%Wz=wd?|{1GhqSLyeu(V*Q0N0c?%F=@9#mLU?Wc1| z6Ql`Yn;fobZwkWe*<7aWTW8Vuu+lk&(kI$r;&Xg05%UeC@Nwrh=>PnTN9*{V4gYDi z+Iy#JyY!+SqL_ko+4Iw$suEE=X~kH*anF2;~0_qwj%^-M=6&uLDyu$T=^M~|5?p?5se zO(fjM0BGxKisyIWb4^02VTJzaSLSYJUBQQdFfU4D0@aMQx4qt`ae@)=wYMYCtKp>kwRp_=#xq zH&yrNC9&=>w4dDF3=*>#;XO|AD8(Qj4@xuOoLF9v(MQ`vPYzAD?rDl0AV|*Cokpb? zi5d{{UbdP&@Pq zAk2b-ALgyWHPigw`O4^{<=ETmp)HafTkn(aa6fSD1g_ua4nCZJ?z1JuPMpSNJdfP+ zSa7=>mObb)SBW_J7deCb=F}ezVzCOUqF&ZPYhWA{dt-_Z9di67K)j#NHb$=L{KPW& zMP}7*7{^z$_gHVZj>q@QbjPbm?v!pNlCXx&8?VYVgW*;;{7%(QXZm8}%=RN`d);^s z(FxD^TnC|jaNfaqHHx1P7Vd}-7B&So<8OP zAOW+CFztPCQ3wA7Ch5Q514J$}fHdJ)Oc zeF}ZStRJfFjw2N`xck=8;vsU^J9s+#i*c-W;g3(3e{Es^J6C@BpP#n``i)i5vy)1& z9iW<<_BcYz-oN+69bg;o6K=1oSKW=}9#FK!9YhXeWBm8sVt^tu|1w6)8T_331?~q_ zwD)CJyeVe4NG$JUQ{`}iq?4Lp@GV~`L|?-~(e8&6z|kNbV2&x`n{T^KmxNaCfXA6W zNe^`uUNu8e!_D+Qdm=1U3iFI?}ufQvC36j|TgI2BKcsGtu3hLaf2*wWM zU3ui3m3uEYq_HyVv3{Nr_7pq*nNHqf078}A4jNGX*>9hSCuCAOs0#17Qx znIiQ`-Qkpdt{l31uydpKr_L7p-?Q-H{Tr8T-`{eREZ-_U;f|_5(wF732K=@0PQ!v` zKK%k~`X~{1Jo~ImKj$qu#uwGPD8#O1@Zmzk;7abHn$~?)oA{S!h$o&>Dirt=}^9i%YednpNg7 zrtCj364vmf9c1oa%j34-vmRrRg2=Y{(%|u&d>4sIjmXjQeF<%$)O5ym56BGif z$f4t&@`Ubu`}uo()YB->5cM%z#`^l@(XIG+3qNu1H+L9ie|JFA`_ivHE?kFilTxb} z?dz8oxz()+bzrJP^~YaJt(*Rdnn3QppKrvLQ-iopzY&A`;R(KYn|&Gna;!mjdE9aJydYb?FzBGl8Z z{vH5L)f!Rx>6eYEhY!#yzQ^sniP@;-?u+R(;F+w~$+V;6cU2XRCtE5$T)r{RM!}Mx z??6|YF{_R5DjbN(I zzlLfCV$>c+QHDMAWIt!Z|FXyW*|ej)i&sPr-824%9o~boEZ6o>6E1m+4d*`8lk(#z zGoEp{oF*{Q>_2X^uW4WpwZ?loX0)jszBl`8e-A->oY}RwxZ!z23Y>xo+%@9v$Vgi|UzGlE7H8Ssl3BPzJHjw&MauTOEs8OU zZxUbdObm-Y9UhFTveH@Z<*la#Z2FuI_5M3?5AAfXy}z?mN~igA!o}}&IydJ6BjYNf zuIqwIk@-nK{g&hSNWatt2;ooUJl_%BMmtveJlFXW3ztZb6y*owmcey(UR$+(;9Op* zVgj36WI}#NXPQB8oI)nO`;hX=ah#B#6u+P)1~E!G*CDb`X^6^ie4t!S_IQ+}bcZ4*YJ&sT*DM@)ibo z#%MoZi!k0N@R~cmn6~9@N1NMW@aedkQEchA$0uB{2s!J)Y1wDx3J8jfT$MalN$2mj zQiwfVk3`SbEvcGEcbIG1%~=#TM}BwAuT4Q(`olupXVY`r%NJ))bbIpad*e;gRgMK| zQFn~m-GYu2Z{<&q)9O3C*S{S2a-Ze`RtR}zU&U@u-WrE@U&#YX>~%XCHP&E}j<-ut zzNK=c?kA>j-RCVV@IhSGFs4GZmSEv5T}2Js-!pj>0M_wTrfC3IeCAsxLU@`9PmeTW zsTY8(Rk7~Ozw-wj>YR-QeSJS?Me2OV-3MoXv(tp%>v(erDfX73J17K6pt%cOzigLb zX_v@dCTPjXaF2{Q?@9|8g-}~+V z7T+Ic3GYgeL{_!sDCbEbg$GWYa^}y3Ji2j85ab?`F6kX}{c;YhQbtTOGWd`Cf*=*qlO8jSrN>S6|?Wo#NYFli|CO z%kN+x?+xrmj-zh$C!NCdy~k!Hjt4@8fg`)rzNb& zQlG4*xZSi!_~WCG{dK6ngLymyiVW)K z_YT^7z(!A$UJX}I3#!+I0b~jg>bV|=w@(9ZdHBEs36t$RM$ck)X;^~gxTV968s4iB zvkx2@SK?u?u$5E4fOHq_VAQkf`*&a#IBm-MbCg;+l0SFEoNwjPkK9^NnRqwa|LtK) zNN-KP0W7VlC*PMbMtRBx0|S)1NA)ua2fJH{XdZ6xfmsVsw8S|7aO$Ccx92jziza=7 zp`qUqWE{+EcRNMi&T+6szZ!HtWcn--b-=9ZGj3-J?J>YNYDzdSvb?ZnnXM1!IV}Qk z8@3zc#}~iggKWPU2u_&H@xJO}d>M{z-rq5SxNevwUB?!r_W|0X3Zqi+GC`t*dFnbEe@P|Tr6%wZ$4#oC~5HSQW4XCsIT)o zO|IL7;f?Ej5rucKc75J&y%P1nP7pbiE?c=Pr6#^Mt!J`~fQ0@7g_*w=xsf#)@w>7A|F`7bDi?nwp3~C;`ic50blX1CYc7J zd*!6$Hw>S*=epL+YvG+uW)95GR}m^#z=QE*EN}(9!omqC0BBA_=f1u`0kakdLvI>ys+1V zRXn|l?$t&6Ks5B!gIQbC0D9|pPCx#=tC&^DcH1}QyaYF>`{y=Ty0K|sD27k`L5}QJ z%RqFD4(b%66gQo6Wc5zt!GiVvZ@zpVB_o3-tbB(XkWAq7gN;kLS@jh*-%FQXx62)$ zL$1%w`9JS8@P|=UH_|LepB78C3j>|A7U;CzeSJrh1Md%doFe_a<2cTd0Aj)lga6Jp zDAoAR_`BbC#_9yVQ-Ws!{6Mf=ROiWuRT3h6TvsBsWVLCBR50N_dEnD%WEOUBr|L`z z$0f%6l2o|rR$(Kco@}yRhmC?B&+M@p_FThwHWAltzqWz~+e5q4VqpZa9jvI}k7n1F z)fW=^ReID4>I4rO3WEu;dZcCrdP`Fkt)Tq6wXlnQuc<2Uxl7${Z<|j5lUDpQ2wQdd z1sFe2W<7g6d82P-U=?N*KAbu?ydF14cEB*$*%^q%*NED8&oTvQ-~`tk=1YoW(Sr@W z>*RPr`I~QkGmH=3dc{05<)yq%c@c41Qr*CQKWiV|u{2&g<5RthG@@$=?@~8u{&1mn z?cr6#aNTK>7oZ;J8r?3e;svgD$neaeoI@tpMGt=ASak^&Wl|i37KyiSpynZl*@a1+@ zo?h|uGbkEjWpZj5I5wW9|M4G>rb9Nle0$lnmCe6-ClqVybU4~P3}F3zAC}j!W@?`x zy555E8oK)Sb_O6K!{(Ivs2_ai$B<};!rr~-9!?zP`?;PVDO9nC#6j@+)u{#14(C_^ z@3<{~3dYfUHi9;Kh#0WX4Q88h^(if0OTzj#&d)+T#OU4G9dYh78tl^~x%}>$hr=<= z@|gROE|w2RmJ=T3^U~w&VQ_J5UyuMc;Pl#c2iwH^t|TN&;h%rTyu2g{scLxN;_h03 z;=*uyfQS@~_;3tWeK@_wGxT8=xoyrXk;mR!pU;)(wz#XHw+45WM-nuPuhi(*r~=Gb z+$S=@!+*L+;KE201ls0+0;+q{gQ5hnLJnmHqa6X5Jq4STkzD51AA;f@6)2n-9GRSHc;lfg|Q(iF1Xb9s3Y9dlNzhv4}KAXxEGfQE<^{Ho!^|} zt=0X<(ScvfIyLmQV5t(VAzt%&P3UZLF<+v+#3hRc#qz!Rb~`%=!gO;g=QVDQ;cX2H zCwVU)-rg#CffrTtC_!Eiv2K)qci4kX?64ITHD?M;&41O42H8^G*}lQzJounfi0^iG zbVoJW7BQ$O4c|-7r`@>7r&2e=ZucwsCukwR&qT}Z`FnLv#HGPIq5Kpd!S)bVxTFVq zqXP9?FvfV=R?p>xAA1XD&-FoqlKKhBIAjnlzMWYqLAyY-w(EA_K^mIMgYx$-3xP5? zi5G{6^<&O&P;rea&`)R_ztlm)Mrvkn4CJ~e)fmulz7Hi$CDi*+k9 zqrPQ%I_yLizQt|$V_`;j)_umi(>Jk?Tw|>Fst%{ruqS$ThWWyNVnZ46^$sm@N&$d@ zd1NtufW!P|<$E-C)w@Q5gS*`B{a5O23u2v~6Uy}=GZ`$&+0oHc{{FqYE^qc3aED9JhOSud83YFmW!*iX44xvyzq> z9#Oj|$JR!eqlRgj(XQwam0+b@|VD>UmUv5EBH?Nu<$)R2O6Cg&T zBb&l?4|^-$T{pBrWyE9N~M`1Y7%qTROvQhappaQ9K z_3mr5?6%rP_-+lBao|qd6mS&1`WC0{`;N+p%PaVTQ;Ex$Y9%5{C-7d*wVfH(_Op%- zf|5?Lc-tE*C)msHd*vjft`5&QYra0})Z(%srw+Q%dkksM8F4TCI*Z2I`5BnND)5rvf?6YtMtZR`C_aMx z#R9kTJiieAsB$o)J_c4)7=`*>Op9mousKtEbV`^~{pxwiZ(`(5&_Oec4c;Mcu}Qh# zq<=$u4PHv{`b8z{RaR;9*FDOccqf-rLJ$Mp)Q-})Pp>8RONbC>dlkNq?6S)?@>bMo z>D=EA7Fq#4L6+HHbrXCRBg(2pd_963)y|auy6ayptI}6!aq{lxSAE_gC!B}RUZdkd z6LD8vcs-Uc|x zNw44^cp2ctb32Ze>#aRA%LRHr8o{cMO1icK9$JS>JMuE$%NF0sM+%VAuZ!tX4g7NV zJ!#oFDtd`5DQyS`RrjBDIT$l_ChVqRC9EEA^q_yxM`P+l+0ET9Ii1T$BbehCQbL54 zOYR)5x8gU{FlsWCiHzqq!^&8dtX}b4NG3m zo70_6j@tuA!g+pMm3O7CU&Yey$V}3YpY3h%dRuJy8Rzqv8&=q>QS<5!q=}?zA)%0= zc%nazDsJa(^~aCAJ-4WsjQscqwLxSH#sK?G-m3DZHhOSyrOtjU+bnQ2z>I7CsiOC# zA+5r>y7I&KfHlO0K#`LfTz3?!;m`FRPhZ0$h`{My>)+?Xd}>Q+N5JM0(}ZQe$6ZG* zSZ>%LWN>D%*eiX8`HI4rqHY!RKv~O`WkNEn+CbO$|{X=_w#etp7*A5kwaCg(hqu?FFgULw|UcePefRAGSULiI3Uor^=;xt{#sz#d zT|aH4O@mVptjH@Un#vRDZAF}$2sE?78^xZNZRapA2ad>HkU z{&fU=jh&Hc7xD^m5P`0zq|;^n=qMzH2y z>58_)%$mFK3~dc^#x=d6F`;{68>|e`TY{HKXjh2Dn1LC4AnMoVt|v-_Cd zl`Bu676BaObN|^8=Fut_@R99)emvW%ckf#34lgZ#<70JpSGsj>M$^r~$)4oa{nask z)uQH3XBdJMyzsXEy&3~syAFSuJ*+G*ijPNRz&IZPppYDXRxSiQ*tv7zR{YPLa-`Gc zbw*0p>ckf80rSm%$mKg#!5%PE_(i(!1y~|5pg?06@jJ3Yt?hL4H+x|>akfC!P%mnC zDvW^J$R9l|GxOs1VCJ9B@u?8#Tryq*-Zv_51*m!3ulnccY>qoIDev`xoweiIP<7_B zk$Vc@vGCE4b`3!?c!A9@r&FLt>uO5>{a2eSRTqxhv(ybiuupTYf3j_A$(xp z#?|ySJz;wQ&dx&mxmxhZ)Yspg2w6x|t&gHe&8pdk$H}?XCLziX=s~obiR2l~`G9_|vJD8$`|jYP%jSr*Em82? zHtKLG_ei>x?0Ad>{Z`*SyotRy1{6s7!cV8~-+>P5=9&y}ADU*9%g6HE?HB9!yQ7$J zdLHc;oKHK$1r{oM>&zgVXFY%_y>kNJHg>@;oT&xJtSElJyooZUd{(qD4nD#;7zBwB zbcDRc{PuXD-338KuDwN!E+Ln)$pwfX5$&ZE?~+`)H%Gfry{CrlV8Ld36_-E%C-Zwz}RC;mJgDr?bD z0(VPyO~as8oE7WezpE{4(CSSEU3hq)(&{Ma?KuEBN5~Zqs2AFDiI9j|h)C{!0xU15K7(DIMnBtc%yYz14As?;th! z;#T(FJT}r~vP7DeW42e@S*L#m~#W zj+V0lziMO z#-qL0x&z6)+pejoyg~PbCb0$^K2veLa2rf$zw_qr87gsyrTc_;(u&;V>b4d^`WGo_ z;#1009;;rb6^r7&Glm~TVhd=EW(!~I^+AoVI(9FvnoG)O2p)*1tDWO$*n86~N^S(v zwIAeM9e_r=t#zuf2J-TUpD+9W|DCU^bq%-qaMetlDK|>G%=g#{%{v{;rwh%93x(R7 zc~zO@h9batGiLu6Z`*(^>Z z>@WOnJw|c92AbV0X#fXhfC$j^D-h${ztkbEtSUY9MXXt>cMV+Qu$;~7Ez`CD7q~?+ z3#boAj8&=8GlssET<+8M_iriE=KLLfU?fN5JX2|s{g_+qZl8J2ALi{hZA?lZ)VfOH3_5Qli4Wjp{zQ0#Z5JfmLmsKSF2 zS|0YH^)$aQN#H)JeoEA2oEbm25SPL$OSjg#Qq4UlN<8Bef_k~RU3^@#nsT$Uf~MVH zQy>e=sjDaCje_8sT~B6NY8P8AD$^ri4X+P2ZW}LT-4wx%{ig=c0J1PQFMR%TlWjsp14Tl`ITOMrdt-`C%+URX=lS=}#B2w&hzXzN`+t8HpKMq# z1%eNPym9i8`_a^ccogo~KMHu=NDWE>KA53a%&&MIt?j4`taN4DYPZ2I6+Slnd3L)G zs)~=ei#y*7>f{*k**+fECK-0P?o~X_=*ju>MjNR3{LLR`Zxpe5Smi%Pq-?3zrA8MlVp^X4o_?Qw3h&47XPIAa;8TBpS$DUn zmI3DM+dzq0?ZbftNQ{}IYJJ+^pFux!vnLO^_Q>_~va25jk9_GvJ&K281VGB|-**Nb zfzk8yI`pi3!@H{4z6NE34CjQHO#Am8K_)80;oS0l*TO<*G{B#>SO7nOMZb^j4j=6G^6~Z`7f_F*h2XY8k534VLklNA0XRuj-8n%v3#$q^*-Hy%KEH9 z42PTH=ik4$pgvx2wF{!orQS-_jVRWfnTn`J@%J5$@Wuc!@UtIqg0Xo2+1H=P_qDU2 zMVc18KwkX^X!OMZ@VD7qT9TJ{EO^gAAJdQl!v5pF>+j@i>&&@1*ze~$(E!Kex@WSd zHqP9gA2&Fx`k~N=JUIj8xFvAC=gdxKpv7Iwz2M{ZOhMe4KRUu2x9};e9+7wI2W(Zy zp1^m*!Pm{^3iX4)r*d~xvESg=XM2L{7L0^r%u|)6ZoWX4pRwU;=XrLU>K#XS*h`Ov4_okbin-}hg{yLs6XMfgnVb49Sm&FGwe7Swn zMe@;O6B!Ee_r*&B=2G>@N7YS~L9do&-hGB&?#tAquSJeL?761CDJm*2XCapN2ft=) zWZl$B%g-KdIqV84-+5-X_Pv&BA|fpHac{V6k6!RYXjU9n)=Q({POebYuWNph<=M|| zgc}}4plWy&At%w=?rLAC*7^Cmmkq=*HmRh=bR9SHGg&6Y7$`gvCc)=&tV?)QSMw)1 zB=!x25K37+p2!VdOW6o}uhq25PP6Z|jq>2Sbi^#jsl3~`Nzn-7p*9Y{z z`MwZt=WB8uck@{+fj2~W$@X+<42<&?FeiWPr5l@B+I1nLwT4?3AuHnwuH`8DA+LFy zuJm3!|2#(kR{=zYmv&OcU;)D^>#R7pvj%m;DbUUgI4 z;%fmk<-@=~4eu3;>8C3HT3#aG#>e&n}_cf@@2*3}HY#$Op78>zY?ckoQpd)XOOHL5h z>gFv*cm8M1nk=V-$s3#8ie8H&jby<6?nYhKmK8AqpUSf@M}}y<;wl3ySfu)$k)U}k z3NHdT)G!u%$Ma@^k{}wDbJzJ!D%%HY+)y_hq@md@Uf*qHzlZJ3*nl_e_$on)y=(?x$D5bl zgq`KhnDQ6?F1_FnTh&&S3mEEsKavrFPPZByqIbq^?@YXx`N}y3&*QV7u@N*GYVp|v zr$@h$wjZv74<{A$h&x7|x&Yl}67DWI5(3@I-Xsp-;4$t4s|6^XXm7u-N$6WOySYwm z()TW#xCnD35oy%lH(uVT_oj*ei5^;(Ki!3$RO~+s!bd z$Abu@Deya&+gjPA^#q!xC8=s?t}RADbOH?z;Oa~?f;NrYeEWFrR)eN`6`|Wtthc#8 z)o>*1m*bSeu^x@+UDeiUaSIKIoQ*Z$?&;ddTo4(Y?4e4OAHurNX^MfP5knB@1)4i@ z!;q-7UfgeY`HDD}bBf#}(~fs?37@$~Tfxg=wcE%hu#cMtT&Nwl7V?~*k9g)#{puYm z6ixy1rS^)fwy*H(@GPGpsuK0s4fgu))$kk=1w60(h#5nNUYn8*q3 z9U-&u-F5CE+X`5l$?kRFRjT`Le}I2iI{;u;@8k|eGHedJU9pa@2```Tyk#WSj@Mx3 zi985c5D$alUFhJvktMa1<_yu$HxWroUOySw^7zH=kPn82fWMbE594W+;&JaQ-dLuO z0v7EK-Qyg69g-6A7jg#OBXtRGf>OV#I!dvWFfDMZ4wwgs?D$nct9~95O4F-Lq*gab zb~n()IE&|9fI{cFS`M`hi#Ha;Bo!g!LWz~b!_eyf#Tvc%@e9n+S1jhi?^-FqyBP6M2cqvd(i24)G~ z$j|k@MBc!HYqrd^=Mi8Vq!DtGi0!j75!>*qj!kyz>Nzop=W1?w0Z}b@Xjg0YzcDX_ z6aL=ot^8_jkj0S`7bMV#SLKoWtwfn|atWF3&zkF;Js+RP;q->jnT*=Zc_MgL;kRRy zt)I07&&eNsMGTok=k1Y)y&Fe_q?%Vaz6#4g*0&(=e+Kvc12^0ySqb_}tMeG%pVi)0 zWhfUZLO)6)II>j7A7{}; z$2;xT8~D@a&qyF&s4y6?DIhJ~|LLsOZ}1)?F#EJxU*5`0LZ-=JW4ab1KMLS;d-_># z!Od>&EnsYSJX7!026b*Vc?ps#4_CN0S2BBw|I{yjPR|-vu2}eQeYp!3^79}tXM`2k z%Xu+BA4nqkU3YOiQ`A<_4ZA0O_VYnq6F3+6KBrg+j@dtp;4Yb4;#IpXbX{=;qFgM1Wkbsd1l;Puk?&GnK&wuD=tzf;lNqd(wt^_aE z^TmZ;0JiRaOxUm|D&FuE``+S!9*)Y(N)IM=!lnSfgY8_al-kMP?}UT?yKdfp5T|{E znw-q8?r1`ObXIYc9l1sGmS5Ri!|wl7=kH?BFOm)h_Y@qk9ZMdUh;$i78Xg?DPcMr$ zd91)u`mXI{=PmkZh|LbeFvYxCFQ@s$^(X=>n!P=p_wV|mzop{=5Y{j?N62Q&A+Bb8 ze81f*vsdd6Y(Y0yS!%3W_o5+2_bp`75q7xto>4Yasr~HPx0eK2%leXsAK?b;THB9$ zG${Ux3}BmEAJB09>;*m>Z$H;6eL4o9Zh~sHh8r%#CnkgIMSw@MuYRwIVjr(c`+<0h zD27Mi4zJfw+#jna*4`&r3O!&AE=AipKkjU6r~GPzlePbK zeJg8uKJP6U#O|$l0-m~rwe8qWi z`(uAeche)yPf*MkJETD=xHlBinD32YjKOb$`^QdL{=S|vQ_<+_<~0!+lZ|@LjnUUh zwtc&37=3fM*RR@-107yY&Bda;-RxD_As;S}eSpOGc=ifx!9x4Fem3`H@zlp--JDRL zrUXU_Re>HCOFjM5+QA>nPvha}e1aQlpwKC6hD#T?)pr=r|HRvt+*7D_o9aXymh$Rq z$*@AC>)rFdh>?%>S>ty6u@9ZYGiElkL+JLJ=&SK8`!al6k^Hf{j@wK$FU$p8+Mnmc znungCQ7fX#b}J3F{<`s(4X9CX$PtP`>rb%b`Qkw6CRmu)scMd@`y77Y+Pik0!a~aA z1yUhl*Zt|eE)bG<_He)5SGVFMrs?3z`oWrJo&8z+eP0fH`2pCjH4dn2h7_V%w>)fL zF8Z50qJ4khSinCy@IfIdUJ-LIvU^^K7S?gU?76B{W66Dt%YInr7 zs8e&cuT-4nDKt&L_ts(md^Fiv}|k!-$u+$;k;~p}JvM zstv+truXRw2C+ei@VD2~(d&VNTjQLw;88&sHS&I89}e3%VGa-!DZuiV?hZR$qpW{y zD=U6A`;cROo#lmx`Q*V?8tWq+wD1_{#@=xrhC_ z6SIzghi&F|sFCeUCmevLKm|e7V2=BI#R`k@Ehff9l4Z9T5WM}&MTDhl9(A}_pA$+$ z=7OZG7?<4+^|v~v7x=(HCk3-biw|MxJRBdsd|Wr#`?%RZEo5#;N9>QUspg=chk*d@ zo5OL*OJRLH7JGQujB!Tg5%M#gjV^b=InAzcqxt$1LpOksHuy~;IU~Ih*UxoJj8v&> z*)F4AvTY)U@1%HqvwBV2`T3#G-*W`Cr|lw`w9{+#OP&64fYh7tq7SuwrLv(23~JtC?eUgT|;*2HjR-_j9xt^@(8 zx{x?h|4b8cSg$8R=6Qky_G_TZ{vNxpbgv&N<$LsBwt|A(Nqw%%g{EnaFp(S2k&7ry z5~c_pdH?z6bTbx?oNg8ILRSX+M~Ry5u0hg+-1no*EuEih8Q9?kFf0ny`4^}B!lHo5 zI$iv09V600`Gpm3?wRv@U(qk_?{n&=+<%{~c-r_^&2qsFbosRxTAA|;m%<#y{avG8 z@U->|Gl4R|82iV&F_{tRGe54x{&V;>rvNvy`F-Z?k`A75KXLILEB~p^ekASBc@S{F z!>^e)o~?-x4EO`TOSJLuyQVC5%`coVIVIiUVC$pewajq?Zsjz>4$)tSmydqqL@|41 zmGA7;i_g^$+@lyNb_}n8m5R}}EMH%Hj2x3R{p<)M7iy@twILFCUV)Kf$z9vbf=xRn;?Geb!T*XLp|#tf{~;)S zo`o%!Z$Sp}^In~KP1u2x>*$EqC5+2kk`$E`7jN=C;|{PH4#Snv52Qq_OSrxcx7FXCbilSv2`*?>t@xDWEI{nhLy#40^&q;2?jQJ$!af7uvE+T-`@7wlb;9hwxK*K$Y0MzdrE;w(ji_fG8F_LE_ozL)yvZt@v5rSU85fV;n_>2_ zT9Yv%3Fe|+KQ=>qiUG2Kk9RcThM}?uUfnkJ*vF;6F)t8?zSZt?tXD$+M(ih4L=ZyX zTckK26{B<#NPOJh7a`lF4!keUF1QvvhdBneriLK;J_c^_mI4Rg*(l;{bLb$Ud{E`5 z2Ln%lmyGusV_xPr7k=`5+C}b7+9u(8yux7wuMMBP_nTMD+CS^DG@a4&MN1Zd)$0%&X1LYyR&*+t?b_6>|z*E z()LIAen}GUsBE`3seG2Vj#uzPjHg817|HI>2jhZTWl?ho`4C}EvIlJ{gnPP(m$>z# zADmvbeTp^u^6+*aaad1}pzAtZvz40dUWk&G=^7rfTn3ro4qhqR)Ou=q`TB^o<|VuL z=JKMDdJYqi-FMxWoEc`CyeX|*^5TNSoMMw_mg4fd&?8vF) z^*uE(0Tq#m*8^sBfDfYzkcmgrX@%q+sgeBfoBYE#Gs|W=X z9#Ia%SjA@G=mvYs140pR+XdFJgS}1$2W9NLlyWW?Re7JF)w?MHi7y*aW_nH5q{Q3A z`Quuyx*utuyTiP1Bj5|XTu97b7x2lR9u&BH5&=UG<{=S~k$pZZ-Zm2tyowiU#5;2e zT0u`S3%*bt(q)l40I@BvxV0GNF53xMY^Dn1)Vl)rs^=pN1)|`3##ZSh>!1wgM{B>8Z^QcwfHDg!^I%^W-PBU5>$< z^*nD805b=gxufoV{HxEJ&-}aJ{5Z(}!8!lmxb}e1(MV23MQfB1Fd+-Q93X1n z?f&=w@c-K6|L}+T@yGr@|1lN+;~)O;f4BEP`)x|%NB_(J^~e8|()i8a{ZB#CR=NNA zTj0k2AJc*O!ykVA3CM*0@CQ7{gn#_q|4G_y*tFy;PQ#)N3(^YxN1TA?fBOD2JcfQ# z%>N#g5Aqm3y1oguvI|@CZ|{AQ2V~k;pDt|vHhhPVzQaiwh8er~Tao`;_J6I4=O5el zPwzMV&wutl{?p(6hc0|~B;ICH{PFMp=l=}}=6LeIX_G1Z8=9gJ*ho=-GbUa9H}v1g z@38$p{`hzQWAgH!Avr&<_y2f*_(S3>^~*>hvlDP8WZJ-^H}mLFrmpxuRagP4M!#7K z3&O{5WZkiiMa%_dwoms#t%kEF+`1G+}AL@xm zP-^$*fA;v2KDQ5fy+#LVe(sgG+_@g=Dp`v0f5!E^Ee$@Xz%N)bn|yNyQdH<{aAV*0 zEfQGKg^f+J)y&Ni32_M70#;{V8w4vW@B78fS8}||gu|yVq}z<1wkExmudci*cNb{L zFRiII%@ei+*#)lvhJyTDt;%e*0|oUnF!GDrvU5cav*2-E18Dv3t?P7i zg;oiV?M`|EQ0U2Jj{I2@X#vmhoRPrn{B|E z8sSF}zY|wJ%wg&+zA5Rzb!Q>(JGXPu<1a4dxPtg*XDcy6TR(Qo92_{;T3SGw?Hw5? z0ukSsKxSEKJHgfK$8$R;hsf{-=l72e>luGPo4j~$=PwIiPhwo<`Gc(GP(}#j{5W0z zO|HRm_2VT#Z2kQb<9U7~D_K0F-^F#hF5 zj=AC~Q`M3U*c}HP;k)&DygvVZ-uogF!e>DDwD>_-g9FQ#H;kZFway7LYSiN}unfbM z(`~`QCkb(QM)T;slLOsPCD1$gaUOeja+x=ng?fF3)z17Gk7^@s%G0EwSqKfM#%wdZ zP;jRAZ&ET|@69wJ#mK$P>lW!R`q8tA90^+RodKZzd@k_Qm7M8!Z{wpJUtabUB)%8& z!_9IzJW5!Gl5a8gYC0U?p`L$eOs96M!Et-qgZcwuO5W1uqsxBd)8C#{pH&716#Eszua@72AAXjz4Gkma!0Njn+no|Q}ZQq!lrq}Uvx+IqqoK|Lb zZ1T+T(%RP8t~a?EA)#JH>3+k3cm^44F10AJhJf6m^xk1$WjArzhrXlOE*Sf}51#h# z=*g+ttwTd~?vI5fbxdL1rrMiGdD**5T>sUI zC(}3y;KbznZeI0+q3Z(eM?D0jZev!v!tY*GW8RzB>owS5xTZ&^rapTq|DMh3)x%q8 z7c;95+w|7*hWGKMu!qjfJ)SGgm$pe9U{iI5ONCB!J_ll2GOEaM#w+3zB16;Op`TaD zwcef7HCa>Ywat-}c62xB;?pQzI1^dID4@osXmO@qBi`cF96zL1>1a()XArF3)AF!h5OBcCon`fY zIPe{-RisZw`AGDWzwzLb4vzLZb%#^ZzhI2$`^ezV~%=6*^*99Jm?hg`fQ zkOPDJ*c~~KYj}m;ykHO9vouBq?}th72*|} zj&NZGz<)&OdRZ$x1l5E42wUTZkJ?T7E$puHiY&6K=%kjuou22yir?qzNX;}Nkj5+1 zLT|j6GcJrkT2#hx?+*@7gkFJ6vH8ZG4{MyEI4c0FPcc`|HHR#dr+OIShtV=cJeG4E zCNlS+;wY)6d>>}_T*SAZA4SMvWoE|)e{ZuYx9K}~t~j3-WV1ai52!PVjk5E+?;k~n zGB+tdOSpe&ZTN4p-z;pk$9s83>MGY@SQ(3)Fw`C;R?rb+guj=>&li7Pt=6-3!ueF-<$cj^{6tbXmvyn85eh+_lM)s zKkhTeueNvX1qU5iVWW7XxCh~v4l2*shiRPEc^NR^r}^~ei}~EDqFR1%&-Sm@HB`Q4 zST;XccpfS;^3VE`eJ-ocZIoqu-+nIqINr4knU%$>7^wDp{>htcsqdX$fbEHy(VBBR zy)4Lby?aGL+6L1-)Y}lt`rmtdjpkiaQw^mzA6_6G;nlot71)}gC-i&P?*NxI96<&< z>bbS(+*u4*CR4fn(JQQ;frHGVq6U-e{ZXJCd1IaBM#;YnBQy`$qS z&!vVB&kQhnLW&)b>Olj%c-f&>bXz!~t2V|>%sJ{ljn=nDZuXK>AEL8W`9oRc-s{R! zBBJVMHZgk?MomM8Kh74wc7HMBX zQtaZYNg+mNV)bf?7vNLQgiuXFAbMrjGv2jdrKjWSkUhqvB#agEuSUmrnchgs;e9p( z$F(h{nNEQp-co+pbe5w?i|BSW-k2y5$IjJr9%NMwTl`o*BvRa#lkP!Xb#ETt>&3Io zqL;?}UHdg?dh|(3g^m??K}p_0!!~d31?6y^N5X{7zqZcle4TY$xoJ`?)&cly=AZWv z7T5Z9UGjUusa{4G?MBIad9c4BM5AuEI5Vrz7+yoLNay!RH{U*DkYUySq_<$iz3ZHp z`f?HI^sOWsC4F<|qtGWhh)c>ptk%m>;)nZmn#Kvpqsw!mP7pp{aI z?mL*Nu!jt19<0Tq$*v)$dU2SzYYlpl5Mp;Lqmk`4ubbBiTpu^Rwp+z-8DE1lQM{xI zGb9LUzZeumTLyjhGT)^bH4{Epk+`gYYs+0bm$-4{$@V;Emb9@o#p5DTuo=SRx=Kh7 zQ>i5BdrHG-gJ<#DkLHx_O{MGGj=Ch47(`y$y zcS$+%<$DI;z_}qFF?k4i3yW5ZTaRYB{?-c19Pa!72simRIU9fP&CkKmo{Efs^KpMy z&1#BD%}!=>_SBp*$Oh=aIeLy#<(Vs9IT>a@9{r?ZQdhT}t$O6|SI^8?9%+7mTK5HK4p+9lB z(aGL=iV+dddN8F!1OXx~s-%SrLAA;2c}xZK$^kv~w>)b*93tI-0sw8chT01ZO8fbv z^!w=K(uZvJekp~Zp1$J|%`Hs0Xn98|Jnw9sy0$hrWwR1L5=&cGHFa7%P7J`Pu49C| zGmoe>4?jENh$(vT?ul>^f2~>6mQ=|i+Wt}b{;SSj*1kGq$DH9mdQSO6@!@P6yyA6y zP8}SI7d$6s@CsDHmQ%CG67>hG`hoaCaF*Vn>{=8>>p9?i|c08Ii z5)>2W;9Y*yqaS3pRnk7cF;Ti8nSOg<34Xu47GJb zI%Rvk@2`k&7<4&Zjba~KkAAw>Pt1t&TLY^?13(Q!+k33--@`1>EXN>$P$m-R`6HXB$AgCpr2><5jja*tlu z#8Dx@9zS2>tK)d<86OlC4)GnEaCULHNuF>`g8T8fbNx<pPG;KbEhL>`8^`qE= z&fGS8M*eXIqYCo>VQ-gIh#O4OdhpxfL^SwkKAeQkr1P+pxPB`T=}}ljK5%gVaA)>6 z>~Qh#1hh-L2FLC8ev}%vWXm8(31DL(+$9 zC@_BXN_yqp_s+X#$F`TDJC{bNwd?4}lO7WLSj!3AFh^_+{z>FYaET%{*TSahG9{XN zuWRkQk-ToTw>Wacp{t>qK!VEBA?SlI4(ARB(o5nDmTBPSK>*cc+pxzOEd*FfZwmB> z_(Mck1Mk51ssjV=Kjcv}1|!S1!Vzog4or`=UI?9&PA9{l67x&z$JjwB0D@$Usi}g9 z+28FX`V;tFf2EHkqCY>MSz-+Xt$*(Mtcf$`GLP?%pR7CDvzBoC#cEE>L)X~H_uOBs zfkjgA&OGGSo&`*OD0X3>zbvbRQ5q}~?iV;N>=6_-tK}fMdhW+VJY#OM9IxxYI&=BQ zxY`o5PQhEB*YH%59`EDDs&HKY0$zusS%&!lho)g#^M1dJRJh4cL7+Sr7&}0|V_`^UqKU4rtgffr>`ad#VFG&bcmJ zdiI-7==Pd`AN={O=fDbY;9E@4AXh2hVl0py-oWbczwrv&nI|xodr8w03G0&nTj#=< zJbI$4g?);hDa$ADL|+H%zuqgWw{0ui)I#I~!6ZM{4{>_q%-jWr3V1(MV>63kl=wcH zo8(Np%@;>B>4{Cu5PlChH_eb`VA9w)$R*i5FG`1lNNhS};9nE)zi?FAWV7>zsFsssKafI7Yer)`4_1|7d@fK=TiX73FjN9lV#_ z6IPJb=CZqd9xMi7Az_*y?t-eL-e>%yR#4XW1->-WE;rkCx3%^g$ljcqWQv=7E|D@Z z%4Uk#;A2?Cs5^oCZAJDbVwz34R?a*-X24h3f7{l$m zZ%(eU<&8VMpdwIzJ6gDV9?bOMDt6Pyjelw}3K|r_1;3}9Z3Om|kbU}`g8Z_sTgEGT z_@^G|k|X`R%n4K(Q24K@sl+k9h!}i8xkZkdgM)=*$G-M+>0om_vApjKwnV7|8@0u0 z3%6eMz%(KVYVckc!fxTo<>3R;@>B&*j=O!s13J{LA>g9tc-2t102iNN@s@DjmY@GO zNc1LLmk|g(@!XG|cmiCx{K3rc?-IFqe>~ow_sBW^M(-mNSM+QQ=UzNifAQ>to7Ew? z<`-)-Rkhy%ob>VCr)LQhKI!ow$$V={Cs4vau;vSQJJO$>l`@4G^!DGq zMBayMZ!3I$;L6wwcns>QkBLEX=YDJVZAg3w$MkYOoM&#>W3bLjJY$04A10f(L9064 z<9xS#j=pcO1c7X#hHHP+&T#C9z#@DzNSnsryNw&DW221TYM8-hIB<{Zm6$oM0d|k8 zQ9SPWjMgQ2%L$lT>I(C_?=gS~tT-5z_xFOy&+#A6=2D{p8$pic#le({P+b^n;ZYhX zw`GEi+j%h8!{e#I^yybm^Sf{SGj4(U1M`$u>GGqh-co2ccmx0X^S9SN?EEz!;MP_+ zrxknM<52(ipHKb7iy?JMs^bTKtC?hIpJd)=ZZ0r&U4cMKEHQI)f1fq~;yL4A?_-s> z(9U&)^B8upjRJm+3!zTizk2=uTXH)dM`^ek5}?h7J;rbNT5pei% zp2%IS+_v6_XY$+vo)vEKjYQI|_C_EE$H>%!fSU^fJaQpDwJ-08m;#;SnTh?t!3;Uo z6|jn+6~#Mq$+`0dHug{WK}XFE)MC`B30NA*<-o%j`w`VJJC1ZjHd>gU!Of6h?yL4u zV^(;lCTl1L*ul8)pG96a0zNWMaXZ=dIT4Dvp0VpTbf z=p<*4(dv212@y@sXTf*jAdn8@t$@40_xI&CWBxE=VjQ--XF9%x$moy|-!tYNdyd9w z{51c5FuU74%d8ekPN8+9(@DT(xAjjqf!niBZrhUuvL-$ap&yR0$9-18)g0(I?05a=&2TT?nS4+YEo}?V110_-;Oq-ZUbQs`3$ey{IU?I z6pj0qkMXwRkHC<}ye6pIqx0q-r{3&WJZyV$y$~3lzEkwb`-}uSEdz2~Z4TfR%7^s< zM61PqVma=h9W0JW-=KWKo{;EmWyZ$5SbiCN-w!B4+(r*^?+1)^6GRL89w>$?3>YN1 zrRlZ}-;9I?UnfOESfI{7bLRTosu*&w&GIjNzb&>c-7vZp{OzI0>&~Nzyu;ekY}DIX zwii3-IYrDLccz&QH#R2LBMeG0WB<-7Ooj99hnzo7b0cysis@rN$n?NVZ4K|^f<78W z&QRBf<{QX>ZAHxMC1W9aq&HP8Fh11oY*WCC?~qjMSmRT+4>K1MQqvc#*Pfpar7cmdPY5@RZuf)RKg71{#4c%J@2=;KVNB8; zGa>O%N67a1v@lWEQXpO!d*Hnt(x_fM(0ZNb@9DgEK0=G}dBq(ZuJJolY^7ry^drwN z%G%{S5??GmS*TD0?F4I3zvrjqDkn?h@HI-d!A$9 zkQ{Q09;v@GmTK_6M5>NZO0aQw9&ieo;42z}I$w(%)Cx*>Jxz-8e2P3+g)mepF9W79 z3IH@8)AbZ^wuq?U+Pua}AdBM#^V{^t{FYdXLQs6tC8R`IFm!ogz2g4NywD4po}HP% zL*M$4eQvs0?K3dZhx9!-%ld80_8OwI_f^i7?b<=6IQS0o%Od(Kr&?#ituqS~oGyYd z<0&IObd4e0GAK~#C3l)M-01cI0`1GF*#Vd`_$HRYYB*ncSCxnd!Pe@)_MgihZDUm4 zoyL%&d1QzCuB4feW{gN!P<(YM7uSrBnnq_DB^e&nqd%W#?6}UDyFVTmv+XRI$>2~e z?XU`f$WONLK1z!>f%$9Dq2N93s-U9|Ge0m*c=y067a}T;`J|As4c^kTQ#ZBxJ@5ZA zkM>`WQ6M`NWs!H26>^lke&SqAD zq0#Mu+i;Hq<|3;n^#oN?T4Sb$KrsNklY5`6J?^!IT1dbT2T5%iaMd~QxEDMhF`ZpQ z-$}&8p*IEw>~y!cbt8#XUOb37Iw07h--^%0BuF%565Z{PJ;#T^AB&>M9VV!*kMwz< z?^^Cl63c2c90050Xh0JfHFc!3H%z3k&gno9u*DaG__(81dNBh@_9RP5YeQxEPCJ@K z2S6$y%2}S%4+7jR414#G1>EEk*wW_nu#D#+n+-UD_YNwua~H6OL(r%`3~6ORZnhYt zwJ7Lgiw0IQ2gFoKhvQKcJV}2|9ryr;1jJWuHBGzo{`x-OU78s{gyy{>j*A>$Zf#($ z(cLk!WEs+XK3URHoZwMM#iTGrIBYz>V~C+BhTgRcb8SVU2`B_sX&GWJh{ywR8-T{* z>Tn@6dR$P8;Y}-4U;-5Dl?cAZAzgl^TgzGkpqgwypX-DG?(Vn*p&T{>l@|$uL(#WK zWur`UY3+jqPuP^QT?sDj5}q&35#Iym<_HR}=_6^L$n2tC(A-w^Kuu{kfKUc3n9m^9 zyHy277lYD@i-i!@u~YMHX5zg{R2kr!9YI{H57dmQ#ODV5At~Id!l!I_Hi=!#Nc;R{ zDod=(4cbq9F#;RxGpu}E(1Q{Z4Qx}xr2L%nl|}QKas>Xp_86q!7>R5XkhCk_3RKaY zhvd~RJh%jGQ4+gvws=p;g4DUn|D+HDO`>4g=%_K|<#ZKN*TBi7hZdb#793vV$=ZGH|Bl{*YDpe1g@@68j1vk~$np?tYOu4 zuvtGiu63*l_n?58hkksn51fnL?Mr5`pBPc`NF?z-(}~ol?m+prG>6dPzX4yNK|UnO z>=lua&ylrokBnm5c-1Kf`X!(d*iVm%ouC++ZgJ3HO%mNQ;$uTX%jml1r@2Iz}!eY9U=&Y^prrs)#RLEACg09Rxb!UeUQl1jgb z_kB(85^sM*d0?aO%0Kb@+L6Pe33z-b^ok(K)l^MJ2wcQ(A-_E;RBxh6Jj~pWYezFK z7py92>+IJh?>13DXXx)fk~QNX`z>&l8u{`atXOu(rc>>6*IEui)Y%+RO8a{IJkTqIWGKkp$N^ivee0xy!%FS$h!hfvYFipo!sGkF z53Yqs-f4OVM-_tH6ZjkmGO<1QhlGfe22GG&mP~sxEa?cTtypU-3N;!=k3)rklr=sb zWGH>R1=Dx?U&C|zu=dQCx?X?HJmS^oFL9%PoPA4s<{Bf2m9TTPh6t}wQwm8_uPRLt z|JekHE)`JgC5dwKwr?arf;!1NaqzG===x%KqAs(c#;i-roSu`qAz;!~d<0*mKL_*o zRuGlM^AroJFPvUnmJzU>L_qV-h^LjQAA9l*25(tt21YtsM00Bw!z{sGTB8h}aDClp z?}f9b;dhX~x7cP*cBS8wq@lxRBAbpKsP1A1+Zm_R1reVgiP+zDb|`>Jx&?F~I2@}R z(mWhfqV;j%YZ6qq?WeDgs9*Q?>03wnGf@iGejuN)!EhIgD(CDi)|G!n_?1}i{Ot>n z9|g9s;`uU;_oM)Sr||W`oo<39g!j|SXK+@+un2f44Qg``0J8A)nfq2>9|i%87EKMb zCQ?w+^;9@_xQOfMY5d?dIY+p_L#wR{n=eo1bjP|F3<*+si-Ep+WAkBj*nIbP(}efS z=~Z;bdx}d&SP?w8=qiCJVf3)_?E_?tzS! zF(}G@M9cnE&E?eU1l`qkbxLE{Zds$~f$w+08U65Gf@C=q_k&$4%9^GHVdf$o@6n?H zZp$B3Y$cL;&i0z;p%%Mwxt(i+xE(t5e#jU>A+>v7=Cgz&qmo~yIi~~2&*qNXGhRq3 zNy!f6Z$#L1uqs`zDiS-TygT5;ILoKqU9pF_!(f9Ugh?l9$wCZqtT^Y{xzc_Z8_YPD zB7FcOg=Iz24wWi~OI32&(at4or~0+Lw;LJT$CpgBlxV@Lix&K2m@C#6YI4YmnR*g9 zPDdIKW}pX|m^)Sg_Y(ZVk;;X!YP`Jmo|4ug>K|#62Bw33A{)8s?2%U-N36e@sRW$SJm65+XB3d7xE-S(iB5OmGsO!OF}h}bVCxw z0E#hx_*0)6BK~}Rd5-Qpe;GC{dVT51xwluC-)@~b4>nmLCTeezZeSbR&L%`{$SEyz zl^S60F2CNqm73@M+r8VympDVsQTtSx5#J<=Qv0u_T77@El(U_eIpGW5C%ZjL z!XN+`!p_ZQHmMx#@YgqHk>mKELEP zcii=F*=ou7_!g}V(Y#NdLb$3~myrEmg}gT0g>y($O^hW1`mdib=(6+Aj7c;)Qm zNyo$BlnpS(J+;WpzBmc7cjv3qFTE87ehzilKc!0$CG&7bE;0~ml(23>4*RRL z_BU|TgzJGAHZy#}g&&cPBhX0NGnoJGX1C53i7igi5HPP#1hA)jG+x2{0s!7sXxQ?wSQjU4{LEFQt0N?6#l`;p~o6R zLUu5KIBDl*fohyQ?hV{9c%*g5@gJ<^A38PIVwfE4DOf;1w{1L~-Y4^RwD`aR$pO+o zVBQ@dI-^XSADn>nK&s6ZFd`GsrG;2V$q=^li-uDu_qt~QfB zW8}t;XuwW>ZJ-MCPbMr(7A@=mpXEDzHL_5WnXmT}|IfezohxP|-yQ`WG$a$ZyUzBn z6cPrF0eq3qpXGkZRw!}r*k(6tF4iV+(>F3oJ76x37Y^ma^MYWDta?pYo^@<#b8VnN z-w&fikg&m7i}nt(+KS3z3Vc0V!eb){Lq974X9w0Tl`seBD9X-_r#65Fbm5hONSJ5_xt|&EAa@?3pZ0HC};Cg^>}F1N~-?7D$?^ z9@;l{uEW0e9GXh=uVg;n@{U2g)%y}eHAV^qWET)u1U(sn6Pp>>S3$~2UhA0YDPb8$ zq|%aTk^dr2IbABM09p2~-7iq(gKc|CS3E(WuY9c)ZLSkACqcyh+i-k|fPs{c8D4ot zDzjh;(pyK^H0+d+6JAR5JjC(Z!9ccSQA>rh=43^^{rxlS*SSK7=nBeldn~H^=droV z{2}Qr4Dn2(*A7k?fOAUw^quz8+^D`s$iG61|7Mx5$iA+Y(^1TVPZb~#c&GiIJQNy8rJlE8K{rrb8^wso}<5v!>uSdCZ6$G z9$L1%A22E+sZY{Pt689czGhbsPL2IwNE#%7?!Xs>d<&ob6XW*Crt>SExMJbHZj2q| z;8;3H8wyMZSSuN#w@1cjwTNK(vRKW21uOVZ>S`n%ENkLx$v6Y=o8A`^n8ACnyBDA$ zSeVvFfd~H9ra_j1N_!E?7_&K;zjiyyjHi9-(s$o z#;j);wnlwE47()X9GH5_YmKUn$d23VWfstmBSuLG9K-tAgIINf2I5m;b`aSuw0qWt z6LYL3-`F6`I{@?tyLRb_BtKWaq_@X&E%1^<8V>R|s>;dY)Znor{>;`-|@}zlN^R%d=;5hYt3s z%RlygF8Cae+$iNfpU{WTjW;qx4By;Yfe7hT%)qh>hUx6ACw3r;g0!WhPF>@Erea_i zo(&fVW?INQ_4)PQD0Jf?>e{I9aYDYMjSv3A^E*LU14P3tWz(BhH7-i@14ie;rc1QB z9omJR0&}Gq=L0965m-;*1j^r?e&92F(Ms|M^By7r{NWxR+Ezl~b7iSgo5aA;kXjC{5xq>{tI3w|9D2T3||`N{?8B|G~dT=k4fV9cmIk#?w{+qvOJt*h?I}n2lV(5 z8N-W1J%M;{68r0uCBS>k&2{-mnXO~%&FJMD8f;4+H7Z8De4sDE9WeVjo{n_ztqI_7 zY^xgx;cuheBz3@Q)8h*3ihB=jb1QG&3o)X_7TUvcu4Q-EW?Rl!TR(WN3$Cxz#?U8W z`ZW$#CrLz2;hu0T%pdw;woJtHyB}2-SjjwV%^Nr8stP(I6Mvw)x|Bt;liIpWw&%?SoG}+Ij%qEE@ zOo~v7T@+tc7GFeU#*jgpv~r&3$jHd-ZntC1m@_h_j7))mWoV-C3950Vigc5U|N{rkrI43FqoI9~Led<0XKJojJE$RHr0Y4m853K$JZb>q1x^fTk|c&C?aq3wI0Vcl z%4>Dtv!u*C?NJ(h;f(~=`VDGuj7Xje%@Of5X}Jdf2yY-kV|jvFJ+aZZBkW|woCwBwF0jQ}Jg~_UGQDXSXqIULGSrnvFaku! zC7W~IGawDB5&S>EGeT8C9qfzasT(JcLC=Es`e)y9-=rE^0e2U^hp#T&y1+F^R4)JSS%v zex6pRNH*P!URv$V88NAeu!am;+h|J~831Y5mnK+4GAV_aqB8u3*w#2hQSvlJ8vhuW znTUOybfrlbwn_x(6k~?CcaDBniFQywwlGxkX$I=9xdBb!1^9B7=OO}{1Rhl%%A%b0 z?0kZ1)}TAwh9tL^XZ!8mY%&JaqwU5rEEFMNBv$%-$S3+FsHzc(!#O4S2rW{kNFfMV z8lbYEQ?yYJm_~54s!wWz0wrklg_LU{g9z&&+#~;RxLgH`0Sau5+x4kU!!mqU`kjrs zCN&%vDA7tFH+oJ?yX*maQZyLQyzY(Xh0Kjm7F4I;N{8_IMWZoVtfyxB>|fIxb2!*b>%5 zk`c)iefEr2Np*N;%Sr-$Wh+Do z2r^g{r5;QNcF+Pmr`xJ19qB zHaI^32>B^od?~aDp@w?1;}Nw*abx%%NW6$Y6F}oyC((u{7KVWk@l5h67sQN_NL`#Q zgF-p`11Ud>5|c@#rki3DNK>8`*J=s$E6^(yH3*cj_i(6Mj%N2evQ8R^_3NB6R76B{ z0diI=h>K%tbd%~<<|2k}w8HB7+$45GNrIL#Y5DgiqjyXccuP=7GE*HJV}{an~!@iD4;jYY+pQ5^V1X zF@a6nxBBN%Chn{hVchbV_-qk^vV*-q1+LEu!QmGh1pL6L{CPZzoWS?jaM2u$v#w05 zdL~W#9USSz7O%&-k@&kLOef<>An5C6&`WmXXx1upvKLn~Ap2Z+F5>Ww2#XrDhp&5P zS8?_Y*Cal)b*5_j;nG9iBJ9-bA&doQrE}~ebZCg6-_9oOE(a@&w+s`71qe+55 z_g!qyAu7+v5fDVVRRwuJT-PiB5_X^u%K-}Gz?O=AEYfE_>gwU}OqN9~h`dO(O{y_N zZk9YjZIlr*ycnDfm$y!Bw^z$8(R|u2CRp8YaUhB%Wl4{mCZ1vQuOaqJ{iRT zEQRP;^T)yrHbKpUHN`xHu%(YDnsH)RI+Dwc899R>;g?;)lZeBgPMIo< zM#O%FuvEC`Aj6Sz%PVqrYCbYNdehJbxLK7FmjZleGC9+Z9H0J7!N?!cIZOp=qJwERk7gU^pS*!GL$Ss&Q-r2n7@X+s(->XV)&UO^nvI0o8UQlNuV}b4$SG zAa>EUS@D2SZ1-S;OKxFb-;A;^G-pz)G`T_tHLJ{J4aDhNc>L(8KI1P5(V*1+tHMopfJ1@GjkPzi7;gtKJq4$ za?d8Uqu|C;s=~rvK+2m+!+A85co|~QrcKTdIP%y2rItvBGRw>s*E?B0>vRhp5J*Da z_PR^dQL6ST6JUroQE3gS%CL)}n4lnT2Ag#)KuLQ=ML9<$A~Ft8xktnfpJTEaKoXqF zP>o?_>;({Ft*#kVxOEESdjsYVh&mamA;@P~og5btpDPo?fXabkj_1^tO-TNw4Nn_? z%4ddxb1}}&iO`O@?$($E^WGe`G)Y8oki#0FyO>h6}6EVb%6rUYt+6<)<77? z0aT`tKe^d2Xu;Smh4Y|AS9>TSL2ButdXHH-LvMlnpocom?^YA~cia8+Z4EO)Rn3`H}O!QzDanHUqJHS9S_Su5w*;?V!ob9b*mJ;_kxQJPUk68G8%~!x@<<1N5yx(3^lRYS*B~A=n~8Vq3jY-b5~^khz|+68jl+C z$VaH4J)s}Kke-E@!NUr1L&b7NosT<&239d+LL7}O_!OGTHtGYXfYYlAblq46R)q}T z19shfznPWGW1Z5|GIXso`k9k>K5Y~W?1pS+rc6Y^C90O{@cJ9sZY`vPCLB`81GtPA zA_cJddT!+aWGT-;01N!_sL)exDst4Hh6$6jP%GqMLq<8M<8HU9G+CurK8XpiK^Aef zDC``S2atq^oQ9ZP0uoe7E53}$np(VED||<^Vn-hN33RI_5=^`yiJw_3lyE}v5Yb)k zk$=&xqXzjI2OO5mw#ri)JdjFE;sm=8jgCiRO@uv1)QaO?hs(^yTJ_ro{DBeAbDVtu zblFg!_Bu_(UzHIjV9gE;Xi9=04-AW<)W_7rNr|#=oHp5J6LT%ItYIEj)etNONH5!R zrXo4sUN^HA>c-Eo(k4M(7&Q@2n{5i)nok!CS!s-5dvI3JN#K1!$u1%nnHz>@iEfU{ z872&HlL+$wo$8>Zm)NyS9lr6VeaQv=leDW`>$v7Al}X1Vwd(U;dS}johySrm^H)@7 zHeC@_ncd$Z|M^|=pNDGAzlUFc=>9(b`?qeYIom&Nf6M-vAAVu~${&33(*9TQ$FJev zU&p_H0ssERAAa%r=k{3|W$BOfeHNx)41X%Kf6M(Xv|@iYh&w<34g012sr_B|f1q&X zoAys;n);+EcZf&T+Xl(|zd_#ruKS7pb z#p|Ea_lEfeY43l;b7=4Hqv$i~#AAE*9F?lc$bS0u_ts`fSHn^i?~P11OKRy8_6MmG zm`REKq!d6NbBZqrDPG#&dHtO)J^aOA|Ki%xGdJ<^U!t!cpV*&GGR^(R-@VkyzWe&O zAHH?@20n3f<)LZJ#dqC5|3*Vk3Hl}}{}H}|sra{ohpD)BB-8MfpSh0g;Tw;ap6T>c z`oHlld-n80S8`*l{|FOsrS#o`dg=c0m#(>g{VzT~_IjX|ey`cnJ!g<&yxHZoqJxGscSH89E5yW6<;>6NA*v&jd7T_)vs zF)44Z?OXELziIy^_n%_K?mxqS$eR3X7%M1Tdzek^lgk=^I-ltG{qL^6TIK z{`X6C38l|Vl~Sqt!xyFRm)KH?E0y?CNx1y1l}aKCrI#3n{A4O6rdndy62tuvzwr;= zCa;tCOVtN}7`G49gd!lxb>1-_lN?Sy{W&dx4j9<6OYwGjM@=$$HA}N93 zmsfxmao0^UVlo@pSPxxK@Cf9H^tgXjTHjF9Ea1EFu{L}dk+2c(zMdt(ksv=btn{1j zV(A+`Z%mJp^8V>uzUVH~jVI!{&Z`;JfZ0zR}Fv zH~0pp(BFI9;MYD}WQ*UvZr1nO$2UXzz!#qz`*&V{^TlI}mm~VxH~Zxs=d!PTWKXSv*jq%5vqCfh0Q}lSO z-B94g&DB4F?*Fro*8OjO{@82xkALYR-+Y-%yp5CGEU4Finojb^alQW2)vxE)!