diff --git a/README.md b/README.md
index 1095f1aa4..f77faf870 100644
--- a/README.md
+++ b/README.md
@@ -377,6 +377,7 @@ Recommended prereading: Chapters 1-2 (linear algebra) and chapter 3 (statistics)
 - Lecture Thursday: Summary on PCA and discussion of Clustering for unsupervised learning. Decision trees, classification and regression
   - Video of Lecture at https://www.uio.no/studier/emner/matnat/fys/FYS-STK3155/h21/forelesningsvideoer/LectureNovember4.mp4?vrtx=view-as-webpage
 - Lecture Friday: Decision trees, basic algorithms
+  - Video of Lecture at https://www.uio.no/studier/emner/matnat/fys/FYS-STK3155/h21/forelesningsvideoer/LectureNovember5.mp4?vrtx=view-as-webpage
 - Reading recommendations:
   - See lecture notes for week 44 at https://compphysics.github.io/MachineLearning/doc/web/course.html.
   - Hastie et al sections 9.1 and 9.2. Geron's text chapter 6 (Decision trees) and chapter 8 on PCA and Clustering
diff --git a/doc/HandWrittenNotes/2021/NotesNovember5.pdf b/doc/HandWrittenNotes/2021/NotesNovember5.pdf
new file mode 100644
index 000000000..bfe619338
Binary files /dev/null and b/doc/HandWrittenNotes/2021/NotesNovember5.pdf differ
diff --git a/doc/LectureNotes/schedule.md b/doc/LectureNotes/schedule.md
index fbb84248e..9333732d7 100644
--- a/doc/LectureNotes/schedule.md
+++ b/doc/LectureNotes/schedule.md
@@ -146,6 +146,7 @@ For the reading assignments we use the following abbreviations:
 - Lecture Thursday: Summary on PCA and discussion of Clustering for unsupervised learning. Decision trees, classification and regression
   - Video of Lecture at https://www.uio.no/studier/emner/matnat/fys/FYS-STK3155/h21/forelesningsvideoer/LectureNovember4.mp4?vrtx=view-as-webpage
 - Lecture Friday: Decision trees, basic algorithms
+  - Video of Lecture at https://www.uio.no/studier/emner/matnat/fys/FYS-STK3155/h21/forelesningsvideoer/LectureNovember5.mp4?vrtx=view-as-webpage
 - Reading recommendations:
   - See lecture notes for week 44 at https://compphysics.github.io/MachineLearning/doc/web/course.html.
   - Hastie et al sections 9.1 and 9.2. Geron's text chapter 6 (Decision trees) and chapter 8 on PCA and Clustering
diff --git a/doc/pub/week44/html/._week44-bs001.html b/doc/pub/week44/html/._week44-bs001.html
index b9a663548..0a870a874 100644
--- a/doc/pub/week44/html/._week44-bs001.html
+++ b/doc/pub/week44/html/._week44-bs001.html
@@ -337,6 +337,9 @@ MathJax.Hub.Config({
   <li> <a href="https://www.uio.no/studier/emner/matnat/fys/FYS-STK3155/h21/forelesningsvideoer/LectureNovember4.mp4?vrtx=view-as-webpage" target="_self">Video of Lecture</a></li>
 </ul>
 <li> Friday: Decision trees, voting models and bagging</li>
+<ul>
+  <li> <a href="https://www.uio.no/studier/emner/matnat/fys/FYS-STK3155/h21/forelesningsvideoer/LectureNovember5.mp4?vrtx=view-as-webpage" target="_self">Video of Lecture</a></li>
+</ul>
 </ul>
 <div class="panel panel-default">
 <div class="panel-body">
diff --git a/doc/pub/week44/html/week44-reveal.html b/doc/pub/week44/html/week44-reveal.html
index e050f0d12..bf7fa89e7 100644
--- a/doc/pub/week44/html/week44-reveal.html
+++ b/doc/pub/week44/html/week44-reveal.html
@@ -205,6 +205,11 @@ MathJax.Hub.Config({
 </ul>
 <p>
 <p><li> Friday: Decision trees, voting models and bagging</li>
+<ul>
+
+<p><li> <a href="https://www.uio.no/studier/emner/matnat/fys/FYS-STK3155/h21/forelesningsvideoer/LectureNovember5.mp4?vrtx=view-as-webpage" target="_blank">Video of Lecture</a></li>
+</ul>
+<p>
 </ul>
 <p>
 <div class="alert alert-block alert-block alert-text-normal">
diff --git a/doc/pub/week44/html/week44-solarized.html b/doc/pub/week44/html/week44-solarized.html
index 9374b007a..fc31ac050 100644
--- a/doc/pub/week44/html/week44-solarized.html
+++ b/doc/pub/week44/html/week44-solarized.html
@@ -297,6 +297,9 @@ MathJax.Hub.Config({
   <li> <a href="https://www.uio.no/studier/emner/matnat/fys/FYS-STK3155/h21/forelesningsvideoer/LectureNovember4.mp4?vrtx=view-as-webpage" target="_blank">Video of Lecture</a></li>
 </ul>
 <li> Friday: Decision trees, voting models and bagging</li>
+<ul>
+  <li> <a href="https://www.uio.no/studier/emner/matnat/fys/FYS-STK3155/h21/forelesningsvideoer/LectureNovember5.mp4?vrtx=view-as-webpage" target="_blank">Video of Lecture</a></li>
+</ul>
 </ul>
 <div class="alert alert-block alert-block alert-text-normal">
 <b>Videos</b>
diff --git a/doc/pub/week44/html/week44.html b/doc/pub/week44/html/week44.html
index 4f621ed07..b0bac39bb 100644
--- a/doc/pub/week44/html/week44.html
+++ b/doc/pub/week44/html/week44.html
@@ -374,6 +374,9 @@ MathJax.Hub.Config({
   <li> <a href="https://www.uio.no/studier/emner/matnat/fys/FYS-STK3155/h21/forelesningsvideoer/LectureNovember4.mp4?vrtx=view-as-webpage" target="_blank">Video of Lecture</a></li>
 </ul>
 <li> Friday: Decision trees, voting models and bagging</li>
+<ul>
+  <li> <a href="https://www.uio.no/studier/emner/matnat/fys/FYS-STK3155/h21/forelesningsvideoer/LectureNovember5.mp4?vrtx=view-as-webpage" target="_blank">Video of Lecture</a></li>
+</ul>
 </ul>
 <div class="alert alert-block alert-block alert-text-normal">
 <b>Videos</b>
diff --git a/doc/pub/week44/ipynb/ipynb-week44-src.tar.gz b/doc/pub/week44/ipynb/ipynb-week44-src.tar.gz
index a35a9706c..9575c0a1b 100644
Binary files a/doc/pub/week44/ipynb/ipynb-week44-src.tar.gz and b/doc/pub/week44/ipynb/ipynb-week44-src.tar.gz differ
diff --git a/doc/pub/week44/ipynb/week44.ipynb b/doc/pub/week44/ipynb/week44.ipynb
index 3e0d4c6fc..3173b9261 100644
--- a/doc/pub/week44/ipynb/week44.ipynb
+++ b/doc/pub/week44/ipynb/week44.ipynb
@@ -2,8 +2,10 @@
  "cells": [
   {
    "cell_type": "markdown",
-   "id": "7ca66fc0",
-   "metadata": {},
+   "id": "edd99c57",
+   "metadata": {
+    "editable": true
+   },
    "source": [
     "<!-- HTML file automatically generated from DocOnce source (https://github.com/doconce/doconce/)\n",
     "doconce format html week44.do.txt --no_mako -->\n",
@@ -12,8 +14,10 @@
   },
   {
    "cell_type": "markdown",
-   "id": "7131ccec",
-   "metadata": {},
+   "id": "c9d8e8e1",
+   "metadata": {
+    "editable": true
+   },
    "source": [
     "# Week 44: Dimensionality Reduction, PCA and Clustering. Decision Trees\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",
@@ -25,8 +29,10 @@
   },
   {
    "cell_type": "markdown",
-   "id": "12ec3183",
-   "metadata": {},
+   "id": "c92e8e9c",
+   "metadata": {
+    "editable": true
+   },
    "source": [
     "## Overview of week 44\n",
     "\n",
@@ -36,6 +42,8 @@
     "\n",
     "* Friday: Decision trees, voting models and bagging\n",
     "\n",
+    "  * [Video of Lecture](https://www.uio.no/studier/emner/matnat/fys/FYS-STK3155/h21/forelesningsvideoer/LectureNovember5.mp4?vrtx=view-as-webpage)\n",
+    "\n",
     "**Videos.**\n",
     "\n",
     "1. [Video on Decision trees](https://www.youtube.com/watch?v=RmajweUFKvM&ab_channel=Simplilearn)\n",
@@ -53,8 +61,10 @@
   },
   {
    "cell_type": "markdown",
-   "id": "7dede74e",
-   "metadata": {},
+   "id": "0f3e9a0d",
+   "metadata": {
+    "editable": true
+   },
    "source": [
     "## Digression First\n",
     "\n",
@@ -69,8 +79,10 @@
   },
   {
    "cell_type": "markdown",
-   "id": "e399f8f8",
-   "metadata": {},
+   "id": "acf64785",
+   "metadata": {
+    "editable": true
+   },
    "source": [
     "## A short Discussion of Project 2\n",
     "\n",
@@ -81,130 +93,12 @@
   {
    "cell_type": "code",
    "execution_count": 1,
-   "id": "b18dd53d",
-   "metadata": {},
-   "outputs": [
-    {
-     "data": {
-      "image/png": "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\n",
-      "text/plain": [
-       "<Figure size 432x288 with 1 Axes>"
-      ]
-     },
-     "metadata": {
-      "needs_background": "light"
-     },
-     "output_type": "display_data"
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "/Users/mhjensen/Software/anaconda3/lib/python3.8/site-packages/sklearn/neural_network/_multilayer_perceptron.py:614: ConvergenceWarning: Stochastic Optimizer: Maximum iterations (100) reached and the optimization hasn't converged yet.\n",
-      "  warnings.warn(\n",
-      "/Users/mhjensen/Software/anaconda3/lib/python3.8/site-packages/sklearn/neural_network/_multilayer_perceptron.py:614: ConvergenceWarning: Stochastic Optimizer: Maximum iterations (100) reached and the optimization hasn't converged yet.\n",
-      "  warnings.warn(\n",
-      "/Users/mhjensen/Software/anaconda3/lib/python3.8/site-packages/sklearn/neural_network/_multilayer_perceptron.py:614: ConvergenceWarning: Stochastic Optimizer: Maximum iterations (100) reached and the optimization hasn't converged yet.\n",
-      "  warnings.warn(\n",
-      "/Users/mhjensen/Software/anaconda3/lib/python3.8/site-packages/sklearn/neural_network/_multilayer_perceptron.py:614: ConvergenceWarning: Stochastic Optimizer: Maximum iterations (100) reached and the optimization hasn't converged yet.\n",
-      "  warnings.warn(\n",
-      "/Users/mhjensen/Software/anaconda3/lib/python3.8/site-packages/sklearn/neural_network/_multilayer_perceptron.py:614: ConvergenceWarning: Stochastic Optimizer: Maximum iterations (100) reached and the optimization hasn't converged yet.\n",
-      "  warnings.warn(\n",
-      "/Users/mhjensen/Software/anaconda3/lib/python3.8/site-packages/sklearn/neural_network/_multilayer_perceptron.py:614: ConvergenceWarning: Stochastic Optimizer: Maximum iterations (100) reached and the optimization hasn't converged yet.\n",
-      "  warnings.warn(\n",
-      "/Users/mhjensen/Software/anaconda3/lib/python3.8/site-packages/sklearn/neural_network/_multilayer_perceptron.py:614: ConvergenceWarning: Stochastic Optimizer: Maximum iterations (100) reached and the optimization hasn't converged yet.\n",
-      "  warnings.warn(\n",
-      "/Users/mhjensen/Software/anaconda3/lib/python3.8/site-packages/sklearn/neural_network/_multilayer_perceptron.py:614: ConvergenceWarning: Stochastic Optimizer: Maximum iterations (100) reached and the optimization hasn't converged yet.\n",
-      "  warnings.warn(\n",
-      "/Users/mhjensen/Software/anaconda3/lib/python3.8/site-packages/sklearn/neural_network/_multilayer_perceptron.py:614: ConvergenceWarning: Stochastic Optimizer: Maximum iterations (100) reached and the optimization hasn't converged yet.\n",
-      "  warnings.warn(\n",
-      "/Users/mhjensen/Software/anaconda3/lib/python3.8/site-packages/sklearn/neural_network/_multilayer_perceptron.py:614: ConvergenceWarning: Stochastic Optimizer: Maximum iterations (100) reached and the optimization hasn't converged yet.\n",
-      "  warnings.warn(\n",
-      "/Users/mhjensen/Software/anaconda3/lib/python3.8/site-packages/sklearn/neural_network/_multilayer_perceptron.py:614: ConvergenceWarning: Stochastic Optimizer: Maximum iterations (100) reached and the optimization hasn't converged yet.\n",
-      "  warnings.warn(\n",
-      "/Users/mhjensen/Software/anaconda3/lib/python3.8/site-packages/sklearn/neural_network/_multilayer_perceptron.py:614: ConvergenceWarning: Stochastic Optimizer: Maximum iterations (100) reached and the optimization hasn't converged yet.\n",
-      "  warnings.warn(\n",
-      "/Users/mhjensen/Software/anaconda3/lib/python3.8/site-packages/sklearn/neural_network/_multilayer_perceptron.py:614: ConvergenceWarning: Stochastic Optimizer: Maximum iterations (100) reached and the optimization hasn't converged yet.\n",
-      "  warnings.warn(\n",
-      "/Users/mhjensen/Software/anaconda3/lib/python3.8/site-packages/sklearn/neural_network/_multilayer_perceptron.py:614: ConvergenceWarning: Stochastic Optimizer: Maximum iterations (100) reached and the optimization hasn't converged yet.\n",
-      "  warnings.warn(\n",
-      "/Users/mhjensen/Software/anaconda3/lib/python3.8/site-packages/sklearn/neural_network/_multilayer_perceptron.py:614: ConvergenceWarning: Stochastic Optimizer: Maximum iterations (100) reached and the optimization hasn't converged yet.\n",
-      "  warnings.warn(\n",
-      "/Users/mhjensen/Software/anaconda3/lib/python3.8/site-packages/sklearn/neural_network/_multilayer_perceptron.py:614: ConvergenceWarning: Stochastic Optimizer: Maximum iterations (100) reached and the optimization hasn't converged yet.\n",
-      "  warnings.warn(\n",
-      "/Users/mhjensen/Software/anaconda3/lib/python3.8/site-packages/sklearn/neural_network/_multilayer_perceptron.py:614: ConvergenceWarning: Stochastic Optimizer: Maximum iterations (100) reached and the optimization hasn't converged yet.\n",
-      "  warnings.warn(\n",
-      "/Users/mhjensen/Software/anaconda3/lib/python3.8/site-packages/sklearn/neural_network/_multilayer_perceptron.py:614: ConvergenceWarning: Stochastic Optimizer: Maximum iterations (100) reached and the optimization hasn't converged yet.\n",
-      "  warnings.warn(\n",
-      "/Users/mhjensen/Software/anaconda3/lib/python3.8/site-packages/sklearn/neural_network/_multilayer_perceptron.py:614: ConvergenceWarning: Stochastic Optimizer: Maximum iterations (100) reached and the optimization hasn't converged yet.\n",
-      "  warnings.warn(\n",
-      "/Users/mhjensen/Software/anaconda3/lib/python3.8/site-packages/sklearn/neural_network/_multilayer_perceptron.py:614: ConvergenceWarning: Stochastic Optimizer: Maximum iterations (100) reached and the optimization hasn't converged yet.\n",
-      "  warnings.warn(\n"
-     ]
-    },
-    {
-     "data": {
-      "image/png": "iVBORw0KGgoAAAANSUhEUgAAAjkAAAJgCAYAAABoanJSAAAAOXRFWHRTb2Z0d2FyZQBNYXRwbG90bGliIHZlcnNpb24zLjMuNCwgaHR0cHM6Ly9tYXRwbG90bGliLm9yZy8QVMy6AAAACXBIWXMAAAsTAAALEwEAmpwYAACe20lEQVR4nOzdd3hT1R/H8XfSprSFsveSvZS9l+whIEu2skfLnpU9ZChTtmxkI4IKiIAiQ6aCyBJl790WpIUCHenvj2ogdNDSJg39fV7Pk+ehNyfJ5x5uTk++99zUEBYWFoaIiIhIImNM6AAiIiIitqBJjoiIiCRKmuSIiIhIoqRJjoiIiCRKmuSIiIhIoqRJjoiIiCRKzgkdQOT/zfjx4zly5AgAFy9eJEuWLLi6ugKwbt06y79fpWvXrgwePJg8efJE2WbmzJm89dZbNG7cOM65/9O7d28OHz7Mnj17cHNzi7fnFRGJbwZ9T45IwqlevTozZ86kcOHCCR0lRu7evUujRo0oWrQoVatWpXXr1gkdSUQkSjpdJeJAZs+eTefOnXn//fcZNGgQvr6+9OjRg5YtW1K9enXatm2Ln58fED5BOnXqFL/99hutWrXC29ubxo0b06BBA44ePQrAkCFDWLJkCQCFCxdm9uzZtGrViurVq7NmzRoAQkND+eyzz6hVqxZNmzZlzJgxtG3bNtJ8X3/9NeXLl6dJkyasWLGCFz8jnThxgubNm9OgQQOaNGnCoUOHot2eP39+7t+/b3n8fz//9ttvNGzYkFatWvH+++8TFBTE+PHjad68OfXq1eO9996z7N/jx48ZOnQoderUoV69enz++ecEBgZSunRpLl++bHnuDh068PPPP8fL/5GIvDk0yRFxMDdv3uS7775j6tSp/PDDDxQrVox169axc+dOXF1d2bRpU4THnDx5kk6dOrFx40aaNm3K9OnTI7QJCgoiVapUfPXVV8yaNYvPPvuMZ8+esX79ek6fPs2WLVv46quvuH79eqS5QkJC+Prrr2nYsCHVq1fHz8+PvXv3AhAcHEzPnj3p2bMnW7ZsYdy4cXz66acEBQVFut1sNkfbB+fPn2fatGl8//33nD59mnv37rFu3Tq2bt1KkyZNWLRoEQCzZs3i2bNnbN26lY0bN/LHH39w6tQpGjduzPr16wG4du0aV65coVq1arH6fxCRN5/W5Ig4mGLFiuHsHP7WbN++Pb///jtffvklV65c4fz58xQtWjTCYzJnzkzBggUBKFSoEN99912kz12jRg0A3n77bYKCgggMDOSXX36hUaNGJEmSBICWLVuycuXKCI/duXMnZrOZypUr4+zsTL169VixYgVVqlTh3LlzGI1GqlatCsA777xjmaBEtv1VMmXKRJYsWQAoXrw4KVKksEzAfvvtN5ImTQrAwYMHGTp0KE5OTjg5ObFq1SoA0qdPz0cffUT//v1Zt24dzZo1w8nJ6ZWvKyKJiyY5Ig7G3d3d8u8pU6Zw8uRJPvjgA8qWLUtISAiRLaN7cbGywWCItA1gmcgYDAYAwsLCLBOq/xiNkRd416xZw9OnT6lduzYQXhny8fHh/PnzODk5WZ7zP+fOnYtye65cuay2BQUFWf38Yh/s2bOHCRMm0LFjR2rUqEGuXLnYvHkzAM7OzlbPf/v2bVxdXcmZMyf58+dn586dbNmyha+//jrSfRKRxE2nq0Qc2P79+2nfvj2NGzcmTZo0HDx4kNDQ0Hh9jSpVqrB582aCgoIICQmJtAp0+fJljhw5wrfffsuuXbvYtWsX+/fvp3Tp0qxYsYJcuXJhMBg4cOAAAKdPn6Z9+/ZRbjebzaROnZpTp04BsGXLlijzHThwgGrVqtGmTRveeecdfv75Z0sflC9fnu+++w6z2UxQUBB9+vSxXLnWpk0bJk+eTJEiRciQIUO89pmIvBk0yRFxYD179mTy5Mm8//77dO/enRIlSnDt2rV4fY2mTZtSpEgRGjduTKtWrTCZTBEuDV+7di01a9bkrbfeipBv06ZNPHr0iNmzZzNnzhwaNWrE6NGjmT17Ni4uLlFuHzFiBGPHjqVJkyZcvHiRdOnSRZqvVatWHD58mPfff58mTZqQLVs2bty4gdlsplevXphMJho1akTjxo2pUqWKpdJUrVo1AgMDadWqVbz2l4i8OXQJucj/uf379+Pn50ejRo2A8O/xSZIkCd7e3gmcLG6OHTvGiBEj2LJlS4RTZiLy/0GTHJH/c3fv3mXIkCH4+vpiNpspUKAAY8aMwcPDI6GjvbbBgwdz+PBhpk+fTrFixRI6jogkEE1yREREJFHSmhwRERFJlDTJERERkURJkxwRERFJlN7ILwOs+t7khI4QK6YfjyR0hFhxzh/1X7V2VKEXLr+6kYMx/PvFfG8Kc2BgQkeINaciBRM6Qqw9y5A0oSPEimnXsYSOEGtOKVMmdIRY2+Yz366vZ76Tz26vZcx4znbPbbNnFhEREUlAb2QlR0RERGzHTPR/RDc+2bLaokqOiIiIJEqq5IiIiIiV0DD7VXJsORFRJUdEREQSJU1yREREJFHS6SoRERGxYiZx/MUnVXJEREQkUVIlR0RERKzY8xJyW1IlR0RERBIlVXJERETESmiY1uSIiIiIOCxVckRERMSKrq4SERERcWCq5IiIiIiVUFVyRERERByXKjkiIiJiRWtyRERERByYKjkiIiJiRd+TIyIiIuLAVMkRERERK4njL1f9H09yhgysx+UrPqz75kiE+7p3qUbVyvkJCHgCwLUbDxg7cbNN85SpV4LOn7bBlMTE5ZNXmdZlHoH/vv6r2ri4utB7bmfyl86DwWDgzOHzzO65hKCnQeQrlZse0zvgmtQVo5ORdZM3snP1vnjPX7pKfjr2r4PJxZnLZ+8wY8Q3BD5+Zrm/RqPiNGlfyfJzUg9X0mZIQdtqE/F/8JgeIxtSuFROAI7sPcviKdviPSNAmfeK02lCK0wuJi6fusbn3RZE7Oco2oz8qj+Z82SwtMuYIz0n9/7F6KZTKVe/BIOW9sDnuq/l/gFVx/Dk0VOb7AdAmTpF6fhJ8/A+P32d6T2WEBhg/XrVW1ageb/3CAsL41lgEF94r+L8sSvxmyMOx67RaMRzWjtK1SmGk7MTG6ZtZsuCHQDRHruj1g8kV9EcPP23f4/v+ZP5A5bHz/5UzkfH3jXD+/X8HaaP2WR1LAM0bFWWhq3K8uxZMNcv+TDnsx945G+9zyOntcLPJ4AvJv4QL7liY8igely64svXGw5H2aZi+bwM+7g+9ZvMsEsmW7338pXKRfdp7XFNmgSjk5Gvp2xm55r98Z6/dK136Di8MaYkzlz+6yYz+q4k8KX39/udq1K/w7uEhYVx+4ovMwes4qFvAMOXdiNTznTP82dPy6mD5/ik7bx4zynWDGFhb96Jt6rvTX7tx2bPlpp+PWpRsEAmlq06EOkkZ+7nH/LFot2c/vtWXGJamH6M+BovSpE2OYv+/Jz+lUZw88Idukz8EDcPN2b3XByjNh3GtSJ9trRM6TgXg8HAkJW9uXnhDstHr2P1lXlM7fwFx3aeIm2W1HxxdLLlOaLinD9PrPYvRaqkzP++HwM/nM+tq350GlgXt6RJmDt2U6TtnZyNTFnpyY7vjrLt68PUbFyCGo1KMLzzEgxGA5+v6c76Jb+w/8c/Y5wh9MLlV+dM68GiE1PpV2U0ty7cofOnbXD3cGV276WxagOQr1QuRn7VnwFVx+Bzw49O41sRGPCUryZtjHFmQ5IkMW4b2b4sPPIp/WuO59bFu3Qe2wI3D1fm9F9haZM1b0YmbxtKr4qjuH/3IaVrF6HPzA60LTjgtV7THBgYSY64Hbvvd69NufolGdloEu4ebsw8OIHJ7edw9siFaI/dr24soGfpIfjdfhBtZqciBWO1jylSubPgm14M6LCYW9fu06lvrfBj+dMtljZFSuXEe0JT+rddhO89f2rUL0q5qgWY4L3O0qZZh0o0a1eRvT/9GetJzrMMSWPV/kXZs6Whb69/x7eVB6Kc5GTJnIpJE5qTOlVS6jWe/tqvB2DadeyVbWz53lt1cQ7Tus7n2K4/w4+Tw59ZniMqTilTxmofU6RJxvx9oxjYYCq3Lt2j08gmuCVzZe7gtZY2eYpkZ8SXnvSoOo7AgKd0GfMBbsmSMHvQGuv8xd5i2NJuDGowFd9b0R+/L9rmMz9WmePq1s3MdnutzFni53dtZP7v1uQ0aVCCH348yS/7zkZ6v8nkRN7cGWjdrCxLv+jIJ8MbkT6dh00zlaxdhHNHLlomHt/P+4kabSrHuM2pvX+xesI3hIWFYTabuXD8Mumzp8WUxMTKses5tvMUAL437/PQx5+0WdPEa/4SFfNy7s8b3LrqB8CWtb9SrUGxKNs371KFf/wese3r8AHY6GTE1c0Fk4szJhdnnE1OBD8LideMACVrFeHs7xctg9+WBTuo3rpSrNs4m5zwXtKD+QNX4HMjfJ8Llc9HsWpvM+/oJKbtHkPhSgXiPf+LSlR/h7NHL3Hr4t3wnIt3Ub1Feas2wc9CmNFzKffvPgTg3LHLpMqQAmeTU7zliOuxW7FxWX5cthtzqJlH/zxmz7oD1PiocrTHbsYc6XHzcKP/Qi8WnpjGoCU98EiVLF72p0T5PJw7fYtb1+4D8MP6I1R/r4hVm7yFMnP8t0v43vMHYP/OvyhbJT/OzuH9WqRUDkpVyMPWDdF/uLGFxg2Ls3X7CX7ZG/n4BpAkiTPDBzfgiwW77JbLVu89UxITq8Z/w7Fd4R+IfG/e5x8ff9JlSR2v+UtULcS541e5deleeLZle6nWrIxVmwsnr9G57EgCA55iSuJMmkwp8X/wOEL+gXM6sHDE+lhNcBJCKGF2u9mS3SY5Fy9e5IsvvmDUqFGMGTOGL774glOnTtnr5S1mzvuZnXv+jvL+NKmT8ceJqyxZsY9OPb7krzO3mTC6qU0zpcuWFp8bz09z+NzwI2kKd9w93GLU5uiOk9w8fxuA9NnT0rRvffZuOETws2C2L30+kNXrWhN3Dzf+/vV8vOZPmzEFPrcfWn72vetPUg9X3JNGrFQkT+lO0w6VWTjx+Sfjn787yiP/J6zcM5TVe4dx65ofv+05E68ZAdJlTWOZlEAU/RyDNnU7Vcfv9gMObHr+S8zf7xE/LPyZ7iUHs3TEWkZvGEjaeB5orfclNb437z/PefP+vzldLdvuXvPl8I8nLD97ftaGX7ceIyQ4NP5yxPHYTZctDT7Xn/e37w0/0mVJE+2xmzJ9cv74+RQzuy/Eq7g3Tx4/ZeCS7vGzPxlS4HPn+bHsE8mxfObUDYqWzkn6TCkAqN2oOC4uziRP6UbqdB54eddj8rANmM32L5LPmvszO3dHPb4BDOhTh+9/OM7Fy/fslMp2773gZ8Fs/3K35f56XWqEHye/xfMYlyUVPjefT0p8bz0gaXI33JO5WrULDTFT/r2irDwxkXfK52XH2kNW99f5sCJ+d/7h4Nbj8ZpPomaXSc7q1asZMCC8RF64cGHefvttAEaOHMnSpUuje6jd3bn7kCGjvuHy1fBBed03h8mcKSUZM6Sw2WsajQYiO2loDjXHqk3eErmYvnccm+Zu57cf/rBq13JwY9qNacHIhhMJehoUb9n/y0Yks/FQc8Sla++1KMOvu/7izo3nA8aHPWvw8MFj2lSeQNuqn+GRwo2mHSpFeGxcGYzGV/ZhTNo07VOPNZ9+Z3X/2Bafs+/b3wA4feAsfx06R4maheMneCSiOh5CQyP2eRJ3F4av7EnmXOmZ3jN+329xPXbD73vhToPB6rEQ8dg9c/gCn3wwBZ8bfpjNZlaM+Zqy9UvgbIr7EkPDy3n+9WK/nj52ldUL9jDq89bMWu1JWFgY/v8EYjaHMeSz5iyYuo37vo/inMUWGjUoTqg5jG0/2fcDpi3fe/9p6d2QtqOaMarJZIKeBsc584uMRgORhYtsjDu07QStCgxi9eQtjF/XG4PBYLmvsVcN1n5um/WG8S00zH43W7LLwuMVK1awceNG3NzcrLZ37NiRJk2a0KlTJ3vEiJFcOdKRO1c6duz6y7LNgIHQ0Pj79Puye9d8KVAmr+XntFlS43//EU8Dn8W4TdWWFeg9tytzei9h99rni+5MLs54f9mT7IWy0rfCcO5e9Yn//Lf/IX+RbM+zZUhOwD+BPHsScaB5970izP/0e6ttFWq9zbzx3xMSHEpIcCg/b/yDSnUK8+2y+F086HPdlwJlnq83iqyfX9Umd7EcODkbObn3+fGRNIU773vVtl6PYzAQGo8Vk5fdu36fAqVyP8+ZORUB9x/xLNB6Apsua2rGru/PtbO3+LjexHgf/ON67N675kuazM8rXmkyp8LnZvin+aiO3XcqFcAjVTIOff87AAaDAbM5LMLk6HX43P6HAu9keZ41vQcBDwN59kK/ubm7cPLoFX7cGP5BIk16D9r1qEGmrKnJlDUV3QbVBSBVmmQYjUZcXJyZEcX6NHurU/sdXJOYWPRFB5ydnXBxcWbRFx0YMmIDfvdtNzGz1XsPwo+TQUu6k71QVvpVHmWbMe7GffKXyPk8W6aUBDx4bPV+y5QzHanTJ+f0bxcB+GnNAXpNbUOylO4EPHhM7sLZcHIycurguXjPJ1GzSyXH2dmZkJCIayyePn2KyWSyR4QYCwsLo49XTUvlplH9Yly8fA8fG34yO/rTCQqWy0uWPBkBaOBVm0ObjsS4TbkGJekxsxND64yzmuAADFnZB/fk7vSrOMImb36APw6cp0DRbGR+K3ytT72WZTm0668I7ZIldyVz9jT8deyq1fYLf93i3ffCqx5OzkbKVS/ImRPX4j3n0R0nKVg2D5n/68NuNS2/KGPapsi7BTm+57TVY54EPKFh99pUahJ+jj53sRwUKJ2bIy+cKor3fdl1igJlcpM5d/gVJ/U7V+fQD9YLQN2SuTJl21D2bz7KZx3mxfsEB+J+7B7cfIQ6HathdDKSNIU71VpW5ODG8PuiOnbdkrnSc1YnyzqcFt4N2bfhV8yRfKqO9f4cukiBItnInD184lW/WWkOvXTqNE06DyYv7mg5hdWqSxX2bD/F3yev07buNHq2nEfPlvPYuuF39v70p8NMcAB69FlJJ8+ldO2xjCEj1xMUFELXHstsOsEB2733AAYv74V7cjf622iCA/DHnr8pUDInmXOlB6Beh3c5tN36/Z06QwqGLOxC8tThC8erNSvD1b9vEfDvupzCFfJyYn/Ua6UcjdmON1uySyXHy8uLxo0bU758edKlS4fBYODevXv8+uuv9O/f3x4RopU/b0a8+9ahS6/lXL7qy6x5P/PZmKYYjUZ8fAMYN+n7Vz9JHPzj48/UTl8wcv1ATC7O3Lp4l8nt55CvZC4GLOqOVwnvKNsAdJvSDoPBwIBFz9clnD54hp9X7ePd5uW5fvYWM/aPt9y3eMgqfv8p/n4BP7z/mOnDv2H4jA9xNjlx+/p9pg75mrxvZ6HvuKb0ajobgMzZ03LfJ4DQEOvDeuHEH+gxoiELf+iP2RzG8UMX2bBkb7zl+88/Pv5M7TKfkev6YzI5c+vSXaZ0nEvekrkYsKAb3UsNibLNf7LkycjdK9YDqdkcxugPptJzRgfajWpOaGgoE9rMxN8vIN734T8PfQKY5rWYkat64ezizO1L95jSbSF5i+eg/9xO9KgwioaeNUmfPS0V3y9BxfdLWB47uMEkAu4/jubZYy6ux+73834ic+6MLDg+FZOLM1sW7uDk3r8oWC5flMfuke3H2Th7KzP2j8NgNHL51DWmd4ufK08ePnjM56O/Y8SUVuHH8o37TBnxLXkLZabf6Eb0bDmPG1f9+HrpPmas7IbRaOD0savMTYDLxGMqX96MePevS9ceyxIsg63eewXL5eXdZuW4fvYW0/d+Ytm+eOgaju44GW/5H/oGML3vCoYv6YazixO3r/gwtecy8hbNTt8ZbelVbQKnf73AV9O3MWnjAEJDzdy/85Cx7Z9fIp45V3ruvrD+TOzDbpeQ3717l0OHDnHv3j3MZjMZM2akfPnyZMiQ4dUPfklcLiFPCK+6hNzRxPYSckcQk0vIHU1cLiFPCJFdQu7oYnsJuSOIyyXkCSEml5A7mtheQu4I7H0J+fkb9ruEPG9W211CbrcvA8yQIQONGze218uJiIjI/7n/2288FhERkcglwDcg2MT/3ZcBioiIyP8HVXJERETESiiGVzd6A6iSIyIiIomSKjkiIiJiRZUcEREREQemSo6IiIhYMYepkiMiIiLisDTJERERkURJp6tERETEihYei4iIiDgwVXJERETESmgiqYEkjr0QEREReYkqOSIiImJFl5CLiIiIODBVckRERMSKrq4SERERcWCq5IiIiIiV0LDEUQNJHHshIiIi8hJVckRERMSKOZHUQBLHXoiIiIi8RJUcERERsZJYrq56Iyc5SXafSOgIseLTtUJCR4iVNIsOJnSE/wtO6dMldIRYMV+9ntARYi3s/JWEjhBrLucTOkEsOTkldIJYC/HzS+gIYidv5CRHREREbEdXV4mIiIg4ME1yREREJFHS6SoRERGxYk4kC49VyREREZFESZUcERERsRKaSGogiWMvRERERF6iSo6IiIhY0SXkIiIiIg5MlRwRERGxoj/QKSIiIuLAVMkRERERK6Fh+p4cEREREYelSo6IiIhYcdTvydm1axdz5szhyZMnVKxYkREjRkTb3jH3QkREROQF169fZ/To0XzxxRds3ryZv/76i19++SXax6iSIyIiIlbMDvg9OTt27KBevXpkzJgRgOnTp5MkSZJoH6NJjoiIiCQYf39//P39I2xPnjw5yZMnt/x89epVTCYTXl5e3L59m6pVq9KvX79on1uTHBEREbFizzU5y5cvZ86cORG29+rVi969ez/PFBrK77//zsqVK3F3d6d79+589913NG3aNMrn1iRHREREEkz79u1p0qRJhO0vVnEA0qZNS/ny5UmdOjUANWvW5OTJk5rkiIiIiGN6+bRUVKpVq8bgwYPx9/cnadKk7Nu3jxo1akT7GE1yRERExIojfhlg0aJF6dKlC23atCE4OJiKFSvywQcfRPsYTXJERETkjdCsWTOaNWsW4/b/F5OcMnWL0XFcS0xJnLl86jrTvRYRGPAk0raDFnty5c/rbJixNcJ9I7/qx/3bD5jbf7mtI1upV7YA7WqVIowwngaFMHndHv6+eteqTcuqRWlWpShhYWHc8HnIuFU7eBDFPsaXMvVK0PnTNpiSmLh88irTusyL0K+vapMuaxpmHfoUz2KD8PcLAMAjVTJ6zurEW4Wy4uLmwtpPv+XnVXvtntFoNOI5rR2l6hTDydmJDdM2s2XBDgDylcpNj+kdcE3qitHJyLrJG9m5eh8A7ce2pHLTcgCcPXKBWT0W8exJ0Gvlf1HpagXp6P0eJhdnLp+5zYwhXxP46JlVmxz5M9J9dBOSergSajYze/gGLvx5E4Cvfv8E3zv/WNp+s2gPuzcdi3Oul5WpV5zOE1qH9+epa0zrMj+SPo+6zYa7i/C9cd/S9utp37NrzX7Lz3U6VqVi4zKMajQ53rMDlKlTlI5jm2NyMXH5z+tM77GYwICnkbYdtLAbV05fZ8PMbQB4pEpK7xkdyFUkO08Dn/HTyn1snr/DJjnjI++IVb3InDuD5f6Mb6Xj5P4zjGkxw7aZ4zgmJ03hztSfR/K550LO/3HZdjltNMYBlKxVhK6T2uJVwttm+eNCf6DzDZEirQcDF3ZjXKsZdCnizZ3L9+g0vmWEdtnyZ2bS9mFUblIm0udpPqAB71TMb+u4EbyVIRV9P3iXXrO+o/X41Sze+htTvRpYtSmYPT1ta5Wk46SvaDF2JdfuPaBHwwo2zZUibXIGLe3B2GZT6VSwL7cv36XzxA9j1aZm23eZ9stY0mZJbfU47y974nvTj+4lP2ZwrbH0mNkxQht7ZKzvWZOseTPRtfAAepUZQpO+9clfOg8AozcMYvmYr/Eq4c2wehPwnNaeLHkyUqlJGUrVLoZXcW+6vNMfV/ckNOlbL9bZI+xL6qQMmNSS8T1W0LXmZO5cv0/Hj+tbtUniamLC8m5sWLibXu9PZ+3sn/l4evi+ZMmZjoCHgfRqMN1ys8UEJ0VaDwYt6c7Y5p/TqVB/bl+6S+fP2sS4TdZ8mQi4/wivkoMtt/8mOB6pktL3iy70mN4Bg40q6SnSejBwQVfGtZlNl+KDuXPlHp3GRjFebB1C5calrbZ7TvqQJ4+f0q3kEPpV/YTStYtQtm4x24SNh7zjP5pDj/Ij6VF+JDN6LuXRw0Dm9l9hs7yWzHEYk0vXKcrMfZ+QNV8mG+e0zRjn4upCh3GtGP5Vf4zOif5XcIJL9D1comZhzh69xK2L4ZWPLYt+pnqrihHaNfSqxfYv97D328MR7ivybkFK1S7CD4t32jzvy4JCQhm3Yge+/o8B+OvqXdImT4qz0/P/ur+v3aPxyGU8ehqEi7MT6VMm4+HjyD/JxZeStYtw7shFbl64A8D3836iRpvKMW6TJlMqKjYqw9C6460e45EqGSVqFWHlJ+sB8L15n97lhhFw/5HdM1ZsXJYfl+3GHGrm0T+P2bPuADU+qowpiYmVY9dzbOcpS8aHPv6kzZqG/d8dpl+lEYQEh+Du4UbK9Cnw94t99peVqJyPc6euc+uKLwBbVh2kWqPiEdrcvubHkT1nAPj159N82nslAIVK5sAcambKuh58sXUAbXrXwmiM/5lCydpFOff7C/05fwc12lSKcZu3K+THHBrG53vGsODYZD4a8YElZ5UW5fG79YCFH6+K99z/KVHjnZfGi11Ub1k+QruG3Wqwfdkv7P3OerzIWzwHO9cewGwOIyQ4lMPbj1OpSekIj3eUvP9xNjkxaGE35n+8Gp+b9yNtE2+Z4zgmN+5Zh8kd53H/haqkLdhqjCtVpyiuSZMwpcNcm+aPq9Awo91utpToT1ely5rGqvTtc+M+SVO44+7hZlVS/O8UVImaha0enzpTSrpPbcvwhpOp16W6fUK/4LafP7f9nn9J0sDmVfjlxCVCQs1W7ULMZqoWzc3IdrUIDg5l3vfrbZorXba0+Nzwtfzsc8MvQr9G18bv9gM+aTY1wvNmzpOR+7cf8MGABpSpWxxTEhPrp23m5vnbds+YLlsafK77We7zveFHrsJvEfwsmO1Ld1m21+taE3cPN/7+9TwAoSGhNOpZlw7jWuF78z4HovjFEhtpM6XE5/Y/z7PceUhSDzfckyWxnLLKkjMdD3wC6DexOTkLZuax/xOWTPwBACcnI8cPnGfp5K04Oxv5ZElnAh89ZeOX++Kc7UXpslr3WaR9Hk0bo7ORP3aeYsnQNTiZnJjw/RAe+z/hu1lb2bLgZwBqt68Sr5lfzm81Xtz8b7xwtToFNHdg+OSxRI13rB5/5shFarSuyOlD5zElcaZS49KEBIc6bN7/1G1fhft3/uHg90dtlvU/cR2Thze0zWnKCDltNMYd3HSEg5uOUKRKIdvvhNinknPr1q1ob7ZkNBoICwuLsD30pUlCZJycnRi6ohfzP15l808Nr+Lq4sykbvXJli4lY1dGfo5/z4mL1Bg4nwVbDjG3T1OblfThv36NuN38Qr/GpM3LnE1OZMqVgUD/J/SrPJIJrWfg9XkH8pbIZfeMEY4dgyFC9paDG9NuTAtGNpxI0NPn6242zd1Ok9QdOLDxMKPWD4x19sj2JbKgoaHPtzk7O1GqagG2rf2Nvo1msnn5AcYu7YzJxYnt635j3icbefYkiMcBT/lu6V4q1I78F15cc0b2fovY55G32bZ4F3P7fsnTwGc8fhjIhhlbqNTYdpWQlxkNrz9eACwcupawsDC+ODSOMev68ceuPwkJConvmBZxzfufJr3qsmbSpviKFa24jMn2ZKsx7k1hxmC3my3ZpZLj6enJlStXSJ8+fYSD22AwsHOn7U4D3bvuR4F/11EApM2SmoD7j3gW+CyaR4XLVzInmXKmx3PSRwCkypACo5MRk6uJGd0X2yzzyzKm8mBGz0ZcvnOfbp+v59lLnwyzpUtBmuRJOX4xfMK46cBphn1Yg+TurjY7bXXvmi8FyuS1/Jw2S2r87z/i6Qv9GpM2L/O79QCAH7/cDcCti3c4vf8M+cvk4fwfl+ya8d41X9Jkfn4uPU3mVPjcDK9AmFyc8f6yJ9kLZaVvheHcveoDQK4ib2EwGrh4/AoA2xbvpEmfuK/JuXfzH/IXzf48Z4YUBPwTaLWg2e+eP9cv3OPsiWtA+Omqfp81J2O2NOQtnJVLZ25z5Ux4RcxgMBASEv8VhnvXfSlQ1vr9FqHPo2lT86PKXDxxlcunrj3PacNKSIT8N/woUDr382yZU/07XsRs4bi7hxtLRqwj4EH46eVWg97n1qW7r3jU64trXoDcRd/CydnIyX1nbBExgriMyfZkqzFO7MsulZy1a9eSM2dOJk+ezK5du6xutpzgABz9+RQFyuSxXEFQv2sNDm2JWUn2798u8FGePvQoO4weZYfxw+Kd7N3wq10nOO5JTCwc2Jxdxy8wdPHWCBMcgLQpkvFZ13qkTOoKwHtlC3Dxpp9N1+Uc/ekEBcvlJUue8D+U1sCrNoc2HYl1m5fduXKPc0cvUbt9VQBSpk9BoQr5Off7RbtnPLj5CHU6VsPoZCRpCneqtazIwY3h9w1Z2Qf35O70qzjCMsGB8EmO99KeJHFzAaBWuyoc3/VnrLO/7I/95yhQ/C0y50gLQL0Py3Ho59NWbX7fc4aM2VKT550sALxTOhdhYXDn+n1y5M9E2351MBoNuCRx5v22Fdm75UScc73s6E8nKVj2hf70rMWhzb/HuE2Ot7PR/pMW4TldTTTqUYc96w/Ge84o8+88RYEyuZ+PF12qc+iHP2L8+AZdqtFuRPi3r6ZMn5y6Haqwe90hm2SFuOcFKFKpAMd/+csW8SIVlzHZnmw1xr0ptCYnFpIlS8b48eNZv349JUuWtMdLWjz08WdatwWMXNsXZxdnbl+6x5TO88hbIif953WlR9lhds0TWy2rFSNTGg+qFctNtWLPP7FNWLWT4R/VoPX41Ry7cJMlWw+zcGBzQs1mfP55zIB5m22a6x8ff6Z2+oKR6wdicnHm1sW7TG4/h3wlczFgUXe8SnhH2eZVxjSdQu85nWngVRuj0cCqcetfa5IT14zfz/uJzLkzsuD4VEwuzmxZuIOTe/+iYLl8vNu8PNfP3mLG/ueLChcPWcXPq/aSOU9G5h6ZRGhIKFdPX2dal3mxzv6yh36PmP7xOobPbYezyYnb1/yYOnAteQtnpe9nzenVYDoPfAMY67mMnmM/wNXNheCgEMb3WEZwUAirZ/5Ej0+aMG/bIJxMRvZtPcn2db/FOdfL/vHxZ2rneYz8ekB4f166w+T2c8P7fKEnXiUHR9kGYOXYDfSa3YmFJ6bibHJi74Zf2bZ41yteNf489AlgmtciRq7ujbPJmduX7zGl6wLyFs9J/y860aP8yGgf/9XULXy82JMFRz7FAKwY/y3nbHiJc1zzAmTOnYG7V31f2S6+vCljsi3HOLEfQ1hkJ0cdXB3XD1/dyIH4tC+V0BFiJc0i+31y/n/mnOOthI4QKyFXryd0hFgzuiZJ6AiJX6j9TifGF3NQ3L+3yt52mG17McnLvjhbzW6v1SP/bps9d6K/hFxERET+PyX6S8hFREQkdswO+LerXocqOSIiIpIoqZIjIiIiVkITSQ0kceyFiIiIyEs0yREREZFESaerRERExIrZxl/SZy+JYy9EREREXqJKjoiIiFgJtfEfzrQXVXJEREQkUVIlR0RERKxoTY6IiIiIA1MlR0RERKxoTY6IiIiIA1MlR0RERKxoTY6IiIiIA1MlR0RERKyEqpIjIiIi4rhUyRERERErZl1dJSIiIuK4VMkRERERK1qTIyIiIuLA3shKjjkoKKEjxEqaRQcTOoI4oJArVxM6QqJnfvIkoSOIvJHMYVqTIyIiIuKwNMkRERGRROmNPF0lIiIithOaSGogiWMvRERERF6iSo6IiIhY0cJjEREREQemSo6IiIhYMSeSGkji2AsRERGRl6iSIyIiIlZCtSZHRERExHGpkiMiIiJWdHWViIiIiANTJUdERESsmMMSRw0kceyFiIiIyEtUyREREREroWhNjoiIiIjDUiVHRERErOjqKhEREREHpkmOiIiIJEo6XSUiIiJWdAm5iIiIiANTJUdERESsmBPJJeT/F5OcMvVK0PnTNpiSmLh88irTuswjMOBJrNqky5qGWYc+xbPYIPz9AhI8l9FoxHNaO0rVKYaTsxMbpm1my4IdVo/NmCM9c3+fxNA64zh39BIA9bvVpHHvephDzdy5fI9pXebFy/78v/VxvlK56TG9A65JXTE6GVk3eSM7V++zPKfJxZlx3w/lh4U72PfNrwmS38XVhd5zO5O/dB4MBgNnDp9nds8lBD0NomjVt+k2uS1OJieCngQxt++XnD1y4bVz2iL/f2xxXMRXxuiOkaJV38ZzajucnJ3w9wtgXv9lXDp51SFy/yeqvi1ZqwhdJ7XFq4R3guR7Vb9GdezGdXyzRebsBbMybHVfy+ONTkZyFs7OJx9MYf93hylcuSBdJ32Ei5sLjx8GMqXjXO5cvve63S4vSfSnq1KkTc6gpT0Y22wqnQr25fblu3Se+GGs2tRs+y7TfhlL2iypHSZXfc+aZM2bia6FB9CrzBCa9K1P/tJ5LI81JTExZGVvTC7P57EZc6Sn4/jWDKgyCs9ig7h71Yf2n7RI8H2BN6+PR28YxPIxX+NVwpth9SbgOa09WfJkBKBguXzMPDiBtyvmT9D8bYY3xcnJCc+ig/AsOogkri60HtoEZ5Mzw7/qz+fd5uNV3JvVE75h8Ireccpqi/xgm+MiPjNGdYy4J3dn9DeDWPTxSjyLDWJWj0WMWDfA6v2YkLkh8r51cXWhw7hWDP+qP0bn1//1YKt+je7Yjev4ZqvM1/6+gVcJb8vt6I4T7Fqzn/3fHSZtltSM+dabWT0X41Xcm/3f/kafuV1fu9/jU2iYwW43W7LbJOfnn39m5cqVXLt2zWr7unXrbPq6JWsX4dyRi9y8cAeA7+f9RI02lWPcJk2mVFRsVIahdcc7VK6Kjcvy47LdmEPNPPrnMXvWHaDGR88f33tuF35cvoeHvv6WbUYnI84mZ9w93DAYDCRxdyHoaXCC78ub1semJCZWjl3PsZ2nAPC9eZ+HPv6kzZoGgCa932PJ0NWcPRy3ykhc85/a+xerJ3xDWFgYZrOZC8cvkz57WkKCQ2id1ZOLx68AkClXBptUSBz1uIjPjFEdI1nzZuTxw0CO7foTgOtnbxHoH0jB8vkcIndUfVuqTlFckyZhSoe5CZovqn6N7tiN6/hm6zEZ4J1KBaj8QTlmdl8IQOVm5Ti87RgXjl0GYMuCHczr/2WMM8ur2WWSM3XqVFatWsWVK1do3bo1mzZtstz31Vdf2fS102VLi88NX8vPPjf8SJrCHXcPtxi18bv9gE+aTeXm+dsOlStdtjT4XPez3Od7w490WcJ/yb7XuTrOzk5sW7zT6jVvXbzD11M3sfTMTNbdWkiRdwux5tNvE3xf3rQ+Dn4WzPaluyzb63WtibuHG3//eh6ATz+cydEdJxM8/9EdJy19mj57Wpr2rc/eDYcACA0JJWX6FKy9voCuk9vy9ZTn78n44qjHRXxmjOoYuXHuNq5JXSlZqwgQfnrzrbezkSZTKofIHVXfHtx0hPkDlvPYPzBB80U3vkV17MZ1fLNl5v90m9yWL0estZwCy5ovM08DnzFsTT/mHZ3MiK/6ExwUEuPMtmQOM9rtZkt2meT88ssvLF68mJEjR7J69WpmzpzJtm3bAAgLC7PpaxuNBiJ7CXOoOVZtHC1X+H0v3GkwYA41k6d4Thp41rZ8UnhRyVpFqNy0HB9m96Jl5m4c3Pw73l/2TPB9sRVb9fGLWg5uTLsxLRjZcCJBT4PiK/ors8WmTd4SuZi+dxyb5m7ntx/+sGz/595DWmfzpG+F4Qxa2oMseTM5ZH5bstUxEhjwhDFNJtN6aFPmH5tCrXZVOL7rz3j7BebofWvr915kx25cxzdbZy5UPh8p0iVn15r9lm3OJicqNCzN8lFf0b3kxxzbdYox37z+OiiJyC6TnLCwMAyG8PNuOXLkYMGCBUyYMIHffvvNst1W7l3ztfr0lDZLavzvP+Jp4LNYtXG0XPeu+ZIm8/Nz6Wkyp8Lnph+12lXBPbkbMw9MYP4fU0iTOTVDVvWl/PulKN+wNIe+/51/fPwJCwtj89ztFKv2ToLvi63Yqo8hfGHxsNV9qdaqIn0rDI/XBaXxlR+gassKTPxpJIuHrmbtZ98B4J7cnYqNy1gec+HYZS6duErOwtkdLr+t2eoYMRgMPHn0lEHVx+BV3Ju5fZaSNV8mbv17miOhc9uarfo1umM3ruObLccLgKotK7Jj5S9WEyG/Ww84feCM5fTX9iW7yF0sBy6uLjHObSvmMIPdbrZkl0lO3bp1adu2LSdPhpfw8+bNy8yZM+nXr1+ENTrx7ehPJyhYLq9lUWgDr9oc2nQk1m0cLdfBzUeo07EaRicjSVO4U61lRQ5uPMK8/svoWKCvZZGb3637TPxoJoe+/53zf1yibL0SuCZ1BaDyB2X5+9dzCb4vtmKrPgYYsrIP7snd6VdxBHev+jhk/nINStJjZieG1hnH7rXPPz2aQ80MXNKdtyuEL4x+q1BWshXIwpnfzjtUfnuw1TESFhbGhB+Gka9kLgCqtKhA0NPgeJsMO3rf2qpfozt24zq+2XK8ACjybiGO7fzT6vkOfHeYtysWIGOO9ABUalqWy39ei/eq8P8zQ5itzxf969ChQ6RPn57cuXNbtt2+fZulS5cyfPjwWD1XLWPzWLUv815xOn3aBpOLM7cu3mVy+zlkypWeAYu6Wy6RjKxNwINHVs+zw7yeD9J1ir/Lm+OQy+hkxHNqO0rULILJxZktC3ewYdr3EV5j5aW5jGs+zXIJeftPWlKlRQWCnwVz96oPs3oswvfm/QTdlxe9CX1csFw+Zh2cwPWztwh68nwwWjxkFb//dMLy89RdY9g0d3vcLiGPQ/6lf8/EI3Uy/F74/z198Ayzey2hyLuF6DalLc4mZ4KeBbN02BqO7/4zqhgJkv9F8X1cxFfG6N6HRd4tRPfpHXB2ceb+7QdM91wQr5cG27Jvi1QpRK/ZnelWZGCC5HtVv0Z17MZ1fLPlmLw5YCWdCvSNkKdSkzJ8NLI5TiYnHj14zPRu87l25maEbDvM62P3HxBHH/5mv6u8VpddZLPnttskJz7FdpIjIiLyJtMk5/X8X3wZoIiIiMScrdfK2Eui/zJAERER+f+kSo6IiIhY0V8hFxEREXFgmuSIiIhIoqTTVSIiImJFC49FREREHJgqOSIiImLFjGNWctq2bcv9+/dxdg6fvowdO5aiRYtG2V6THBEREXF4YWFhXLlyhd27d1smOa+iSY6IiIhYseeaHH9/f/z9/SNsT548OcmTJ7f8fOlS+J8n6tSpE//88w8tWrTgo48+iva5NckRERGRBLN8+XLmzJkTYXuvXr3o3bu35Wd/f3/Kly/PyJEjCQ4Opl27duTMmZOKFStG+dya5IiIiIgVe1Zy2rdvT5MmTSJsf7GKA1C8eHGKFy9u+blZs2b88ssvmuSIiIiIY3r5tFRUfv/9d4KDgylfvjwQvkbnVWtzdAm5iIiIWDGHGex2i6mAgAAmT57Ms2fPePToEd999x21atWK9jGq5IiIiIjDq1atGidOnKBx48aYzWbatGljdfoqMprkiIiIiBVH/cbjfv360a9fvxi31+kqERERSZRUyRERERErjvqNx7GlSo6IiIgkSqrkiIiIiBVHXZMTW6rkiIiISKKkSY6IiIgkSjpdZQ+GN2wuGWZO6ASx96b1sUhU3rT335v43nvT+jgB6HSViIiIiANTJUdERESsqJIjIiIi4sBUyRERERErquSIiIiIODBVckRERMRKmCo5IiIiIo5LlRwRERGxoj/QKSIiIuLAVMkRERERK7q6SkRERMSBqZIjIiIiVnR1lYiIiIgDUyVHRERErGhNjoiIiIgD0yRHREREEiWdrhIRERErWngsIiIi4sBUyRERERErWngsIiIi4sBUyRERERErYWEJnSB+qJIjIiIiiVKireSUqVeCzp+2wZTExOWTV5nWZR6BAU9i1MbF1YXeczuTv3QeDAYDZw6fZ3bPJWTMmZ5hq/taHm90MpKzcHY++WAK+787HMe8xek8oXV4llPXmNZlfiR5I2/jntyNgYu9yJY/C0ajgR0rfmHdlM1Wj63TsSoVG5dhVKPJccz5+v1qNBrxnNaOUnWK4eTsxIZpm9myYMdLOav9m3OS1XbvL3ty+c9rbJj2fRzz26af85XKTY/P2+OaNAlGJyPrpmxi5+r9ccpqy7z/yZgjHXOPTGRo3QmcO3opznnjmtnF1UTvOf+99+DM4QvM7rWEoKfBZC+Yhf7zu+GWzJWwsDCWDFvL7z+dSNC80fVxuQYl8P6yJz7XfC3P07/KaJ48evqaOeP/vZe9YNYox7Qs+TJTrWVFy30p0iXHzcOVxinbv2Z+2/Rz0apv023ShziZnAl6EsTcfl9y9sjF18poncU2Y12+UrnpMb0Drkldw8eKyRvZuXpfnPPGNzNak+OwUqRNzqClPRjbbCqdCvbl9uW7dJ74YYzbtBneFCcnJzyLDsKz6CCSuLrQemgTrv19A68S3pbb0R0n2LVmf5wnOCnSejBoSXfGNv+cToX6c/vSXTp/1ibGbTqMbYnvjft0KzqIXmWH0cCrFgXL5QXAI1VS+n7RhR7TO2CI4zEb136t71mTrHkz0bXwAHqVGUKTvvXJXzrPvzmT0XdeV3rM6IjhhaDZC2Rh8s+jqdysXNzCY9t+Hr1+AMs/WY9XycEMq/8ZnlPbkSVPRofNC2BKYmLIit6YXOLvs05cM7cZ1hQnZyc8i3njWcybJG4utB7SGIA+czqzfdluvEoOZmqX+Yz4qh9Gp7gNYbbs40Ll87Nh2vd4lRxsub3uBMdW773oxrR1kzZatg+sNpqnj58yodX018xvm352NjkxfG1fPvdciFeJj1n96bcMXt7rtTJaZ7HdWDd6wyCWj/karxLeDKs3Ac9p7eM8VkjUEuUkp2TtIpw7cpGbF+4A8P28n6jRpnKM25za+xerJ3xDWFgYZrOZC8cvkz57WqvHv1OpAJU/KMfM7gvjIW9Rzv3+Qpb5O6jRplKM23zRbxkLvFcCkDpTSkxJTDx+GAhAlRbl8bv1gIUfr4qHnHHr14qNy/Ljst2YQ808+ucxe9YdoMZHla1zeq+wer6GPeuybclO9q3/NR7y26afTUlMrBy3gWM7TwHge/M+D338SZs1jUPm/U/vOZ34ccUeHvr6xylnfGY+te9vVk/49t/3XhgXjl0h/VvpgPAqg0fKZAC4e7gR9DQowfNG18dvl89HsWrvMP+PyXy+ZwyFKxeMQ07bvff+E92Y5jm1HUe2H+fI9uOvmd82/RwSHErrbN25ePwKAJlypsffL+C1MlpnsU1/m5KYWDl2fbyPFbYQFmaw282W7DbJuXLlCnfv3gVg/fr1jB8/nq1bt9rktdJlS4vPjeclYp8bfiRN4Y67h1uM2hzdcZKb528DkD57Wpr2rc/eDYesXqPb5LZ8OWJthPLla+XNmgaf637R531FG3OomcErerHo5FRO/vIXN87eAmDLgp9ZNf4bgp8Fxz1nHPs1XTbrffC94Ue6LGn+zbmDVeM2EPwsxOo15/Rewu61cT/tA7br5+BnwWxfutvymHpda+Du4cbfv55zyLwA73WujrPJmW2Ld8UpY3xnjvjee4+9G8InuLN7L6XVkEasufoFk34awayeSzCHmhM0L0Tdx/73H7Fl4Q68SnzMkuFrGfPNQNJmSf16OW343vtPVGNa9oJZqdCoNMtGrXut7GDbfg4NCSVl+hSsvTaPrpM/4uup1qdkXyuvjfo7fKx4/p6r17Xmv2PF+ThnlsjZZZKzbNkyOnfuTKtWrRg6dCg//PADOXPm5JtvvmHu3Lnx/npGoyHSleEvDogxaZO3RC6m7x3Hprnb+e2HPyzbC5XPR4p0ydm1Jn5++YZniRgmYt7o20xqN4cP0nfBI3UyPhrZLF6yRcwZcXtM+zXCPhgMcf4lFRv26OeWHzei3ejmjGw0maCncZtY2ipvnuI5adCtJjO7L4pTPltmzlsiJ9N/+YRNc3/ktx/+wJTExIi1/ZjSaR5t3urBwKpj6DuvK+ni+AnYlsfEJ82mse+b3wA4feAspw+do2StInHIGXF7fL33ohvTmvarz6a52wn0D4xwX+zy2+6998+9h7TO3p2+FUcyaEl3suTN9NpZn2eJuD0+x7qWgxvTbkwLRjacGC9VyfhmDjPY7WZLdpnkfPPNN2zdupVVq1axfft2FixYwIcffsi8efP48ccf4/317l3zJU2mVJaf02ZJjf/9RzwNfBbjNlVbVmDiTyNZPHQ1az/7zur5q7asyI6Vv0T6hnytvNd9SZP5FXmjaVOqdlHLvjx9/IzdXx0gT4mc8ZLNKmcc+/XeNV/SZH7+STZN5lT43Hz+acfWbNnPJhdnhq3uQ7VWFelbcSSXTl512Ly12r6Le3I3Zu4fx/yjk0iTOTVDVvam/PslEzwz/Pve+3EEi4etYe3EjQDkfCcbSdxdLB82/v7tPFdPX6dA2TwJmjeqPk6awt2ylug/BgOEBFtXKmOc08bvvajGNKPRSOWmZflp2Z7Xym3JZqN+dk/uRsXGpS2PuXDsMpdOXCVn4Wxxy2vD/g4fK/qGjxUVhsfLWCFRs8skx2w24+LiQpYsWejUqRNJkiSx3BcaGhrvr3f0pxMULJfXspirgVdtDm06EuM25RqUpMfMTgytMy7SUyVF3i3EsZ1/xmPekxQs+0IWz1oc2vx7jNu827wcH40K/1RjcnGmSvPyHN8Vf/meZ4hbvx7cfIQ6HathdDKSNIU71VpW5OBG68fbki37ecjK3rgnd6NfpZHcverj0HnnDVhOx4L9LYth/W7dZ2Lb2Rz6/miCZy7XoAQ9ZnRgaN0J7F57wPKYmxfukDSFO4XK5wMgU64MZC+UlQvHriRo3qj6+EnAExr2qEOlpmUAyF0sB/lL5+HI9te7GszW772oxrSchbMT8OBxnI9pW/WzOdTMwMVevF0hPwBvFcpKtgJZOPPbhTjmtV1/D1nZB/fk7vSrOCLexgpbCAuz382WDGHxVY6IxsyZMzl8+DArVqzAyckJgDNnzjBixAiqVq1Kr16xWw1fy9j8lW3KvFecTp+2weTizK2Ld5ncfg6ZcqVnwKLueJXwjrJNwINHLP17Jh6pk+F3877l+U4fPMPsXksA2Bywkk4F+uL7wv3RMrx6LlnmvWJ0mvBvlkt3mNx+LplyZWDAQk+8Sg6Osk3Ag8ckTeFO33ldyfF2+KeXAxsPs2LMeqtPZbXbV6HyB2UZ2TAGl5CHRX0KKS79anQy4jm1HSVqFsHk4syWhTsiXBJeu31VKn9QjpENJ1pt917ak8uno7mEPAZ9HJ4t/vu5QNk8zDownutnbxH05HnZefHQNXG+xNnWxwXAyouzGddievxdQh6HzEv/mh7Je+8ss3svpWjVt+k68UNcXE2EhoSyctwGDm76PaoYdskbXR/nK5mLnjM74ubhhjkklHkDV3Biz+lXB4ri/WfL915UY9q7zcpRv1stBtceF3XeBHzvhYWFUeTdgnSb3BZnkxNBz4JZOnwtx3e/op+jGeOe543//i5YLh+zDk6IOFYMWfXKsWKHef0rM8enoltG2u21TjSI5viKI7tMcgCOHDlC6dLPy4qXLl3i+vXrVKlSJdbPFZNJjkOJ4SDgMGIwADicN62PRaLypr3/3sT33pvWx9h/klPk+1F2e62T74+12XPb7csAX5zgAOTKlYtcuXLZ6+VFRETk/8wbOAUXERERebVE+2cdRERE5PXY+kv67EWVHBEREUmUVMkRERERK7b+kj57USVHREREEiVVckRERMSKfb5cxvZUyREREZFESZUcERERsaKrq0REREQcmCo5IiIiYkWVHBEREREHpkqOiIiIWEkkF1epkiMiIiKJkyo5IiIiYkVrckREREQcmCo5IiIiYi2RLMpRJUdEREQSJU1yREREJFHS6SoRERGxooXHIiIiIg5MlRwRERGxEqaFxyIiIiKOS5UcOzA4OSV0hFgJC03oBP8nwswJnSDxM+hznM3pOE6UtCZHRERExIGpkiMiIiLWVMkRERERcVyq5IiIiIgVXV0lIiIi4sBUyRERERFrquSIiIiIOC5VckRERMSKvidHREREJAFMmjSJIUOGvLKdJjkiIiJiLcyOt1g6dOgQ3333XYza6nSViIiIJBh/f3/8/f0jbE+ePDnJkye32vbPP/8wffp0vLy8OHPmzCufW5McERERSTDLly9nzpw5Ebb36tWL3r17W20bNWoU/fv35/bt2zF6bk1yRERExIo9Fx63b9+eJk2aRNj+chVn/fr1ZMqUifLly/Ptt9/G6Lk1yREREZEEE9lpqchs3boVHx8fGjVqxMOHDwkMDOTTTz9l2LBhUT5GkxwRERGx5oBfBvjll19a/v3tt99y+PDhaCc4oKurREREJJFSJUdERERe4thfBti0aVOaNm36ynaq5IiIiEiipEqOiIiIWHPANTmvQ5UcERERSZRUyRERERFrquSIiIiIOK5EW8kpU68EnT9tgymJicsnrzKtyzwCA57Eqk26rGmYdehTPIsNwt8vAIB8pXLTY3oHXJO6YnQysm7yRnau3hf3vO8Vo9P4VpiSOHP51HU+77YwYt4o2nikSkrvOZ3IXfQtnj5+xk/Lf2HTFz8BkL1gFvp90QW3ZEkIC4Mlw7/i6I6Tcc4LUKZecTpPaB3ef6euMa3L/Ej6OPI27sndGLjYi2z5s2A0Gtix4hfWTdls9diMOdIx98hEhtadwLmjl+Ilc3zlB9hwdxG+N+5b2n497Xt2rdkfD7le/9g1Go14TmtHqTrFcHJ2YsO0zWxZsAOAolXfxnNqO5ycnfD3C2Be/2VcOnkVgMKVC9J10ke4uLnw+GEgUzrO5c7lewma9z91OlajYuMyjGo0ybKt2YAG1OlYndCQUB76+DPDayG3L92NdV+HZ4vbcfCf0RsG4nfrPnP6hH+XR9Gqb+M5pS1Ozkb8/R4xb8ByS3+/Xk779/ObdlyMWj+QXEVz8PTRUwCO7/mT+QOWxyivLffnP5H9TnFYdvzGY1tKlJWcFGmTM2hpD8Y2m0qngn25ffkunSd+GKs2Ndu+y7RfxpI2S2qrx43eMIjlY77Gq4Q3w+pNwHNae7LkyRjHvB4MWuTJ2JYz6PzOoPAsE1rFuI3X1LY8ffSUrkW86VtpFKXrFKNsveIA9J7VkR+X7aF76WFM67aAEWv6YHSK+397irQeDFrSnbHNP6dTof7cvnSXzp+1iXGbDmNb4nvjPt2KDqJX2WE08KpFwXJ5LY81JTExZEVvTC62mYfHNX/WfJkIuP8Ir5KDLbf4mODE9dit71mTrHkz0bXwAHqVGUKTvvXJXzoP7sndGf3NIBZ9vBLPYoOY1WMRI9YNwOTiTNosqRnzrTezei7Gq7g3+7/9jT5zuyZoXgCPVMnoO68rPWZ0xGB4PuAWr1GYup1q0LfC8PC83/3GoKU9XrO/43Yc/KfFoIa8U6mA5Wf35G6M3jCARYNX4Vn8Y2b1XMyIr/q99vGcEP38ph0XAIXK52NglVF4lfDGq4R3vE1wbPk7RWwrQSY5EydOtOnzl6xdhHNHLnLzwh0Avp/3EzXaVI5xmzSZUlGxURmG1h1v9RhTEhMrx67n2M5TAPjevM9DH3/SZk0Tt7y1inD290vc+jfLlgU/U711xRi3yVsiJz+v3o/ZHEZIcCi/bTtG5aZlADA6GUmWKikA7sncCHoaHKesljy1i3Lu9xf6b/4OarSpFOM2X/RbxgLvlQCkzpQSUxITjx8GWh7be04nflyxh4e+Ef8yrSPkf7tCfsyhYXy+ZwwLjk3moxEfYDTG/ZNPXI/dio3L8uOy3ZhDzTz65zF71h2gxkeVyZo3I48fBnJs158AXD97i0D/QAqWz0flZuU4vO0YF45dBmDLgh3M6/8lMWGrvABVWpTH79YDFnqvsHq+B3f+YVaPRZZPyOd+v0SGt9LFKG/E/HE7DgCKVClEqTpFrSoNWfNmiqS/n1CwfL7XzGn/fn7TjouMOdLj5uFG/4VeLDwxjUFLeuCRKlmM8tp6f6L6neLIwsLsd7Mlm5+uGjp0aIRtu3bt4uHDhwB89tln8f6a6bKlxeeGr+Vnnxt+JE3hjruHm2VgjK6N3+0HfNJsaoTnDX4WzPaluyw/1+taE3cPN/7+9Xzc8mZNjc8Nvxey3I+YN5o2Zw5foOaHlTh98BymJM5UblKGkOBQAOb0/ZLJP46gaZ/3SJk+BZ9+NBtzqDlOecPzpMHn+ot5IunjV7Qxh5oZvKIX735QlgMbj3Dj7C0A3utcHWeTM9sW76LN0Ih/tC0+xDW/0dnIHztPsWToGpxMTkz4fgiP/Z/w3aytccsVx2M3XTbrzL43/MhV+C1unLuNa1JXStYqwtEdJ8lXKjdvvZ2NNJlSkTVfZp4GPmPYmn5ky5+Ze9d8mTdgWYLmBSyThtrtq1q95pXT1y3/Nrk40/mzD9m74VCM8kbIH8fjwC2ZKz2md2BYvU+p362mpU3k/Z2VNJlSvl7OBOjnN+24SJk+OX/8fIov+i7F79YDus/owMAl3RnTdEqMMttyf6L6nSK2Z/NKTsqUKdmzZw8FChSgTJkylClTBnd3d8u/bcFoNEQ6O3zxl3tM2kSn5eDGtBvTgpENJxL0NOh1owJgMBpfmSW6Ngs+Xk1YGMw78iljNgzkj52nCAkOwZTExPDVfZjaZT4f5urNwOpj6Tu3M+myxr1cGt5/EQNF7OPo20xqN4cP0nfBI3UyPhrZjDzFc9KgW01mdl8U54zRiWv+bYt3MbfvlzwNfMbjh4FsmLGFSo1Lx1OuiNtjeuxGyGwwYA41ExjwhDFNJtN6aFPmH5tCrXZVOL7rT4KDQnA2OVGhYWmWj/qK7iU/5tiuU4z5xjtB88ZEirTJmfjjSJ4+esrSYWtj9JiXxeU4wADDVvdh/sDl3L/zj9VdgQFPGNN0Kq2HNGb+H5Op1fZdju8O7+/Xzxlxuy37+U07Ls4cvsAnH0zB54YfZrOZFWO+pmz9Ejib4v5Z3h6/UxxOmB1vNmTzSc7gwYP5/PPP2bp1K5kzZ6ZJkyakSJGCJk2aRPqn1ePDvWu+pMmUyvJz2iyp8b//iKeBz2LVJjImF2eGre5LtVYV6VtheJwWEv7H57ovaTKnjDZLdG3ck7uxeOgauhUfzJD3PgWDgVsX7pDj7awkcXPht63HgPBB4OpfNyhQJk+cM9+77kuazK/o42jalKpd1NL/Tx8/Y/dXB8hTIie12r6Le3I3Zu4fx/yjk0iTOTVDVvam/Psl45w5PvPX/KgyOQtnt9xnMBgs1bM45YrjsXvvmi9pMj+fxKbJnAqfm34YDAaePHrKoOpj8Cruzdw+S8maLxO3LtzB79YDTh84Yymzb1+yi9zFcuDi6pJgeV8lZ+HszDn8GeePXWJM0ymEBL/e5CEux8FbhbKSMVd6vKa2Y/7RSTTwrEWVFhUYsNDzeX/XGItXiY+Z2/dLsubNxK0Lr7c4OiH6+U07Lt6pVIDy75ey/GwwGDCbw+JlkmHL3yliW3ZZk1O+fHkWLFjAmjVrmDRpEqGhcf9lEJ2jP52gYLm8lgXBDbxqc2jTkVi3icyQlX1wT+5Ov4ojuHvVJ37y7jhFwTJ5yfxflm41OPT90Ri3adCtJu1GNwfCS7bvdazGrq8OcuviXZKmcKfQvwt6M+VKz1sFs3Dh+JW4Z/7pJAXLvtB/nrU4tPn3GLd5t3k5PhrVDAifOFZpXp7ju/5k3oDldCzY37KY1+/WfSa2nR2hPxI6f463s9H+kxYYjQZcXE006lGHPesPxkOuuB27BzcfoU7HahidjCRN4U61lhU5uPEIYWFhTPhhGPlK5gKgSosKBD0N5tLJqxz47jBvVyxAxhzpAajUtCyX/7wWowqlrfJGJ22W1EzZOZpV4zYwf8ByzObX/yUWl+Pg71/P82GOnpZjdcuCHfzy9UE+77YgvL+3DHmhv8tb+vv1ctq/n9+048ItmSs9Z3WyrMNp4d2QfRt+jdPxEV/7IwnHEBZpHdZ21q9fz7Zt21i6dOlrP0ctY/NXtinzXnE6fdoGk4szty7eZXL7OWTKlZ4Bi7rjVcI7yjYBDx5ZPc8O83o+SNcJf78ACpbLx6yDE7h+9hZBT56/0RcPWcXvP52IMovB2fTKvKXrFqPT+JaWLFM6zSNjzvQMWNCV7qWHRdkm4MFj3JK5MnhZDzLnzgAGA+smb2LnmgMAFK1SiC6ftcbF1URoiJlV47/l4EuD+MvCYjgJLfNeMTpN+Lf/Lt1hcvu5ZMqVgQELPfEqOTjKNgEPHpM0hTt953Ulx9vZADiw8TArxqyPcFpg5cXZjGsx3TaXkMchfxI3F3rN7kTBsnlxNjmxd8OvLB3xVewChEU++Mbl2DU6GfGc2o4SNYtgcnFmy8IdbJj2PQBF3i1E9+kdcHZx5v7tB0z3XGC5HLhSkzJ8NLI5TiYnHj14zPRu87l25mYM+9E2ef9Tu31VKn9QjpENwy9Y6Du/G7XaVrGs4QIIehZMn/LDIoYzvPpzXFyOgxe1HdWMFGk9LJeQF3m3IN0/b/9vf//DdK+FMbv82s7HxX9e7md4s44LCP9qgfc618BgNHL51DWmd5vPo3+s/59ely1+p8TGDvP6eNmPmHprcdzXMsXU1S4xOw36Ouw+yYkPMZnkOJKYTHIcSUwnORJHUfwyk3gUg0mOw9FxIZHQJOf1JNovAxQREZHXY3jjyh+RewM/5oiIiIi8mio5IiIiYk2VHBERERHHpUqOiIiIWNMf6BQRERFxXKrkiIiIiDWtyRERERFxXKrkiIiIiDVVckREREQclyo5IiIiYk2VHBERERHHpUqOiIiIWNP35IiIiIg4Lk1yREREJFHS6SoRERGxYtDCYxERERHHpUqOiIiIWFMlR0RERMRxaZIjIiIiiZImOSIiIpIovXJNztKlS5kzZw6hoaFkyZKFfPnykT9/fvLnz0++fPnImjWrPXKKiIiInSSWq6teOclZsGABkydPpkiRIly/fp1z585x9uxZ9u7dy/nz5wHImzcva9eutXnYN1VYSHBCRxD5/xRmTugEIpKAXjnJSZYsGVWrVsXZ2Zn06dNTsmRJq/tv3LhhmeyIiIhIIvD/8mcdunXrxvr166O8P2vWrFSrVi1eQ4mIiIjE1SsrORMnTiQ4OJh9+/ZRuXJlChYsSP78+XFzc7NHPhEREbG3/5c1OZs2beLs2bOcPXuWgwcPsnTpUm7dukXWrFn58ccf7ZFRREREJNZeOcnJnj072bNnp1atWpZtgYGBnDt3zqbBREREJIEkkkrOa31Pjru7O8WKFYvnKCIiIiLxR3+7SkRERKwklu/J0Tcei4iISKKkSo6IiIhYUyVHRERExHFpkiMiIiKJkk5XiYiIiDWdrhIRERFxXKrkiIiIiBVdQi4iIiLiwFTJEREREWthhoROEC9UyREREZFESZUcERERsaY1OSIiIiKOS5UcERERsaKrq0REREQcmCo5IiIiYi2RVHISzSSnTL0SdP60DaYkJi6fvMq0LvMIDHgSozZGoxHPae0oVacYTs5ObJi2mS0Ldlg9NmOO9Mz9fRJD64zj3NFLADQb0IA6HasTGhLKQx9/Zngt5PaluwmeuVyDkngv64XPNV/L8/R/dyRPHj2l/diWVG5aDoCzRy4wq8cinj0JSvDMHqmS0XNWJ94qlBUXNxfWfvotP6/aC0D9bjVp3Lse5lAzdy7fY1qXefj7BSRo3qJV38ZzajucnJ3w9wtgXv9lXDp5FYAO41pRtUUFnj5+xulDZ5k/YDnBz4ITvI/zlcpNj+kdcE3qitHJyLrJG9m5ep/lOU0uzoz7fig/LNzBvm9+jXFeR8nvCBn/U6djNSo2LsOoRpMs2xz1vRddZgDvL3ty+c9rbJj2fYyzJlTeUesHkqtoDp4+egrA8T1/Mn/AcofOHNfxQqKXKE5XpUibnEFLezC22VQ6FezL7ct36Tzxwxi3qe9Zk6x5M9G18AB6lRlCk771yV86j+WxpiQmhqzsjcnl+ZyweI3C1O1Ug74VhuNV3Jv93/3GoKU9HCJzoQr52TBtM14lvC23J4+eUqlJGUrVLoZXcW+6vNMfV/ckNOlbzyEye3/ZE9+bfnQv+TGDa42lx8yOpM2Smow50tNxfGsGVBmFZ7FB3L3qQ/tPWiRoXvfk7oz+ZhCLPl6JZ7FBzOqxiBHrBmBycaZOh6qUq1+SnmWG4FXCm/u3H9BxfCuH6OPRGwaxfMzXeJXwZli9CXhOa0+WPBkBKFguHzMPTuDtivljnNWR8jtKRo9Uyeg7rys9ZnTEYHj+PSOO/N6LKnP2AlmY/PNoKjcrF4veTbi8AIXK52NglVGWcS82E5yEyBzX8cKWDGH2u9mSXSY5J0+etPz70KFDTJw4kalTp3LixIl4ef6StYtw7shFbl64A8D3836iRpvKMW5TsXFZfly2G3OomUf/PGbPugPU+Oj543vP7cKPy/fw0Nffsu3BnX+Y1WORZZZ/7vdLZHgrnUNkfrt8fopVe4f5x6bw+S9jKVy5IAD7vztMv0ojCAkOwd3DjZTpU+Dv9yjBM3ukSkaJWkVY+cl6AHxv3qd3uWEE3H+E0cmIs8kZdw83DAYDSdxdCHoas085tsqbNW9GHj8M5NiuPwG4fvYWgf6BFCyfj7wlc3Ng02EePwwM7/Nvf6PyBzH/JWGrzKYkJlaOXc+xnacsffzQx5+0WdMA0KT3eywZupqzhy/EOKsj5XeEjABVWpTH79YDFnqvsHo+R33vRZe5Yc+6bFuyk33rY1/VS4i8GXOkx83Djf4LvVh4YhqDlvTAI1Uyh84c1/FCXs0uk5zRo0cDsHr1aj799FMyZsxI2rRpGTVqFKtWrYrz86fLlhafG89Pzfjc8CNpCnfcPdxi1CZdtjT4XPez3Od7w490WcIHz/c6V8fZ2Ylti3daveaV09c5ufcvILzM3/mzD9m74ZBDZPb3C2DLgh14FfdmybA1jPnWm7RZUgMQGhJKo551WX11HsnTenDgu8MJnjlznozcv/2ADwY0YMa+ccw9PJG8JXLy7EkQty7e4eupm1h6Zibrbi2kyLuFWPPptwma98a527gmdaVkrSJA+GmUt97ORppMqTjz23nKv1+K5Gk8MBgM1GpXhdSZUsUory0zBz8LZvvSXZbt9brWxN3Djb9/PQ/Apx/O5OiO5x9GXldC5XeEjABbFuxg1bgNBD8LifC6jvjeiy7znN5L2L12f4wzJnTelOmT88fPp5jZfSFexb158vgpA5d0d+jMcR0vbCrMjjcbsuuanK+//poVK1aQKlX4f2KzZs1o1qwZH330UZye12g0EBZJR5lDzTFqE37fC3caDJhDzeQpnpMGnrUZUGVUlK+dIm1yRq0fyOOHgSwdtjbBMwN80myqZfPpA2c4ffAsJWsV4cdlewDYNHc7m+Zup8O4VoxaP5CB1UYnaGZnkxOZcmUg0P8J/SqPJHPujHy+dyw3z98heZpkVG5ajg+ze/HQN4Aukz7C+8ueEdYN2DNvYMATxjSZTMfxrek6uS2n9v3N8V1/EhwUwu6vDpA2a2qm7BzN08fP2LpoByFBEX/h2Tvzi1oObkyTPvUY9t4Egp7GfE1ITLwJ+e2RMSqO9t6zlYTIe+bwBT75YIrl5xVjvubr24twNjkTEvzq92BCZP551d44jRfyanap5ISEhGA2m0mZMiUuLi6W7S4uLhiNcY9w75ovaV6Y/abNkhr/+494GvgsRm3uXfMlTebUlvvSZE6Fz00/arWrgntyN2YemMD8P6aQJnNqhqzqS/n3SwGQs3B25hz+jPPHLjGm6ZQYvZFsnTlpCndaD21i9VoGg4GQ4FByFXmL3MVyWLZvW7yTPCVyJnhmv1sPAPjxy90A3Lp4h9P7z5C/TB7KNyzNoe9/5x8ff8LCwtg8dzvFqr2ToHkNBgNPHj1lUPUxeBX3Zm6fpWTNl4lbF+7gkSoZu9bsx7PYIPpWHM71s7e49W9pOyEzQ3jFcdjqvlRrVZG+FYZbFkrHpzchvy0zRsVR33u2khB536lUwDI2Q/i4ZzaHxXgylxCZ4zpeyKvZZZKTMmVKqlatyuXLlxk3bhwQvjanVatW1K1bN87Pf/SnExQsl9eyCLGBV20ObToS4zYHNx+hTsdqGJ2MJE3hTrWWFTm48Qjz+i+jY4G+lkVsfrfuM/GjmRz6/nfSZgmffa8at4H5A5ZjNsfuU5GtMj8JeErDHnWp1LQsALmL5SB/mTwc2X6cXEXewntpT5K4hU80a7WrwvF/15UkZOY7V+5x7uglarevCkDK9CkoVCE/536/yPk/LlG2Xglck7oCUPmDsvz967kEzRsWFsaEH4aRr2QuAKq0qEDQ02AunbxKvlK5GPOtN07OThidjLQa3ISda2J+BZCtMgMMWdkH9+Tu9Ks4grtXfWKcKTbehPy2zBgVR33v2UpC5HVL5krPWZ0s63BaeDdk34ZfYzw2J0TmuI4XNpVITlcZwsIiK77ZxqVLl/D396dYsWIcPXqUgIAAqlatGuvnqWVsHmFbmfeK0+nTNphcnLl18S6T288hU670DFjUHa8S3lG2CXgQvrjVc2o7StQsgsnFmS0Ld0R6ueTKS3MZ13wa545eou/8btRqW4UbZ29Z7g96Fkyf8sNivB+2ypyvZC56zuqMm4cr5hAz8wYs48Se0wC0G9OCd5uVJzQklKunrzOnz9IYX45ty8zpsqWl95zOZMqVAaPRwLczf+CHhT8D0P6TllRpUYHgZ8HcverDrB6L8L15P0HzFnm3EN2nd8DZxZn7tx8w3XMBdy7fA6Dj+NZUalIGg9HIwU2HWTpsbawmwbbIXLBcPmYdnMD1s7cIeuGy5cVDVvH7T88vAJi6awyb5m6P2yXkCZg/ITO+qHb7qlT+oBwjG060bHPU9150mQG8l/bk8unXuIQ8AfI2G9CA9zrXwGA0cvnUNaZ3m8+jfx47dOaYjhc7zOtjvB/xId/46XZ7rXMj+tvsue06yYkvkU1yREREEit7T3Lyj7PfJOfsSNtNchLF9+SIiIiIvEyTHBEREXkjzJw5k3r16lG/fn2+/PLLV7ZPNH/WQURERBKvw4cP8+uvv7J582ZCQkKoV68eVapUIVeuXFE+RpMcERERseaAq3XLlCnDihUrcHZ25u7du4SGhuLu7h7tYzTJERERkQTj7++Pv79/hO3JkycnefLkVttMJhOzZs1i6dKl1K1blwwZMkT73FqTIyIiIlbs+Qc6ly9fTo0aNSLcli+P/A+s9unTh0OHDnH79m2+/vrraPdDlRwRERFJMO3bt6dJkyYRtr9cxbl48SJBQUEULFgQNzc3ateuzdmzZ6N9bk1yRERExJod1+REdloqMjdu3GDWrFmsXRv+dyJ37tzJBx98EO1jNMkRERERh1elShVOnjxJ48aNcXJyonbt2tSvXz/ax2iSIyIiItYc8OoqgN69e9O7d+8Yt9fCYxEREUmUVMkRERERKwYHreTElio5IiIikihpkiMiIiKJkk5XiYiIiDWdrhIRERFxXKrkiIiIiBUtPBYRERFxYKrkiIiIiDVVckREREQclyo5IiIiYk2VHBERERHHpUqOSEIx6DOGrRmcnBI6QuyFmRM6Qay8iX1sDgpK6AgOT1dXiYiIiDgwVXJERETEmio5IiIiIo5LlRwRERGxpkqOiIiIiONSJUdERESs6OoqEREREQemSY6IiIgkSjpdJSIiItZ0ukpERETEcamSIyIiIla08FhERETEgamSIyIiItZUyRERERFxXKrkiIiIiDVVckREREQclyo5IiIiYsWQ0AHiiSo5IiIikiipkiMiIiLWtCZHRERExHGpkiMiIiJW9I3HIiIiIg5MlRwRERGxlkgqOYlmklOmXgk6f9oGUxITl09eZVqXeQQGPIlRG6PRiOe0dpSqUwwnZyc2TNvMlgU7rB5bp2M1KjYuw6hGkyzbOoxrRdUWFXj6+BmnD51l/oDlBD8LTvDM+Urlpsf0DrgmdcXoZGTd5I3sXL0PgPZjW1K5aTkAzh65wKwei3j2JCjBM2fJk5EBi7uTIm1ynjx6yuT2s7l+9hYAhSsXpOukj3Bxc+Hxw0CmdJzLncv3EjRvuQYl8V7WC59rvpbn6f/uSJ48ehrn48I6W3E6T2gdnu3UNaZ1mR9J/sjbuCd3Y+BiL7Llz4LRaGDHil9YN2Wz1WMz5kjH3CMTGVp3AueOXnqtjPGZ2cXVRO85nclfOg8GA5w5fIHZvZYQ9DSY7AWz0H9+N9ySuRIWFsaSYWv5/acT8ZI5yn15rxidxrfClMSZy6eu83m3hRH25T/eS7y4/Od1Nkz/waaZwnMVp9OEVphcwvvv824LIvZxNG3e96pF3U7VSeLqwvljl/i86wKCg0IoWqUQ3aa0xcnZiL/fI+YPXM6lk9fiP3/dYnQc19LSr9O9FkXZr4MWe3Llz+tsmLHVsi1pCnem/jySzz0Xcv6Py/GXy85jcsvBjanWsqLluVOkS46bhyuNU7aPt336f5coTlelSJucQUt7MLbZVDoV7Mvty3fpPPHDGLep71mTrHkz0bXwAHqVGUKTvvXJXzoPAB6pktF3Xld6zOiIwfD8mwPqdKhKufol6VlmCF4lvLl/+wEdx7dyiMyjNwxi+Ziv8SrhzbB6E/Cc1p4seTJSqUkZStUuhldxb7q80x9X9yQ06VvPITIPWdWXLQt20OWd/qwYs46R6wcCkDZLasZ8682snovxKu7N/m9/o8/crgmet1CF/GyYthmvEt6W25NHT+N8XFhn82DQku6Mbf45nQr15/alu3T+rE2M23QY2xLfG/fpVnQQvcoOo4FXLQqWy2t5rCmJiSEremNyib/POnHN3GZYU5ycnfAs5o1nMW+SuLnQekhjAPrM6cz2ZbvxKjmYqV3mM+KrfhidbDeEpUjrwaBFnoxtOYPO7wwKPzYmRPy/zFYgM5N/HE7lpmVsliVCrsVejG0xnc7vDOD25Xt0/rR1jNtUbFyaRj3qMqTOeLoWHYSLqwtN+9bDPbkbo9YPYNHg1XiVGMzsXksYvqZfvB4f/2UbuLAb41rNoEsRb+5cvken8S0jtMuWPzOTtg+jchPrfi1dpygz931C1nyZ4jmX/cfkdZM2WsaPgdVG8/TxUya0mh6v+/X/zm6TnH379uHv7w/Axo0bGTt2LN988028PHfJ2kU4d+QiNy/cAeD7eT9Ro03lGLep2LgsPy7bjTnUzKN/HrNn3QFqfBR+X5UW5fG79YCF3iusni9vydwc2HSYxw8DAdj/7W9U/qBcgmc2JTGxcux6ju08BYDvzfs89PEnbdY07P/uMP0qjSAkOAR3DzdSpk+Bv9+jBM+cJnNqshXIzJ6vDgBwZPtx3JK5kqd4Tio3K8fhbce4cCz809qWBTuY1//LBM0L8Hb5/BSr9g7zj03h81/GUrhyQSDux4V1tqKc+/2FbPN3UKNNpRi3+aLfMhZ4rwQgdaaUmJKYLLkAes/pxI8r9vDQ1/+18tki86l9f7N6wreEhYVhNodx4dgV0r+VDgCjkxGPlMkAcPdwI+hpzCuQr7UvtYpw9vdL3Po355YFP1O9dcUI7Rp61Wbbl7vZ+81vNs1jneviC7l2UL11pRi3qfXRu2yYsYWAB48JCwtjVs/F/Lx6H1nyZuLxwycc3/0nANfP3iIw4AkFy+WL1/wlahbm7NFL3Lp4Nzzbop+p3iqyfq3F9i/3sPfbw1bbG/esw+SO87h/5594zZUQY/KLPKe248j24xzZfjxe9+u1hdnxZkN2meRMmDCBBQsW8OzZM2bMmMHmzZvJkycPO3bsYPz48XF+/nTZ0uJz4/lpA58bfiRN4Y67h1uM2qTLlgaf636W+3xv+JEuS/gBuGXBDlaN20DwsxCr1zzz23nKv1+K5Gk8MBgM1GpXhdSZUiV45uBnwWxfusuyvV7Xmrh7uPH3r+cBCA0JpVHPuqy+Oo/kaT048J31AJIQmdNnS4PfrQeEhYW9cN990mVNQ9Z8mXka+Ixha/ox7+hkRnzVn+Ag6/8Le+cF8PcLYMuCHXgV92bJsDWM+dabtFlSx/m4sMqf1fr1I83/ijbmUDODV/Ri0cmpnPzlL278ewrwvc7VcTY5s23x82MlPsQ189EdJ7l5/jYA6bOnpWnf99i74VcAZvdeSqshjVhz9Qsm/TSCWT2XYA41x2t+631Jjc+NF3Pej7AvAHP7LWP3VwdtliNirjQv5Yqij6NokyVvJlKmS8GELUOY/8ck2o5qxuN/Arl57jauSZNQsmYRAPKVysVbhbKSOlPKeM/ve+P+C9mi6Nf+y9m9LmK/Dm84Od5OrVrlSqAxGSB7waxUaFSaZaPWxft+/b+zyyTn4MGDLF++nHTp0vHLL78wf/582rRpw9y5czlw4ECcn99oNBAWyWzwxQEwujbh971wp8HwysHz51V72bvhEFN2jmbG/vFcP3OTkBj+8rVX5paDG9NuTAtGNpxo9al309ztNEndgQMbDzPq39NCCZnZYDTw8oMMBggNNeNscqJCw9IsH/UV3Ut+zLFdpxjzjXeC5gX4pNlU9n0T/sv39IEznD54lpK1isT5uIiYP2K4iPmjbzOp3Rw+SN8Fj9TJ+GhkM/IUz0mDbjWZ2X3Ra+WyR+a8JXIy/ZdP2DT3R3774Q9MSUyMWNuPKZ3m0eatHgysOoa+87qS7qVPw/HJYDS+8vhJCDHJFV0bZ5MTJWoWZkLrmfQqOwyPVMnoMK4lgQFPGNNsKq2GNGbe0UnU/Ohdju8+/drHb1Si+v8PTeB+TcgxuWm/+myau51A/0AchSHMfjdbssskx9XVFT+/8BluxowZCQwM/4988uQJzs5xP99775ovaV74tJw2S2r87z/iaeCzGLW5d82XNJlTW+5LkzkVPjefz8gj45EqGbvW7Mez2CD6VhzO9bO3LKXhhM5scnFm2Oq+VGtVkb4VhnPp5FUAchV5i9zFclges23xTvKUyJngme9d841Q7UidOTW+N/zwu/WA0wfOWMrD25fsInexHLi4uiRY3qQp3Gk9tInVaxkMBkKCQ+N8XFjlv+5LmsyvyB9Nm1K1i1r27enjZ+z+6gB5SuSkVtt3cU/uxsz945h/dBJpMqdmyMrelH+/5GvljM/MAFVbVmDijyNYPGwNayduBCDnO9lI4u7Cbz/8AcDfv53n6unrFCibJ86Zo+Jz3Zc0mVNGuy8Jwef6q4/r6Nr43X7AgY2HCQx4QkhwKDvX7KdQuXwYDAaePnqKd82xdC85mC/6LSNr3kzcuvh6x29U7l33i5At4P4jniVwvybEmAxgNBqp3LQsPy3bY8O9+/9ll0lOz549adasGZMmTSJr1qy0bduWTz/9lBYtWtCxY8c4P//Rn05QsFxesuTJCEADr9oc2nQkxm0Obj5CnY7VMDoZSZrCnWotK3Jwo/XjX5avVC7GfOuNk7MTRicjrQY3YeeafQ6RecjKPrgnd6dfxRHcvepjeb5cRd7Ce2lPkriFTxBqtavC8V1/Jnhm35v3uXXhDlVbVgCgVO2ihJnNXD51jQPfHebtigXImCM9AJWaluXyn9ditB7DVnmfBDylYY+6VGpaFoDcxXKQv0wejmw/HufjwjrbSQqWfSGbZy0Obf49xm3ebV6Oj0Y1A8IH2SrNy3N815/MG7CcjgX741VyMF4lB+N36z4T287m0PdHXytnfGYu16AEPWZ0YGjdCexe+7zKe/PCHZKmcKdQ+fD1IZlyZSB7oaxcOHYlzpmj3JcdpyhYJi+Z/8vZrUa89FFcHd1xkoJl87yQqyaHvv89xm32ffsb7zYrj4urCYAKjUpx9veLhIWFMX7zEPKWzAVAleblCXoWFO9XVx39+RQFyuQhc+4MANTvWoNDWxygXxNgTAbIWTg7AQ8eR9ie4BLJmhxDWGR1Qxu4fv06P//8M1evXiU0NJS0adNSrVo1ihQpEuvnqmVsHmFbmfeK0+nTNphcnLl18S6T288hU670DFjUHa8S3lG2CXjwCKOTEc+p7ShRswgmF2e2LNzBhmnfWz1/7fZVqfxBOUY2nGjZ1nF8ayo1KYPBaOTgpsMsHbYWsznmJVdbZC5YLh+zDk7g+tlbBL1wafjiIav4/acTtBvTgneblSc0JJSrp68zp89S/P0CEjQzhF9C3n+hF8nTehD8NJjpngssi40rNSnDRyOb42Ry4tGDx0zvNp9rZ24maN58JXPRc1Zn3DxcMYeYmTdgGSf2nAZicVwYXv0Zo8x7xeg04d9sl+4wuf1cMuXKwICFnniVHBxlm4AHj0mawp2+87qS4+1sABzYeJgVY9ZHOFWw8uJsxrWYHn+XkMch89K/puOROhl+N5+v2Th98Cyzey+laNW36TrxQ1xcTYSGhLJy3AYObvo9qhgAGJyc4rQvpesWo9P4lpZjY0qneWTMmZ4BC7rSvfQwq7aDFnty5fSNuF9CHvbqMaR03WJ0mtAak8mZW5fuMqXjXDLmysCABd3oXmpIlG0CHjzGaDTQZlhTqjQvj9HJyIVjl5nZYzGBAU8oXLkg3T9vh7PJmft3/mFG90Wv/LqG1+nj0nWK0mlcS5xdnLl96R5TOof3a/95XelR1rpfBy7y5Opp60vIAZafncH41jNf6xJyc1DkH5ISYkx+t1k56nerxeDa46LNvMO8Ptb7GRfFetnvKq/jc/rb7LntNsmJT5FNckTeODGY5EjcxHWSkyBiMMlxJG9iH0c1yXFk9p7kFO9pv0nOsbm2m+RolBUREZFEKdF847GIiIjEkzfuHE/kVMkRERGRREmVHBEREbFi6++vsRdVckRERCRRUiVHRERErKmSIyIiIuK4VMkRERERa6rkiIiIiDguTXJEREQkUdLpKhEREbGiS8hFREREHJgqOSIiImJNlRwRERERx6VKjoiIiFgxhCWOUo4qOSIiIpIoqZIjIiIi1hJHIUeVHBEREUmcVMkRERERK/qeHBEREREHpkqOiIiIWFMlR0RERMRxvZGVHKdkyRI6QuwYDAmdIFbCQkISOkLsvWF9/CYKKV0goSPEmunouYSOEGthoaEJHSF23sT3XlBQQidweFqTIyIiIuLA3shKjoiIiNhQIqnkaJIjIiIib4Q5c+awbds2AKpUqcLHH38cbXudrhIRERGHd/DgQfbv3893333Hxo0bOX36NDt27Ij2MarkiIiIiBV7Ljz29/fH398/wvbkyZOTPHlyy8/p0qVjyJAhuLi4AJA7d25u3boV7XNrkiMiIiIJZvny5cyZMyfC9l69etG7d2/Lz3nz5rX8+8qVK2zbto21a9dG+9ya5IiIiIg1O1Zy2rdvT5MmTSJsf7GK86Lz58/j6enJxx9/TI4cOaJ9bk1yREREJMG8fFoqOkePHqVPnz4MGzaM+vXrv7K9JjkiIiJixRG/DPD27dv07NmT6dOnU758+Rg9RpMcERERcXhLlizh2bNnTJw40bKtVatWtG7dOsrHaJIjIiIi1sIcr5QzYsQIRowYEavH6HtyREREJFFSJUdERESsOOKanNehSo6IiIgkSqrkiIiIiDVVckREREQclyo5IiIiYsVgTugE8UOVHBEREUmUVMkRERERa1qTIyIiIuK4NMkRERGRREmnq0RERMRKYvkywP+LSU6ZOkXoOLoZpiTOXP7zBtN7LSUw4KlVm+oty9OsT13CwuDZkyDmfbya88euWLUZuaoXfnf+4YtBq2yfuXYROo7+AFMSE5dPX2d6ry8jZm5RjmZ93iMsLCw88+A1lszrLs3E9+YDS9sNs7aze/2vtstbpygdxzbH5GLi8p/Xmd5jcYS8/xm0sBtXTl9nw8xtAIxY1YvMuTNY7s/4VjpO7j/DmBYzbJbXkvmT5phcnMP7uMeSqDMv6MqV0zfYMCs8s0eqpPSe0Z5chbPzNPAZP63ax+b5P9s078tikr96ywo07/fvMRIYxBfeqyIc1/Y2eEgDLl26x/qvD0e4r1HjkjRsVJywMLh16wGfT93GP/8E2jVfXMYL9+Ru9J/TkWz5MmEwGvh5zUHWz9hq47yJ8733qmM3XZbUzNg9iu7lR+Dv9yh+ctUrQedP24SPuyevMq3LPAIDnsSojdFoxHNaO0rVKYaTsxMbpm1my4IdAOQrlZse0zvgmtQVo5ORdZM3snP1PgBGrR9IrqI5ePoofP+P7/mT+QOWx8v+yP/B6aoUaTwY8EVnxrWdS5eSw7h9xYeOnzS3apM1T0a6jGvBiKaf07PSaNZO+Z6Rq3pZtWnW9z3erpDPjpk7hWcu9W/mMc0iz/zB5/SsPCY888qelvsCHjymZ+UxlpstJzgp0nowcEFXxrWZTZfig7lz5R6dxraM0C5b/sxM2jqEyo1LW20f/9EcepQfSY/yI5nRcymPHgYyt/8Km+W1ZJ7fhXEfzqZLiSHcuexDp7EtIsmciUk/DI6Q2XNiG548ekq3UkPpV20spWsVoWzdojbN/KKY5M+aNyNdJrRkeOOp9KgwijWTNzNqTR+7ZXxZ9uxpmDqtNZXfzR/p/XnzZaRFyzL06bWSLp0Wc/PGAzp2eteuGeM6XrQf0QTfWw/wKjeSPlXH0qBzNQqWyW27vIn0vfeqY7dm64pM/XEYaTOnisdcyRm0tAdjm02lU8G+3L58l84TP4xxm/qeNcmaNxNdCw+gV5khNOlbn/yl8wAwesMglo/5Gq8S3gyrNwHPae3JkicjAIXK52NglVF4lfDGq4S340xwwsLsd7Mhu0xyxo8fz8OHD+3xUhGUqPE25/64zK2LdwH4YckuqjcvZ9UmOCiYGb2/5P7d8Izn/rhMqgwpcDY5AVCkUn5K1SzM1qW77ZO5+r+ZL937N/PuKDIve5752BVL5oJl82AONTN12xDmHfiENh+/j9FosF3eGu9w9uglSx9vWbSL6i3LR2jXsFsNti/7hb3fRfwED+BscmLQwm7M/3g1Pjfv2ywvQInqL2VevIvqLSLLXDPSzHmL52DnVwcxm8MICQ7l8I8nqPTSLxBbikn+4GchzOi59IVjxPq4trdGjUuydesJ9v5yJtL7z5+7Q7uPFvD48TNMJifSpvXA3/9JpG1tJa7jxbyP17Bo+DoAUmdMiSmJM48f2m4fEut7L7pjN3XGlJR/vwTDGk+J11wlaxfh3JGL3LxwB4Dv5/1EjTaVY9ymYuOy/LhsN+ZQM4/+ecyedQeo8VFlTElMrBy7nmM7TwHge/M+D338SZs1DRlzpMfNw43+C71YeGIag5b0wCNVsnjdr/93dpnkbNy4kRYtWvDTTz/Z4+WspMuSGp8bz9+0PjcfkDSFO+4erpZtd6/5cfjHk5afPT9rza9bjxESHErqjCnxmtSGyV0WYA61z7cjpcua2mqgiTLzTy9k/rQVv247TkhwKE7ORo7t+YvhH3zOoHoTKVnjHRp61rRh3jT4WvXx/Qh5AeYOXMnurw9F+Tx121fh/p1/OPj9UZtl/U+6rKnxvRnDzJFUwc4cuUiNVhVwcnbCNWkSKjUqReqMKW0d2yIm+e9e8+XwjycsP3t+1sZyXCeE2bN+YtfOv6JtExpqpmLFvKxb34siRbKxfdvJaNvHt7iOFwDmUDMfL+rGgl/Hc3L/GW6cv227vIn0vRfdsXv/zj+MazObmxfuxm+ubGnxueH7PNcNv39zucWoTbpsafC57me5z/eGH+mypCH4WTDbl+6ybK/XtSbuHm78/et5UqZPzh8/n2Jm94V4FffmyeOnDFzSPV7363UZwux3syW7THKyZs3K3LlzWbFiBc2bN2fr1q08fRr5OeP4ZjAaCIukHBYayYQlibsLw5f3IFOu9Mzo/SVOzk4MWerJgqFfWT5R2EN45ojbo87c3ZIZYPvyvcz7eA3PAoN4/PAJ3879iQoNStgsr9EQ8z6OTpNedVkzaVN8xYqWMRZ9HJmFw74iLAy+ODiWMV/15Y9dpwkJConnlFGLTf4k7i4MX9mTzLnSM73nUjuki5sDB87TtPFMli/fx8TJLTHYrggZQVzGixdN7rqQFjl745EqGW2GNLJZ3sT+3rPnsRtVrhc/3EbXxvjysWMwRPhg3HJwY9qNacHIhhMJehrEmcMX+OSDKfjc8MNsNrNizNeUrV8CZ9P/xXJZu7DLJMdgMJAnTx5WrVpF//79+fHHH6lRowYffvghAwcOtOlr+9y4T5pMz8/bps2cioAHj3gWGGTVLl3W1EzfMZxQs5nB9Sfx+OET8pXIQaYc6en2aSvm7v+Eep2q8W7TMvSb3dG2ma/7keaFqkC0mX8aTmiomcENJlvK4jValifn21kt7QwGCA2x3af3ezf8Ivbx/Yh5o5O76Fs4ORs5uS/yUxnx7d71+xH7OBaZ3T1cWTJyHZ5lhjPk/ckYDFhOL9pDTPOny5qaGTtHhlcX6k3k8UP7LuKNjcyZU/HOO8+P2+3bTpIhQwo8XvgkbWtxGS8AStZ4x1LRe/r4GXvW/0qeom/ZLG9ifu/Z+9i9d83Xui+zpMb//iOeBj6LUZt713xJkzm15b40mVPhczO8smNycWbY6r5Ua1WRvhWGc+nkVQDeqVSA8u+XsjzGYDBgNofZ7axBtMLseLMhu0xyXpzdVqhQgZkzZ7Jnzx6GDh1KzZq2O40CcHTnnxQonctyBUH9TtU49MMxqzZuyVyZ/MNgDnz/BxM7zifoaTAAfx++SNtCA+lZaTQ9K41m69Ld7P32cIRPbfGeedfp8My50v+buSqHfjgeReajTOy0wJIZ4K1CWWg7rDFGowEXVxMNu9bgl28jPxcfL3l3nqJAmdzP+7hLdQ798EesnqNIpQIc/yX6Uxnx6eiulzJ3rh7huIhOg87VaTeiKQAp0yenbvsq0Z4OiG8xye+WzJUp24ayf/NRPuswz+oYcURp0iRlxKhGJE8ePqmpUfNtrlzxseu6nLiMFwDvNinNR/9WbkwuzlRuWoYTe/+2Yd7E+d5LiGP36E8nKFgur2VBcAOv2hzadCTGbQ5uPkKdjtUwOhlJmsKdai0rcnBj+H1DVvbBPbk7/SqO4O5VH6v97Dmrk2UdTgvvhuzb8CtmswNMchIJu9TEPvzwwwjbTCYT77zzDu+8845NX/uhbwCf91jKiBU9cHZx5vble0zxXEze4jnoN7sjPSuNpmG3GqTPnpYKDUpYndYZ0nAyAfcf2zRf9Jl74uzixO3LPkzx+jfzrA70rDyGht2qkz5bmkgyT2H1xM30mPIh8w6Nw9nkxL6NR9i+fK/t8voEMM1rESNX98bZ9G8fd11A3uI56f9FJ3qUH/nK58icOwN3r/q+sl18Cc+8mJGreoUfF5fuMaXbQvIWz0H/uZ3oUWFUtI//atqW8HUXhydgMBhYMf47zv1x2U7pY5a/oWdN0mdPS8X3S1Dx/efHyOAGkxLkuI5MvnwZGehdD8+uSzl16garVx3k8xkfEhpqxs/3EaNGfGPXPHEdLxYO/4reM9oz/9dxABzc8gcbv9hhu7yJ9L2XEMfuPz7+TO30BSPXD8Tk4syti3eZ3H4O+UrmYsCi7niV8I6yDYQvQs6cOyMLjk/F5OLMloU7OLn3LwqWy8e7zctz/ewtZuwfb3m9xUNWcWT7cTbO3sqM/eMwGI1cPnWN6d3m22T/YiuxfE+OISyyE7oOrm5y254uinf2XFQQD8JC7Le2JN68YX38JgopXSChI8Sa6ei5hI4Qa2GhCbMw/LW9ge89c6DjnraNyg7zeru+XuUmU+32Wvu+G2Sz59bqJhEREbH25tU/IpXovwxQRERE/j+pkiMiIiJWEsuaHFVyREREJFFSJUdERESsqZIjIiIi4rg0yREREZFESaerRERExIoWHouIiIg4MFVyRERExJo5cZRyVMkRERGRREmVHBEREbGWOAo5quSIiIhI4qRKjoiIiFjR1VUiIiIiDkyVHBEREbEWljhKOarkiIiISKKkSo6IiIhY0ZocEREREQemSo6IiIhYUyVHRERExHGpkiMiIiJWDInk6qo3cpLzsME7CR0hVp4lf7MKZum//iuhI8SazweFEjpCrKX77u+EjhArAdmTJHSEWHPK9GaNFQCG0IROEDvBSQ0JHSHWXB+YEzqC2Mmb9dtXREREJIbeyEqOiIiI2FAiKXapkiMiIiKJkio5IiIiYiWxLDxWJUdEREQSJVVyRERExFriKOSokiMiIiKJkyo5IiIiYk1rckREREQclyo5IiIiYsWQOAo5quSIiIhI4qRKjoiIiFjTmhwRERERx6VKjoiIiFgx6G9XiYiIiDguVXJERETEmtbkiIiIiDguVXJERETEWuIo5KiSIyIiIomTJjkiIiKSKOl0lYiIiFgxaOGxiIiIiOP6v63kjPSqy8Xrvqz54fcI9zWrXZxmtYvxLCiEK7fuM+3Lnfg/fpoAKcPVK1OAdrVLERYWxtOgECav28Pf1+5atWlZtSjN3i1KWFgYN3wfMm7VDh4EPLFbxjK1CtNxVFNMLs5c/usG0/ssJzDAus/e71KNBp2qEhYWxu3LPszot4KHvgGW+9NmScWMH4fS492x+N9/ZLfsAO+VLUC7OqUII4ynz0KY8tUe/r56N9ZtbKlMrcJ0HNEEUxJnLp++yfS+ywl89FIfd65Gg45Vwvv4ig8z+q/koW8A7h5u9J/Zjmx5M2IwGvj5q0Osn/2j3bJHpW6FgrR97/mxPW3Vbv6+Yr8+jak3abwAGNGjLhev+bJ2SyR56xbngzrhea/evM/UJTsJSMC875UryEfvlYJ/j4Gpa6I+BkZ3rsPFG76s+vGonVNGblif97h01YevNln3c52qhWjZsJTl56TuSUifJhlNuyzgwcNAe8d8ParkvJneypya2cObU61MvkjvL1EoG23fL03vT9fTfthKDh2/xOAuteyc8rm3MqSi7wfv0mvWd7SesJrF235jqlcDqzYFs6enba2SdJz8FS3GreTavQf0eL+C3TKmSJOMAXM6MK79PLqUHcntK750HNXUqk2eotlp1qs2/etMxKviGG5eukv7YY0s99doWZ6pWz4mbeZUdsv9n7cypKJfs3fpPfM72oxdzZIffmNq9waxbmNLKdIkY8Cs9ozrOJ8u5UZx+6pP5H3csxb935uEV+VPuHnpHu2Hhvdx+6EN8b31AK/Kn9Cn1qc06FiFgqVy2S1/ZLJnTEWflpXpM/VbPhq1iqWbf2NSn/cTNNPL3rjxIktqZo9sTrWyUeR9OxsfNSxNn3Hr6TB4JYeOXWJItwTMmzEVfVpUps/n3/LhmFUs+f43JveMeAzkyJSaL7ybUaNU5Ptlb29lTc2MsS2oWj7yPD/u+YtOA1bQacAKunqv4v4/j5m+aOebM8FJROw2yTl06BDHjh0DYOnSpXh5eTFnzhyCgoLsFQGAZrWL8f3uU+z67Wyk9xfImYEjf17F599Kwp4j56lUIhfOTgkzHwwKCWXcyh34+j8G4K+rd0mbPKlVnr+v3aPxyGU8ehqEi7MT6VMm46EdP5mVqPY2545d4dalewD8sHQP1ZuXtWpz4cQ1OpUaQWDAE0xJnEmbKRX+98P3KXXGFFSoV4zhzWbYLfOLgkJCGbdiB74Pn/dxmhTWfRyTNrZUolohzh2/+ryPv/yF6s0i6eMyI1/o45SWiti8YetYNHoDAKkzpMCUxMRjf/tV+iITHBLKhKU78Pu3T/++fMeufRoTb9p48UHtYmzedYpdv0aeN3/ODBw59ULew+epWDIBx7fgUMYve+EYuBL5MdC8ejE27f2TnUfOJUTMCJq8V5wtO06y52Dk/fyiD5uU4cHDQDb/dNIOyeKR2Y43G7LL6arJkyfz+++/ExISQtasWTEYDLRu3Zpdu3YxduxYxo8fb48YAExbtguAMoXfivT+0xdu07xOcTKm9eCObwANqryDi8mZFB5u+P3z2G45/3Pbz5/bfv6Wnwc2q8IvJy8REmp9ZISYzVQtmpuRbWsRHBLKvO/X2y1juiyp8Ln5wPKzz60HJE3ujruHq9Upq9CQUMrXK0a/me0IfhbCis82AXD/zkPGtZ9nt7wve7mPB7Sowi8nrPs4Jm1sKV3m1PjcvG/5ObyP3XBP5mp1yio0JJTy7xWj34x2BAcFs2LiZst95lAzH8/rRKX3S3Jw6zFuXLhjl+xRue3rz23f533ar01V9h67aLc+jYk3bbz4/Mt/8xaJPO9fF27T/L3neetXdazxrX+rquw9HvEYmLI6fL/KvR35ftnbjEU7AShTLEe07VJ4uNGqUSk6D1pph1QSGbtM3/ft28dXX33FmjVrOHz4MFOnTqVKlSqMGTOGkycda3Z74uxNln57iIn9G7F0/IeYzWE8DHhCcEhoguZydXFmUtf6ZEuXkrErd0TaZs+Ji9QYNJ8FWw4xt3dTDAb7ZDMYjYRFcv42NJJfVoe2Hqdl3gGsmvw9Ezb0w2CvkDHg6uLMJM/6ZEufknHLI+/jmLSxBYPREHkfmyPp423HaZn/3z7+uq9VH0/uvpQW+QfgkTIpbbztd7otOq4uznzWswFZ06dkwlL79Wl8cNTxIionztxk6YZDfDaoEUs+/ZCwMMfI6+rizGfdw4+B8V++WcdAdBrWLsL+wxe4ffdhQkeJNUNYmN1usfXo0SMaNGjAjRs3XtnWLpOcsLAwAgICePDgAU+ePOHRo/BS6dOnTwkODrZHhBhzdzVx7O8bdBi+ik4jVrPv6EUA/B8l3MK8jKk8WPZxK8zmMLpNX8+jJ8+s7s+WLgXFcme2/LzpwGkypfEguburXfL53PAjTcaUlp/TZkpJwIPHPAt8fioyU850vF02j+Xnn1btJ322NCRL6W6XjK+SMbUHXw5pRag5DM+pEfs4pm1sxefm/dj38eoDlj4uWa0QqTOmAODp42fs+fYweYpkt1v+qGRI7cGSka0JNZvpMXE9jwLt16fxwRHHi+i4u5o49tcNOg5ZRedhq9l7JOHzZkjtwZLhrTGbzXSfbN/3la1Vr5ifrbv+TOgYicqJEydo3bo1V65ciVF7u0xyunbtSu3atWnUqBHe3t506tSJyZMn06ZNGz744AN7RIixtKmSMXdEC9zdXABo37gsOw6dSbA87klMLBzQnF3HLjB0yVaeBUf8xJU2RTI+61KPlEnDJzXvlSnAxVt+dluXc3T3XxQolYvMudIDUL9jFQ5tO27VJnWGlAxZ0o3kqZMBUK15Oa7+fZOAB/Yvkb/MPYmJBYPC+3jYosj7OCZtbOno7r8oUPKFPu4QWR+nYMiirs/7uFlZSx+/26gUH3mHL+g0uThTuVEpTux79XoCW3J3NTF/aHN2Hz3PiHlbeRYckqB5XoejjRevkjZVMuaOfp63Q9Oy7DiQgOObq4kFg8OPgeEL3sxjICrJkiYhS6ZUnDpzK6GjvJ6wMPvdYuHrr79m9OjRpE+fPkbt7bImp1GjRtSpU4fQ0FCSJk1K6dKl2b9/P4MGDaJixYr2iBCtAjkzMLRrbdoPW8m12w9Y+f1hloxtg8Fg4OTZm5bz8gmhZdViZErjQbViualWLLdl+4TVOxn+YQ1aT1jNsQs3WbLtMAsHNCfUbMbn4WMGzNsczbPGr4e+AXze60tGLPPC2cWZ25d9mNJ9CXmLvUW/me3/196dR0dR5msc/1YnnY0kQBIgSEAUgWBkBzWKMEGFCQHRwIyCgghcRRQUN5BBGdmu4IKso16QGRBlAIfBBTdAHUlQ0FGiIhARZAskBELI3umu+0c7YBOyzdGuTvN8zuF4qnzpPJZdb//qV2+lua/XNL77LJNVz73DnLcewVnuIvdoHk/dsdhrGatya++fj3HnViR1PnuMZ63YxORh1zN02spKx9z73BteKSZPHT/N8+P/ypRX7nEf4/05PDP2Ffcxnjuc+5Km891nP7Bq7gbmrH/47DEe7j7GLz+5hnHP3cGLn04FIP2dr/jnS5t+89xV+cMNnYiNieR3XS7jd13OdqDum73Wqwvna8uX54vzib+0CZPu6cOIiT/nXb+NJTN/zrvrMM+9Yl3eP/buRGx0JEldLiPpF++BWcs3Mnn4Ddz+51cty1ZbbVs1YeJ9fRn50HIA4po2JPdkwXlv24un/Px88vPzK+yPjIwkMjLSY9/MmTNr9dqGeb4b/T4ucehzVkeoldJI33lapCYar95pdYRayxl0udURaq3Ruu+tjlArJ1LirY5QawGOOje9Yfjmcp5KOer5zrq6mgo5WfcKj0/XPeLVn9e361Sv/az+I2JYuHBhhf33338/48aNO+/f6d27N8uXLycuLq7K175gfxmgiIiIWO/OO+/klltuqbD/3C7Of0NFjoiIiHjyYrPrfLelfi116z6KiIiISA2pkyMiIiIefP1byDdvrtmCeXVyRERExC+pyBERERG/pNtVIiIi4snHb1fVlDo5IiIi4pfUyRERERFP6uSIiIiI+C51ckRERMSTOjkiIiIivkudHBEREfFU977D9LzUyRERERG/pE6OiIiIePD1r3WoKXVyRERExC+pkyMiIiKe1MkRERER8V3q5IiIiIgnlzo5IiIiIj5LnRwRERHxpDU5IiIiIr6rTnZyps1cYnWEWpn+Y3+rI9RK0R8a8HHCeqtj1Mrt+w2rI9Saa2Tdusa4JapuvScA2occtDpCrZ12hVgdoVZey0m0OkKt9YvKsDrCf+ERqwPUSXWyyJHfVl0rcERE5Fem21UiIiIivkudHBEREfGkTo6IiIiI71InR0RERDzplwGKiIiI+C51ckRERMST6bI6wa9CnRwRERHxS+rkiIiIiCc9XSUiIiLiu9TJEREREU96ukpERETEd6mTIyIiIp60JkdERETEd6mTIyIiIp7UyRERERHxXSpyRERExC/pdpWIiIh40u0qEREREd+lTo6IiIh4cukLOkVERER8ljo5IiIi4klrckRERER81wXXyTm8z2TNYpOSIjBsMGS8QYvWhseYbZtMNq01wYCgYBh8r8HFbYxKXtE7esQkMCXhNn7/yRMe+/vGduWPLXqe2Q4PDKFRcH0Gpc3gZFmBt2MCsGcvzJgPBQVgC4CnHoaEtp5jXn0DVq6DkGC4tAU8MQEaRFoSF4BDr+/l5LYcAsPdp0RwbBiX3nd5hXGmafLT/+0mNK4eTfo193ZMD4df/4G87dkE1LMDENI0jJZjEyqMM02TA0t2ERpXj8bJLbwd84xPluazJ62EkAj3tVXDZoH0f6yBx5iv3i7k63eKCAwyiIoLpPeYSEIjrLsWO7gPVi4KoLjQwGYzufMBJy3beI7ZuN7GR2/bMIBGF5nc9aCTyIaWxAXgyD6TtYtdFBeBzQa3jrdVmOO2b3Kxaa2JYYA9GAbfa6OFRXPcT6/9SO62XALruc+9kKahtLk/3mNMTlo2We8cAsPAFmSj5bBLCb80woq4lTq238k7L5ZQUmhis8FN94dyUesAq2P99/ykk3NBFTllJSaLJpvcPsEg4UqDjK0mf5tt8sSSsyf3sYMm/1xiMnGhQf1og++2mSyZbjJ9hXVFTlxoDGNb9wcqZnj/6Je8f/RLAAIMGwu6jmXlTx9ZVuAUl8CoR2DGROh1NWzaAo/OgA0rzo75/N+w5HVYtRhiG8P692HqszBvmiWRASjMPMUlY9sR3rp+pWOKjxRycPkPFO3NJzSunhfTnV/hD6doeW8C9arIXHKkkEMr9vyc+RIvpqvoyC4HKY824KJ2Qef99wcyStn+RiFDnokmIiaAnR8Vs3HRKQZMsqZiKC2B5x4P5K6HnHS80uTf6QYvPR3I/75SfmbM/j3w3lob014sJ6werHrZxj/+ZmPEg9Ys2iwrMVk82cWQCbYzc9zy2S6mLDn7YXvsoMn6JSaPLrSdmeOWTnfx1AprPpBPZ56m9di2RLQ5/1VOcVYRB17fR/sZnQlqEMTJr0+wZ/4uurzQ3ctJK1dWYvK3KUXc/EAIbbrb+X6rg7XPFjP+pXCro13wvFbkbNy4kY0bN5KTk4PdbqdFixYkJyfTuXNnb0Xg+39DTFNIuNJdLLS/GqKbeBYOgXYY+qC7wAFo0QbyT0K5wyTQ7v1CJ9hmZ0rCEBZlvsUTCUOrHHv7xUnklRXw5uHPvJSuorTt0KKZu8AB6H0txDX1HPPdHkjs6i5wAG7sCU88A2UOCLJ7Ny+Ay+Gi6EABxzYc5EB2JiGxocQNbUVQdIjHuOMbjxDTK5b86GDvhzyHy+Gi+KcCjm04QFlOMcFNwmg29LKKmTcdJrrnRdijQip5Je8od5hk/+hg+z8KyTuaT8OLAvjd6EgiG539YM3eW06LjkFExLj3tU4M5sMFp3A6TAIsOPe++9KgcVOTjle6r2g7J5o0ii33GNOyDTy9rJzAQHCUQd5xg5hY666Ad513jvPshAXaYciDNp+Y41wOF4U/FXDknUOULCshNDaUi2+/hOCYs+9XI9DGpaNbE9TAXRyHXxKOI68MV7kLW6BvrLjY+1U5UU1ttOnunsDirw6kYaxvZPuvufyjk+OV/wsvvfQSb7zxBh06dMAwDDp16kSTJk2YPHkyq1ev9kYEALIPQ2QUrHzexexxLhY+buJyeo6JjjW44ir3iW6aJv94yaT91VhS4AA8Ej+INw9/xt6CrCrH1beHcWuLnizY86aXkp3f/oMQEwV/mg2D74aRD0P5Oce4Qzt3N+fwUff2unfB4TDIy/d+XgBHXikR7Rpy0aBLaDejK/VaRbL3he8wz2nXNh/emqjEJtaEPIcjr5TwyxvQdNAltJ3enXqtItk375sKmeOGtaGhD2QuzHXSvEMQ194RzvD50TRtG8T6GSc98sa2sXMwo4z8bPcb5tuNxTjLofi0NV2Ro4cN6jeEV54L4Kn7Anh2UgBOZ8VxgYHw7zSDh4YGsvsbgx59rXv0NvuwSUQUvPa8i2fGOVn0uOu8c1zCL+a4dS+ZXGHRHFd2soz67RrQfPDFdJjVmfDLItj9wvce74uQRiE07BR1Ju9Pr+2jYZconylwAI4fdhHe0OCfLxTz4gMF/O1PRRWOu1jDK++SDRs2sHjxYoYOHcqiRYtIT09n1KhRrF69mmXLlnkjAgDOcvhuO1zbz2DiAhu9BhosftLEUVaxYi0tMXllpklOlruzY4WbmyXiNF1syNpe7dgBF13NlpydZJWc8EKyypU74V+fwR8HwNqX4Y5UGDMRysrOjunWEcaOgHFT3IWQYUD9SBO7RTdPgxuFctnD7QmNq4dhGDROjqM0u5iy4yXWBKqB4EahtHqoI6Fx4RiGQaPk5j6duX5sIKlTo4i52I5hGHS7JYxTR53kHzv7SRCXEMTVt4Xz5qyTrHzoOIbNICTCICDQmvPPWQ4Z2w169XMxdZGT6we6mDslEEdZxbFdrjVZsLacm4c5ef7xQMt+xYizHHZuh2v6GTy6IICeA228+KSr0jlu2UwXOVkmQx60pmAIaRxC/KMJhDV3n3tN+zWj9FgJpTmlFcY6S5xkLthFybESLh3V2oK0lXOVQ+YX5XT9vZ0x88K5akAQr04totxRd7shpuny2p/fklfe2aWlpRQXFwNQUlJCXl4eAGFhYdhs3ju56kdDbHNoGe+eNDskGpguyD3qOe5EtsnzE0yMABg/2yAs3JpJNrlpN+Ijm7P0ygnM6TSK4AA7S6+cQHRQxXvXvZt0rFEx9FtrHA2XXgwdf16ze30PcDrh4JGzYwqLoHtH+McSdyF0fQ/3fqsWHhcdKCA37ViF/UaA71wpnqv4YAEn0o5W2G8EWLtAvjI5+xzs/KjYY58J2H5RwJQVuYi7Iog7Xojh9udjaHWV+7ZgSIQ1/00Nok2aNodW7dwfVF2uMXG5IOcXh/3YYdjz7dl81/U1OZ4NRdYsiaN+NDQ5Z45zVTLHzZ3gwhZgMG62zbI5rvBAITlbsj32mYBxTmFberyE76btwLAZXD75ijOLlH1FRLRBTJyN5vHuXO0S7bhccDLLP36hXl3mlVk8NTWVIUOG8MwzzzB8+HBSU1M5cuQIgwYNon///t6IAEBCN/fJfiDTPWn98I37n9GxZ8eUFJnMe8yk47UGIx+3ERRs3YfGPV8sYMTnzzFq21we+3oppU4Ho7bNJbfM875OeGAozcJi+PbUfmuC/sJ1V8HhLPhut3t7+w53p+aX63Kyj8OdD0JBoXv7xRWQcr17nBUMm8GhV3+gNMf9IXx88xFC4+oRFGX92ptKGXB4ZeaZzLlnMlu79qYyhg0+ejmfU0fda1p2vFtMo4sDz6y/ASg44WLNn05QWuT+YNi2uoC214ViWPTG6NDd5Pgx9+JigN0ZhvsJql/MF6dOGLw4K4DTp9zbWzcbxLWEcIsK9su7GZw4Z44zqDjHLXjMRcdrDUZYPMcZBuxfsZeSbHcH8timo4Q1DyP4F+ees7icnbO+IapbDK3vj8cW5HtPLLXuGkjeMRdHMt2dyf3flmMY0KAur8txmd778xvySjl899130759e3bu3MmkSZNITEyksLCQ2bNn07Zt2+pf4FcSGWVw91T4+0KTshKTQDv8zxMGR/bDay+4eHyxjU/ehBPZsCPdZEf62YM/7mmD8EjfuEpuGxHHY+3+wKhtcwGIC40mtzQf52/c9quJRtGwYCZMmwtFJe6FxPOnQ+Y+9+LidUvhkhbwP0Ph1jHu93eX9vDEg9ZlDo2rR9wdl7F37reYLgiKCuKSse0o3HeaA6/spt30btaFq0RoXDjN7mjNvhe+wXSZ2KOCufjeBIr25XPgld3ET/edJ08AYi62k3R3JP+ckYfpMgmPDqDfow04mungw4WnGDYvhqi4QLoPqsfrj+RimnBRuyB632PdY8L1o2DcVCcrFgRQWmIQaIf7pzo5tN9g2fMBTHuxnDbtTfoPcTH7kUBsAe7uz7ip5dW/+G8kMspg9FQbaxa6KCuBADuMesJG1n54/QUnExcH8K83TU5kQ0a6SUb62duF9z9to56X57iw5vVoObwVu5/fiWmaBDcMpvXYthT8eJofl/5Ah5mdOfphFqXHSznxZS4nvsw983fbTboCe4QFTyqcR0SUjSFPhPHW4mIcpRAQCLf9KRR7kG98ZlzIDPPclYp1wIf72lkdoVam/+i9btWv4eOE9VZHqLXb9//O6gi15jLr1lVe76jvrY5Qa+1DDlododZOu3yzG1eZ13ISrY5Qa/2iMqyOUGu3Xubd5Qi/bzjaaz/rvZNLfrPXrluzrIiIiEgNqcgRERERv+RbS9RFRETEelb9HoRfmTo5IiIi4pfUyRERERFPde+ZpPNSJ0dERET8kjo5IiIi4sHUmhwRERER36VOjoiIiHjSmhwRERER36VOjoiIiHj6jb8401vUyRERERG/pE6OiIiIeDL1dJWIiIiIz1InR0RERDyYWpMjIiIi4rvUyRERERFPWpMjIiIi4rtU5IiIiIhf0u0qERER8aCFxyIiIiI+TJ0cERER8eQnC48N0/STrxoVERER+QXdrhIRERG/pCJHRERE/JKKHBEREfFLKnJERETEL6nIEREREb+kIkdERET8koocERER8UsqckRERMQvqcgRERERv6QiB3jrrbfo168fffr0YeXKlVbHqbGCggL69+/PoUOHrI5SIwsXLiQlJYWUlBTmzJljdZxqzZs3j379+pGSksKyZcusjlMrs2fPZtKkSVbHqJFhw4aRkpLCwIEDGThwIDt27LA6UpU2b95MamoqycnJzJgxw+o41VqzZs2ZYztw4EC6du3KtGnTrI5VrfXr15+ZL2bPnm11nGq9/PLL9O3blwEDBvCXv/zF6jjyH+YF7ujRo2ZSUpJ58uRJs7Cw0BwwYICZmZlpdaxqff3112b//v3NhIQE8+DBg1bHqVZaWpp56623mqWlpWZZWZk5fPhw84MPPrA6VqU+//xz87bbbjMdDodZXFxsJiUlmXv37rU6Vo2kp6ebV111lTlx4kSro1TL5XKZPXr0MB0Oh9VRauTAgQNmjx49zKysLLOsrMwcMmSI+fHHH1sdq8b27Nlj3njjjWZubq7VUapUVFRkdu/e3czNzTUdDoc5ePBgMy0tzepYlUpLSzP79+9vnj592iwvLzfvuece8/3337c6lpimecF3ctLT07n66qtp0KABYWFh9O3bl/fee8/qWNVavXo1U6dOpXHjxlZHqZFGjRoxadIkgoKCsNvttGrViiNHjlgdq1JXXnkly5cvJzAwkNzcXJxOJ2FhYVbHqlZeXh5z585lzJgxVkepkR9//BGAkSNHctNNN/Hqq69anKhqH374If369SM2Nha73c7cuXPp2LGj1bFq7M9//jMTJkwgKirK6ihVcjqduFwuiouLKS8vp7y8nODgYKtjVWrnzp306NGD8PBwAgICuO6669i4caPVsQTdriI7O5tGjRqd2W7cuDHHjh2zMFHNzJw5k27dulkdo8Zat25Np06dANi/fz/vvvsuvXr1sjZUNex2O/PnzyclJYXExESaNGlidaRqPfnkk0yYMIHIyEiro9RIfn4+iYmJLFq0iL/+9a+sWrWKtLQ0q2NV6qeffsLpdDJmzBgGDhzIa6+9Rv369a2OVSPp6emUlJSQnJxsdZRqhYeH88ADD5CcnEyvXr1o1qwZXbp0sTpWpRISEtiyZQt5eXmUlpayefNmjh8/bnUsQUUOLpcLwzDObJum6bEtv67MzExGjhzJY489RsuWLa2OU63x48ezdetWsrKyWL16tdVxqrRmzRqaNm1KYmKi1VFqrHPnzsyZM4eIiAiioqIYPHgwn3zyidWxKuV0Otm6dSuzZs3i73//OxkZGaxbt87qWDWyatUq7rrrLqtj1MiuXbt44403+Oijj/j000+x2WwsXbrU6liVSkxMJDU1lWHDhjF69Gi6du2K3W63OpagIofY2FhycnLObOfk5NSZW0B1zZdffsmIESN4+OGHueWWW6yOU6W9e/fy/fffAxAaGkqfPn3YvXu3xamqtmHDBtLS0hg4cCDz589n8+bNzJo1y+pYVfriiy/YunXrmW3TNAkMDLQwUdViYmJITEwkKiqKkJAQbrjhBjIyMqyOVa2ysjK2b99O7969rY5SI1u2bCExMZHo6GiCgoJITU1l27ZtVseqVEFBAX369OGtt95ixYoVBAUF0bx5c6tjCSpyuOaaa9i6dSsnTpyguLiYDz74gJ49e1ody+9kZWVx33338eyzz5KSkmJ1nGodOnSIKVOmUFZWRllZGZs2baJr165Wx6rSsmXLePvtt1m/fj3jx4+nd+/eTJ482epYVTp9+jRz5syhtLSUgoIC1q1bx4033mh1rEolJSWxZcsW8vPzcTqdfPrppyQkJFgdq1q7d++mZcuWdWJdGUB8fDzp6ekUFRVhmiabN2+mffv2Vseq1KFDhxg7dizl5eWcPn2atWvX1onbghcC371k8pImTZowYcIEhg8fjsPhYPDgwXTo0MHqWH5n6dKllJaW8vTTT5/Zd9tttzFkyBALU1WuV69eZGRkcPPNNxMQEECfPn3qRHFW1yQlJbFjxw5uvvlmXC4XQ4cOpXPnzlbHqlTHjh0ZPXo0Q4cOxeFwcO211zJo0CCrY1Xr4MGDxMbGWh2jxnr06MHOnTtJTU3FbrfTvn177r77bqtjVSo+Pp4+ffpw00034XQ6GTFihM9fFF0oDNM0TatDiIiIiPzaLvjbVSIiIuKfVOSIiIiIX1KRIyIiIn5JRY6IiIj4JRU5IiIi4pdU5IiIiIhfUpEjIiIifklFjojUSHJyMj179iQzM9PqKCIiNaIiR0Rq5O2336Zly5a8//77VkcREakRFTkiUiMBAQF07drV57+oVETkPy74764SkZopKSlhw4YN6JtgRKSuUCdHRGpk7ty5NG7cmAMHDlBYWGh1HBGRaqnIEZFqffXVV7z77rssWLCAiIgILT4WkTpBRY6IVKm0tJTJkyfz1FNP0aBBA+Lj49m1a5fVsUREqqUiR0SqNG/ePDp16kRSUhIA8fHxWnwsInWCihwRqVRGRgbvvfcekydPPrOvXbt26uSISJ1gmHpUQkRERPyQOjkiIiLil1TkiIiIiF9SkSMiIiJ+SUWOiIiI+CUVOSIiIuKXVOSIiIiIX1KRIyIiIn5JRY6IiIj4pf8HuQjtIVSOyrMAAAAASUVORK5CYII=\n",
-      "text/plain": [
-       "<Figure size 720x720 with 2 Axes>"
-      ]
-     },
-     "metadata": {},
-     "output_type": "display_data"
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "/Users/mhjensen/Software/anaconda3/lib/python3.8/site-packages/sklearn/neural_network/_multilayer_perceptron.py:614: ConvergenceWarning: Stochastic Optimizer: Maximum iterations (100) reached and the optimization hasn't converged yet.\n",
-      "  warnings.warn(\n",
-      "/Users/mhjensen/Software/anaconda3/lib/python3.8/site-packages/sklearn/neural_network/_multilayer_perceptron.py:614: ConvergenceWarning: Stochastic Optimizer: Maximum iterations (100) reached and the optimization hasn't converged yet.\n",
-      "  warnings.warn(\n",
-      "/Users/mhjensen/Software/anaconda3/lib/python3.8/site-packages/sklearn/neural_network/_multilayer_perceptron.py:614: ConvergenceWarning: Stochastic Optimizer: Maximum iterations (100) reached and the optimization hasn't converged yet.\n",
-      "  warnings.warn(\n",
-      "/Users/mhjensen/Software/anaconda3/lib/python3.8/site-packages/sklearn/neural_network/_multilayer_perceptron.py:614: ConvergenceWarning: Stochastic Optimizer: Maximum iterations (100) reached and the optimization hasn't converged yet.\n",
-      "  warnings.warn(\n",
-      "/Users/mhjensen/Software/anaconda3/lib/python3.8/site-packages/sklearn/neural_network/_multilayer_perceptron.py:614: ConvergenceWarning: Stochastic Optimizer: Maximum iterations (100) reached and the optimization hasn't converged yet.\n",
-      "  warnings.warn(\n",
-      "/Users/mhjensen/Software/anaconda3/lib/python3.8/site-packages/sklearn/neural_network/_multilayer_perceptron.py:614: ConvergenceWarning: Stochastic Optimizer: Maximum iterations (100) reached and the optimization hasn't converged yet.\n",
-      "  warnings.warn(\n",
-      "/Users/mhjensen/Software/anaconda3/lib/python3.8/site-packages/sklearn/neural_network/_multilayer_perceptron.py:614: ConvergenceWarning: Stochastic Optimizer: Maximum iterations (100) reached and the optimization hasn't converged yet.\n",
-      "  warnings.warn(\n",
-      "/Users/mhjensen/Software/anaconda3/lib/python3.8/site-packages/sklearn/neural_network/_multilayer_perceptron.py:614: ConvergenceWarning: Stochastic Optimizer: Maximum iterations (100) reached and the optimization hasn't converged yet.\n",
-      "  warnings.warn(\n",
-      "/Users/mhjensen/Software/anaconda3/lib/python3.8/site-packages/sklearn/neural_network/_multilayer_perceptron.py:614: ConvergenceWarning: Stochastic Optimizer: Maximum iterations (100) reached and the optimization hasn't converged yet.\n",
-      "  warnings.warn(\n",
-      "/Users/mhjensen/Software/anaconda3/lib/python3.8/site-packages/sklearn/neural_network/_multilayer_perceptron.py:614: ConvergenceWarning: Stochastic Optimizer: Maximum iterations (100) reached and the optimization hasn't converged yet.\n",
-      "  warnings.warn(\n",
-      "/Users/mhjensen/Software/anaconda3/lib/python3.8/site-packages/sklearn/neural_network/_multilayer_perceptron.py:614: ConvergenceWarning: Stochastic Optimizer: Maximum iterations (100) reached and the optimization hasn't converged yet.\n",
-      "  warnings.warn(\n",
-      "/Users/mhjensen/Software/anaconda3/lib/python3.8/site-packages/sklearn/neural_network/_multilayer_perceptron.py:614: ConvergenceWarning: Stochastic Optimizer: Maximum iterations (100) reached and the optimization hasn't converged yet.\n",
-      "  warnings.warn(\n",
-      "/Users/mhjensen/Software/anaconda3/lib/python3.8/site-packages/sklearn/neural_network/_multilayer_perceptron.py:614: ConvergenceWarning: Stochastic Optimizer: Maximum iterations (100) reached and the optimization hasn't converged yet.\n",
-      "  warnings.warn(\n",
-      "/Users/mhjensen/Software/anaconda3/lib/python3.8/site-packages/sklearn/neural_network/_multilayer_perceptron.py:614: ConvergenceWarning: Stochastic Optimizer: Maximum iterations (100) reached and the optimization hasn't converged yet.\n",
-      "  warnings.warn(\n",
-      "/Users/mhjensen/Software/anaconda3/lib/python3.8/site-packages/sklearn/neural_network/_multilayer_perceptron.py:614: ConvergenceWarning: Stochastic Optimizer: Maximum iterations (100) reached and the optimization hasn't converged yet.\n",
-      "  warnings.warn(\n",
-      "/Users/mhjensen/Software/anaconda3/lib/python3.8/site-packages/sklearn/neural_network/_multilayer_perceptron.py:614: ConvergenceWarning: Stochastic Optimizer: Maximum iterations (100) reached and the optimization hasn't converged yet.\n",
-      "  warnings.warn(\n",
-      "/Users/mhjensen/Software/anaconda3/lib/python3.8/site-packages/sklearn/neural_network/_multilayer_perceptron.py:614: ConvergenceWarning: Stochastic Optimizer: Maximum iterations (100) reached and the optimization hasn't converged yet.\n",
-      "  warnings.warn(\n",
-      "/Users/mhjensen/Software/anaconda3/lib/python3.8/site-packages/sklearn/neural_network/_multilayer_perceptron.py:614: ConvergenceWarning: Stochastic Optimizer: Maximum iterations (100) reached and the optimization hasn't converged yet.\n",
-      "  warnings.warn(\n"
-     ]
-    },
-    {
-     "data": {
-      "image/png": "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\n",
-      "text/plain": [
-       "<Figure size 720x720 with 2 Axes>"
-      ]
-     },
-     "metadata": {},
-     "output_type": "display_data"
-    }
-   ],
+   "id": "09a1c0a5",
+   "metadata": {
+    "collapsed": false,
+    "editable": true
+   },
+   "outputs": [],
    "source": [
     "%matplotlib inline\n",
     "\n",
@@ -315,8 +209,10 @@
   },
   {
    "cell_type": "markdown",
-   "id": "719d1468",
-   "metadata": {},
+   "id": "d27a4d7a",
+   "metadata": {
+    "editable": true
+   },
    "source": [
     "## Learning Rate and more\n",
     "\n",
@@ -337,8 +233,10 @@
   },
   {
    "cell_type": "markdown",
-   "id": "e1456c44",
-   "metadata": {},
+   "id": "b40cdb70",
+   "metadata": {
+    "editable": true
+   },
    "source": [
     "## Thursday, Principal Component Analysis\n",
     "\n",
@@ -348,8 +246,10 @@
   },
   {
    "cell_type": "markdown",
-   "id": "9b140121",
-   "metadata": {},
+   "id": "d686ca41",
+   "metadata": {
+    "editable": true
+   },
    "source": [
     "## A kind of Bird's view  on PCA\n",
     "\n",
@@ -380,8 +280,10 @@
   },
   {
    "cell_type": "markdown",
-   "id": "f5bf9640",
-   "metadata": {},
+   "id": "cf3a902b",
+   "metadata": {
+    "editable": true
+   },
    "source": [
     "## Thursday: Clustering and Unsupervised Learning\n",
     "\n",
@@ -398,8 +300,10 @@
   },
   {
    "cell_type": "markdown",
-   "id": "7511445d",
-   "metadata": {},
+   "id": "fbbc0619",
+   "metadata": {
+    "editable": true
+   },
    "source": [
     "## Basic Idea of the $k$-means Clustering Algorithm\n",
     "\n",
@@ -412,8 +316,10 @@
   },
   {
    "cell_type": "markdown",
-   "id": "de976ee7",
-   "metadata": {},
+   "id": "0b8bd522",
+   "metadata": {
+    "editable": true
+   },
    "source": [
     "## The $k$-means Algorithm\n",
     "\n",
@@ -423,8 +329,10 @@
   },
   {
    "cell_type": "markdown",
-   "id": "133e6369",
-   "metadata": {},
+   "id": "344e68f0",
+   "metadata": {
+    "editable": true
+   },
    "source": [
     "$$\n",
     "k\\in\\{1, \\cdots, K \\}.\n",
@@ -433,8 +341,10 @@
   },
   {
    "cell_type": "markdown",
-   "id": "0108fed5",
-   "metadata": {},
+   "id": "9ef8dcf3",
+   "metadata": {
+    "editable": true
+   },
    "source": [
     "In the basic k-means algorithm each point is assigned to only\n",
     "one cluster $k$, and these assignments are *non-injective* i.e. many-to-one. We\n",
@@ -453,8 +363,10 @@
   },
   {
    "cell_type": "markdown",
-   "id": "8a483f87",
-   "metadata": {},
+   "id": "50cfcdd3",
+   "metadata": {
+    "editable": true
+   },
    "source": [
     "## Basic Math of the $k$-means Algorithm\n",
     "\n",
@@ -463,8 +375,10 @@
   },
   {
    "cell_type": "markdown",
-   "id": "834339d7",
-   "metadata": {},
+   "id": "f1dccb55",
+   "metadata": {
+    "editable": true
+   },
    "source": [
     "<!-- Equation labels as ordinary links -->\n",
     "<div id=\"eq:kmeanspoints\"></div>\n",
@@ -478,8 +392,10 @@
   },
   {
    "cell_type": "markdown",
-   "id": "cc15d3e7",
-   "metadata": {},
+   "id": "d8e16bc5",
+   "metadata": {
+    "editable": true
+   },
    "source": [
     "which we wish to group into $K < n$ clusters. For our dissimilarity measure we\n",
     "use the *squared Euclidean distance*"
@@ -487,8 +403,10 @@
   },
   {
    "cell_type": "markdown",
-   "id": "eba07965",
-   "metadata": {},
+   "id": "dd222257",
+   "metadata": {
+    "editable": true
+   },
    "source": [
     "<!-- Equation labels as ordinary links -->\n",
     "<div id=\"eq:squaredeuclidean\"></div>\n",
@@ -503,8 +421,10 @@
   },
   {
    "cell_type": "markdown",
-   "id": "5ac0a715",
-   "metadata": {},
+   "id": "5578c171",
+   "metadata": {
+    "editable": true
+   },
    "source": [
     "## Within Cluster Point Scatter\n",
     "\n",
@@ -515,8 +435,10 @@
   },
   {
    "cell_type": "markdown",
-   "id": "0c4f3952",
-   "metadata": {},
+   "id": "474f106f",
+   "metadata": {
+    "editable": true
+   },
    "source": [
     "<!-- Equation labels as ordinary links -->\n",
     "<div id=\"eq:withincluster\"></div>\n",
@@ -532,8 +454,10 @@
   },
   {
    "cell_type": "markdown",
-   "id": "086d7bb8",
-   "metadata": {},
+   "id": "5cea0534",
+   "metadata": {
+    "editable": true
+   },
    "source": [
     "where $\\boldsymbol{\\overline{x_k}}$ is the mean vector associated with the $k$-th\n",
     "cluster, and $N_k = \\sum_{i=1}^nI(C(i) = k)$, where the $I()$ notation is\n",
@@ -547,8 +471,10 @@
   },
   {
    "cell_type": "markdown",
-   "id": "93153229",
-   "metadata": {},
+   "id": "cffd78be",
+   "metadata": {
+    "editable": true
+   },
    "source": [
     "## More Details\n",
     "\n",
@@ -557,8 +483,10 @@
   },
   {
    "cell_type": "markdown",
-   "id": "d662e081",
-   "metadata": {},
+   "id": "1b9b26b4",
+   "metadata": {
+    "editable": true
+   },
    "source": [
     "<!-- Equation labels as ordinary links -->\n",
     "<div id=\"eq:totalscatter\"></div>\n",
@@ -576,8 +504,10 @@
   },
   {
    "cell_type": "markdown",
-   "id": "9a93a5fe",
-   "metadata": {},
+   "id": "2cfcf75c",
+   "metadata": {
+    "editable": true
+   },
    "source": [
     "This is a quantity that is conserved throughout the $k$-means algorithm. It can\n",
     "be thought of as the total amount of information in the data, and it is composed\n",
@@ -588,8 +518,10 @@
   },
   {
    "cell_type": "markdown",
-   "id": "f3f21886",
-   "metadata": {},
+   "id": "0ccc7514",
+   "metadata": {
+    "editable": true
+   },
    "source": [
     "## Total Cluster Variance\n",
     "Given a cluster mean $\\boldsymbol{m_k}$ we define the **total cluster variance**"
@@ -597,8 +529,10 @@
   },
   {
    "cell_type": "markdown",
-   "id": "ef7025dc",
-   "metadata": {},
+   "id": "1962a7bd",
+   "metadata": {
+    "editable": true
+   },
    "source": [
     "<!-- Equation labels as ordinary links -->\n",
     "<div id=\"eq:totalclustervariance\"></div>\n",
@@ -612,16 +546,20 @@
   },
   {
    "cell_type": "markdown",
-   "id": "ddc8521a",
-   "metadata": {},
+   "id": "8e9d7070",
+   "metadata": {
+    "editable": true
+   },
    "source": [
     "Now we have all the pieces necessary to formally revisit the $k$-means algorithm."