~1U8 z970W{KTVP`ubaU^4Rrcx&C}SR<2jj(yuV@ zt8=*jJ-+e!d+#9=UhG2uHJ*Np0P_>CZUrs!>zQHQidi2prqADdOhk`*o0#>R?-e3NB)R#UQ^?&-Jl-v;I z{=z%@`T@Jb{%C#u=Bvkkx_|p;o;};2nq8i=UEHWPH@1u4y((7srcC=UUoX7omM~So zW&lkbc!f}0cTjVQLR$);Ci|s~*c71GCA#A|>2E`^j>FGByKq6G-2LWzz5Y0|_k95~ z^w&UIsAZ3`I4SM37*?E%+MSl7J!S&-fYQAt{`tdfEbnIH z0x<~-0hIcC>&i3psKPdZQdVd?ge8Pn8(=Fz<9BWYqXY|0c5hoFGy1zfM#paE`NwJo z)Aje?*jTsg;CA#6>)^@7n|1KyIvW0u-)Q*VE8;(UToKn^UCafok3#pyu6~^Mo}t~_ zS1NIW+zgSd)H}!5jmh&{kUQ44n!=!TXILVp&ijR0LdkO*YwKcGyO<@3P41$q8m0xd z0&`u-%0itOGhcji`h?i@U{DIMBJWH}xf(mf?p6Av_~ccoLF`Jzs`&7Ba&KU~H%OK~ z0mkVkC4>tR>+7r13u0gjvj8>vV1q^5_<3iMEPe6=ZSNb&DZu~!O7RDuT-x0^xf#B| zvWK6>*ar`@2tmnL;v(Th-T&9UE_QGlVAqd$-4agbh`eZk2%C|KQNt}aok*d zrn7HfdpG8oU;Sz>cJr~fJ@w4jpDcyff9@$ayi)DW%TEdT-OAm0aJ54JSnK`8BLlt} z)a})02Jzk`Y<&!#e$%gy)85w}(bLKM`6oxsb?)A{`gH2}k2!VJ2Oe%Wbo}5~zc$IR zRBB)MP`&B!*KgyQom}Nh$zph03)aXq6iMcB8aybQtne3ymT*u!)tx@ zTt6p+zkv1uPdy0)xHC_XhOSaIK8+ZxJ8ED4_wv)vKKuMGUVXeJ-;~j?__S$oBOYzhj)qz zQFRcxK!%Q>hP#g;6ojbzx|*2y&YGA3$g58YjNy<@g=7?@vn1m0E>_}7yBBv~xL1xy z3(v^yVBRL)yr>w^ih>OK(;48AFIXZ=H(ex?Qu*uXV$O3l?U8(_8kvC*M~=w<1f6)O0Fy8 z%Qqg^#h35lBmd>cS{1K<`8j5GGvMd%KR3?zrS;E0;gmO@dgI13-*_tgyhB&}pFe~~ zSJnC}HqYx%uSd%}nfc9tKH#Ni2K)96d9!$b|HnH%ZaVzqw)D&>K4{ARua7xpKM8Bd z&DbtKpXuOxllgn^alGDq@4X&>u0N0b;%Dy9>MNUg`2ENo9xkD!pR0a=ZvD2S;`Mi* zmkn-4_f=0kH=y@r49o|M9ycBO8ZST7*Ed!xB%3Skf0F$DK=+Hi>(dXR_q!O(FMe5q zdi>n$=k7k!{r6tW-+mCzZa#8z@tL-tlICZxGToIvj~AX2sr@mD^jq&KK;8`My=7L7 zL=C*kCs!W&=zfA3^HGg^aqByRp4f@uvO?;?Qx7mS!+SLbZ(dwrNHZ8+eEN$Amp(Me zs}hFDdlEQ)Nwx6c_kp*{G@Ofz4%%PppyI+`IsHND_g?%!^&?v?l}kU+On8prH+oj( zww&~3@%af#>LrGpXy=zP5Kr^odU5eOfAaFF{rU6TpQk_g^plIyPtNQ#hBu3-l9$+c z;vTy?86#Eq5Py!rB~JnpE+Ivic>hOV_9?;*1Qp1RQ`6rLCjkaKXE8Z?nPiH#(I^k@>&-}e2| zP>Q^PyOCU$CeeAnb+;;Rw(Io@w&ve`V}m`}ny;Lf~ zG4Jn4-9z&kbI>BR>+zJ7WgU1UFmsBc}Ml@Aw9ZYcY8-u^Kt z{Q8%kk&14*^X%UDE_Wx{L>e~>!#!P7v9;`pS}ov z*Ph=0dfHLrV|Mh{-XdP!bpNf7Ju|5H-BGV;A}@WA2>U>cukr3PJ$<(hcq0xyt7QGn zZ+_z&Bw-}-_jdw4q$KzuFOvR!XyR3C_&!{A`2!1t5U~AjIlTV3%f#^(X3SVsmor%PK-YZKu8Sa$1 zOBf_VK#97uv(t;q?=d*=FTLM{+^q2TeFIDAZ@jSqpIhv2KJzq}=f&fkU$^@0rN?X@Tz;WX7Kg5A9V0*e{Zflboe57{_=^sdA6 zW+3l=_L*V6_muzYMN57Dlzt$<>$g4i%-7#7tliAvbHdu|U%#>CUJ^#G2_>Xf%$@vz zA-?0OhyJ@YGI`&1`45@HOO2oZ?eWxo?C001`lb9sh@amp^)K~)h&h?~>GsI1xR*JT z7heu9x?XyeLQn?gBGG{zM1K0hA~ycSyCmDax=Y~r(Oo*;ePeIh+g`jV?rM+S#=Rjh z9uAQ^_sC}jFotiV;=-5rx6wS3{_ysjZNB{U#ofJESM$z`B1Dy<`x<8`&-3#8-=}~0 z`S+P0{t#ceXEC^a|JMD5m*k~SU%bG$UXd|get%xNKL2^?H{##^4b(n+xQ%)v%Ac+B-+eJcIGweH5V`;T(7=me+OkIcf(0(a&6X86s|Kh(2r0)&AN8rS=&XASNvmvWqtZET=Z(omSsb;lNNZidHTSkYV4)(d!k$O& zDjP44I~9nbdT-1F*&@Atb`*#w09bD})=(sEHQLm-%$%4x-EAyqTWz;g%|{ZW74+Es#P0Ck{qHIjB(#GnviQHL2@9|A zjc(y{0Q5xxdA@9gq3bxR)GZID7S)zebvw(>E{gJwT!T9SSavw{mz;5_%*_KwE2_p7 zVF>WPYOx^DGr$G5jLBpIcq1_b;7U-K)$X7lRgzk~)YeR@^x573)u1?QVa|r1}nF|Vfrid6To=F9a@ASpo)4RjZe`kz7+3vQ5kzS0YY0C zrrlnvVF%s)7Jw;J9VmkFk_Et33``l_mt}zBE|(`^0jMEkK>I2ngGDU{fKX61^N!!L z0eG2Vl^sOGvKUe^nprM9wX4Mfw~c@~=LRXYJ6(!OZ&-ln!)sh2B@jRM3#F}N&5kNwig|_B1 z0E2NGh5?|eIuj1VAfipNES@tEoE2&S_0v)BzMOYw7JnX%fa^I9Gz-9+>bPP~t04e9 zB~Ned)~)%R-j2N`iji|d)I9Byc(81ptF$-465_1^z&PT{r~w29;Gz)3kYV$1a1KBl z5Cj6;pysn#w|?vnRs{G+%>D5xBbY4&j4W$mZk@&81P~N@0RV(yN0QvYr!A8zPluy2 zieOWxQ}4)kQG%LN(PmEZT(4JURuc*J*VC*TGbkv&l0k4quEdMTqX^)~xYI09@fyXf zQ*DcB0@6G%>pKF)q7FZR4PuT$q4U}Xpg6-p$0;u=S+N@0iiG0uR$K|P+}Cs8NhE@x zgyQoR3||{@n;4|y0Tdqf6#_kD404MCtOfo#nVsXI2NYT$ki?@I?Qy`8n1o@iYEV9a z6)oQ{=S-~}(jtIQ0o1H%T0fl4nb_-j-Fde@Nm-6#s%{%N47MMJy>55B#vY%}>bvku#@Tobbf>-80fGg965P(7ZnoTVmgSR5bWnF^U@@FPA7RsN0mygOYq#mzh8NXz ze8jy8hbsAuOAi~3MIifIb%yMRvZA}04PQicfn8fWOORe+}Vt?#xO}U+(8-~S$F`>TUNBY zeYGGUEUX}5y-dvuIPGXB1AleHaRsKJ1Ly&vFV-sh)R?mTa5!?Y2rE;kz$SEC!|856 zZm{fTrI547?E;lR->_KpfTqUZ>UJ`#)b^d$$h3grw5d7s{^|mJQ1FwceVQ0p!ja!< zB$aay4!Di(re^@5k7wP}pzXRF0@}6Bg0o2F_j4o~hUL~4Vx>~4c2@+)Spn)pmK^{z z4IDsWWDRN=Fx4`)0NsJDT|c+VQ-5Yv_Nz`~(H26gW$&0S0WH&kS}W2@wyE*@RM*!-hVd2}sMdRmHh7 zNu9XnT6we8<87=1ewpVqN5C=qjA&)OrVSWHfGXfSoeuU2KsdS~3!r46Jp@ZCUxu@C z2!NI;Kv=OCvv9iwn1x$lg|;02wsuU2)?w0K|F_D zuSMi+RH?og>$JF=&fQ=xCmaETVYY+i#wUQh(Qe;w#`1|r2v#vECU3aqL|atm}Y4zXsmhi;vqBMclvuT*;TMHJSWB$z!85M zq&11Jj`jI$FdrZD4Ndly3Q$pg8<8^^P?+$K{Nv1BR7YIhCB zZB;XE+jnBEJneL8CQ$$%laB<7h|Emclk-lWoU_fn+|06OvsuK3mA7_t3*d?Jgxnfb z^z$ld#yUH8tON+I%V)U)oxGXYU>swi2i~xw3Vj0VY1;C*ha%P+WhR8!kK8rFy%PandWx0jzp=Yu0%NBiZ0T^aV#I78m(Sdu}-!rg* z3Ux~8g+O(8)QP#w3-<7a$+QZS&CR*hT%LFR3cwmG{Am?IsJb9&0$e==hhM9cO4$@M z0pRrh9+*FlFG&fQs@2=q!de7~`boI0sE5NL?E|dvwD3lDZHC3u^J<>H&T?T|Bo{z) z;XL2$M^%8c<@{kONogMt*>0=lGUmEg0Yc^&Xfck%B`3hx00bDz{1~i8(!r1b-Z!Qf zxYjpq582SAJy>1bDrE#2QLawh`^(|1ODpi$&q67W0C^$jtfX@%wt5IOGHGQKQ zy65|}G;C@D%kJ_CfUAE!$Vlk;fC#+GS zQ=9jWlL9(p7dqo?G7$i}x#(|gyUWGu(p%IMprtMW>N!>!z^*zekgOo0&Fo;nssR+Y zVcD`$njj0Mlr72(hQGq7=5w(;ZMF`FO6o5bW=lEmz%W)3U9&Qy8k9#3oH+9cu&Sr1 z2T6euFTikK()SxN&dep{>#^rV6@s3YTMPp^ej!I4MS;A~>93;go&c=*n^9xaU7!_7 z6uLS^6Wkzb-J4NId+egGJf+0Ix*Bo}IRlnQ2T)*ykDLVn<;`&5g%-9H7Qj@q>XH?N z09(rfU9SlX@GrKYor&J8&*>>n8$sp($l3?u735v(P+6Ons});S-3jM}n)$`T94JBs z*BL04>ZwQPioodvNOA*|C(Y6dqI;Pgh6A6$`K|zF2MU=N0w*2dnW5jNzDV;G7b_4-lWz{8W~g(yB5^;_2D21dc1`rxWCNan?!r zamv-EjYey6WLGojyTJV&F?>S!pDcnyiWbpt+^mL;G}I~8r~qUU=NnH=XL*_sl~RIk zYaa4-EN3ABEI#Nv~~cwwkorSID?HtvC08>udp~r zv_ODE0sN`?3iQok8~Sk}VMvt4OEY2Yg&|*n`TAXGJ1Gr)GFPFipDjp!lPTQ=kQ$_p zvm1>jVgYem3eV%}gfS=}IvE32;?EKe8+*cG`$1R$fFl7LC1-V(Loqx}@^0@~4l6iQ z4@}1?)C(T(1#}RHKE%0*$P;o}2AHJM?XHbIIfr35noePhqBSE|L~^V^Q|@+}PIYVu zlB*FMw25(G4Sftl6cI94Kybybjl-bpL6_=aq43mNs0!6-75bly^#?r9X=r6}!#i)? zIk(P{ZNLc2F$@=d-jce8UjxxZu@dT8uLHrb+v}r)dZr9dQ?VfY(9D{R2F`OA>Jr0& z22DL(j~eyfUhI*7`?NV_n$W=;gF!h3=vJBO8^>w2!ZY>$5DIF|!XcPuD+owcZIM^c zEbJV|^U$GF*H|9OKESDI7#tl)19vXWCY(5R7m$1WeiN*4)Nk%Ktpk7wS3YMchY2)U zoC6hCs@4ZX*b%pNFmVt33KHOH*r&TS0+7D6VQ1_2vfQ#vxvw{m?ah9Ctk=`A5B^;7 ziTx#ql1sqWRu$;Q0NFn7>N|R62laU)O~Sm2)dLaGShkn~b~59B|HTYlTMpXHSnti7 z!We*}bA7U9#B#dP^YOWTRu{Wn-O&s{Nyoq>%~Eeemj_&N+~va2K2vilahlzD--|l{ zR`vN@78RL6pVdghGMG$7v#L!*#jb1hEqz*^32$IDyI?`uCb3^PPwnxJ*j5{xPT~C8{v zPTf6j;`)dqQDa?E*l0p(TYh)JInKG;TE`uKqNTtF<}7kPO1pp%q_OL$+x|8MYFbgj zpfwF=KS7q95gmllVQ1vd%>x;Hw^50l-5D6`>ov7jU?YWM1X+9rxN69JF3=H0-vjXJ z?#QTZ*t=WxqJ3JN+dOP-G63$1fw8zu!m-<#uDWy5Xe*t=j!phLorW+*fLPr%Fys66 z`nY*ob~k9Jv0E>fXYx#fOKb98XSY5ru_$rLsm#~p58qpzn&i?L^*iUVd-of@ryqe~ z->N6D#uA{lO~>;R^2`XAd=G!ztb;ym&7^yS?MJoIqs2enW7B-82iin~!aj8-+fimt zg*lG*WloiQ=K;I285w?x?w~cU$8|<14?Cx*;9TYid(a|l9)Q$M!an5^}#MQ?3)5LN*`I&4VH ziRI?YhBvD=lkFnvx9Z0x-O#aLJNZc-Y^v*RTlB)bWro38KFy>4u2DC+OaFY16;gdc z_v-E4gv@bjO9%RFW-R9Yuxg*0wdNY9@VT=%&FS)RGjH=5exE#hzNioDB3W~l!K}64 z#=^Gd9~W_L-1YcS%|yZL@n`IV6Yn~XHTd+#l-(*0AqMzw2E4B%h}O%$bu5=;NxOyQCkZ@nCf_PYKRsn&>al zc~6*eecgwRJN3a#{2r0%0F&7{%vt!yu+_89)R;E`5DUFnBDS!pI<1& z%02(27vqCe(P0atj}{E}1)Mft2)bBb+oHkkon{#oj2_C zm~p^kPdIXnG_PapCY9>!WY4x*pihNO%nZ$(?1usDz3@djt{n%{vQX_(hCrN_YJE1_ z@04MdiCHFXGiP#K_XbTj$kXs78PRgLcX!2lqvrW;RHeA(oeW0w+%Aq4US;<#@ozRI z8Fu4gmXC@>-$@7Yp4R-9>}K(4)Zrmxbes;a@5fWX&PV2{;huUpzwXaJ48;~kJvYKR zwoWTjvmVOKS{|Nu+_F9$4BhdO(XpSPySA!EXT8Y=adXK{_>;1&`W??1HaizTYqRe6 z8cDSfr0LY0R>oQ*yqpb<`qH+=a&1G8(s`JM-Q$2GzSriwz3pc_;n|7J zmy2G*xqnY}cRCH%&`2L|XA8Or+k#xp^<5xP^L}*K#uPHueiDa@U*8P`YjNImA@wRV zYs;3C3UHK9@aguOtD09UE37pQ7V~m_eGc8cKG=Xatp}YBP?Cv!Rp(t#uVuO%wf4hx zqv1CQulO@?o@MgbAp1ROxh-#Ko|G|bR0=5hj8(2#&@Z{(;n1y17vK1>W#s)t8HTf9 zrVP?*qsfh=-EMJKs%LJH)6smj*r~!raIH6Kr)m}RK!GB_?!E2GV``hpDcTo`A#|F| zc-1ve?TcT1v@|wL`;5cwWVZ*4ynO82Td6pXD$C7s&W$I#$wlty?#@z0=Db4L_64sR z4~)=Ut(X1%z_`d9{dz?&3!7eQ6!Ttok!N}I0pL~$9T}44HRF`zy$rKmFL6RnbURG$L5~bBNAUxZ)iJ3 z!_tvvxwp<;I{{P0VSk8y$_Mw04)f!9*XWPHx9a1TcUhA`-WA*G9sdcqIkP`UL=Fmu zqkg^FVu*Zk93RJX4we$G?RNSxk3b1{UynT@T8;a)pn>oj&Kn<_yS~p2lT3@pJM*M5 zb}pSqL$1GS&zqZO4f4>y+2}Q^lJ(ivuD58B*ph**UFDr!b?Z1mt#i@aV1o)yrgi2m zxb%70cVVQl^1ei3N5;n5uCE%yvTlV#n3JNKyxh@^X`G+kTGZck@I9NHquYzm7w71C zK>)?)bhw-X`+Q%dS=MgDS0}6pxc#a~^!jkQgpXS-SM*4&Y4l-`*IPqFN-cPYM&h2Of)? zn}rPIyFeZKMsSH;p;9UrD>=?V_|NpYL;$G6+HhZ=I8$duZE9Xc?Wa`xWcFAiWBbKf z&k#9L)K|?z&>U_xsd47KBb)~Ie86$+K7%1Z&BkuOSlLGj;+t|#cF6-?q*gd4Rj9z!k+H$}zk9ft?V1~}84g>-#v&A^R+iwHG^C4NOgOBm z*lr)CL@>)u14!1M84CudA`U1$Fk7gNJ=J9&?DuNpevfXRH`Sc258|Rc_rzU)d#9`RdiGcHCvPA{C(Ro#y$cVY_YJOd5?6#D zxr@PeNzTn-GwB*Lf33}T{f#)f#HRI|)A79U&vDUn{raAdbYs75^3=o>y`a~o)Xv}% zr#7kEVG^GPPIg*UhpBQhWk1oxWaVFUZMxZ;_Kei+QZ77j9ZDFvR-fqJ-J{P8ja;k4 z9VKa*OVic*MJLaO;2SAL*|o;p^3sldXpfJ^uw&SpmFc*fgM88b8~JJE^ZQ;l=^keJ zs>UstGh9pLPjRuU&QqM}Vp`rF`JS2~n1{$^+KLX_tWiGHdTnu#`_MUIAJ}yJn_6cL z)7Y#go6C6Ej{9+!b`Y2r?cpS~#Z^V!XJ9p_3{=neq6eOMh{KsfQQT}Sbb6C>udgm< z2daBGL~3I`TCC~*&eB{%3gEgtx1bhuY85u!azf@W@@9D{PnO+5zy!*=OcR*;vB|cV zm35=OxWr>+>OdUw-XxkQL{~(VisnP~=xs-W>uwR1SZ}EGsM$2u5_Rrx#QF&>NRh9DAKe$$Wl&r zF7iZc>5i7^X4g^L6>k%B;Z_^2RHDzH$Hxtk`>6N~CU=v!|Y&H|mTk9kQg@&Np>^t>FTu9r4Qvuv@ za|%=CoUK$LYfe`y=uK+D4I7hK3rus`A3y*|l44&oM=coh(=1dpRow*RSZDUax;;yK z!=fWt+QB?$iX!h$+vJp|@P0-K4XYpQl5Q?elqglgAwo*JVw37-%QOj?Z9x3RTZh>u z-U6OrX>o}g7$Np;b-dU|Rk~iM`%-JaYLqu}p%&l)ZHHQkqT|hE0CyCJDHNp5%tE{u z6^|5(cSwBLlK2pL?&9m?5k7QegMRDSns@daTcX$7X~Iy8Ek8_RC*Rc@_0eF+b=9-c z(IU6lpBEIu*+j%bmbW5LVuK7c##Q3RE?Mds&K0%8oH@R87MkUH)Xtr4+^Eb}1Nhfr z+ppz_)j;f=jQ1mbd=#70o|Ix6GgUrCtd|ITY4x}e&M-(dnLRI^>9`R}%e9;CIx-iu zi*r=AI%^JE-vkc5f>CoEu?ToHM~K;CMia&|8r z&vqO{2#ny%a?)(4tIZBO7WG;8+$pPqfq58*Ys>Wcn58y(xoxm@t}+-KV#)~hgK*q2 zltOQ%gBexCT~VbV4#9bZ*nvu`C%_kDxZThSg0*$vRnyXZsEGY$#j(KaJ4+*AS=jT* zS#=CmrynmjSG!?u72_aKxK*!$;!v^{KsKe;E4n878%Kc7toIG=Om`-X=I)mTGuc*y z0p~1lZ3ctp+;1yAd9BI87EvXTbBdMHIayAOIPFEn-tUZwdR7Zc>9ET^-9IJGDDN>y zRj2tb*Wk_OvDwd=t;#m+X;g`GlWWcbV>~}lqsn|_F8v64pjTJbA={ChddP@#Z8xbG ziL?y1jAF9EFmZ(K`LyaFN);Pq9ENaHbn<;5ajKX2)mhluE4)~z!?AkqM+b_Rtzezm z!EqRfi1!JwqOz*z&Fx?%*BHxOUi8wOYfa&1cTUb+s`EXn=XDMn7Dl$^aTrn1cNwS~ zJ1dhabC1u}GD7WSLvRlLH0!|*%kDMDs5km8S@Y?_U}%+g(Y`*Jm~_Us*>HOh8{M|w zYu8(dz?Rx6GX&r6j(c;xFujPCE45Xt+I8ht^fH;ZJjq2v;dJgjI9iIoNAD zh?iY$u|Z^ox@xO6Y~vK(^I)JYZNKDs6Mh07Y@Oz&qlrUT=1rR3 zb)CI~Xi4bz#v+7?DQ+*rR6uS(zpkxjlTqt1g+<5PIICI+FFIT&`=ajo4s zm_l{MVH;Z;Gv+nEoWuw^Ytm(JvS`HQr8m-TVhFWBgibc|d*v>QcJG9A_2x;zus3unGes)_1ZyramSRF%VBZ&n?J zfr5mE*}UFb%IQ(qb8fBDJ1p1BMhDT~vXp1O(OASCHlB~Qib`p5Ydp30^Lrkkh0I=fwGF;%I` zW=C5(B6|7muCbS#{!$Xg7L$y-<7R76$%ol=TNNDml$Q*>Cv!M9=w5G5*C$PAXsUG? z-*&O>kK+lY^vB*|DmGV^)xtT$oU#r*Io1t-+lrlWFpHNa+@qth(7>a8c}(pPHeO$O zd@FJ|a(k^d2HhFcTGB<*mH{<# zy>Y+FR05@0NzN7T$b{xuT3dcH$^#Fv_t9!v6X~qAw5pY9K~Kbdnj&MTdh~-NOZ!9x zM2xpNL+VPv`KEk>ag?` zv$EdA-BEAX+?iIp+;H{nva2@a(TL@v1YtJ&`flnFmK0AXtzO)ekI})|DjEs*;}CGL z>g?#A%uJ+xr8}K5Tg12@Ld3F{p-~#G^M)2z-HG2yfY(uQk=Um||SJdmh8FxP`T$jaw3oX@NNxqT??FbZ>~*Vc{7dCVel!c7=y zm|2=4vnqXzXzo}$bhOrS;j(8Ikru@FU@n}FJ&yx!43~+bE*8f)Xhn;~s@bd}D!1Aw zQv;n#*L+*(n{aY0u>oQ={inEE?SvqH8n>as|m5ICC{Yo>`XO zM{pUBte~w1&_wH_ndJ0fl9)4TKXc#R@mEDdJ~2=y^?a z2TS{8mXgEkxiS;SxHROaZ%(H$%a0hqN`YE4wW8`EHdPPH{5ler?Jykr3CZFz-O(8geXoroz1d$`eFdNd%Bm?*L9eqc?5?#u z$h)3bk$Q+ud%MrY^SGimE0T2v?>Mlc$q1BE>O`JcE#Pg*W#A7y%(2{%b8G=rT!^9 zt*EN6ZuZG}$H8{V>=B=F*dboGm}{ZV=9B;*9Pg7@LCH2uv)dbsm02}P@_`x*E!CB_ zsf`%fkx{Mbqd?|c65EpfL7;B5(|lIrXpi)%a-h7Sj5r)7806Cxu_0#X&_awd^IG7|DV>~hP zpP5d&s##qWNs*!)k7x9zL{g$eilUgFY49bH;!}J{RHFkMhyfd@MFNzAWRsn<3y@{j zStQ;Bhz%rJ1ju5taTeJa-er@I`akafR^O_w>U$?~fLv7FhyK*zIfsYm{2t%;{q{T@ zx6yX!5rOY_{CLmqCgH7?k7;$NO+T*vT6Fu1>(Ir@94iNPfE-5V0;BcXv7xLnTy*vLM!J(kwvwTPbOJm3R7CL>yN&0J8uTK5y}`*|<;|x|Al& zi6@j!v>EIWEip$2P45Epa%N3q*`;iq=({`0-ql;j5xm;lcD?C%HMjt;=5@=M(7Sz_ zVS}PSw??9^jv~eMCkMzW1!I`5?6SF%Zq*!3>=WRY%>>=y=j&mAw;gW`X-lb~8MRtZ zBbiQSeo7f&CX`{PW6iV`zJC-$fX8XI>|Mf6A`I#sTT+5B?2`Gypa!8q&#vS^pN@PA zNA3~1mff5)f?y8+Ij%>@vp5&uH%DYLW!3#fL=K?i)5^iXnr;BX9rBsTD!qW`PNyT1 z#Qv>VPUo6!?)Anw%W+CX&M7=Lal@wb^%^;mEnBxp=+2H+W(J;drwqLce80J;BTYxd zCw7zqs!VTnkvRpbCiLwsnP9e5TGN8oj;B;$!fh9uKL)r;!0KBL+Sm=?uT%CpkVKOAzlB8*~vPqLc`mhVmtt?z8mE6zw zroivXRd|zc;gv2=ZQSjs9GmgXSk=G@YS(NuJIQio_xLsTUDKPvIKJ;I$RA?$a>5{- z2|gHta4-{rfa77w!!|!T7kesUt^I5$jKf(yuELXflssS>fZ^rltFd`)&dFuk z)mJpBgi|?R^cLf2U(PpeTzRb%5#RAg#m$b`Efd`Igzibp1D$iL)rh@z0sSsg(chE# zbu@DvCnPrWE)SCQZFr9jJEpN(T$tf5yB_Rr5#}Y=O!APnyD2A~j>v&u0refu$y5wV z!LR5zY&q4%U^J>au!QGkVDG_Aw#kZ*0yd{6HMmDo|CD)TI`Z#pFQ1M`1UC(HxY(%# zO%KfFz3=eN(D$)?wWmyeyG4D2@|sQ_lC>zE(fz|An-Teq8>Q)%JMqVb1E9Uw?C50h z)Q2(punXrFJSv9Jm6aZaYs&7Oc887MF}Ng>&849mR1of0+(O)vPMGVKRXEESyaU81 zCaUadn0)7SRCGR4cNF6|pk(&?j@!&8mgZPO0hH@4;1_-4Sc%ikl`rzxGdqzZ*~V!Y zwm7%ppnKL#b-SDw%gpjzF3(52y&KugwW*`gz_Q1KG7?msG!nMY?5gWAT+P&wO|Dm- zTpxBtqhEjq#D>xG$S317r8=8l)aii(#&*i#20s71F~(^qZGuWmYr;A>3#Sf^dgcoP zONR8!KTU4z707A==JGTMFE*SQr`S@_M8gftTj{E+=jVRj$$PGrx;Z92whkc!7Ye+% zopxryYXSkC(JB6X>uwjEnzd{CN)Qq-oM)#1lKN5^pl--Om|X&Fr)i51@&9})lfU~8S>l8F`?=%xQ@UL$oMz_OiRJnxxSSPtqu%6nC66m*I4EYU z-s=}y)82C@WqQxEc6j02y|LYM#M34y*E;OU39=cK6DOiKTx{zFH=OjRv7Ld#PlA+M zAf>k)_pM8*c#hUDtTJ8O`^B)hOjtwS#=w(If(jW38iZ=D+ziDPH(MJE_)rxEqAc>> zkx6#$`_ep`zw5?c?1l|)WV@HSyCgYl{ZkWV+YWs`F~)wX z`5l|9mHfuXdgs=GySSpY{*ob=QCMm!USwx9>IrtWM2r>+2;F_y3F4%WU40}Ap{I3a zTa;ItQ;ui+-YP-uxJ8*U2eWy9l4t(qzGvG4@9p7Z)u!y^!|T3KT(T2xdJYvG^TBYu zFi*sV8j9{wkExAd3`WaKxQK87cX~{dq}RYhfVZ0x`B?!ri1Vx4^mN#%N?x72Lq%ed ztt&f$M#POXSlBv{y;MMLt{2!J)wWKC!zyC+!$Mp#y-SxYv$$eu+aZDXy4f^~WE#M~ zTbA6q*TW6_haRkAl_k#Rs7P!tn<(2+ynqu&uW$))GPxZcM9}o})Eo*mqZiD$raS#$ ze}t9T>qwee6Q1EzP-H05nVKPANc%ozD5D8k3Cmq=lsGSufjls~$(2#Sj_oDLH6c%P zBv!i4ttAP*@gDZcB|*rSoJvL5yBUL%bM-#Il0tvDIY{cB83*neA``<+ zhjSUJ8FZARvm3%3tHLI@l?gtv)X#wis+f9ZPzN2fAJ{$p zb4z_<5rlc+6dY-W~47uog$<*x|+eTS>zI|DmYZ?8$a?<+fQaVG_kQedK^k{!{cyyn0}N;(1UD#CShMH*8U0Ch zlm+K#NPV_EWHb$@g*w{7q0Z@Ub1;tU5mZDhaof*SEf^wBgHXb3tnFbzrqE*O5{tf& zP|1y*api>_t|!U3JlvK;J1RZkf>0S`t7`n(g40wmMAr|yhibA(GipJ zo-blSQW{o4T#I34N7@Zh>x&u zE);JcYmVmbnDd)@4u874{38HQzC&e6=+i2!h0;jW8;YN~1P~bzpfDQUyMBJ1_^m;=7$& zG3c&>T_7w3x9`k)aYX+J=Wh36u@n-#A-@KNxzhO^2fa2j=4bbkDiN zuO;-Ld%3FFeznlmCSj+ivoEF-wPPDY-m4531o=^BL-B)i+csg*Pn)iN7W=*NVcSyz zPO&fNPOx82J7y|T@qEvnri3ZVI<3l6Cjpntjz;;D*O=gB$P)Ji$-ncPj76*kp%8KN<=9;i3@BH}Y^*C>p+K+wPk zF*q9Wq%oF`5_>*&<$>0@Em+cGw{<>gIz(XyTko*j4vSjej zv73~x%yqND{2-P~^jQ%yEvX$OijFV|rX0IY;l9hsek(ZzaZsB1#nFfJy&ST)l{a^* znXLl5nI7Z)E+S;$_gF;I=zJ*+%VaX^^I|sS3%i^3u)EuRt@O_|_C@fFWhRXSfh45s zCF#SDJnm*=^Wc!HD8DGO#qEd2QoK#O?#Per)z$;oetW_RY#WT?oDf+*_7q>A;{@WA zFi<_7PQnAvtP*c`;ICa`U5}CO8_hfBLI{aq-Jw@QVQqH>(D5b%@G$DDc4H47;vGYe z#1p?AEVF;=W9_S>n`NoGIUkJ~|4PnXGTno`++90#WP_3|9f0LC;Xjb1V$Ln= zG!M^ZF}TrHIOwJ3MVJQ_MKaKH+3bpZ7HgX%E16ZfT#D&zxbB6(is?&$MzUR0q^Z~{ zP@HYEYk}f!7|p+kzSP0;FI2q!r8#(P&XLmFZl#2JXom@%V#Oi=MQo6Cn zbWR1hbbEdzT{c{o5cTya?9Sy%=a*1{Bc?c@fpwr*_s~pNoV2`N5pdbw5~dd)u_#th zZPqvE9ZO%vibWl_*vHmmY#@BEVdGP7 zT#t+xpJvF`Oy?m?+hvj6_ht}y*d}Z-L@Wgi!4MuLjFoYVIgnYTg1fdjEb2kF;}Cmn;}V1x`lmK#rz*jkp?aATsv<45 z33U!J)#G|2`d59a9sSXOKVZ#FmOJREWKM^WU?(QmA%r}rI=XJTJR;P22MmtXS!pc5 zvN@==u0~^-g%xP9d}ptMoY;(-jToP=sS}FpgN7gpL|1B2BLcvGDx2hFSoZs6|Ad^M zcUU7fS#J;F@;d0Sk$+ZJ!4lw%f~eNiEV&MRnuoWT<;`+12QJ_erSh8SHQOp0MDEQk z{Ox|NulO|S zjj5B!>KuYlXV1??CA>96nlnX-J#srYMNK*)FEh4{i8>mt#_J)QdEo?(!R?$~kss8K z!43LQZ9c5;88>qc-mN$$w)5d4l}9u<_8DOakKx6>W{B+8A6)o8HHjliI29Y7zEr}Z z7}3(SxJB_kk8^gh1$S+wB=)4c;QH)6uI{b~q$i}M)9W`K9VgwbW)H_};4y8ek zlxn%HY2vITJ7L~G#8xxkmv{Ses_WX`VTHljS)L^#ozH_7=iczAB1*+Um*+u&?of+c zBFiN)PguJ-m*eeucNqjXhmi8^$|`Ui6~+u!3j+O>x_1Jqf3D|#K-G`7ra6JF*>x?S z-#CVUI)db`A>@+voZYGuYTI5tV8yaT(^S11!I2dlqwf%nb%O&`WZX2)6{R=zvRy&( zLKPc1zdBvZj6Ucixbn~^&`!xX6qJ*nj1Cl;PN-Z5VOjN$5HZ@2XP&5K$=qD~?m`@w zDk-_qV7Lw9SuFyc)$inn)-8Jp!9Y3=@rxM<-|qN$xQ;}`c#c+PHO~H^a@(Nr)}2B! zZ%}!0j6^ThDaY9R4ku-Uo($7%7p)6};Wno!*AM+mHUmd#2%bveZS=h5Kra_6MBCCl z?UytSY0c}dkb>P}p&_bD7*25jJv>5EN5^M2p?;2-eb?I!U zGV-JV@Porp>fELDxBT%qwxor{i|moxiWk9fr>hQI=g^xVk;IoFc@kXLkU6tSA};%V zqM|x^0q%Wo3o85$at*A?6z^=c>G*bCOzIW54JLOmN&`twtr@7`<|Ez2=8{F64_!^tN8~qNz*l#@3Bn z%`!Rlz%>BBBa-+FBTSB-0`II`nY?mR6EE@@I%xnPEkJ`jaMEbUpR-BdjFx9wrSG}; zLZFlNIL?Crx;oBkW-vVwZizykz0JDb0_@m>kGKjO5xMSiEYpXDLMHrlV(nJY#XvOM zG!WDQ7V-#q=@J~Uysr#r{HB}5;NwyrQJ<7P$Os6+xqVwoaPB7XH-U8RhBBLG>)y;v zTwty1tvF1P;h0|6DT485)=*|}#~aWuZB~mQ(lFg3txnYz!pK?1uspYuB-XNaR-%er ze?Fy}H7WT=J2H7DxB_)U?Ces0R!E(hS_a*Y^+6AZc25vYBdtp=__DU=WRt?6&sopDT^pG-j;`IefG^lS@F4O z3st&C=-%z&Xfcu#x7-50G8-BRWhLZtuwHSB4kG7Pp7tVR?kGz?j8_8HBqSG4V5*Wt z+R>%t79JcZJ=QvYW~-#Uyrn^IBG)O4{y07==Nnt^V{>>zHb z&^LK{xWMsPQq^!`DWTW^xzQV*t|88T-oCZC zc*Sz+=*YSWvd|=kbknl^lpW?A>~S${?fi;q4vqzzceL)B{oT!4M>r%o&JWSQZi@$b z{Cb^nxiwCZ4e zOcw!i+LAfb7*!B2!PxbH{RM}*lu~eJ8-$>xsg8h(WaUc0JG-7YU2+#4>4YSo!?rd_ z!O)?Jroz;UkWa-E-fo-IDU2HvWFxtmMS7Uyu`QOfPB-6YfPPIH{-Df=!G7~#>SzFEw# z48L6ff7~QnlS-V)Xw`B~OefPfa&hV4euaUUFy4T0-yQd2+ww0)Pf+{h8up!wmt`kT zi7Q{1?m5%k)RNCpW|`m_#lgtjY{8D`lYkCC>LvhtL`>!v%3NRFh#WH~;!k!UVq;9}9 z(MLXy^B-x!pmWpBTrv}f44zs-#eal zvmcY1q_d4_o-IO00vJF7yf;l7sxri>AWx5NZu0Iw@Kt^HACmEWD<_#Y5eD+S0|}q* zU>2at`@*Z^SywXko*RSd3SP8?h)>a_%P$>*)d= zZ>Ro|2BxqJ0q@IgpUBB^rXH6YS6y^%?d*fqO_N=LO}R+l!(Gbswb&zX zHSZ8ug}MmJB46w)(ie%nTMhT7_oOYu35o=}%|R4!>3Dr~z==FVy-F)>GVNHSH6)>G z>PjLxX5!V>3*X%Jm)LKow0Iky-I+Fy60)-sBPjy@;xySTHm8E`&}5a(yM{V~0pB^Y z47bj}!E|zwQ^+tiPd7&8l9SLckMyaGtjG8XDekT*A(W=JRoSGkx$v{XDr)fgnHI6U>H-*~!d2aPX zQabm?r@kB`J~+xoFr3Yx)rf|p=TX&Q#kDxN-XRvQpvN3)@scy3{X+t395T2;RGv@) z(?laKSGeG~5xH{5iTAk5CQp}y0?jBzs}gTB-*1eCF`g}1d*^5~3)(8iS_TMoL=XHi zNN!KOYG>lIr9GFm%L1Gq=4vn7#+UJA&iEse9LD(`zSz2wrdm!{Z9KdvMLs=eF>-k3 znK=#J;T71J%cAR!$-Eiq6K}Jf1H(c91lx@}4TId0nxCuL_^`jn*SA`WwcA2tlx$b$ z3PQSS6)%#ojC>(!|@y4ko16@?%5%1MvY-c;O!v!rSRA}oeKxhHd4v5BUTLDrQm;I(b zo`@l1U#{fv1jla990yq&SG%p}s6gSBy6Cm`QUe@8(YvarbVYqb?rRKmm|IUrrcCrR zq}tD`5grrNnXzwg2TM6XzNYVQ7tNuUa?A=^g1}5ho3F$s)QrDG<}f^5PuETfyJdge zkA~NlLj@gh8|4nVYdySWXP}a6IV=Z5IoPdteSab%W5)t(c(&+x@wB%9$p47_a+di; z1>A@19r@N*2z|Z|N6jpC8nX`yaSd(%Q#72<)|ksaIO0;N*X=w)tpM8nE0J}1zm5882EKj$EukFCuY4o5aHC>PhiKd<~8QSJl zM2a$)t#=$KY`|qAoW(T``lg}Z5T&GnbFx-SyyfRsd5k5Nzm#Ere8feQ5eo)Tq0v>B z9eLtp2a+dZm8IzHZZ<%id)2_ZW~jD7^{e27%!M+Zs)+5v$B{N?Ktkph5c~UTVpE{b zuBlCMoNIG7o@U6K9U7|MSV_mo zx-2h^yy}I_QeSkZuA3R11k^o{|B)RO`d4+oKr0J840PQLH&Nwx%_i`aJ=a9hD- zQR3sc(bZo+lI6l?GVE%iK8chK?+sbU7W!4-IB&d}{lhK9zW*-T`( zgF7zUM+b@}GCY?Si`{qtF*xI8(P5S|Ww(-c^OGiMyiqO=^(5OIg=5QO;{~l-+%AXO zU-M^iRBa&Vr?3jl_siv0#r9mm_So(p1=x^#2PkfYjZTS`&Md_%AdlxoEA0vdSX7_; zICJ@sv*$}@+Ekr#bDXR%F1a7@q{0GkoL9XkFylq0X*>+lKV+ zX?TecRL(}y36VUiKQU{2AFp)G&EgO*Q7(v=y2bd#FBuGl?M+;i04cM0YMtJ8GKITf zbcylZm(8K61G(6_K^+}3Cbv+~(6U}I3FXu}_cWK7DZwflYm}>+gmBR3BSYEJ02!}= zcj-}Uxm#~X13MyP2*=7qp7j=^TbAB&2{z;_U~hsdb86ruqo!^QiKu}lQdE9D`wV6R zIB|7ZQmRWKna*6QK?&|kz#|cFgDg5S>((cQG6N?o_E(;*EM4ke<%3cWw_^@|Dz)Na^YH}&wy^o&i@mn_I!k2) z3fFE5%%2kVX8<;4qvbK|oUido$c6Hxfc%ne>)YhY5&RT+{~)%vHqaJ1>1M#1jF^0? zt)ROcjE}VA#Ce~$$H?;^TKBmMz0EOHZ&{s(<=&I7Szxb(wJSqsIJ~*NVxSG$cg9AJ z-o3VN2>3R7h59=yBLVVJu?M=&9TAYFA+iZsT+}i8l*~ zwltSx*bKz=2J55&25Zu$1&xa6VB!O%u(=3v?~>?Hk~F~Zm9SY(A|L^+jeHn7DqPPHZt$V({7aF z(TY*j%tt06&u8?WUCLAF?xAwWD_?ljXdb@+9x(O=4sg%Z(XfJfcdg?5sZDxsCR%oeWM zG1%$#Nl$Rj2sa^SljJHlSISnL1F*=w@%SK_%+@>wZdqmVetuxJ6J!BS3o2oNFd!6K zB7Gr5Xt~9UEm_I52G?<(==p`KstmYuNhLOrTm%|H9%mO$&wDLLpp6wOjcGuGx;~u{ z)CESRxob66;3ooCI>PhX9K3xm2Y=g3FE-4aWYp>dvT1P&*5}wVyqM_|=^i1(7C#J`nlrbeXQmllV2+j{6(^8a^rt|fT$Me01S)2= zUX4XKd_E-fam1(0p{IoNlb^?MmA7^SNT&mimNJCjv&f-wylq zb_D-(l=gbUV!Q$I1{z{FMa$M@8W-IsKlhR#W<<3ZEh}&Rap=_>0^ru8&U_=rVyzU)QP>u$T_;Uiu#ixx{M zOc%48u$c&mXIs+*-&X`dRAdN4o9oayNJgL7dg}354Hw6b?{!o_16>5$phpv(dQeB~ z1OUEx#(~4O1exajB4};AjRDZW_2NkKY_cKO!{ba}C+T(z?f}aMo ztZ}v$L)o#<1IVb&p;>hq6z5ww$+M8ZdM-krz3Vv?U{3HzsyFcm%}@An$d|=>l5A6aWyE1?#VN4mF=Nq6p-7Jcw5LzEh1~* zTPt9}UAIoSRDu{%8Fn5hEmvCebaO3=>zgb>y+03$g3IRpS%+9JtV2gVbev{((bvvn zf6$4d8JI)lt`(qd*T{)qcBqGfaL0>QY?2wI8{M@x!~}u^2iQApnI&YZGpV~f0|7)^ zYsIez`w=Nz6C1+WMU~F>TpILEdLGKz+zo3MRK$E~iKpEWRHp@d8p-`>MBIIZ{jeIw ziPAInSbe22T%-KLOw88mlYVA@&W-l8z$W`ZB?L8y)LND5N9`hV%$3I^u1HEnHNC1? z$)H%Z`W)od%+luAR^i0v4stX5RMn*jI)w5~(Ywwp zY^Bk_cyU5 z(Dle4KnzNk!Jj15{+Gsye&vFOUMMJH7@T&uVZQ9gUk}(=ia@XM&xeh7HEs zJ8jOV9tC64bts){|Eg^F%dUv1J8gDzqj2tUsSzh&)N!YP>T4_A26y5JD=xS-Hgx3A zD)_JGfJY8_x^*Thuvg}|f5|sD0QnA+w(@6D4OeWcb!#InMK2FCrq9y>QZuIeK)Y(Lp>ok*zljUrPf<3`yfmlpm zvrrqSrZ#zZC$dh?+94aBhkg=us*DAlw9q<=$GR(8?Ro|~aR}g$oBY&3myp><@X+=J zbV91>1Tm13VcpC#uC*3t2U&>Lc{o+qCq>2^OE|W@Q)r5rcUq0y#SAbdwkNyD)dyg`hygM>0S@U{LTblZ9& zd0tnm0(D!|WkW;!$!KVX<~qchE<^&(6Xz8>9H<$0MmCk)O{sq)AOKh79ro*lH~Q^d>D+) zNq3@u)5BBMS1ipW(J&9lUT*uezo@dHsQlO?| z>DFV^B_PudigQLTY796npyICKut_^kBJWVPa9YO|B8rA^uLDE1wJzG4c%mww*37|i z_Aa!UjO}9LE&Fj+FWFXyk1{BV#Tkrxe50xBt!7hof86r!ct^Ovkg%}piObbSjiOy! z`xDH2geC~0Dk#U3CX0!Mwt!U`RLXPv?v?704NA%)iqMHh8~ z%7Y7_cDIZa-TJ6yV{;j*e00lG+J~Tqi6@5oV{`*WN@28YwR|+ z*U+1g#&AbvWzj4hcRI9Lh+2{r>H$w@C)7qlPcN6YzF%GUI19>DZLPbuW?jrd&wM>a z9fQkN%9C(Xp)Ll&cTm^RGH0ly97lo z2~tfVBiWx-tKe7`EOYF)8dfFh$7GvHu$U;4PSw?68Mj~1Qfd`ysDIZxDc5r!;Xuze z8I*kk?ox``%FEkrB7{mM6w6SmO`ihI9XIQ6F9;}=v7JMwJ3h$?t4&3UfH>*G-s&@d z4=Bjy&?{YlQcTqBGqaV>qweXZk|WCvF3|L4rjV2)j2_RouY=I*>8sxMjEV(~M=}fG z3$GL1W~oX=Rmnm|$<1<)3X}nz<_D$U)=jc-M#(5W#r0<=|FT~RsKv1wP7ZDV+j=2e z0ySP-=x8w)l-a$Zo+RWai5wMRT(uh-D9)O8R0Y+ix_!J4HR7|*ZCnIga zNJ?^|DbuNTXCOJ-KbI*jc=jf#Q=-$>jC4Khp)Lv!){Z(E3Bg%|Pz-cb`|@BsCIYMu zPP-6OsH_Kb6qS(yBRw3>C~>0IIa${=)!Sqppvi~?iD{hS^66AxNzIb`BugBkdwmmE zh8sbjg6kY2fAhKIF0(8n5WWV(s_9yor8iRwI$Yd2L*DWd~EiB2VYI5AYM~yfZ7^@H0pMie7W-okb58? zvO&G85H+@fu~~4=d5^OcaxP8N(@<|mz$Ol+k^{j$xB~=qUD|rG2DT>4Lp?(G+}63I z!378~RVe#sBwER6sMG`&NSECKb;kn9KahIZnr03;4(H3-LGhX9qRyjx ze>K{=6+H#TCQ-f&8gW@)K&5cI=p68!D@l3XF7_4VR`*E60j)kGZ>7zU8ZvvB%i(y8 z!Xz7cv)K_|Z@*FI_gcL~qGfd5)(8Or7SABcwX8!L!)u=pl>q(hf$hNHekEo%?^uRr z7mnkdZ>U384>NGGD6`jPZ1)V@UALE)(~?BFs1Dv`!XYNteXL{Jzjq7>-x! zBnNm!IQE!3l2fMflAw0ng)ytVIrxo zK){i&^ZqV}y~tPv>a00*7wL|qZfiHHL)6N_9!g(OukzgBTn2U~mv`8};Mris^>D!S z%~?q>CMFQ7dl8S4EBHQBqabh3LOm1)?>XH==^}b_l2F^VR_0WPBW1OeP*aI0vu$Nq z#R@zMF?>GfH_@3QS97E8L%5^1ZjIuTD5XV$g^dzgNcj>Y-2I~AIDu+V_HOaah zZ4p?1WL;GZ3K=_Y2Q>^0j>Ei^(iyvuu18ipzLC5ju2B) zn6spkaac=vzSvxyOV&d_8*q`=7zb?FAgCZ#ye6rsZmp?0sStsOc2*f?qS`2T#l}N> z790@uK#`vIT~ibkRDIN2cE;lyL32&&%Xb?_SY}IJn?_{z3=_~!mi%_)jIX@+39b#zy15|ZzO*E^zVN8$?1>q zmw#~j+xY$Ozq;Q4f&ZKSzxtgUw-2MF8=a+`2TO<|9=Pn|NftT`NeOgRhd=g z&z!VM$}h$5SN@MqKSC@1j~9Qw`>WscKk+~Hf9LdPEI#?Z{~HzXZm*jkTDB7RA;OjULu@&Ika!P~ zXXQzd9MLEM@#~K~Y&zaD#|wnmiPKd+*Y>%7?VdA0jkj^Rznp_|tprQI-ZtS$y_jS7rNQ?mbxeKem$Q4W4Ec zpy2Jp#Sa|+{yCa`$h|C2-OBOY2fKNF>)bou@0TW@KRoQb2P}igeS^UMLl#*LzK><$ zK3p&~+zEXwV$9zI8aw7ze4i1=x00jxa7go)sYjpQ94x2AM?vy%$kPPFJv{vI`osG- z+HoXlj+P$W0FxhJ9GDz*K+BuCC|`^^2Y`5}JvWxJR^@qhb^$wztCU;e!> zpVrUEY7ooxAG|F4rT^n)Wuv#>fAjWEcp=|=&FCYnySI1w;-fV8{+@orXs}t_Uv!L_ z|8?JiSA+QV+xU>4|M3UDgs%qh!A*V0I3^!uGk7(ckJR9YjA{7cThprneT>#VWHkTg zdv?iJ-Fxqk-*dmyKmDD%6>vWZPj-9ywr4)}o$K4y?)%O^{>t9;?rHwjbNrv6S=a&p z{6BoL1D^M``>xjcuDki$&V2FRzx$qXfAh}zYA^cBhv#GDRTo};_@1`kozwrNH9el@ zw0YaceNO-Pk2$Bm(H?SdPo?`m-_yHy4XLj@H(z=8p*`D8m3{h8KYhDUzW5t&nukAn zprHKU`Mg6t{Im>WSR2bvI-gOWe)i^m)MAEz#Z@nTz0bw}g}L~ujrh8EU;HNC-`vW+ z{0I0OkXK&*<hTeYzL+^4odRlt|CW-4EU`DwQ zR`Gzs+-VNW>0$h6H^D4{X%(euh#x^YE&t<(IRH$a3)`uAlY6j;TI;PfNb(dmBaDe92Vmp8q&1hm#$I{2v^Jyn@N&*Y?WI-;8|=lhgE8j@j|L1bjd3$v^kR&)9d3Jd zzXOcWptU966khrHgOFZYbM!O(2tzErqHH_*qo>|@jrXH==&4-?FxZ;bbbNqjSWrA} zC{1g3wdPZl;#+wI+e&E7MD*B4g`S5r!FQhLtsUO;&7Un^_iiJ`FuBY1YfQ6 z=TETM{|bkN0B6Jh7%H#GfScbG3fWQ@Yc+MZqw?&G!jAtPgcjqUQ)Abzc{zpuaMb9|(Y zrWED#nf~~Xm!tdnhre@Dzsm;d?{Qpz-R}A3)vo{cMz248Pk(>4S@Y_4@3jsjSO*AW zBsk;0aymJP&v1|;edV2l z5{AY;tq>hSNW_LQP~}+;%fW3Az}7OjTLW!a=Am$)hlk@CVWq;0+%(4d3+tk+aDLie zlOo1)Kj`0i{hrU$&mRVFiW1Q$E61Vxe8{!|m-{JuKV)BKyWI=gkBjst4nj5P%nyHx zVAY?|KYa6i3_pBgJ=7Ma;xR1KULAW@@{{6RA&%reczKStKathRr=Px@*t3r`tFKo1 zM{5!*DgMgBecu`Ro@=1!{1KktDQez(01g zFVlB_>i;dC`UiUKfAB9}9H_Tb^VVbk;(vQ`*WZrr?zgw+&f_uUcn_c8$ixx)?33Qp zET2C6<2Weu=FJZ=V?TV%Qa}yr?(&9hG_Y;QyJk_~z}K&>sJi>{KYVq!&mQoT$9&Km zBw$*{`u;8CgxXsaI4Ilm{oWAHz&79TnC*$Jusy}wv`A6Dyr^$n1WJ+uS4BwGd`qYH zpMK@-ddI2#0*mDN$v?lOuRnVCk^Qey{moOtp}&wQQM^W zJ=Kjp@E)^#itOEYzcve-#t5ZOgT!rH3gEgRei_6_h!-zg;qwlC_mSRY7LvjqysYBk zlOO)niZb7N%=rHBrwDZ7@9?HtC(5x3@6#8z$wENXsq!3md4s(+Mnv@FKgYNrtpHs{TK9`3nt*DK(0+RqQ6MG_#A z`T%G{faB(&Ky}qeNB{;~R2jeut>^gW8BqZ1y8>wlm%Kd30#E@2SD*d9r-$(rvi{|V z{O0)~qYG^m8k5#`yPdMPGlXG1bqLSRPcgC=+`t2)1!Mlpe;K^T>HhG{LyO<u5Kh-aGoxF5!n4pZjf( zY_ENvo&XeH{?=+>M2>3rpoc;ANoo@>VK`}?6A#jEaroc6x+cwQYq zzxDErv1`5R*}I>==ML|l(7*Y(-#uF-&;NYc{_n=N_?1cjRwr}st>yOoK<<{?5AG}Q zRga%O_?2D#!F@M=?&;IN-tFk0eaw#j{;%BkUk&10T>PE^e)H;m^|VJH;e>hB+mF)R zhm7Y>-tOhU-f8!0FdyF5hm7QJ{`$x6t1)~?D<9JPKl#v;|J4{iysZxz$>QUgAg{*s zFyEj<_BE#EtMPs9CGQ*6d(fEA$LcF!@o#@I|MsRUQn24-yuRw`?Atf` zjrMRGNPpYwug96bz2?;!xVy*lzr8Vy6ahx~PR9AYCiSavuD|0gezm>+K_lK{2=7|^ z7|=(t_g{^9`xoL+e9*XmaCb&t_3`P0_pF|;TC?|@;q&YM{)E9l`!4VJ=_wBRb+7qf z{{~m-?H=<@SG{LYzdD}ssypwEr+oiTD|ijDf4HD_Mw{V%j8*?~co?;1W|BANiH5j5ADz2$u!?h{r1x*Kp9-v$B07f z9JetYL^_`Ob9X>r8h^^=Ui{|a(n9;&3(*E{c)tm9yfDrSXjvoU{Rn=0_p5*WDSYMo zGH6lv|CRO*+u&dFsd%;S|3B7oEamU>?*?(-=i$8Pn$0^)>*GBAx3Aw{MC#u%o zr*D1Yx3BHH*|_q}Pra-N05SU6&wq+QnxDr%e_q?a_{DRI?x)BFl@C9)(+C1pG5$a@ z?%^k||NWAq`^EiQB9R0d{ReYV88HP*DWc zbG@HDrt`kO**ABZRq~VP#vWc8d-w#mZQDYy@Fy=Zc|=~@;Pd01tT#swF*y*B+Ae{v z_1<<~;;k4<@Vccp_b~Q7;Q2KZ;3Le~b^%78ut2~Pc*dmA=CY8Q~dC@@a}&4E%vGRT=TbH9@MY#)L)I^!`k`I z{eNXe|IybknQyW5UJc;`8~UIze9#N|Ea%jK6bg_V1gC(?0<_`59)5gSRE9p8n@w z`t0=ge*f)d#(#l>6D~pu+XE@249O(Wf3ueT+kS-8u$`nRus_e5`*h*QSya9Ol{S8W z^jJ$f{``?V{IkcvFtDk=K^uZ_BPv5*j_djokf@|CU z;DrC=`3pa3J|*w}{`9klKgiQR`1F3Ubq$J7{sZ*%^Ui1BCw=zN`JDaJ#~)oI%l4vA z@*jZ#^rOd*nwO8h$?AK)8cD>+!}mAOKG=N)J~h>Hv_E+SzWTrY|39gJ`JdFwn|(KX zn_pq}wsf=8Kg0WZ`akenOFa9J@MdB^s9*Mj=TrXO9pUtU;`(3GI{2UPA>f_%fBdpZ z7EkSfZuf_O`1YND+!{`wynJ*b@Yg^6@~wmeg@1qXTQC+|>iy4J|NhHUO}rI(Ks~y< zEW{0eeDQy?_a;5ht7&=|8n%|owxyw)IgCGDGs93C~%ZS zkrYXhltkE@tdgLzJK5xqBtIkj09j<4ZGJ#5>Ko6gQ$tr(Cmo<(9KPrMB#PqjJoj@C z*L__9X#*W`CyR3iEE=S<56PR9;6&~|k`t(-kwEPq9A^=!euPhGH*}JbzW}p!4g#{S zdI78Pi)5rF1kDgK4_B7^1x?YvpnhJJr|<6fuf!ACfB5D^e)`Lww8^t2ah{j*yI=nK zf4#h%MkM?FG9(`)iUO+)1q1*%1LzNvXLA4R?|%7@;o_eXay+c}KOJEF9OywjsI3Aj zar|hOeO}ln{MAVKwUTDgIhsu7M?+BF|9)7$pB%)#_(t#9(Nc5k>57dl##(@CENOJ!>9kJe?j zx7<({ALP1#KDoa+4i>qA+@EBuvZ@^VZ7hK)UE+mi{jYTJCf&lQP!5L6=ypsq!DGBmWjmmy3Tc7 z@>Q&cmN_iJb{4u_r?0mV_zjO^pQguNJ3z!-9G+*8QLQfY#%;_S2xU3$ z!9W4Abw!b7%hOR)YEu*;tOON{J}b+REm_vHXfW#?5_xM~HyhA_HHEmU@2nSk`$>*Y;aD!)0G~EOv(>g-vZ;* zaoAi=HMnhF8R*I8O9&0&c)9N6;60bys@d4r`SdjGpX=*Eb4zQpVxLba34_(1%`ebA zIpZEKl{eeg$SRck`T+u;T}QF=^NBqqps}h3l8}z1K#L?%Maq22^iS^YTGa&Xe2e+O zgYkP*uiSDZE>Dn?H_KRAGmQf|ybg?v=k;MAp-3sx4GT_AjDve-whTC*Ky8;^UwfSN z05wAp#vW^^P(z%O#x*^%iY7r4L3Mx`natR*WnaYd5$rlwwHac0 zn%$mYE!s=3SO+8cD=MBA1pLxi2dO0Z$2`#LIpa+d>DNp*h#gBlr<&nvBv^`)7Gz&g z2=jAyAL$^u>w04Y@kc)lNjDTlFb@SR%{?LcsgS{Way>LNu;BKmBqc-NmydZ)KQBG< zzzIclF4Nx`b>%|RI7^RUS%YzQvn#KIno&-Ana2c+Yl;rz8^sbMQzvvFK^Ikt&Yd}^ z>izO+fTs(4IX;NL$^pRn6QoG>)~iTUqog2r@YCChs- zdJ*zCCBjyM0GFF5{c5>nVJv{e3&BkVHnbhoOu=dy)+9a>lG{5+;*JOs*exMW-=$Yx zft37g8T93oXLOdJjxqriGblngnBXK^kRoOh+2kUL@7N!F;SRRJ$J2M?60}<2-QQ5R zqF-gx>i{J|aIdixb?vmUFm$j{VNTUFD+-`=6-0koxMhj^4kg?9^G3bYn4F#-$J?qL z_{`&b#qpE=V4A#pxC%Sikf(X=%!dv>Xj)Hqg`@TQfM=aH&y1Ds7RZa*0Q7#~P!#n0 zIW$dx*%{Qnd0qD~??MF@v1)P6eajYh_r90+nkEmYmKn;SVx1e(bBx^aa2Ka7d3tB9U6LMbYqCFl?E&cWKXa}NeOv3GPe@xP?jvwVOR)t&V`;O zc%c8Pt4N*g&mh*zUsWAkr}RsY1?c)r^u>vstRD{8&LH)nm)jyGlV{mM8aClAFDGIV zG}V%~Q7MlkX;0*d7NoQo+fLylIs;|xw2ed8DJswn6D}zG6{n_x&EmBic6oY;uI|MI z?PZ;h>(`;i^NQDTEWgfJzDUmk`CC1BVn5Dr5{$0w;EFyT1Z01Jl8rP5q^E@YBn*(@ zv0>^l`+#IcmL%Kt+BE8pIpvN zCQt^YgBpasuka>C5kzw^Uf5?DF}*<w4udk*!;35)d8P(&-q9OXpX>ZW{mDUfHPfIyJ&kL^_8A3rp=s3R7sutDKzGfJ8k$^z1 z&gKxJoiiTRNXQy8!c-YpD6v5qSXI>_;n;Da31H_XMf}lu{Zi;z7Cf<-&OEd~Sjb7A zaxZ+=+snEktFVbfolQG>XL}y;Wa)D>5f=vzo|lAY9175C3}vf0_#Fk*t7}=Qe%E-g zn}Y8Vx~6eA9M?&{&{u4pI|&8lA%zvE>B)J5Nz|!fQ{?wrU1R)EwKY54K}&f)x(b=R z*#ikL=e@1STDNK&EB4kg>T}{BNX!p|26bP@(pbY~3#7+cx)FzN`4CnKN$?CN7t}kg z)+1`aXT!>gh!nbYv_x0)3f@^WvXHyY^mMWaJ0-z*{E4;lv9~=tYd!pFm9JK zL{x0ip#*0uOLr_HP~r$$Mrb39nPHImEFmce-xt`K$%(fLekj#qIiwvQO3RovADM5R zk*PRzU~;f1W%OtQpXZ2!ANh(CLg0xG_8iJ2_I8fXw9QaG_>r;p{NNH}d#Y@~zp)}O zTQI@&ZNFKN)_g?{6HOBO%?h5yl^ysyJ9K<@zuFP#lHtEXflL{qdTSLGTfiAmio-Zw zFgrx~0#0*kB+D$|jOMS~Gp*>jCem;;K1Ux0R(9db7j~r`Vs8Q3T>8qBlDXNwnSlAk z%j@vMfy7&kW&h3ExukgrG)8P!2MGjs_O?E4ZioR!r7ybLSGH_{(Nx}Sq+^}-&>$8e zsQ%({^sA7}?LQIlQ=t+KPdW+oVk&qwV!GNaEmcd?-o`XVK&qKvH6g4rI*_}v&(-TbF zYL%*?*uXts%dyaa=~RwE5k6!Un77N~J)VhHG1B?~mRdO(ZN^+F!&y9!6~tJR`NEb5 zoos{M&}nqn6R3TO{q$-=2NTzPgPsp@77X~ImI@yQ^2INyKiD=UEqj-NswfD%Ida31 z3ucs(Z6V-W$?CzSwSG@e`}^ljKDZ3UKj)(4Du-hx`i(zvuvX2#UX93S4yTJyTU%3!#nm3mQWVz=;^g@7%}KaX6{C4t*XyD zX`D}l%Rj(&)uFwDPWAJ7wi59^K5Ov z86GFz`tw}G3*$b@Zl9ho-jvDiaT#Oz+4#b8WU1ZlFXVXK-6T9O-}mx3`Z(hY$Mf`g{GHHj4-6r83dm!Oq<-p0|g8 z6PMYOX~1w!Pt`C!KOP}1Xv;agMlel*DH!90(jNI!yidUfZ9Ch&zhnFxAJxvd&NwiS z{l$kbeTE-j;3O8Vq zzLA4OE&{I@TDB=58WSClEvz|yS}f8FR)SC8dll3TSq3T_H6lRoa=UGn^P}*wCJObf zUYx)NJ)NtY8z#VPvbWkD7jyy3xQfa z_o1kL-MD=tb_;e~OA+@m9my1(Om{3aa>SS*vDSh`xq?e{J|jhGK)AQaq_}yB^}gF6 zd$y>IkYePyt;mDD{kS=sFdX`&kvVt1f?x7M{9Ipc#JoOmWrLt}_o2O)Ck zI2&sXjnO+3K)qfl&nGEWuaMF6^rE^F>FOT2W8U&MbJmx+jxfJx=mZKF0~p?OE3fKs zD|maT$&yCQ>1vH3LB|K1UcyI&Z$fml`J5fF{4{iMq2n&IiV!MO2vr6yoZMer#jc4z z+4S+*e9im*$)^8(wCR~{a+-jc9dUT;&CmPVEvkD{#YzL4fm}86sS`;QGn6UzR0r{A z_q^v)_{wK{w1o;IaQj0V$4hQLECT>97AM7R}>{_4$u`R9xW5_Yd4Y|0$k5*gw)ahp-H2lX9sofF5$=yOl+8~ebi z*5mGMBqH@*MrjM>JMVLZ2-gkDjAM>B~$ zl>$w;wRG`i)1)#6#pMYy>$nWROsM zm?M_GXXAM1Bwewp&2{jZ2KnrQAdXUE1U1wXnvG0ekk1sYYRn_9)az?=VU)L@Oso59 z;Kyg(Frk5J1!DeG5c`>%^J%F_!o9Amt%l{J?~8J*Cpfe$J7eyv^5&e6+*cgn*g_o$ z0>8<*e)N?lJ7)3_*Y~X~XqRpJl4?U@qW$C*<+|@$R22)#P2&O9__#q*o-NJog&Ebt zCX@Y)`+v*#f0$8vYSoMALOU~y(=vxJ9Mq6l%9fZ|AJWTtj5#J#<}zdwRG?{#Mx`!y zgrvDau_-mmvVo#VbP3;a{`Ayx*<2j`$-#t%#ymZ8Dfm|pSAKE!-f@g}>bQOu7FAu3 zt{V!!I%0Tzb?9sWUV`MA56dSi`pw!hBS zdXN05EJH+OAbR8w*jEQJi5hi`Tt(iCZiDGqSDv0!`YvFoF-&m{^wPSmf;(a@_!4N% zHyRSkMx-~^C2AEl%B&A2;}}_(+7n5+QBjSK5o-z*{F(3u36YNCk?*OC@j^uA^sz?$ zDwaNSkE=`eNHS7H!GeSuPn$$jPWy&fbC( zTLkA%Th*XLJybiWPWvr`x_&~C)u>EI1+M26jTgM1&pb3&!<3PsYbH93=v2t>gf+a$ zo(`e@#6H>N`B*(oZrCx5>jHUjDOF`-dR z8)T!co2b(zqc7R#`eeGOtF@NEag#N_n((Qz6=iW$fhnp|A8qt{wmzFk1|lt|+5oX4 zhZ-KKw>J;Pf=hoYAj`wl8pBc;duDSU@89g<*?X^F6_9VbN~^qZtGGFzZsT0OjdtTm zp~^nS$A>~$u_Wp!Oiw`C`=w6@f$bBR#xBXLpui_qjJ)Qs^W?GMOqN)+?;PEz80E%Z z!fbV2f`;AUJ}ZunP;j5NmmS3HMNKwCsvIC-w#9vJw>bG0X#y`V1|B($=h_+9OJEYV z-CAYOs3%VpC*MG1Pw=67rI)Zb$ZHy%G-4Olv&C4&X2X1_2mv`v6j|cdGrQ&++ktQWG$8=fj`b$;b_%EO{KGia1mvMAs1!kIl0^{V z#MQ8Y^fYRf6kC?18-G3KVSxG$YCFZ#M4oGz_St;(y779liB_f-sqRf_P8>5M?Jt`} zZ8f=@({xGBQET*6K~=^xoM;O>?l1DF6o!Y-jdiZoL|BCoB0`@`(8-bU@?b^O(=joGiF;@Jx@kk3@T{b_ihB9Sk9GC2u4Fav zB~aQF<7!#b?|ce^!)yk9n~Xx8A`L>+pyXuCm5r*4w2c}-a2Q2xLi$r8)qq|zi=}h3 z#WSF|5nOOMLuok3lW_dz6UqqPj_gNY?I?~lMM$7^)_SZvh|hPvXCF*ouJ05kDp0s~ z5wv21E*^#OMKIb+>I@W+l)ENc8!HlXe`V(7Ej*QVc=kSS73eP7nj5II^C+0Nou!tq zCH*m{x?nOKs0u&MZ}b(Bk#2%WJ2Gn@A!#%R!BVI@lLe$(M#{m8VU8` zXrtzhEVNz6D8Gu3w?gf2IYYR&n=@a=gH^ukAx?|B;yb5`y12;ZxH+TR89kuTMUhA4 zZEse`%{F~PbZxavMqi43WIB$S8$N3lxPK!!WWo5clI^J-IB~&E6js&S20`o5Ae3+{XN54VfdW1I&hu z8_DG-O^TWY)1MzVXNzdw8EbUFMGUcl zn$82LFkyDuFMxqqE^}1=YluAAZ9#_zWK9nyPJ5wz8z<=G^yn96G59bZM7Kn0)z_wF|S?JRnmII*RoXuG(pK1mn=-W`VIzVVk5uh{(3L|!+lnV zX83XQ!yswz)tHZ3zo7UIoQyrz=OAYHael+^ikINFk<(_ZmN7jFg3dXV$xI6B;*7-j zHn_0vm+izpDto_jkILMvuVdbynDQa6GX{LFer+aa)K`YL$|h=iF-mPA&qu&bZ7u5V zi~G^avw)^L;OUiGRvb{UJH3HM5!_RH22zxjZKq z4Zg2}5L%}b%%5i$vjk$Qs|@g;A;=xmywxce!8<*_U+L~jmlSKcF>N@518T)1o?x5Z zMVCZzzz23D00!?%eb+#e8Q_{6%G3b@wy;Jtc&q0Z3jXDE67l=J&vKqh3-__!`92Ph zs7pINlEWhzYsOQ4AV*AGk@;;=Ak~EeTzejU&bj9Ordq+|#HFJuaXJ*!ao(-hrp$20 zyS9!%&Q_58X-R6V69A|{7)gVC3a~=P%h+zab_f4>@~w|N9O{*kJ`&i2$S$lG;k^oi ze|3<{H62Yzy6zS}^v#L=>W7`ZTjs46#@iS5*Vk5tdaOLEcX!D}2tUd7eio;|V`W@O# zs57|^=lANsP%HYCsMNG%eXe&KQ8F0Ik6iBf@wx4|L$uracU7p^rvc4n@cwOyaPlxO z6#UdF%E}k==*>HZ>6eg>>vUl)wzP_e;l{@ld$1-rL4iKLF(o=nBNW9mAVG zvgHknJ5c@8DFNl`hp@ZcO=ize2#I*XC#Ci=0W{XTrae1`59JlIbV%;G@P&hvTe)hJ zEAO@sHdmD-@^B|k6Hhr@9v7}5g(bU;-$s1Jdff`tbiU!jDfz~HtgVHl+y|O& zn>-EosoexNu?_j`%34%h7?z6bCmx}B#ih;`S-}|^ZbR#Y)j~@7vvb~z-`I=MqC?V9A6C@@$mECG zxY6NE%bXFv8m~R9_I^?uq36{lWtqA&hE+;aN63cx!G>A-!G42heNyh*K8v3oNo`jW zAJm&mABJqDIfxng7vogx>6v=1oS8JEU(}%$XZMfiFfmLqS{7p6lIt{fXnwfS&6H%h zE78spQT6u6L|M&`j&4QB`?U;G!2pkdWSn+w|zQDAv@t@8q!X_-vzF4<)fpWx6S<37-3Ua$NU=V$IIy z-Se33)_Y1nAyipR)W_cGcg{N0&MgwHcKei+7qcEF3n0{&>wz8fuI?GQ-Pg>m{KM?v z)-;ek`BD*HzGTghJGCJ9QX>W{@i-i3ds@%zVXlw(kU%MKayi=ut0P}em=JhP!jrCf zNp=Ozn7Kfl<~^S}H`~~m%=8wmtZi4sQn%lss5-r^flY~H^ib$4dnXXIw-@jFv=3bE zd~cB|xoQ5Hc${_Ao8T*;R171X|hi*_TlNc5Ffbc(8uS&#;U#4xUSkpq^)s0 zzkt;p&l{*w)oKp*(&=;FjvbrTw!1AO*TC`RX5AZVpm<8NeWC=S^_adw98&XwX&+5xeiY_Rl)8_U}ib{LR9tTkr>!J%q1$JYr|PXe97EMB(l(iU&#RkFHn&DCPihAG+=A-L4o z;pQxueA2IurC?&JiAxk2=m(olA#uLSSHjby=S?m>!WGj-iP)^H-b_mA`Z(FoOR6Rr z7Y2*RY!kK1+n~4YOOFQI@@D+AdoDOiWltA!?eX0DR2TarccI3FIEB2Ijndd~k%R?N zE1B>j&%1LvU#_IbB&PN&i@#}VyNJd6e7Aef_tZ08oK|;gvP_8iQP?i`bhk|Q>r+u| ze31{On-K691GOj-V%}?JX3r&Qu}=@^P6_X`dqQx!evn>m%pG|oZi{*2I=MO|uxibRqQvO+RmUG?aiS3C#}YoH#h?fbL#s4hu&WZlIgGL+sy zI^~=mmSLV%kyKJS>9)p+=yZNEiN#Xb^7`Czm5lMqwj}`?EhK+HWkp`t)$Mv&3rD#> zrZv~NMM82 zaF(=5v*7q=1bfZi?6q-kFz zg5vjlbmWIh`a+j7T_Vp|?$GdIKyiUlz^Av$}xD7U<3* z&X*m8 zj;y)#&d^rL4q4h9Oj)w&RUI;ybSicoa~PhMNF^pKDd)>xBX>r}H`TNwr>pCdIbAuL z^jIgz)+v8wkEC1*ZAM(YuF-U-YFE5)GSh7|nHqO^oJrTVHmV7(G)r?NxJ}_cucMXb z$d=>^Sc`c}4kqUa8NeMmGxCX%o;A;XmgoaqNXIQ9`961a>goL;od{;J*6v3pA}Zey z{b+Msg}v;sn>6t}b!Np=@(f(_Q>gFEbIS$6aVq*pIc+Il<)+hvV#29_I1t*WkXX9yKPJJdsQE7imhQd&V_t%4^)*>7#Vq z$qAVn#GyU+ZMhhFF`I{UMT(im@s7YJ?pb>(I(M+sz~~gQ$~K~l)ipYk$LoVOMEhV; zccCmv($vUh!CcuJ>+bXIDHGB>-c@2!pmf5PvA;)4onJ=ILsBK(+K_(uB3sgy>(W1j zgl?9ZF3v7=U>cl7=GW~iXa^@jx=~V-7{F*Vp6Qp#LbBrPz+Yq8Wlf)I_`5b|%Sycp z!twH=RgrVzC9Ck^G*;qzcBS3;DxmvjzG1~ZeafTEq@xqTDt4<^_tz~=b#q}z_4FhH zOinG5)AEV>v=uTu2ORRIAwqSHm4(^I(}$$YXN4wtcQR4wZR#rKHRF1Szl$Bm8?TKWC`(~@ z#L@BfoW6FARix_F94@j-d(HAiEqa&+jd`VlY>@5BD~dzbKOOWG?|Vvh=a=3HUT9KS z-nY`G(`wYO=(!MvDJIZ@>iWT)K6#h8TcJX--Ar$T>%>o@;Y6;M)xDI7%k6>-9T3UW zN$0G5rtOi(C%u(H@+O>-)~3ZwM&I41CoZbj=rO&Xf$LOOW8UHR z;^XdSQQ|QZ=2~g`gLPZ1X2rGPHexhApK)%@;32b0mkdft9&wrW7jq`;(^{ub3n{?T zLwKr_ibL?MyO=+%oTR)41N%5c(}%b1&g*nKn;|=KKR@*3U>LJ`F`+f@h%Y;@rqd`y z^DS|+o^w-tpuU~#hC4%SB14pNH1`&wXomMhJXKlB?&~J%9}i{@{Kt#d4sgX{8mI&2 zsNE}S;mX%!$m|&>&69Xg+}Baxc==(Y&KY*P4!jdz2@Nrzy#g)3ZIAnee$=|0n|{8R zBvzljB(xnrde3!hPb;P>6U!?zNTXYwZrAoX0^;%9#o2^J)FFvS8u{iseO(7)iA74S zRqgR0ZbSM+A%{wcxUuRGNLb=|ni^V6#nbd4-z8u{t^r%4S)4m?m!tRF>N7nHfL8&0 zFVmkMYhZI0_pY-|A00vHcY6BGrjj1_D{-T}xygm{WhjmYwOA?aL*AzxzdK*t$8$-^ zSTjSidP;ZL&%RX}zrKs>X)o3D{#>S;+jcHC#tne|r&2xyTBoLHPNWtdQHbifqm{Pm z=i%a_&y4K8eZgHLZEKn=b_%)W8nIT&($H07DjrHZ*(B+4z3rE~g=R^c6U|doMX0FT zit@!CHZH$dMROMYNhUva))rf_l3gKML|4M-?Lk>UjX-LH9P|H1Vg=MM^zuP%HsmF7 zcS7ToGJmJJb_G09kQt~L!arXt6LcFk^Lk4g@Y4y4uL)v*uu7UqZ#yEg8_FlhlUfpAYJaZ0=TR}X)0c0=Uf7_n9hR5KZnLCkrjJK{(9l2`^siP#!tve( zY{}1IWR>JPf4G9M0Z7@D3X`1^Yvm zTcvLYf)AKe+mU0=<3gH)8=Hz-g{D|N>^Pn6%)5cLBRLlIx!h$aG(G36lvjyY3){=S zLdDP%(U80w&|QKsdgcQ(XS@OKLFu-d+iO{_&`>Z9QfFrwGJ^zLGjPY3WrNLqea zqsF!OsdG$|^6bg#E?{Pj{uILCCc6keE%lujK|oy$NGz_^#tUb2f4ACDsG%qGo2PE& zS!iU7cy2%A=eg{Zb$27R+xFfeS|E~c2`OlJI@6W+IJ>urwpUjupxr}#uZ8e+U(t0* zK8cM^tjNQYy%J^A9_+2*7z5dAGcsKTwP|VRctKAi!dWltMf5~7;Hy__SVDW*GI9sU z{~+qgg*X>hj$@#wos1SA_C(r^&}&)WxjTc*#U$YTP2PIf zuBz^ttXJGaLLfS}Fwctv$ras14x}s<{h7ULfzzaEp}7?3uv)%2>&VLlW71;%3Ye;O zEZp269K?N&CNR%vqeY?7Lw9sDiz|KY+y_^|%}DO#uj8zqvxV$tXW^-;q$AsFNhY^h zz-Fo|XA-%R2zf6beP7Dx*Y&RTjWqhC>-H?@Y7tdk#Ea|AUeNB2=wBlqZZbwH%5b?fp9e zetP;MI=VrLNOcjV-CGods6)nSNZuJF>cB=y_ftkaJ-d}l0xozZgt9X_SfO;)f<6E} z{Y)uVL~&LPGAQo0b*3`LC4dWHZcfbd9U>aZhnWT>PCOiF@>H`cU{V}_7#`Nc6IDV} zD6Nl&{j$!N2U4u485%gcTIv}iwg3WNxn*eArBM=He*=tiAuDt5?mc;8OS1G%KCN{H z0gXW1`<)!d2?^lKEa9*Y6v?V%fTy{4FaJ($(=eZ~Lwatzl?|K?fAHq1gpxc@&C|`E zifbfF{d{Zr0UZ%BD?B6$-tv*8(A{fm%w;`WDhZLLy-0#LWv3tffnyzJK5{SQ{wrz} zV48pxB6qqncMNb^u=E4*NSyejuvJ#_oFt_|2KbL+kL{)yla|_Ceu^YKOHew@-+0be z%3iDr4<0yD=W6M*r@oJjRrg@~7r+3jl0DMv8xOd(fjMXRuF3q4-CnHgd9$H_H4O-p z(lbXQR?`i2fBCSaGEp8z$4#&hjNQAJ?zz~^;?;=n!RxoxukF*jnzIb~5%mjBzm?XDMg#Ch#n+K3XFP$+ z1Nvv45BzG&^Q%DATtk_oQJozKMYWIDeVwy=Tbbq;_`m4Wv~rZq;Ax<#G0+MoP#g3v zoiD7?Ew*y1#Q^}(^RW-dUxQcV`OHjky?02buU%#=ktM}#{1~AEI{MYGZ>87lBwmCYz`%T1AENyFg&p++~jV( z1pYa@HCwLTBu~Y+^)?m=z)s~if62YvJfeW{TJgY`64H|~?Kt@Xyeac(BPWg17de1p z%0iCzhl6BYx+7XF42O_o$7{w0ue=1lm>JYv_v(89NCaeZSkWE(*^aGqHMcXW)zIMH zqanfsHa$O~S0Z;oT>}5m2(K|vLTa*l9`7C!Bl}y_ARzQ9t_s&9N6^@FF-c+wSy^c7 z&Mt(MqSuEpXWBC7O3&YrqGjN5CD*0S6**k3oF)uZYFb?uM}=yv+US2mT%BFdjwAk zxCc-???(C_)nLKhLl};~Gfxr5u(1baNLQlR#G7Ww#)}GF)TTJ%q>_GkJ_m;&SLbnJV&VY?FI#L#W6e42ishA7GOaLa zy17o>u@RjBeMugv;H4P*(ZP3c^6jm^;;vb_YCPX(Bv)6x9@Hx%@77{tGmlI>(<}5x z7wD14oCAT<&X!@=uD|KK8|h;WPEd>$F_sS5)*%ftwqrrP9=?aWR<2&8prhuots z*>MiYyUBe1I`t}eKN2#=xGyTQ-+KM)gfQ5vMH@ERN39$10am`Tz1FvK)pxKXAvvF2 zfo}snkYt%dMmOM6=vU~_z`C)yzK)B{cy7X(E_>7!sI9<_wYgAp^0?(m_-6CW zh69?;O;AZ-Ng2;S=nm^^+6*ONU~F`}9I=K12#7ouf?lLkW#C<0UbS1d1;Yr8GGN>! z7E6ZC7O@dIy(bhf`>sP!Qont*7C0=D$&1C>mbq8LU*JCEY?GjOi0Q{Z z1c5YGnAZ7%nPqkYuR~s`;6RBRRy{w_ebJROVD-_X`2Jf3=+abW^P=53??sHbjAntg z6#Ydy(E&tey3XBCrROF>dYO3ha#_fWAO)|J{rygQ7-MW|yZ4g2C+{)c4fL9-r^rW{ zz&(rUQR-gp$|zBY473^80oS|LTs{KJJY0awA2EdQ-hD^AZxYT7LJBxfiDFv-oe|mw z?c&s-Uj%S_yGGA%j^K8(#gx;%?G??Q5t=?*6YOuVJFEHrkop(Z9$1_f{0ZKVQ{qa& zjI;;ydQ?&g6;{}Q7?`7#=b?85BmpCTmNAWA>zDgH3KD&RbGE3gun;<}5TkmtwHDXX zDl(_xS9>9~jda*Ncw5G(CQ~gX4NVg|u3Kg#v5QCyf#Y5+@b5ElyMmU)ceBgqP4BMe z(~PC*rHY_l};<$#VUadFYn+M#Lp*MN~&Ii#N`P^dNbsQ;>#BiEw#wNIcTx$f3dlDv< zGa^7mnza@M_zI12y|~sE`b-*U%pdU`X;nw0;|Pu){Oe$%S9v>fzl=OYOGP#W`?Nbc zfyiUc5#WF>2V5`7x(`y`R~Yc)Iv^_-Gi^ppvqX*yhkFAb-i@jXdL@i&p+qFc!2xH* zLne*+eB?mM@4&mKaK$OC&BgITuPURQpUpYy+Q{4CAy`3Ck9`{aP1a$}dIN4R_!7>O z+2~tbOn`fOwAt|6D@zWAHsXPN_*xal!J*;@ckz@@Z+~h>xm(c~@c@%qiP|l2Cw~l1 zgw13JE;;bQy!+cnjtkkQ8uSW#BknwU_ZLyqklgJivoMqI#|gE2qHoRIjC^Bm0|==L zt5kwmEll8sZLAl#ls@JzUm@^ho6P|@ADp+T2jIsNt;=+g$wnB4L8w`l3yb6a+NZBmcPiDs}VB$D(^&Ex_z=`g4 z9PQxVm@H3=Bd8#hQ{i-jf1{H`Uo6LU)*9DPXIw(vPshNGe9SdwfeMw8?kB{D&h=_jlv@{BI+%?LW&t>ppxv-dFvHU;gj&w;t{& zatns_3&VJIBDQ`^y`32D1LU193Ww=526>2ola{tLWfDTUZ;f@{h z54Q&5u+0eyHJ{}=KD_Cfp|sF|SNsMhY{dQf zq{Y8p1nful`RhOIj(>A4f9R3^*4OZvoEd^Ri$BVP|K?);NC*5wuIZota2S3aHox-L zk9^PfC;PWX2Xp#OV&D8PUzn;t&uz%b?msiwd;b8`^b@EnqZMKlT8<&c0%_%+efZb^ z+KMjMOZ#u$#L`fF9tBK5`w!-M2)*1#B`ZX&&}Y7tL4IjpKmW-mU4T(QC3&KsJx}m| z%+Tl~{r`LNy@jNIR4W|wc9gQZ;KNNb9^#`+Oaggk{A;u|AGN3{@Bg< zX3YHf`*<|}=MSgmS3Sjl^6jnsEO_w!7r#FC@4t=%|6e~i@b_1TA3pOV7L~`>Xa4!D z-V(xp{#zg7Hy8Rl?EGU_{UdsdpU>g^(=SHrU;WO5<(o75TYTt8&g_SZcW=G=&ky6r z^_%|_8EfL7o&Uk-6aS5O{i zfB(p7{+LGD*Ju5W;a>i6CiXYy^v62lA97XP?`3DcPW0dJ^FMONzkLz-W=#IrBJj%z zYJ|z?osD7`c>F*4Y`{M`bKkS{qlfpy)#0oC{HH%S)He_9SKh+4EPpU^e{4+s$Ua|I zm|u5--+b+F-}lGP>z{?^KEC+d)N`1hQ^bdl5<2|fxq?pBT*~&Re|dn{ zf<7Z|!6!$LC1uoqvF&cdM{wE^5jh+9? z596`N+wetT?xW}R;Wz$#`jWrc{mKXb>chYMIg|dyhkyC~d;UJ?PhUU#@LB)oUya|r zc)ry{;BS6$>)sFSub?3UeN%XDDZ151?b7)2b~1nCNsVuQzIq4BgTbh-`ssM%N&O{G z>hqBJl~eiNm0*N?azKCU7ykGTpHJh*kNWW*ji)o-_%EaO%eegB$$c1a)cZJ}$LSw- zYTw+XA35p|PVMtoew-TLJ1-2hZ`7SWKh{yq>EC=3bNa0O^!o6#zie)wgqA)jJVD!O z)OezQ&j0L#_;c!a(Rh0OP{`?{Jk^JwNvmO8v=7 z{mDvw6sP;Wtkjoq;4NnMfV23UG<<)pm|6S9%lsU6ec#Xgjbdj1?f>y5MO1$}&hIE@ z_S3Jq@wb}Ue}rUj5)|KMEV9$T#J^%>zQ4=(@n54R_piD#Kl$+Qn4i;Us{CgnT#{Po-JC$tX|NU>0Y#V8%zDTysCRX%r5=o>YtZrp9I6+vUpRpLz>MUJwXq?xBv`KfWGblBtsDI3gGr7cXCIOdpK`*)IsR)u>oe&7c>dt*aym_ z#7>Y}TAiQWE%EKQ6wVg16+&IvomX`pG!Y?(pyWF+{=zc4pARQGn zy)1p9K?@8V4EH4H6c8HlVgWma?~voohG%WgTcUhi=eRqhM~^T;`}&q2fe>0;bp#R7 zeVY@*Nar>9Xy$p|!A5AF6$27%Cg_~d9om!6R}#|gic(SY27(mO4_XA}3z&cjeKrTH zpyQB0B=MhUEkDY-kfgpaB9AcAMouBC2YES8Z=aoVO93W(j~Bu{n&&!jOEVTp5rlw{ z(gE{Y?WhDgGh#xtRaSh?NH$xcu0A3h;>0pdqJe%8`i?yG$BYoZPo?ZpfTd>pt_xC` zXS3PNN^fT~PHY973|K}$g^4wWRCyA*4vp`EK%H(#?|gnrZ+c`1@hrQ(EWo`5D%v^2 z(;XPJSd0(Q6OXj2B<=|ya<5j!wG!<}7h9Edgm(>E*eox^fllzq7%Z zk=}MIkhj|r1LTgfz3_O;glRHO*<=gOT(l{Mq%69!Gs*_Ckk5Eam60ReS_<&ZF5dY-XgX2rZ&E_Ie`$lw5(#X_Ymp%_cv?NTzI0kR_SG7tq6xYmLo ziK`3bI_`UUcuemDY}Rx>JOB$;MtLCUF#!&h0NXIa6IOtR>iWD%aUD_oyZ~OMs5tpF zHZPO?&Ug|%yE+^W(a8KOHti~4+KOO<%Bi`>;gDt1&H&}2-1Z%b|8orHlIXiC)a6oi zQ33^}B?4r8L{RWY;kj5GM|#X1ur&bo25(85by_wkGwr}b3?{mraxj#7%e2~lnC~_` zII+v@3;^}T=*7@|-ZdSNy4U~1*L$=rsz%$QKZu4B1Zj$ij0%!^WJFYQ`t^74)!O?x z_cTs*R;VgJ#W&13<_Noj(T>7|&)hCulp^+!pMIbhn&v*n-C{o0JjVA%Cdm8ZAmrW6K zH0N%5_$qCNbXsX%e7$LAL<_=;0}?^1`@pOi8hbBUkf28}M1nWJ`)sniCSEgai}Q&a z=(M9gPPE26O{ML+&T|XYdo#~4a>~;YLV%|BD2m0oDU`ro+0EmpEXpEN(D^;}vI7)3+fGQWKV9NjPGw``R(6qREi@3u4U@bIhYX!pgj>jW!Zc;={Zrj&G zqI4KI4Y2%e5$yT+eO*wP(*}`eL{}o_#f1K2yzklK3cc%q1WAfW{%9@}C^46d>2Tjm zhkU^rIba|fTI>BFZ9jEW??AhybotFj^$BPHJFgwuA$GD1z5EX0dvHi@iq{cz+J#8L z4RcfyltFu;8AiGxN2#Z|29Cu;aHGN171{NisFBY&!?`*#n$^X(buUu_@c{A_Wom$g zZjIA)8rZBOgbkcPcj@@x1#>)PWkg=6J2;A^Y*VhbxJ0jlTzLPwX;Md;VQgp9zEnZ| zUS)XJ8e7$9N^FLrb~~u&Y&po%XJYuIer1r<@sLTuwhKa#nsq9b#6eksw^zGDwhc(- za&7G5fTkQhL+7>Jc-#|{IQ&l z^VLR(XB%#rUoTkWo|HJfsq)`99;Zf-a5 z9z`4)c)WOei0k8dL;>N9*oXxnD$eWx7+B`A6O zgk7o^_w8(KXc+v`@O>YW`|@X@d=uDPr9ylvAfEMnS=rIxd|yOxPt)7B>^lDr+pNdk z(vTCfn*ahF0yib`%MS!~i(%CScOZ3t3?+(;1a%Z}kYSbHO* z7B*jGD2Gnh3e4|WC5Ol`dKj#`Px59-7V)JKor-&t=2q`+{e=6F=+`J##K(vt@BUeG zGd2-apt5b?hF*073goJh}0>3 zY7R0O9=4{{ww7>51wYtgLfPyiI@=FS+2nkT)HPB@m}0ne9qwhATZU zaJqZ=+365p@lZqWV^y=q8~T=w<;yDVsEa?l@yp?NHuxD)C(VN=LuUu#yLrmW0BeUd zy?u_%nf1=7>4xO;EhDY>(;F_IBrMNU*OGWxw=EPqd@R@jU$nOg4|1$bF+e=%PBxec zhyK+`f2(!+^Mc!gLGtPbnZDEjYgjmxVspSQ6p^wYlY0N||9vOUmu2z9=Xk+74ux8(+Zu?v9X^R9Kg4*#ci74Wi z2`g{&hXW4^NkqPJkJUa@-qx6$)cEyk)M@n#Ts>_$K3XZDTMm2c)yc-7N)qjoBn*C$ zm-#PlW;RJ7K&&P`nGM#+>MPosu9hfL`NppO36<_haCUDg4~?;MN8AVe1^?E; zO-FPZ0v}UYR73C5i}-jfJq%74a*lhF9y8Q02stGX&)49?48c6-fA#+Z!K`e8J#=phJe_QN!;c6pM^RO2jT;r)5ZE*TU#0T(_gH>;a~62 z8@kRRX5g;;G1BqINyuKY^q}%0DDvG^jtU(jmUp$rcsy51GsyiB73(W)d9@CAhi++L z>i%dp%w%r1Ydk8+BAS zck0+`LvNpm&FI!p=?`tK5vZ|te>{-Ona30r`hx)>U4%x+fr=2aG?c*$(SZWZ1^eq! zaGQBHQ=kQdjb0ah3VMLBS?@0{Jb7HJ@h$ErUcbVyO2$_`eAu1uBfA4Js})HQJ?s-@ z{q`q?I53-u#2T_~)UdXbbJx|z9=!_<2Pzkz1zoQq9M%|?zDN7CJbGF!D2{;Ea@yEy zWC>ZaXbl{@G7<55k=FBbs#M?RJ@?p=!3m}}9{qttq#WepgGfaBF@E_HUqn^0`Z4ce zHb~Ky4C&LK#XjdD$s1BWKm;}H#u1^};_j%ycW-G0M&iz-eITgWB=?hqwe26&qhFFd z;jD2tvhhcqKY?7W=rDf23n9a4&H?Rr01coRs@7(eB9X9-u3+X4DP>ijg-q0dH=MJ= zlgPR~>tTf=q543jDa-KH*$e|c;ismX7{{!$olD^{Ar6=&fv*KzB{tmh<+ZH> z@;6-ofKZU2f%;)}RDPqz*0SmJXS-_QqS5rL43H`_>0@|CbY|LKv-*glAKy596u2m& z{_G16*cE;r5A=@DIj{S(@D%Z~0l50#PRC2r7I9m>Q4iiVp@_rMFgNxD0ikUSH%%Kq z^ZI))Epxoo&yd^MZC|KuWVQdZgw#$Sc%FP91l>pQ8^hX0EIg&MMAtr#Yor5W*0kP8 z-(`)|=B+89)fdI6r!!vs?StzODk$2{!}K!B3bE7?8t1g6j!780em=z1m7vWhLsP+G z`vrC%RX57=9Dh$0hX|WpsxYyxi~xgYwVmmHIi*}H@1^NODKL{^S&Akhdb~{}&Os5F z*Khqe(Rf)OiU@(+vR|LmU7Ol7<%QS0dak|lDl^t}xMPB@pPg@>+%7EYh7SJc$Mue8 zAB?iT&~lYLcBq%{TyLP9FHaQFoM6@l98MBdWSZ}K)+VQ#b^q4K8qruo45%B!42vLj zagXKh568R0>7Crf6QrtITl5?8MaoZDG_2U(`D7X`5!QPNxJre?b!(u+*awwZqsx~R zqblcAH~kgQGlXkiU!za&&H$+1cVkZk`Fn5QWQO^&UV~cd*gZMuy0nKo!|sSUU3bK-1a;;RGKqii{3}8N za~BB;I?pJlKP*x@aUb!`SFfU;CGiQehDJ8aGf8_G-^`*?OQLL1uu?%Oux|{F~cKT<_ zDzLG!*#W-CU$)E;(SAZGD3oEz^BeA@Ir>45B8>U`aAnI7;tjHe6b3;k4{vv9eP2xR zV_iFRNGaGI?Z4-%9ZIicZCL9kzx-OdwE$O(*RUtaU4O4Q9{P=;-uJ`%K|0g$)CNNS~)SBl{6n?dq4b4L($z@f4^e-8{uD1e-8m=>sa$Bjdro0%J>v^?)WS&hP!%prZ$6gfROG!JsMdh`pV5ubs zrFz*8*R$}r?U={;f7V7#m+#)M#Nr|wi!1LsYI1&J0+dXGK~?-7d1uhyY#O@N4{rF9 z^J_0D{EuiBo-X)jRqTm>pYIh;xW=VOYm-eb@j*|#9?l2GrtSqsQbQ4xAJ_ni&C|F& zZ_2XV_@DV+*2APd*H5B!meVJdn)+iX``4A$XXjT)Qp=s^)qd2IFCJSar+hKC@N5aT z;_ZB~`?y3(9-_JjsVA4i#zxS3KHbH?s5dA2&mK zB39|Sg*_V9c6-iRVNB2I>2*TmeY_22&W)U}E}^z-{JVd5bNSNZy}H2j@k^Or+y1QO zPdHzluT=O!O7bB}^JCk*jt@HwM-v6Z1s`gBo)l5rSgk#ogbGjMV#seC(-g6KI8~vk z+q?0nt)D{`yg`bVL{Ek-A*Nz(%}6`85Ep$-Xu{f_^4AU49QV`Jy~F1A@4J&8pX-&* z1Ds7ATAW15JAFLw?!Q^owvW1dxU|_%0!%7hC@?jt+Dhv)V+5h%tfAiKLg#y#{;DD8 zQXQ-=+VZ>0cRe?abITG8_pwU{wc_-=J-r(S0_-vQO-YmCyskQ$Xt!6NN|V#nzIA%X z396OV%N8L^7xOk<9zY^CI!;OMX7cZggCBl`o$aZD$tGzZBf1$kXC#T-5H`&PQO>bL zNYzJ2+wUoUEDKiQ?u0gQ)c%)?suWn&`boPo50>sX}x;Mf6bH}&RyOKqE@USxMup2hg$v1||7@jxAH*RtZ_*#+P4-rCB~T~|%^ zLsCvhx}cAAOV**W&H!OWd!FWchC5^gEwX~ePU|m&B_-wf883SYU(QidI{DgcUlI9c zn)ffu`Cr>TtEg8VqmDE(eLVxDLeo%SOwc=LEc>9G>hf+ayXp`*E(?ogHn9NAabQki#_Ex=&BiO<+j)`ghWHlr+TJJt!Dzzm_?_Q*&&$AxbO1 z$LmaAajO`S*x$Dkz?&*4Zhm48_lhC?mM`95pv&A4p+uP=7t&_tCm_G zwD$h`w+3I=(WMRLPV6hyd+P0;I}M%WVhFD!BBF~w+r+6Uu|G7=1jXOODQ8sFZ&ho; zo2pQ7xfKqNYuTZ|ItO;(z@cDFXZNXd=hyBSjIlzU|LUj>?jmQqX=j+!5YpjAWq)V1 zq)N~u$LEB5eb~Y5nRE4{+qs(SUA)CnOZ_%8?-oz(^YD_2;ZD|kW&C58FV|l~@n%2` zzf1m=ME&c#z5CrQVyd>6eLoIMh;fDOJ0Ahr0sDz=na8icNhwRIi%2+8g;%#FpKr*$ z@+DI^%(~Z`W`+Xk7;YooKT1(R(tp#&FFeDDs9)5C)AYUJUFGq(3@Lh)W7{b||4x&- zIfUP?9c}&9Bz)d1_N+e=r9C#r^NM|k+oxoXw>G)d0v{H?u{pWts~Ts2-x=awW6yDk z>ycB#8@V4~OG8ws(EeL%om{m~_(_QUeaC}4A!G_CZX=kj-;|h^!kg!RY-+_d3BVs| z{RGw;{Dx+itlWUVxWf$b+SStk5IdAzOl6xj?fvlZFs3gdZ8pRZxXh~~S;Q`~KVW&? z5m8pd6AuRw)WAWBcXGvjX-YSgmv+5rcfJR(&Dbz?_8Q-m^CPk^fV*0shjo@`U`qOVA&-Q&g*dsYJK8ms@I13hTj=ryRN5_O9~yuriWe0ndV-MrTD2 z8#rl#UQiLhx?!Pa*R)AsJb1ZhXZ@<4UvdVUuC#$*e)M1$-*NxlA!>&PTZe;He;N4w zcoEr7|1~J4-7wt6NF?XjE<2yl#PVkT13%&-<`MP2MH9<6d(MEZOG~?$jmGNx&FuG2 z6LUfi-z(l)38S0(k~eU%V=-B9u?OvCmmfsXe$0!S``2hkxr8-D8WWf@+t|AQ z2tbq)n$Io2>4g5MbnZN5v;_jsrLIcy{FHB&XP)Va|IBpfg+cZ^AA#3m+yTrb=U3Yg zdjhbVYq!?Wi&SnY~PI5Mg1w>wBqY3>pbW2Dz&YNx~Tr2p&T zXSvrZh7$Ja>ziZM&ei*K@r>(u7Av97KfVOz)`3E9{SD43j9Q%J2lyT1R3tr zy9%-JU#AWm0AgP(!b=H!h5wsDs|^P%E1ez|F{y^g9ec6W*dMmakH8jgond;2{osHVVl{!8O%r& zXLD+*6X+9L(sD7Ei>UbwJMTn+$Dh|018yhP+&xhI-e23`V5_qJkIxm&!R9&oL4VI{ z@#uE+iLNL!8v%?Lw(*_mbdu`(?vY$c7M`Ct$2Rga4=?9s?Wyh=;@;l=%Rk4-XWQ7y z=aIinzI`inNL45E%+0}L7c^eN9J@#0#_Egj!u))4HJ4Jj(_vD@d96*Z-h49Lrz*$v ze)cZO5LY!kA^hw)<|Ph&z=(+|$OapVw}4e6_M_jF=s(N4+f7I?CgRuJ zJ6mG@1*24T`5zu47v~x=-0M7TkjuZ)vKnZL>?Kow;=D-kHl2p&KUjNQd?W#>)}NDC zJK|swwh~^lq#)}nG8{JSej=WuswRiASi&u90TrdUrWHO?X&F3xkHn2|Jv72y{5>rx zEP_VH_C+f#f5!A0N6^zA&5%BT-A~|UG{dc{4%+W~yaRvqibazr?$)R$-p_`PzO<>{ zU5~KPVkkD@Si-NLBx5NT#5sO)J2;BIOlkF?w<#!>|AAZ%7ye|n5LS>&HbM5`*>58@&h-@HNgc!<@tJqz-)cCPaI0DM z%STLZcFd1yGDhs>^Si-+p;Cp7V;}SR#BS&F+RKc; zw|PB2tAJ=7(G62N1xE0;_ll}>m|FN$4wDjNw+~7YIpbMYv=>tT!$c6awF?gldY-Ip ziZ`6kWa068-Y4R~p64Do!|{B6?(d6UvyUfoeVz`=(UBRpj1e9;8{4as29>D?MwNR5 zzo35ut2j?Yer_Mr{ouBLHN_c-PL^WyAMbb=xJ*jPOrofT!Q(mc?9(Mv8vF){7>=Fe zwYLmE>nla5mj%H%JNC)^qCw z_7rnhvvP7L%{VsY@AYUebMulOo_~}m%#jY~v%Acq+9fyM!dbI>r0lDBQOvueGe7#t zm}R+Vj5ls4|9w6(%qB3$y9@i*Fk)`|{A$Qs{e!XM6*1`y?XlGKb=pMt>E-|gdD|CN zF)+s(69(tWJh^e5pC#xFv(E`ITej?q;mJD7e|HocF7}T)@1~)hE+58v8N^i+VbPm% zy;8$FUc30F{eT1W^Fk~rz{e0__Sc=&rb_x+?kCM79j}UT{z!*yYy8gW&Au^3Zjznd zWuL`-evgs5n}xNvz6-UNdWwtR?^YXb6bZaX|5}+l!C7t39Qmz=Tq?y(CL@O(Yl1&} z28Ov@Lpcg}qpYC^lwTTrjQTfh$}fd(>_xeF9kw&EW+PfBWHMc?#M#Jlh^$Lqt;OB6{YkVT` zj<`x79qsz#H_hj-fx!!p{MaogI_sYuTP~pw_eLnjGh055b8~*nZK5zryquGq-|oHA zx&qMnzCH{JLgB3!b9&2PqqHqa{2e=zx8=S2PHc(s*ArwwF;(8m7G!Jd`#S;w2NdX@ znjm}H?~ysiaQHrw%)hx)x>sc7@p?uaP8qnyzL#RfKC=T~U;rH_&B?eOS3; zwBz$2UFdz9yVQK=IiA581~b&Xxh+FA*loRC6no3|et+Sey zGH_<_L#6s1f4J|UdRzAMYwr)AVi0@dXA!u7(&2k_l{UnP?JVpxHu{j4erdJWSFGar zJSea=-s()$Dw+6LJhNYr1l1li;lXs@-?<+Cup81w`6n;O;>42H+tLAbAD+>Ixf8%gf*kffJJGSg`aT_^MD<{9$27s)kXle z821#eHR>{d&mlODPZYBJlgonxqWUanT_52*aNifmNb8q3>SWtmh$w+3 z;I9Eo)!i_#7c#V0&gmY5?n)G}{$yN=cf2y$pPlCiq-U11FFy1QyBx1+V({=ts~2}v z&xg}H@DKOX;qtAc1lfy6q$Lc;&Aoec!sRVUUHS2ayYQAY{cg30lw7e|%sNHxsfn*@ zca!4i@qP>0+4ALfT*=f+(!cVYx6Cbs5=Budw+*7ocyn+$f)QU@^J46ej+A!|_MIop z`Xj>Gx93M(z4?dTQvoR9`^j_zgEA=R?Z=2C$Zbk0Yj-F9=6kpau1D6*`JULO> z-VH2xcjaq-%!r}5PW_>{Dyk;7;{et$<`nxUaf558@dh~jLW0RPZ|IqrZ~N^1xFT<5 zp8K>JzcVM?ZrvSJZkm06WBc_eY@ECWt#!;W65qgGG4{m|Qu^~i%JfH)81BC6V3^^@ z4hxY121rgG)`u<}dnr>8eE544Xg`Hl{)cb-!*7fXq$hMr$(<^+mHcQ+6 z8+*VdFBso$%Lf~ekHZlkMEKyWyna$k{C(W6a`GxC?! z;FG`3ZMtt$3?WXSP-hcPHNbHaT`Lz^zW?zCA{_KMgN7&O5zW34mAc%1{B{%hs5fH_ z^i)axX#{n9fLb1{_(zR7XQkaRCZ}0v;CwWeALJ5SPW#Jm7tZ3|exnwd(YVM|<&ygO zeJ=prx%dsP%sQiY>OgP%`8Ea4@=Zs~cRXqv>>gHiYCxC$2CNhPUiu}V>Euj@CFyiM z?)6Amj-d=qm9)R?ccAK)FBvIc1Z!bka5F)BPof=9?U)!ja>(G(`gnnhPQzWC#c`lK zC@mp=`y=;0qTV^usLD;x6&cVOjr!N>vabhoc9z!9d^qmj`A$04l#Mvo_knrfP6_i{ zYwYMf8&G|>5$+^uY14a}6fRZ;$mhUm@DTM^jB0;J8o@!~US#3x-^T{Hm}OIkQE4k_ zZt7>0=?C1$;HU7IO(aLi_GYq6Wu&kb-u=>fyNf~hb08wk0P#@!cXnfoyAgo>5k)!a z^&k!fsoIa0uURZ5bzsa}DQ`N2NcU=EeGb3FyH`s6$=>fU&t+Q#NN=S5vuM3faD0pY zalzd#xJZi)WrPk+8SGtg!5%JSzUAAk@61x{ihy>GXna6Ql`!ur?*1FdQODZ-^B72% zD?(Ff(rU~k0)p`P9D#P1GDd()rCrni?R5*gJy0F$DCxjq&JB##SKn^1PhM8J_~XZL zgf!Is?{|y!7CyJL0D@LsyLEhf`8(ShqGkIfQQU94h;pGKz()MsT}0G|c|H$;z&{M? z0J%ve9YKuIPEQ?o9`TSTfkjy4_Y9jz#D>)(E}l2iQrFpBbRfRrC^i3s)37-V%S)CI z!LMrcA9+TG(a>W~xz=WSJhCqjGh4gZa!jCX-}6ay;S*@lGvpSN@@><@dvfgDcX1ZlhAj$!dH)UGuSMv2fZH&fbe zG4szcW-h^LtkfoYmH}!M$=G&ZN|M`qG;_g?zrujt(r(2TaP{)Vq}n_IBMXoNkXC^WvA%iQ^2YWx&UnUh@ANCoh#y$p1KPo-CXtw9);KW$)CjsF1(`$7H zcT#y-XWZv>_Qa)0Y3M3!oi^$=+juA451`gtaawazd#4>(tbN#?cl@xO7MDNY&rG@N z3}++bER)~PWlFu$R_pgVY@(1chT-tTc-`KcvKnM%C7`PUj>z;h{j|s{GCJ4y94k>;>>H<)FUsqSB+Zf~9kOdLTQRRt zL?zP(UFLv@Ngv@(%3YIw8gnZ4>h(!@vY^IO?JQMeT7wod5XhK=D1V7P{rNt$jU3+= zvE4k#AVfylZ$q8sOZ_?DodG=+691@+hINW?^C_lYtVIq=;#_5TT@&@z_#Gz%!z7z? zz}eqzPdUJ`;5&=)QW?UCJ_#ATpa&8cvQ-a`bcSf>R6aY8(}jeC z+V7k(5DN83iJGF7wxxVy{=**-*;|3<)-os6iGLg^jk@ol_Hr@VlmRMWgHm&o;=r## zmCI!uB%ctr$ww?}Bs+A8fq3>auU9=#*RH2tcV(K<)4q0J^6nK-`Vl@E4R7$-i*FrI z%b``6Nc!fZ(>NT-97CeYd12nBoOv{w{`)@60SK7lVW%)VMu%>Bpkj+V4#%>xPm@^A z&Pgf-?+`mN&KjKIkb;i}XWSBrobKeOl}XP}6FEe3W=&JS7Soo;y_SI1&&VlodHaPy=aJ$lrL;H^+kx)&=||E-lKMXBZ}=hDd?{8bY{kecO<)I=>*nBBG`kXc zKVofMI`qa@Ppui)zOGnkVN`*Z1iIKEsye8T9{3j zu*91y=AC^4iC?0M_|#&RLo`r$^`GjmI9UUTn1rk$9>_Qmzc01tI))pu`p zCP!l~-v(>sK-fU*HK31+5V{0-mG)0PHjjG}{8vRkD60yqJw-YLpL@ubZ{3?}l5FBj zrVMHwxJ+sfxmKg`AmiJAe(XfCYS&l}JpInNTuAnpPtc5B!29=IfM2&v%R{?{SmgC+HE0?RM2ZIwC-M9|An+1Y8%gW0*?#(#Q8k;{cH9wDxf1^*gnogt>X> zPMhTNun-J%WAFTo7eEJ2qSzu{PY7|_;MzR)ge(1NVv|(^L*2c+@CUkvDrin2Qfvp( zgjVUQQpVxRxEl5g`MBHlFG16z#{7Rx&%wsAb4FD2lLg7DW|#WT9=&dC%MANNy_(uPEL*oX$O4QsI#B40fm|bA$;JQfXO#ss-1ix&X ziDsk#aShqy*Tnm;!M~bK;m2hmv@Xeg$M;=s!C6N>=U_Bq)VSTsQ=3tEKFOB8UMQgT z6VbfiTmCOX#C+pw^dQta-XJB$FOFDMS=-ns&F$y~053JJJq$NGm6t*KAwSlH6ryhR zWc#nj3d-G0lv>(pl8j-Ep8Fc|Se!#g_M51PrG0&h5yv`)J61w^LlwFkY+l4d%&mGbwgOkA5nsRi_5DPr)(>*~s<+l%%`%5eDz~B> zRSt(fD<9%)R83|?&V7Ff{L82_x@3Iax;kOq>V}e!Ad2=#v0bCR=?sDCb$7C5=TdG( zaLi850}=$s^mKWL0XD|)r$=^2Z4%MPMh$-kvRusVh&>FR+nl3LvE|E+_(A&K#*hj>5hMFf&zh@vOVnhO(Q@gVA##t~#d*>Y?GiK} zpF(ck#TY`*<7`N2s_kiX4~IatzvoIpz>mupyo;Mlm!sFm=Bl7OUXhvY1(5L^?a%Y- za0q#Gz@hQORevK%6sDem`NyS7$z%9nMui|R+X|A`kra?LbUV*)lARteoc!Bm5$s#F zyPhpBI)S;2APr-+=WtdX`-j-&loaQR62mCu*QKSmBcqP-LHwam+V=hC)g~nQZa-V@ z^=tP(klwy_cqPrvkH0=WQ{M%MN6x`7pg-?3zL~JmKr-s8W^Ory{3gVHM{ZC1r=u8w z_@1pi!CTEx?1m^VsO?mtW58`|wlgC`umexzU} z68F1q5YH5s$?g$vPj072$0tQ-ZN;RYE1M|jSneaeIm5#tKW)HE@MEVxy1hP7Ca^w4 zL0-Ylpi^*`I!})X3Tg1;ve1}R|LG-Pcz4@1(uQ3nah(QD-<%_*ZH_TC;_o=)d(T_X zpuG-(VQ6jHAUd~h*1E4HPQL(j2&Bu!%8@dsd$}q4WNGV5Pr?NwS^PXNX6A;dco!oA;WzBtKYb{`+4XJb_YzNxCvT-%z znCtH=5p}lKVdo8`Wr{;VCxjP}2)UdnBakEpSk1I!+7KVOO{|_nT;f!8RtA%A!Gl1MtCvP6b1QzW>!`tiUIseVZ;8OBnBO z75~A4>3$5uDs?FChxSzTyj5~`?rj(M`e-R**dcet*WeK5?SbDk%nQ~F2$p0O{=!Ue z*(~Mekr?kU*g?Ikf0d>^3j9v2k&j&j*Uc_knAC|ejn*TogFvB%&5ODgYRH~!gj7qu zd?Y`p?;y;`QKFV_w%h0b^l2xJf%u>ls_#8MeZEQc*QX_XSjQ&0n?t|16R;Qkjdk0y z%vUqE2-P&xWSK)W9CcXUgw2N6Zh7E=*W#|cmge-^O3Aiqi3~9spi|k-hih0W;u3W% zxp?Gp?@(7nwiy;G-h-BpD!P_WsM&F@}ATKvxXY!?|D$J zaD>`^Lf_-<{t&@<0S-O|DJY?FBx3OvQmTZRye1FboXzGN%jrn~GxY*Q2*EY8iNZvT29!uFi}b4E}|Boe^2Ujv{HVQ6hQLS`FEiy@{4vx@5a^S?HhR)3?8aKtJ+w(uK*d`Z);9oXVF=4aZOAF<0(3m zvkx%uaen&|nl8OD*-EgUxv*vzMtZDj5&oD%LMFxGkA3AdDMU8-EZ+rG)qx)p3_1s0p%lJ{|C2}O54%ur zB62_PL#D|`kcrLg3$p*z%>H|4gVKpv7+!rltbM1$ASWF^zkPu(&HoR+q*mhDX3uZ# z)`|#JLfA_i++Wy($czCH9v0D3sb>ORzq*pB$-W z(tJ>}=XHO|Eb$+XDmtC&Eff$Iklk3jK9GQ?(h(e56M7>kklGzkj(z{K^V(C>U<*x4 z_YJI4PTl>}6Tj7Hv%6mO_1*h%s-9z!Od|}nkwiGH@`jdu#>`85E?VcgaKlg}a<;(UL9AZ*raqVbpu>i_f)d-_~rZ_slPRc+TMu{(;po9XN_gFX^B2cPT# zeeyQtKfiIub*ZtZ+J^zl70=?s)ZySnNMPp_TwO@BTo^3d9*ENYAW!W{Lo6S-E@y?q-K zW_}(nGrRts(}*_W5S@R098ejs*8$k7I|je(jEyGh zumX8MUu~<+u2q{LM-?xHdFsn}5CM$eDCpckgN%1!G(D0G1 z@&gHY(ADvTv+j8v&lfXsD~O`lb9h$10?t9N6%|z#(lPp`(3oA-?JXfUr}2jik??5y#=z+Y#kO>>ovosI$R2YT68RrA--W_M(f7f0nSD#ie3H?5reVSI+!3vn`eT42YThD3FF!$}-;a`(^<#s=vweUm5jq|A7IYg1a$5}m@&s>@Gga$=nBZbh8(?!rj2(527egq zQJn6Za*86AMi0WK=3k`VSEhO(*W=uA}AELw7- zKCTEX#?qn;0(G9crMvHzkz1qm#fYk%$2iaLOb;C(dfhioCr69zG*U4s9>&jjea(?J zg|$T=7;YIfwSRlsJ@AQGrtvHWJd0JIeb9le_^Ql|7j2k+#5ak2ZXxO}cPNS!zm#_E zy?s-Ws$0tZ@@%ZzP~CR0ntAg(>^dAtnC;FVVafxMH}*^cAAnB;gT?L$)sL?lqk_u=a*B9;gb?wvw@LIw+eD4-_h$tzd*ME1-Il#XP~?lTCBn2Cb{IeL&Qvb_a?3&&vdD+KLCk+V0`M$n3QdmKiYmYas7KHtsqmSKMANk@1Tg&u!kdTY3DBM>=E8)@+!#oWEbO^aK*vHgMjHR0wL z!r%FHxP3-^)>!}4aPKUDBEFcM%F6r*<(t_=NL+yX|nRdJ` zh&0Y7ieA4uNhG;E2r3ey!Sk&qZsdaiC#ct(8`Gn| zYQ19rO;nM-5K^ahVtNf#N9$j&eBvGf*Bdvb=Rvv#35OuM4kl$vx{vn=7arX=m0)K4 z52reWJO_?a3l7m!*7s8w@O=`_!5oBqX8rH?adJUG$qw-gF10KnqF{qR5Z$;N7yict z{DQI{{WKJsKu^=;)AN`2!XUF?<)>v7XrLn%&TN~3nyPq#tMnij=)hQ54K~I9$KJaD zxss)2V%^iP88OUk&oFleW`%Pt$nIKpNZufP9f zp3IY~EJ;O|Ncv}(nMnq2GuqQ-C|)GSF=95hU9~L5RZ@= zsDa#L88j;yj=$POxV3VzSuO5EPh~)dl1Wvfk;SvkR;AF$Lo^E@;5fUz8;kEBsK{`W z)Gp$h5?nZn%)(x^7zxR7^O6_NB|qoHu8rWn8TnH&s6hAk$7rjU0XQR zD;pChM*%Aa(A4*Y!AGbl8GD?mplmFXRaX&yRzFwO*lska)Y9O;0`NCBc8=7>>c%m2 zH_fd`R;@J;Rx3vf6Pqh56wB5~O4Z6S3V3U^nf-;c*hE=Ngn*G&qjeEKpWO*mjMnDF z%HGA=#ZGlQtR-4Cgi$T-83xwzBpff*;=9O=nIjuSv$T>qS<`2c##Sw(tnSJ(ro?i` zmEkq9pW9wLSXpmxw4sR#BCIhuvAowpx}%)Fy%M`v&{GGc>e*H#3K}z$*bkp?mL>vF z$;XkaGZQ<2cN%gug>tZdhGLOWCAfc7sTLEvhh{uWC93U)!;84i;VUqMz@|7cR00?3=3xNH>9uV=ZH1E3FP3K8F>7x`_k-CylGsTrYtnXMcNHY- z5b+kslBg|(@|jR=V`DV|Z?*Q~;zVm^*Rmmi7#ty6txQ>ZS8!>C7T^hbcCa>+lw(E! zvGhx^TeyH9QAn54n~jOsMh+>lE*7g>`BEg_Dz9v-(UYLIc33E{&snkcp@W&# z4G8ELwMGaub8Q{5`QdVSt0~22TMNa_#CbRk6YhMbQCQnC3c0l-Et%Q8$Spx0-Ccq` zIf;BVTdPRCd9>Wn=I4_}`S>^*10NqlJ$d8~IM|p|kK)j;nLak*o#t`^>Bn(jgI~}J z%$K-PS3|WuL~g}q7dB^S;l(7)Dzm%f(gyE3=o1XJ4L|h)G#p#8h1sLTVc;Sz8PQTz zjczU?dHj*0#tt%BBe^=ak`C=bmP~9c?WHTh`ZBVO#ujFl4|9eQ%g;gKun~x?T|@!j z*~tv@gl#P%amsdcyJ={fb74f>Ml!kMSiTBuU1W|5G0Hv~pA5C4aW8u?D{Qm&q@{jIISHhe)ENMlqx zMrx-0SSB;GFpu+qZ0uXx`q}>OZs0t)uAjjrF#|nQB3Un9EG#a9T?nnOw0A*-XBUsQ zVUpXIb7iED*qWD**Q?2+jj)0A5}Bo)bX}+S*RA)lVCjRC#pOK&8x=C?^ilwUZ2Ex) z{Ory{XIDzDwU!~GhNBm7Sdx)n1Sv7#+5rFac49ug8kk*$C+KRRp-hlJEL@`DPF+6P z-dREpvW2sy$|^YRi~36G35`V(wCrpp5Noc_ zZ0N^idl2o*=zMl@Jp+O^126FA!UD9g`uceW5hO>*@e-YB)>d=pTN8ObbskxbW|j@( zq`I>KBVYnne8eBj?COX0`6CG_JQmD81slYSuD9wLcYD%rGz1@lSacZv_JxgpLVOMCYk)1g|D4t;o z3$ft^9tFy%O1n_b^)k*v3% z9;B1l2y^GvLSr$x5Gl(M<8T#8x^&1^$@cb1e6@shlV_J5WQsDiS~#YEFlou#(!j zh@NQ%^c+=4-_U7bRtQR4S*zlfM0(e`z+wyOoOOy_y+|cz4CJg*BT^nNvN~9X-Do=9 zTHoI)&owV3ikpFtSFpUDoT%(XW3|#mVX2Az1aG(u(l5+~k}7r#42Y{BOslz2Ov)J2 z1q=%D7E-LprLwZR7%V}NXRXiX_C^%;1X%RuYX;>iTS?@O;;F4#V-1;Z12EfD9DEL0 z{}4EtSU71eB7@x7(Q09}77m@)o9&IiRj~M z=B!eh*W$&MLhzUqEiYSRI}c5!hBIcJsOIV*E%|s(CCpV&o6%3z@A-^>9gA z3tTjc+pXHl;_7y^zQ0;g=d^`(o?y@y8xhF;Wq4Mr7v%<$z^3=-c4lM6cnkKQSuI?y z8OKLU6O`X@W`4gOJwDkDEwimXXs} zo66xivbCVsW|d^3IeU08kKCfEq#jVp?P{g88Edz5b4zVwAye4cG*XCz zg-oCvwT{w7_zA9Vw)y3`L`eFpN1kSXRi@6}w5QNW@`9M9~oUg1b zp3lv$DZ7ZBjqGIN`;pwq3jD}0!2BXWEhiiK<>mN6JX)MsX{=4`vmBi8q1!|5%1i^H zLbG$(dNDa4kz9dE!Jg@7l#qziPP9i%pAa|oL|s^s&<&4Y5J5Xr>WX9#UZ#`cs*2qD3jA(yey0&-dWa-!c0!unWtQ(^C!r( zzp=P{4paU%xQJpO=>nyHI)f-WxT&>Qg@<;?-I*IN?DYr;Fy;Y6Q6-uR< zi$>v~DZ^PlznYOUh5f@!1Lntcs{tCGGg@i6P5nV_+H4^%XclJQgEIr-~f*aC#uo`oLBPM$vR@+cwMQ2nMB|l27lSZVv1Lv#_NzN`c@+HzkADMZO zv|3q5R;JCpjZiZXj#_aA8}o~V%iV+qp{$AItqFv(qRa~Nx9=aVZ|(;h%Ho99I$uex z=_~sy%SX|}ye3&OjPkjh-Bn?;p+(cv=s=Fm!&xGf+B-a2&Ps@gt{{tXMODa8;xOMx zrwzG&DCZ)Qv3GtX&4+b4F$Z7MiL)avo0vX>M|nhoTr6ftUsH!qucV(JZe+Ff_6bUm zAbI~L90j7vLM$5Ij%vw9T~^Kl7Zb=Fww&LXErR5%QZ5+EZQG2TRaRnKiw2Ub>>>a8 z(sG^ZSxi8WgB0kEJmUK<8XL*tDqPt&k2X)BK(FFM*odD^q)J(^q?;RX_fTePmGH#b zGV9aIms{M(W@0<(4gCU|3pqe(m$5piNdgW!(1<58$6+`|D$-)eP!cgM)oQmww9l9J z@<@Vwvac`CL>6jCbMO=5I!G(dEP0ka&u*u-gD2Uom5a0*+Hc|9v`{Z-ZE1pP{J;kW zY)2%XNrW2F`HB2`K7@dN*q{={3@&k&7oF-H1=FZEa*klf?QB491mdU)fbhhC77We> z4)Xck=2@-0gI94Lm&%Qkc400`Sd0ti1uumX| zSuod{dPGt?I zfYNpa864J%2+Uh*7F2l5AGQw`x8wtM4iT)^tZZax?Bi-Rx<4m}^P8x9kf;>TnxwN{ zZEYZsBAu%vIC>*`evnt_y@eRPr{*K2fD$;~(;~;(+F}jmV%9_3Y=2}+iwl|ag+e|) zlT-F!qKa?NmJqavcjveFYQ^N?LNgz41-43Si=d#28rXqP3u5WW-dEPviu(t1Anyx_ z2x6v|S_h4dbEJvM?KpC_1bZKgGYlRFs3zN5LPHGP!SdGJ`FZ>dRe+F}bx*4xRWD?M z$|{oGz-N88nQJa1vkY|3D@IdV+E^$c^$~(fL()R9j;v(CV+nC3+msJSmA53#D6E|r z$h*2NEfg|M)yze_oJBU3MmiALp2!@}FSnOwq5qLewF{*x$#aGgLOfzAm^G05KRp+x z%Qdl0@(U7hO+}{W<7J#J}FikwQM5=pQ&oKxF82me0)$y1^L|4@PQAWRp%zE zl1t=Rx_l`$(yT)iHgr5pAXdB<&2V^v)!!pJC=TH@9 zVR5ykAXU;_c)l=`l{Q-W#zhP@7c&U_L;1Blxd8_DkB?D*EWNS6gqk!|Z*P4Q)gEFf z{Ugm4wa^5)+-~fj)eeu!CzbsJQCFrCtLTYefA-RGm^gwP7 z3H4J_J+)meEAf0))rxCp)fQqo;iWYjfp!s2tZ4sHX$V5d72?HJDw+BEnOY3I~Kx z3+pVGQ4rIS1WUiWrLXSix0bNakX;>neAod(vhyo35Sh!ZW(oTVqg zf*qjd!bVbQ7*V~kl0n*QBcF-}P{|{kpDV@NtbP#H)~n6u^$7lIO1&5fo^2U(t4N86 zx-G{@+b&a}d3srGA|SJN)+lVx7gjRc)r~T+oLQdOnjwUUM?&TO-CFWOjvzM=@r%ZI&g0_(lCIQuooxJ3+md! z{@lshTzj`2X`=q6v5WeZZH0VpFB+Sz=23h7Vl}t8JF^8&WEXzTu}C8>qXyk}Fjo&r zsnqK7at?To$?(HWOKlYCYb_ii>K6XKNT5yi8yO#IEEEv5fsKy(MVgH2Tc~qclMv!m zhNE8eB9MhQ?rNYw1!5L8A~et+rYBCvTI9ohq1`q za&j%1Lp>H`kx*)fheu1r{j_?Ko|(aSEqH-M=f{h2b$x*%v=DYvjU3iNX<)kv#d1ap ziH(h!_!iWt##sY(UuFtA3_QDgt4KfHLgHkYG?5r$0{KDU#TrV>dL*1K?C&N?WLb^C z$2wmREM|9haeqym)17h=JBuU64tc0I%KLf@N`v|NR$QgJC1rKyU>42_4JB2hdXmVz z4L^s%Y9=1_4@I}f7_(^_Ne1bHL$ zKx9K(01&8+GoeFyevZ0}<=T3%wpQL}^(T#tkw>}$)C)sFhNXcZj1`Q{D8;$anu*PTJz})DUX5K;;sLdVTuAx>w#MQ%3QNUeSa7`psTJF} zd=gOB4w3SI@mSu>#iC%=)pHQ3&_30Mg_S3kYtJ5nng${lvGdY}jz+VqB_pgY&mzgj zkrCM}?x7xNu?eHe#P-JKN@*6SM_XNNB-3TAqJFR*n?ZioXbp9MHjZ#^w(|ze{9Dz0 z9mRAEB%IneRs#7QFvL()#(_yIw z5Z5rFQO?*SSmKXP@~f&8+h0NKKrEWTdS+DAD$HkgVD3865gCqJKKp0zJ6=o0BF%g* z-fFSjCl`At;?*i6UHWDWCwu-PFq23jHl?`Q$S+M~x0jc2_OghohNuJkclrWF1`$}_ zZX?eFN*B*W_TmdOMP$j@rV>!u^EGK@9(N+rVaVt3IF?a0H;A_h8Me;}F%5Tmf~M zh@MuOfeXa?&26T1$d0IAjFgb!iHYO1WrwYwm9gW%XH%YAQX*a%FZ)Ymz|c#xNO6I%;mmM>^sN2rNXf}Ots^Zm)z+7hbr%$M;R)h?hf+pKtEnE&(g|DIBD%2y2lh%or&$AFRzs1JBy2p(K^My zAlK+tB1}thwjgD4xbQ&-TC_4E)+ikOoyEU2hcv>DmEAl@D_ zYm3z{0SixyO?*1?X|VjyBKo&9Xr$)ObKkhuARde!V>hE{Z4*h*s2!Ea}KIimT+{N5!W-p|EA6Ppm%Km)4 znl%))>K`A^!pc5A?k^|}S@+j zi%Jy@vT%*X+igWgdTYOL^BbxD(RsLiTs z-Pohw{bmC{YcT1T{FYaIV5#>;7v zp=8I*J_#LVRoDGF8HtbanxsFbJv>@`x%2fdfFFPFV{7@lf52|}d-m>27RTWuSWNT1 zLOV;&vp&(K`NiqU`teTb*Sb1z@BFSkUp&Eq`O*u2T;0ZF zE~T&DVaJ|r{mu()C-eDO-|Pv20Ng44-gV|u`U-mQF`bWGJ~P5ZyngkVg0LJPu+JNx zgYd+jM@M*w{{HwnGwQiIFIi_?n1lVu3-Fga&-$FU487fZ&AmP^nn#*Xj(@dh#=3a! zJ|}MGcI~;_`mNBnK4~iD%)j&G$MRSNH-bN4(@c(I;fWi~cZP}P7Z`;WaA7^@3-J5d zi3L&T@H!9N;EoLwTFu%0RXjWOYFJoRnuFO5FTs9@sS75sU-{b*AB z`p{6yIT=qMjrkw=AHo`%eLM8%?dl`nL%m)(eOq}DeDsC4t5cyzqwP~=%5HwDjC~EoN~iH~D18M`fxuqEr6tM7=;i&eF$Nwvq{k57n+leNdm;%mjv5;y&2;0MV2=}DVe zaggUQ)ScfUR!ax}S_ZRBY#ifQC)r1E&cs5~Q}E5x{ zii++q_GpxmiT&1&7+ zpYI|wfbDmO3jqPdIsx#nNp$M3tk zmg?$*NC(bhr+;DJK5%>)E$QH@4Qmey3F4|Y9uw+MI0aC=&VK64mM}d&u7!2TbTR}% z8-T1@fx-Z?>&PBXn@JEzpvo&*g=A1Q@5_;dU4gNcL|%{w2&S6aP*BYj@*-|My{^e5 zL=@E~Xhyk=&JB8`BUxve8fmhRNC?OP4tEA(J0wzt$&eX5!eOsKH&CAT&&xXchOnq) zAh|P8{h$@0=^$gx6vLMV^+5+!xd325YDN)aDAjdPC*F(SY65>*1p&z#9QHuPG+iE> z_9uL{aL-1>Taw|I%1x2G$Di$saxlk~Ox6a6<4~hV!Q<5~MJfQKFDlqBK%M#6A zhi-roPf`y^CU&hU0aYWx>EMV%!=5J^ChULnJ2t~lbZt$6BYMeNOuo16@6JB6AEBq8 z>FTNHCTDEV-*I+02ZQbKk9uq#0d~)yJ*MJ5sLx^d@tLsC_AJ;9`FF1aJwKvXP2d~6 zcDXPE@83P9;6>9ps*0nQq5?P65Dt(4-cY)`_G|=tzC4`6EKF%wJ>F(kpT8w-5vFtN zu5L4r`!}a?!W3@PiwE@X!~P*RE#>FF`>~q@{K+s$z_XLiTucA>qhO&uXsrjw=A3Tf zJWO5dCU6GsT=PW_7~Od7LqtFD`VEv)R}oR4bD0S<5})=57ndMk`{(Ghd%-_7OmLr_ zc6u-Uz)PMB-k;MFkm1E?b$)aWSGy%ty7%~_Q)PsB8R8Qh_J;{!T!lWOOc})yi)%8i z1&~qgx4M+^T3wXkOw)zQF)>Dt#vvSH6y-wS2u94 z=!33ddh#Ir7XSMW8^Xb4Y{+N&pi`J;-==+0@I0*zpRW1EJ++--PVIx@CJ^S~e%=@8 z=dgV^%b76Ku%&-zNd$G<=bFfe0ri;-Ef~a9PKlY6N>*2s@Dt_lmMca3 z=-9x$2#4t!FJU+SWY;-xQ~qv_j5!~?-06PoM(=;x)#X4`{;NM_Bb0;0sQhz;54-;k z`|1I9|3f4U;H;SY5Cwe?&5eu$BI=I)9y=dLWZG62U;jmWMr=d=%I!Dg*M7sspEEsY zL#Ez<4k%Gou>mzdG`CRH8c@ARMYu^|n<`M+RAf?A6ePGk;Qz^q0&H!z4rL4+B50>V z*#Wf%eFbxZlnclsNp#O=>RxD9OBr1)Lz!e*{ztbGOJle2Dd_5sc@e;yph-#_K%Iq> znvFeD4vkEacLsAbfP$(Ud;kWOF}(xUONUkqZU}S~kvqmzBQfuXY2N{!0cJNf_vh7e zS#3Hz)Zr7sqp-=J&;U3#U+FrUUJ4A4Hs5K}t*#|`r&d@%&btqb2Oiy2^L^zIXS?X5 z`>g*_*Afgw9sl%S*{7Q?52KEY!`Su?fSuv==YgQ!8%>aPeoa8F-PP^o4#tt2s z1V7|{UD)8=zhIku4AU|F5N(C+B}1J@o7V;d$wpmgz!y9q>c4S6@`eXK-5d9deBv|co4D4ab01pE6z*NJoAo<0XF z{1z1-xfg4>tE+)-({RUL9u5k-OFN0DmG76-xj`j0WuF+_fLXizwbI0tz$`8Sy6&vm8mI@FJ??xg&v^ zlm@%<$#iaGr}Wq9_}wXWu5${DRyz{)iY|a+Ftr92w-hs2~71u zPYUQc+!RouIOl^Lt1EDVV1m2~f!!!8GUzbSMd(CGHz>4B?p)pCFz9&|-U~={Pr|%Z zrXE;|AP1vAt^xiIepP=D4NgLhrjoYDIn8a;+y7n9dincVAl@}&6qz-R0r*H1F5AE~Z>DST&ivAQZ z-sh~pM%&+uzTrr7)vy&7gRMAVYkN+mUpHyguXXL}p1csFQEzy`?G_t;+qZi9_Ct7Q z8IoJxl^%^fV1nzzx8eR?P^xcBnkKa$y`9ZIvi)wu5N-vTSc30u_|a!!Ss)RbSlvh8 z=KlTL(B-+`9Pi;n>w|x^yVaC1g4x(VHu+hzTSl0gDC+fS`XM5_EU-*b+L5IH(#^}> z4vcI3D)z!HO&s(8waq1aUSMyml7+)%zK|Y05SO$4h=f65{cU0Jk>LCG0_#VhC)NX; z#IJSjXt$sc6}ujMXf9OT^mR9)|F{dpo`;T`wDLhqgn zmw|SK-Q$*ipEw3&dL%2AAt_9y4jGcz0MlH+88yyY_)tZL1+h9Wo6fn=D=;U0_sdq; zG2Ehy_rdf2!q>i@tM&f&go$bF>(_atCMXjN{QMUFpmTCSjH?Fj6Iu!4G4K1U^(=wr z&ww3fdW))zT3@mb?_f=l$qEHeWC|~UvZ5mC*m7+9bvNgy{0WZWtoRcg1RLeE*tET9 zIbr|vz<%c0k8te2%3g6aPN{zg^WP@ydpNZSC4prR<}k!*s(u^awIU39SreHij%j6d zxlG~K8A3fAsbNQhhqJC$Ah1YiZaX_$zgVl_lkG+GC#;sX(Gg+U*&_GSw!Fu4w%!Y> zDFj0MpbaCRbVwF#KPaT(BB@3)R8sxY!uv4f4I7cVA)6=097&o#gF3>C9VkOaf*j}^X~)VyL=DO~ z#5x1m91D!rNUDO629I;3sfCL?MWJK5kbi-8idt7~k9j8R*=WHJMQHoULYY;Vk#!W& z?dYn8y^hG3GHK^9ZgtF|uBCTwNd-duPL7K0KRW=;_Gt4hx7~xnjBnr9wdWxSY$Jml z1_9c^+Iv9cX0Kkdju)q-_II1^F-~)*Yk3A@fN~D0;!DREpl`hLC=2uJ(a2*`Ua~zO zQ%F7Wa_6HS#6lR=^JkCoTu3baF2&wkn%#uc8^c_An3($@y9F(x<_y$vKko-`=h-x0 zZhUet^tTTa+)t4r`YNL94BYA6uK#qB_H>d?uMGP?Jk05QiB0FdbxGK(*Lg2O=dpAS zC(D^qp4Nsq9MY)@WP>;yvf6@d*jZyb>j{TFAifX_Qr8itN`YrmhD=_LVB#UY#y2HYB(S9}i_NnPW&=r=jD z@sCsfdcyJ09H6BQGCMQ>4dCs?i4G8_tc|*u)JseFie(zD+kWrXnr;!xcUV;nwlZYp z=N3g9M*9g+`x{-Tb&=)Hvvt0{_+-D&=J=Ja7YDk}zI)rA6(5-0XP@AF>!nH9gCZEz z;%zUr@t8*cGa`U;)ecGe>ev)pqhEMC6n^v&2IQhvd3)i}SRfR}^LQjQP1SYdvooW! zu`&O{BJ8|b`R(9zC|iL(&uYIVA3X|WzYum*YQyfCdmTh1jwF>Hp9JGWW6mq_1*XqqB@?*kCLii_V}< zd}K5}R(B3`&o(xg44vdv+vT7UNR*#dm_ z_6zXUk9<@V_%G4Y{}q-$y5Zgo2SZWoo+HO|+p34?>*MM5=~egx7bg8H(}{Xcne=Z> zAG7bv(<{>($o(ZZCjI-yCg-cjuGULFdi+%Kzq^PdUHsTE(Q=1Tl}jgBnBP?`Jf_q8;0S6@kwDm!>xfT1 zdhbtah5hP~S~mw7@XarorUfvD>8;aMKja*^Hz$d)q>ocvpr$Vl`+e>A>}jzz`(>=z zEv4%}{Z{+3bS5XT0%KXH#ZuK{_BGab8#H zQ#>iZbpr`>zo#Vsn_XMkMbA3VVJe*2VxQeO{YPCd4@A=5_eC3vd~in6KFcNb-Y65! z#h`CsC-adw`_eT{EQ38w`s|+OKN;pUKjk$|zTD2ho!;#{rsQ?>yQhsd_iwSIY_!~} z7Z2F`6Bc3DIA_mISRS|ti>an_sEhU8A~EJSlMK1Z%q@GdQDo`?K7VVX^O66;J}%D0 z1)?)=5gpfjANXU_;kkHl#1BQ1Noid3f8d{+4#q+e_PZnJ^`sP^z+6Oig8K-4%yWEx zsIK_cjjUI?1{jE%+(mjBD~&V3^C8ta)y#-%nUkD+ok^Tw;1JFik%snmYMKTUq5S1H6^oi8++R z)NUn?*N~9XPl^Y@cn`b2i`9Ye31ZM4cXbkr5=fM1X>E0NiUN@#X8Fd)%L+s;C@VCz zX1dLckDG=rBx0A03wj5B6KD(N290Wl7Be@O7KJ90-JdNWNkeNxo1(BLL+ljmy4AIR zyePa!o6xl}F3jKtFMB}hq76OGw5MHj9O%%GIES9kpB?&-T;4ar)VzN6fW0@C9TvLy zqWiRSNH{qWk_ogT)w-Z8g zmEm=0)YIb>H-uwij*fMh)70 z&z?$8Vx$~>HZ-u=L# zeyMFU7c)o}ctOeEK)xI}(~<&(Xj}+H5!%HX>V>n&JTsn-)5jXO*Wkvw0 ztYi7%Bice9cAYi>_bo-{<70{lrwl!Cn66Mhc5t!GbVo$iQvM)aGvd98BL-+N`Jd7L zfHnxjXr`Tj1~hZXBN)>JebO&W@NZ=`UlauNSe>%u?+6)}HG~w9wSkh>(?DiOfju;S zgWzYGb zIVg;_j$t2JawTy=jJ$BJ~t+#8?k}s4gFX{*+YMvY)cH{2-K6 zcx@0$+WG6kL0>?T3bm5yCZk?D35%r46!%HxAvGCkgIK5%DhM@YaF~o2tVs%E^(-?v z(M5-%S_L?X*l`-@FmNJO@q+6L0_52g1ZcgBYPcD?JKl;HPK>Vl***`9Fzt5@F%V(e za0n9zkxBZ;CRG|fer=dLPizPebobxx0wPwfvE7B&2HEbZ_qiAc5`x+ls&I;^088$= ztZHL>o$gg?K@x?ot67Bw5HMB%_pN_Ns+SeWTiG&#W1-QnX-YM#AOe?B30%i?P}tRs zg0PTq*yT+xnkQq*vZdPWqnZ{m9wf$DwgR4!i}4%Oi}kwQ4YPwV->fNf z0I_4;Ic1-8PX8rb2q&y(Gc0$#YwNpD*Ee|SFZtQ>{?Xp0>|}j=SN8**tS#qcaq!s5 z`ijL^{UusW8(W>fgp>2wUj3*_UCTtMbHE}u}Hs-bOqqhQ9aL8 z%;fL^0mIx_NS7qp{b)y`QWR5U6Pdv~sJU#?0=8R;X!wwDfdbuGNohLz(D39SN-#B! zb=IjvQ^??C#e9OYeQGva*HHb+j2{-1F%)2|K-11bof+AIMxIJI!v44K1i+*@1c0JlWxD~2}`P{OjYtO(j`*oIvv)~Se8B&KHbLxH0DCTe5 zA?eOJb6)El8|oC|4Up|ZDo>GhXNn2j$bVsp*i%e|g%y8_WidcQGl9gETAeb(7N&4> zUTQ6*#yEjsG;o#*HpswPDkL$)ky2;~NgM`Cq4CjetstSWCJ_??l2E|!SWi5S$ zj>w(TZ{trtDTDG$>}}Wvs^4O-IBM27n$zZgQ0yn08i99GJ&vTkno7J+40;EZLXkeGpB1vjX&52Q8helo%PJQ4$(B1K4sZT?0a_<({ z5y3OiAuwaR%zVYVq1p!nzED{!m$1o=&|zZnT2&SFO|spJK{1ShDQUVu`V* zsHrk$-rhuyaa8}`Zql9R_TtV5#Vy9~arZ-q-ngHmDWT_#-4H&*1^(ZqD&%h+D6fRV2yHOxN1%syUL|urI2TYlovKTj{7S)2#b=XS-M6#1y}qeQ>(Cwg>;SyL+-;FB|$@-}2hZ;oj2e+M@6@u&hu=%V2-dVli=$uzp_zU&)>Z z?)rQRya#|lRiCaQd%(2ZLKZB2w0p3z`#wMZL#xVJPSGy^epN>{U_uWtf1wY3)cNhI zw=JMO-sQjeD2fP6fdu!bG=b5)QaDv|)*G4(Mh~}%HMx?iRGm>L!5Ol)W*>xVvkQFc z-Gw#yB;AJ8((Hg1@DyFTL8z6DY5IkJxC|yjk?u~{s)f4%233zFeF`zUkR#o|!jY z5x}QIJDEkwL?&&U5#N?R)Cs7dJkanxW_~*_x$)cN&6KvMs*ToY=nf5^o;&CdahC$N8FngbD)aU_7~MA zH3EGn6R&|+s|b`=NRGfon?(^g-1n5ok(EtxdM3dGvIWnQ%d{01Y*vLj=ymz8w#d-A zc=vE5i0x?iKSo?ANfN*#i z3;ZQ#jo&l7$C>tf5ju|*?Jpw;=;w5$p1F~X0K&r<^;(;fQCplgSSc{nwX%=#R7Sfj zPeWrcdQX?(9IaKsHQ~o;ExRLWQbm9BULKC8(|HLQSKIgA0%MGZnv%a~a%)@QLU%x) zMq868XQESYsFj4#)|<*(lm0gQ*Bp|4WMct9b4)xkyXCK%u#9q;-VApAPB@aw z&hH`XcN(@VBL+M-T2`|Uf)0=P6upF7{6{Dn9(wH~&3J?}kgx9RStMFl@(4wn?%jY# z`0jsTlR(+(ryGc&@(3r`OWQD3RN<_SVSy zxWMFKBrR|*Tidgp6pq~N$znH2VzzzKc|sdXZo_VG%Ye$VKSRApjLG=8sZyYLPQP<= z=P1Gmpo3jNMjNTj%8*zJ$sJHK6}4j zU3SrAxw-TV9R2aG8TRBvcxi|){ZsoS^4T+Ht+ z?9%hxiEBe6r_N}dA$EG3xjncYfp^yZmK}M_p+CbeY!`=NcYFa-|G~4*JhKLGNakDw zTOdsBbl-xo6u@HRGp;F=k*L+VZzPom#C2@e{jiLKxKx`c^b1EPVv(0&4+NWRMqyCl zQPfDtQ~3#|{zN7^gXzp2^Pnl;tE8+2|4qZ0mnUn_NQYI1g5vKG0>^^TFc1OCcn_#9 z$T@%ob3mmJZGlpqhQ}wfE8wQamCgJ>5o*lq7_y0xCjqmHLVTsS%!$JJO7u~XauqW% zA4Vf)z}pwW^gJMZNGPvWASQziDe@u*Ru8Bjh&C2XVto#C!q5w|5AZOxH4v$XPuI!B z$`e{AhwMB>^%Fi4WK?~A-ZU_B>*Niu&#&+5rYG0NuFoHHST+s=W7%d+cYen0U*mW> z#QlaHc;KQxQ5PoR5OohN%xGUzZSnbMp1FJXt|=}+ zWOBak$N-zEmGE~JcMw&AWe~)L@rN+RmDr)dp(OW*Sd069`_6Wz%3`|J@_n><0QLaY zm-3{B_XkOfMgBSF*DHs(`Ue`^q~+8GgG-@FB{HeZTK^wvO-hkTX=V~1@}bD|EdC8y z|3)VB@#zTtB8Ayw=K;E4FNFCEo)FOBxQ9_Q&ji6lycPbz7zdO8F?k0Rg))jdvsW-z zYbfE=CUl9iX~)N!&p5Db1l{zii0~Pic-R%9v^ci$FLB^C`_4oW{9YGMZyEXiRr81%9zxS3Z!!e%xj> zZ=kUM=?{I3CyTmg^#h~XtFJmPa{!JU>qhNIr3rk*lYseTv=qXJ&WGfdoP|I9DKyXU z3VU2?pl~N|^XPGD4voI3XG)KR#~mNlZw}PTaCm#1s(|0S=fcuE`Q>5t-DLM3R^Ls2 z?_t%#^t;0FvC-c(j*pH0uCaV<^mmQtW23)oOdlKlUE}&5R_{I59lF%{ut~q5*g8eD zWz~4R@#(trvs8+MewFUiKd;k2Ht~CaZ{J^f1OI+eXkUE6B%8&LKYBb`{6_dweG>l@ z{Hi)1G!=S$uxH6j>mGW6qm@9D6E;nDs}D*WXnM&}>n^>2r^E@lV~=r*?L)P|ehZX; zq&&P**=eaiNv2~O((t4|GU=aTx>E=gl*FBsl69S>&$aDRJSrXT5SAqg-WQJf6+!~M ztGa`^CSk=Toi2sDm)k4`M51_Ek|%J+nfRnbnx_O}WF;*l+an4Ik-8W8f6Au3R7LtS zQ{%$sWNL3Ai?`(56gw=Ict+Yjk~U3HtWXkPmLgM_k{IFsR2Z4Mb~LU2MRI?J`kF%4 z%uq1d)}(fphl5E+VK}rNv8@!F&$!yq>d|I_5OB+76(%&4?yfx>&RN0y`JM0f788*1 z?!$5$On%JstO(P)qJh_#j=!I6!8D80@UJ$rEt)uguxm@ZiL6MkDc9HuX!9@3+Wa!# z>r6-cG4F%zjCw@_kGZ&sbvFv_mcM}{rA%JPlEng zG6^sHXi@Zgm)^Y|`WiLY zOl*Qgo0_I-`h$B}HVhmW?S(ZzOw(9ZX><$#FOc&x?la~Od4>uL0E)8ndyO4H^+QzQ zBc!cpDtxJFw$6PAG+DXstm|OXpWyvqQ(0pd=*>)f6kCJFUnVDN>PJ(Xwi^~}gVk{Q zW|~22R*_mtrCxD!2JOqkNHzF8jh3ZKCMWrg`+nn1W16G!!2{>>G&&p|d&_oSe0pGn z^X$i-e|lhW5}zIz`|#KY#=iQPcI)SH)80tC^|SUB&3Q2QCEYV*Z`r z)(ebgKJL6A(;fD><2#~@V2KFn>_;J`2eNnk~7GV{P?ZMqn)Eqz8QQy5~@rM??3cdd2Dy=08P(b2ifDx0SC@MT2V0x zWD_ED5{pGCOS&=kIQ7du^3Z_;j-P=ZuB=u4Z$^S|QTHfNQ8gb&E1#nvASNu`_lMtL zZD%T@W7N#|$u~ozcD!S;1!jTC@fN&)u|=eBi6&aFlPb4;N~31@ML}lg2|N#Y!2|kX6+i3#8)nY zTH5lP>jpf>4F%b_CO7mZnh=+TOV7MaIRiuwI2_cC_?+FNmA5#DCU8>3M6v$p8DpL* zm(>ur7?P_kgi%Z$u2-L?h661;CNbuFoSKCCYnc+X0WZWeetQ5Z{S;UV3UVYMR~veu z(#D?va=ipT(vfa<4;X!Xw_R1%t}H>RzQWami}S}6GVF-XBYkK-lS zM#jg_n)C@<+s#Wyg8V?6t1?HYLdg>@=segfI9GvK!Z0+-`muk&GJ;blCKm#pdUuvZ^Z~)n<=d5g-b7)CRu{XM2*nETzC5y zs0sxcA`&!DH1FJcFBFY2vQS4#7WvqO6hARsbiHpLPX0dp=(0%Y1AEdX2%MkXJy^$# zdKd#}mNfE)-`Wl~hS`#sNn$uC_ziT5A^|L7hi_g2!8m(?GvBl=K{@*$avx)+--I{n45IAvFlyJ z`|E-ZS*UcGZ8L#fSjR|IB$#Iio0JVqm&aWOr|{rfYLV`j&EC4O3LXpe(KwnU+dh~Z%6J~9q6uh#)JOS0gK@Q%7J z2nx4fu@!Dz3cFse3tUV0j<_!T4qO+GWy<&JByT096)|FD{DN-+86#k5z!L<7qfm~< zGSOOAeM%KWuGff`@(l7~d1>K}jf5~LXrZGx4@GyI;pt+mx#>G`IX-+XkB)t)6vRwH zEJU2lKZxK4ivdR!go{`G3xS1+31qC~E~_jAtjY3)vxybSw5R$g22N&DM2qLIX(^^q}E0r9+<*V9(g~joGAv> zt+>ePA;rXj%RnMdJ7)dOC%CeLiTa5S1LN?Y*y``Aoi04uL@;}b1h~%D6J~Xz*S(;< znOXjs1$P9Nn}Bp%#K|oG)xT;h`Z+e3S^g!2bkZpj=4LGCWy zf8gA^d@k(X{X|!m8GCV^K|5Es={t{J*0L^$*-l2B#5k}iz%jC zDPigOI|aAK$8)l-6sXKS+%Q{|$PL04>(?kkmM#<_Pn%vcd;m1_k37t%m-Nm zA?F-v3S7X#*Z?n8W{>c%A-^nAS)~?Dkqj5_AOr&m4&a|jFFRK*oL<{iwW7cv zK|(mLY!ibzyLQ2mhFGk@jQFtPfXes_?)qMg1?J!aLPBNgb;?Ksjez3R8*P=U{IT`vBV zF9jB}TARL*HB}#Fxt$YZle5VDoO<*AWRUVohuFsueN3>AVfJx+d^9{A3`C}bX4?pV zIu#Nh&xnt0X7#-Yn!T=!2%TY1b+eG7V)*Lx#`b2s0U!Im|Hr_ z{EC+gV`YV4?f@H0TpL+d$TZIC4Z^#a`BzICo)swjFE~m|D?(Wk&3cXwhxP*NSs)?S z100F(voUmu_xU=rs1yT)6H(VQdyzV>$LRIn@9MQb*Ygqo9iEzkgT%O=&)o_E4urSs z#{*IQX@@YS+tH4NY&nkuk4jS0o3PzU+Md1Wqhm-GZ;YlU{ai{N^Wi}o&GFK-B@v9K z?882kzHGFz)A?UwvAYk(K&SKP?Ok$%(|LEr-Y`FF_0tW+P*3L%@4$Hnh&64QuOM%l zMbF9Z$&>(;OjL)%5sO?STO1ukECw+>Imm7WQyl|0wLG$rQi%}QW;N9`zM`Ee+OZmA zB$_b=Cwt#e3#dGZjBiaM5SNelhuokE=e+wD?Bn0Ek!~IMud}Pjz4W<^<`2B#e; z?q2WT?dsv`!`*q&bnJRu93c`-VYNON2z=cs()wLTr#;K}04y#nnG4mQ;DoF8k+>DX zNj09MKw%Q=sivIYsyJtclDd3|E`PD~VRyGKy?EdM+H^R7*Z-PXsLoZ!Zj@6mDwJll z!SPTiE=v`};&9=5QALa_D|APR0CA$obAd|hSR{@vz<&Q(u-!W%R}P^+g6kgO;-&Pw zpkedj#q|clL@#JKBp$t*Xd-Y3_g(e;E<h!!R^pp;L{UG2`(<5K${I<%KV#B|7G(g z|MKWFFmB*K@B{zK>aZJ{+jF@NXVLkn<*Ep7bqb8;6d4{KOFW;I__NK2;%BFPVDUcu zv-X_oz<(PF0Idq)uX8>Vc!gDZwD>LjLFcsu*=s1nKYS2jPceN2;RK*jihtQa+{Bsw zdCry&*xFvl(l;+L1bzyCx{)U?C9$WUC-DDUn~nNL_KM&P@r%S1K}0vpfI&RBB15Rc zALXooyCtk84Mj)&9hB}eojqYr0T*R+{fM1FwyLCxYnRt0CxM;|{!^CZe~-e+%Z4&l zmfB{5jwCOV(UD_U-RBemnLf^c3mp$-U{j(M{fb2M)S97)9iu|IQh%2z!tD!CkjTL>6(V_{i)d~!|ABAvMTCCt&X_tqt==*!hT969+4-j zd!;Zzr21DH%)Rx&JzyTy(v@tNq|wdgnlcZ8K?pM=-%d%wLv)j3Jit6Cv102K@d4Tc za~C)TAOWeVO*Hq>q~F?5P77zHP&x9=5}6b5lAUnNy#`{FX(qalTDw)~`6|KDs(pz8 zsQM*RO+hC>>x8IeqaxKt-9rIaRg{*0aG=#u7DsA5kXn$0(eA#zRU*I72m;^+DctshQ6i>e`2mR?7-c&*I^q)X53{ZRTTT8cZRpX{?GxFD+e zKF)2Tf0Mo92%;&!<@6{iNPj37p(~}SL5zg%S5tF!aszB5qXfd_Aa63M6q<6Ka(Y2P zrDFEv!;kPl-wsQ40DE#q!xLDqXlc-w0wL2XQfCF{u_Rwkfj;4tvT`OPQjf)kjE_?U zwuxi&b4$`R$%^O0Ptfm@rWFI4A%1?u0z$xLvM`GoBnwwr$%9+0Bas@6YKpA+z>gIH z8FDZeIOwKy4bIJknM>W&g7g-S+`DuD*7Mew5+tD^b%?$2^VaF?B@}tISsm7@36mOL zpVyujr*OrWyJK@M&E3&V@K_^LuI>?v^y^(XcGE#GorK|>JPrWUNxW}TRG-i{ucraeB{6^K1G+$F1vMHH{S(g4DLawmN2(#yyP{14_yi0na+g_GkWAE zbkf1ujb8VF*SV6f(z^&pj4n6pzTM?I;ZzA1+;Ux`tDyqz#H2?cxUF(!w#mHQWKL05 zRdhJ3lixa}{bz;IYHE$D%EBC)#ce4g$AT#xLvveD5ieh?n5qvQIRG?VC9pel0eafM zNr3{UFCtP~5|4p<>;Rtps)nS^O}ggDKOb?z`Fh#97g4btYJ!}MGWAYJ%xT1Q2_eUS z0x?Gcbu>k~y3Gm#Imn#~bS_8$VcpUg6A6hB@@|J8urPbmBZTS_Ty_OBaQ{<(Q~^O^ za9|3&;5$>c0}k*5G?H^weo(}@uzlUnvEn0L$H^<=?Q)xL@_wm>LzB9qDJ|`(D<0F? zw_T0zlxDiX>wntY4$bFKF`6G0borN9A%J{rhqd?f#gcHE~c$<-EojUk&+viv2wu__gmhZLkUf~$K(YrQEJ2!eAEBuSsS%xCnGQZbZga69LQqR>Z{+#=@|J;79 zcr`A6X$34RQ5Sd!Qm%JWD%ol$a>NANN!jDcC*cwsl7|6@IY~2KYJ9woq7u-ek+u%m zwcys7lM1kPAwU<}A#k>5Om}4pTNV?H$KYwl$CIYpL()<&n#!jAdaZ_fuKpuf1+l`` z_&Pe1jjVn6*M~O+;k*yCS8Raa>e>K8ZTfGz8f|>n_G;p6&R(qm!tZv0(0enHJID7q zdyvD==)k9YE~bFQJ`H>0<-=Wjf+OS7a|Z*Le!>Xc6Y)izro8ut$)R>!W!b8Ki1WC&x6kI{O@=xkfiWO$5DlZ3O+G zgP`;^5G1@d5Q2VqiPDCGcjCO1?9agVm8E@0uAkQK%qWsR#S(DQMg)_Ulhu44yAwgf z^g~&J@e7!nL~N)oLI24lE9_E)ijoGDOHPKIEmoCtR^g8JuvBeZmbk4=Kv7e&Htyep zklD-Hc@F}IV`yA^m;I2l%g(Q{%Y@ek+GR4|Wmz>Rzv53|=}j)XNmZNJdCa2Vldd2} z(LAGcJfTE4)d}1Wtvm48H1*rg+WgeML!&vn;T;+fE8MyE3jeUP!ry<56&79_XoZ&( zreTB_oAGfdgvj(xwsU<76xR_Ph%P{DQUC>^U{sh0bXN1rlCo?@=j(+21Qy2i82I>G zUHA}~+UE%fz9q~r&Wc$-!a~{AK~ENhrONpc2cdj)CTm1)GF=Cv8@=vtA4gIQu-7+_X7b*YblLs1kMBy9~ubF2IJGgcqkf&#TQ&<7D^3-s}_|) z5gEr&4n(cM9+{JK)4qKLs#!@Zw=u|;T!hmx?21wuUiQ|DSB^0kM5>Ruxo~8R`i6Tp zf$a2bAKjUoOjtPMH+vsD<)3%$l+rK1@0n+~a;|g78>M_de!}Z#ieV5SyRwTrrT?>Q z?5pWW={EsY$KP)uA46~{{SumDi~Xpxq4^vc$@vUlvnv)`0KIQh5BzyqSNZt17UAX2 z*9lun7}53Eqj&e}e9Ut%^2PbM@GFZevG%Gk+*KXiDZRYv7GQ6>H1_@6e{%}Z;^IGTiX0bg5h6@J!DKO-g5@HHQoGDgs07e`N0Mm^rGeBOS z0#%wajW~ic;{$XELDe5)B{v?r7MOPpmtEe3< zY2;l2OO8^prH27q+v`z^(=NGFis4T`y#U4QeJN#|mS)&1j@m!<$M7N%fMww)1Yb_3 zm=?zElJ19CA5Ez-krXTu(+AnI6YdJ+e$1e50@x?~Dp@HMHLMJ>cQ8?mRM#VIBxS@E zLa9GsqowDhC5OVna-(D~BTRw39qqSpBT2~KkF-5`c#^{3k^iE*?N_Zw{s(WiP7w>y zIt@)e%ptm-KE7R@3O#!33kM_9e%}GpVv$QK?}K(erMfh$T7VlwMJl>{ss<^`Y3AeO z2)M+}A%jP>6k+4z*p)Si-t^4w3H2f{M|#Bqmj7}IPL{t?7?q0USfkqAVYirCH!FPu zzVZI}FHq5yvALKZEB}qX#xk(9{UxfkYfeF-s!6MaidSvl7fm84%!ohf4fabG(d0ne-yM+cN9gH?h6eEaIdv33 zcAoVH`u&`&bEusM4%p5!boMhtgZnjyy!W_Bgh>tfg2#+ql+c~Jw)Kcl-Icl)k8K37 zWAS&dGw*&R68c=%CH$nXLuW3XcYJ7%=M?9BdglHt>=*x9PH8wja3$pw5W) z0Wj=N>JLT+yDJyROKQZfu8`nIhmqqGV2s?rH0ROZv58PUd5tG)tJ%6%G1MZNQUl z32OtkcCYH(FcI<1bRYB}!1mCcel0yv)Blnc$dho%Uc=AxRjQvsRWG2HP!MlVxg#e1 z;Yq)xF@d^d#JojZ^txvb{5Nlc;2(1c?XmSfBeXAB&EM9S@}l|RLGVM*byZ=Mv0M zI9rwv&bI7}CZ!i<#Gmv9^U4ir5xgsZcTeX(9@=#JZ&(2f-)HZ)MR(Nfo4f}sn z4Iih_kf`k(6-7ksT}MZXFP8Dv*~pjlucrzrir-d(kC=j33E{7!FIH-#Fz&bUnOaYT ziEChWzgDlZyg4k_)ktuJJeEe#DcJsf6rs(?2#93P^-MycK9KAhk%leuMY0R?xps5u zbClcA(pPqu>G&URvi5(|*~uLa2AHvB@PpZ)tmZV!<^3OpvOhnHiN&@4<)70h;w>^&JgUX|F^@O z=ks*dodG)L_kQqoo&$B@8{RcKB z>VKUGuQ}IA@6pHuMqrx+{@M0`Nqw`GHm0CLV+4yMX?`3tG`6v6%w2!(t$oO~$%Cp@+g7ctYl1`1+fT1g}@r z@2eJsNcimoj5|a;3Fl_$U1MiPyH1hof_1CG2UQn*zN^cgyOuMN|B-X^a*!AkY325C zj-B=3dY})g9M~Hs=s)}K(C&5c`|lFe9-E*yts_?(VW&B?&Uvjf;t)1C(U^p7N^nw{ zVooYf!1ilSdz%n?c(q*eopJn62JxL46+9C-RF_BbudVSLbMP1JwJ)`3``;-w@MjPY znxFm-+k-}DuQ(nwoqx0d!ilICxT#RQCn9C2gee7lB4f7#e-)BrvPFblXDKY3VrujN z_b{a^h7>Z)mxi2SG}(vf8mf|$Gc|5Zy>C^)f#%5>0Ms4Q4v8HU3{E#tw=)O?9}JBy zQ5;LFz{`c)D?#lk$r&78P~lVpy{EFRDAqH=%1C7LtQsprEtwJg{U#?6?fz|n@$c!P zJ1#2RQ_T6nt~UoFwtvf6I6g8Xwx8~~BEqElH0(R0UZo>{a+ovvpty&G3Amqoz>8JB zBMWM>ZK|(#`)oFf@X@)m7)(%a-jxJ7}FKp?4zpmn_-80as^Yel6lD zlFlw)2CF(YWm==^*wg+*&Nd>0%O|qT4Zy_3^J@TvUTPrk6pQ#b?b(!iyTYyuQOQB# z#3*xbhZ`j_i#Fsj^V;C*sLRraqWj>V4^LF{K7gcwyM}}TN`eU(Z0AN>6AZ9vwv-=I z&HFr<09zVj1*trSbaIg3p85aSdlxXds_RS?Ng$wj3ut45%|W#3>ZYsuAqfn)0SQSU zTL>%(Xpm4(b$4}lm8z@S^-!y=^u!@{9?qGGLuAL!Af0!v_vCy@>kPMx^30GCvn zm4seq5Dm=1Hx#Y{HjojylMVfJMSyA$G!U@{lQvGo6<#Vj+GV^)JESq^bCokgED%AD z`l1Gf2Q6h7hn^5I)X-Cgf!^+_%-#`5ZwY5uxX#*86Bn&vyE(?c$mR8Th5cPK;>8(O zVV*d1ltzTwa#@u#wG{)#@(8_x)>vY+MVOq|AU}T-*{*%;{C|oxm58JNh~emJD9q8X ziR?UU3T>Z!)A;p^t@{@;O}X5*S{m9a^3hsNt2b!zns>We8XsTvl-VjkZnr7lc-l0= zyT=Kq{A-v3#QshYx~~uFV-2sbW;~Gh!AY&GC4XF|=$|zd^Ul+*iy#I$=6_0t z@qE#uOz8QDuI76JY0L(`(&od~jNSL12_^>e_IT!Q^_!%$XEZ5n%x~xktkOll6J5NL zj_N8#nl(N5y=NlHz}jWH(|)%kyw-TdBJ#)5oNhL$#AOB%Ca>cGlM8@by2){Br*$vn z0_Vq51x`{y(gsfAIv(I`1cxqDGOPlZdEtWQr8GfvUmpUq1+BiC*)RYB=F61OZVkq~ z^R(>Zts_7r-MIfP%>}rGPZ!qc<%`~ip47JSl{ANbYs?wQnpA92&vcV*B9ywAPC`~^ z;@Q)pD-yh^!|6=zzmDJab__cfLFZQ;bWaZ5#mpEX;Zk{Gv}UPa`6l`@?yu>4=XY=L zn5h7<;rbd-%=6$U*h>s8wH3O1S>#% z2%rk6b96icSgjibFxA2#vl%+u40ENDbrnBrs&p|M23#kSaLCx*l2{He+b3P<6xhuR z4fpaHg84vs4S$kY{$Biqw)~yqDwgH%%Lgo<4HGtq)ose%A}BzgxX7=xmtsREsFiVE z*@00;*lP@v%}!jpl-J1F07y1M_SwJ=67IWbL)=S;ZM4F*-Dqe)+iP@u1oReu=oAn%Z zfK~tI$cA%vZCC5#ha)u;ZPia2g1@dWVz8=Fcc=I~-j}`q~WGnbE)l=p&4MBrx z=AEbAcue^jLl_OFls`Ib9YuC#_Uy~<9)^{xFf)E_gOj&=OpfuFev z@p~u#ULVaU#=o)3dU`CJeHqZ|CLx4dVPmWpR?dDaezlfoi}kaIC|4y}sXv05z!LM) z?>NFkbVE$P1N1jAL;3pmqvHh!>=HQ11nJ2Kk*P z)Po9C(mpAmB?>k2h>8R2q>$nVSEj~CCq^encZ}|Y-O@^RM7xy7NsFEw~BqI2CE+3q28b7P%jl`jl2b9{mKJfA3umr31#3Bpb3W6vh&*0x{G>OSd>OV z#Chj}<(V|WGT^6d)?7N3h?`c|Te8b(&S7`oMA({c3XORn(;c0ZY1c)I%Qat6NMXHk zQQ{lZ1m|Un3t3Px?>v)phrJ==z(>=ZfKU4q-MjH}nZ<#OTxK*L(@R(^P+BciO^Ddl)m3Cy zM~@C7Dpjl)fNz77fRI8poqNH3=RBj&Oz8BS2d~uz+eez83reJ!kwJr zBwD>dPAfD;j7G>@(C@HnhrHY((iz;*=gEDYx}&7lYt&vKWi>G^Y0ANBAdX`ZQFzdZ zKOi~_pumFF5(1}F2u0w?+(~k-!=k~j4G!{J5fvOnP9yS-4-V^~pGE@w`qvrhEUNIj z4+X^Nry`WYM`=A}tgT~B$bRc-+YNm?XybIJEvHC#vcj6GhsnxgjK30@e`o1h1Ta3N z0vM-50_>Q&pEokQf;h|Uf$-JoOeU-qh%f6~7sqgSsU$iI^!iytmyac%OAI*6*Sgab zPrW__&H~))HGrA)(Z+{l2_1cP`>RD)HMU;Tk)rx$`3?wi2`cBa`R0WaoXX5@-1A&5|O_Q zo!*`zG-IsjhVV95gg9G)qzDsvquH9LTXz(HN&0C(1fq)-8~{-zd37v*u0e0=*c$x( z*K~yIH5uTVZa^qKI$hL0DKD?1ALc=HJp{M^8YCh^$aAkMl6Xi0nh>@zT<9}#RgrRk znfr#!&~$T{p1NGl2_ne&&pJUguI`?+1zr*HxlMR(6`k9Pv?#851Z&yTGbP;7;4q4V zC8?DZL0Tw6mEf*cM<@<~o6QLNj$^R0guv@G3wR+QZ7wpH$rMqfdxXlgxQyGHY=woG zU2AZlNFi7Qmcm9M)R==9kGwGwG?r_KP_Achgw%s+F1t;NQ*9S$o+E7Ew6w*q6ucuD z!l~_+w7A}EEQs6{8A4|X&Jsla)NDI71(vlwa$e%TwSwpA0DD7))9anKuNM`%6n9bK zK$@tKAw!6W*=oVxej7XKE7?I=QXn-o_oX|5<7rMnh56B4gz8P~z^`i~lWO#yFS>o+ zjqT-DQIWKG)IC(7Qq4*M8z{uH*jSKRmI^BnCQBSI4qdN6%p@}` zX-M_WRg9R1ApI@bse-JrdX&^WEXPuMv)n642S_?N=n_fPk}?=m4c=~VQwxR#7U(vIf zwJBnO!SOmW4#JnV4hk)fn^UlJz)Evw4Ur@7JYHOBlq$6k ztOM+~j_gvU6J@KUaX>o9y=cHOCVdsF)J<)Xz*FhfJ&r~r$~ePaDhz>!3dc_%{)G4u z&>w)C5O;B0^UTqBtEg^mX!QomeDP!5j-wf~5Nb2ouUtr66=^CFLEK!{b5}!Qf_OXg z)0i3R{=-DYJ=2ZHYHNT7t4*~qE3ZbYw0S~B#(D87B9Wd_k(pRts!qIGtu36F(S9Y- z-`#h(xC*PLl(a}x;@_+on@5-{=vg2;iE%1b9@#u8qq17?zS__$RNg_@F;JespKjYl zY5BH&hsKLMS20??@ICv<^$o_)HBP<3N-vh=NPjiT$|%TR>@e3{BKZ$!G*?5U70MgO z##gE1E2;}JTAI44Q`6S&>0Ac$dmyq29C;$VR1Q$VRzGVvF->_S(nzA6biIL?8U*j8 zaqT^r6c~CiVefT4ATXPy)5*aaIxV&!fDY%F{(2l9D8R~Msd@&s@x|)MdIrkaJEjCX z7)P!%Vha<4vi;{AdMmb|*}36;b;U_?Ag4LWNphN#IE(TYodSy<*$obQ^hDJ z|5z{F8dtFx3&0X^|W}ud@KgG3HHmLt#4LVNCLZ< zqy_pdu#qZA^KU(Z@{b9?{z%V&J)HCO>9EQ0VF$3x6B)RYOO8q|iI`=~E;XRVBh!7P z>ovemtvx+`UVxwJe*tEXdVrB^0e(X)z_0bZ0QEDTKHUX)(p>;~ViRkij&I|m`dEeR zKl-;>3{|jwJ@eIF%jG$eoQLiO#c<{c@-f{i5e5C27Y*J z;JsU8Qq{l@ZwkNrCbXeyc|b?V0M8e|r1nFKVnTDk|`(yI>b! zDZMNtmTU}`8ts{OzS{rheBrM>o50$fw@UMckojP*fpSTom7z0G+cdVE9(noV$62b` zOn-WkCSH8gTiO||vth$`IW(8030u6FUbml^)2%zHu@wbg&nvu5wMh*GUcPGqfo=+r z1hU6V_j^EME#JwbPR`aW+lcg2- z>KF30`r;TpjafBj1RWeUTE@X7omyIyWaS|U2N9HUeWJHngOb-s6n6SP>9q)bU(wre zq_@uEuJCRiSKiG@L1z0ezg*M{sbf-Fh^VGo_(&f|x*Q#c za_Tr_&UXiNo4ud!B4@0&)1Eo$BsuNfFI^W)?^EZW-VU4ca%sQKXoM?2PM9@NJ`}V6 z)w%AKP~*nCxr*7~(~m+zc?w$`C(_#NDM~?r3p`}Cu9TKblwAOZXi|C#8emzM;ZTU% z!4wiGAHZc1;YsM~KYaEo1(@Zjib`p)g6k!?F$3M|;Av@vEs0a0ib!pw7#dGvXD3sUQOnyaTm6 zBQhgmQ24jrT&gW{B57qprx`fP+Dr#MFxlbJNHvg(dKKWnFtlckNd{Td_oe|>i^`?b z9?<4^gf97Rop{O&CRt%?yvfRY#^dO@%d@uw*X8Z()24Z5fYr!MI#XC|1(mnwi)J^d zSu&-3vv82`pr+|H>{7@xlkSjJHz!f*MlbSP{dOqe>C=H;cnO;}6&sUJnvgIMzco!D zUK81=))d-4#SZ=|XPc`@MBciS`JOZn`$ZlbEC*`q>5kZ>I_TEN_4$d_oTbQF-MdDW12qQ*R@M zbrRkzf=BG%qePv)825pdUczS*BkjXDophvO?9BLtdV*!_%=jdpC~<*n8ap#ihg4$= zidx1{bHZtL!fAD)L#q>Rt5E|PTAg%Sopf5A?9l3@+iE8}S!rEc$Lv6^5Pe~m7+nwsg@99BjrUd5Af2fyCb{3(ehZZ+`R)+iZwVva8hrt%px`rMn=G*4}GlgM0)D zRv6kQ)`gvI63?#a#pXAblpvL%3dB>c0>PB4KqU255yF+I0@;(RK6}<%qQXDI9Y?)dBF#%2$$S?Z=Ej&Na=lm@8)OS52FQ*Bl%k&1*orLC{XUOrgn}vKvb~Dw&Ev5Mh6KRGH zGUZWB$vKP|d0ZSu%6XKCJA}OXF(M+uT1&)7w!EiULmqk2%%w!3F0 zynt_Y>U!}`9g!N_R>9Lz=7L__XMK51>?EC*>1!MxG&y3~Y}?`PEF!^)uKt$}_lTb8 zrfbl0>_*sG4k>6Hhge^qxT7&P*vUnmU1enJBk8j0;GXgm}=7mlk|E>ynGLlt4kXpnM)( zV8obB_M|!dgK6#`YvSp)>j7DJ984X+r3xj)Ye)OW3)LXCCn)zeQ4v$Zx8JZ)WuqpB!^Q;+%DI zG>*wuAy%6@g(5Lh&7m-fqw&aN#0)v;{sQ^0f=_iyQMc+fgto`sPDcsBBj5D;3k`BH7{ zQG~mKIqe|gztZK>vH9BE*h*`549daD!|(y#i!1nq^CnMkSg5GfY9~n=LO?G7 z%StKGmO#vm#P42zq_|wlA&_W^{&b`1*m+DVcqch0F77`;nt+)lx?&V^Ed|eyvC>VRb z7!Z3tqN`u&5yJN<2=|PoNg()88klURoJw<^^)M8|BLeH+h2X~HdAW)hc3P7qT7RqYRkBx6(HCku0S+0;xCd2q4EThG4A63(XX9I&p5FIebN8#;arXK2VRa&O!Akuww5sXVts1IJ<$O| zDk+|x!91q+7b=Y+pmTe$?{pJsEo-EhnU~fbCV7+)8rg^N60*wB?L*|tByMf7eVBAc zb8Lg`4&?j@>G$HEhsSPTdC6l$c=V7F=qt1W`hEi#*Wh;f{*?E|W z?hTs9nt27rsVVb2j|Q{D&kkpH>meS)(4NgaV?95E=R?->Av{Z@w%#f<$2XZo-2SK# z|5*axAt=zmSt%%*1f#2foX$+6ZgnO9zGA)B$Yv|p>$`_XcMT6`rjOk_I!<^n!9OSH z=WhNv$v;O%vXlAou^stwQFe!Vo13s-@3ddjLL8+Fd({%qa-|MNPx89RMJ)JSW^b{9 z7+{YU;6;2IU4lgD)yYl|JD>Bs&3IgPE#w~~9U~E#V?z^~I_y4?MN-aTem;?<9Jl;? zVvJTn^2V&)jtb{|fni@@*d*IrVAvNJHl0x}FlZ-VAw3t9)m!7fnmR%3|k-b z*$(_yIOBKIr&3z^@|SR0FaHJpAwRtj;G7QSz+Yo0Pn* zQT`lWLQn8QL2GCKLbekfMER@H`r+ks#Y$zSxwcX~8(vHr5!N657iw~#tn>|>9Bbs= zn3U1@hTr%U)VHpsRz$*Sw;`%5z!PMxMRElzqdcU+Rz|lI*`NaMz^57rV0E(UiuGut<9vZP574P63&~8?BFjB*A>L%Bt4qeUv?{^ z$6J1YFma$f)eAzhdh+GZdq!whGaP}H1hIXP5juxm%y-LYD*`9by0-sa1ZE)o&(KQ(KthR8(xE!yd|Z4E5&bSo7* zX`kP{#BJXvce3wKbFv-o2P%LlCmlmgI@y6NXwr@mcA)c`H+&q!?2|XVI`~%Q7-c4H zNX7Imkc>$43cYTv4t+7}W0g8mU9d4;3$({6t_LpJSdq6HwaO{w7AGiAWDMM zmOE>)#71(G`x=xZLMoUW@YjRl9=)y>p`0T+C9d}bly+e-$chA7CIRRYi~Z_PX6?xy+Fy@g}v3ozWmY1=5dLUzTY7? zqkeXG;ERz)5|NwD2Q{v!K`^;_?)6`53!vx2XkwRX3vg302>$IZ&#$JrJnv3%4_I(c zwb@vJU14oL1vuxO3&1a=3Bb$rX4jpB=ACEg@w~>`N`~yZyyo{Z4`m(6g73WzPaR*V z7v|1Pte>f_izHM?@u?y$(;dw$P%CFaOXRc~J~8Rkq>{(a9OnvlFKg>L`%$;Eu9`X8 zdmT~r__{eCeNE0yBL@p~UjYX8$(y$|G`%%QVt8|S6n=fe{6w4#VmVoz93h*ofJweo z5UC=_*@`%xD4mn{Z4snX2=$gUeuJ-dYybPdV>fI%+D%2Wp(|mTNRx@!)%Ne!;8R0l zb~WBJNc74g^H9&=YzIg@d9a3VR^BBKKbe3$B;4e_NYu%?l2rX053eafK?iNoroOOG|VzYDHV`{!G|3E z!_8ePT7<7_G0bRBWJbQb4xTbsIYYDhi+u3(;2r@sJ){IA{L-t&7<@D`v_y1tuYtE3 zHq+4#2X9p-`N7-jz-$Va+8v3bc9XqILq-@mCvCfMU+$lB9KPml-45y@2?Fp-K~hbi zdx3q%8KK}T*n|=fIjh0p;U&3Rg24r<-4&>KX5UE@2gh+C%cmUC(cdG>~W?&EBO~Pz`|h z(X~+^Ta$197CZb+lWOSr(H|X zFq8NptY$Y6Apwbh;bpz)4S)@apT1@DMHk@!0^{7E2f#21wv+647mF*PsR7@GH7V}oU1Pa#Xw76AZiA5UK8*Kc$BV@;= zS=W0oO9`vqZ|*L5Fw%G;X7}RXYrI#3V`ev!9HXtN_EO6O4j+?Kqq3OXn>%hHYbad` zd3tsiB1Wn>o+hBTD`~Iuj<;r&q_k&x-2tndX;EreV|E;Iu?E#cCC}J;0{!VUL4O_Z zWt%oylk$A@3_dYn_oqX3tpTRhVn4Imn+6lG=9Er*{mf{8IvmNGQ(7(dGpmP42 zqV2NQMUX((bz~NL#Fqu|J{wtf7iYB3S$7|_|0mK&B2nxYjVPuD!J^pP6T#G)XTl1x zlfBWqOiCi{@Ks|jpUl3TCLr!~BHG0uh#p7SQ#B7z;4gv}^?)aN?{BMes5*b*bB6imuiX@48eks$JMq9X+G+O_&W(eSrS-WaD`G zVb2^~RR3Z|VC!*;CRD0OkF9){KR;~zsdECWC)ux+s5j8J(OQNo zR=c+nu9eq?|0z4Uri!^9y#1P)k6wO8%{~32=H_4WAcKXPZ-ox91eIpQ&y?acLC9Bl z8dFM-I*cg@B7L}LeBSm&&lFsI{&?^BY;K4$(rZxu*R($d%3l|=49ZVra#F*3jjLFD`|77C4Qf?o{ZgAb z`r7mzioQQYe|nOmcDSSP8T8KA4Pb`%tu7<4|GOMI+PXZy`f0(Ga2P}pIcJhm` z21vx*M@Eaz9ucBT051u;Pu3mK>fCpR&VXIE(b~F^T3(~xG;DbneX0Ll^xWU-l{SDh zyJ-5#Ef-w`<_H%7sAlQ<0p~msp3$V&cH_S%zzU2tpd5seGWU{o-OaKlkadU~le3)Pi1`ce}SOyI*`np?^MVDNuY&J?W% zqV$r(38Md!=RUkBF*X`kakfrwRbqCH791CWO(P=*pBNbdevvOp4X~t9VlX2kN3dLo zLthV`q$HTZUb_TpWRE<#cbI!cYU+8hwB&$^_@_V&^iP;4)-DsdY8XYlLF4c7j*adL zi%V?04G_)0ix75~m$aw(=(zV3U+JZaONTZ+B}lOH)kwr+p1?A z&$PRPRXGp2z`0zrLj@x1jSHx!(*)G?xnjN+NY7m#8wNg>Xm{Vzfi=Yx8tZ2+5B4jk zSX1f0t$t>*FBO5wnodd$_A{rczQi|cE`2uSo5M51-*9&QY~rJEe9=G48AnQixS7|0K%28YpJBy0;pz18!< z?z(VO#x%%BV#D|S3@T1}B9+o{#WbL~)BmFvSn69P9pv9lc{8Q*hmf1bGxK-_iG{Sj zbA9+Z9GmC>i%^E-R$r@*jNBXStp#hf7S2Ps&&H=B_$Du}P>=?Bdd7)(iH?_i&dk!e zsZ#>BVb-VPu*uirr1utS*W?LS9mB-AD~LPs4?cj*IOrXhz>!~UffNPg4%Xma=#YMz zE`LA3y9C;~rLFD){eEPDmJGeP+69B!XVKTXy)gO(%kzhk=DVJMn5KNMS$s7%KK!h| zu8Uw0FMOQ`0-!3mC<)#bG~+hthW7Da^|Fp?A9q^HI})O-!K|b;Jiv)32-YwSK`_kUp)>`5PZWqfd!O4^f+AljD<+ zxO;Atzw;OhG}9DaNh&qlVqW*rf(BCgK^ogY`ToRkqCH0$`#xd7V&-SS5)L;&DRP2R z+EWaOnS42B^B=V2I(rv;dw!k;7r?ZvVtXh*q&FRnC7m0Fd;>TxoafOF)jE0&t{T7g#?Yy1|TsB_%4reR0(b3E32t)QQg>vSF9!vS- zv^WFh@9G87MBx9Q^YrezZya$Jm@WNmmfoQ69Nh7Y_r^JCTZ4s{=!g1WqF4Ud10;)L zT`EtUYK8Q(9!dFU#R7e*=LLFo>vm;$>a+vb+84<31JERE$|hv#F5~Ms0u5qb?ElpN zVsFlS0B$YzzoURRLLmV8nzRbI_r=~eY_)Z4vciu;$6X*{N4SiuD`z4egJyQHk{v{Z zfx5m+1uHY@Ht4b$C;<1Sa!Yz5<`{eL+qw_Z;)ii1K~;V)g0wDw^ko~6=ULw;cfI~7 z(sXA^YH`MGPv{j=Lu1ZZQqcg;J)HF{!q>1<&r-y5a0^(5epu-I(Efq287=V(FVTY?@X!CIH#Yx$SygjHRZhvgGDu7IWD38_Q5K^eG1qYFWp&1+jv_U!) z*GW{?!0pDb9{DCGG&(wy|Rb`-QG>HF%Ll+VRMfmZ3AQRWhX+Ipv}7oHXk zwd-^Mv{sR}y*vPZ7MTT=4HI(LrBJ_qzWvn)kq=Ro3cuxcwL8te$37${H_9DT$k0DH z3?iL0gdVunAwTn}>~#KU9$~(ayLnjr%^wv%RPt&{3Qgn#yPupC;Tgyjq+Uc?bTSlW z);J#&8lDaw;~w;qYLo7wYPhv(QLdoJ3Shxtvwpl z=W5v6Q->hW4<8$UR_^8Mil|3)0ga4;MyO=#Val!QMG=|=EXRg+<_mfqH?T7ge?>3p z_se#ogXlFQtXetm&b(_kU=FejbNd=`t(8g*k^68SpatVoDA8MTYbFgWznDjgcZJRy zt*${`{!cW^f%2y{(8LDnj{KytpS|gJr7BS~+z@U~zlfY`kIJOX`$X`lp=SeNonR(l zIS*5|OPtiQ{(x&M}x}h)Z}O;u>Ru?r-pVf7bnLj?h+&E z(yW4Bd#l0R)X?&fxAFa@rf9fQT*Ora0HaYjRh$8+vfIUgsqe=Q9@##eVW=(DRCad_;y&#L`sj*&x`azcisJWBL$7i9e-U^G%KsFz%p})5fH^$3pcm%vxr(KI_{vk_ zIy9hAqNI}W5Yzk$@mq;BLp@6&x}YH#Jd6Yyjky|F7vBv7gEKa12$qmIs_@Mst%M=m zGN+G_K4GnfH`-k3WT}~h9;OaoG?GZEaom3wSHf!0(KIS0TsO;S;3r9GK}4)DSi>RW z(qP)!kP%+lM@**RB(4h#5rfuAb1aE>w3n${@@;SRuuhq0x+xbnAJ!=^=%-#~-pSWT zs&?h$%J}&Kv)-y}mScDKy>@1FVG50TKw}B|SK4Tzwu}2x!zy&&qv1Px0US&JouGD0 zHw3i+(!HE-t{$IOwO;B>frHtbI_v?f>yAZyy&8YW2+*L2KzHuTE)aewMF@AZ!x`#_?`45i8Z#z>9O;x0$tWue;)N;+DjZA>2V?CeP=!orvdZwV zD5>`F>(H}a0w$`bu+~w@B$0U3&`7cY@#y(~qq*>kY$rO1Ud1DY0p6qN%_MbTudLQu z719z))`@edO5sFU(<=>9f?keRlvwmswpwd>T zu35yn+|0{#W4-hYHJ;{Lo%M&st3-1F4n=eoB^5NcDl~Hq1k*(UL5*!<>=NRfDl#%M zIXqU)WW)}k);n&I*R6lO7QFxdKP-0?^%L#CFKIm4!2WxASfk9J$#$ZHNOk|+M)X&y z0_lKLFCzC7B{7tzLv4FbP*MZ1eEBh^#h20_%V61k%aDTamB;n``@>?vzvX21)$6so zAD^WRQJ8Hg;X&iZ%i(y_C!K=Z*aXV?A~w_z`A)! zOq8<0-5N0&a+V{NyD}hkV7}OF57jw~ZI?>tLu+FCm1m&XRBg9`ReNeOD6>BuRJI0{ zR*OB)NpTI#>VZCYmNlKeo9bsC`_tLs)^yTpv7cG(>7U?OGfJbierEHw?zGPuXdUali=z-pZ?`8HleI*NiUW9`iJ*^*dzYz6Dml=+(96Q|{}&?7 zBw~738m6a)!A$Q)FGQ`$btvGOjt}!xUy32RQ;y;8f0gD$Z}8!VHBbL{&otdBC}CZC z;;Kh?#Wo-B;he0*luj#lla}No$ZSofbD7u)ZNZjM7|6ffsoa?6RJMw(XANAv@eH#& zdRc_c35y(ZyyW)17f-k>_#49I+^d_;;Ixwwhc_q0tGF~YJY{Foi6ml>2}t-F9w%a8 zC)YD;>oX-44iE^&g6pQ+eoY_m4Psgxbw*@{CI08TO(7Or1fMRz zb)v9HL0?r-cA2pFEo2ngNKxGXXqYQ%*R^$I?PSkKZ0d(2 z0>;kFagZ`|izH)^{CSs?=pCOs(co!(S>WuCMs|+7bP4k;z8GmF(K7Bd%cusyl;!Pg z5U1?yKy6%k@#n6zXiUNiv6FpE=haYDwp$Smcs_;vYMLOq%0&jDMf~i1tg?Ab57A-$mC8|#eZqj*2u(&{!jfQ`s}xQP|HH}xU6%+-7}_? z9(95wc2_>zgQ|shNBw{IOu^k9-?zct5xw~C%Vf8kk}0)E~yxZ?=v+e-zRrk%V|!_7lB)0t}>j&A9F0UH!`QGM!|4)8doU}xceLg07sQ# zR0FSpD&^Y&LpWkPK~55>Qa;8N6VZYf-hPKtrHJm5sZvB)1H4YE6s!4=2W2szXfjVJ z;YVLAgXN$4%BMAK)sR_0 zOO(D-_n$c1r|Kg)E42n_cBQ*VlIGuR2edr4orq@pjFz0;K(^0l8`z3<3gkANtTzo? zCU4iA==*^7>X-CN8$cSiN;1hVS0)ML?LCI+z6L_d2m`_0Nr{A%9Wl_e_QU3Dhm?>a zx=SXch_VKnorDyt`5_*ZMaFJDut3%bHbkhq?;-$~I3_8o5L-^8PWce}fEaU-{`4fq zTx`HVB`F=-&F_QJJJQ#2?o#;^*fe{?##3M3D``{AmHU`BtM>5mh zv*96FXSO~X0fLny25ur*bK8gbR82VwOq+X z0c)+zUUWr)ZwFE0T?J}%oZY-mPK~dhIJ1Iu-k5dyJ8<)G-{}GGbr~Y^HgL)&H#jyzG>8B7iwn;(0NX3ea7?j6L z<|^?JN(6~1)+vT9A{4548*U_9Nj%{`lLY}p)E-=<i$wyNifkEgn z<%Y3;KONb88=|Mb6=@_9J>ByYdKuLqn4WGYKcyHzYn%#`l=e)syZl7{1J>{imboNg zAtSW?Cnn(s%1AP-H?Fnqr5F2&NoDZiJ%3zz4aln4{pt;j09t}a6gRcAU#spka9OhX z)BZQ?;os9MZ9r*l*eh`-p;ck`{8ClT)_tkRRQ_ASwSn^A^n!A1@tgez&nVmlecr#I zLexw|;{`F6$1f?Pa>a_n94eAIENkX~ipzK_&TYUVVj<=A+w|g}k3-Xo!ichIrfcUYvc9iNAwys%R5tmZw@@~z#XDd#U%CR#TT$8rWf~c88{5wQ}U#V5r zs<@U@sEmS{A|nTy0e5x7yYJXQe-^vkP<0TO`!R3(6zi;K`41-WRk$#0S~I=zCU`hf zGZ82JMzf%*XXb?C!tm7t-1LqNd#~%6cXwnVE@=&&ki~a;e@A9*YAt(uI1t3GfT#_t z0bb0M@JfUkMMffGpW}CmzY{Q~myCnM#v9P!;I)}yZ0@`w3C`%x*Ywsi)3x@;@}6ki zLZEu-6vy7cwLdy&%h&;I{inNl2wF(nM|#+f3%>#RG=Y$Z2$3rG2TuG*%SW+$+p?ww zaorj$4dcrK5o!@Mb~Zqmh@hR0G|?IE7HNCoqZ+L}#34ihDn+jQfsM&CfKvTP)EQ5XLWU2%fkv#Ckdf$f{Ug!KR}8C@fk7fe zNa$p6ch4sSBk8^dCxgFcAZ&n<{(TJeEcW@zq=u5{F4@UIlr_-obTY7-|1uBC+Qm=r z#})lTfD|wYt;{J0vYq7CVUqLbYt^AWxD^o+ zVAnajG)Mu~ff7p@X9(6s>B}@=b#I}0=hPAb6}uw_odUjS@Qx6}cM6!u9A7LfFH@$V zHZmy)DLAllo&_g0YOf8{)DvU!vkPGClZUA*Nd<`XIZ6yWTu@$OD+JO=pO*vek2wEQwjiQPM;R`=m_gq z*Ir89*1XSF+=&<3IvX9)iUWt~~e$secH z3v4|uC7-FRF5}SHbJe^C4in<y%p2?1qf@N?6+3#K3F zA560+Jzz2zJ-rzrOpa1^V%EP=V5RJQXX!yW5e^59 z7L{#eYRKnV4HoLPzR+MdW&Wd_p?aJ`*(|foQI3wqRs{m*lZ8sF80;-l(vVuC#IYW; zN1og}jEGUN0nb~>LaN2n$cI%do;25M_Vf=6OO{NdHPDeyM(7A+`L@V|o-z;gxhU2| z`fjS{Sy*D~jb7xiM%ST$r%(6LB~^VTMa%WGy9<9e0{+gzw{-xkKd<+lS{h-~j>lzd zX2_iyhxv5CP(3KOmhK2*f%g7Bw~Yo=*l$aoS;U_CAvnl#p}LlvtsW!VX3CVv&cO0p#Y2jc2n<&E`tu z-m$UO)zy517}^{X+SXy?$%8YE$v0z#db0$K7+Wco#*U2dxO;qJ*WEkrxo3QQVq*NR z;e0^sDAPp5V{*}jG6fR@-&+B=Fd*Wn6r%`$tj<%O?vatX#wny#pmK(%y(jhMv?$a$ zXdH-qdBK&OeFV)@W^Wp3W=$@g_IjR=MWA>0jq}!YQfRE7x$IA8_gNE4tHlk^s{9L^ zttc|L#gYXk_~bwRmd-`3`E@IWF;67eC7v>*Aq0uC`cZE@Z5nPG)diP-3v&-2N`cOu zCAsP6(HazpA26&*ZE%*GwhCHk4_dz2@Zw<^h7*%ktK%Lj`Nn2apKSrPRw4lZ)(kxq zp9ad)ktOabdx{Klod77gg6U(c;uG!kw)3i!2tkToYn@1h5Q<(SMufjhglo3ASgLZq zN#>Eo;PEva!RV9+R?T7T!OR+^Ww7izNeipw{j*kU35MPPe@0Gu5=9WZ6?~U@V50zL z2y+0jUMrPU&EtscP^AKUblc_;-STN6s9xt?cZ znC8+}jpM9rYMZgyfm;P)s7ag`2cAw5uVd(|&YwrVi1TH0mUffLf)IDOKT7SU{q% z1>S$87Lpg0*f>avr=Uc~4ax(;`#m4*Z`El>FAG{x%rszpJV|?cWaMyZezEBGlf@oK zE;^Go7WuhrtFT5cm7oAaw%1AviC=?4W@!!iM)VZ`D5NTd<=OedAmzetAb|)sgPQ~u zP!&ky+>D_W+vDM3ZJQ*ev2s5YK|?E9>D6|!(jlGM>00|W?4UO1Z>us;{;5a@@p%4W zgXd~=(pM|Gw$^m7Yg>5IWT^VxG#Q>U52b)J*4R>MuIJep3Km|j@z)xa_0re2p=y^f z$}6HKpA6+tp9jjnpW0IIv{y6f_Oj--vHCtRcyyx%VJr||6WQC=VA?);`iW{11z}Jy zzf=+m(Cb7}B(!-TO!q18 z3#K$OUQmHj7rP=(-8vWwWm1ffKjgzFqtmcJ1NF<4*Ch$JPCLmP+78m60Y7n=kfl@l& znFh3@_2T>t=XHZ5J~_ilKu5(_93wJQ) zKse`POe6F7;m6*!@1dhJhaY?F=*->&hhg;FeweQlHMVE=A9(nQ!~13q?6uyG?dOK} zLs^Crdv_n*Ex+$Yqx^PkdnQv_fE+_W&adFmkT0GtHJXiVv@@Bp7^Rj^Le1Cyy;DPa zU{(u-lcXwaWX-ouwdJ5ab=8*)be;=XfWl&Nh9-~&^kz!)ZiZzwxiZwYrq@w|G?f)? z5U52H_|?4$+4(3fk7wo*!|&&1S{eMuRHOs*S1a&|Z)# zR2v!%hB&X}+R*SYRXe60pA`)>Ycn#}UDo+JD$>q1riNf2h3*E^5}o4T{CvH(QY~ch zN)8BZIkn+G$K9* zSFG2NShIo^kgX1n?!?@tkKH@EgC-^4j*Mh?=Eui&#e0Ld=O-7o2XFUKP?Kj@Co07N_UR)D=XQeaL8K(UH<)1iL9xC-w@u_!=s*?s zpB&xLlR$-n)gFy(2qRN;+&>(hbLAzNLYJYHS(>1$tPBC|@|} z2tEnHpIl3sbGBwlfNOyK7f$Dq4|nD?%%8i>|4nf++>ibue`#i=-$;Z3|YUnFi>h&A8|gLKr-rzZ*8<)hXOkw?W4}ObuZN zK{EqWClbvNca3eGX=;1h!Q9l)@{qR+koMSC8RA3F`rBRfw|khGh|>Isoh@NlDJ~YP z^8me;Y)JT!C!g)eD@~#eZtZ1<&wk{Czj6`(C$5WLkmoPR^S)z+lG^X(O+=>&brw)x zF39s2}g@*Dwx(jJuPvM)ivH-Ob2CU@DUI0@*av*ch@MoI-ecj z)p;?mS4VZvM)5aw0E{)Yjzv6E@wxb@{wyQjy^Yl4`kTtP$*h$Yb*Hr1caI0KHgUjlTr`32Y{*>9S28&I#@G{_D zj>)C5QPVqNEiOVlTv<|l-x=2B|f3%2DYot3< zl&ZH%8cgNyBU~FOe-Hjd*+qnu@m-OZp3rpc<6OmT?deZ!zUZO@9IvfP#<>b@Gl+ZA&Rso$3hzFOolr3SGh ze~dP!bzR)Y1UzLPk}&9J?^yFmrMaGGV-fak?fcjop6{!#H{%U=rEMx!#M6DLiDT%# zN5j7wS(L7_A3NaxXG1X6YO&xqn1uRRGfh_BH+PQxUcmt0Q0uE5GN|1Z#HPp-v>C$noaByx=+Wi`c5sJOnx z6G4tVMG+J&D+}U(g`1lw zAjZOu6mUIiQCJ6O7&%pBWMp!9ta`3IiszvopfmObPhyh2NKug3lX#c(B$f`q!D&Lix<}3{%U|06#!5X$!~~_(58$ zsWx(Idln<#0h3uEEF9=2$!!uUpL*#ua0X$r_@*Op2hmSS&xHQyAA#h!dr_z?=20#y z2a!LTpNF@ed>S6MpYlh=qZ}S}#FJTqrkz}jSQBHsfsMnnY%O?D^e;@C+m9+B9G)aM zw>mI9%XC0YUid*{@uJ1Cb9H&Kiz5}*yM;4>Ajuss@LXWG+OTnf-NL$bf!zuwe7>+-eLQFV;|VBUx)~um zI?f!^8XKiYbM=B<9cNztI&IRNmhD6b(W~Q(I_n$#x=|H`quOSbgB2`Cl4Gt^&9UqQ zizx0$&*w-GF_sQgyI&OsZMz31= zn+aeDZ5*?3esB}7fHNfu^OEleThY(_|Yh8JPcDj zjy;rJP61cPivn9ib_lX9H;Z#iRlZY%E1kmfU4WMv1(3q2iGo5Zq)Dwk4W05Y5grYc zf06$5gic>|=Pl4_=^vH9ln4lrUHVD)h1oaL1Dh_oXb~25@?{9rF_8jw)@v1*<`Xq+rn$LO|qeT*6` zBN*sOG2O}-0I`HIFEy7d!^X=0vu{xNSgQCp>=dvmJ`>p#ZkWXD+K@nPQ_mN@;X=j+J$xcJ3(=w79_tap)S*b1DV)?x=B!h zB!g@&){)oY4-4cwbE?z;!7sg!rp5h{%;_Qg6m}n!dS1_6vX6)EymK^j zxJ5eB{jf6CF+^e|FsTr`hT0El1lR))G9R4PSkC1%mt>vda4!s(*WWu-}PT z*wBAlSgVr}(&pnoo-+GVfu}W@lp5@LMix!Y_qMv$;Crp<8>QhzTYxo+8}VDVgmazx}JaTk!d^lNZ<~YV+&{(68hBAsFBui{a1-(?;G(bwVS>VDadRk4QmzS8; z`~g`x$$8JJ_U{u``(d{?Yiaf2C;S5Bbr8FwxZPQ+F97}{BN5_h=p-F6h=SHz>{6!0 zcxdX7X$!}s%(2~&|9;>$B6k;kay!TOpFAy==7em>P zp^OHP4IM55E7pV_3HerVEoUW4?=t6xoc&0t*UWEcjkpug8u|vk?fu% zC$6^^PSIJ%oV=z<4FMm;T1K6UaNV3swtwub4un!qYion_2j8m6em6 zBdluQl&~6|Bdlr`jLbRW2We{~I$P_sph42&0J8`ioQlFsjLYV5fW{pl+(?n81B*_u zT4og%YgnFFYAc-Z_la4Uvs-jaT~{1sRSua!$QG?w9gH)p2t>n22o7MgrdLGjcPv%T z$=7hS)`ogby9H8xB7#&tGUq9CB`H%Be68WT?|tnXa+g3D__@gF;%VIt2IbYTnby6X zyd~mSUvIiFVFk|=O`fNu&NIf>1sp z<|(r;l_jtylv0B|&&bkp@9rBRtofwSSU+>QH4ZfmIf^an8Am*wezPGv79ogu>UD9b z89KJRT7YBTe8G6R&DZ7{`GS1S`pMx@vBzB1*k!7!IuMu_X4>W*<~OvER7D{aMQ>4_ zQ0+sqRYGqwK)7A@z#MhcsKJ!-=dWiGRTW5nY_(bsbnD&OJW+P5+FKJ=BR?Ojnzf*s zvQOUzKOdO`P{fG>X@o~*3%MXNwtPvdY$Dx)RI)&M*z5Qs&c;Yfx>(FL5HbnPkP|ml z(n!GD0Hq%#*B44B0#`}2Q$T(dBuv7I9Gn7n5Q?O=P?|%KvE>zr#8jRwm4(u>2%trA z7)uLeAYmUZm{Y3oHzFrsZUQ@~Qd^_PeDJs|B0WYM8S)Yp<#D?ZF{&^jPcw}*IAShC zh-O5#bwqFK04jqQVaFoC*GD7x>Z978GW*k62y2jOwb=8VEV{if6}+$}l~RNK%xP~L zSZYlvo%Z^fQLd*gV-3B>ioP+LgVQCv6BS>OPlhR|&jaQ6MRr(sx=M~sfg$#4>j`4- z@ncm5k`sHYb&LEa=ciN0_EljaZY?e~>F`-wkygJ3%pI$%t9g()@zt^WiIQXD^y4zw zYoqNcptgT7@NNHw<@(;lpcc$`STWz&aofE34zoNTPssM@_+(Z4Xu@j5WUXr7nXno$ zS*x10%9_cBA4Al!f@Ga8SEbX3#q@{=Dwb$Cprhy^CYRwd4YX=qfdL0Sg+QjWu0^H>O%R zp)SScCUO!3a;+7P!iwN3IidW^S?k}hZYEBu%5`(h-b)uK2+yHGu5%z>mVAjc8}*m%0j5}TUu~GR?W-9q=9?C~-&j@`UpK$1J@Rhg zD%J(QhIO3;8N^6a2#uiy4${*RV}OmcRTaUx2G_EuhX;|No-RHPo(_&@ZS!^}_TvD8jSjmft)nGUp<( z{s&KEETtxH70%D2?MAaU2R$a0tJX@;f6^_(`aG?()N;xI(GKq$JWl!G&Kz3LVj{zX z`OHy_&N!3FBm?r0O=@oKR)$Cz6jPdDMk68Y8C)BL9jVfSiZsh3n;0J#u_9KG)wbEN zZU>Gl*OH{bw+LkKb%8W@00ZnxqHc`Ni)m>Unu`aGuY5~>EKNngc(2E)d; zND&Bil=q!vJY{xngkD?l-dO!O2$#EI-`O-lc?nY_YeMox>+kXgeQBn-cE*U0IS(|02A z@`zimDhsN;mPS(=ZcNkuGp5$fv!-Jhn@{V-RtIXAw|5O=v+d2JD*w~}sbL$b-(&tK zwMLe|Rm3f!OJIud@1ClcAjxXUp4>NR4XKEsSI4YmKAd^NSj))nv9h$* zfK4PXBR!OAV=|?P$|y1h1J>9TnQfIS^J5egVhnOAQf<^HM2LuCmaDZn zMH)SDU%LqBq4#N*MH&{LOIQ+@nJCD`kyNiaNVXIoqgGj~)|R0`GNbsi!fT^YR@m*O~Te+N#m* z59-aJ;K1VUljmr~4UEoJ51ti`r?(au{b>o=|HLYriQ1c^Cuo~4~+fk(i5%GzLxKnKDpaJa$u&r3H*Xl4B1ocwmB))(X zkj1@TFE)@s$yQ=OLj^VieFrNVlox<#WQg z_drh@j_qD%!@aWyjJv~BGZ@z$zsYUTqM=HRYR#5EI&AUanGA(tJU&~i%;R1w{+wA` zAGIHkHzBta@pgR}LhbQ|dSUL&#QK@)dgeF+sLz}!O^vUgI8)6{tRujADW{9il!i}C zj%E}QJLmmqd|~nT834E2Rt~o!aaX;ta`s#Ci`9~650OZWEnfZz-~-@IE^78|fM-;u z;ipK&M;mwW@QKMmSP3baqf(CMGw>uFl)$jT2{_J_Sd&RrrKe4F`wo_J%_THh;FP99 zm1xz95Q2KED0V-2;)pzzax`LOFdasAJzZ9ta-TaV+Xwj)Jlz+f4f8e zRGLGcP^*!6=UVgHK;`(!ci+9gk>=#Drpa3bNW(dde(?;uJC7rdY7q@Xrd=NQp$w)Q z<#B<3-x8Cf{2+qSIV=uuC)NYva`auXMdowsXS$S}E!4q2!4209J3OC;q!)xa=l_ef z?~`*L{*6ljv&~y#EksG7)2({UZ%fH6&(?9b&1dGK#guZz8J$vtsTh8qXXTh>Q(l zi-Ca$^RY$pTJr0?q6@L>OMN3`eM?TMCC&5svqL917 zYrKQWocwmgc&%Tl)~UG zVwp;FSeGXf&@xXMaeqXqEg08?qh3#7wC0migFVkk8CF5Vhm$X=*$h2Y@{G+8qfQp` zv+jO~#-0wp?I@5NH)$9dYZSkSWpLd956rPUOu zKK2mM{c&MT9eecPzIvgt+-i)?R%){pV;|xN8&Z!VR2v7G9>Wb`x;fTBG?!+6Wq!f( zpc_g!C~N%_R{<1HMR3-=wQ;3AQ$_FGmuC6g_h|d;BW-s+6A0_&5oNth5t6py@?&QG z)wKDz;q%i`1(KgNtk#Lzwqe)zJO&p^!BLFf0G9y=PqTw*ZpY{jc$f-LPf%ZkWF=f9 z-&ASR3kIuG@WU9iT`fgea0KFORiLybiP(~ig#wsb;ckUP0ROKJ=W$Sm3l82)j0VzM3(Z36&gM>2>fPYZU?RUO7$NU2ew#g=n;fPucUlf# z!hal&;sG4IMuXFNZdAKXzX3+77n^l03e?qQ?1j@>`2G{w zPIM5xW0odgGJ*7efIvYt7n)0LzH@wn z75SD~d8a4}QA%~B6Q^8tlG9>AG~L4Ok)^a;eKr>~rJ$b%+WcXlJQAte6${vz=cQlM zD4_Z!6zDuAwOhTqq)7KDGto1^tyyiLGLT2jLrIs;CJHxAE9n8hGys{F?TZY*EA-SJ z>Hxs-sdI%jdd%mp3l9+Ecc29b-wvF<2l{fv-87pJWK{XxWyPJ*Vu{}2>Zq;3f)^gd zbly~LNyT~pin_KeKQh9h*+)i(ajAM>(edw zD%|TM|Ee}UjgTGM6byV34eE8=44XrEKM@8{9wiDZD~S6ChJpNla4oJ#WlR_9(veo2 zh@h-ZD`pL?z)yoVo9V+qxfrS172BCsy!>TND^$NeTA{vKoYWH%)07fkzMvJi3R=+- zFRVGl7R3bHdN6l=BVLd~W_Dj1c)9P<@cYw(TnLRvkEm_IU;~xAL*)|QHHtjSCj$rd zd7ykYH2`d~5VJgV9i$)6x^=}Kiy!^^*UDx$F#npFl4o7xS&Bt)ye#E=n5E1SOW8d? zk1M+f4dWLs_PCc?tuzRwfNw~u0bT8dtAmp#4U*?@TpLr4<0*s zL~{t}dr17(A|1wFlA=vQr}BUj@fTg+ayDR@7qk^o>^PXQu!QuCD950gNE$YyC7+B6z! zwt-&=o!u0kg~JapDS_W$RGR#m2>r0R)|}y5_-S^+X8JHt{-sFOc&_!z4S8k9SN;09 zmipG6Ynf7-YwhVD^{i>8(Hg)M9j7Y;Z=Tqts674DKxQfU3%x*CNx>a}JpCAU=!H$i z{uQZhD!p76pliHWQiHB%^TabM3;hkFGS$K{WeCpg$gz?@nC(l|98vxp_(x806#ima z?Z;Ks0G4y1U|^m@dIci2#Cud-K8v&mIWeYcWvaJ^_5kIj&+XWmLvRU^VF(e+bIlsO zbBj5o*seE}$Z+<+GLk|M^ilJu1tC1UNvRpVl1KkOn+Ruhp#N3 zh=O@`X_)Nzo5HK-TDTumZO+K|hr%n>8>oPbXAgy!$}l}4WZpb*RW zY`FDFj@5DYJI~4+iVqwLFPHH+YIW4V9IJ(Of>%Bst`ObKpzV`*L>>u>$vM-iSMYQd zf{)BlQW^S+?k>T&>T74iZ40$plP;86AK$$xyb8BCn~>ONPUGmid=_u6rpWOtGmu2s z-ian}7H^aVbcO_inYjugHDlq>qpYA`TnV!*vf9odrgE`z_T8Jq%u=DEA1?{7BQJv) zGNiT|s?a6jCG*AE)*{-w8X4Qky9_08vR^)XsQf#7F1qMj!mCSFg#DaBeT(}cQaQYqR-^$4Ey^KI^mHC$nr!}P01q>IQW2RCXhB`4(74p+;TXO ziM?D>0XrsarEp5ulX$2 ze&Jb=o97)ID44aCES(H%^6{rDN%Xx2znBf+e(6kqdJumQ?A*a&YP}YtVsxp)1-{aa zHJg==lFr~TXVX<(w&4wL8l9VudKTJ_7UW>qk3t!x+BvorK+IgSCwC3+?Lgwwa4&vN**IXD7`SUen#(y`iT(dYwpBMnoFG#?jqp zJ`K{j=YM5R{ZX6eU^Sjca8QktJBKOg3T!v;5dK|x34Qj4yUV-4aC-TNZ&m(HHhYUb zD1=SZ>LQC5`)^TiUN4Hf=^p2}A8ephdG&BU{RfqOtQ0O_W)ydNv#_Z54+j2T8UuFE zCB7!UB*yUmy?2ginghg$C3Arm;`e#LFT~OLK#_QI0q{6+iMUAkRX~n-hj^PfQ`fz;y0oY1MIz&0S<5{*&@GtX#xGd|OtxC^dny_5V=7H&So+v!617IA#A z-|fq5(rK&5FhLX-UC7oDBV2HcyMHN;^>PHx?K>Jh@lVW>DH7L znBNVX+x-MqHR8s8;2N>%Dd0XJZ07jzKq8&#y|eQ06)VO1us|&_Mw}y#CxD~G8^miw zV?R(&Y|Q|hi5nhp4Jd@w>Di=Zla5UqHtE--U6XE2nlQ97M9ErF1FT($#s0WJ|~ABa$s0q&LZy-eM$M8lgAImfmF~TUtqPk}aKKBwI=> zL?m1KxCW7I>3+JDZ0SLIlWgfaBiYiC7$VuyWxAAXX;u>=+0qMiDcRC1bSc@=YI>7w zDalB-w2>|)TiQ>Tk}d6|OUai0pi9Y??xIV{mJZXUWJ_<-rDRKA(WPWd7gi#YE&bGi zNVaro4I}RvZWCwWlPKG zQnICW^d{PpS7g+=8`#O@cZ|9S8O>!zGMcmW9U6_dhrZ+Q13qGMAswX1q`V}?-SAxOxcqm65FHPbOtOO%QZs zJ>!gIJtyctvK~%?8d(qDD3bMfykAfV>!uDub$+f(WFq6_z&Fa_B|~|+Xlyk#Ct41J zatuZJPJU%vt3?;h$gC_~J#CBCf4kc1@cZaPUIgdPaeL0U+IB&0x!bV3n91SuQ2 z6p?RZMiEgERIn>uL=>c{D5Cg3_s-7j%w~2Uzu({U;{W2|1)I5Z&*zkT&bf7F z4$evW?5|MmtVYjO@7DJ4^7HSSS5wr%6dm2Uc3f?Bjmer68*jFicx86b%S-Bun~bV2 z_FkkcoL4`)enx#{aU*5<-iKbj8lk~9zG(|hPGyBHrfEtOfm~jeyu2x=sB}`>h1P!9 zw5Rw-XItF{PQ1vnU1&DN_OtIUoQBB62PlHi$$GvxvN)>Pzcj`6vEN-&KlI2W#i&?Q z9ND)xx^HcMv2KyBs%UIcRZ&GjQN69+_J#i@JObG!Mn$$>)EMs6R+ZG3jsmLM;ri47vi%&gNoN=C?_;R^Am?3j*cTc1 zUJFe`_+4ZR4a>zJQC(tuP70C_5v#t7$kN|YfNl|rs|QX{`Oc{JHbXdvfkpH1-|;O0 zd#FfoLsU&F`O#(xY`yoTR>cT6!DM0?YHo{+C`Qd}%OX0UCbp9iL#6VLZF->Aj`G88 z!ld%Q+vK7YNBPRO5m3&=xY?G&TI?|8AWCNo&g_e8FM% z*DY<(H87*a_NY|{rMBkQIrN7%=}9Yx&x#mDBC3F4j_<59Xqf)IhB_!ePORXiVdl4; zkLU1@)Jr3br9TKhBsst)usXP#{o1F7QsfgsfnLbk){)3J>z z7US*kwL%eKwrzSwtN?&#Ye;8|jke1fUEII~+WK`Y#5)<37^6-o4UN%2uZu#oGod8R zKApZ+#Z1X;gHO1{yR*&ELW1}>GZg-2UJ}}wLlbP#oy+i#8k={Q4!%E7t)sK6ywM|~ zWi+g{ZTCC3*F6x-cVA<(WThDfFHrmQ@f|B!hX;_0e54t zzACUzP9VVV{ISz9*UPJw2|{s zY6C*w8D+K|=)+6OeBGxP!Y?yr=ugkS-Hk7+XtSYjKYT#JW_Xwo_WPLb=009GK*h+8O)o(Q;`!Z``}R|1-#VUqy%B1FZ<# zPCp*w=jal$k9;Ok-`Cm>4jhEx2mFctqz-yg73EG%Gz#&6l0G=vi6S)Yy1{E*i)x32 zs-nL?aH;*o`S3O~VidgyIkNh6lK$2Fo^tc~sVFdllqzlNRink3w) z1>AH)A-#aa%))bT(C`xo&ut_R^2^~^4D!N8LXh_uNsKlJoj6nihqT=pnTejK()x-P zz1vG7w%Mvi%|JHW?NP2wQ%BE4c%OnPo+!~dnC=Z46M@isfNnAPtaQC=Tb4Hqf7XaK z7W^dVryD<05%8(}Ht4FtoW4$|&l)kOL!W_&mO$AJg^6s#3r^sF6vBodbQNds{K6Py zY}&YC4m(y9hXWhSbC~t2MBUVuI5tC-Y~I*5xSe~l8)K7EQ=4~zMK41uwB?QaOV^(Y z;a~b#W5Ej+74xW%ZDnzWE?2lQsxf3~v+dCm-q6P(uaK!zN88CK$%wQ4IeHt}mV&(T z_{P*PjE>|#AVDMgMIW1GzVF^9)f`C-s)BLv9}`Al<8c)gimS8n8OC1h zBj#+CXpc80yFz$hn^(<9bet-Jk2kh0tQn+=M2&INJ(6uy?HCC}NEi2N3)~`cO{goW z%4GZMiLNe4gD1V~Qqq6&DwmR0Q`Wka+@C^RN{&x$>sF#{4-!>Qn+!1x^Xo{CrxNo*yT9j@Gr593v6uo#j!W|V%d~}UOTZMWF{m~E4Huvf$ zfb<0ri!F5tuLQF7Uvd(URNz>LHo%#+wBA_e;4kmjc5fboY5~~UuVu}Yh|6prEGxie zUL>rq!D1V|oO9t^yZk18R>66|OA;|?zy>MDY-cpa7aFoA7o+%=wg)7LyuU!-9R7$z zFDnGeKPh3oU@Kgiss>`)wQ@Cj!#&wEs~%S+`+b!aopMiBy1Gb}?DFbpbkRLo&YFq% z1uxoDt5W~ACJFuSp1SP$Qx0nQA(vM2&25v{E|wLcOs%i2(+f*wMQoPkwQh}T(b;v+ zP!P5@F=xFA$LYw#7;Ltk-N2(4Y!}yemhPr+sK8l@yVo|bMbugax5|66)&VMNY8LM>- z6DDQ&EMpkrn8uVjeM2OGB`t5;l9!`wPraN7j2Qo)UuOL2^w(zCVni)$VOzpb2&tHY zTG_^K8K>Jzx%rpw207?J@~N@%2nx%Fs;?e^J;=%)+o_%iBzM z{cOH=Z&jQWdmB8%gOuy-aSoCEoQ9J}N|XIh;ClA}iupIR91WRf2dE1Q$=`fnt8p9G zFdjso*r$M=kkja zkMYv-oasn+UtxJJTh5fXQJct0nmS|`rl@ZndDs{i@p7YVEOx5PGq2d&@=>IH? zX?A_W;ikNhfOo!SZ3K<@|6kPkKS>Kx#z#0if1wjL?1Z%y3GBCeiN%oX1N6J z=bkL^+jgpC)Y&(=Cp-1+L{&2C>~{BLXU+~)B@-=t!aeER=SJXKJH5@{GP&Df2Rw~G{i7pLr_{tt!XplF+-FA}I#0L1{`?+3E z7?{u3*z&HzVxFQAU%C1Qo}<9vZb`jI{=#%L?Bh)mpuG!?jTeziMEX zf}hquz2>|UqTKs>ds+l>8Q5AzNioIAqix~!dVG?JBCc6kVNUJXuvl%o^T4=w)(sd@ zo^?>kr+f}yM&HZrmvu`bKWngs-0B*tLhAHHVJL|Ha1U|*mPwU6bwkdE?nrK^6>&WhTC>UkAM|<;bPgNnP z%7fgKt^B15gUxB^z>oRYVl@zQItrO#r^>AbTK=|CjSd#B14&sM6p7}#ryX>!qeB8e zRV&y&yf+7}c2B?L_wN6LyEu%u-91MCKb`^^gp~&FK4)01@b|F$lkt0x((o1ieSp80 z+~0j|f8DS1`tng0yq^P`7~7$tjRNyCoV65yC;$8cf2RPfDs)!ed*?xSWc-DqDLXl` zK1d&E%l|tD{Uujr&NCA2FOS+j`MZr8t<)5_X;b-JPD%XC!_DXyTj%Q*y{w!@w6AUM zKYPj21BM7=WYdO%QUAae1}t{JPdcTFeC`_Rp-Pv9&_>+VEggx#C{2wJd?JV}#;6z% zbx)k6LCH9>Da~bMod)sBRwZ@~x{W8m>b`T|b@?92lB*4DBtmW^ARRF_LNj!Wsowsj z&opIul^kq@c(j0g*a&^3d(Q9(>>9#9vZ^tfZCusRLe%_pCQYs&6epT!)7KKaRb)pK z)C#X^N+S`iBKMl0990}Tgm_1xvjXKyFO;E5M+Z8m-P3K+p+pCF_+ecE@#oaB$nBB5 zFIlpm563?IClx$bTI_Joip}qD58*0`zzp&I;nd$V>2~biNa>&&!%VvDpHu|OkYVu z2k&2+p;wHx?s(5+yhTU6Tq{x6k}w}spi0QbJ)uX|l|SE}~Zy zQr~@E;>)D2GQOcA@Q^q(j4W-2wB(96iWZ#>AC+j|Xhtshp#k^}#ye1UM`1VnG=JoU z$VG2Js&9r;MA!1UE+IK=cQpX5Fy3e=3LD1$rf9ZsA5Qek8_kG!bCj({NGh76eB?z= zH+MRvlJZWDAr9XV6p-CfC_oklp^tEww>)K8QziZjn#xkv(O^hf9lcq~O7|90)`S+2 zvQo+P7HE<&o8EHiUT7949|t-URM#;Qcs7~T5~ZSSvb!ZpH>5hKg%}RIA5I<%fjyy* zuQ##f-VdM`t#BEWQ#A5``4UvB{cs4niHy@5iXf&*G*4lw{2dbUbZ^$fsnOE7U&-i1 zzn0UHhheB!s0v-fxPR3>$dPbl!5{<8($h&`E3{5c4RWFtNN*R*p!}AWCPfq9%Q1& zVxUDk2O-$%cDkFw(aFweREqO_(i}}QX_f9O>c?rdH30ImI!Qtf%v@u(vUP5lgp>=qP4?9>D z;Jl$w$^KP)v;*PY3K{lHlu#TpT(h8I#=|Nyz)_#k=!C+qM^;MIhkeMQ#V7{DFPx-F zb5Xw}9+?pSjyivZM zixVa4Xj0h$jmObO*7xbt8Zc)kar!8j`;3&xfjK+T*(d|`N5+wExECq7htHMBN0Og9 zLLO3~6HbFoW`trW$_b5%Va!M)OKT%ZX(kL?+``%ZH5~DtsSU9$J>qMSF?A?QhGwDP zb=!qjdzH0XV1!dAMca{eUC?HHKw&=XE0X>q;+C#xuJL$7>j_pkqYyjmv_yW~NIvL> zMq~J;JIw*kJ4zuYbVpn8b%hWE{*X{aA*S^}U37m7YCRCt$`3U--AwQ-=92cNJ<&)6 z(+lt3NIJGz)m>JZxdr*C7qWN-`?3INPAmf8-_UisjoeG7}8;U#h0zTT=6Aihofz>OS*$gdXGTkjaM9U$`;XtQ}_Q+ zotX`Cq|-GvNF1%Pu7k?OKBOMo#l>(y!ENvEcQvG(ISka{p4BG z8r)QD)=zzf#vhx9h%Viad1wbecC02VOIAzXDt+_Olenh>aX^WzF53>VCl;WQ7>50w zhoe^T^Li0l;<)k~M)|PpEF1EWnPbr)T;V6*C&^zb!HP6=d6(plLn&m)IMmgFh==(J zqlZt&p+uutRc`Mk&l#feLIy4kg=FC5sbciB42)T}R|#4wD`O4nQ;PPvl&u(#!axAp z00x=BqGhYcqrdPwe)KHGH2fa?!Z`{OQjT~iw6`lquORq?5tljz0%F#4wyi`z>23(k z@)OX)Ap?>*0cd~lBRLb$EaM-NDW#DTI}DEel<{QFjc#^bkRS^UeDCJSHVOJ2l>kfN^{OjC_j*}0vITjR--n$7=Pw9(f+L8K3)wjsDL7us?iCYqJY{M z(@gY02b7@}wbo?|P(1~x(ptnfS3o%j`irKJOU(=|N$eA76!CfjLSTr3!I7!14E}rq zy=ELs87RjELf=xUu-BOl67^Vrc7l=QPKHcBmh_*6Ead0OLJP1aGE9N&%8rCg*F7i5 zZ}Vqk91=7YacHSMVk!*Kj2l!~U!8{9;8z%H(JQZfAhF&+a;Brsp(=z1wJI$KNf{#=;1snFTzsmfGFCyukQj4puuoX1D15t1`cq9okMJ;z@2VAiU_ z(X|nSajtt1!&7JjZW%xoV(pACx_cp#)t(umJ^vked-J!QLy!ewGPJ) z)PVr<$1`Y*8YPqWa}R_+FG3yN5DI5Hu6ZD4bDaZ%mLbnFB}ltxQ368tG0&neHRw@t zn7}9|b2F?!jaZI?boxN1xh{~PWBL&C{BjiH+k}=yXNMO_3TXq$C4Y@Sxw0I!(_w*R zO9086sSPIaHgpNc1+v3-qdf+t+Ai))8QdU+p&HgJvHHi4uqh=a9ji0s(MdIfIOhZy`s6)Z5FyIkUGfv8+ewdby|s6*V&Ys(Qov^{6*AV%TQXTGbIEnp1Zc9U;Ww z&~qM>1PiBJ1(P5$c>{t6P{<1#&@zKHDL%y-Z?PsNCZ!~k^o=M5^&+(!VToe^S>~@v z_w7t6qqAjL9h6=h{Jh3^8mUB?_FKuEEehD=~XtjHz5QS0d97fr=Rx(Px(a&rQRC{Gs-nE|`qCW7RbgdqO?~NO^vcg1XSP_9lPs1bOR_mRF+Mdh z)tbcB*UqRf9RL*;ROjcF4un5S2hslq)Bhy&p>Xwd=`i?z0jsZQ2buUgSUUv3zC_rE z$X9HNdXG(!yaf&Q`V^oc#V33umgMGR4Oyf+)1M1vF1J zGv29SqJ*SWT55*7$;r$x=2TE2nUz{nl9E$X5(QN(sbDZ>4J%Z!rZP0p9|#>Xr&v=H z1^tph=OiXvQc|4-M2=?|Nr|ZmU<9UNGN_o!#4snMfXP{@CBd9%jb}_~{Fnt~vjr+A zGlWF5IVs-ESX&c;bv%TvOc85hauS%fj zDT(o@OSXXX2sO;$IhKSJhG9ueuz(4eMDYpnAT9ed$qF_XFyg@}9UhvPkYW`K2lh!c zCkhbYE#{05p|O)v&2@sijo>AzmQ;spSiy0usew!5E-Osx@KMe~`-cZgaUTBi>id#MYM+Nz^{H)p?a?hs}Kcb(9F>r_QgVVYnX<(*f+Rw}3d2eEB*mQqiVO!}(<+h5;xb*&Ie?;ZU66bL`I(PV955x4{RdElD&cKPxZFMAh&ND) zix7Xmf!4SboqiKm_?enPB;zgA8QYb*zD3Iu`e(`rQxh>?02$8!X+B+aI_Y+x-(HAKQt;n7d;n zCVx4s4vhYHd(%bs5hg3-%S3Z>3UpBrEAgpyX6Qm8giP^qRx{++RLDwDDLEeEjdpag z7O0d29Yjj%C~iRdD`$>_BuFDS!Ag@ws@dYaoinf-+^3n=YDs`TDFt$5 z0^o6jir_UoB5@LAHS@?sNF?!)BZYe+CG=#_%_Kl7NKK(V*8jptOJ-sJU^?P;9cld) zq&Dci&Ps#qTRwy_H0~PA!ZH;vkeaJ=u;3FgNpTr*stx_^v8Pb17Cr9XKZXR${X?7t z`s|b#4s=MboCJ0b7A7T`XV7(A8%(@Ia1iP7DaybzL1vl_(m#i6P)m+{il#sXmPu;K zn9tBqS{;^0o0Bu2p%lDES-t1yD92Hq)?=%%AAOE$X&Ho%KKu(wu+H|`U%*^l_aRsW z#-qoBiKVHbtseGr9P0|lg6(&{1n&4t#vXpi(r;kZ-g(L3Yrlo)RFwIW^s}g5S!N`< zbFdt*sAnYKo`Ya_DcgA-G7Iq9{ffatdS8I;gJZ$MeqreaG!&s0dJMN{!7@d!%aAF6ls*?}FS(3vA(SDIW{??IP`OV=3zvL3ocwhKWueD} zT91)}?@>H{jG{$0Db0Y_k1UENX|4DW^8NS7+vs@WB-3fI45GV=(wtnFNHeaYwJt>i ze}L6}NfuTs_!^4E8G_(buR+TnBhWg&_SM&r2I86CRn4AiD~Vvet3)Ql8L;~AFpvO8y$e> zyOxCnD(bN%HAL@Fp&@PrLqqhm z{}GG>Fm&9_Lg0;T`EZZ+sk1`i-s5C*2<}Du^bkB6KcT#}C=|bl9}gv$I%-?l2bpj% zf{GKuaJr!m< zh=JJfA=_i{Y)2h>lexmUSiHuyEG-V)!^cF03D_j#Lir1g<7u>SZI7RBga?_(oexke z)ur72Ci!qK$FXX;CsER;uanci8SY0q7Z!VyNr^Zl$g$AqT#8(zEzGOQgY``^I|Rqo7CnFeZln_E|wz` z8;{#p4#o=*-eID<^M)fMrDliw%-gGm;xqUI!Ocn8Fi5HIne0=B;bjPY$vhl?X(Hy~ zc$@5!IkVpgoM`;g;XLw8z{2vbNuCKln=A1JwBsXiM^(z8kB4I;iy`GYE(MX)> zDoCSI&=G&hA}CN+`#q;$LwcJ&3ZKMn!{q7h@+*>1@0o;SFt3ir#F!i=gq~cd!MQjI z`eTJ;cTY?7$zd$LsZll_1C#?9rPLqGDanj6xKfoTwIdukpgh$nOY?9p2G(~*S;${` zn1hxR+B7&H-_@M0Vs&WtU) z!Hn%|zgmWyA!CLLuC4-byDM;8J8?6}gbMsE&S1D?MkVI;a;te*a(c58TR2=4?%q=Q z;c`nAIXWS0g``xjL)`yv%}F&;lS5PS(~pW>hBN*9k+Nx!X8Mq|({P@4Ty0Jl5(}FF zjZ-Yu`9rJ7Cz~~)_8!ymOVc{b7ky-1)_=IuW_0X$%CwzA4wvFUmyNdEaJ4iJ&cYUF zTi(a};FNc`5X^u6iFvObU^D8^9$F^h0bat{Pd3s#%lSR`T3hr8{m0%a4QB=XOOJVI zvUe3tR_ti90dGl7cIf}9$=vOB+S9x>5sfU4X8SKqEtB#axv6n_b7Go`1IW@4uBprB z@(yPHAp5KUO6|Ue%pv?%? zbfRUHc1Nf{%NBw@3e}9z;4*=>jPz}#dD(FVKLTxBYt1T`vK8>IV3#8DNrYyNqYRbV zm$uOuk!zK+Z8h;wCaC@@Roy~XM{0OfMm9%kdKk;7-IOc#^h6dqNUJ)#u`;JU%Sd&U zX0U^gpOapGG?cxg`U?*b3!^nt)Od@B+|ZAVSbCkQoPR6w(?~;Wj{?v`N9YlfXVFLx z(#R3W6ET{_6oB@AvKx&^=UC0Vx;CwuFSTwh_)--YAodSo_D*q{Y>cg~nbTOw4zniL zXr=X)He>>HRR~bygt3wh7R@LJ3j7F-o@|BI6p+O-J0GvhUprYqN^-k2V z*22s>Fj0f?WG11{WLMFKlfKEC99Rkf+eA5*6h{zqqGm+%dgqJZv!^;?C$|=!9)e#M z6BAQlz6BR-apeVy6GKd?nr3J+u-BA3IMW)e`j@GiwJv4$?Hyn(-KCKHou+x8mO+~s zWb8pJ7IFR=nskIeZA}Js)C@r9nQ48`QuU&=`e^nNOAn2eWaMag>i|mcn3ev^{f4PInkHJjFv9)dV19&r za3Bt&mJgG{#`k{hVR=h?MZHq)&%2TjF)&IS} zy2tu`4CFnK6XGvW#zbLW@Q?_XXwj z6Uy7lkEvTPICUpsRT_9Au~K8v)d?1w(Uv8FXDS;&y;!L^gP&1A4Txp`f7qE zR<~AwS|dPpoY(+r$VAO_yj1~JHBAZijP6YVd{)%O82#Z_hno5ieJ*cM#H%nt9y;66o0S4+7l4uqM@-?^P}-MhYV7Jh7A#VuK%IJ zS&np+h<_8DMTL$z3-*qbdzpfeu;=!FYs+2$5#WSWHuRQBn!6~P?5@#B@3S~lB(Zn2 z&fk+Y?;ATrHgI$sytj(%s?lg|)lt&h4=yi~$U8&|PZy|=l9^LA6?g~}UvyA8C5fG; z`5bqMWEoI)Lm|Dr&vZ=^LX`^f@9vfO>&fXEnzy_bQORM!h*lFG)FW@rguZn?`Cz7I zD>*tvyoGl{-p^~Y)p_f$yo`kK)3d;KCL;gdrYX66GiiLTmA*9R<`}0 zg&JOC9O0_Txz?oRvzm8sp`eLlC^X1PIfArUqS=Q>M6p4_2y$-;3_nLi5sMC6$cd#I zPM__-{2$gRnk>@{_Qs2&+z${JM#%?=;)$jF_arUmJ30NQTNs`;9pK(D4nOk9psLy; zQ+`oRUI)_%Ym7bnMGe9o#Dyj4m^C}Zt-2BgIB+tjbPg<-z=p(=WWz%3=oTrKTua=9 zigEST)vCJ`!ZH;;x{SOq4a3=*&6;iv7OU*ASe3pkyT10hM;xy&aze=#tp3y8hq{7B z((Z%I${V88b|2dpnmWP*`cz4qp?IY8*b1{A(aC;C%8gY@LpxvhlmPf710>l!wY;GL)F84XTdN}ndunIk}cCBj}>8D-nS~jYG!+P-pv}wSLdEfd0S{{S5vs8O%fc77qPdnBI&DsgifZiIY z<&eSt=RmC;kt;b`Z&G-hv%mxX{YPk{$idrO0GZQI>qmMG(c0+!WMUkuohQ^Zh2Wm3 zE3L^MaM54+TT(xSv>&EzMOydQrjlodX;%qF+tI95Q@Sp#2cR zi5N$1{U6R6L5zlQMNZ{96lvdslfY8#Kb^I$0tZKO#1g)Vl`Lhhd zVn3@+%;ip_jwuI^`BbQQy9hVtoq~SCY8$l9lKJiES0Kro722lMyIBlgsL-C&J)leE!F8_*}W#QY$CRBf|j@5a~O>dRQ}zn7I}Yy_In&0>we4< z7%LyMh>KddPfIb)`o*d(YJrsOq0r@3+RZpQmaU57%vjQYjlsfKOT@|K<7((5lVh3f zThwTIy<7FN$un72XMqA=p498<`jf$$ODy!-j zH7cseD=(^F#P=$nP+3*eO(<<#^h91+ZBhNOUQHf(gd0;4~DM>XOO|lO@g?$8luR zByCDv2UA`(S5ol=oB%Hw2j68aG?i4CMp#D0m}-iPOnJ36#g$dnrpmE!SyFAHM@g!S zYD`5H<4P)u;47zvraZ2qvLcouRMnK^mjRc&s**hVM|f5^fLGU+)1&D%#d$TRs=R`d zyfRaDQQ6qo>Y{N~MdRx7YN$lTc@$_uWpznS$rDAUlJW_81vMsmqq4TT$TXp?c0|Z6_(VN z#}!nTx6drBEGVg{$paq&H)u~Ay}Blr635DjV=b2WqWGe*V-pkdQaW-RG_I*wTWKIjc{_>exd4jvQ{fJ~9)kUSt^6j1fx zcy5`gEU&sIs(#oC*bMJd1lNp?wuJj+MoU6G95ERRzyb!41s@umdGSV6Etl9cY1RZ3|Q zq_m{PTgy%CUpy7u^q7z_*?~Bk#YFZAmhudWQErj}L`Eqg5*dVpBq=G)9A6IWG+I-X z$X!`INu~PKT5U)Rse1je-SDJA_Y%mIP?yR&lWcoJn^q^P+&(uK9_y*e&5fHdrGq6g znIgu}^vtR!mFMP;gUNSIO;v6#D@iDiqIuML|rINV=H- zt(4)ghC^A4HK9D5)~2mWo0%5KEaiGjsM|qq4~sdKi9j2pyn39Bn`rr(qRBOrs`4fT zkEjz|2^xiYM0sIRAvkHIjCXjrz(T>nVwNjOMHHIeWPZ&zWQ$$RqQzbf`N-0KB z4WxLHMsl{4@^NLA`FUk5my}0Fji8PXkC+b2gFzKjk4ZU59ClHE>R_Uyt^dS*)V$~a z23u^@_eGD!KY1+4}H*c*;&Zm@bb$HP>1r(!BAPQtUUNmJQv9w*`5 zXKTCYJ`vUnK4R+y83USzh!c4Eg!|vE8myS3eHCB!AnyfLdGnJbo@YJE`|><(f88T- zY<=S)Ks}{R`)}-8`4p^|!ec6Vv$X1O2WlFpwze_nNl8q7oTs&ol)^?+yv%}_ab($S zaDkr+8~r!SF!sozMm;b*`sh~FPO74AJR^yk?nzYprn6p^uv!u)Jp2}S-m487MEhj=e-7ql~!EvibB&G)+xT=6)DysuU_yn!6SGLfVhiZS+o*+sI>T^S2%jH zK_z-B!ciw3*&Ey@WtY5uqW9_d$DLMa6GRqFOwOI;Jgm0v_id$xk8zao(jY|kE@#RJ>3CB#Rg{yRnbL~%=+;He%InWU;nIByc2q(-htXUEI& z#MYM`Gy9iIvvxxQ2d6=w_aM?LRgtV#Nu(8Wk;J#$LB~Z;;*(kHxO2Mq1UGoMy|BW( zXg$Z{L+$OW)^pKFcV4)8mfdWtpC#db-QNDs1`eJ>{)xGdVUXe$yx93s_<|rMRvwhH z9V>!Io6Yh)#vxA1`|Ziy&0G?`FSO+FmpMM*YX=BBY~g$_1iAAvS4moK=bDhaFLTpz zu$k@wif?Yue_1A|uvc_?3%3HdGYbi6?p7`wCz#oTr-rJJq{?vr%2qDY*v{NQa^dBw zJr$xWDYw4D?FSCj3FVkyw-*H1`zlwiE1ZRY$Y z2`GXk?ch4=W(#0-0@$t{u3+SY9o!YXSb?>%OPJ`bB39E~oJF@zz*;L{P1)4|YuPUD zGJaKob!3?wi=E*AVmB9njc+zIpN)R==cvMZXZB0vZ<@)R*SOJYg!F4ALBz0+>xsYg zKu-376TE3=N16dG^>waF744nZxqkQ;4?z9w+(I=<>HK|TvU@Wpea%OyMCE>NsvF`= zc;wtY;miZva8*M3#k3d?gynB=XQ|%w{J^v~A#|Zt+3wMrH@R!N0T$+N{VZ$;SARh= zc#ee}e2c5_8Y5H~O*zDnG2`@&1LT#2C}5#ypZPYo93G;u$m8s8<8aZN0Fj+WuRh2% zhtH`{T$j)nzqU6|p$?9dAf`h{aF~1D4Ke+mirj!oLir)5=@w>=w~v51KrCjCb4R#( z-P?k;Z(4*@xBgwIu-`(qzsqei9#@q(6P-~o^&Kopd)z{99_6;-;{vyn?{R$d{SFY9 zWVHysuGGvBL$(hv_>j0`;HlRYW(=P$p@KN<46osRZkq9dicHiYw50QEP8YPkC{aJK zkd_~CG5CQX)3gsDj1@B3Z69!21Utjt2RZ3A|5+y_0FnKl$GIG@_EzRSv6P#z={)O% zDIIOnDjZxakL3o8;w87?e`ihR4Sy1 z!qGj$oUsyKp4FaviW`P;m6e5hm6e?PnCot=qEs&awtMp!^rXU4Pdb5s@T*U_9Woqt zz~bO(ZjEc1?F_fpwXEb*j<}Yke#XVpGMfKoobs$fVC?^l8;Z0v`H`gD0)73x>FECGEc9HpwoTK3?B)b7>h( z4{v`f5VJ&m?ptmQ!uohN9k8WusK9>kH@t_zQ13Jn+-`K9>xlHk@+sGf)-E~EZIfNH zGe(bHfW+Xe!uSSVaYOpCmUrXjBcA%jl0O6CqMx}rG90F7kDJ_9 zw_q1MfUzfh093HnEpS}87<`+{#P=vwBs-=<%UFf$x4C_;tiQg)y$Tg*D+S5~UGLCL z=nFo&%XLM#d4jwz*!Y^H)%tj$No#-Qjw54Kg1S+x3DhX!_iy)nE0K!??EANgWOqH^ zoTUEFwIqJO1KTLF;SM-sR065{o%=|3$y9pk5AH=-Sy%}if-AVs4N;SVoV?Ga;4w@L z@pPU-4AT8iE?b7iI2`|z+ex|8St)t-0pu@H-4hSEH<58pLv_i@zqxe$jDpdAr@nI% zi2p-wfGQ;u@dXc*zdht)&>X=g0Mz3jZj2g`4YDDA!#&Qvk^C`)=OnOpm&vAV_cF|D z;ZZY1yC1==#cVGc;!_Quhm7B;7@|ib{vy7i5aUdgME_j^DQV2dsZvrykSFhQ@HxV$ z5V5tCw5^-)6X0!6%sl|=jVAnbH7NQ7A`VWJN2C(xLoa>;{*IY~lZgSil*R}DOLH;ZW{X`?p#Vc zoeku>gP~b-%kDsXSr^2g$8kv%lk5!U zd8I3m_k;O+s6Tdm_;0!0L+VDB}S`yiP(-75| zy|}O)eQ{ws#Z$&gN^DEBVcbm!2V060;!z$ire_NhBYpiqs*E ze*xY*x6H&#Q(Gm>i&1>ED&@r}eli>ac2BuF8d7=#L%`!V-$wKApbj1=<&!$6VVNTF zF?=oc$2@;Mp{qa7K!}7f=EOrSmWbNf8E-i_>8U0n)Mjv@M%Lsg{_J zPO8!KJaVM#j^&sGR=)CmNHJ38}E%5Yd*jnCpo`7{6XKBe^~JEHz3S6(6O_o7;mCM)h>Ze~_WG z2Nd=Yv5F1I?k4(7+>WsiISFS0q2p7q7aW~+xS`p6Ao0)UTe}*iI-75=rW)Co&8OfV z9&~Hpn;)V|>HISLa1Z42OyJT`#eHB10cCV5DpP2*!_|cx|7{%G* zA1t;Um#t*NB{K)w(BQZtc{ z2f`?3bc!J1t%3YmbXBN#HI>{M#6Rh{^t&p_Eq^)9j=}sO{Fg$2Mo!5AqU#VoF5O8h zeW=g5FH?HYAH;)iHx+v?LM8R{>SxzGU((dHgFHl(&^L$hBaJH1WYkbT8i#qHJU*0f zBU6*bc;qk`9$Xb{a$uNX6E@%ZdKe^6W0wvMnvKl@`Y70NPTjk7AhSn8>vZYBa=r?^ z@ZGWk4*falZsHXkl5x=&KnIuxLKOq{gvKjDS{4F@Gc2@a}gh_ zD(K^Nd>n4)0d2@wzQz?zGma;&WuK1YJF9YNTMQifdEh{b`9c{Qtg|u8&>Zx3i7W@5 zE8*WYR;4uvH#Vll(-a*1obgtbMiR&K%T+0vyFKfHa%34Sk5r|xg!ogLAPgH@apn9O zyeCZ1ZBoPp0J#o zBF7~;oey~|vW9P^3eCbh%>%T2Byd=0y|h|ry`5>oQq_oBJ{9AE>1={MFrBVwKXP=Zw>T9yW9crb%Bj6roCfRsiS`cV3{0}Q5Sf%w>bzPYN5)8@mP z?rIOvKg{PV0EXoU5$)Lp{3%*SJEp}?3)zJA1>2wIH|dTG`n;bZ?Cs53$n$YWp$w)L z|Mra58w>djjq$e`?vLtyl_5W>Cm!9k&Xc;I&ok7{m>$ib&(FeJJnQ*k*!Vk@R5{UL zBi2Vc%2R#THVO3i3{p;DdGz-TW)HaZTgh*hUBce2{F1%&|L`hU{B%;V_E@-@&rMfh zFG~lpjX^lanBVF$=1*nZ&Ag7} z&vksgaRt4nY!k9!J>LeeQ^+vrQ>jr_bhMqnWl|+f-vESr+!M0zsi;z3pp@@dnN6Rm8*a{I2va*v%OSked2;Ov#UVwRWW+!s_6@HuSlDX3RukxW# zcKSu$Vi@I=5Fl8RNZH0;)m3z2E>PABewZy6WR`$`{Sal1@moUwmOF0!B#(eL6@)Ch$s<|Yr6AMfH54J8hi!akt)ZazkX z_ji&nkW__5ipvotodjXmzs5hVJ0U3Z0aeBl&{I}PP(oO7fmPOE()1W-An)wsBgyK0 z{BZn*0)Kg>j8tfhp|A7sYQn1xts#sAZYh-7xI&`8+G)jpzF3t|>TfX4lzW|Ziw8>i$YWq8%NN6sIOEkm^$4#+#zQIwWfO|y z3h2#FgC5Ex;Yayls+4g@4GH)xqZALiC@96ag4MDX(B5}Vs0DUnOHvLKQoS1;Tm`nCIgiUuAez6$95)5 zPx5_KDcJ;Mj(bYF85bzS8tmXMB+s``LDpHJFxF+OTw*u{;7cxj1YO5w6|r}H%%`B8 z3g&kom&iAFX457$LRggcBa=UYlySs8H97YQKUS45Q~Glcl>H~`!!huO4|oJP1ybtX z_Y8jn-&E+1XG_9EYq4_(Yd_^fy&lP8jrx$FeY_>mXN#xF+T zt1BRyKj-&(g$Rf+|9cm<5&Mm6OhUilIfGKdq%ZhyaI^w1t7WvzpO}QzU&4Wf4irz> zv6FAVgx2XoIY^u61G-A&9kR&auONIoWU<`y_E)f9t7QNASNuafQo%ldyhJY=DCryU z=`t1eEx!f!wF>rC%O&!%EJD784ZpH1Hr9j7&SzoN<-BBP<=UQuJy0m4qp6+eAUgtA zHWd2!9Dhu=T`=OSSwgJMIUu2L$s(uE^AC*&8p=h7<=}O4t32r>Jdj16ya>x62Lzrm zm%u7p93Vo-H2cudoZM_?m_$Ci#IMKSD(tiTqFe;lJYQbscN?!altb7?|5YK##wP8= z*1euZZWm}`;SoIVw|EPgeg(WkDag6GdL~E~IoQk)Mw)&P2OkW?`%CAsnmut692kU2 z^V9eIO=HV04V~rsRel$oC*5$`=`2SEOXMxPkaIuqXH_X_Plr-HP|ABc0HTRg?}Qd5 zv;WB7HTG{P8EdcM3izW=>i%8G=<6`A?B9j@NTBSF!dUj`8!+HQ)e7^RnJ(!k2;oaM z{>-m2&Q%eDey3oOLWs*RO4M_^2(O%;%Y-22Tdq!H?|F;Ah~UhGymjuLkN`v*JadQt z$hfZ|dp3qb?~B{U#h{0A%+IC0nmj`0F5@pqI#7jv4b#Ec&&f-^?8XKTk9**z`x_2MIBBJ2H`3>Cz6L(?LA4e~Q3|ca zE~eO1u?hAM&GA!RdN2THryfY5%|pKo^t#`469?hW6ZWeFfU&0Zbn1 zfJxK#2&CsRcot3D_Gw7(i*(1kGCzI4EBlNvIf(TfKH8Ohi1jOtpVNEFj*Ml1^9rsB z<0LoxyekRR>bt`$4liAYM7dO}=M6_4AVS98kZlMix0@Lbl7}INCgfr>!#VtWS9vd; z^{fO3a3zP|^bb$*|hA;3+g@xusOA3ezACAWAzxv7QT z`-V~f13sY;YvW`IP817VF_ByxXwZ^MKmGH@ZyE|Hq`L1Ea_w0s0e$0eO1G5vJWw*H z1O)bg!A}8tP8nTx@JbHhrrqV-(z`vaPT*_k?Q=`XV(#Wpm=b3_&`>FJs-Ez3v=^lFuI1ufw6;Szrc-G-y@u zt}wE5fT0=L5vVtkuS4|VWL1cM0v@lh%4Od;F=W6htfwst)&GF-G+;zOOI;bJ?}F!a z7an}Nn4*wD#DYD2)!A9>Va}+1Vp3?CCv`_s(V8FkhXdgH7qol zMenqvX!j2y_3ywZ2)mPIH@H@)JJ}Yk-z2+aYyAt`>6gpO*x+SwjDC%4SyZh40F+VZ zFx-=~vWLa#y^*d{57ygd^blq#xIk*x4n6D@?IC(}IYO1*J;-dcJ`H#1!TKQkX|vuR z86T%N8}^7ezlVI8v9S~O@gC%Pt3Cn4Fa0(#>Oua$%C0-Uieme-OUs2BA-N$5HGm*h zQlta|n1qr-vLPV_(v%{?1rZShK?y{P6e$U0kS4t;)hCw+PfGZS@}%1kpHIQ3f?@*| zo;>w;&Y8P=ckkWY&wKgfa3%$c$?v%ki&ZKg{q$_Edze(=HKtIb)XisPG` ziL|cZ*S$P>QN!sT(Um2^rj2BC)ec!`5?_j0w>wi5$1Ac7>ykxq4{sU7@E+_{$8P!T z)nr=g)@Hv6LY7T7)Y=GTj`~+icCnXDY28p~8mQ{&Wa^lnP8Or%*&fp+lq*zdz1a%u zJ*T^AAJ$k=P8)^gNq?GP<%n`#U-pNiMhe;L53*G|_CSkHiRAR`@3C@@&u9Oq+?4eIfbxd2U7kz$m)Mzw zik`#RgZ|jC68+)^aNUFeQhhg!^$qbWPl4!Dz=o?sQjNv%?-sB=`U-EWbj=D`dy6=Y z#LPmr+UM5hA~sO0Dq=a7`=O$3FCRq?e#qCGf@aolbB!GI%t-~XB7}CF&;wM%~Uae6x(LHr1oL-V{C!%z4oKo%f9!18_jwG237Qb znR78a{PT~q@roLmX0GVBUNea#9X@?5o3A*d(j=?tBSqpX7b{m_*?t}~<}%gy4gRP! zad;eCqC|<9p->{YoG>27k~TmUPaRB9asuGsumW&`i@}Z0Ji!{P4KJ0B!3hXccG!WZU}H1on-h&ar4DS0-9hHy)HO9m zkCnhk%7g#=ck!5T?~|h*D5*ktm%Ky~C8?~Qd*^}rFDT;A59m~ z7XzrvN?B}VU{p_Y{dfS-zO$fv;svETd~z1siuce5SI=hk!z~K*N-eU=*iv!q63iuJ zm$9|t#u(PyIK1enp#hHuMb--}-mw}L80K0vNVdmcno^nkT)-^#&&oE7P0CoTZffwq zR&&{I#d*-i99QQt*oI>%a`{6B>%l?tV^r{e>U`)1!vEm0%KZwQ=b@^!4x_Gk>_rw~ z3r&{(EC6)c0+wLQNiU^u1>mH42@r;)7`Tw-+QQJ>%4Z8%ZSn3x)=qV#o9lwLl(f#= zPCrjBVo7SV>N#m2Uh~D(o829~jD1^E>|Mp`x?`5HyEWD5baRB>RA6XZH~r!jEY*>e zPNq*tr&T8Rt%TraaV+-(D_OI;s%8PJ+F=HxmpEJ3vRjUE5^QX`=Y{EcBiZP5_j~K0 z!BMBeGh8e*{}q@Yn*|rRiT8bP!l?*Bkrk&%H$Zf3zX5umQ`4!20rxz(bn2%|&!4(5GvaYtA)W6ynfb;G~R%8-^+~K87Fj40fD`7LdrPK@e{ASioeNPsSTZQ;( zGn;NJ#LO*FL%t3m1UVz*K)JWu%A#yxprVC}=eL3|e+0myO>Z_zr13!9HW&{CXP_7B zlQ`xwh~;ZxVkGl-SgCSm8#E}R(`EB^a~nJBXqQ3m)HZ{<;a9wN9c|bZH$v6h!R9II zLm6fdz4oigTVx;N_D*(1arQ$@p8*%elXQ|%pY6HT{2@IQ^~(@LUxNj!{lxGM?0!1{ z@4#nd0FbQR5QhPbJoeCT=_RqWr0-Ls=u@4cndosh3`T&0A6~{GUHvCz2BwD+S2t5>!7?YPHboL7}%v}ASFCp zdxniN5>Y4kZU02(KJYHeiFZG2lmPOhCg;vsRu%M}^n`Cco^Xyi)$5x3mvgMPqW;?> z3udFLnN)Lm|EmTNJfC%eG8~HtETbi6q>1GSQXOAiB{7kBz^D{;0kI?J$ zUeb#3|NO|7Mb5_pS?ioP;J7?p=}noI9@iE_2tW?H#abdVdTYTgP#B1S-s+xyi_KKj z!%~F9nWDwdY?tYhBDwMld(!vb&R-z30viDGN^e#GOLj>4mBlKKpQIgrkaiF|??A>k zGu;R8U>y0~zf3fUsx#PJj4kgP#rQo_4x)aiTq8_RZhD~PAgal4Fvkq9I8K~{pt!H0 z(oFC7AGl>;-IT=_75CVu&ZxnD+QoxEI*Yykfrc;6B2QK0Zn~#N4W^Z7raM+SN`Ges ziUQpNUpX!%7#O-7z5iq%I*V-NpibFi77?yJZm<^(Ub&nn*)mc;a9Z_@qCnv-)S|)U z61x;Q-^eO`mBOzp%5s0{Z!Iyh*QMvRcvP*;Aid~&fyIcyjqBGAKWIuN)hn&@QY{Y0 zy6yGH4f)i>A)RwuT^_DDkJ+f@LJ)sPeTPcd!Sjx%b*=8YWpob6(fqkk5nYeRi;nep zruv~pF&0*Fq#lp6&9qK^{-}B*0Ot-k7)U)vD&;0jT}|B?Kjl=jY@KbIT0hI|_ienT zQL`-j(p7Qs-=O3s_i?ODvJL2UAOAim8j-_XT|~@1y*Cis$;+k3g_Cz|X~SuX za{4sHGXY?Fh4L-1KZ_L9uo3ulCyy}F_u4n&2NY$Ar5GbN7;=D$s2F|1`4#7Sn__f~ z;05Y-Oa7DIHrUr^iBl1Luq`Jk;BWxWjg9$eTTWWwe71VdiVf~A%6eJkADj3UIjAWw zS7GzM*>Yvy8#3!f{=GR56U|!ic8 z&4ZXty?f|&QP1InNPgTIn(goWw28BMw%Pd)j5OFov*qfOYB{3=aMFu@K)@IM;a*Hj zdBmdD{AV@QB7W6EBYzN|dRf=*=X)HZQT#C1sBG$2h+}Pd{aVA}9-J)3Vqqc5Z_Y_J z1+*?YQD;~Let*A_)ue2>=)?|#l(ZxOCk=}Mp|TwxV z4S&ZDd>r0`Mn1wMC>B{xPT&$@T8Q$tMSs^W8-*GU(~Uiu(;d-?yHw{#{_4RtU(Dyc zOFjKv{hvL=G0q!_)?N66>PJ$dkFv#-E_{S70KPc?50%UhLPYU+69g5iel(A=!;!l> zB8H$N`T<>u=7}DlM&3f07R!--qwJZLSpGy{W;`%)pgnWfhxqJ(%)-aNitTYqyYkuf zQS_Bv&(wfFGBl`_bkegMPqxzub;zEz18nW^9FqbD!UYL%h!mZ_4`(W6%f@?NcMhG~ zNcJL>%qKi|`V=tm$wdBe%NUsCa%@Ju$=_ zb<}ooCLze}X7}dZROiJZeqo17c7;l&&zyv42K&V!V$j39YoraMH~#7U?(YJi+Xh0cc_ZUv0Wn68WfVg$vFxheWGzza{d)CLFTi3rW16Eg0612Lpi3=*N58GNM-| z1Yq1-S844l#rFQZuv)O90AOMO#2=HUaK`(-fdRm#1pqUToBOj%|pe+ zWPZ`HCWpp?aK@EoF`T+32g7@-aF^b(oMQL|vQ%u$Z&~T8S(|xpugVdPQu!m!L-5#V znC63h!Xk7VFT|l7(IJg@Q4i&ivJN{-p%W7is@feg@j2^A;P z`DW)g{(_he!MSY_BI%@o@lB3g?Fav1w{E?sj4j3EI{@*2D22vDMn=R4vrSN z)KWIfrC#QU;GTNLw3g`~S-eb9J6a$o#hDVz4%vwz{3T~EgtU%<<<`c2x#o&e_K3mW zD_4Ax!>6mga!IF4bNzI>Js0yYvgBVr&j5fTQ50F6&tFlTu@Li@$s==KKc{{sYWHDC<0ROs>Yj&JI^6d@)@l6qL<10{dF`sV> zi;>}U05Eg?gTmr|59ZazsvP%;66mO_SEV|x=88p+@&e~o8wF!dw=Fqs_W}Xq^x@FI z_2Q5o2aMoD?7(CT-yqNIE><+N+yIJkW9CSR8{i1EAMTZr{3}P-Jo4?>Jo$R(!25=o zqw?G*M)9?(nvh3!PRJ84JkE#WB|`Br;DAxc4Q@=8x?*B!4|mZRzEV+#=9%kN)jboa zNObXRhf8KVCXZ&l&bXjsZo%?4OpDKom@)8?^X8>IQZyXT=ZK@@_`lR=EIC|D?WNbr zs61KCDxctqV&D_JLY*fwsXu|&Z&F<*ed~$Y&+%}vtc-K9W&&>_CQRVD>Pky4>MC@knK-&76w}7Kc5_Ss2Q+;wbnaOu4>NE@Fh%!@R>FMoe@sAw~CFG0w z^txa4n$7E}dY;2(^I2*oWd>(_1gHfG-dfN>Of2L1>Q+nUWf#nu(@?VG3lK!AWah{7 zZ@%S`&Qu@8Z+k zSiW>%fB^@b6BqGbCLoH;Uo7G;``$aL{cdO z)NrZ7fEYVeWH0Ak?6?I^2`O^}aMmy96V$OoDU`fg?rTtSvYd~Hi667@*A5#w>%x~; z@Z|VC{=$2MgsT_&iRW;c$v%h6xGnPCx@zF>87gvDz#wD~$``}D5A=-htl)E<=lwG# zM;4zy1A9N-f0}pH2VXyX5zY@4_g2Czh7B`*-Awt`B9oQzt4fI3=cUfl1cYBpCGZw{ z@d}Z+lxK_Mf`6~p8fK2Xs-urjr4Yd{^XtygVg8i>DeN)Qrlu!jy4(^m7D zD*O*_q2?kmi06%vvp9uKqBW6t92;uAan#$R{r}%aquOD8G zF2wTne5TlY6P8Mqujh-@aTay7&Ns^AL3Pi1h0ju)GyL@d-A()=kXaqEGY$3`!z`=% zW=N?`2>@UA5H|5LRb4xb8oIT^#JMdn^Ru>^?DkN0`Yyw+-t2S+I{qkl8*Fh7+Q!>@ zV3oCE<6>y1MsMTmd~WsL&S%)=MyKT~?^#M`$xig$!8`kaZQcQ~Lzl$2lcW3)0L;CU z-vuySFBlIkgN)9~tGrNg1{L^uB2H&0!6JCM*AaVpRS{Gm7nTJTxEt)|@Y>G?L2kHe z9{_?@Fa{M+JYstT_|x9Ke1`mT;J&@kQ%fu`SFfb4hC}FHx@I5G4;q4n3Ug(l0P=kJ zPWydhp1a?E{-dfsVgVd++YhkvFZ^}qlm1%5sj{YG>KnX+GK~tVyUnB~ef2u8vyt1} zcM#mB<*)FC>IMgSQ(H*djk?I9HVc|Kc97@Ta$YTl?zY)tRzCAsPsd5AwG#z$EK-(el;dcDNc=0G>^yIyhIjtT6JSZKIqx}M&hrH#?Jys&o~KMB zOizw_u&75-c?4?dPZm>@k1=OYb@|I9TqsVZ(9UBcDwgeUuhuIxcS$!bH6WBi5qy;Q zSCv8v1aLXyC?9BtB?rh41OUoA#z%R8T6u*r&EJ}uhPGnX0p3=$ISw6%J^?T{ALp7$ zIO^bZJi(u~m2lq)K2$utksIHTuol#8Y%Dh(kg&E2I;3Dm(&LdT{;1-7%3qIyUJy+u zIdym5;Z>r}LGHZoE&gx!_P01J3VEuK>hV8Mfk#0e)G__z6hGzIfLVmO))#t4w+9V- ztSPK~hrjRGBNMzuJl!(nowjHyx{NrF~=E+^>@OG zxK!(5y%t&!-Ecrfw4z?NKwj%)N-QBapW#g%-$=;o67p8IDV6j=*&S|hmakIOUoDX8 zbW>s(aO<7t;}mC|B0u*PFJ9o?l?Gzt8{UW;veDqLQ&f2oMoo2!$aUdg$*W=F^@}`7 zY`MsDy!YkcHRcj@wjmL<;$Dz7g|b}RF7X>dy-|iRS1-(w;v*09OXYe%4?(qd7MGBPXG;`(lL9RWeyAA9xwN3LE3xcC;WmU%8tNP_t!N+lO5Ay zfAHoaE*{}d_j{l6U`6B}CN4i7W+Z`2~MXQNl#x z86K}APFmzmED^hW$&(!ICE^2!7$bIl=_lQZFL_G^j)XE}m4EDu)$eOw>FkeKKC`Yg zF_KYi3EMRi^|JLZ7LQ)%>9(B5uEQ3tM+0znx&d(-5SHJ7(VEqQAK&2h6y;fq&!1Gl2Pp7(gpMWbu zyIZ?vZP&~P;g#=!Tku})YO%Z9ZGN_9%WmCQc!p55;-cZgdMtnQ67YjC5qF12s!dD8 zusgiD+N?xOy93{QdQd()bceUXXP?}G^URu*h~T?CTLBMC7wdbgAZI_2GsC$#4dw1c~54Rv?+%07w~< z?!iDFLUK0*$S+8yg#wv^$@JzxrXqQ&1&|3y21Ei$Lh=Wadq}EU0y&0cPAed@k-XX($POgx z{XqW2UoF}IX^JGXZ7I<7wm@D*vIB{u9gsRm=ClVg8%c5pApMcl>jVT&E~??W-5JP_ zNZyPBau~^nNZvz|76T+1$s0%xASsCjQix<7eA3ai8c3_l>+50Ils%HRl4S1FRw4+9yABs&pECX%g5KsF&c0SAM)jw0y+8&O?dk=#Y{ z3zEyQL(BC+Dbgdb)5vuQ$;fmdk0Rl)z|&O^$(Km3A<4=Fq9M6~Tv{V{*2tAL*T51?gI)~x8B+9KjXYN)uhqz7HS$)CJXIqv)yPBPJ~*aE zo~e;nYUGfb>trc7qDG#mkr!&@ff{+AMxLjU*J>fPyrclt0OJ(}s8L{Y8K72UyrKa0VgvX^0jg&({GtGLF9d#3fSQ3(iUQPo z_-kPpkgqXbQK(vmmlUdYgkyA|STzGf7lo=e7_TT)eT%;+R3(C&$WV0(e^IEa#K=XV z>iOpIi$c}p7VwKgRZ1lMI)+C;O6vf>C{%HbTokH)?F_#tR2`3kUlgi7#$ObwGGgFY zVQDN-{D?KhD%Wtlq)>&QCY7NIzkDe}6@Cv)hAR9@kPKCOa-hN`(3xhPcO zS(Y+X;aPk#RN+ZxGE~8#Hl?0eg(o$*KEP0gTk2(~!X2hERN;0k8LDu1h747>eL#jP zT&XTY6|V4>p$gZt%20(1zGSGvH6$`r;frV)sygCZ2^p(!hD?Sk9O}wYg+mbtRY1y% L-l%`?M&kH0vvB{{JZ$>Y!-XU0n$%T6Ru zl9~C>x$kbTZq<8*dQH-@^hxT%d-vXV&$;KG{hs^58@~I2Yp%V9{uA8RTrZVtmnRCv zVy#~Eo7=&jVtu*2=GR)=-?csZ4clAWBf;KAVWU}ZH4xAt-+E6r>pgt-iO0Q_a@F?=?N)uQ&?+w%s?|+z)vx)DLd!3D zD~rB-XbdFa4_)pD!UUYc00uN}bm>S&_=9nFMKyp?(b1AC>` zTGiX|{fkpG6UF*O>vGG>W^47uwZg?Ze!VTTUApnYc4=>L{aODqf%$5j;x}(I?n^h6 zb_cuH3&3`3yL5AVsSsoetyZJF)NWz5Xmxg#i%qOVaN}~d&}`x%e&0|ltchQHitTm% z$5LVWV#8nIHoFD7wu9>lVcWsp%WKs`&GiDU@}BjE-}D=o{OxvdW2>-ABW#y4!EQ+g zCl9;}@0$nKN)^A>^lJys`UQ|hZS}wt{ICDGUue|mZ!FG%$NlA2yWyXzW6lS{l_{@p z)|T+`YPsfbKe7KUrJ>TU(zT^s?WNL9g6=>&?_t_0*4GZ5edO%pCk}b%u&mzH%pvb2 zQOi3U#d59C*z_L9Accl^+F!-Io8@}VYt_Be<>D&Htyc6N2V(HIehVrPM6mCwe!^Hp zfcF4auXHDttaKO1?+y6hoAAH8@xObpWO6x5!=*Qu?r)dgQp%J@N~5K*CvG=!vp2Z0 z32XvHV~>?~6Ge}Jq;F`ITUFn96`V{5WfEO!4X03(-UNqAM|xqHQ2KVD^WIa8*P+r| zL27%0z1UoZ)ka~xWMb{-$HtzhH(Gwpd$@vsOW8-6%*V#Yz2iQ5w1`7`^%d{Q(q^-~ z+#L7bRV!b@jwrV_>G3<8)jE@&vo*gt(rh*Awffp7|8)u+v0f`wy)*4~zX1+cY-5#c ztKPBA=dx$~^_IW3?2*CXQBx1TNf z-ddqdl5`ym&VveaNPgMfTmP(qE zl!ANd&0-mJXz(}j+5qwHqm8n^;x+trA5xQ)23A3#MYR~!657~y3h>g4fbm!RgK<{E z_{##u-sJd;z>4be^C4D#NfJv3h_lE2M)?wp7LrOWtf~LLHvcV1sxCFCs!w1y@e&%8 zgnXynH9~$L2>EyYA!JS>4L@aozzCoHIv|UoMy<(wNU}@}M zF08Fr{U#x;u)bb}u|fpGf0M!rU9+LINr|niGPXwLe*r50bAPBjBvJWiNl~eK#G~@u z6X5-gGE^4gO+;E%q2_x)?AcPg(JU4=4|!-+@%y*a?3{N?HnhgdJdHZ`#6uFRGYPRuGGBGdC+tMKKz2&76dO;UD?u|@suvnX zuSOmTy%dI*=@=+JwCy@v8cWss(t$O|OTWSHjfdf5IM*n*U@i(5M}9Itb%1|DgPqDv ztQS|ridGH*C@HOj*Fu#Af#uB3t2U5ThXil)J`T*9jeu}KL>B_%wa za8Zd8RHuc6orn@-CrJstmGPfL52a3hj}Vfj9?JOZPWuJ8oK_+I!4lyEfW|A*64#7%#K+=;@y20uh_PwdwWqcA~Z;OP59dXUs^@2VpM zPhM`r6h>03j%69DJRg~O_id`UZRLk)eKk)#F4tWmp}o|b#Azp~PTvzwAdbRlC#g=~ zr8_QLh(Q{A#tnG437pYpZ49|2hVmxKyrIeRAUX>z?!rk9*6d0z3r`FHibn zs8koKtNv0$=-{E7v*}Gu5Y(Md$mz-*NUO&+!wrx zW~8X#)if#4V=vGd;RWJdw^CRuS2st;0qMFA)xhl{yE=m_0DPXr#~GkN4vO#;q!awobT0qiZ+)U@OKpe)>^q%gcz~`^AKxkw>sH@;s%2cq@f!U z(A`e|7*U$ujFsg2Srg7sd(|%7>PeU+q^uS^#FOx=U2ntd*RFB+(Az*rT>?lkur;6D zInS~}3rCHIzt&jJl50mbXnNl8`K5Zb*xX#hKUdB#!I`r)Ebv15-npyvRYOa>YM%g! z-5Xg1N)v$h$_ftd??iwU60TQjp;-saMn2GUl`9WW>#--^Ef-o&j{{@ZP8dkRACBp3 zZXS)X=n7LK@l|+_cn&&erPYV(+d8PCenbO7$XnI+jcIawuq5dQsv%5_vo7 ztFRmFs5@|Ws-G3%h}b!~9FHlS^;|~Qf>fu6Ri_^M^#Aq_gp(0L zBNlM6NyF8#(HkDv0M@UG#}|DB_D=b2`ot-}wNY!JzXrN5$f=L>Au&Kfb;@+9bvHYN83VS1U}R9+^UKQlcRFQ?8!NX(C_fMpJ)*Z|WGIDHxl}GRvyvJ;C{qa1t*n458}%l=sFsC;pUmGT zr3A1!1?oh=lmevETx$8trCRxYAZ|gsg&MK|S)D@Gvq+$kcz+enOf6~fDx4g)->tj) zHH-_A!fpz?CXsonQz8oUC50^`Z~h+d2#7*x(i_m$h2qT#+2xfmd4zZ(v~Sqd#NMjV zzj=E`Lhm)9Z`VS7TT;!-^fgThFVhFHy7%|Jy32BP@9SfARi{L&d-4cHGK5?k8-rJD z6UI#m3)jrT_R@v{@dKE;$R942$wb2u3bM+i6~)U(w$M$+c!siKJq9k`7QuyKja*NY zkmMl#(5n@`9ICt{GC)sdgA;CjiA?!zwk4)^0<50Tj=DSGkJoP1^dIbl7F4H1v@pc# z2(fh1NtAId*P`2Ng^fy;rZ!Zm^tCqRn^~1>v)Tu6s*?t;CmJg!NeYiWq5KnuBSPe0+8khbT;n_GPg zn5*chlR6^bn46rMn4Fu-PmR*p&^GJV$ZE$z6+G{Y_(LU56N|{Nu>CyR#3GM}o6f;(S&F$!a0ZB#^SCW(gs4n!DwSby;d-;;~H~ z*aPpqHlxR2i%foB<_{2mHV8_$wjVo2x7X$lCnd_Ixzl({DG>f2|JmZx`=qf7{n6sR~oDCD0 zvtZd-5xPPL3S4C=zLTZgZjQAXfwr?4oK!bEsn_Gcm>iwL$~rxo6}XtdSVyc*#-vIK zVs#@N;qD_*J9!7Se3j1;Nexwg2mi!r#}rdr`qMC`_OH2vj;Sp?j3DYe+YOODy-~u+ zB&5%K8wIFAFu*8%8b_RPmVnL&QsR*a(1$7#k~-K4(1bRep=@i!?fGC;xwhVhnPxeP zE^j?^_VCk}7bnLrFXr&S{P_7|z1768E46HH>%uUv4D7B9f_L2An8+IR^r}7HCXcs? z@isBurW$WkjyI7(yby;6apb^5iZkM$7~B(s3wW0y+LnBX5I!-9^yZ>BLVhobEJ{N4 zmJ3aP)LSAnxFT`GE5n&q3E3;FB_)1Nq=Hd{x1=;6DCYmzWt(Fz7VBv9TF2@d^K-s- ze9iXEjhmskIP#F3xW7(n$FS`9s|fJjB_x9M(wkS5dq<*$CEp%Ntp*nKGY9Cs5lv@B zAH!BgtGl|AzwxOajU3vq+p}gsH_Fm$`Fc3 z5n5FSDhKTFunt7gyHrNbY}k2-N)ug?b}A4tObAASB?)QZRnhJG!j zsU=3X0r%7n)`|ksat^)Zi=)l46qebTeJaEC4UHi!?{JcwF~cqm9N)CbY>%W`Nm=@V zO-w(OCNa4*iRdcEiW`$u4S}OQZ(n&trNTlR*m}QGUSraW=Xqt5h4Pon5_)I z0#0~<`(&Jk$9WX)Df&p_(+Pc>TU$|9JRI_(A}ncmz(Zph45?nrFvF5x)&c&EWw(hW zL9*TW7wj$ZZ!Y{-+HvCPm36k|bV}igR4`zWSxN(fEPpXVPc9YR(dKs7Y8VrAzju7k z-Ujz4TTi)3k~X)u&~HURPQ;HtuKBS<2lM0CcPA|a9lcsPkkWe*41RQH7wR=W-L=V% zziThqL+0Mw$v%;bIru>KGXF)I%k1Kmk`AOyjOUaF5ji>K^QiMAN;i-LN=5#mFu`fl ztY@j>82mGc(Un(ga7aOYx=ac&ynIM}gs-aTufRnGUyR9INprHfnP8e=l*6oeQFF-w z;j=@gb!*eb|KObxl@%x;cru;28kCyWh#>46Zm_Lw*M@Sm+24scV}7o;j&Ir9W60Vb z3h|QYyS=ta`OXM9i8$6zXpSX86~2|OYi_`LSNBE^kb9$7@+%uL1Er)*q=}GSMAi!7 z0srX$GJbm-7}wj|HX9$b%*IgKVIv;)OgdTEGXD}xRU3{2jiKNaHaqY*py~L+CzPS0 zfi|4$cfh$$@n@4wfk_FTR$p&H{X@2$JifvHavaE5EJJ65iOBq{2-8sOgk)7_Rz-3- z*?~J2$#8;)~pPEs+ zI$Ylb0gV<;6nRsAQP`g}W4W#IiE)og4MMf#=_r=HTyM4xRFRXV0MXjvct7Yd2(`a{ zpy+dvU1M*^8-?;(maIwrZIjGE!@FURW9|LCX!@Ef@g< z&8k{oe8yA;v+Yp15ecV0$?Ai3M7L#hI7xJS=qx_d$mXKVX!8IO!SK#4u^iMzMMj!pWjS&$jur;mEWsX^HAfZK#9zMU) zC@f#eZC$Btokv)F@k;sd7rpSUd)BhN=HxfjXUcy<^FsMP>rX!kk7TcrUqy$*r zJHnc_4CMtF$f0tE{13{Vq+B_Qeh?l?aeBe9k8gL4ZU_(edvJxnitGkk zlH6*N*TRDTV=E$$L*>FeI7Xi_h%Aq}58TSB~1 z*@{XLMWQbN`TEWog;=g z%uw1vJ-GqL!}ot*Z?qqH1ZTU$Tx2RMCQf%7&PcT)!^bQq;v0H&GTZ8 zy2Y2!po}^tIDWSdWr6f@qB`kr?{IvEQTr_%kr zrrRLxk+FZ)BHO^;KR2*)F85IQm%W~sA_FAaNBKWdD<~(x`{*@MBpbkYzKfmywRt&p z{IaM0p){v`i%kgXOF`s?W5V$)!N8Sf3A$S_1hUMM(VHbVW>&II!}_KcF0(jlYa8}# z5^FpANTlX6Y2@rUE2kZ6sHs&t3|bl~2-&4OKpYf0EedM{n6Bjf@}XE`~O8 z^I1c_$cfnx^>=?+eD@dWpT30iaeD^TxxHlb^1n-Jqm~kX$7ZdTlI8yY9z#C~l-<+Q z7HNrvHOT8v!_<8o{kTXDAR$@QVel{{A_KZ%1f;wYhL%Mca~3u@dQWvM3($o@u!`fhF&gE~ppxg^c|kWGH2ymk0|wNP7yg$-w_cODf`={Lo= zDYQF@(@y2_$t@&E)1Nv1GbjJd^PhSANhhPiHte3|7j#U@nWp{-#sW6M1b!UXoo9n0>?t3F5sgi02kipV!!2y7PIg26k zv4{b~nT4;(t|?^r9vrISMkSYEE{Pk-AcsW4r`OtCXP=GnmQ+6!>8?_^1EnC5T`cEa zZsD9ZM#UbeWprXG+*8W)tH zI*vKhZE97V+a^3=P@MFW1)K>64!6kW9tDr#YbBpfHK z;%NDVha^#3xO$v)zu{+CQZl4^eJEICtdA-OtQJPDfVLQA(z~KtGY$SNAYW7Qv^m*p z9rPwOTIW0U4c;4*k--xQ!{>fX?FKnH7KUTV>D&+y{qzENlwULiT*rYbN1MC4ZY*Oe zJsLT_Y%fHN*710nh`v{R+4Kru81 zm;M}l2UIMTE3cAJweyhD19hbES4q_d5r?JJlwX6Czn(KQ$RoZjkoPYm%Wl(*%Iys6Q>wq!g0b56n~^~h zscrvAt8H=;thT+G&=HGM1I~mUVu8KGxlB@f?ef+}#23>;ueN7RTQLa zfF%!TAhols3*`3IM?qBCvxkEVKRO)OsHBp+&cZI@!q974=@o zj>;A}x;V*Dy>T?+G{C3BhH=@5mfH*ohNjyr{8PHkvg|esAKGp+nUjTpt#ZF0>fyeL`bCt{ z2ooOl#9!7-G0@;qn4jZGe07x*+e zv?s2wqgdU81AM_y0|y!gdeG6xKC(68>j@OOE5#r7Qal#vo=69N>AMv2<>y%kzOx(7 z)Hj2!O&p-at8~Uhy0L_h^v@D>u?3;*J#&_X-XuqO^t%NVrxUEeI@}mZk?)cJs`Fl7 z)pJy9$6L2J_}2Z>FDUBKi>B8)$f{^L#}b-cEK+C0WMQCZwNa}xbm-=!j?SFTtvj=I zZ*{)s0+rgNtKc5h$u1&sCqNh|yxqCD{n)i2@g7&t_L-3rTBd#WQfpCpj`re!A#6e}|a!KcRp6 zQfGJBvln`ZE%{%)TS#l6uj)CfW#VoA(HOc)U`OrWdxKQhh~zqy$Lqq=BoL+aQ+>bk zQ-Vx>vTriEchd1in@rAH2h^E`TeWpuJl<&F;^umNug>5KF}yIpF!;jcaZ)(cqn!)$ zE|%(AOe-iy!N_Cq6{|znOrBdngs&)xovyJRjSiWOpkG~6dr4)Ti2&w~@l&*uJaBC!%iY`s^-c8ql;W~Ju z1$vB}dH3;A{wjr*IOKz`Ga|A4VLGl@JG;74RLbJmDJV^@uEsj%akkWMG>dGFb9~9a zIHBam+)j6sAzgMp2AJ*thzJB*294P}uXCg6JuBr=KV5A8b;I61RA_nZYUy7ojwL~1 z*>tNoE+Scofv)JASR_1XBOxk?d$J#im4U{v(e%1B(e!n_*`tBBxR$YKyfI|85+&+y z8@vb71TPU=H-JpmJ{Htn5EK$j{%wQ!wlqN;OD>QMK>O+C0N0hFB)6Z;zOy;WUL^}9 zVvHv?dft^LdKRvhW$pHBLk}j28byPHV7;a4XUIVpbS3NAds9$MO!k! zNol}AU^+aI?qa~HP{`$Fa=eU1Mizmq=Z2=YMM+tq~am^H> z*(Cq@esCG5(mv3SfuZIR^wrIQ%y{>Uu@78cgWz{zhLJ&xx>a=6qFx&tJLDa&dzuh*$gnl+y=XCd_uv@uGSgnoA`C!T|g{GQc^Bb$MAV=BLk5_!eBTUmH z&y;jd!6ql8QrK}`oIhds?cO=^4dDDF4lS?9yuT)Y1+$~GEz7O9^Tvbkue4j?n%Dey zB5Q73r+KT52Dx>kkJWfV^bMBh_aejh^x!d@s%jHS&W%l^tygprjQ#!!PXtJncya5l zaeID8tl`i5Sx3nlx-I4X2}xE{R?;304^b!?aZ4TC z6LHJR`_UpUUO9S(t};Pwy_I%VZg=7#p)(3Q7im4@ITJOpVaD{)Lm{uSFT-)l+wf1X zWF#4E@6ByS~~q! zZ#T716M*};#BE|Cx`?FCI z;F$*oO-I1FR=c>+R9ucqB?Zv88)x|t+7A<+ajP=UVRNhxca5q+t$lOjB!Jz$}j{(wpDk3aw3)iYQy6G-M zipPqm*_v634B6A%kZS4`O|WuGY;oMc)TO@=gby53cgZ<9mekVGW?u)T8lyX2I=*Bh z>Do1EmEo6-iVviTihYXKyl^||uLX{maTBk6kY;z|g>6Dybmrfg=FBsC(;HJZpT^BK z7?QUi+sr~@zT0biIesWjpyqeXrwkknFo*+Xy?2127oALpQyPGzHR2#p-D)##V|LLu zj<48z+G2c{-HZ>9ZSwk!G|B5GL(b^$1lHqNFs`l14T4|xWdB2&lijOWlm1FzJakMn z8Lir@GHQm^dx}^Ib{{=#^n58z^ti4Si%O<=oz4)E~`iTRFKzJbTMsu5SfGioV;@pjkujP-ZF2PtH3vJF&wk*%$l zROfhYWXME1$8%cekW*rvV?XO07Lp9GTyOgWDk(p?KTV)+vDVdqC-TApifgM%gc*v} zZK4>GEE(z<-{^Sd_=-gZl`*>3FVsy|^hm5=9!(7|@te+|5xwc`Jkk5CJW= z!+T+*)M~9a4;?t**CsZ~7t8B@v0Rv_H&zeOUk7CKMX?-BM(jiAWR`eXs2~B}k`RxgZl+y0z}C^MG6MRX zbVZjS>S+30*3e|h)EwaF!Dljk;6sFTK%|MvbiySgyL^PLkw z9RyV~q1z#V@?RNHH{ zFc5^|id3{%e=KKyEQ9D0DerthN@Sr~juqv4F+T69FE7yT?k_%GRg%Dr`wD&3Ixjkh~R+87=Sdnfm9KgApD-vynb4A&9^z8&xYD}i@u8vuDp`cs`1?BXI znHAi0vu)Z9L_s$h6r{fcpSaM6iLkaElkbgUBP_DNa}yh%alLhX%|?|)tx3I^Z%Gqr zB0ldK)au|n2AIj(I{;6HW*a?w6}wZEq@UQl=xu2tWsf8o191J!0bIN(Xs|tP3TkiC z!b31L`R)wlFE_)_hl~W5w;7(nlI1P2;idt1)dkWz0p2&y{) z8dFTz!7-!07UunFF3cUyy<-5?rGW#8-e@%>(}kP+$0C*Q=BH~(a7=bc)?{bAT79bx8P>5ZNSdJD9mk0jtp%}79pGwF)h$YA5F#;q zN0ctO7wP9^s(Qzzjw^>JQOcf@wF_M8`0`>!g%%PuRS+@HIs$C=5=seDI6nJDOI~&O zLw}ib;fK$o8WJ6wEu-ppZahCOvSpE057BWJqK1yaUMd&csB<3fL6wdlwa`d(ky$FQ zIAc-M+*|{<_l5;ph9@$Q&`B#ghekFZ6ep5rT@oe46>-sPvXKLEQRkH1z^@JJ4#Yx8v|c`b&JJd%q4Rl zNfUSb#9132^z2p80(#q$FHijyn?T184l~pLHNbZ<^o^BVQ7!q-@w{jkEm0kkNo@K1$QS zU?y9UM?u@{NjwUBPlO}oCFvMX6c#G~QxL;{k3od=8{GSY3fix57lX8)*IAVaA#<47 z8=(TB%P1v!pjvO5>7OJWk@>kw6-l6tamK#r(;UxK+BlUj>YP9=V;=!slHTM%0q&Be zOK3->Qyx4OmpIUI5k9&Z>UF{?kO}X1!2P>?n3GXKM*qWU%~kW=6vxEw+91KiYcQ`2Y%9=3HZ-j{!wh{x__>9JQ$y{tywn(5x~*<3w(GI2fDGJnn4y>)3$m z>iDyo(y<$L;Mf?GiVS0;_CD1^-*Na3sUC31JX#xdd1e|Go9hZf&4Q`Vuvp{a4xNoS zkuexNWhz4+?1}HISfiA5I450B$!E!fsTmKSH@DACKMOjtJcyly1xITSRE2e#{aP}u zVq7uA9+u~!2rIHJPs`Lw>R&k)88VTLdGs$8y~-)Ejd{BZAqM+$zXykqqe$b$0<7op z;CH7v|Lew0V}SmOo11+mAgO&@N^{cJQ!bc+Wbt?G#0?K?oX_=2n$wj@R_t>%rfolu zoxVlvN&Tk(Buzlv#H?gPNGUlu(Y`>{0VJLKlz#u9XEVL@@K zGJi!4| zO-`WhNJ8qnpN+b&q=~vaoGO@szAgxy>@7FO%LbZ)roUpDqe+=3e(@?^zM@g-NtAnKhrJb)l^LS7p~_T0B*z}YrNa)mY!Bg69Uek9 zs10YZy<&XPuwj2byLEVJ?aGnJ%9>XRUBxdb6fq$j8JrLrxJWU)gv&_?|NInP9Hc^v z!q=s1fa$_Qv{^toPr4JvGO%eQz{EyYP2@2b@IopLo%@i> z8#3m_Y^?M@2 zCSt$O{Uf!ya$0P$-VilI!UwU_-;vs|mgdw?@X4Wp2}U6|NNGR^>f$Afu|Ce-_tPjN zkKLgBLD&|`vklh|%g^v7ZboB17V+Oul^&DiI{6k{LdShvr9_*$Bk2yz&g|_P4PGj2 zcq+V2Tw?pXue}CtJN$>NJMwhz7BCq5OFjY0z9m8$_GXdFduS-iKh@eX6a4nb5Q#R% zH|dQbr@$NIj_^c)2p&ij8*}f{AQqIjOSkO~S4pyofyc3t_k5bjyDdUV2HHAa#Ud=C zZ^x3ML{Q)TY=r!5nh3eY-WuvlLF9!48S%WsAYsirY*lBaFI8uAt5elUz)f^e{N?(b z!lSU|v0?*i!ykS@iAjx0y#m2r88*%966oroM-L;p*E&ksSEO`G60wSuPU$^V`7Ksi=DgyCr z;P|2~-YsP^sWbbHX(H-1tOs*^Ut~lZP<6iR51^z`kppQ0baSY`aH4_%jQ!jJNN-w@ zt~9h73iBJ7ap(6vC{;q8hom%`hFtFpKi<1!A_VFpoNG-3F zmvIj#QwR@e=<|JiqJk{HRUBg^5~hqDqHRU9 zcXj=YL5@8dfzmz~A(I_Y+7}{2B%-vJ+6sem3e5cO>j;8&BE|qNQS(?ZIqy8&O^zJ& zzf2Rr+np<_C^T@tcYqMTEe#xNDz&%eGqILEQu4Pvb)ZV`T9M<9z4}0O|KiQX$lkr$ zpHb*zOMcJ3fj9VYm7_5^dh=KBKTBr^=i64IGW_0=4>X z(6gBX{CG+?CZw0kru0TErQ6D~AbKNS$J%w(Uulh)4apB~oq|TjY@@tdYK>}t)+_O8 zg>BvuhX&sf`~OU>xkjeY_v4aGJS~`s{;uA{f z-D-cx*gw%XAf-nm|oXP=1-nP|t{yFVkX962T4F?W)k?ZArxRo5o5;N5K# zs^$77OU|Z9w%?{qR6Lyd{5!z{O>m7fU zMpqc(P5loB-_-eeMV1;-8o$anot<(ytm$FIVXd9TeL1YBB`GS0^|amrm5&m^4OM<1 z243l~KKfn-)c0~1gG-H^<2x>yQ-vpcR8SPRYl?Sv77y!J@nK9*IP{WM`^}g z9lMF_x1Wv-k%-M4*PzQOFq^rRt`0STQ-l;m-#8|(>7kp;%J?i{+~uoD6IooyD0`#&Qn~)7y3Cfp#o}N z_t(cfb>SKri;14@;M?;^+;f_afCQBZ%o|?mt=skmkU*Jngt*hh8-5nm1V{+fe7JDL zg@(Y2*vzaC$Ix41U9w*lh zD|~Of_&1P~q;)JRc0rwxCI>0`c*fh1-HD3L-G#)H_D8``K?3hiQ1}pvzhWMz{`Mv zsK)OqB~b&R&6MEvlqye}cxNpyxgUBpQS+_*4z1x(<=^zPlzfunx&Psqq3w(L&RAaz zwy!e?ai0CLSci@aNXo`J4C?&=)+^Eo-6D-b&#hk6SK-Xmk}wH~bd@WrAB7YGfJDUmhigtuiy8`K^7;dqaL;CmXUeys@*Lq~jp3^fVO8 zc?%pFd<%T`SJWzN)aw<~0h4K0z=R$~0wy|GktAR;dKRi29j3KQh;jC@xM-wNzJv;4 zmwc(+_0dBitMUwOfT7Cy7<|cq%S(Tvkn$9FF?fQmPlj@5g+{duk8J@Lg*2OGTm-@u z)zn?OM*YA}7$rdI4XEL*3V18@j}f)$x$jxI{bL()SK#AwnPXPM0IvRQ6}Cpht3z?2 zUTsSx(CE|}q18fR&EgKRYSF*4xdr7_WEDJp# z=2q`MVg~1pqvv0huqm=&o^d&54OWqQx3tEPe3S1#uP9J2tg*?zf;0l$31XB$DEhR~yKZnt zB|x&P+qH{0PFEv;4hkgTS~0p^45y|MCB@M>YT-I%Cxi~lykizrV1Z8Lag{&6*%B%8 zxLLluR(@6{EmNgaEtjJX+b$Ean3VjaVnKJuU_kSMAhs#?-Y-P>L<+3u(~%()v7URs zQ7ycjk}&;UCAGRB&b@*LLXHeRSS-r+ck&9UbGcsGJLuo0i8|K-5{X;sws5(@9c?aL zRf0EG=qi8c>aN~jy?m=D<3RDE(%4u|j{3f{Zd=H#Z4o*aHo!NLe@(kj6rMo=XR2N< zYgD&N4IhkgsZK@A(U=@|Vo$2hA%ktGEh z6}~k+-L|MSyxIFY#xwYZ<0ba^TOzA!3pE!T4*lD%S2hACBSR+=ZbyGdp-fJVh1)&s z*Y1f0_4Ob@V+ZK*48oY4UQe5#k0#KijTHZlNRgWj!`4k>D1{Ry=|=`9>C<0P>!VR% zko29bxpj~Ib$zd9T6vo2W~lO1Kjb4ysNH=_r`c;S&qt$PN~f!&i_2c@NAM_iQs&u_ z5?#yg{>zPSk$`Ym&B|WglT-`EB(*v?Ni|M7mdzlkTS=x$cLnM+g$yYASk0@lDF|qz zZvuJ__ZWpGdg6!GvcHH*s63X=JmzDedqTtO1UYd$tO$vks*>##*M*0Lw?$@d^4?TUN# zPgE@!lg+;zoNPWj=~zCkK?b8R{jwBO%7$0(WcliyEM!?0akH#Gr(lHbs8hmVTSr(= zhs2VE^@iSwPf-xSUujoiTvUxqen95kUMnxK_hL z-BByXa-=Kbj&vaID3GqrjH~_~8+m*07}%e3-N$2*SBxU>e6_xM<@_b6nx>|XGxPMQ zn@J{6XJH-3m#^Sf-_d8zYPt9Fe9T7UU4x@>|8F_aXvnT1X1`e>9I{$C6l9Ds5G^_w zbZ4^3ONvhT7_Cm2G1agHp&n@Yc%1)D(n=_h!MZ=$68?-$0_|x6&Wa8 zpBO%367C^f6P|}_T=C4lBH3TA!_?KPL3qj|V>|p@u`we!=ZuMY?@||KviX%UOfAZ` z)!&30az%?$Oozk!%RUZ(0%%n&nV`uuyG+=r!_a|JGsIVJ>MOL~J|LbAH|M}ZfqIS- z5gGE(75Z_sIg!e08?dA_VBZkQkO|<<+KU!Ld&b=R?C6+dimvDjkp)fUiXPUyK`u7C zqH)7ZWH%XLJ6<|K>rGGw`j4lvPmSrNGu|K&Jv1=WP|Q9Ud@KhfS`bQcXJ$~+WxfVs zkkD}Ga0@xej)*4GMZFEZzmbz7{X2(X>7$Uo<$jL&BKeP=j&}}NmkTEd$%QT^@y~^B z&hmwb{=cAaE&dwvMt6cdwJq3G`8L*Oy7RdNrb_+|w@D9`CUdPH1xL^lUq39L!$(JtI^eZ!+DR*1{jeRb z?m^N){~Z-Tyqq5&d^t~-9pLHZT=+S#tdmd$>y2W$R)EqAZ3g<9a9=_DE3?9iBByYj z__*^1RWL{?hO-`*P>)CjvR=#7{L84r?)w*UyAqY%Aieiep#gOs7lMTM%GTFg++YOA;ptMs~Ls|E3B7*{cE4YEeJK_C{_ytE0&onbqXreA0 ze;w|h79bnW9jFbDdOk`_!(~JjPbeK+O-1*sa z!yVkK^#))?6WsU$%n@vg;!GFCCxUn#UhL1ubVvee& zN}*bA@%_6vx+bg$S_!ry4ipQm0=^(d%3uYM(Y`jp<`I>ZKc2?=nc6}s<6$%YTx2u4 z^dCo?*`1M+0l`j3=zGpmXS0>o*L9<5Y0-9XVDJBb6+vKk#%|Vg`3|+?C30DT#SL^j z*iZ&mcR0X~kqUCz-?^QQ3Ax@nzGg4ZF0cc+4*c6j`TvzB%4c`Rb_@`AI)VcYy?39a zWVCu{P_AdpfAFyef#h`h?AL(pYK%Szw0o3fP$V7bXO5BMZJs5~OPtE!AB~MY4u@9( z!P4rgztkvr?`tE~8`{C4u`$m(29*%*BbgH^-Frghk|b9%i64KiAAdS$Kj;0u<9wZS*-|mfIoYo=I3{cce39^Wr7?LFV29thwWP{sE%pK0}ON4cKs}RHNYccYHo*YD; ze`{$J$q6zOxx)>)`eM+ffdf!YsoflL#w2K+9FDjEm9Sk46e$J~ack+rtG(N~l4Epy z^_BRv!ZWYzWhUP4>zTj_^xPj^GLnO<$Dcf^L+gslsmMuW5mYDt{HTv7}=6(r>7x z{m&YxseyMj_wCE)Y4AUSX{s-m?S*7R%&Wh8nmYUI*Vq zJ_vl=?5G{CiHqZ@d#li(OO;@ED3{Eh>AXwr5FS3(uCUNb$6mIyXsDpX#o;!tND9xrsEZ~nd zoyZR}3)s(9&^>dJ_2&ZD+qkLsEF=AfH0ORl+gP!*Xuy-SM;wfH9q^=ej$Pk0op0_k0X5?IY(9UrmJ%7}HL1PzP+0-CI_>x2&hY zyZ3aOL~y&4$tiXbxZgXbucd1@%hX^XBxqcg>7yBCX5#w6!?0K23|X8+aY6bw$M>A^ z&pduUlMkOy(H~RcAJg>5w9ZFOb4Z02UWbcVhhCnO1eWBNaH(B*;6$B$4F3 z?#_LZO5`M1@}kDRYh4YfyR}FPj$%R~I8j#gy=j88ThO5~efcDIx_cGvO8gs7>=pR& zG^Y&w8c}1lQw$KgwTJ_$rw;VXX~J-H@J(&No5pAk+_)4Gxfi4&VsA)!5r(JKVB?8R z5}!*GoqHrxGmxU6IY6_gy`ySvf08BuuDU-_RL2W@gJ)^Urn?3AhE-qaCD3WdOlnGytbHdjdq({Mil*}bjTSa4) zn_kBT`Ck0fOJ9%%`Tn;lcE6ju7z)8}h$9k>0&JFs*K9Qkbju}XyisVtCa+VDA%eXS z(`=xJv1E~;M*c3c+{GDkey>x_YQS;qywwXaP#B+pg z7TmJ7*=#M=mL_W8i_Ps|&oRGRJ%!)f-?c6Mn8LAHSwyek7JC0k4L&?)qtf2s79?`| zjY4&CsajvYXbiLPOK>&bC)tW-SYT;nP3Ih~cKLzHiQJgoswSG!P~-vv*~`^7vVz6+^2+GK99b#1n^UDnOlqZFTjsC>yrErPkeLNB?`Qo+y*V<1 zTm42ZkB-lbj%F5~J~Tdg0dI2?ll(`H{QGt>EBJj5qf#);NC@%j~g0$5G0vRu8EAX7SNi84Q1ok z)=~PS|E{j1;wkLpsA6CDQd&xHF5MsOsTOLh?ZT=L7ExZ`Y?bP@DGH8MD#S~MDytz& zVOPi4V;utqnPo7J#WHaYWYN6o!nSd|sNz%au}AOqm0GkEju)L+a6OG2jx(Y?EA=86S}Ai$V+qOf(|2RyrSDG#&*f5mEw+)7-M!Y&G9EvH(&T_ZoaK z`S2-(h)18EybyB4+PdgathYwcdmIc^)znC9IJFGCLw^=Cj&1~V3(*d(Jc~w^E7Vf& z$`|mbP+O(r++MrNKR|x)Zv4OOdXIUsX3cHLm4uqN_w^1KG z)EZa*fY3Ws`2zllV%S_}X+56CZGWLl`S-bt!O;HdoT#b_o3@P8N-ZQKv!9m89CfQH z*om}=P^B3@ogem^%XCu|J9MFRA@;i5ZZ<`&YLI`;7wU{U(j*lebzWy|?96icV!4%t z9o?vb6;l2mv?=II;=(y992*KAAJFd@gHOt#nNc8?yv?-a zJZU)#lkblA1G>Rw`|F2w`cqo2uEyYXr}L5+=%-p`-pPL*>1uDs$YRT+!?Sw5<)@jO z9vOJ;^z4EZ26LdMq{Yq6CYeYK*$)-20{b}z-hG#i^PY%f8PpAHZ|p^&210tbbHVC} zq{{V@k`3OFJG<-wWNb z?PjI<5x+60)Ozliu$FG!ta5`&iI)qjd?$*``{26sPUlB97s*(L`m(qNQCb~6l=1K% zWSmno_dj8X8vt9WS-~lGr2=xAXwOUw*=D7W#U=K0|S_Pa* z+x|8TTlrtn2;-G*z}g{2vUDev%DW3c-hlrZu7Kd?5DYGKxQ+Bmm@@y2Fg^CDf%}gt z+}jiz+{AtWF^26Tpn-mXx(!w2%IQsJbLmt!?fte+S|}nm13h+Z?1?icz;1=^ZTJp` z-0cmS)2#&{`!^w8l(L~!gI)NZS*bD78vp%Zl10h3A5o(LitZV|e z?C6172E_@8t?}p`eC_4`utGmG&97jEcf>URt0IjZFwN)x7eyss3daG{{0M$VTs0q4 zk19WepBFT9sr(rJCN9QYt@0D$U(C}gpP;|)n4FlLoXbt;b8~a^2j{0JCuiplGEbAt zr%?H6G_1Tp|MxTWf0A=meinaysPc38|J0b30rSnTms*{@p(>xo2RmFZA&-)XdRchX zJ)~G50t41BF18Y-50Q-)x;<1-JV8rEag`haK2$jn!Y`SUjRn_Ef8jHVU5p`Vj8)6&c%=h4A2nha|n-z$gnx34;jPMbBI5(H) z@8N^F88I5>JDU&jmYbTLmw?R8&j38?H$4vqJj1xpP0dYDV>m+A!5kD#@iaf1pOI*p znVp^$D}q&>niGIb=JV5lMf5v3HFHoPZflXr5L7MK0i4>$E$}y389QmfI5d))R-Whl52MGAY=-UHZwCl zDVBONm!HZ_^EYyn^PsnR9%33Q_2jf5KHzX_O0<}n&dr7cgKF}#{1iksJtI&*2|)8= zN%ON)(>Z~wnR!f3OlNLpYEFQU*!Jw?w0N4&17;p8pPQVW$<6T)`Dsi?(B@ozej39u zMAK8V2L+AI&P;-Od5EcL;ABQnI>-()6GKda>;>i_OhFgC9+0O%A@|G8O@rQeY4Y<^ zATzNQa18?rfewu}4heFB zz4qD?A6CUF#-^VstfSD)Wz^eiQQf}b{DG-q!q@Qhftg`hkdG%}e356xcdk*by$r5T zZ&4vT;4ch}5n}jTfRHgSf@z|v9(*O?z$l_aUK>JGF~jF1L|jdErvu7ay2JqhjEyao z3(c&o$Opdw5K#2%D=QPIoQ>ez1}bXf(pZk;ddxR65 zDCdKyAI~q$#LX<>=p`j888fH6CqXyBO;5_vM>bBRLa&BXBc%bcBfl$Tqte`PWtBVH z91C&K8w0)fjsZ_9!}Se~RNn#f{?2`DOwaY!^)>B3ip1l{iMKBjq*Kf>@*D&IRAf_^JFwlX?%2elQK#2y_v3)PzP?QriJ{lKv^PNGwFO<2Uj$dY?4c?Y#T zl~c6ohANNapCoqZOY_POeT2I>GEHJ*_Y2c-$G#b6)q1tws+M7L)o{|l&&UHB^``t~ z9@P*vby4}eRwNCs>8%%KGd*`n(;b`-a|R78ZHA$36VO zic^+T_y9lf0I}OBJ%p*;fJqKBo6o&p(vj!*=(3W0an*Ie-^PY2y5SX+PSwO3zaVK^2wUZ5<`3p`h?06!6LZsu;N=j)#39i+gtKR+5b@3;r4K>LnS(Pk7cz#- z$Z)FP{NyzLGc$vj@zk__4UUcX2%t|PcsrXrI5Ryrdypcc%+F8fxiey<^Ru&v>>}Qb zNT+1=)DaQ!gNPAQq;_g@b{-*i$|8J4GH#4zX{lw2ENicf8@ZO+x2Nq5GE@4^3MBQ~ zrZGKUFoI|ePC5zGKpc4@(;!>Oijs%Iq9M~j*T%L8G$A89M92QMnGV;Q;2*KS);gd4l z<_NqYT!b(hTQ4k{S#vUMj75Gm!iQOLMO3x0pXhxZX_zk2j($6pfzb1~pHlc0N zac|LeloJcZ@5N@Ry|O~#pu_n1db`z}Sgx;cj)*qm6J{InM7H69psj`{;lr`Q&!}!< ztj=bU(MK~poB)SnS~R29hy-Cw!zl)gXypn3_1&irsj)8LMlFU;zf|uIUEuFN6{@x# zegKPvF-EZNVGS33X%5HZh1p$^S&q~2q+9b3d`D`hUn2&hW`*p(r^KLG7ONVcis43G zRgHhqAqFBcsn-GA{hw64?We2~KE^jWxxgPWHVZ zB28hpatk-oM5F%2ItdHDijK@&?w&!Y8XUuK;08Lxs>8FW?EM-WYx%Wiy|IF01{jvQ zh@ypXBsFkbp15#1BT^y2hmko@Uqi8@VtCwzq+qqsqLM{2`G8NN>fm%nLt!{&&8HAA zpHq0~I2M1i3AvPW_CrM+f&Cl}aCpz< z?4*Mqp_$irUua`Ky;`}xt%DL7O)PRH%tv}1%%>RgZ&O=^*L5RN1HSHUT+sEztTae~ z+x!mpfJVqpdOK#TmDX;)dV_o=b7?Q>Zox20%TU%Bsgqf7kE~WFv&xNc=(%D081=J5 z$JKgZ5*_!!({ux+U|h)5LEaGf3Dqz6R~tS!7Jjba2Z{=zVmTayg$CVgzv^8o<78Br zIyTT4YN0BlZ)6YtTkubmxktIh+YuVc|4+p&hPjL8-wU5XeWfP~waw0SF?Hh?+?aLb z4}o9T+f6WEfQl-wm&i4Vd?&a;3HHni@`~ChhNo-5vZh2BDA%Yq{IWmc;TRh3P5_H8 z)+rwe$zNd=q0nKO!BMjY>eQh{6U?4(Ql;bkoOH(ZhQK^H6Rd>7cEG=Mz!tpKdcByD z7dVVlG+={*CrE_D<)@TlhHr%+QNC9l73^w|6e~Ed0R5Trm}o+NX1R?!TX|iP?p7l& zuaFfUm4I)xQT7G1BZU;53)SpKy@8XJ5?4Ioax)`FM|8Pa#(_2(9Uqa`muk{cI786{ zx`DNU<8K(7j@<%p82}E6*uagfbSzGOgr0?2SK$jJn`u#YJdM>f7*#ssflbU1(Ha#H zTv2*Qn-dC2lrPA|g?B($20$qd*f&H5n||A1WNrX6=tzS=adhzAWs42Nr{$d>o>q z;VH2cCI|CXo+NL`N?AkhFzzl{Z&z_UXylq}mLQa>3%zx@R4db^p>%5}2?p3-e1|sq z2O$km=2g`l8hP^AkqN@<6p$^YW|qb3w=9B`1eq!2ykduwUO$V~Nu2VF61Y!~n8!V2Q@ex})8 zYOcedaABm>YOOa99XR0ECN@xcY8}M}3KR9l>H+%ez!7eaWDv9+Wo3|$J>VPAY&pMR z9WD#Zg-=S9P+Zyi9QVTs0Qln>gp~p`W4@T4Zt1N4Yhn)3{3$6hKoagApASw3i?^}S;$Ak`$~G=>8KeI&uQbhLSMqUAN_ zo3MjpMwLULNX4CRi%<+(Y*dJPw|HTEQa-_$pGW|uqs<;km&U02nPc4U+pqE{pa{m2 zlQ);SoJS`Zh7ajIE7yYENVi3{fHBRER}Rd&Gv$^ULAL&9ynsf$rd#&(X z`CG!vQ02?`CyAfu=7p;9Rd=NYSs1FmGPKJ>yVHvI}4+rbu$Z3psD5c>I z?@0Fw0ifhpmV|JnkW+I4Pm!@VhOP^OmmVG*94W*p!Zq?c zEf;X3AuiJtXV&-zB1lAtUwA}XbiEOr9i-$op|6rNiDa^x$|*km2vJKdg#5&zzZ!v7 zfXhYpf%rTC=fN7@p$3*3I)kA@OB~up75emqcP9Ld8c-B7g6sxVA_^%SP-{RX^b1k4 zh@D>41+}y54X6RQONrc1bbTXz1X26?rk2?c4Z0Erix_+?P}mJ`iucVp+VGLJ0SUqY zC6(d&hQ?5$Po_hh21sd*I0#h7X=9M@l}-xpbgvjNr8C|j5Ir>L#x)04R3zol(CM{fufVL!|I5;t!pPZZ=p2)CAel0wX&%tpL zWYRQL;>eVABA!H_RCu7T(OlONBF9#Sn+S--)Y)^inW3xuB3P0bIZMJ7eUM@#5RZy~ zj52H^Zj-S-#5V2*zJ%9>OZ74W^n?wR$g7s&zzQX$GLRl8gtP2TfdGt+neMnC|04;6 zoTJU8COfqjJ!#T_q5r;p&(jcJPo%mT3@}n2cn}!(sWp&W)R?E^rR!TdS6~-iP7%gt z`M2h;;?+>ak5El~a>iqtX-aZptNK=(ix~5czHv<2K3#l0aUeNy@rRl@Cm(J0Gi!Oi zxZA{c3sz@LSUzz~)TrKltIZnae4~%m%!B9~3?K9Z2v?Zw21Q0QW&;xQsRNn_+KHh{ zFs|o6)Z`iMAM0nfacFnlxF-q9$fxPJiCMQXcti2!5JCoCU!LzdR?Ovma$@AIgGfvR z(!s_V1cIrZh;2o%!H&8+<{Pg@8e5Va6CJLeA?;@%e-BLU=qX&g1smg}a&(@z)jp6U z9-23u46oke91r5pt_ufZT4{{NGz9Mc01P6DE9dlM%9ZmUxQpS+c^aAL&H_tK^5sAi zmPwA}Rw#Me;EJF_$5a3@u-;#?t8j0qQ%#7aXJ8-jx$iVR$)>*wfr9wiDgF{c6bfA1C8mY zGF+d~eD||Azz2Z;Sb?1(H(M~~+O37_^IBiO)n+SF6^lMrgd0TPVEEU6o$c$~Il0|p zF*O6Y$cx@E4YqkE(t@V@b~m)h4qa0dwbAP6;OyK$W*VcpR=|-{?S$r`K_!a;%iv=T z0?F|-M4SOlI^zuj(L;mETLYTG#~K8ZJDh^wm|m9#u5W67IT&wQON+PQ8sbo6F#yuf zVqh?J9Le!-wjOGJZ$HPt-;f#%yM;DwKp>yE=AV?iOjx`!R#`K?-fvIGEN$<`waT@D zUkatH`~A~?uqgc+-L$kDSl!fL2*L;P6U@owzc#14^8|l7)d?b`S@QK4f*ZsG#{}bT zUjqwd$#vMiZ;~6IP0%b#QdwuobS8t{kj#Qe!@E&n^PUTo-%~n-G}2!-&UJdj^=I+Y*goQK5Xm1!cBx@PX7rLvx-%asdJD{_81l~}L&j_K zMNNTnK5RVh>mW1(1jkDkJPxiezhRh$XRihU84Ax4* zy(3-Z-zx!sy1vwIwzS`}-naEJhX()CRM5 zgsHg3CCv;T_f}@4TE2**L#UVlA3Dyg!Xr)BRyE}d{%r4ji=EwF~- zF}Q1hGdnPQ&M|>1gHyV!G$2`p&&J|b?lv7kCA`B;w~;+*(SD31-j#b!Hc%-}REc9lJQSZQfTXX>jBlyrVC5%B>v1Y_tKRy~KqzD8f&ZP`X;Nd zLWc*ROdF-fHc5YMkkY3jij=9Lxl&{70E42;&g*=BH8OC#hSt*5DrdzS+K`)!49s+E z(Hp*wP_ekMDEe5#7=44`Kc5;$CDa3P(=F6CVFEJJD#-YMSVSW2U z_{HV5wog%!L)QqjNl{!C1vRR3NqP*B-O$Nxo7ra3IPkH zy%p=s08}4QTwlP&gOR<5 z6PcJ2I$6b}c8duZj6^;GE#K(b*1R1}ywzR+Nn6p!Hi^6@GGtFFA>)i6{!fZ1~(LxrYD|JdTCv)mjp@sqh z1$hQjAMFRayd`*#GaYszdC7zUM@i9ExnPLS4Zm82WIV@Z3%H76AtP$uhZk>g9ybN6 z>2e+}6eLQThebM(lzxJ82g2;{WxhQaGPIVV>IQI-!()yMwjk!qD>%m~rS?XtjtR5K z<|B_Bpl_q#@G>qC*3Ry?4~PweR}VZC)_6U_XxhuzTK0AM$hwM;!;p_Wxrq{IwF$T=)~j@sUVs(;nK3SoKvkBJ+~g!(ZU%FM4;r=C z!Fh9&-eqqlu5{r=ZZZRYO}}O`3;2IM4)ONd2sIn07NePkC&`YYrt8It3Uxy-Azf`v?)b);;Wf-mC#^+(hIDccGn=fUa;{=rG!WcZ4c7( zF0U76lydx&T6lcquBh;+d`vy6{1ASUIQbFrXr%IE_z~P3vX4cIBy0zJP!OcRKV>_8 zEmm;7^jF%shX4E;l{D`Kg1G)Ms+y;1nbj<6w%fFQYzF`PuvwZc)SKWw_An z;A}>~md{V4CB8mA4a6LzmIr5Mr)GE@z%xCA`Oq@}F_Yo@Wd*l>pb{Qvh)=iu!9?HC5_yr193 z-~X@?E^NVn{=+e% zc-)T<_LcG9{oVVWBbkA%`R;!EF{smF_J@%C>UoL(uiWeZ-s8New_o^6-cjYnFMI*) z>jTkB=Z~Hq`}O?#-7x-q_9y7QbI{4h-uljc$DW`50RO=|H?hm|r$6}6(;tjo{|V@e z_WMEj33U4Y^iO~A`TOs8kDZ4ne)ba-e!L%!@ptTX0sgvxcwIogE}⁢Ocg79DL?| z>wa>dmd7`toxkMc-p_y(9*ZB|^S*0iv%Q}^S;6b_Cu4YB4s`b56R#_tT;ru2uHHB5 zRqI}j#Mp=jmw9>i*|-PKd0h^@d9a|*DxMtab;a1~kw3kZ!`0iZdo?XEc29=(^6;~H z5BB!D93FUZyVn)KlkU9l^YRBLd?|;kw_Ep$M((Y{@2vCX;YaJnR@^!1>k1gWJ70ZW zKKAp@WnU?L#`eE(gwimldzeq16x3@w(zENM6d}>g~ocQ1hyB#9i>b zJo|oTpK|E4ild^Y28RJcNzEc@N;G#67O~SD30y| z@QsRxJba_#As$~U;Og!6aZvNRee_+PzC8SX_^_`Z;`MdKcw*@&Y+si{Pam@Pb;VN> zzm&t(+szxP^V8-5N4|^hmxn(z?;*)wS3KqV>+%m`{&fYA$zABbl*84%dGPNj(m^Dm zcbPa|j5y%q<5@pCsr3m`--FrTD&gQBJNdI{xKLGfD z-thv|qkr^K@vjo5(=0_jU^*PA3;6sFA^{1rcW{SO>Bp$AMSIDp@GAbv;bcMwUFJi)-M0cqpoX~6e6p)eM{ zbH4_;%W)5gic=hb%yH4y8=`2sdr^Y)+#els-T>^vCgzvDH z0##&u23ih1Bd`&sj{*m9`2C9vl(P3RpfDQFGag$6%arCH?_n8&As;ZEOL+64k-NIa-Ly1jDNs%nr7L@+p%$2@1ssZ%c%QI!80r< zRAawMI5V046sG^qU&8c%a$x#n@xQR_hfo+n(Z~v3mjl7v8N=)H$6~@pCFB*{e=v=g za=3b1V!eUVA57-u*=O4xEa!DOtfU7AdR+mXx$~pf`h%anJp63l zgS)*hhp#=D-Rp`c>w8^3s!Agxd?|;kw_EoaN*`I)$T(k~{UGd_J0E>r@#Lzn%f~Ug zGuh87o;>%Z0h0!zhSHzn z;N{up)INm6>vCxJT~xd-e+rJ*v*heoifZ7kIDBKghq&DxTu-vkK_wT{^y0z}4IB zdkdvM#Oce!?}u;HWk%`xy5cEoUzd-Qco)5|E1=zXLHtqgpSa^31BAuYYq)9{G>pEfCiFk>~!u|KPcQ<@x`IaI5|C3&-dG z{qgzVi=OWOmz_>O4K<7YEr=ldQUS3hkSpzcrZ~yp1 zfXH)(Yv+YhzWo>9A5Jqm%puhI$Iq#HhMj*DZ2r9U84CWq^%->jd8qkI==S#sHUFCs z5%^=+Kl*v<*)z2Kv+|ee_^b-X=wF60`aW^x|Kq>$VPyWL`y(IG`~UoY1MK&yNw5dZ zC(-qf!*a$D>=c>|8)`p?;QgK|P%-YO_60l?)Ue?-)?c8{=j->zU+m3Q|^ty>tEq zjsk-3xUkLKc*@Z|tNDu$v3U2a;rqaj3BmJUNjE=^1OC;#5N45nMd@!vj=yow{8uvM zANS~2^TI!MkDjq$(C^>92ULDS03S8*t=c!f_GwPpcO*z@uLl2@vYBV%+yC^ko}LqP z4~_rlJ|onRTK`7ncQ*dF9(4X>56@peaD{s~p8Kop!tZ{*q(17yTeWX=;+IqKNAvy9 zzFMsxI`-}Bnm4}k!rEVhkujfUln5Wq)5!PUO5r{Hf)w5_ogdp@y^+TYT=0>#`*;5s znBo2M9i;buD289`5Ba=*F)#lxNcY+QH=$#{Oa^?9_g>Ncr|bT=Kg`K<^?X$F;eGcZ{10Ef=zH;i|KlHh7_?_YzAO3ldEXP# zeAeLi1ocsapCz9*_#gZ#8~oMxp1hA3!Jp!x@0_Xc;L!iwud=hh|JF7lAE%msydTc@ zxcQCFeK%YBh;&}q(#vDt{!LgyBh-2Wm_DnXDC~0}`hxYo4-n-Ku#w$UcTw*9VoM06gypD&LbB7ng8EmIQ<~j5q#~WWx}^@hp&x znEc6?&jZ~0V^ef9f4^G3U( zKm3iCp!;us=i~8vQpKl*A13X|u=`_BmHz0*$dNH2x0U;{CLyJ7ux$GjWi z)WRnbd{Xv-2JRvkdG)gIC364im$`X1<~}!n`v}`qaZdU3{_*2v?~i8o-Q9Tle(S-zA~|ZDkarB!F#ZqP z=nV{vBe)$aDge57_VYp#_@BCQFSGycpW$H`;s4+jy}Tkc^C?|^!+iPFozVW{R}X$K zLi^zhp*=r*C$w+=qDT0J9{<8W^~RunH`#tPFfU~LhWz{PjR^kgU;D5T0qlcPBsuKp z?R;JI;r}?R|DM7B=FSE0)A;54ZU(zif|lha&%Vbl1KJ0!w|E%O%TFJ= z?~L&Ih6eXl^3AwBzPT@+Pai5Sg+K1B@Z4S?1u6c`v+#>AUT-rn#&WeQ%<>Gy3fu+Jm2ciGbVEy4e$?~!1#!tcA_YrY?`8hp) z`FPP!AOC#yqj#^V{7dN1H+L_O>lfAg-50*Pf5S}z7>E0p?)xx&+SwnyAK}Nn{Wl{d z_$g$R24BO59OD_b&r$m3F*wir#@f$sd>NXr-rYa`GUI>rX#1bQLyxO_{Rfizs2T|4 zzFozLN$(e5zMuRb138S}y+hV_kCwd9+;_cUBu+3g-@EvH!xzA1z8*QwmoE+d(Yp_g z`q8_@cKqb0e`hRt*meF6Y{~KFGaqRG<)Ql*@9W|HQ;8q?*@*SWSCr?x{qhN`&A()a zUq80M`ueU8{Utl}VfU2xOZ6|=;d`azDW3n59gh6y|Cj9W0|35*_kRfB{k5L_v2OSa zmG%GT1M2@XDC$wbj{eo3~lLJ0N zzj5kI;-OJp^k7~824bF0sd~%`Q^_(X}YQWYXIu?sk&>iwHW3T__Ns`&+}slSC2J#LYH^Lr{Yp9cyLZhPJfBTuEW%p07T> zS5Eo<)T5RatoiZXGjqB$Oa-p^GyKr3t(a?!S4<{Tw>T#At-hl&mGnHaJ$eBvab8dt zg}9y0mtk&gw`x3J&ZS~^T<;>aGx3E$;@Wg8bDCNfl;B@ZOrA~5W66`n?6{cjj@$F1 z$n$*|hf8z2TS)H*766Bzx7pnsgE&q)jP28sqRDOd8Qb zMhc-XGi~5e7pr$fF=@;j&S^l=4T_-tA%nXz8ut^_znl#iN=3(Yls{JNbx=D zOAc4x_pK8Ol&R5y?cJzT)RICgG9-oQI+B*CHX!IeRU=)~`31H?eX5cAGOwr&qiq_& zJPg4=D9b9+26LS_l_nO1v0v?lQfbwd9@t885$E>84qHv=`BRvyLaB#k;n^ zw%{Y2y&;&5r)CGnZ%bK-QBO?|_9p3RheDd${7k?DGS*{s zIiH5MfmB1wNt4+mTuuy`=G2`npKV=E`1NqYcrGyUQ)T3O*t#0suq;ai>tvSB&-tmR zPr5m|O)uTHV0eVt+!(GooJxXrBuTndI)`SyPFL9Zc;v90ij3nxxdP5&nbwwiyy9e| zTla(mJC*R~eGS8SzIwv85{XQib_>&GZ<9lFIP5Xl;7HkJ=UQuAauHmx+LUY4FbFik zbuT!1vvBJVesii|{$nXzCx-%+i-Jb`{!%xJi29mPkZjyt?aS5Kq}a?-rP=#E7qFnx?0VbSSzN!$S-Symzt{P{ifY8gBB@tm`_i6P6oT;Z$c=+nl{ckpSaD zqR2j39p)K|awl})&{aq{`fb&eG-49?!J3L1hZt!)^o%8_8CPT23_V5smFRZDacyl* zq>4t(0j*buVVGTNTtWghIeINw&#-CJ+=A_Vf9(bo;kKObBW>s0P~Hotc15t8lH-uR zS2azMk5_%OI>b~8#N*~iRibLLI=HnVgL+jD?qs>2p9!%i;!Bw=P&v;jw69o{zj=G2 zvr1DTqn28&gN)45)Ku&9ZC4TW2}K(P{baWa{Hra{TwVc128M0pc9**F9Yq8MgEBkbz4jRu+ZfK=W zBq5*#2X+IPsKmNYwphfL^9j_q4a&sl3RSe=O0KSc8HT+Q#j|_l&j&o5;B)%_cfbgn9CJhramD9T7fhTt;hXy3gDT;Olv>+AYF1Dsaurl;D?)4y8 zNXiE$O`LN^iqUmn-Y)#%h%aOZ)kuD}&DYoDu;F1F3W?pMgTJ0mJ2pg{rUBtYu*cq0 zi(_$QYzm)t+AUF6`$*v3$*xR5nL% zyIPO8hLbMF`{R>@8l}0G{9KgxOMOEEzn)r+8FyR&g2-=-i^Idb0fOjzV_M8bVcHD9 z`}nk7PNtqpg53{65Q=IVwBPS?%$~T6bkc%~z+lQ#JSXLISD#Rv-)uCD-4z%v%S(#m zj&*9MgVzkjGTEb1lHkblVkPG`->yi>G)>>-FtH>q#6l#QtsSq@)83r6$}~QSCtXdD zmG7O=&8b{V44V!uQpDj`%6EJ@$j+22x$1thPI-M6sLS0g>*!U0a;rRb8)Yf87_8#;)dM_3 zosWP;yCiT3ZMN&0<#4HE58o~?un_hNZ!8aH@4FJ-ND1Qzhd>kd%dL;kddFo`8Rs^% zk5;Qe+jLZa@+R^8Br=EPVgV4C@y-m{1f}dSq&4AY!4xyQhHY4Ewr}YR7gT^GXc@NW zfdjP&VpWK~ti^82t;%EKYJ{V)Qew^RO~5kCix2{SKFb6><-$m8Znd3hZqV|q)O8n( z_oWr)tx19$`PXE)flAW%r=Z7?xp!5)%0fwGjt_X3=00j}2gXb2O1I_9{OlF(1TcQw z3Ifa7J2WDj>k3yomx#8iwUPKq7kLn;Qfz{RCg_kVW*7>5#=m7^N0Bp-bGr6GiQF8J(_pe0GZIg^G@|$pH7Z-H!)cvwn^nlhh+i`pC>CcPms~dD8y%q#z>ejG<2z*Nck?ZG0X?Q(cFmmP zTKZ<{tF@la^;>X8QIE7-)a2oWoxPh>i?|{;dv@h+%cF6yB;E$Rk#E>CmC(1zKvxnfSL)e{&Bw5B1IZ-pP*%#H@ zT@Dgpw_rV2uQ!Y^vDvw0x%iD+8`Fb;xNQiCW_LVhsUy&AOy(Tns!?qF1x=6_9<>XL9TgSm#c$h=W3M!0+$^jIkM`F+ebqXXDJfJsOv-f^&IDFf4Bq~zr6PD)d?M5 z3s9acNk+?VLMGD((S_@7=2?p29)mOG&yzhl@=04RK-VHSohwGWywwJp>tfCqrXzpj z_{~C+gbFZ5)igy6nC2F;2(N)M;iW=FI@gTPGF-kc0769rNlKavijX&*SR!^?C3_ym z0>Naw4sHxyU%N(V-6`mli>L?vXVDh$-ZIm5;QZV9WD=k#?C%s4&hF;bnHe=f;O8VL zhE2pE>C&2(*{at&p7+e-4M&1}4Qu)~bi15#RejyxP?f*+R$eZ;Wrf%7jV_VR%~b_@ z;aIA_10Aaybu4;Qdge6ty6aM!R?Ci*lgkOP$&AMA9m|b09x!-}1QrJR{=wZ7 z;v|S^AWa>an=G?dHLjikD_T{=V1q8jt4>PQr6YFog5lB)2t^79-6NF<*p(^*;E&Tb zo6(-{=c%umb?^Eck-asIR>O7|IJ1w7WnJGGkl$XD)4DAINp!2IB8 zYfa{>**2b-lD66GS~MtHzz^0|>cD6Mz+XIgH7JpM5*SE&ojTjI*Y|qA}=mX5;P=JI2MN> zmow;U`muKrpud&8*C$0%AOWD1Ac&)=%dzQYiD)NO1H1%w3)){^CgB9ENbPn2{jcl+ zm(c4QY&p_rU2xDBVSSoScGVP7XWQx=UMjMXw5**)b;I`69ySYJ_G=wuH`#zMQ3An< zECUtFmqBctF=jfYeKU(`9}F6cDY8{>c4agxzY(i~-DBJpRfKcgpM_+gi-YYo&Y&29 zIqfDVQID^lI5<^KjAoI2IazL{9li-$YeUGOwqr@C1{J?K>ZpRB=7U12tqfMRr0o{Q zz*tO~pE)h$f#-4Vl~e&cU&MGfsGVaGnV)Z%1&IvPu&#hX>@8blYssAt7uN6G(%X?q z-=);i5gOU*m!Pn~wwale^{d5t4f^D;&%INInhG zD`K`^Y4QMs(J*!^88ZybZnT8B2s+(v=NR;Zz;3$ETSPkuYiSbPSQRs8390Wqgj;xv zTHI{q(C?0fthhvo;Ul@nl6Vc3Y?z}V(g$f1>Hq@8!<7)vTw}DUj#vy4Su0xLQKr;M zf?rYmwVLy1j_pndIz^+FMsY>t>r=W6#Zv*Q^sOwD^vcTqX02awh(y#)lOw8%r`DmO zoh>y`GxKo8l`QT{s!^k>O{=?jG!`7CwGQTiF1C6_SZIJ8RC3`<$pj~Ak6}Srmutez zsgMO6g*a>>?6}76IbXuf>{b&OZnYNoEewwuwRlJ%`qCG@`84P_N2E8JTausxW-;g$ z?%=ITY$n&Y6!g~eAa$euu)7kD*N7&{_6vMIApErj+ffs8()5#p&0(&hC zu+TL_7mW-i`P_)3 zWD#DizNWb8<-AqU7M=5_B#4xZbrYAdaNHgkce;A4b;@f_Ay$F1U+Y`p%A2#u!7hl# zo?EZwF(Gz%$y?dmjy-LULsQXWmD<9hm^0g4Oq6_WZ|m|rH2Q|)`l{O=t#c{5v{Tcp zN8plzt_t8b%c+Gbiy0}4#RRN@WYCp|;oyV$!`$;ZR)8waRmM`=5>|cUBqkg}SIQQd zjve9#4B+c)6<;-mc9$Z;t*BCA{mE>HR5YbGaW=8sQNQmTm!OeltmaOK2`cWKRzbiH z1#Hr+uv8XXB&VLPdWZ6SnP)fp+MO{hhHm^TFZ^qYv)i>2u9|SGEcGFq969% zc6T+cwY)MDbBkPVq+R2jC^;;@RFy66pu>`Ewr(1lEa#^40QAzDFiv^DSPx){DKn`V zZA+Xs4R3W*XKKd8=uxW8A)QsUU+ayRD@NtdFOq&pH72^CGcckY&CXeCi-B(Yz&p;S zq$^=E8}yjm&JX9n61{DmC`V1GR?FLr3T5S@C7g#_94ut;$}NkiZ02jQP=1SVG3E_mz*FA z_8j`yH~a?oTyxsP;NTa&9!_AsY(p9B*?GNNV*Wl|otHgrRRfWtZmq9xx1rw`U_u0y z1Ku|QV2=*`rL*vq^)4j9Q@62qpywzDg7qr7ffJ2(;L)hv_+)5Sd8RsHz8PG0dA%ma z+-l^Ck-?sJDCJsFLra2`Cxg(y-nu2{ppy(IHOjlpy!NIh$8-!FJ!)kABD5tbsWKQw z2>N!b(y#-!mb0+z%@tc8378-7qAEh^UiY?dR;}F0D2-A+l4qG z#uZ;~0hkU#G>wP#ZLbXl#wrBsKJ>V3;#+!xU3aSmZPYf3t!JFT=7a#o2VtR4L#!|@ zr0h;H-I+bJ_8r71$@uTBLTu=}hQ` z&oH|afXAkq#5+Tv0`Yed1&HfdhqoOz@qahIHS^Zh(oU48OIY(_hx z1C}*w3ASsyb$v~A8~-rU+>JcJe(AeXJ(1{aHV1t1}3Jutk37jZiX z;^J)W41d+sV6USttKOGH0^v$y=X4b1AwK9#_yx14z-u^mF>r`B*(zcQ_;>(K=)~EI zxZO%q@JN9PI~{;!11P6(OT#2{nr{&t4Z!N|$K_gQLDf$1g0Qv=WG9me%P1`Gtp#pM z&tUzCol>unTqNBMJwrE#QU9GEyj@|i;8{VYqIKHkdjzjdEmKm`-l%}T(`Zj?!I>EC zsSpZK@$~vIZ_rVd0;*$x)?MiJoF&s<g>2WXNM3oDKLXdHy^2Ko79IqbJ-!oDu-ji^t73<*v5(bs}b`? z>>X^QBuQkZ*hody zF5k6T3ow?A2Ar~zZPtjbePCyGxyZrh1*qW6`Ay!ja!PCxz$!dv4BI_=+9h`Fr~UFG z);TW(hh&xQB0@X_^=8E)fmhO!Z;fH0EY%704G7u-uDQ< z1Aj$uOaLn%@y*FlqGi9|RG`QbL4jRCeRovpyxh)NaEZxh@UX=Y~LBzw~#%G}uyZU3mo?0r*cQ=?<*p6PG*8X!Q`s%?bK_ zG|rZ>IILPKwojXswn||jvEw|wkA+(T{^n;O!+lZMHR9+$G~}dTIXKHRjJRdmMR(M2 z7H>t>2h5)>rvRks%5~Isxg42Qu#XFP$-DXbpXx~PdYHG z*<^rJ8rKUno>VGRGfF|C&zmf{97C_TO7xX$oGl`>({t2m+Mcga3vF7NfRjC2%GU7F z7HT;g+n2g{hfub-*8S~boi_6&%c2Ms0nQ+>L~YK*L_@*mWdm=kCa~^~lDFILDtsAH z>~yJG*QUJesZ)xa5oH@i5*VqDX<=9gg9mM;Myr-*1Y-vI$!6*iAxaBTXHDeIxs7M@ zAwe}`mKlJ5C9uVoCGML?_Y|F^bGvX=&Yr22iwwrG^{LjM>By8p(Q;BxvSPmReel_C zqeDZ_k~p%`j1cVnikIMZ<ma~%{jyuvi9ho4&IWsh)EvOhJcOj_askz_0%JSoiC)(7d9k=$ zkLaSxU2*KpVJ#st}w@Y`~0Hy1K?r;&nW zmIR!*U3Y0V12JtY!e!c8eJw)USK^)bgzUap}yV_H}u3ADAhFfxbofCM#9acv)QKGmB&j>C}oD1$?wJ)C4&5icK zxXjDNI(LO!U5G8(wUM`y6uci&3#sRuC_Cqe!>JL|ke=4o%oHj2D%yAxx$*JJtyi6k#Kocliu#<0{xx)NNq)##Lm& zvAGIodkiaT_#t$IzM&5E3Mo}?>C*Oa24DQcZs9LLzpLHFZqeyE=%*3IgYQH|8c{jS z&KU4=22c9=pbyi41dvlqmY`1*>yDQ~v29ONz>W-TN@D8FIorDk!L5MT;fi?`g?=ar zE0FjQiCkF@ZHRmV?twWt;`1tb>(Dd7+Y1ut{tC8iZy0?_ggphDBg6@XhLP4QPZ%H? z0Uv^mid?+R%xN*H15L>^a0^Dtadu?rau}M(@8lBBA?ZBpYFYD0T4n9P=xblx7&`8P&}frhpxuiKInI6I-A*BP6-s@vSx+&hYDT42l1G5p>p2yI~?!r&~iE-qII>un1vmahoV z5u%JZqT-Aryj%3qgLptoJLhM;bpa3Lv^bnFl~8julIsp}O|`fX_N>%~V-tEyumpf# z841?Y(A-r3O*%sNHd)qvw3esaAAQJkbU-w6h8n zbmf)^^I~h#exNP6B{f0Sn$2uLtjC=jJH;GA^9V!4T!$>H$wHJC^`a_Kp~O!(jkuP@ zG-=+mtK|-40zs{7*^*bo1;AbY)+NR;5F4dP3n)iM*XsxVT{ zk@WyLir@36BUriUf(70Dayx{scq@WpMsKZkGPU)TMm5o^f{w*?=xeq*+00rbYmz&; zvg=k9c*Au1G~Y{c0{$`_N2wh+BHRN%(ta$NY!qoJ?txxl*6zr&1}%w%jtYov;v`5j zrNfO>#lm#~Yi1!WhItV|mo(#R>xx)ZUTJ03$YVC^1OMJt-Fo~Yq@IzbeRdFlVUsX+!MhOtXw*UuL5<<`x-`>(%(UZBHL(oks*@Qw{av(6Yy*9MIhzoI(3_X_ZfD8$Oe%x}fGx&`h)P8aO$wx`7X*=fGKi}~Lwq>I zfy!Oj3*`*aJ!3e~bH-7wI%{Mhs0PFm&p3x5`ujWy`p%kV(lzL2Qj)f*H5{hqUVh-$ zVBZjU&YR4#>UgXv8Tyuc&2CTIZ9561Giyw&nVFQZX&^%6dX<=+UCr5bzQ0*TafS#x9MheR(jP7~Y5wBLcqWrMni;(>-QtGW6tW2hljW z8|#j61*r#p1TB$mS9K=N(Q5e z<_j<1WDwSGn-;Uwm-E?$DGT;OVBUUyq*nz*-CU${0m_+x5n?*(oX7!dLWBV}w6YS& zDH+>T7-2ulr~WQ&H7glYE~rQXdoinJK*E4M(jGhXvl>hFetStEK8#AQC0-${3bvx4 zSX{jTO&lY38KnkKu}3-R5xLL%vDjJ=R@*@&l$T+W;S`vxue=F_zWQVGLOX@{W-8ka zE1bY#w)U5{UdvmrWX}j_o8WDjvtlvVlq*i2nnPn8g+pyRe!$*VGT^<_9O6D#VS2#X zP4e&+LV&L$a`jcW86r8_Qud5qQp(tvv8?_{g?~(#j(+B#|zu-`jSHs5Dx~c z(FZ*Y5SlW(Cced9u6@tQ``!L#cMGoVPO>JPIv{C+3|w}#nu88=mGtNWpv~Hd@%}Kd z^lA!muIXW$&qYNN(mk#2`!fx8Ky#Vs5U#yCLTtGx@kn!o7}@o_G$1r=v`ZCB0(>Ia z9MQzcS0OH$jxgr5AtlFgJg^W`Lf{BBay)d+pf~ZutpeQG$7acFsRli-pXalzK zsj9lCGAgm-T3udQ1tzuK-R2;!ngiIvAzB)-kB-_LuRF~&C1s-!z*ROAM9qSFfS6N? zj2Omtr=sB162y+CCdBl5ZsHul20aIBZb+O|@NVe9o4`H1f;6CX*{ebhIb4dIahIGP5ocqw5Ut&v+!iIidAV}3zi zag{B*k0O`E}LH^(?ei= z63dQFE3-dTEm90rvW1YUo^6q?->tWdhJ^Qxs`dNUTo~?s#b~ z%YCjJ^Odk=A@~MdgUInL?}sLvmD!1cc!XMouyQ&?A)IOq!>D+tX~AE*W_is7b4{49 zr~3;QT=i-Pc5;_==T}}l?ym$jBXX~!+X7wvRl49L9QBSfe*Bs z9FyfvEhXL8%c zKIDO&v761S=$L~t&|u{Q7v!Nbz)IXi;RFHSO&x*fgTtluQevc~FybjtPh)o2v*KCQ zywQdh?V95f1q_xch68SOX*H*3y)Na!LWh_ub=GA_23aISYJ~bGWET73+DYAh!8dzf z@==0>+=FKA;Yz*izPz9wkzqQ1@$ye5qL51C9M=EW$+H)=C7i4O>pnCOkOsPGl%fj9|{H ztE+w@SBvFUo=`CbZkMnSi_M~<^f}}}ZM40XV^MG2S0(TpQ{^r2 z8QVD6`QR{AYLXkd3pQ;Al&>bR4^%ThD0wMgZqykf8c0f=+TKP!nsW?ID8o#yjPu$mCj{QCIFVop0JbxC%q0TioHYT^u(;_vWw^N8;P#stpBqk?IXR(M}6H+l-)sk&1-InDT zWqG)s*VQGh#G8KHs0;pb;v6#-ck4m`Udvu-e}aTm54z24w*VS47gW(@y?C9iO}yCA_rN2Nyw%P*VLI@+(?ozupPG1N4*Gl0xGX zL^yI@cw&bWZbe6N%V`WYZ8ZadWKh*Yu==i(_`-Ivh(os;Bgk4c? z!2YXUT+r#XdB%5@KCO(3yyk_P1YVH(rP@(C$kM?M4yz`^N9PvP90Pfk?kPe zjZ>Iw0|x8?V(pfo(}VZmVmlp|yA3`x$GPAgn`2ei(S(kUaHrJ+HuzD1{2} zP;l^o!4+)FpvxV|F-YxvkvmsDmM5}%=1FKor`_$B76N>9y-FK@f@!C%Kh6Ii_TDX4 zmh3za8&VXd*`X*hgFgkq+^x?&DdsGgRQj48#X)+3jS z`dniqVdJz;I@4O(V_~Qiy0u}s=H+c^McS_7P5GcI)WQkx+8(xY^>$m2TkR>aRUiB{ z^#rlqH%%IQ#inF$5R5Y6ok}5VXs+5vJc>4l-oFmmVz!jh15CWzw%H6iNIbI@Io)Mh zyDArFw#bBSbUD+RJL^&+HCU(D6IB`rX`CXOD9kD(|MI+<&bK2Ugp07Nwz7+2d$M|$ z9{HgG@b_31fzO$Bl^N;NTVGq+l*iMVH50Tu?Z$FRY)*(@N?=Z=hSjBN)oW6DuFNzb`I;`I0D2kpQGkZ=}?Em_v^7O7Nc*WrtsLIO6_ zR)5o?ba}QOWk+K5%Y~9gXQs=JpB%0OO}EpDY`@gmRd~|v z1eMK92nH~U0a1B5R9BHqr_*wEsO5(+5fmFKrCZMyOtWk+<0`_An>99kW#HVy>dOE9`KExo0lo)k)i`Xf35CD1-c?dox`Iu^$Ky$|4ihCUd-L9+3&3obccS=G(;s6)i3pVbvL`M_ zmg(pYHiTNyn2v@@YtXdf%lry(o}4nXM8DVd0UYIjWRW`~GZnQ`v2zJaiAMa@pmRLDPDTo+$6bGCXucQe4}KB>>A1@e5ggY)vRu}z!FN>8zJsWMN};~C=g%N z_acrC1sj;8UP}R6A83eKSg+h8Ax@6z*453BW<>4D@U zsF>~6s$ga89AZf(TZTb&;Q?3I>n)eM$@J=Fb6ZQS17PCPN^ZCnC*2W{PPr<}!vD_{ z#RL;}N^P3X-ondOE4yCG%dRoIb$iJ`X_FXd-JVX@sZmgvwiN{XZxpI&t@F8zmmzq$ z-D;tuEHiAywP7`bt$2SJr*cbg&=N~RD=UTL9A~I@-^`os?Jg`RL%Ucux})4!;A=)P zmq<4_SZI>T`WSttn`FA#nj(z*?EqM&2_iG*VVT6(CJch`CnJ$z;na{{hou_(}aj#O%0dnSd3mc=P1F{2rqsg{T+Tz{$e0%z;C+*PyL zXb6aRvjd-jcMClf!8%)n0<_BcbJMjy{nW; z=NiOVJ6po=Re_Cfi2aG^g`)+(U1|I{$1kLAXH#e^DPT-_K+8r2r6~>5TPiQ?vhW2+ zBiFB4tJbnI9S_BIv6|+0k#gVihZe|q5Sq5Lnuy||gid$sH`LBdm}dYCtu~4kPp|Ek zEpur0s0Ez`eraB5aXHs!_`Y7Nb;j^PXR&Pd#oW+NwpK=>F(JCEk$2adhSi7{?TI!R zt`v2=%GnaJhsaJZYw}&7@uyT)^wN^Gq9+PHx-X+@g?A-TyPNa zTMvtMYr?0pqj8e#(Mt;re*se{1S6~5X$(osF!qg5^TB;mmUcm#%T9Z&kxJVmtTEX0 zb!NGu08AOjAQUMr%zZC~n4xaE7B?4a^v+}I4J!Q=V2KG~o+vjE_(Wq)93v*EialL{V+M4-oZ<{%D=gPlXEU?j8)VzQ zHFUEG$(SZ+=ff>*vn9cy5Inq`t`O5TXmjurEc8j( z4JsRj=w{0y2i>e3PmcgE9OmqBncQN{P9&N71P%tNR-f~RzS}M0H1vA}dSh?q7I#u@ zXRPdLipll3Ik#LA{8QHhVamD!pPo?K#7Et-G@AFSYa*k#FzTmQnQEokD5x9BC=BTd zJ#Qh>XwoXC!MZY0021Eu87>D7r^+}!%&{GQJz0cI0=!Ehp&DTvA-)2QS8c3U@g<^L zNUcexE%Sb(V#M7>d>X6~hzB1Tv~}zSEbO3w)X8PBH<XP(TdOO5%bEbLhw(MdLp?g?6#W%U%>>^1IYlCu%*3L z8oRy%+oUVkS5@1d6@s*G34MeaNr6G!#Iq#!O>P666Vr)a!VGAHEt>eJN=ARp@@b}? zW*IJ?Ehhv3g&d0b*?Nms1umuy+tdsZBUH_$;*~Jnr;6J+FkHRzv~E{bwg~*!BASy5 zXuIWjhq-IrZF0I;lrVpe3zdS}peqwFDEQMrX+k?(?E6v~b6C%s1qk2HAzZ0xESTy} z#(bRh(jy|=!N&G76X0-a6`7TZJ*d;EfIAJuHQ?Q%x}50{rx}|cC;V+L&SaI&w6TCe zcacbn60dZ`N>wWJPrJA$-c>zuWt;2brcn&i!ziX;TjM+! zmCc!6BJ%GO5-ha+0CS%?3AJ$Am-6*h$*y)nfV3$c1aH9i!pB@LRC_7J0!WHD&WJS8 zUzhC`HQ5Bv;kW`poOt1k*%Z;XHA|9JOj4^}y1kWrKZVFf zGXogG)bw&eE&8yDOYP1=oFGo4o|e)%V0rn%a9LDI8}F7wGG{cK>sHb#X2VIUnhUno zFxez(T!~ARHN+?^#DHDu#P(_D8|V{mu?tgmglk5y!3^%~a*%5-ur8?S?ljO+tYWry zG_eO_Mjw@n%Y?>P#B^M;bKMb8C)iuU*WKSuR$Uv2g~_xJ?hsx`HEJHV;eFCq+exOn zHMVQEp>~1Uk5>j>ez?m?GheLRz|8L^P^kUctX%={qLd=qf(~AH5?c;1BIaRtw&a3> zl?})1RyrXFiWxA5Hk#z?@E>=YeYY^J*B!s0WoVy*ol4Hj3)A3K7F1+SGldYwc9l)8 z$()qW0LwjV%n?he%f@Lh<>~~Or%rRZj+YZ$U#uZM95&W=qC;dl9_7Horc`*(lE$#Z4+4>`&{c?3 zCvnq>nLCi--YfQ0GPkUlq@*UGvbCB;s5`JZv@6D{Rd+k>IoGz-jZqs2t^OL?RR~iE z`G9WFg()KfM7vE>@(Ob&76xdx&dxKE3^u4cboxnYPHUU3o93f-M^ z7<1LUy51b0X7qvIN62q{d5ggNCAgvLot|yX=RrtfA98aL z*_qfw%-ai~imDQ<=EV`S^0pL+R3tIwE|QzclI8-?OZHRgp(jHh0`_7uXBBvD>gcK5 zXru55Q(RMR(;_h&9=JoY$kXq1;a@M4y=I}?cJkSJ(K1`u+S|31J?FJp~gvcpm(0T3A|^n(%}crq~vzmP2A6 zDYf<7E?5=V#5j@GicM)U<$yr%Z`=LSa4-TH*=*Q{PYnSYU1vRBBcOi?t^==U4&Xx_ zjm9-b?!{9Aq6hV^*Z0Ar#>oAF2U36{@qyR)Mz~sGQm$j_&l2vBnx%y8f#8m_<3(@2 zR^Uy*elnkF_4`yQJA+KPGPPUhI5U|m@H+fPbjdEYb2Z?9<8gniuy9}QR>j(Q5`aW5 z+;-8s;lNr7J!w1LUUF)hU3Tfd7FvUm zSLnrq+1e^L0H|-p;Xf9YZfRSaEeGkf0@AR4wPFjL8q}3UX4)t%_!U^Ff^5rPkNPU~ z4k{&2pf@0frnj`yAZnCNpI$To;%(Ee%vkebC+k>*lP$4YB?v~Ok~JMVTM8>pXDK%2 z;z$4nEw?1L&9=FLRhJKnAbd-Yq=}dd5Rj1AhMmR|d(Pef(O>##0TbOQ-mD6}RMSdo zglDoZEJ|>PCkc*W4DP|9+KO*_LoPF`*h_xrEp{BUUxP+$s zvl*vbGTGaZv0NWlds|^^+08_ALuV2*PN`RwDeU87#Y2!B!el{-Iuccmcjq<<*5t|>NRGpTgwB$w_ zV%(-)Hckars-IL8acjCAI}tY4VRl(x!;ijl6OAPuFQm-obiTJ|WA@D=COd3_nXC*> zu^ovE@f^Y>JT7z2csb6j2eXdnsm^Mr4xmp|wDEuof!FdEEn>0D_k?tr@aow$HeG>E zT5h_2+6+1k5IuEQ+0jVFe#<2LEx^*_^=!66FY_6|_>7+lm*hu{Lmh6+W>hWi@RXClHjo%Qk$RQdwxs#bVtMIe*&k1c)Of`qONiR~J?` z(c9E2#nz;|N^L8~ZY@_jJk;d=(qhGunz3A{)qSkPP0`ca2^|~p%1&M=NtU5H%3|K4 z$eJ`%h~Ydw&atDElhsX-fJiVEvJS$^?Kz`#3dszsbt;=W{J?oDkS)JQYa6%xyzFg+>r2In?v!&5huGuO_d#-^?_j_xc9nxQJ8?$T!ao4o9$@OeRidDKy zT}xC(V=dimr{b8!A{(0pUJ)Mnjs7$Mz0_9LuVvmx+$I`&#K;EB@+%I~D|oi)>FPCd5}B)S=?DN@;WZrUA++mTxzh5Tv@ zmsL7pN}%m3g|fqn-SKE`BTg2fM^^QmOmeP`640g4U zS?;C)K;`5y?7P7jFm^Sa0KpufEW=Tz=cs&qXWJ6(fk|j9XOam3Cz&?zIlC43(Ug9_ zRs#;9;ctnV*`%REa)ZV$Z`9h|a@=XJI*qKEXM8gc-c~0$Tb0MTbbRb~94wOXq7>3w z1dx`pQ)i3)h`UTTsC6|MPBF(etLvPOZP9RCDD|sNu{Bi?X1JTVDd;=Z6V>5TOFx`+1GMsZf-2rmJ@$&ERtBn$mCOioj9#I9HUP)g)-=}odzab?)AN|rEa z&P)=xDd&16VQxfty`JwkY|E0WiJ>vpSme0|C+SkD8!W0nQziJcMut<2yKZZ#w({`J zZV*u2TvyiNG+pQhvuqA9FEWoU8g6AgV7v5YIO~t+s+_Xsh#zY;oT3Uy5A+g81|3D3 z%5RtbB=9w*P?#f{&JYsLNVGIgsHA}HtigoRN;SBYp4#xXpb8dM-PwhD*c=y&40sX1 z`It%u>!s0+2L;eeRDgcUv;4+%Rp|A#PO4m7*X)#7Ee+V|REGm%Y^XE%iI!z>_^#$O z%Pl&UU1pMF^l1a_<`v-{pAFbqd2P6J;M%vlq$XmG1wWo9+Ev4~1E-TN3iEXVZX`^p z1+aH7d^TMj2;Ed$obGCK*jA)+vOg+2`MBley7hd2Q5@HkCO9(EQ{Xf5l%1g0xuB+l zMrQk-gz4rex7n~~25epRHJ9!3;{=;7WU4T~wW?cvR_oS)A*yT!nf7!C zEJ-PzLg@X97v{ref}yAh*WQe}v+k@E_6AHIYhAfQL!vtb#{iO+qNc$%o0#So+gjY~ zXX7)3vSr0;*{wA#*{P*X!Pmick^K z-_UU`*`3j;Wa#9QtGR&nas;**=ol2jB8pRY4aPXqSGu6V$tHtE3kSD}HMJSp1RBdU ziBa)jfdjuMTc}dLI+91b`YzjBurS!L$WNZBV1Ggcs@n3jQf6iFOk%qPUz7v>N}&^o zk|%1}O>2xkC`}i2f`y){BUTxa7-Ix)8$y?DRH?9`?AG>*ZcU0XJF%UT+$j1+yE`!3 z3>?^?3op{;ek4=Yvpbf>W!F2QLA9xM0|1Un2k%d7s=?N)Q1w`~;45)8mkb&zW0%od^vX#1>rAIAVtx^$o<0?WH7^>JVQ3j~5*Q4n;vSH0jZl%4j z*cDfmHpFqFTI8qfG9jyUw#Za7UZa|-17QVTp-nRp z=Un@C8l^F7tV;l@PU-y4p#~cCb8zMN`e4>d012m7GG22sD{ix^TD2o?^E9}n z7yV?|n)yZFaeZktY~<3FW*Q5p;qKIFvfXSoGm|(~B{mM6l~C%4Een=d?DN!0U0YFN z-W8K_Zfmz_F4VmCasV*p&>ha!tjTeXT+5oQSrBqKwI{=RBPm(EdDmH#3`4Ji%%Vk?r+J0ih+S(Wwh}cPE<_i+ zpya%StxywkRe27Oe{HxiB$b6Ll|^jMXp*+7N&uIl>{Qr(QVnP2;)D()Z^_6~W}E4Zu!h5M zG6>?WnIcK6ykem4{*DD#MRx))64MefPvyILue~U&HE?gqy@H=u)vLLLjxaN<(d9); zZ@G(EaykY94fwVC)HbUjUd$W-n=~B`SFJ$ZD0OxcjiIm{?SI$JVwaNEySQ+%O5n~# z{JYrdGNGU*voNKx>GEy|SXZN7h!7jPlqs@_#SEmMogxQF{#qjY)qH!_Uz%%h-)%Yyh}}|*XR08`1K!RocjOHj+iV_; z<{%q$u*R;#RTA8Z#c8y@H2Hk4RGrR2iJMK#)kuFRdHpn*hpkkvLhRQFsRrH>BSoTH z;3(c|)Yx~H6%&rLB=5z3)y2FX?4=R!Z-*i|7%P1VLOPU9{C))w%@pLUBiode4 zL9NV(vNpyx6`Vpk@PVo3paTFGaJwZO=8}I^TM;?fVc1(rpi{IuC15&O(QkFTR1Wxp zI54nZk9`(-pmcaKL5Ok|P8T$O%0K-eOI+0SNLEcDemXj`aar{9E z*qcSJ?aYQXyXy~e{00R>*l1k?)0CJ3f@nRit*3Bt^J7BBS+Q#%bF_ht$u^vWzo1>~ zSbc3_3?hzW7g6}R1~Zh6)ItqG$A5z#GnLf}&x4XpoUxI-uiIe!93 z|AsZr&DUH$)6dO@3VIG0pZxe#DT`zeh%pCJ_`!IyEEtYz_yIsz?y@s?$MjB;`>@Fy z+(KhgD@1(K0P-!g_-3%Y%^w6zm)uAV=n&BQRx%SW6k7VU&u+j^7@fvq0SJm&25djX zb~@@55p5*f0eIqfsW_#qL>zsCcp$;0nC)0u5o4gu27)#Q3cr?KgZ!uL0PF9Lm1Q^d ztwp8}5?`2;mqo6fAHi7B55QkAu5qLkI3e9nwz8swc;)w zcbiN;+is3lpyDU*jbJC5ObBix1aWLq!0=qJxBb8c%kM4#gDrGk(53;eVJl!$QVGfK zys_!J64)&fOj<4VyPL>1h%Phh%qP=XCbGLOz)cH_WKG190Q#@;SXI`9vz{|+RvIY# z&R~vZ%^f}aZv)gtGy3~iR~>%!XD#d|?+&Wk3%7e$;AATQiZ8bo{o zEvU2{4)Zp66&Mf5PKo3Cw6V&Dv#K-J=YD#nr+gK*`_df1h|};Nwu1HBK}c z7cw&dYKRR@7zX?f-E7coK~qsgt{JWKoiylFo54g`FUn)^r=&p($2HT1M%7aZ)(v{9 zO!h0|^|WLR$5MLJU2*`P=SOi1_yV9cNDLCa;i}mQvHQUP>t#Us1(Rj5B{0Cm_p%xy zkx7gYo>|c|DH&JtbDUOGgWpy(xj8Viwa#vn!R~%i4r*F^3B|3Q@5Kp*L4%Ib%oY+& z1BZHvt#CiL56IkJ(Ka}!hSH=7!64=J{D`cj+GN>CZ?|hIp>Vzeih~)vITouX*!&yRZk*r7VqEb$Dm3l@IN7SfH)~YT!!vklL)U*s5W)4sJ%=VLHOckmw z_BJ*G+lom*m*hiVooL|Xt7uCa0Yu3{U?;HI?!(^-h>e*fx>nK~55d#`cO`tIZiV=` z$+LK7PR_5YE90dK1D79`q(LqL5=l{7CTT~6&(|Am^_7y`?fNdW;43<)1_!G&6;NwG@Xt6|EPJ ztxT=PRT|*k%ap0C$aUNrE5?Vg60L)Ql%6X_BeU)0<{NtgZ1-e5SW?_(2s;HWQUby> zmJLtI@d~Uj@Dn-fOgsrf+?+lYY2YZTQ$I0wIx;p~t(CUwm6zo)kWnSN!%32x9gnLu zo)WY`rwYBDRdS^2Ofl>n9K3@?OW7dWZkx6d_^9=Sj%K%H+nN>%A~o#Qx`sS$FU7Rz zl{c)B}wVmW787GQ;m&MTtBO_Vmb=4lgII&(QZOawglM>k1#xOn2;P_rO?e%=^ zY)d#*1mukRdbkY6^kxuW)<#lY477>AQNxwy@Kpo?jj(ng#tEiTDNBhX$aFfHjd`&@ zsU*Vt9R)4()_bQMID9@w2uz4yHyb+1_>36c`|A zAwEvnpfql`ffn!Sy;Kho5f=8mZ3N`-V7*#*7-h?WOR)xu4aEhYu;qk(b(6I#3Lxfo zv0~%{DpTOu_$c1kdJRj6OMr8hi~;7NlF7{wY%?_+UfMZ8Z8CA#@iXOxHC}fnH6}Hb zCd@!h2TgU$7XzB+s1%psQ^`VQ8CK(EoK0iy2F^U_&4bEHLNp>Hf}v!!QQ5&d80PXT*NM-phEf=emN>x788@*T zv2~5*>D7?w`xVg3FVz$d2=p4Pq4g(HJhSjuaz8~0PC=UG#=CA76yYSWv&@G>QFKdG zXVjuSTMYc6y7sAIC+_)Ze;ci0Iitx=Oaj$9uFT_edb`5B1oeiSbsK`wRhLS<$mBrp z3e+}-^E`ZdSEkx2sh4Z_g9*QD+jcpwBF43+*vyzphE^fbXAPxKVecTwVaKM~Z3DX! zD>HPr8+6U13*m2ZbI> z;)M}2Kym?2r%zRBm4X?dX>ecxu5A4&8nHBmbG(Ev7F>k#`qhYE8q*6GY@D8Dm5p^H z19xk23zadGt#10|ATF}CUAASGoKh~c=33;0L=ZpICPIo za$C??X8ZHrfN-eea6*c5OI~pZdZNLSNx%zbZdM~*%7E)n7u#5?x)xn5@)RdhZG+Yu zLNkG|Ro6+bR$1Qz1AfaRXAxeWCkWkGis#5tZoOqciXo>%z9oaxvAAs1cVOW?mn}Z6 zfHP>5OEDE98t^^AhXSeNpqUq)wTQOKjQzOQ?YDbU5nytH;q}TueY;y&2@uv+9Wjz6 zVsGFO{_cq&@MDwi53E7IF%ig-6qet&8iR4AGg~ad$Kk@GR+{51uZG))UN@imk|j_S zjwV_8y1K*h2o?yd0g*<0dJ_jY`a^QQV;$V{MuGUYfqNEI0HxSaF_NBQ@8Ay*>|J@D zqm#VaS&snA1Z^RmqNw437uW&}bDHmi#-JN&t7;Bz_*w>MVP(Jt+1_GGU^GPCPdmM^ z>VS4?JHcT;b-?Y52-ZPZz27a(I?)+zp--_mHv|~`fz!iw0xlB7%6Ea$%|OF!WOFzH z0U>uI&*QC1aUS2mppJ9R0C@E(2^^gj&T(!QPRdY<1powWi^Q~hbX@>XXsSmc&M8!U z9w$qfnKrg9VHa2eGX0SQ1It-snwYd_d;_iyol6L|-|>n7FsZvm0dHU)TiNyi4%Z^k z!=Bc}nNO6RT!yQ0h~EGnsYw;2H(P`{TQwYDqcb=lE!EdGeFboWJqZR2PUwkA3rE7y z0*(+_+ z4n-QrzOfBf5e%Ff0l-W$-XxO@iCO2Wz_6ROWW)1nLC7Zs)7@DOp24Xg7|bigwct#m zoPMui%z$@z6q53y=Bn9#ARMLH?vG9Y)xpREFkQ(Z*23UXF^rLEx6N~urmmCUS!6=lklna1W39J=V@dfK+Kcc05R*V1W;yN z8^e~8Q8$Q3XZ%66Xs#s6!TBg*#Rh2@ zAv$|eNpcaZuRX2-Fgk#JL?5&M3W#6K;z54|BE9xpt9c!C5nWyI3Zv3+F;`Sj`_sw{ zb6Gx@+u^`h9MuzV6kx@JcxD5BqOuzxdlvDUXKq8iwZRDz0nUL)cy(~qPHKxhSi93W zL=p!dZx=hy3YA91)@tKnaV`pKoEmzaL{KSNBUajqezm$4SA86lxR!zKahAjRMrA^Z zQBu6I?^n;`|7GK2Ar98il*kKX1!s|f`NU#3sg;bwW)9a;N_nI602v9>l>%*)Mhh^zli)6zd}4pqP^Wfb*kv;;tsw7aNBtM~Nn| zFv(PHS#?d*L+qW$D*9>_fZv~kao7`bg(S0^`N`BY%~6m%Hp?8k3R%;5tZibA69mG; zlI$a1XHt;*Dvrl0OB2HibuC%x>!T5?*&>#S@l@&ccgvvZu;2 zDUu_*)16+w(XQ~>QK|IN)#u^)pz@1L+4@g^{+)NM-zWe40r}_e_W@#*gDT`JedC=f>AR`~2GYd0hM={{Kt(|DVJEf8{%$KmCdm25uO9qBx-) zd|vrNXnfQ9caV$mVfo@X`2X>A9K3uhE9)O2seG9sdH>%g@4sgq&yY8+k7vuR4r{gUFS+UF#{-#|L#_b0!CKVL9@?7sY-rf>{=fV1JB1cvrx zp~<%Y#9xN8r>Rdg&vU#dvj0R6Z6z=r`-!7JQJjT4*EZmN{#-r^<&;SbnZ%+@Vuws( zQ6@3jj~z3KIeP3?CI^Y4z{a;Ay)XWYpM57P>3hasAf*Ne_^+X*NIM)F<=Xg5#~V*e zHOJFpuBW-4qd@;eO=8*xmczN`KaK@!=ZR`AG}}k%<@xam9-y3(C)+daRIbmX_Ws&K z=J?k?Ka~3+Gev{`^f%slC!E~wQFr>1@ok7Q^S9qSh|>B>^ok{;M;v9h@8Q>${>(jV zc5!R?m#^M==NqxCvsgHG%v`vR7x-8EzcJ@@g^(n7OWN6Xj}KkhR&fLWbJgQLK)l_# z6U@!Yjk_gR(c^h=eD2TYn(Wy(bJND(PZsFPbCLx2uXN8@kc%k6LJM#-y?-cB)agDs z^tn%>K6fWM$>>2<1OU53AEYO)i+`TLqqoroR}}K@E5&KH>aVeK`OQyQ*od+ZlJ4PHQR_9 z$aX(zHyYhfa;0|cquBdx%@5~+|NfO!D&Q!zPfEFqyOb1VB$2n@zsjY%>BDmzW-Lc{ zsrRq0Og&~p#*TmE%7Jl%aq9>E_1%v>`qotp{~^_4rkdWf&!3mksbCj5$TJOj_}AxW z&wKk&=zHEhKDoM5H63jwPqj}-1+F2zPfYdjhNlIgXP+u(Ii`L7>SH2ll6Id55%oR` zT)jAp!^al>zj5v9`zQ?Q7Qsi~#IJ9nNKw7^ z6OeS6T(38ex2V{=gmsZdLnm$o{zKbEo4MCdt`j#5|KWA&!_5=s(T5*0k77@dfZW2p z?cv^|{maZVFO&D;bo3s`HEt5o%QVRjfy<8$ud&f<7oQ{_6Ua*xcX;LWJvPeg@FIs7 zpP(@3!jd;Rk^~=$$`@sWGjO&kLe=$bm?zH zX|R|~wQKq@$&!?5dHjZnFPONAFW@#wKRc%<4@l~Fhrj-<$IJNaJ9z7Q^C8}NGJAv< zw;z5uBcC}4ZV2IgBUY1VWSLuNzA=R}pOlt#Zx{U^ChAIIvb=s}(@O}9hF&vfe;8h{AzZj*jw zKO)l(Y7|YqL@LpAOe#leL1yKsW>>>cq6d#-xWG;Hh~o`hkW?Q%Gm&2pAMYOT=XFfR zAEAGeVW-S>q{SL?Q;imwwl>9NOtgdRM>o0|T%W#l_yS(~Myz|#YVImEC}W$6`3h8! zE7v1E>it?LkM08LX}FJdz@C09_UX5782z*NZ-`9g;F{=1x0kAG6zc|SjcO`U2~eX) zQ60$zq<_f!_^mr1xSK!8EGiSJ43XAeMkJ#vQYQ58kM1m6*N+ZQE@gm5+e`VA=q;59 zE_(e2jbX#khaPfB5hcZ^UYwHD=IU4(3Bwx;VQhg`Ux6tYOX3~5eQd`*JxlHIr5mKb zma&X|l(>-0DKmNVdYQ?ai_Bh7G+Dm=p=KP{d}#F95DA(cob7)E=N zU}MY;2iDgVBXZGC?nV?60waQ^{z-zriqSVhBEbsa2O_^?{7s5YCSceQ@iQ4?Z`f3d zr4u}jp8^uoViM^ElC^LZ<8Ek<0b@K(Qj2)ZaY=^b8Ire%FS7y;g~Gw|_?e1{H;l+6 zcwRtaI&p=^Vu}VbhsKxb1YS-g5b?^A)cDEX@C=(|08+EPnFy{#@|cMUHwhdAkrX)cGZF!xq5%OwEok-%CE-Ob#U$AzeskYBOZmBb z-$=^D(h~ibxB+rpNQfy87DRF>vPph_$>Bg#;c$sBB=?v2Gz(criD^cFFrrHag+9E; z2yor+?*ep3$D&IS`7+}EGDSl=`z%Cwzxn;`sGZsUdx#np_Zf>k2Vw2sOX4GkyU7$M zGKVY#{Mdh56glotAhd@luov<;_qyBj8pMIzkK%|uK_{YxBuyvi=o%oL1fLYiHO;Ur z`WL&uMk_Fku)h}3Yd91Kc27}EqVOpsBG+6pnL^glHOsIGCb_?+MF#JaYk^0%L8skc zC-?+Sq)Q&4g6I?bL|if5QYQKqALq%9puWR+cJq1jY341Y)YUL z_$KZGZ^?5Bl!duTCU}lbuw*zTS)^srPjJZ#7}jWST#5_^B}1}EVKlOQlmKEN6~Iuz zZS+)u^i~$b1mFVHl3cP;FNxuj0m&$OF;6a08UYW;rO2je+`hs!O9oUbNwUCH!6#5C za>;QtlVZ?i$nRPYq zVkYjz+soM5W&O0UfI0NZEnnJ`qmTB<9T)BKLFA6sBM)8w1g>+_S4-#7;}OmOPrb>qW2PzmFcyuWfOw_~f{zIiUf?fc01vpX5z9>#b5 z`XlIl>bdQYr9yeW_Vi1C{ICA5e^J{ne$)T_zLJ0K=@+if$sz^zn2&LNsNL6|<{zZ- z&)<2d3}3rOM-&Yt^zFCpisyEG>#Xjn$9d8`LTfH3r{?XZC&T^#kU0)0C8g=}B>S`Z7}C;=i&%_)Yp z47decv1>yPjxGa|+BckVuEvmkGD_ruL9YdY5}#! z@8OY$(^CMVLD$Bji3KON@5BdxtmDC@PL@3k2`qEK^*A?IT_Xg#3}}S?cp(rQ8H7+| zVI|a` z6`h!O@|dHH4*B?Dwt<+*^6!vx2C_Mi+1e(6fV3Hkx-Y&i1J8uTe;yJvp})skkw=G> z<{1qnb{z?c$k#WZ!bG@-4?ZS%j876DJcwo(S)80L4 zGH*YiE~@bmxxIE>E+#xIB5yyoFY5C!`MphzvJWuPTvX^mvU{8Q9m5$IzEf8`YmUES<+a>go4Mn~OGszw|mavEujwb|%lO%)j!YW%{B{ zFHUz))$Y^Ek77LAwQdXGXP(sxj^$?h)h5 zw_z8f`MeD~zxMR!0|zErXyi{Kv*(k@>iHzHdY;3AegPYV=h;S|F}t1(ny+GZ{i!JK zC(0a_&109nbN3`Y>$gaAzGwX={=ABD)w}xoF>vOuM6aBUtHZwqBw{JrNfP@rf$U<7 z`2FvZ2qYLYZ6KCSUB^bi4!-}r2roVBYy|TUGMX-m`#>4KO`U%C*p+_h#`cAreuxYCHnRWv z^JcHpD)scaN$&aXc`bgPtKedYkwxsTt6=y)VIk`p+SRXjqE$%U2X}nu+6V&I{}x60 zduQN2+|u!;6gm$Kr4&qxA?&5pRI@eW%~PpkOeR*qa~ST;K3ne)8F^y_i}|CgQxq_4 zg?IgpSVbb+Bo+qRQn99zs1|h}auoSXPypM3{Sr5!!94RCX*yaB zNj2eQ!CUx-g13o}mDrXMq(s8e4sM$TsR^k>w4Odw&`4V6W%0+*$`|7+`iUO(KirwO z@0%I#rm?<-PIKB${?x6Wb5g=?-#vHlyUE|P{>hypJb&r1%J}fpU;hF2%_w3%g|A>Q zyF0H=M+ro$(=%S6HpJ=VaQ`1IV z|M$Ol1T7p4B(Mt+9of*#sR0cc0ywLs&^3Md+HbCkAynT(8ld!$k~r^Soxu#b_uXT> z0*@Di#=ZBU47_$5u^~#G%ykQ1!Q|8>c*&P_&?%qC$&H9IAE`HDY1N?av zx6p6WC%4dl61{Ta7V2OnuUuf@Q3`lGBIpg7xlfcSXFE>>DLinV;ISFGR1S!}z1_+O znC<-LUe6}Ro(OPHkayrBx&mem9{`FUu96^xwaC`iCvzE0AW^Yn+QUtGxXhpSw#E#C{>rS3F6z@G%8BxL`XZ8uJ4K_)*s)ttxCazDSrxDQ`xw<|P zbRAi$?mR!-etaN{I+9s|#p>_`9>0SGhpds{^4muyFccb0VUfGxmfjT2r2AQ% znDMW^5!F*u4|KpNoi_mkC*`Kg89RzgPA7PG;L=@TgNp6oCIIctc8f-ryS>fedRXGtSoE{%8 z;`rZNeeKUjTJ=xk&s~Y%jby=#{fp{qzs3BoYn!t_KsBgE$XFY($2peIQz-uo5H?QAfA1GGEqkuYAK@d=w2@ z;Bt+DTQ-_h_n{+DK0myOI15|)0SWNwqDLe|OBjI!~kpV}A2-ypB z7qTUQC;+A4q$QsOLJpSmgJJJ%$j&}M-7XZX2gwdP!Y`55i`c?Xk)Y4GJ?}|#>VPkk z@Q2pXPd0bD?$HGQ@1J|`Q7VxM z{>P)W`z3$X0o z+}y;DKR7>6y}JpR9t2kg+o&HJkTc*xM<)!(I$<&i5DJM1#l7o;SWU3G z*~f++LPKwb24YV5p)TX8#Vl_>RNU7dD&POdFKnaXPh!UysXAD7BmdWaO^q6Woby0} z*u#Bf(Xn~=CsSO5{N)je=)Hr!zWQMJ!CuLVR`JNA zgw`f*am2DCz!kB=K$2ZVZbrenH&+9K^+u5cu#QIEDT+6R+65gT0(KEdHo}sLK65Jf zUbTo&;ZZ>lp}KzqiJXbHjfN{RgMITAC33Owyz(oU@c#0hR=f=lK7|V%rqn~^B1Fb`TGyqF5H_8j&p&YzS;Y4EG5X}@#~Dti;}+Hd-s&^ zRtr5n4Vo7ZqVGRsV?nbZTbCEiFQ*aw^yO*qsp88OyNmJtJjLk4tG&MSF$p6g3_#h> zK0RF@bePYe6(t^@)R)(J(&r^h=lE#fQo`=9vcUh6+jrEgW-pFGL=B$KD-d-oLi<^A|VGSBPBzxnchoFM)9 z$-cWYoAbAK%b|F8u(YWQdM{)eF`C(%daE{67f%W?P5GN;aYZh{M=(M=68WF`zk z#1SxWS*#GQV8d%XS_%5WU9 z(e-U1rS81^N`v5wpp=cw1?P`PWAs_@o7!WaKX>*&osXR)7y_!%qq*^c`vR_vcWFkav^ zBinRC;194*I~i@B^YkQp%ONA=J!|n2@sscdVq<>)zc|U*ie9;xF8;>B4oh}rMC;fS zI1*PIF*T7bK2RJ89y%=9F#E#P4BE;IwxNrKoowq5+dBG#o2v$p8T+8t$TD!+@WHG= z%*uMio=A3#fpeONj+WfFDbU4a^&r_n)}IoQUl@jO&uFi>y#LmnOkQbb`{3Mq$3pCF ztdSArqN+c>zwxStrH@naq44xMt7vflTMt>-FWj7Sx4um{GoBUceS6DejgJZu(){$D zUUkm+*+=($<&7Hd_a9Og|MGp^|1`Lt-uw8Tikv6O=fM{)dJY-)dpqFmB`SMm9}TFl zyd)8`D$&uRrHnqWKo64FNe)pT{O?fgx73%I|K--?_lz<0tAnE|M5erxUUK*Lsa)3o zOhoyf^+&JMB_iv1=F2~SR8gMS9D}Qi)_9Kj`>ZSM8{m0na-weRo9f&|Kd}5y;)$B= ze|`IAYd^V1SQqQoSN8C|JyPyClij{~DwFkp@0;vjympgKy7!dg_6T}>_3c{@88YXc`|G`Qsz@Zpzw_VRQ<;m#`H6!nb`<&P_o*b7uooo%+JgMO|MQ-2-xlOIE~hB;{O!pHN0Wg7 zf8BYyd8M?cVn+hZzP$i{|Lec->^yrRz;S7hOxTC;&m%223amNuR!07oJ;(ZqQWGNp zey_6zdrQ-e_L#RUTHku}Z(QgzZ<7lKQs++lzme+m@tsUwI2w-xC*S{zrzSWS;$=GP zG2KzqySK0}(^;K|EbP1IWVuG z?>;cAakQKMLAC#>;7@DLQHf5C8_je7`0eMpfA$Bb z;dpM4b2~o$S$)r8j(O(NoOtFUJSHFnKo|DLXRMfKOW~_nF~2$h4#_36D|KY$Db3v%#?g5wF?PQq#4_KPh zMxTI6{@hD)x|r--%_C53cb09-TxN^`!szPS&q9m4E3h#ADH- zsr;vIOXKvVr*|IQQ>Amyd!FU#;-jSH_C}Z6GsyVrW0>M^t-AY3gg6JUPjkh0yQj-X z-~ALejnhv&xtvE%GtGGq_k;YzNnTOQ{M@6r-jn~#7k}}%YdMSTqQn2Ky&WDqkc)nO zsx)yZT|C%E^X+q0o2&iqP51Eso@JvP%3~b9pgQ!Nt){&jn~(_eeJ!(sKu_9?yM(s$N||Fk}L5^l5%{wCV?ZQV7^)BJfB<;61C zjUd2hu1sQ-{&p;lQMER}i43+b5_tqFD#WPn4>TfSQs0gp+}v}=!C8gm7#@%d9FOSR zFJ>5rKbXu|ICed!%yimruV+A_9me{sadYLK8o0{--Ag9sL=V z|Ey%ciprm;?)i<{=Yx>;BnhSCQEEW;*(wYw)BlgXH|d!r&C-Nwg&@R+9qfYYO+;B% z*yJ{qx&WWd%-u$JH*+_)QYmHgJkN%D&muQSiG+lNkXQg}wZwu2Y-#ltiGP5QkdXKj z9Q(c-HzKnms-U|zEoDl1!#{VM-szm@Jm)#DeM$*_G#dZ^PyDId{@G`@{nNi^cKsMO z-2dyZo%P>;obuE3u?CRU8y`C)Z7+d@jY+3%KhqC6!dBP}<#m4vMQu>NuoXFj0f+s( zzwEsV1rl4MHd(}HN!!<2WGH9Y4g$9DN2SE3wu1LjeQw_Ri!Yq}yw`8G{hosauDQL3 z(#waBZOOOt>J}#P&;I`IFFtk(|Jn9fW%f}D@a;eUFP9NsI{ED*i3%tXgx#*beR%Od z|DTtj{EP2@_*UGs8yjo2?GCm*|Cd^Tk5+-K|D&ql*LGI_RMdP(K7RN{-S)Qlti#?U zG_cHIv26tb9Vj_I3lTmqy6vFxQ8B&UZgY2A3HDET@qhX^vHO4Kd;iURey}?K%O6>t zKP(|6{}m?Kk8As1>D;f&`*;6Jr$dAO*FS2|-;E@`Y#M0%WE_6%kPjpw|3fa8pG}v4 z*z5knFoN6qmtu<_TlTZq;y?b^UB5q#*T43qexVgV`LbW56n-{vn^pfpDLDWBPql>r zL7?{IyT5lcj{oA{{2y==X~SUxZF{a<~vy_da&_!my=fYpKnJ~r9-{^JLDyW`N7AHNO7cVABa%O4N9w{(L&PL{~dr@E!J>Z=rq@hgL0Lo*SO+vmNyhPUp0( zvwZhAGi-PMZT;4uAe( z-+$f_wr1R3GrPSP@zbvZX86TB!t{bm{P9HkZoB5!XZ>p)+;H&y=Qb+a_rnsl zB>B7MIIws4*4kg3x*tFO;`IHlhPAetrfq%vY_@Iy?;l{sZu9aFChR}@cH4UAGrI=! z@e9)29@_fAjLYZ#6`%VfZ9wv8n;dqqSy2^++dFALEG1MDwGJ##7{i~oJNl&qz!?5` zz`wj$p>M1&mxbv7fBkrq@4xwJIDWnX)0aE^blR7-0G;@C$~xt?C*9ZcVO4(p{PT79 zvsDQ%zf0i#t6OdF*F(RD^L}lqemw||*(TxFzdu&%j}P+WJp9?h-fr{@_t~!T54+ew z;{FGn@GGkn3<~n~;eTn_|Ja7F2mQ*0zAX1&TEH;Jzn=Y@Z~y!+|MJhju2dL;Z@+`= z*dILV_kYhS|AQ<1_waG?T=4O1cB&xpQ?cP-?RP%Q2qo^ zfSuUz$k*u#pZ)|;{`|)^_A@*7#qRyX+N__t{Z9bpPXOgl0Od~r#q0kBP`>|(*ZN5J z{68P;`mfV&zq+;I|NWJ@`*9zSKfK7_xwWDDFTT?I|JP4M(0}zG{4o)f{x@I0O8;B< zxKTs@-RD=|rT+tb_}#zN^{|Uk@%!|je)-D>*!}zTpTS?&H&CPYvuOGcS&*MChra@X zkst{}JZJf7ZEwG>QIQ5cPt{_>;=} zefqzB`)7al;}Plq0sGOwiT@}3=XVYY5pUa}MVtmDyebzpwzt+oXp1VJZ(0N#yWtWx z<`ev4-wx{Ax=*gaVXlxT7tzkWQmtKLx5}wGD32*}#5?AR3N0^O|MO$zf?MnbeZNDA z+pc}I4wsjuz$Y$-fAsfFsC3$|;r`up&d;~!eOGFv?~{@F48uJea0Rw>S-lqy@p*SS z91f>!snsS*AGy>-$8$}c-43hG%;4{j8yhKy1N?Gy4p_$TviMLvoaA`EiLI@)EXuZ* z@iAX77kO~Kl+n8#Ixx!WcROFD1|xu5n@Mx2jz{5qKFisD>E*+6gwN8Y$`t9ie10!1 zSr;D;$K#bBYk7aWMNxd0>HCyjE|>T1hM4ca@7P%#J(nJzwA&MO{2t`v(ma=b9_8Kb zcB|sDI!03RF0T2J@`VKWW4+5)o_dpVjUQJQ)kzI)@9+#qahXD^#h2Xei$!axf$PM> z?A^}Go>Xz)BS=3ros&P1F72zu>b?mz&0frSEHuLokA_7hJf%kHwIhqS(y`a$t=u7D zX0L-nDOMk|)@e6!)>HLa`H1=A9iM$Gc*+hYJ#19FTh~FP)Qr6dxuweq+! zYQ3cStHEDy0`Fxzcpvez!prILl4Nyq??|`VSC5+3%=yNPGaI%!g32wz8s~IzPZTfv zftFUx4jJoYyFUGdF+JL5wXfvTWW*G%;lUi9Rozf91U2+0t(*DvVML6!a`W!S%+OCd zm8+)LVAV0sY{6f+fC?|mIclCX*%#|tBR<}WTa0riEQW7@g0o9lfFp_!;Yk&zrie> zXWFw}m-S25z44DwDTm`res&M>uqs1owUM&QOyFvz*}q?hRL&DTrC8ce4;aH&2O+&f z2eCU3de%?gw02D^x=8tSj*hp?77z8gFf@^*)k8NG8{#nC&Wcbzu9vqadJP+d+SI!izj~OOn+>1t5Z$~FF!Qhl6%qaz zzup?@4VMSZ&D^wOuvPq-g}Ei|P9eH1e#YnLM9>f_BG9W3)7Tpv^uqCxm%iK7D6T@< zuOW%B)0Rwj-m*JYx*f2rg zJ8d1-cV|jzyyKR!#p#`>T<#ZGyC)uJGCv_=ireq@15#6-53AR8nIhD^C-D$&?d&n4 zM3rbcnC@YvFh(m+<*DI?R1@7!;F~_Lv(=uPmpU?i&mjue26*q`OMt8^#j=I~?gf`} zgAMg{kDT7!OD~Yy=0na>D}%S0Zk@Gj`cuNtuT^xZ70vwP8>5(FT=e^U)Y36+16ei- z^&(|^YxS91Bzs0EBXm&Kq)c%I1@@SflX;&N21P0PLix0s%omiTIR`$x>&-?W2(n|~ zEoam;%K3tp^E@LeF`h_n@oMQ^z}%x>8J7595M{93m7Ahtnx0@_i{kNEH{UGD z6LEUB7s(oK%#^OuZa(lvBkRK(=@$!TtnreP{&|`E=j|LlNbnGPu`{Z3Q83d(h#RS; z*%2KXq=$Kx<^xrUnZ;lL)I-M2bbI z{<4NwZ7dJD9EYXi&*n@|l>-*wI>-fezO!)Qp=~(6bzXUWKigpa_qR+7U1=EcAchqO z6HIS?y3auM@Y*THC;CY<>BhO*QxO?*|?Mtz)KnzbL zsRt#CI#HsqVNzN4L2qv=J3KG;VVaXyz8hY5Vs97gD^_71^2)`)@HoU$i+%|s9fEf2 z=JS@xY~Xf@smCi*qyyu}T9Pq*{xHk0ad-LN};@z(km1x1zx>5c@!G+;Zx)1P?wol9TjPUcFL(wyI zM1fOiXjz1-mM6lJa!uekj!IeW1c4N7lr^OVWkc_*{CJC`+wh{Q)3N?>d-Sx@G-T=4@3H4GTTg*8z9LH;#cq#!Hacp!Yd@%$Y?TthMcCAhi@l@S9 zu!bXW6={V+K;^!0)c{AI-14g}+_SfkNYcG#$G5D8RuHXgU(PBcEWO$EQyS2lqHa4s+c2Po2ng=-5OI%W2n+~&1e@!?_GxYgmD#1a37|n5mpUh zP0RU4i|@E=h6Jbc(FY*53($ARLZ_^ZFd^E*Fy@F0S|bk3>v3NKl5Foawz%#<^#OE* zZxepWXk`EJ%9{xyX4|FD??82TMB)yp0cbm!T)!ih`rSJmVALFAT8Zd8=sSp-p8OO3 zA?D6K#?K~xJSE&Co_+*!rq6h905D3)?R4&tqR~tmA|Vw*2(d`*{xzHix2@B8q8wOb zz0YCT#Vc2ACf~{)Mfaq)*8rD_BrdLOyb83dcm#tA3T3^cmA2P1wxzO&sR zH(7$9@d5AH^er%&k=-STe_r9M-3-g+nxf1S=deD4V^Ap;eu$p*f)M4x>qTWc>W3fC z7GJNkKo{eQ@~Ru$-va(^=~Pr$C;HbF;#?b1OfWD8hm5c8)xM-k+DF%naAvSk9+{@8;Vb+T zx$g#aTsfKxn4Dr42PTd1I%OXCl?P9{+5Pr@qI%>;uQ3aHkt@5(1dfW@;95<{=TtO$ zLOp{?_nC8YS1F3Z$p#|8%TU(z+m(--&xmg*?PN82(l7;Q@>V}#t-1P}$m zd9gZ$En0lm8^g^yP*jj5;p@!EqQKO72n?5xp=k=t9<4qiEO zjji0YlW|(=>__fq)lLFsoVp9T<1gBj8(gI!y?i{|g}@)|5AGs){peSZ{vKg(m``8Z zQa#Cc;<1?VmuE`f-2*(Wv~c$mIH1FT3uz}pTo^vj@%0UXIsn!;cIDPPrA=<)lS;E( zol~TW43dOTq^?r)`H4Z|{iWM^v#8t8etEQh+6(4M?@O!~ZTb3mBcFYByU?xeKy(pC zd9;wabHZEw^*VJ~2ko2A)Ki+@Z&e_#Ea{_Rx#lZXM}1j@^L+P1R@p(!k_6JOJ!VJ# zM~my-J>FH`Q#nm35`)(C(4;c5p2P*n-51N7AZ z?4sqPj1T<$0u*ni`Qw1uPJYyd%3*p6$#3gLmH@rq%vm{U2+K}PzSP!f?RMJ6-w>_c zFDrxq0^n#}R!gHN5#4oNw9GP$RS4{Qy5R-w9}Bn{mS}0?Y-?!aBWC)3&8C&10 zj&=4%tD6m1;oS9_x=c?nrjwhxm`*#nbl5QbXs=+9Ql0=%#>67B1B)j~@XeMth;$9=TZ zPab2-i9|fh#7%v+4SC7w)5*vhjCuK_E!=GOk(dTyO8>co`VYw;pTA z9$p8^JL3A|J$U8gV&~5(pl9=7TpkL;-6-wRqeRFlX)b$M2>rB2M=*Q&ol0rm=>iui9Oer@JePs5m!yQ;ac1YOZ&Y%dXC9#JP z$JPnqPgevL;|8Z0h)*nen-?=ns_7H#Z!NrweVqA2IT9{J+YHL#<32E-{2k_k7;_pD zTF{#|IddZv8*&ITE3P2)^+2{0HSIjzMvV%yZ_V@Fg7fW8p6+%p1H#11v2B)abNiU% zOXuVgT_%!;Ikd!EI|+4kO&WL90H!+O@8n0-Y`oqaw9keBmvj&b4i0H}@#ION3lOn- zwfAaoo~~K)yf@Dq;O`oI-#=XM!dq!ir zl4;oLn5be}7^gTQJCZ@dr8Zle>GgQp`J276+2JL-2{nYGVXWxPcHQWqVsiIapEPsn z(OiKXvRTf5T3dg1#A+*Pjnmx&{JRGnAnjESK8|A{$PBZKIu=FeWsimncf!|8Jt$t0nOE* ze_{UQoet2JX-1lkZkJ1P>EW>3W;n@YTWg$_-Xj_?I4a{fj;@RwhTaJ6fwV$YM?3Fv z*@FiU?q^@b=-F1Lw=Q-IU~2VZm}FkZcuiv=#nlEz%_A&xvGw;niaKY_- z#b{e~e45q3zA~Nh#BK9*nCJ+9Rfm@xPnSR!(qJRC5ODMuU7ltt>wsNG^o%+iC^}*) zV?h@49V#0$IVp#|-4V_m$iebmD5+xT>kbVeJoF(lqrE^p9-e@LZy2XumC_*G1sEcI zRjiH6t+B?qp3(45qc2l_4lgjlObWgDD8*@a7U0IkapP)qtHl=iiu&RW8?BMF#}=b4 z06VpHp3eq^EQ84QXri_7Adg!Xi_oVjUt!X|oD=_ST6RK^vg26JgOw#`qMjng9Exi5 z)5^_c6e&5&N1`uWcqUU3)8#FaD4V%3XE+Jgt-2Wn9#$Zp>h9BNEeyWU-)x|H!D%1e zS8*c4p6Fh{^#m6nlxO}}L0COU)9$UdJi+7%*v)wFiRXFp}Y;Zs}7Smgdj8Bd0rUOci_^h{Rzx5DIOkc$822WoxfO*I^--0xS}Bt zlU;RnTF({dC3JTjtcR!2;%^6SYUF7(TnYSWz8RmrdL&&OMbNQ_b->ULw|b;}1pd&v zL&~Sp16MCG0Dt96HTs9lFQ~Ax5DJ2Sg^*t2Z~F#1;=EzPQ`ob}P?Q^A)mbg>6aZcK zdj*-UN|8RU8!y22bqi6>?R+@w0}(tMN@5wuU;PpMvISvUhut1TTuCSJpC=V^3p@OD z@TtJcY|f)u1fdzI{6@wn1*w|L)_(29=eeKIFX^cZ(h2$~eB7&7a$Yq#izXI%E7JM+ zw);KYRXokROojEkkm8g{Egr&rpt<{4&eTO##7l#OgSpsBJ+Xmtl@aV>@|*~PyBL={ z_MmB_Rd6n+lc;nypT_jqb?#wWgNa&h4r*o8@tsJ}vxs1^qK5hl1!L=|rx>F<0SJqc zp{SWV-Z0IEj-_ERdu3<~F$E4lgeWrxKYEEFM*~c^%0Q;qzdo`SQYHGy5&OnzAbMPP zlxAnw^8)+D`%1B`u^0y7YM6Kqey;_W#S+mtVH)JWXrYSaJS|KLx?ziV@Z8kh*$w240 zVGwjfb-)~8KVaYs2Xk4l zMUtwx1I{2aNwYA|U+%p+Z@xV-fe3gh=^n^4n)coM2p&s-M5qj$_H1X2-4mQt825pO ze2=!+mz+f(ws@bs$2q?S!L{Tisd{9bx(n0j$%u3BJR$Mau!?XjYExT^%hi8Lu{qou zZGS$Fhq?DD7$@_YW|>QHx&z!6Z9_wB@BuGt)JcNaO|Hr^RZcQ3xJL-mt0w`^vfE)K z*(DGP;z3FyV@vQJnxA!)l{r>XbixHZwL)4zIzWd4ygQ}0(dr?sby-r~CcUn4M%LF0 zh`X2m)R#6PUg?qH5U!LgNce2wrPXrh9SZjHiP8Pz>iAk=TcwI~p~dQmP9gsFjCtWW zgvagDoIrVmNBcp2E?0^(rSZvW?Nj3V z6xLC{AbcKJeBP4`JTpo!rJ=tEomym(FiYWWUu1@KDP>sC7;ZWtfnlcO1OPc!u{&KFNh zZx_2F+*_TY`tWfIpwvSz_j^w&?fO0u+IZ2yK30gA@2IiR*LwuF3 z>0FW2hFPR1g6LpZS|Y?~RiMyrj^D2{=7J)r3C~y4zjv>7xfkO&?8{^QUiMs32CH{| zyq@lHJSN$BTaWh*4?Tw|d%Pk2jQG z5QMw=v}%h<+Lfl89{4{;-7w`T-m!}oKp)XF___TmXNPSZcAGt*CM2{gBn&H-bI_el zJagLwm)?-?k>t>_LU9fS-VC@5Ql2RcNu*R?GX_ER9YFPs^t+^Qf(Og7GQd0T5;>t& zaN6*zC7mTa0G@?}afLW`G|smo+_Bm@yB-Z-_PsHUF=hsSBLBc>8QAD)uQc4FFs^x0 zh!6S-c`-bJSOikU9kw{&7{Sg&XxQTA37&6jFC;k7l04N4U=nXg&8B?!LT2~~8i3)g zk6z>*8(^<(8NjK;A2V0?NTqhc_vJ=RFozUk6EfX(FByU+o}VW!NDUFaLAI@1ArMk1 zf0*7l#4K-)p#4w%008Q-L{hD+rTeta9|HJBmNRzoF_zrS5q7ANO8reLrM|f_{&mDF z`g$3RX}D0D(J>}i1Td0%nUO}FVb>$nDkKYny!BHwSr9~rp)K|r7mxwWiC!QXihBW9 zW7)3td{oaDV|UeS<8dZOy?~a%X+Qe3Y9xr~UE)xj2u3YTnJ>VZVh-ly#+7RbSjB(^ zo+_6@=N-x;-M?BEUs&Th?J_5+q+|VRg=BHZ3(OZMg81}$+OKDf(+r0TAct9F&JD)* za?om8g<1PPAAk^ecee|vu3ni&TcYk1L88;ABr`uhVC-|;3{c~I$?o^6R~yY(7JlAcJ%xSJ9cNp?G{_#IJ<9U2ldJ1Sj_)+L zxR=m+2@-voGuDvkJKr<=VL})NvHx+fi>mH-e$^zH1ORFU48GS-LWDdhdP%D0ayjnP zh}xQFLMm4xkK7g0j<-Cfl;pl)v@7d#K++^(P=1DXkV(uu6JTRNHNSv_$GhW9tSeU7i9`(ROW7@rkbUk-}AKYL4Sii_OHh$pD3P9B*9)Ct%>ie ztMn@o@own0hwYfx=>j4j;5buGtob)}o@2o%E{>I~_#M{ofiWXrcr_E+aT6(%oP5BO z=<)i@CF;TjlMmH(oNS{6?L>4?v5_iPm9zFnY7ObaSutdI!@Z;*GD&g8%_u^kXk6^I zCN@3FQvxdMb(ej6`~$x1qWIh!VHZLPiEsi))lZnI{d0v-o$r#U}za+&j=A$DQvCv zy8x1PeOZ$DYsdTkdPX505ro>guWv{q*6%knf|n#LOw>xZOU_LWt6$3P_w^Aa2cuzu ze&Hs_$wlGSc((M7p{+7H$l8$v-+)(R#fjG|Vk>63YOln7LW+n1w49`O>;QsDW?)(n z2x$*$d@JG!1bA5T3_=vg&)D7dbkNEP2Y_cG!EsjYAKX#CLyUer0iX!{`wR43X~dl4 zyre-h;Rrn*U(OmrCe-eZy;K4f)nJhBN>F-_+p<>IJ73O^mv%D%d^13=u<3zndcUq9 z*G9334TNU%gnWe{SQYNISDJ(U9D5;8eaK_75cZn@0$h-5SlQ;vo|9kN1+5-qTD;M9 zhJl8e8Y~K01!$W2%A>A0; z*5)3@^1jm!5jvKoxExkTu%hV#Q8DYeYzjg?G1_mKSUB~BEWo%b;&pkK5N;1^fQEy7 z<*1FvIPBj*()r~Ko$jV* zcNj|WAx`;;uY)+$1{U{r+0x{j(O4(?Y8z;!`5NO9*1miu!Wr?*3~i9jUFz>^ty1kt zT+v2j`g?WuOGlUCI$HTG7 z(5|I5mwDCT%c%C{*kl^KGfc)np#Zc5K5D~UtJq^gLE6NGX*jkV=#qTeVj=e82ck8u z9=MrR?2`?j&qWmaq)*~PgYO{2Pvn{V~iJpBb|EA2L|pl6K140g@qYIX{@7v7HF?0V`su#qog0X;Td;Em07VNHH=v}K%+uQ>to9+~>(}cJBFCq6_u-xf zjCll-CzdNV{f2>psu;8laRU%Z2(|ovN{F|49yGmo74m&sl}fyUn#Z?Uq2G(CNfyoX z!Xt8OpXcih0lMLRZeY{DeRYDl>L?=QLKJnS2uOz0?dSvXvWe^ha%2b=vo`=e5BRIV zunFWw1lLzbL5BDdSITsOpAQoxQXUwLcP+j0%w9bAk{X-D+5|!k(Oa4-v-b{xJkD+k zb&7%>-`)AyFAG`SCOy87loP}YuZn%e4&h=d7$Zh=RgFv`HLK2ur1)pi4HVU zAW^f06$b_q(t~2nm>Yxo7)KzbO2F`etqR!#Jovz<2wF10QALA#AN8{zgDBVrA@=k2 zDu|8?%6ak9E7+t*YygS9DW&%rryCHj4Vb&dcGm?Q(GIlGh@qgma7GWXHKaU*=IAi0Ag2535%=1W`vUA2+9|)-1 z-O87nl7TH$fNtA3j}So#(98_N6C|SB_(5#Xa(zDrFGd83y5XGYz0r6n6d@=)~ z;ug5ubOcVBdcTm6tx&x}ua3Abz10>|<&`phY95=2@qRW1(BnK8(N%7jlJ&^;eH;;! z>2C7TNy}+^%e^Yb8IVG^y%^Swm*lsUhvuZfmj9evh?}Sja0qcX2SVy-$UL3-eRlBI zLINc70>CNYi^_@8QD*msD9`bWSqJyB{jmJ;(@GhW?<#po{G zZ{!E0=8UVN19KTLL44kH-G>L5u@& z8T?P&^!KL&T_Ovz-v|{?)>c5Ur~BYsc=ecE*E5j&Jli}*&s@ZYem+N8o@DM0bZ7nI zq=U>D7p&DlFlm~>L*QdOhWt!&Ya~E6{G&rUZ)8>@46gu&%6(_a>1rX|3wVScR?B;K z{R)d9>PNJfWr5MP%_bn`408?;2EzDEm;J#9{E@vO*LYUP!^owbS`zij0b3xm5^2#)-MpPm9SP)$m5l_eV)t!G(WN-dWcdd+^L^5-~$Entm5io z^>EKXIRnXIG$;Xt2Rja+Q#A+rA))Vv#H%ChccYNHnWKiYS2LsK5Jkq~Q zS2;2d3KGW5(J>SX5g%pF?$q_X*?mt`*9+uh#T+zYv~F#6F9`?)KzSBj)Zv-{Q3kad zP{fe#asP!c(rjuLTNU~@oq!8nsr>1*?`UBTd5#a6|>Ym6buijXc(Ra7G4qn)ies|h4ZMg^Pfnf1Y zKD?FB%bLR=3t;X-u7AGo9M|V%e&j+u_g5t|VjgN^7Ep|`(+u(G>Bya2MLfIp5$g^b zsN8|h8>Og`KGrT1FCM9<7{;Q#b$d_I4D1JR7q?>e5Al&dfVv8zrQu~V!>fNLsqQzN zFw-D6J2mAcgPuyn6{BT2294*Dw(7G0MMK?^*n6AL+ZW``ngaBM_2V->=g*xj1Vty+ zZ-bnNh@0E|fODDTS?UCOC+B{tHVu+=c^5i|T_MRQnI(CzmV1O0?+zF8h_08b2-?rB z=1Z9T;(|sI%k8y8f)fW27}P!SK1$N@vqp>;3m{=Jkz#OhuP0=gblkNe2=9F7^ZEAL zu9LLJE+GBM0$~Es$;t86X9g04{&utDRsB*k#XmEf7J3iXtAu%#x9bhRAES~7X<9kk zBCBv22ycuPr}#hBFFl!@Qq$NeAP+)!L*Q)f9bjY&P4G zFKlq)Ar!?&<)sb-8IB-~cnCh`b9teK+%?_upvb*lZ!_?X85D!G{6d+H(I2^U*cX(O z*iUtw1462Qq zEMf@d#>GN|ebCo z3`Yf|0M`>-Aswv(T@4~c)s zZv#}RCt|!~|B$*M#duowtHmjG;AZB^%^EC2i%W_=sjb?q${D;=#AmM3VK!xa-%b46cEx!y$8Y6T>uUfN_L>9;W=lJS^;Q(HY-$ZuIRye@;6heU(%){2VU}iLDrse z@_V(j<0b%p;+US8z}|F4*NuSLp4)&Stq8z28_8sx*=>%UPIwN=Ed)yNgxxT<3#{j2 zf*?ZyI;x_fMv;R+L0{=+7$F2eHxc-zd#JZuIZ)2p6O!8_)-4oJl|5u(G0;Rn5+^rS zUVh)GD^ziKNQOovugBNqVL~Dt_u)JqE-rvj3+jw4DP?XIJ!(ML0pu6mq(=rbH*(c5 zU04yJ&htwGp(~2^2zhCJJsfSW7?Ckwhc}}Ver9hvZRpDP?E)CfJ+2)&CMfXbiYRA~ z6WBckFm4DrQ5e>K>>=L<_yl5akPO;UJ-EV(a@;|IICNTgDD|9G(l4Dyc2$83V>!zr z34U}jZlT_NwdELch;J`oGrYQjhe^J8r$CIq_a9)f<+bjIiFO#$(-12K_! zI32PjhGrfRuPHgm?q5J%1UeH}1wI8Z@Q0viLJFfMB^)wwE9i;BZiICUg}G6k?7GKw zF9N=bFTQAkII6=yP!vsoM%7CST7oxlK2-$RzL`A4*KQmXZ9(ng#wo(0n)c`CeGtnP zG|X_zCvcQ*N6HxpihK)x-bK9A9$xUNdMUyhXpk&M%T0e(0%dT{U>(p(Mk&UI*Hy*< zQ0{@CDAdF)7ffZKLx7-z^gvK_dFW949F8dGGjKlZY&dxGEfeR|!$(XFv#`|Hv-JWI zP;Ej6FhkXsSpy#pwn`8INI!Q_ml09H3o@OPE}k}!8&%JS3yc8xx_vnz}De3~^6cDY9*-i%DvHZ}QR0?p+gy zeCuF`kdF&D{t7kQC%|UVNnx;7<&U`ig@H<@t)DO@Ke((3bXe4Fn~N?KiubS1vRT@@ zJl@5egOF&OLlfqz?STN*4-9;M^u+zN&4swo5M%%$QL_n&!2c+qo$?fwzy|^t^|$g; zly&Q9ph+r3gghvcfmM-!!436(h5{f)+iZvlvH9lP1;znD4E}hKj<1FkfR`-^1X5r= zes8!J$OF=BICBFHHPd-Q`AG#D!|4Fv+|9RfriNi0Syx@5F6f1KP;Nx1WT8XwQ$jzC z7JYtza*9t-7}!Bf=L=MNKlehkX^J381zG-+UQ-+bZ$EMc8sbLQ73Rp@cSm%;)x#F2 ze7!aZ$HlO}0qA<-OCYkGs_S$15fdxstH&@Ui@pup$8DUKMs zG?a?Ll+&8g8q`Q0qeBSTWZRNpNsl2uuJ|6(rI5G`53vpy=7#eJ19l1MQf21=XF?tb zzhjmcxUN{@-@$1@0TuWal!aa^C)wq|PjgI;fZPEDeNYwk<`kfi@gmmt*a%rZ_&(aYukY$uZIjhuD&!_TA%g%$|_$iTFcg7cVzRHV)s{S~D?VF*k=-gOp%@ zfg*tZ1n~{5QRrV_C5wYW4WD|=XxblXAm5}L4+@N~pz8zx+9d(K^ce2~9?EfUH54;L zVKC&ukz6_Vfk8GZFeb3s2dEe~&G(xie1ztxP1o|0?M}Ei>NV>RJA~{F8`ifQZ$8^N zV%mO_BVg_wpv-Z-Bl-?tjc{=q@k#Aiu~eb2o*9JjUbgcwEyf}1C@q_QWtf4XOb!#rtKL~d9ZXU>xgybn6bJm69{pR%KObih zFL67_U;!q6!?Zv_hd?6N^fH5hrNTFRSUzBF!HOLTSUAZXj`ae$m0;OwlwGy&faiFg z?j1p?PpC11g2)2mBJ(-3+Toy&DC_NZzBbtzRBpUC{IIRb-3ag;h5xgD2GolEdX{&P zy0qK?^&*I$q9N>tqWpf8C61)ortfTq*ik&>!P)YN>9_zI)J~vko8(3a)oI=@x*&-8lNw73gLPwDZ&j z^hy!#KwPD*D9i43pm@;|{Kt9%zAS|eA(&OIFyKr)R7y8&yTzcS48=?|;I-png}f5pikq73n@zWo|```!NZRBC}vO}55x%MJjqmb9<&NvGi18Fx66SZD1LE*hRqoEF%-~s>BVMZ`DnHPyUdV&MKvafe2qq}+CI!dd}{Oc4bXSf zxkDxr)mzAO(KdAdrhBnIYH>hl3^XS=&9U!Nqzp!5!&yYS)f2Ql@TuL{ZWtf5(F6ur zGjjqxR0cJKIV9Gc&f4k`0o|C~9k{H} zYH%wXtORJ@b8LbZ1Gv#Q_VPn&!=#($Zp*9gpk8d*^5V*!E};PE~8g)uspi z_#Q=BYUKcXG*5WO&p8|ds00yB%QtwE0$;e-#qcmoymqxwy#ckT0UL-^0Wgx|^}+YH zKs=-DnCn75k+<8H7@I%~mO|VVfX*-#V8@EuG4GHwy#gfJmx(9o9d}ky9!nbeR-Ml$ zeN3Z0t2if0E?WuKPy_^>2HP9iI{06b88&f`3Y9|;HbOEO^7F86DJL()#-RYmsE}p3 zciN`usy0nmU#rADWG>7)kFWKiVXcZxcm>$0W-xRVNskTf10O8|x@IgSBbVwu()bxF z^*_QvC{u{_n}65OPvM?kAqPFN{QNvpQUEnfVX7v`+MME$c)tS@()zr$OF|6l-mFWn zof6>FNk-2-w`JBPDfoK_+FdA+f=b~yfK6B~x-}BLczaiI3?;23IBqCHke+-0m{(n~ zPw8}4u!B=vQP!E7Ek|2tuS1x69>$M0bV7M6fwhO+Zb(Ud))lTDtNYP$60O zerS5N6?Cj5B*4A#8Mh*@$F>g*6GCAk)Ch~aT5BJ21iVE}7)G00;gOB%49Y1{_LkqF z=1K3ZC@2u0i}m&bTEl$zN}iYjmuY0!4odM76#U^l4i~+gSYst4G4%lT0Ef$RCQyRN z>HlT!-C`bD*Yu!0drr`aCd{DhWHial&)z$%UfXMR`A}t-*UTDXmt8)TT|QK~%J!Z; zYuC|L9#2x098@;y(;7xhhKK!y?Y0ue*E zOQwKr@;I=!_9zw-N8v}(3Lpn}Gw5S)j0eZ#Sp+o2Y%u4;3AmYQphz^mP_prX;gyX; z4WmPE-ZgOA>T1P|k!9(^s!?I=SAa6(fiJ;X!x{&7KR#%|q28|Uz-eXQaw!=k*jm&r zcD9n`IOF5`v5m}lZ?K>{p0#RjWxy{2ZK+f(VB(2v< z&(-Q#h9`i?M;}N#UWiu*Lx8Go)5O;?8&Z||0KUYuaY|yFKnz0U$B$KAJHncmkk1ca zuDeY1Y-k_WP9BRJVa-K>j1<0=d9ev6CFY6fKi;W^MBh-&Mo3c*wyv{Erob+#eZ+R+ zMusHMnmYHG%CfHysAIpFkAsHP8kiYC!TKNlbgbXV1j%-R&VDnaypm#C3+%RXWyoZOy~#naS)5+UY^> zYzWT4qV#kmkHESH{h>{;tT-ne=ooNYAFPo~cs`J6RBxnNL`B|yk&Jq&RbA7HGVt>> z_vWK2Kb(L^3BlnCBkF@9CHYf085g@g+VlrtjPm7^WL;eU^pU495vb6scs|0bL@5cXXu+L6SU%Vx;*dG zE05aJK35jY{IGz@$Peo7o8G z%Lh<^WYK`F5PfYkldQ#AkjhJLGxFIHYvkW%~*`Kx|dXB)yPt9GkJEbk9ahj2zQNCz>4mXkO8 zY3)!s8p=K@Gh;byOpq38?WUFHt~0!HH0>L1m-m*}coVy?9gN+iRY`1qrtp(fKh2L* zbJ*Y)Y-%ag{=7soL*qy|gAPJ%RhNxD=T;FyKaE6v|`E#AEtKQDtto+++oM4Re`82d!!lE~; z4H3^O+LU_U>^AFuc_O?H#^Ri>9Tza#x>riMvu*Zj>~U!t`!0gSrRs)xJT(c2Q9s