    ]
   },
   {
    "cell_type": "markdown",
-   "id": "b2ad92fa",
-   "metadata": {},
+   "id": "fb253615",
+   "metadata": {
+    "editable": true
+   },
    "source": [
     "## The $k$-means Clustering Algorithm\n",
     "\n",
@@ -636,8 +574,10 @@
   },
   {
    "cell_type": "markdown",
-   "id": "676162c0",
-   "metadata": {},
+   "id": "534ace62",
+   "metadata": {
+    "editable": true
+   },
    "source": [
     "## Summarizing\n",
     "\n",
@@ -654,8 +594,10 @@
   },
   {
    "cell_type": "markdown",
-   "id": "8daf5606",
-   "metadata": {},
+   "id": "50c0ed67",
+   "metadata": {
+    "editable": true
+   },
    "source": [
     "## Writing our own Code, the Data Set\n",
     "\n",
@@ -672,8 +614,11 @@
   {
    "cell_type": "code",
    "execution_count": 2,
-   "id": "f9839e26",
-   "metadata": {},
+   "id": "396531c2",
+   "metadata": {
+    "collapsed": false,
+    "editable": true
+   },
    "outputs": [],
    "source": [
     "import time\n",
@@ -689,8 +634,10 @@
   },
   {
    "cell_type": "markdown",
-   "id": "6ae4d681",
-   "metadata": {},
+   "id": "56afcdd4",
+   "metadata": {
+    "editable": true
+   },
    "source": [
     "Next we define functions, for ease of use later, to generate Gaussians and to\n",
     "set up our toy data set."
@@ -699,8 +646,11 @@
   {
    "cell_type": "code",
    "execution_count": 3,
-   "id": "0ea42bb9",
-   "metadata": {},
+   "id": "e632f8bf",
+   "metadata": {
+    "collapsed": false,
+    "editable": true
+   },
    "outputs": [],
    "source": [
     "def gaussian_points(dim=2, n_points=1000, mean_vector=np.array([0, 0]),\n",
@@ -756,8 +706,10 @@
   },
   {
    "cell_type": "markdown",
-   "id": "d9a5d89a",
-   "metadata": {},
+   "id": "1ccc01db",
+   "metadata": {
+    "editable": true
+   },
    "source": [
     "## Implementing the $k$-means Algorithm\n",
     "\n",
@@ -768,8 +720,11 @@
   {
    "cell_type": "code",
    "execution_count": 4,
-   "id": "801d745d",
-   "metadata": {},
+   "id": "f0999ed1",
+   "metadata": {
+    "collapsed": false,
+    "editable": true
+   },
    "outputs": [],
    "source": [
     "\n",
@@ -810,8 +765,10 @@
   },
   {
    "cell_type": "markdown",
-   "id": "51bfa3ab",
-   "metadata": {},
+   "id": "7025d35c",
+   "metadata": {
+    "editable": true
+   },
    "source": [
     "## Plotting"
    ]
@@ -819,8 +776,11 @@
   {
    "cell_type": "code",
    "execution_count": 5,
-   "id": "fee06473",
-   "metadata": {},
+   "id": "cd88014d",
+   "metadata": {
+    "collapsed": false,
+    "editable": true
+   },
    "outputs": [],
    "source": [
     "fig = plt.figure()\n",
@@ -840,8 +800,10 @@
   },
   {
    "cell_type": "markdown",
-   "id": "fa5e6821",
-   "metadata": {},
+   "id": "a45d1f7c",
+   "metadata": {
+    "editable": true
+   },
    "source": [
     "So what do we have so far? We have 'picked' $k$ centroids at random from our\n",
     "data points. There are other ways of more intelligently choosing their\n",
@@ -857,8 +819,10 @@
   },
   {
    "cell_type": "markdown",
-   "id": "eded179b",
-   "metadata": {},
+   "id": "e2202d97",
+   "metadata": {
+    "editable": true
+   },
    "source": [
     "## Continuing"
    ]
@@ -866,8 +830,11 @@
   {
    "cell_type": "code",
    "execution_count": 6,
-   "id": "a048acf9",
-   "metadata": {},
+   "id": "83750434",
+   "metadata": {
+    "collapsed": false,
+    "editable": true
+   },
    "outputs": [],
    "source": [
     "\n",
@@ -919,8 +886,10 @@
   },
   {
    "cell_type": "markdown",
-   "id": "94751a0e",
-   "metadata": {},
+   "id": "c12bc8a6",
+   "metadata": {
+    "editable": true
+   },
    "source": [
     "## Wrapping it up\n",
     "We now have a simple , un-optimized $k$-means\n",
@@ -930,8 +899,11 @@
   {
    "cell_type": "code",
    "execution_count": 7,
-   "id": "55656c6a",
-   "metadata": {},
+   "id": "4ab3fba6",
+   "metadata": {
+    "collapsed": false,
+    "editable": true
+   },
    "outputs": [],
    "source": [
     "fig = plt.figure()\n",
@@ -952,8 +924,11 @@
   {
    "cell_type": "code",
    "execution_count": 8,
-   "id": "a388793e",
-   "metadata": {},
+   "id": "f196e068",
+   "metadata": {
+    "collapsed": false,
+    "editable": true
+   },
    "outputs": [],
    "source": [
     "def naive_kmeans(data, n_clusters=4, max_iterations=100, tolerance=1e-8):\n",
@@ -1028,8 +1003,10 @@
   },
   {
    "cell_type": "markdown",
-   "id": "b4aadcb1",
-   "metadata": {},
+   "id": "9b2b9374",
+   "metadata": {
+    "editable": true
+   },
    "source": [
     "## Decision trees, overarching aims\n",
     "\n",
@@ -1057,8 +1034,10 @@
   },
   {
    "cell_type": "markdown",
-   "id": "44df1eab",
-   "metadata": {},
+   "id": "ea71f159",
+   "metadata": {
+    "editable": true
+   },
    "source": [
     "## Basics of a tree\n",
     "\n",
@@ -1075,8 +1054,10 @@
   },
   {
    "cell_type": "markdown",
-   "id": "0bf8db35",
-   "metadata": {},
+   "id": "e2aeaba3",
+   "metadata": {
+    "editable": true
+   },
    "source": [
     "## A Sketch of a Tree, Regression problem\n",
     "\n",
@@ -1085,8 +1066,10 @@
   },
   {
    "cell_type": "markdown",
-   "id": "e28cfb41",
-   "metadata": {},
+   "id": "ae9ecf7e",
+   "metadata": {
+    "editable": true
+   },
    "source": [
     "## A Sketch of a Tree, Classification  problem\n",
     "\n",
@@ -1095,8 +1078,10 @@
   },
   {
    "cell_type": "markdown",
-   "id": "e1767eec",
-   "metadata": {},
+   "id": "73c2c2a3",
+   "metadata": {
+    "editable": true
+   },
    "source": [
     "## A typical Decision Tree with its pertinent Jargon, Classification Problem\n",
     "\n",
@@ -1111,8 +1096,10 @@
   },
   {
    "cell_type": "markdown",
-   "id": "e8c64cbd",
-   "metadata": {},
+   "id": "617b4dcd",
+   "metadata": {
+    "editable": true
+   },
    "source": [
     "## General Features\n",
     "\n",
@@ -1132,8 +1119,10 @@
   },
   {
    "cell_type": "markdown",
-   "id": "25477c67",
-   "metadata": {},
+   "id": "cd186d54",
+   "metadata": {
+    "editable": true
+   },
    "source": [
     "## How do we set it up?\n",
     "\n",
@@ -1153,49 +1142,23 @@
   },
   {
    "cell_type": "markdown",
-   "id": "32a61fb0",
-   "metadata": {},
+   "id": "a7103bf3",
+   "metadata": {
+    "editable": true
+   },
    "source": [
     "## Decision trees and Regression"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 3,
-   "id": "035ee362",
-   "metadata": {},
-   "outputs": [
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "2nd degree coefficients:\n",
-      "zero power:  -1.0213890400311119\n",
-      "first power:  0.18014254613327288\n",
-      "second power:  -0.0005133239735522407\n"
-     ]
-    },
-    {
-     "data": {
-      "image/png": "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\n",
-      "text/plain": [
-       "<Figure size 432x288 with 1 Axes>"
-      ]
-     },
-     "metadata": {},
-     "output_type": "display_data"
-    },
-    {
-     "data": {
-      "image/png": "iVBORw0KGgoAAAANSUhEUgAAAYAAAAEXCAYAAACkpJNEAAAAOXRFWHRTb2Z0d2FyZQBNYXRwbG90bGliIHZlcnNpb24zLjMuNCwgaHR0cHM6Ly9tYXRwbG90bGliLm9yZy8QVMy6AAAACXBIWXMAAAsTAAALEwEAmpwYAABfvUlEQVR4nO2dd3xURdeAn7u76ZVA6L1L7x1pAqEJiopUERE+FVFQEZAXXhUQEORVUUTFgtgQsYAQ6Sqg9I50QhIIKYT0ZLO7d74/NrvJJpuQhGRTdp7fT7N37pQzd5c5d2bOnKMIIQQSiUQicTo0JS2ARCKRSEoGqQAkEonESZEKQCKRSJwUqQAkEonESZEKQCKRSJwUqQAkEonESdGVtACSskl4eDj9+/encePGAKiqipeXFxMmTGDw4MGFrvfpp5/m1VdfpWHDhnbvnz59mk8++YT33nuv0G1YWLhwIYcPHwbgypUr1KhRA3d3dwC+//576+eiYtOmTSxatIiaNWsCIIQgKSmJDh068Oabb+Lm5lak7RUFr732GkOGDKFbt24lLYqkGFDkOQBJYQgPD2fYsGEcP37cmnbjxg0mTpzIyy+/zMCBA0tQuoLTt29f3n33XVq2bFlsbWzatInff/+dNWvWWNP0ej2jR4/mscce4/HHHy+2tiUSe8gZgKTIqFGjBtOnT2ft2rUMHDiQ9PR0li9fzuHDhzGZTDRr1ox58+bh7e3NtWvXmD9/PrGxsWg0Gp555hkGDx5sHYjr16/PnDlzuH79OhqNhubNm/PGG29w+PBh3nzzTbZs2UJiYiKvv/4658+fR1EUevbsycyZM9HpdLRs2ZIpU6awf/9+oqKimDx5MmPGjMl3X95//31OnDhBVFQUTZo0Yfny5axevZrt27ejqio1atRgwYIFVKlShcTERBYtWsTFixcxGAx07dqVWbNmodPd/Z9XXFwcSUlJ+Pn5ARAZGckbb7xBREQEBoOBIUOG8H//93+AWYF8/PHHuLu706VLF9atW8e5c+cKJOv27dtZvXo1iqKg1WqZNWsWHTt2zDV9/PjxjB07lqCgIHbu3MmqVauss705c+bQqlUr3n//fW7cuEF0dDQ3btygSpUqvP3221SuXLlwPySJ4xASSSEICwsTbdq0yZF+8eJF0bp1ayGEEO+//75YsmSJUFVVCCHEihUrxIIFC4QQQowYMUKsX79eCCHEzZs3Rb9+/URiYqLo06ePOHXqlPjpp5/EpEmThBBCGI1G8dprr4mQkBDxzz//iCFDhgghhJg1a5Z48803haqqQq/Xi0mTJok1a9YIIYRo3Lix+Oqrr4QQQpw+fVq0aNFCpKWl5dofS7sW3nvvPTFw4EBhMBiEEEL89NNP4sUXX7Ref/fdd2Ly5MlCCCFmz54t1q1bZ5X15ZdfFh9//HGONn788UfRrl078eCDD4qBAweKzp07i1GjRolvv/3Wmmf8+PFi165dQggh0tLSxPjx48Vvv/0mLl26JLp27SoiIiKsz7Zx48YFlrVfv37i+PHjQggh/vrrL/H+++/nmT5u3Dixbds2cfnyZdGtWzcRGhoqhBDiwIEDonv37iIxMVG899571u9PCCGmTp0q3n333VyftaT0IGcAkiJFURTr2vnevXtJTEzkwIEDABgMBipWrEhcXBznz5/n0UcfBaBatWrs3LnTpp727duzcuVKxo8fT7du3XjiiSeoU6cOt27dsub5888/+fbbb1EUBVdXVx5//HG+/PJLpkyZAkC/fv0AaN68Oenp6aSkpBRonb1NmzbWt/g9e/Zw+vRpRo4cCZj3PFJTU639PH36NBs3bgQgLS0t1zo7dOjAmjVrUFWVDz/8kC1bthAUFARASkoKhw8fJj4+nnfffdeadv78eaKioujevTtVq1YFYNy4cbz//vsFlnXIkCFMmzaNXr160b17d55++uk80y38888/dOnShVq1agHQtWtXAgICOHPmDACdOnXC29sbgGbNmhEfH5/v5ywpOaQCkBQpp0+fttkYnjt3Lr169QIgOTkZvV5vHagURbGWu3r1KtWrV7de16pVix07dnDw4EH++ecfnnzySd544w28vLyseVRVtalDVVWMRqP12jLYW/KIAm53eXp62tSddRkpPT3dOsipqsq7775LgwYNAEhISLCRyx4ajYZp06Zx/PhxZs+ezUcffYSqqggh+O677/Dw8AAgNjYWNzc3Nm3aZCO/VqstlKwzZsxg5MiR7N+/n02bNvHZZ5+xcePGXNOz1pm9T0II6/POumGuKEqBn7WkZJBmoJIi49q1a3z44YdMmjQJgB49evD111+Tnp6Oqqr85z//4Z133sHb25vmzZvz888/AxAREcHo0aNJTEy01vXNN98wZ84cevTowSuvvEKPHj04d+6cTXs9evRg/fr1CCFIT09nw4YNxWat0qNHDzZu3EhSUhIA7777LrNmzbLe++KLL6xyPPPMM6xfvz5f9S5YsID9+/ezc+dOvL29adOmDZ9//jlgViSjR49m165d9OjRg7///pvIyEgAfvjhhwLLajQa6du3L6mpqYwePZoFCxZw4cIF0tPTc0230LVrV/bt20dYWBgAf//9NxEREbRu3bqAT1JSmpAzAEmhSUtLY/jw4YD5jdbNzY2ZM2fSu3dvAJ599lmWLl3KQw89hMlk4r777mP27NkArFixgtdff52vvvoKRVFYtGgRgYGB1rpHjBjBoUOHGDx4MB4eHlSrVo3x48dz/vx5a5558+axcOFChg0bhsFgoGfPntYN06Lm0UcfJTIyksceewxFUahWrRpLliwBzKaSixYtssrRrVs3Jk+enK96a9euzdNPP81bb71Fz549Wb58OW+++SbDhg0jPT2doUOH8uCDDwIwZ84cnnrqKVxdXbnvvvuss4T8yqrT6Zg7dy4vv/wyOp0ORVFYvHgxrq6uuaZbaNiwIQsWLGDatGmYTCbc3d356KOP8PHxuccnKylJpBmoRFIGCAsL45dffuHZZ59Fo9Gwfft2PvnkkzxnAhLJ3ZAzAImkDFC1alWioqIYNmwYWq0WHx8fFi9eXNJiSco4cgYgkUgkTorcBJZIJBInRSoAiUQicVKkApBIJBInRSoAiUQicVLKnBXQnTvJqGrB960rVvTm9u2kYpCo9CL77BzIPjsHhe2zRqNQoYKX3XtlTgGoqiiUArCUdTZkn50D2WfnoKj7LJeAJBKJxEmRCkAikUiclDK3BGSP1NRkkpLiMJmMueaJitKgqqoDpSp5Sk+fFVxd3alQIfCuXjIlEonjKPMKIDU1mcTEO/j7B+Li4prrAKPTaTAaS8Ng6DhKS5+FUImLiyEpKR4fH/+SFkcikWRQ5peAkpLi8PcPxNXVTb5dllIURYOPTwVSU53LakMiKe2UeQVgMhlxcXG9e0ZJiaLV6lBVU0mLIZFIslDmFQAg3/zLAPI7kmQlOHgrvXt3Izh4a0mL4tSUCwUggUWL/svWrZsLVXbt2jWcPHkcgGnTpnDs2JEClf/ss48ZN+4xxo17jA8/fLdQMkiciyVLFnLu3BmWLl1Y0qI4NVIBSDh+/CgmU+GWZw4fPsjhw//w+edf88UX33Dhwnn++GNPEUsoKW/Mnj2P5s1b8Oqr80paFKemzFsBlTaOHTvCunWf4eLiQkTETbp3vx8PDw/++usPhBAsX/4ue/bsJDh4K2lpqbi4uPDf/y7Czc2dp54az6pVH1OjRk0mTx7P1KnT6Nath912hBCsWrWS/fv3UalSJVRVpW3b9gBs27aFH374FiEEjRs3ZebMV3Fzc2Po0P706tWHM2dO4enpyfz5Czlx4hgXLvzL0qULWbx4OQC//fYLq1atJDExiRdeeIkePe5n8eLXuXjxgo0MY8aMp2HDxjz33AxcXFwAqFOnLpGRt4rxCUvKA0FBgwkKGlzSYjg95U4B+I55BLed24ulbv0DA0j4ZuNd8507d5avvvoePz9/hg3rz3PPvcjatV+xePHr7Ny5nf37/2LVqjW4ubnz6acf8eOPG5gxYxbPPPM8y5e/RcuWrWnRolWugz/A3r27uHjxAuvXbyAxMZGJEx8H4OrVK2ze/DOrV3+Gl5cHq1a9x7fffsXEiZOJi7tDixateOWVuWzc+B3/+9/bLF26kt9++5VJk6bQoEFDALy8vPnss6/Zv/8vPv/8E3r0uJ+5cxfctd9hYaHs3r2T1avX5vOJSiSSkqTcKYDSQP36DahSpSoAfn7+dOjQCYAqVaqSmJjAf/+7kJ07txMWFsrBgwdo1KgJAEOGPMju3TvZufN31q37Ps82jh8/Sq9efdDpdFSoUIEuXbpnpB8hPDyMqVOfRFHAYDDQuHFTAFxd3QgKGgLAoEFDWbPmA7t19+zZG4B69eoTHx8HkOsMYMCAQYBZ8cya9SLPPfcCtWrVLsjjkkgkJUS5UwC5vaE78lCUTmf7WLVarfVzVFQkU6c+yciRj9GlSzcCAipy6ZJ5YNXr9URF3cJkMhEdHUnt2nVzbUNRFLIG87S0YTKp9O37AC+++Ao6nYaEhCTr+r5Go1itcVRV2MhlT15zG+ZG8poBnDp1gnnzXmX69Jk88MDAXPNJJJLShdwEdjDnz5+jZs1ajBo1lvvua8aff+6x2sd/+ulHtG/fkeefn8GiRa/nuTHboUMndu/eQXp6OgkJCRw8+DcAbdu2588/93LnTixCCFaseIsNG74BIC0tjX37/gRg69Zf6dy5G2C20S/sJnBk5C3mzn2ZBQsWysFfcleibyWydeMZNn93Ksd/O3/9l7RUQ0mL6FSUuxlAaadjxy5cvnyRceMeRQhBmzbtuHr1CmfOnGbPnp2sW/cdnp5ebNu2he++W8/YsU/Yradnz978++85JkwYRUBARerWrQ9Ao0aNefLJp5k+/f8QQtCwYWPGjZtoLbdnz04++eRDKlYMZN68/wLQuXNXli9/i3nzXi9wf779dj16fTrvv7/SmjZixMOMGPFIgeuSlH/OHo/g+uXbud6v07AijZpVdqBEzo0ihChTTrVv306y8Yl969Z1qlatc9dypcUvjiPJ3ucePTqwb1/BbPyLkvx+V/dCYKAP0dGJxdpGaaMs9Xn3lvNcOBPJhWt/Ub2OH0ePHqF9+w7ER7lQs+p9VKqt59ExA+5aT1nqc1FR2D5rNAoVK3rbvSdnAKWYkyePs3Ll23bvLV/+LpUqBTpYIonk3rC8b549f5gftx5Ar9dz4NBWBvX6P2pWvY9tWzfnSwFIigapAEoxrVu35Ysvvimy+kry7V8iAbBM3qvXqEGfgc+zY0cw/fsHEXXdfI4kaNCwEpTO+ZAKQCKROAyRoQHmzfsvjZpVZu7c+QDs3XaRf09G0LxZi5IUz+mQVkASicRhWJaAsvsGVDS29yWOQSoAiUTiMCzje3bvsJqMa+FcdholjlQAEonEYViWgDQaWwVgPaAoZwAOpVgVwKpVqxgyZAhDhgxh2bJlABw4cIBhw4YxYMAAVq5ceZcaJBJJecK6xJN9CUixZnCoPM5OsSmAAwcOsG/fPn766Sd+/vlnzp49y5YtW5g7dy4ffvghW7du5cyZM/zxxx/FJYJTUZLxAJ5/firjxj3GxIljmDhxDGfPnimUHJLyj2V812RbAlI0lhmAoyVyborNCigwMJDZs2fj6moO19igQQNCQkKoU6cOtWrVAmDYsGEEBwfTq1ev4hJDkg+OHz9qdSVdUIQQhIWFsnHj5hw+kCSSrMTfSSX0aiyQOeBbsCwBnTt+k2atq+HmLn9LjqDYnnKjRo2sn0NCQti2bRvjxo0jMDDz8FLlypWJjIwsLhFKBGeLB9CkyX0AzJw5jfj4eB58cAQjR44qxicsKavs/u289fOxY4eoXT/Ieu3ianZAmBCXxqZv9zD6yf4Ol88ZKXY1e+nSJaZOncqsWbPQarWEhIRY7wkhChwrNvuR5qgoDTpd5krWqF9HsiPk93uSOTf61x3I9w/+mGcerVbDuXNn+fbbH/Dz82PQoAeYPn0GX375NW++uYA9e3bw119/snr1J7i7u/Pxx6vZtOkHXn75VaZNm86KFUto1ao1rVq15v7778+1nd27d3Lp0kW+++4HEhOTGDduFBqNQmjoNbZs+ZlPPvkCNzc3Pvzwfb7//msmTTLHA2jVqjVz5sxjw4bvePfd5Sxf/j+2bt3M5MlTadKkMYqi4OPjw7p137Jv35+sXfsxvXv3Zv58+36CTp8+SceOnXjppVkYjUaefXYKdevWo3PnLjnyajQaAgN9CvbQC4Ej2ihtlIU+G9PNJj7Hz+5i0669PP3Mo9Z7Pfs14sCe87jo3Dl69BjTZz181/rKQp+LmqLuc7EqgKNHjzJ9+nTmzp3LkCFDOHToENHR0db70dHRVK5cMMdP2X0Bqapq4+9GFOMiolDFXf0JmUwq9es3oGJFc7/8/Pxp27YjRqNK5cpViYuLZ8GChfz+e7BNPACjUSUoaBg7duxg+/Zg1q37Ps+2jhw5zP339wa0+Pj40aVLN1RVcPjwIcLCwnjqqSds4gEYjSqurm4MGDAYo1Fl4MDBrF79PkajihACk0m1fu7evRdGo0rt2vWIi4vDaFTzjAfw2mstrWlDhjzI/v1/0b59pxwyq6pa7P5bpI+Y0ovBYPY4eyv2BC+9NDuHzFXrKtwOhzat29+1P2Wlz0VJmfIFFBERwXPPPcfKlSvp2rUrAK1bt+batWtcv36dmjVrsmXLFkaOHFmk7X4zVMYDcGQ8gJMnT2AwpFuD3ggh5F6AxC6WF7ev1n+PXwWPHPebN2/Bn+GXZEAhB1JsVkBr165Fr9ezZMkShg8fzvDhw9m0aRNLlizh+eefZ/DgwdSvX5+goKC7V1aOKG/xAJKSEvnww3fR6/WkpCSzbdtv3H9/n0LVJSnfZJ4Ctr/sa0mXp4EdR7G9qs2bN4958+bZvffrr78WV7OlnvIWD6B7956cO3eGSZPGYjKpPPzwo7Ro0arA9UjKP5aBXZPLa6dFL8jTwI5DxgMox8h4AM5BWenzl+//TUpyOhOmdcHL2y3H/fOnbrFn6wWatKhC36FN86yrrPS5KClTewCSe0fGA5CUJywvbrkvAZn/lq1X0rKNVAClGBkPQFJesFiaQU4/QBasewBIDeAopDM4icQBBAdvpXfvbgQHby1pURyOEILPV+3BkG42NMj17E9G8s4d2/N8TsHBW2nTpg2LF79Bu3YtaN++BYsXv0Hv3t2sf53xORcGOQOQSBzAkiULOXfuDEuXLiQoaHBJi+NQDOkm9Mlm0+LI21dwdbN/wNGiGBITE/N8TpZnef78efR6PQCrV7+PXq/nypVL6PV6p3zOhUEqAInEAcyePY+lSxfy6qv2LePKM2HxoQCkG1Oo2D2ew7cO2c0XG2+eIXgHevPw8Ec5FHHQbr6RLz5K+rdptGvXkb17dwPQu3dfDh8+SMeOnTl8+CAPj7Mt7+3qzX0BzQrseaC8I62AyjGlrc/SCqh4KM19vhp3mX7rezMr6WtSlASW+ozNNe99hm48njqHc7oDfO/5lt08lUw1aWbshpLdn3Q2BIILukNEakOsaav6reGxJqML1Y/SgLQCkuTKokX/pW3b9gweXPCg2mvXrqFDh060bt2WadOmMGnSFNq165Cvsps3/8yPP26wXkdE3GDgwMHMnPlqgeWQlD9CE0OxbDVqNRo6VMnpIsRC1aQGkArVtHUY6jWeeLdbpLrE2+TpEj6WQH39fLXdjr7sq/4ZN5LCiUi+SWjC9UL3o7wiFYDkntxBDxs2gmHDRgBw9eoV5s59mUmTphahdJKyjBACTYYCqOARwNaRO3PNe/3Kbbb+cIYK+hp0jHgMD08Xnni+q82yzQ+fHyUmNYm2nWqh0dmfBaSmGjh3PIJ6Xg2ZO3InSw4t5J0jy4q2Y+UEqQCKGGdzBz1gwCDr9YoVS5gy5Tn8/f2L5+FKyhwCFQ2ZvqXyonptf5q1rUZKUjohl26TmmJACNsA8pbl304966FxsV/fndspnDsekRl/GGlemhvlTgH89sNpQq/EFkvdtRsEMOTRlnfNd+7cWb766nv8/PwZNqw/zz33ImvXfsXixa+zc+d29u//i1Wr1uDm5s6nn37Ejz9uYMaMWTzzzPMsX/4WLVu2pkWLVrkO/gB79+7i4sULrF+/gcTERCZOfBwwv4Vv3vwzq1d/hpeXB6tWvce3337FxIlmd9AtWrTilVfmsnHjd/zvf2+zdOlKfvvtVyZNmkKDBg0B8PLy5rPPvmb//r/4/PNP6NHj/lydwVk4fPgger2evn0fKMATLd/8/tNZawAUC4qi0LFnXVp3rFlCUjkWIQRKxgwgN/t/Cy4uWnoNbAzAmmV/oqoiw31EZjnLWQKtVpPrgG5pJ/v2Zhnb7nQI5U4BlAbq129AlSpVAbM7aIunzCpVqpKYmMB//7uQnTu327iDBrMr5d27d7Jz5++sW/d9nm0cP36UXr36oNPpqFChAl26dM9IP0J4eBhTpz5p4w4awNXVjaCgIQAMGjSUNWs+sFt3z569AahXrz7x8XEAd50B/PLLJkaNGlOQx1SuUVXB1Qsxdu+FXIxxGgWgChWNMCuAAhng5HIqWDVl+BPSKphyGdCznyiWM4DcKXcKILc3dOkOunjcQYNZyZw4cYzXXvtvrnmcDctzU1UT8Rxg164dDOz3CD6aVtyOLZ4ZamlEVQV99GbLn9TUlHyVCQ7eSnq6Kzqti81b+8Zvfycx3h2A3bt3seD115g9e57V3j84eCtLliwkaMBw/DRdSE0xtydPGOeOPAnsYMqbO2iAK1fMPtw9PHL6eHdWLOOWqqqsXv0up08f56efzdZS4eFhJSiZY0mNUWhlNMf8vnkrNF9llixZaP03YRmzhRDcumZ+sTKpRpYsXWQ9WJe13LlzZ/jqqy8AiE9IADJnANLJUE6kAnAwHTt2QVVVxo17lEmTxlGnTl1u3rxpdQc9Zcqz9OnzAH5+fnz33fpc6+nZszdt27ZnwoRRzJ4906476NGjH8FkUnO4g37iicc5ePAfXnjhJSDTHfTp0ycL1acbN24UOLJbeccamU4RPPPM8zRv3oIRI8zBj2rWqFWCkjkWkzHzc9vu+fuNzJ49L0dsACFAqzErgJpNDMxf8BrNm7ewOVg3e/Y8mjdvwbjxZhfqvr6+gJwB5IU8CFaOke6gS450vZG1K/ejc9Hw9Es9Abh1I4GfvjpO5Wo+jHyiXZG1VVr6bI+N+7YRvc+TOz6hzH1ufL7LrV25j3S9iUkvdsfNXYfJpPLx23+h0ShMnXV/nn1OTtSz7oN/8PR25YlpXXnnyDKWHFrIjPYvM6fz/KLqmsORB8GcDOkOuuxiea3KavliCYRStl657g3r+6VS0E5bnlvGDMDqSjofJXOJLOZMzz2/SAVQipHuoMsu9sIfOmPIQ8vALQqoALJb8lj1yF1MSc2ZspWRVkC5IvcAJJJiIK/4t06lAAo5A8i5B5B3MBl7ZclWxpmee36RCkAiKQYscW2zjleZA1EJCFRCZPa1gJ3OMQMoyBKQbVk5A8gdqQAkkmJAtQxYWZYslFxOqJZnVLWwMwDz36xWQOb0/M8Ass8apALIiVQAEkkxkJKUDmTfAzD/La/jf1JCGrejkqwuHG5HJWFMzhhiCr0EZL62xhPOxx6A5TmrqiD6ViIkeBKgVnMqxZtf5CawRFLEJCfq+fHLYwDo01Kt6ZZBLTT0OsHB0YD58NKAAUFs3LgBRYGRIx9j48YN1lOznp6eLFq0jKCgwdaTrllPv5YWIm8msGndcQC8AwzUb1CXU4dvAGbzw5R8ngK2YBnEBwX1IyUtjkdGjsVf0w1Duj4fZc2FjQaVjV8cw4X7eIGPuXxmF3QrkBjlHjkDKGYWLfovW7duzvX+4sWvc+tWhAMlkhQ3CfFp1s+HTm2xfrYMaorQ8tVnP7Lusx8x6b3YGfwPXm7V8HStZv1cyb8Blfwb4OlajXdX/g+wDStZ2oiPzVR01y6HE5dxHZtyizDteQ5E/Vqg+iyD+K1bEYSFhbJu3RcAJCbd3Q7exVXLxZD9RERd4Vb0NRLT7wAQc710npUoSeQMoIQ5duwITz75dEmLISlCLKaP0bHXGDm6nzVdqzW/b/l4B9Cj3QRzYj7Og7m4m3eUS3NYSTXL8krNWrWtz+DPiK85XnUv3av0LFB9loWeyaOXoqomfHz8APDx8clX+YEj2rB06UL69w/i9O1jdAscSc0azuGAryBIBVDE5Oanf82aDzh69DAJCQlUqlSJN954i99+20xMTDSvvPICH3zwCUePHuG779aj1+sxGNKZM2c+LVu2LukuSeyQZkxjd+hOUozJOe6lR7kCAVRvXJ2k+nfYeNHs2VUI8GzijTEhn//sVIX0SDeMJsx11Ifn1rxAEonWOmv51GFoYP+i6lahEVlO5/v5+lvX7MeNn8DxM3upUcDBt0KgF4kJeny9bQ87Vq9ZMV/lg4IGW5fJPvjxO7gE/n4BBZLBGZAKoIix56ffZDIRGhrCRx99hkaj4c035/P779sYP34iv/zyI2+//S4+Pr788suPLFv2P/z9/dmy5Re++uoLli1bWdJdktjhi7OfMn//XLv36hvb8ARvcv7OOdbtLLzrARfhxjw2ojcYeHZn7rPESzUv4UeVQrdzr9xOvc2e0N0omAf5W0kRCJ2KFl8O3zIHZtcoBVttHjSyBfGxOfcN/AI8Cyxfed98vxecWgEUx6aaPT/9Wq2WadNmsHnzz4SGXufs2dM53og0Gg2LF7/N/v1/ERp6nePHj6LRyC2a0kp0inkTt3nFljQJaGpzzye+OlyGQK/KPNzo0cI3IhQ4Bi642K1nb9guYtNiiUqOws+95BTAx6c+YN+VswzlWQAikyPRK6nUpQV/39oPOvB2se+LJjc0GoUKlbyKRL7MvZciqa5c4dQKIOumWlEpAHt++uPj45kxYxqPPz6GPn36maMZZXsdSUlJ4emnn2DAgEG0bt2WBg0a2gRbl5QuLDblDzUayfR2M23uhVy+zbbLZ2gZ2JJX+xc+SI4Qgo+O/YmChqUdVmU5BKXg4+fGkE39iU07VOLmjfH6eGvYR4DKHlUQWhMkwKNNHkNbcThjmubfEVyRYxn5RUEi0jgHTq0AimNTrUOHTnzzzVcMH/4waWlpHDz4N7Vr16Ft2/aMGPEI8fFxHDiwj169+gJmBWEymQgLC0VRFCZMmIQQgjffnI+qOpf30rJE5qBrx9WDansAqbAoioJWq2AyCb5Zc8jmXtNWVUvNASdVqCgic7ZayaMyLi5aohISmdBiElVr+JagdGTxKycVQHacWgFk3SgqKnr27M2//55jwoRRBARUpG7d+uj1ei5fvsiECaMAaNLkPiIibgLQrVtPXn75BVaseI+GDRszZswjaDQKnTp15dSpE0Uqm6TosAy6efn6yZfjsrvQon0Nm9CSqkklOSmd21FJKL6lY0BThUCTxaI8M5ZvpgfUkkRRMhxRSAWQAxkPoBxT2vpcnuIBLNj/Gp+dWMs00wpSQ9NBgYoBlbh9OwZXF08q+FXFy9/IhP/rZ7e8Zf9pwIAgtm8PznMfKjh4K3PnzkJR4LGRk/DVtMfVw8TPtZdyMOJv/pz4J0092xRjb+3z7ec7uHzhFi6VdfilV7emm0wGNBoNiqKleuNUhj8cdE/t2NurK8j3/NHmbxFnzfJVqZ/Gw48NvCd5SoriiAdQCvSzRFL2EAjqGlvgm1KTKpXqU6VifXSKL1Uq1aeCX1UAjhzbl2t5y/7T6tXv3/Vw15IlCwkPDyUsLJQNP3wLQFRUlI0sjkYIwZ1bOir517YZ/AG0WhcURYvRaGD1mhX33Na9HoBTvAzWz8f/CblnecoTUgFIJIVEm7GCGhF1kV93rSBBPc6vu5azYetCftqxlEEPdcy1rCV8oSVcZF77ULNnz6NWrdrUqlWHRx99HIDAwCqZXi5LYBKvqgIlm2nnubg/iVMPsOuf1SSox9m6721enDHjntuyPKvC7tVpK6Ww1e1jABo0aHjP8pQn5BJQOaa09blULQGlp+O+/ks0MdGFame26y72KG48lvoqjYlhmOZCoeopKLeFB1+IdgSQwndeL7NfG8Ye8QQdk6s5pH0LRqHwrrB1rOOr/YOnhWO2Fb283EhOvrtfIIDVLkdYrY3miZSF1CaORzVn891O+oAgjG2KLnznvSBDQtpFQQg1x9uIpHRR2t4zXHfvxGf2S4UurxsImg69zHWdP4vX1uVFJVqepFaoCU+uRomNRRcbBnVBfPklXiEOad5Kuos7PG+rAFxPn8IreLvDZMjvKQH3TqAOaAmAEhaG1w9L8t2G2+afufPXobtnLKOUeQXg6upOXFwMPj4V0Gp192x6Jyl6hBAkJyeg07mWtChWlAynYsb7mqEf8mCBy6e77kSTYfpoanofyc1mF6l8uZEm3EGAKaAiqmdtIBTxxASSk6vftWxRohfaHDFeTC1bktzCMW/LBZkBpLscRWC2ujPWqk3yy3f/rpTEBDzXfIiSlHRPcpZ2yrwCqFAhkKSkeGJjI1FVU675NBqN09nVl6Y+63SuVKhQioLYZ8xIjM1akDLLvkuHvDD8FYdy9BIAaouWpAy9hxO/BSDtTiqsOYTJrwKiel24EYqYMIEUn04Oad8qR6oB3j1gk2Zq246UB4Y5pH2vQB9S8rkcYjjzCeruTwEw1qhFyvi7K3xNeBieaz4s9/4jilUBJCUl8fjjj/PRRx9Rs2ZN5syZw9GjR/Hw8ABg2rRp9O9/b46sFEXBx8cfHx//PPM5yjywNOGMfXYUAoE24/RrUdj755es0a5KMtRh1n04C5pSOvtWUFAxvxwKO3LniVQAhePkyZPMmzePkJAQa9qZM2dYv349lStXLq5mJZL8kRljsHDFESgZRnQaByoAy8EqIUShZS8K7O3paLSlVwEIxTwTtqe47BcqnX0paopNAWzYsIEFCxYwa9YsAFJTU7l58yZz584lMjKS/v37M23aNOnwTFImESaF5oYewL27fCgQGW0Z0k1Ui2tGHWO0QzbYwxPD+CtkH4ZId1BBpGsA/2yild5BU8WsAGIik0iIS8XX3wMhBOEhd6zhOy24uuuo65FxIWcAhWPRokU21zExMXTp0oUFCxbg4+PD1KlT2bhxI4899lhxiSCR5M49zgB8btUlwNQCgLDw60CjIhIsb3Q68wtTut5E85uDaM4gDuw5SpvhXezmLyqPt5OCx1E9tCOdDbmv8YddDyl0/cWJoigYyNww3vD5P0ye0YfImwls+f603TI1Am7zlKMELEEctglcq1YtPvjgA+v1+PHj+fnnnwusAHKzZ80PgYH5iyZUnpB9zgVf8yueu7sL7oV4Rq6qh/XzD7+8z4uzHypwHYXlxIUtYPKkUdN2eGn82bZlJwsm27dsWbHiLc6dO8OKFW8xfvyoQrcZm36bxqICACFpZ4gzmE8iG11S8dT4EhsXRdQfJ1ny0quFbqOg5Pe37evjwW3NDQ4bttDRZSjJKWkcT/ib2GjzrCAuJZqQ26fRKBqq+tansm9t/jrwD08BWqV0/RsqalkcpgAuXLhASEgIAwea/XAIIdDpCt589oNg+cUZN0Rln3PHLT4FXyAtzUBiIZ6R0WD+Df4d8wP/9+xUhz7nh0b1YenShVRpUQsv1Z+ggUG5tv/SS3NYunQhL700555kNBpN1j2Py8f+5tylA3h6erFo0VIAq1ddRz2Hgvy205JNoMCOgHV0TByK0MLA9QNpZujGKOZww/ciP1U1B156IO0JKqfXpmqHurAVTCaV2FLyb6hMHwQTQrB48WK6dOmCp6cn33//PQ895Li3JonELoVdt854B+l5f+8i9yh7NyxebBe/vx6S4b6mze6a914RZHr8XL78f9RrXClHO6WVB+oM5KGGI4lLSYDzoFNc6FWzD5XjG8MNqORZiV41+wDgHeoN6eARUDTBaEo7DlMATZs2ZcqUKYwePRqj0ciAAQMYOnSoo5qXSIqWDNfCJbnvKTI2NtU8NiqPHrjO7Shz3GL/AA869qxbqM1aVajWoC+ONHstCgI9A1kz4HNMRpWPz/+Fi8aVHx78hYtnI9l14zzda/bkvw9OAWD5N59DUpYtIrkJfG/s3r3b+nns2LGMHTu2uJuUSPJPIUdwxeJbviSN2DIiXeVm254Yn8ahP0Ns0ho1q1yoUIsCYQ36UoqNffLEorgsz8vyN6s+s56zKB3nJ4sdaYMpkRSGezMiKhoRMhRAboe9Denmw09ePq74+LoBYDIV7o1WZAn64shzD0VJ1uDwQojMt/ws/bG4FLPOqsr5DEAqAIlzco9moJY4gyX6NmyZAeQySJlMZs3g7uGCm4dLnnnvhiDLElAZnQIoimKjBFQ7oTutH63Rw6QCkEgk2VFLXgFYXEDktlxhedvXajU2LiQK1ZYomZPPRU3W55AZttJmDch63xko887gJJLCYNncE7nE9P1y9W4SYk3otDqMRiMCgRAq1Rtoadq4GX636wIQfiPMkWLbkjEDCNmp8EtosE3oxYS4VH766jgA8QlxGS+yWg4cOMCIkfkL0ZicqOebTw6QmpLOdN0X1vRDh/5hRO17C/NYUigaBVTBB2/tRKNo0GpdCAsLBRoDma42XG/V4+R9fWgZdarkhHUAcgYgkWTDkG4iNUGHi84NRdHi4uKGq4s7bq6enD52jWsXM4O07zq0ucTkTPC6af289dfdNvdu3Uiwfj52ai83boQDsP6rL/Jdf1REIsZ0DS46d5v01R87JvZBcVCjjj8ALjo3tFoXTCYjO/b8aL0v/FKsny826Oxo8RyOVAAS5ySPPQDL2nC6IZU76l98sWkmW/a8D0CD+g2tG4RfeL5Gtwc6OEZeO0RWOstBly0A9Olj61XX0r3wyDMMHdmFGjVrAjBu3MR812/vwOUvBxYzY+bMwglcChj8SAvqtEzmi00zWf31/7Hu55cZPSHTvYUmIJUfPJYBoGo05X4TWC4BSSTZsKz/+vr68MIL85g7dx5h12LZ8v1pKlasZLWuMZJOyxatSk5QRSFdSQOgceMmNrcsfejbrx/9gpryc8wJIpLj6dTJvs8ge9hbB//y86+pUrGSndxlA0VRGDxkMIOH2D+4pigaDJidwwkniDJY/nsokdgjjxmAZVPV1jrE/FlVM4uqqCVqEaOgWA+D5TgLkK17Wa1f8otdn/+l1OVzUaFVtNZnGuOpIVFXvg8ESAUgkWTDMvBltQ7RZDlEZLmvKrlHoHMEWQOdZB+sLW/vSjYNUBDrFnsHzDQabWFELTO4alys3+uhmlqGDC8dfoCKC6kAJM5JHgOhdfC0OSCUxXzQcpIU1RqVqyRQFAU1I9BJ9oE9uwKwCSSTT+xl1Zbz+B1B9YbQvop5X0dBw3VfOQOQSMovuZiBmm/ZWQISwroJXJqWgLL7A8q+wpVp/57/+u35GCrvAZxq+tTi1c6vAaBBYznuUW4p39+mRJIbeYyEd1sCsswAVEwlPwPIJdZtziUg2/T8YG8JSKst30tAkPldK2gwlXMFkC8roLlz57J48WKbtOnTp/Pee+8Vi1ASSXGTJgx81A0iKh5FbH2H1Gs6/g07hncLA3XvdKcKzbmVGMHrB/4DgC7JhwA6c/3GDXRaV1zxMC8BlfAMwBLqcMe2/axd+zEuOhf6DeyJalQAN8LCzNHKLHJ+uWYzHXpVzmEFkzVyWKf2vQjefICzp65Qs+p9Nvm0ZdQNREGwLPfVNbWgsqZpCUtTvOSpABYsWEBkZCRHjx4lNjbWmm40GgkLK8ETkBLJPbLTeI5ZAwDOMOP0DKqLylT3b82mmHfonNYcgGgRwdoT7wLgr1ZmBp3x1PoB5uWfNCUFP1e/EuqBWQGkKuYDX4EBdQgMqANAVIjK2Su7adHwAY4cPcTYyQ/g5q7LyFeP77/+PocCWLJkIefOnWHp0oW88mwt4qNccwz+aaQ4xQzA3T1zWOyrTi9BSYqfPBXAI488wqVLl7hw4YI1kheYp4Ft2rQpbtkkkmIjKcPWu5U+AD9tABjN6d3d+4HZtJ70Klf5T8s3rGXCjv1J2IUoKlUK5FLECcY0eJzetfo5WnQbTrv8iY/WF5GoBSHorhmJh+KNaKGBNNA3SeP+7zrjYfRjBOa1bUNXlfu/sz3lmjg2EbcYN+IqxXE4/CiVqccRNZgYwhEe6WjxIEx7nunKgJLopkOpUMkL30q3SYipiCsedy9QhslTAbRs2ZKWLVvSrVs3qlatSkJCAr6+vo6STSIpNkSGsX+zdH9cXdwwZKylD2n+IEf2X6d2gwCeeXSZbaG2jpYybxpVaIxRSedP7SbwN6e1TeqPh+qN3mRWcIlqAudj/wWgmssWOhuGkmjKTLPBD24YwtEbzQHUj3vvJFx3wXq7nl99NE5wOArggQFt2PRNmNUBXnklX3sAqampDB48mMTERDZu3MjEiRNZtWoVDRo0KG75JJJiwbK9qaDYbHaaMpzrlwWXx690nMPIxo/i7edKbKw56tehH2JJiTMxpO5wIi/pGdV0DHM7m6NdXTqQxI2zqTzfZibLWs7Ltd4jm+6QdNvI6gGf4hvoYk2v41u4aGJlEa3GPDQqlO8lr3wpgDfffJPXXnuNt99+mypVqjBu3Djmz5/P119/XdzySSTFgtVKBltzR9WYM0pUaUVRFBr4NzIHC1fMB5bOuB0lhSTuhJrXtCp5VuK+ivUBiPW8zA1uUNmjCvdVrJVrvac0RwAjDQMa5BpMvLyjzTjwpinnM4B89S4uLo7u3btbr8eOHUtSUlKxCSWRFDcWX/o5ZgAZQVTKWtxbCwGB5nCP6XrzkpZ/gKf1nkZj/zSwEILoW4mEh9whPOQO6XqjTX5nRKvLCH9ZzhVAvp3B6fV66/QvOjoaNbc4dBJJGcCyB6AIxSbmkyWISlkd/PoOaUK7LrUQAnQuWnz9M105Z/ozslUAoVdj2frDmRx1WQZBZ0RjXQIq388gXwpgzJgxPPXUU9y+fZsVK1bw22+/MXny5OKWTSIpNrLuAWTFOgMoo2vdiqLkGvQ9052FbXrCHbPZk5ePG/4BZquXgEAvfPxs4wA4ExaXF+V9CShfCuCRRx6hTp067N27F6PRyJtvvmmzJCSRlDUsS0BabAc5faoBKLtLQHmhyVBqyYlmKx8hBEkJepKTzNeNmgXStY807ADQac1DowYt58MvU8k3gEq+AXmWsTxPIcDFVYOHp6sjRL0n8qUAbt68SY0aNRg7dixgfsu4c+cOFSpUKFbhJJLiQiBwEW7UFvPIOgm4fsV84PHmzXCgbJ4CzXqqNygo88CXZVnr3IkIbkWFEOBfi8vnoqz3//5nH3NeH8+AAUFs3x6co7wzkTkD0LJn/Q2MhODRIJzJj07MtcyuLee5dNb8PIVQqVIvnZGPD8w1f2kgX/Ob0aNH069fP4YPH86IESPo27cvPXv2pGfPnhw7dqy4ZZRIihwB+KgBaBXzkkdKWjyJybe5Ex9JTGw4W3esL1kB74Gsp3qzUrtB5hvs0cNniIk0G3IkJN0mMiaEbzZ8wLlzZ1i9+n275Z0JjVZLyp2tJIpI0tGjw4Vte3bkWcbyPNMNehRFw56d+xwh6j2RrxlAt27d6Ny5MyNGjADg999/Z//+/Tz++OMsWLCAH374oThllEiKHIGKJsPGOyEpitY9vAAdr702C1BYtGhpicp3L8yePY+lSxfy6qu2tv6BVX2oVFtPTKgbLVq0tlo//f7XKuKTohn56KPs2KGjf/8gduwIzlHeqVAUlny+mjRF4bmX3qCO2oZOHbvmWcTyPMMiTtOgdge6d7/fEZLeE/lSAOfPn+ett96yXg8cOJA1a9bQrFkzDAZDsQknkRQXgswNvjp16xIU1BGgXCx5BAUNzrUfrVu3ZlfoeapVrUbkTfPZgZ9+/g2/CuaZ0Ny5823+Ojturq74+PpCHNSuXTfPvLdTb6PFk8QGCWCA3+K2kHTqMk+3esYhshaGfC0BGY1GLl68aL2+ePEiqqqi1+sxGo3FJpxEUlwIIawmfmXV4qcwaLJYAtmLeyDJIOszUczPySTyNn1PMaSa82F+KRZCsDt0Z/HIV0Tkawbw8ssvM378eBo1aoQQgpCQEJYvX857773HAw88UNwySiRFjkBYl4DKqs1/Ych6FsCiAMp5jJd7Q4jMWAp24iPY5jX/ebDRCG6cS0WDBhN3KVPC5EsBVKpUid9//50jR46g1Wpp164dfn5+tGzZEm9v5zwqLinbCCGsS0DO9AZsL7ZxeTR5vWcsvwkhUDQZIUDvogAsZ0p02sxTxOpdZg0lTb5nANu2bcvxti8Hf0lZRSBQRIapnxO9AWeOawLL2ORMCjDf2CwBmf/YC5FpU0RkxF/OUAAaob1rmZImXz/9Jk2asHnzZm7evElcXJz1P4mkrJJ1CciZ3oAtfVVF1iUg5+l/gSnIElBGRq028xSxKA8zgF27dhEcHGyTpigK//5rx6e4RFIGUFUXRqa+BEDcnTslLI3jsAz2l/4Nw9XFA41GK2cA9sjyTCwf005X5N1TG7kdE0ulSoFcu/4vgbWNbN8ezIABQbhoWgOgy4ia1tEwmN0RmZETDekmvvtiDxfPX6FN57qMHJX7ITF9mpENX+7l4oUrNGrcECHgl98/ZMr/PVWklmr5UgCnT58usgYlktKAyVATf1EZgAuXTgF9S1YgB+Ht4waAu5t5+VZvSEHn4kRrYPklyx6A0S3VmuyqBFItMBCAxnW788m3MwmPuMSVK5d44bm1AHj5uVnz17rd3vr5ZmgcSbEuVK/clH+Ph8Go3JsPuxZL0h1z3uQ4c5pOVGLp0oWOVwDp6en88ccfJCebg06YTCZCQ0OZMWNGkQkikTgSkbH8k26M4/6BjUtYGsdRoZIXNZqksPbTzwGFp6dOtC5ZSOyTWP0qt2+m0sTYCYDUtARc3XRoFU9GjRpL8I6N9O8fZN0ErlHPl4MVj6C7XQMvDx9rPRZHgwDVqlbPs02LV9qspBiuF/nhvHwpgBkzZhAWFkZ0dDTNmjXj5MmTdOrUqUgFkUgci/kfq0l3hcFDZpawLI7lwYcG8eBDg0pajNJNlhmARqNwTXvKqgACqvijdVVIijZRu2ZnXpjRDYCwc2ZXEDqNlqbt6nJ5hwEXXaZDuKz7wd4+eYfWtYTlzMo3v32Nr1LxXnqVg3yp/n///ZdNmzbRr18/5s6dy7fffkt8fHyRCiKROBJh9QBXujfpJCWMEOg0OlTFZE0KSbzGuVhz/IS4m0YizumJOGf2F5SOHjdXF6tlmcUyCGzjMNxtQ/nfmJz7qxv/LXqXO/maAVSuXBmdTkfdunW5ePEigwYNIjExsciFkUgchbD+wyzdZnqSEiLLJvBDjR7h9oWNYA6bgJvOFY2iQoZOiPC4QITHBQCqV6+Av+cANBkaIKsCyDroZw/Kk500Qypkc1U+ud1TqGmF7ZB98qUAPD092bx5M02bNmXDhg3Ur1+flJSUopVEInEoSsb/5QxAYocMBaAIQfsqHXFvV4M/f78EQMMKjXB11XIzzLwKMrzDQNp3n2JTXKtkTAGyzgCyrAFlD8uZHXsRF/09/IlNSy54X/IgX0tA8+fP5/z58/To0QOtVsv48eN56qmn7louKSmJoUOHEh4eDsCBAwcYNmwYAwYMYOXKlfcmuURyD8gZgKQgZD0roSiKzdkRjTanGa0lf9aQkqIAS0AmOwqgOM5r3HUGsGPHDj799FMuXrzITz/9ROPGjXn77bfp1atXnuVOnjzJvHnzCAkJASAtLY25c+fy1VdfUa1aNaZOncoff/xx13okkuJAWG02pAKQ2CHLElDFpnXxadgDejwNgOup47gZUqFGSwC8ly2i4rnfbYr7NqwFPRaipOqp2LQuAJ6Ne0O3J80ZIiKs6fbQPtAXQ80nbEXatRPadLm3fmUjTwWwbds2Vq5cyfTp02natCmKonD69GkWL16MXq9nwIABuZbdsGEDCxYsYNasWQCcOnWKOnXqUKtWLQCGDRtGcHCwVABlCFUVRITFo6oq1Wv531PQ8NtRSSTGmxc0K1Tysrojvhsmo8rNsDi0Wg1u7joS49OoXN0XT6+7h9+7fDOEU9fMXm3jTZ74A4pUAJJcMLTviMvRw2hiY9Fm2fPUGNLRpGda6eiSEtHExtqU1SX4m/8q3nzTrAGuKZHcqtvIej/RK4Dz7lqa3YzO0W6aTsutwBb4Z0lTVBNEReXIe6/kqQDWrVvHF198QfXqmTarDRo0oHXr1sydOzdPBbBo0SKb66ioKAIzDlCAeWM5MjKysHJLSoALp2+xd5t5APWvks7oJ/sXqp6EuFQ2fHbUeq1oBE/N6ImLi/auZY8cuM6xA6E2aS7uKjWbprJkyULeemsRXbv2yVFOVVV+/uokXsLfLD/tAEjXF+2aqqT8EPfbDpSMU+IpV+Nhl/lU7+2GDahSJRBCEgDY0r0bM1Iu88ILM+nb1/xvIj38ImxLx0epwtVO9mMrfDl6JS9N6mrdMLbw/o7N+IfUs82s1cDYsRBdtMY3eSqA5ORkm8HfQr169dDrc9qp5oWqqjZHzoUQhTqCXrFi4R3QBQb63D1TOaMo+3zWdNP6+eTxM0yf9XCh6klJTDf/TUvEVeeOTueCj5c7Pn7udykJpvSca6PJiXpWrHiLc+fOMH/+fE6cOJEjT7rBYB38L+gP4SnA15RG4D87CAx8r1D9KE3I33YxUcUPAO86Bj7+6mdSUwzEJPzL2s8+Yd/8T4iOvsUfh74h9k4UyR9/wGPPmpeJ+jWuzQcbn8dLW5F6ri1x1WTOcE+n/UlL9/vxEn74NayJm6vt7DV9mxZL7nPX96M1upBiiACGFXmf81QAWm3ub2R328XOTtWqVYmOzpzuREdHU7ly5QLVAXD7dtJdTajsERjoQ3QRa8/STlH3OTkpU+k3b96y0HXfiTVbkMUn3sLXqxI6XQViYhJJS797dLnU1PQcaW5u7rz00hyWLl3IG2+8YVeuFL15ucmIgcouqVT6/FNei4/j7KAhZf53IX/bjqHP4KbWUJse3i70GFCXpUvXM+GJCezYEcxLL82xkWlk9/tZunQhDQc0t6advLCV2o28MJKODlduRcbh6W67/Gk0mF9y/oz6mpa1arJjxxbrCeDC9FmjUXJ9cc6XGWhR0Lp1a65du8b169epWbMmW7ZsYeTIkY5qXlIEZDVjq1atRqHrsbw8tG/fkYS4VJIS9NgxesilbM40RdFYwyDmNjCYTGajbYHK3Lnz8fD1gzf+Q716DZCLQJL8kD3UZtZreyE0Lfe/X3uE2Gjzr+yZZ6bRulMt3l1i3jS2Z+1j+Y336duPKUNHFWt4zjwVwIULF2jXrl2OdCEE6ek538Tyws3NjSVLlvD888+j1+vp1asXQUFBBZNWUqJk9WxbmFlY9rIaTaYv+vzOKO3lU+34TcmOSTUrANVi91/K/bRLyg82oQUs7rgzfoeW36UNGSbKjnBTnqcC2LFjxz03sHv3buvnrl278uuvv95znZKSwcaO+R4GUGssWo1itW3Or0LJrVmjwYSiUVBN9qcSljctoWT7ByddIUuKmaz2+xrLC4+iggCTvd+9yFmuuMhTAdSoUfhpvqT8YXOS8R5mAJaymiwHavKrUHJTFJ+s2AeYg3H0G9aUBk0Dbe6r1hlARnk5A5A4iKzGLtbfe8YMQLU7A8hZrriQfmAl+cbGl8k9jJ8iyw/c6nQx3zOAnPk0GTMJRTG73L0ZGpcjjzHLHoBE4kiyLuVkLgFlvJDYm7FaQks6YHLqsE1gSdnnXmcAu65vZ/HBN6ma2IQejOevm3vxNlSkAtWZtG08d9xu3rWOnpETqUkz63WE+wX2VjUH4miU0JUOsQ8RmRwJNLIpl3MJyKqFCtwPiaQgaBR7S0ACBBjzmAE4QgNIBSDJF+t3/kLicX/r9dWrt1iy5CKKoiCEQE8Ku30/Y/oDzzCy8WN26wj+Zz99Q57DHS8A4tPj0aoeVAB63HqCVCWZn93/R7juQq5ytDfY2uwkGhM4H2t2neuTXheAU+EnqbuvJscOXiMlOQ2di0KaPh0vdz/UUh6jVVL+ULKss5w+c4qmrapaZ6LffvAPzTq6MHiI2ZrozLEb+N6pDUB42PVil00uAUnyxfXzcTbXOlzxoxK+oiJ+VKIytQnUN+CnSxtzrcPvTh0CRDU8hTkYhv7KHdo3bgGAt6hAoFqTZke6wofg8omL3b+aMNuzKakhsdQPbggfApfNaTEx0fx76hYmgwY3V0+0igde7uYDPTctmYScAUgcQ2BV8+Etk8nIN999DECUyzUAvNz9+fzTr6x5L5zJ9I6w6+/NxS6bnAFI8kfGuuTOG5/QpHoN9u75E1Do26cvt0M0tKrXDw2avN+wM+rYfe1LIk6fZ978eQwc2InfNMFs/vFP2twXRIf7upESf5POnbtx8OCBHH/rVm0IQJJ6jt1//MwLM15gBD1YunQhTWo3BRUCKlbKsUR17vqfbGv+OYrOxLu8WiyPSCKxR9c+9YlNvsh77y1j5kuvALDNbzVjo2sRIKoyZmym0zfL7/YLz9cY0L9nscsmFYDEiu7YEVyOHrZ7T0kz/1SmNGnGCLcK8Ghd672/PSvxdypohBYlLASPT1bbryPZ/OMe16Ihj3foCGHX4dOPeBSo374Nf6SAm1KN/l2fB6B/1/Z2/wJM9Pdi/iMjzHUAD40Zz9rUOOJTwMtgQBhTyPrzHtmkPt9rYqim+uLxyWpcDv2TIZScAUiKF0VRGDpsEEOHDbJJi9NEEmCqSscOna3pFiu3VCWJNq3bFrtsUgFIzKgqfo+OQJOYYPe28vxicAGP4N/wPnTa5p57p8egx3gUNGguXcR7vf03bOW5+eAGHrt34b3fVtG4tx0GfcxBNbRGA5Vv577+6ZMYQ8Oty3HNFjfVo39f4lt2Iz0hDqOSAu6ZcVfjT+6HjqCNT8B7ZaZ8wv3u/ockkqJGURTrPoCwCRST8RfVIWagUgFIzAhhHfxTJk/NedvV3XxwpVNnUlp1s7lndG0AgAYNhpo1SZk8xH4T7p7mOtq1I+U+2xPmBpe61s9+ShpjPc7nLqsHGCdOxJg93dPsVCvCV8HHoCGrh5VvWpr/sWm9fEiZPMac6OVN6vgnc29HIikmNIrGehrYXqxgFRMaB2zRSgUgMZPx6iG0WpIXv53z/v++gTQwDnuI5La2a5PGg2Gw5yoatOgbNiJ5pp3ygHj/S0gGdeBgkjvZumw2Hr8JGSH3lKpVSX7Kfh15UffEVW4Fh+HvWgGd0cUm1ktFz4rc59+csfeNJ7n1swWuWyIpSjRoUJWMGYCdWMEqKhpFKgCJo7jLyVjFcjxdm/NHaZmqKmgQ+dgE1mpyr8PcRuGmvj5uZo+HfWv15/rl2xiNmbI81WoK7bstyq2oROJQNIoGkXEYLNWQRnKGeXPmeRUVxQEKQJqBSszc1SzScjrRzuCdkaQR+bMC0mpyuhnP2mxhfaBkdSynZlNojvCrIpHkl6xLQP+3YzL1PqlGvU+qEZZgDnakolqDlhYncgYgsSGmQg2O/xOKm7sLIEhLNa+0uxvNtsxaOzMAy+Da2TCMPwxhOe7/+vdOrt+IxDXdfADM3ixCY+e4fEGxKJE7t1NyeAh1xIaaRJJfhtR/kLho82+ym+FBfDX+eKn+eGL+d1bduxrtqrTPq4oiQSoAiZmMN+ZtvacQsvdajtvuGT/MM2dOcH+zzjb3XF0zf0Z1wm2DVsckxBL2hwYdNbHEMrpy4QL9WttuJLu6ZdYRn2COrxocvJUlSxYyYEAQ27cHM3v2PBt/7Nmx1HEnJiXHvYuX/6VN51q5lpVIHMnr3RexJ/4C50/doraxObWNzbPcFQSP2oW7h0uxyyEVgMRMhgJIc7ONHBQZc52LVw9BW4UYn3ASvg3h2cdsrYTqNalExDeXqObbCFOq7Zt2fEqieXOYFA5HbyX2zi1Sfw9nymO21je16wdw/N8tJMQnk2K8wcRn+7FkyULOnTvDlSuX0Ov1LF26ME8FUL22PycvbCEhPhUAT28X3Fx9iIgII1F/jcfG5h7DWiJxNO271eH8qVvW64Sk25w8txutq4FnPHo7RAa5ByCxcjkA7njYDuC3CeW4ZisHK2zihOsunpz4dI5yLi5aAjP8s3m4edrcM5rMS0hpJNO8YiBp124w+9X/5KhDq9Pw8Og+RMaf4NlpZgUze/Y8mjdvwTPPPE/z5i2sYfFyQ6NReGLKYC5c38uF63/wyJj+DHukC3dSLvDSy7Py/RwkEkfg6++OX+XMwFopqXe4cP0Pxk4c7jAZFHEvkT1KABkTOP8UpM8iJYXmH1RllPiAympta/pRl9/51WOV9Xr/6CM0qtA4R/mdRw9waYeBaI9rzH9hojX9bOhF/vwmggRtDK++UvwhQOX37ByUlz4f/PMaxw6YN36r1/Zj+Jg2ueYtbJ9LRUxgSenGpBqJ8QIlyXZSWNu3Dg/WfgiAhv4NaejfyF5x6yZudssFa8g7pUy9Z0gkDsEmWEwJGCpIBSABQGScmtIIWwXQu05f7h+Q82RwdjQW236RTQFkBLyQgVgkkpxoisD8+Z7ad3iLklKJyDiAosHWRl+Tz7cSy+EuJZsCMajmPQAhZwASSQ7sRQtzJFIBSACsJ3iz+x/J72FEi56QS0ASSf6xOf8il4DKNyaTitGg4uqmLYUHk1QUoeAhfGxS8yunZQlIUTVEx9+2pickJQGZS0wSiSQTGxcoJTAkSAXgINL1Rr54/y9MRg2efkaeeKZfSYtkg6qqPJWyDFds3SOHhFylGw3uWt5yureCoTobV5/Jcd+k5vDdKZE4PVmXfSKjIoEWDm1fLgE5iPg7qZiM5sd9J1p/l9yORzUJapmaWq9T9YnEJ8bw85Yv8lW+RZ0m3FQvk0pSjv9SSORi1MFiklwiKbvUrONPUkosSSlx7P7rR4e3L2cADiLrcQsPD888cpYMpowDW0YMNGqTDmhYunTFXQ9fWfB296R7u2osXbqQ/v2D+PHHDaSkmF0yeHp6sWjR0uISXSIps1Ss7E3Lbm4sXbow3//WihKpAByEmsUKUqstfY/d4j1TxWR1t5CX2wV7BAUNtpaZO3d+0QookZRTsv67cTRyCchBCDtRf0oTqirt9SUSZ0MqAAeRdQkou6/60oBqMptrSgUgkTgPUgE4CHtxP0sTFvmkApBInAepABxE1hmAELbXpQE1SzBqiUTiHEgF4CCyezAtZeO/XAKSSJwQqQAcQFqqge2/nLJJe3X6Cv731ne8Mm05SxYvo3fvbgQHby1WOYKDt9ptR1UF27ddMn+WCkAicRqkAnAA1y7GYEy3fdT1a3bETalG/ZodOX8qknPnzrB06cJilcMSYSt7OzGRSaQmm11ApBBbrDJIJJLSg1QADsBoNL9Vp+mTqN44Ncf9Nq075Cvi1b1iibCVvR2jIXPd/zftW8Uqg0QiKT2UvhNJ5RCL1U/Hbk3o0b8h33x8iPjYTEXQqlVbXpxzoNjlyO3AiWVD+pr2FKmKnAFIJM6CVADFTFJ6IqeiTgLeXIw7T/j5gyQaqgAu1jzX7lzju/NHbcq5al15oPYAfN38il3GTAsgldLmo1QikRQfUgEUMyuOLOPExTAG8CS7w3awPfpznkl+j6rUs+ZJDXclIbwCl3RH2ej5tjV9csupLO75tr1qC0x4yB12bTmfsdyj0K5rLdp2Mcf+tVgkqZik236JxImQCqCYiU6NsgZZaRzQBP9ao/E76wcpmXm06NCio6XxfjSNbxCaGMI/EQeISY0uMjlCr8aSkpRuvb56ISZTAVgOgSnmmAASicQ5KJFN4PHjxzNkyBCGDx/O8OHDOXnyZEmI4RBUoaJkPOaB9Qaxqt8aavvWtt7vOaAhk17sjlZrHnhX9vqAJ1tMBor2rIBqMlfW8L7AjLqzuKaQS0ASiVPi8BmAEIKQkBD27NmDTlf+JyCqUK1xdi3BH7IGgdDptLi569DqNJhMJlSTQJMRh7EobfItwdldXM3PPKtyEVk8gcolIInEeXD4CHz16lUAJk2aRFxcHI899hjjxo1ztBhFjsmkEn0rCaEKtDoN3r5uxMemok13paaxEZAZ8i1roHWLMjBH1DIRERZH+m0XapgaIYpo/DeZVG6GxgGg05mVi2XQF0IQE2kJ2yhnABKJM+FwBZCQkEDXrl35z3/+g8FgYMKECdSrV4/u3bs7WpS7Ehy8lblzZ6EosGjRsjx9du/feYWzx2/mSG/B49bPl69cokOPumi0mcPsr79u4rdpXzFm2CJAw7YfzwK+TOEdLl3eXyT9+GPbReIyzE4PHfkbD6U2CQmJgPmQ2tEDoQCYMEoFIJE4EQ5XAG3btqVt27bW60ceeYQ//vgj3wqgYkXvQrcdGOhz90xZWLHiLcLDQ62fx48flWvetBQDAMmpCXh5+NrN892Pq3j+5Yfp2a8Rq975geiYCLb/+Ql34mM4XOdXaldrS3JyMl5+vlTyrokapy2wzNkJDPQhNYtsP/2+lnEjXud2TDSBgT5cPhtlzXvE9XeUNOWe2yxpyrr8hUH22Tko6j47XAEcOXIEg8FA165dAfMSREH2Am7fTsrhWC0/BAb6EB2dmO/8QghemD6XJUveBBRefGFOnuXT0syDbETUeRrW6ZTj/t6wL/i/Z6cSHZ1IQBUvOvWpzNKlH/PEkxPZsSOYkaP7A/Daa8uo3KIRD973Ij7evgWSOTuBgT7ciowjKSM04/7z63hgeF8A/CsGcCbkEhGx5oNfl2/u5HrTM9QR2ntqs6Qp6PdcHpB9dg4K22eNRsn1xdnhVkCJiYksW7YMvV5PUlISP/30E/3793e0GHfl95/OEXbWk7HD3mLssMWEnvHixMGwXPNb1tSHDnvQ7v1HHh1ls4QUFDSYPXsOMHfufPbsOWA9pXv06BmemjwVADc393vux4hfBmccRIPr3UPY4P0tAFGGSFp+2ZiVR5YDcKtuHIDcBJZInAiHzwD69OnDyZMnGTFiBKqqMmbMGJslodJC1M0EANw9XVBNKul6E9G3cte+lg3brOv7WVGU/K+uW/IWhU3+8cijtOZRAPw9/PFQXCEZdIoLlT2r4KP6gB48tO5UTYTxl0pfwHqJRFI8lIgd5osvvsiLL75YEk3nG1PGMtOopzpwMzSOHb/8m6ddvmUGoNXan1RpNPkfzDWWKsS9T9BUVOtBtO+HbcLVTcc3aw5R26cOZyZe4uj+6xz6K4QpDcbxy6Q1mKr7Sn+gEomTIL2B5oLl4JRGo1jfyPOK4qUWoQIoyhmASTVZzyGY+2JOt57+zZDb2lIBZioSiaRsIxVALqiqeU3HZtDMawagWhSA/QFUo8n/oy6IssgLIQQCYT2JrChZlFlGHst+unXclwpAInEayv9R3HyQoI/nwM39mESmX3yjyQdQ2B66jdQoHeDJraQIfss4yJaduDQvQMvlhItAzs3bgi0BWWYA96afRcYwb1kCUuzNZuQMQCJxWpxDARiNcOIEutv2N3FfOf9f/om8zpC0/8NVmAfvKqrZlv+p7eNpbOzAGP7D8ahjfBu8kFrGpgSlPY0LrtY6AlR3XNDyw6VvGMCkHG1EHDyEziMgX+Jqb0UAtfFKDmTF7K8JCKiERlGJjo6ionqRQ39t5cknzf6CPv/8U558cjLduuU8R6H6udE3bSyV1JoAnP7uazp1bA9AcmI6m1ZuREEAlYk8dTxfskkkkvKDUygAn+nPwMbvqZDL/ZgnoXmVJ6hlamqTnma8wfDzKr7uAipCtSQNI65DTb/7CfRunKMek5pKnbAzUDlnG5M/WEuFhYvzJW9AswAuB32Ki+KGi39N0jIsjLwC6tL+0GFmXbsC8+cAMASsn7Oj10K3FzYCoDPoGbb4NTSqCc+nPyPF059IfSBdD//IrY4jabDvT3OhAixVSSSSso1TKID0Pv1wv3YZQ7rR7n2T1yW0GRulDY/9Qq1zu1E0Ghp6KlT0as0pz0B+6w4t4zxZcq41wfdV4bg3NDn0A9Uv7kPRaPD18UGNCqOWvzcpbnMIT9LTwE0Q5x1IUvgVtL6eGGq2zpe8usqJrPCeSNfwAB5wXUi6Z2ZQmDhvP865u1OlSlUAIiNvUaVKVXx9cwaOUV2xbgAHrX+WxOrmfGN3LOKT4eY4A0kVKgKQ6u+PoWVr0saUfb9MEokkfziFAtA/+jg8+zRxuZyiM2zqjybEPFBWfmUmTTu+Y70XB4grt+GHM4huPYj737Okbr0Ap25Rdf5rNG1TzaYuFfMOQMOM6woZ/6kZdeWHlPA/SPl1GGldWuNyozLpifrMm+MmErhukdVPaGAedXv6aVDm7ASgxr+XUDUKcZi/dNeV+0jXmzCOfBxO3kJMn0Fc51r5lFAikZQHnEIB3A1VqNYNV3ubtdZDXNZ9U5Fr3qIg01JH5GhDn2ogMT7Neu3qpsPN3f7XaOOKOpuoFu+jFh9GcutXInE+pAIAQGRaytixgsk0A82wnVdt04saiyyqUHO0cfnfaC7/mxkpTKNRGD6mNVVr5lwCMqqZS17Z+2U5r3Dt0m3z/WJSZhKJpPQid/ywjdplbw8003TSkj/DdNIBM4DsbXj7uln/07loUFXB7ehku/WYMs4y2Ass06x1VWs9AYFe1KqX2xa5RCIpr8gZAOYBPXOpJD8zAJFr3qJAyViQuZMWS4oxGYuertI1HZ86qdZ80UddiL+k41zUWW6GnMpZkYsR8EHYUQAdetSlQ4+6xSC9RCIpK0gFQMZae55LQLYzgOLeA3DRugBw8c4FwpNCqUJdAN478Q7nzmYGiRmQ9iTdeZhvzn3N/iubctSjEy78h01knvuVSCSSTKQCAFwNXrQx9ANyGdQzkpIT9Zw5dpP4O+a38OKaAbQObMuTLSYTlhCK12UvyNjzbRnYkuq+XtZ8tSJrQTS0d+1FPe+6pLrewSO9AooAozad5Io34CRotdpikVMikZRt5B4A0DZmmPXz6TMnctx3cTEPoAlxafy1/RK3o8xr7idOHi0WeXQaHUvvf4dvhm6kYaUG1vRaIbW4ufwmE3STmKCbxJ19MQBUTKxPo5t9aBXyMI1u9qFhRB+ahg+k9VmzUsvNqVxw8FZ69+5GcPDWYumHRCIp3cgZAOBmMr9VX711kh93bGTk4wNt7leq4s3JC9tIT7M4fNMSlxBD7PZ/efixgTnqK0q69mnAsoUfEnbjKodObiY1NZmlSxciBFy/FkZKsh5vzwBaNr3fWub2nZtUrFCdY0dP06l1HdLT9XbrXrJkIefOnWHp0oV5xjuWSCTlEzkDIHPT9UL0Xl5+ZXbO+4rCiFH3c/Lib5y8uJV6zdyJSTzDK7Psu2AoSqrW8GXA8FbEJJ5h6tRnaN68Ba++Oo/Zs+dRt34tmrapwPlre2zKxMSFANC+XQcA3Fzd7NY9e/Y8a30SicT5UEReTu5LIcURE3jhO19RMb027UdUoFPTVvcqosOJv5PKN2sOWa9btKvOmWM3adWhJqeOhOPmrmPSizmdxZVHZKxY50D2Of+UqpjApRHrKWClbD6O7JvRuow9i6sXo+3el0gkEpAKIIPc3UCUBbIfXvP1N7u0Tkowr/17+bhmLyKRSCRyExgyrWRyC+he2sn+hl+vUSUqBnrh5uZCfHwqVar7lJBkEomkNCMVAGS6gSijSyXZ3UVotApVa/o55TqpRCLJP3IJiEwroILE7S1NZF+6kmv+EokkP5TNEa+QHNh1hdVL9rJ8wS/8tsV8+GnR6i/wM5pDeB05ciiv4qWW7AO+opgPebVp00Ye8pJIJLniVAog5MptQMHLw591n38LgF+8OQhKtAjnyw8/KkHpCo+rm5bo2GsARMVexcVVy5IlCzl58iRLly4sYekkEklpxakUgMhyfmDUKHPoQ4sTuD3bP+DVV14rEbnuFUVR6NinMht+n0OnPlVQFIXZs+fRunVrechLIpHkilNtAmc98ta+fQdUNTMOwK5d+8rsHgDAoEGDGTQo051DUNBgxo8fJTeBJRJJrjiFAkhKT+To5f2kGgxYXHsKVWBUTQComMr04C+RSCSFwSlGvRf3TGPQ14OITY21poUn3MBoModMtBcxSyKRSMo7TjEDGNVkNCZNOu4nPMD80s/t1BjSTfUA7EbMkkgkkvKOU8wA+tcNYsuYLfi6+lrTDCYjJpNZG0gFIJFInBGnUAAWsnoRNZqMmCxLQIpUABKJxPlwiiWgyJsJ/LBuL6mpJrQac5ePHbjKnt0HaePdT+4BSCQSp8QpFMDxv0OJualYB3+AerpWkOEiO0UklJBkEolEUnI4hQLo/kBDDETz6y+b6TP4fq4mhXLy1AlMRhNanY6BPe+/eyUSiURSznAKBeDj586k/3uQYSP7lLQoEolEUmpwqk1giUQikWQiFYBEIpE4KVIBSCQSiZNSIgpg8+bNDB48mAEDBvD111+XhAgSiUTi9Dh8EzgyMpKVK1eyadMmXF1defzxx+ncuTMNGzZ0tCgSiUTi1Dh8BnDgwAG6dOmCv78/np6eDBw4kODgYEeLIZFIJE6Pw2cAUVFRBAYGWq8rV67MqVOn8l0+e/zbgnAvZcsqss/Ogeyzc1CYPudVxuEKQFVVmxi2QogCBTGvUMGr0G1XrOhd6LJlFdln50D22Tko6j47fAmoatWqREdHW6+jo6OpXLmyo8WQSCQSp8fhCqBbt278/fffxMbGkpqayvbt27n/fumKQSKRSByNw5eAqlSpwowZM5gwYQIGg4FHHnmEVq1aOVoMiUQicXoUIbKGSpdIJBKJsyBPAkskEomTIhWARCKROClSAUgkEomTIhWARCKROClSAUgkEomT4hQKwBm8j44fP54hQ4YwfPhwhg8fzsmTJzlw4ADDhg1jwIABrFy5sqRFLDKSkpIYOnQo4eHhALn2899//+Xhhx9m4MCBvPbaaxiNxpIS+Z7J3uc5c+YwYMAA6/e9Y8cOoPz0edWqVQwZMoQhQ4awbNkyoPx/z/b6XOzfsyjn3Lp1S/Tp00fcuXNHJCcni2HDholLly6VtFhFiqqqokePHsJgMFjTUlNTRa9evURoaKgwGAxi0qRJYu/evSUoZdFw4sQJMXToUNG8eXMRFhaWZz+HDBkijh8/LoQQYs6cOeLrr78uQckLT/Y+CyHE0KFDRWRkZI685aHP+/fvF6NGjRJ6vV6kp6eLCRMmiM2bN5fr79len7dv317s33O5nwE4g/fRq1evAjBp0iQefPBB1q9fz6lTp6hTpw61atVCp9MxbNiwctHvDRs2sGDBAqv7kNz6eePGDdLS0mjTpg0ADz/8cJntf/Y+p6amcvPmTebOncuwYcN47733UFW13PQ5MDCQ2bNn4+rqiouLCw0aNCAkJKRcf8/2+nzz5s1i/57LfVD4e/U+WhZISEiga9eu/Oc//8FgMDBhwgQmT56co9+RkZElKGXRsGjRIptre99vZGRkjvTAwMAy2//sfY6JiaFLly4sWLAAHx8fpk6dysaNG2nUqFG56HOjRo2sn0NCQti2bRvjxo0r19+zvT5//fXXHDp0qFi/53I/A7hX76NlgbZt27Js2TJ8fHwICAjgkUce4b333iv3/Ybcv9/y/L3XqlWLDz74gMqVK+Ph4cH48eP5448/yl2fL126xKRJk5g1axa1atVyiu85a5/r169f7N9zuVcAzuB99MiRI/z999/WayEENWrUKPf9hty/3+zpMTEx5ab/Fy5c4Pfff7deCyHQ6XTlqs9Hjx5l4sSJvPTSSzz00ENO8T1n77MjvudyrwCcwftoYmIiy5YtQ6/Xk5SUxE8//cTMmTO5du0a169fx2QysWXLlnLXb4DWrVvb7WeNGjVwc3Pj6NGjAPzyyy/lpv9CCBYvXkx8fDwGg4Hvv/+e/v37l5s+R0RE8Nxzz7F8+XKGDBkClP/v2V6fHfE9l/s9AGfwPtqnTx9OnjzJiBEjUFWVMWPG0LZtW5YsWcLzzz+PXq+nV69eBAUFlbSoRY6bm1uu/Vy+fDnz5s0jKSmJ5s2bM2HChBKWtmho2rQpU6ZMYfTo0RiNRgYMGMDQoUOB8tHntWvXotfrWbJkiTXt8ccfL9ffc259Lu7vWXoDlUgkEiel3C8BSSQSicQ+UgFIJBKJkyIVgEQikTgpUgFIJBKJkyIVgEQikTgp5d4MVCIpLOHh4fTv35/GjRsD5lPHXl5eTJgwgcGDB+dZdtWqVTRt2pQHHnjAEaJKJIVCKgCJJA/c3d355ZdfrNc3btxg4sSJaLVaBg4cmGu5gwcP0rBhQ0eIKJEUGqkAJJICUKNGDaZPn87atWtp3Lgxb7zxBsnJyURHR9O0aVP+97//sXHjRs6cOcOyZcvQarU0bNjQbj43N7eS7o7EyZF7ABJJAWnatCkXL15kw4YNjBgxgg0bNrB9+3bCw8PZu3cvY8eOpUWLFsyaNYv+/fvnmk8iKWnkDEAiKSCKouDu7s4rr7zC/v37+eSTTwgJCSEqKoqUlJQc+fObTyJxNFIBSCQF5PTp0zRu3JiZM2diMpkYNGgQvXv3JiIiAnueVfKbTyJxNHIJSCIpANeuXePDDz9k0qRJ7Nu3j+eee85qEXTy5ElMJhMAWq3WGqc1r3wSSUkiZwASSR6kpaUxfPhwADQaDW5ubsycOZPevXszY8YMnnvuOTw9PfH29qZjx46EhoYC0LdvX9555x0MBkOe+SSSkkR6A5VIJBInRS4BSSQSiZMiFYBEIpE4KVIBSCQSiZMiFYBEIpE4KVIBSCQSiZMiFYBEIpE4KVIBSCQSiZMiFYBEIpE4Kf8PSc+70IDVdb8AAAAASUVORK5CYII=\n",
-      "text/plain": [
-       "<Figure size 432x288 with 1 Axes>"
-      ]
-     },
-     "metadata": {},
-     "output_type": "display_data"
-    }
-   ],
+   "execution_count": 9,
+   "id": "b91836da",
+   "metadata": {
+    "collapsed": false,
+    "editable": true
+   },
+   "outputs": [],
    "source": [
     "import numpy as np\n",
     "import matplotlib.pyplot as plt\n",
@@ -1262,7 +1225,7 @@
     "from sklearn.tree import DecisionTreeRegressor\n",
     "regr_1=DecisionTreeRegressor(max_depth=2)\n",
     "regr_2=DecisionTreeRegressor(max_depth=5)\n",
-    "regr_3=DecisionTreeRegressor(max_depth=9)\n",
+    "regr_3=DecisionTreeRegressor(max_depth=7)\n",
     "regr_1.fit(X, distance_list)\n",
     "regr_2.fit(X, distance_list)\n",
     "regr_3.fit(X, distance_list)\n",
@@ -1289,8 +1252,10 @@
   },
   {
    "cell_type": "markdown",
-   "id": "5f57d414",
-   "metadata": {},
+   "id": "a9eb9d5e",
+   "metadata": {
+    "editable": true
+   },
    "source": [
     "## Building a tree, regression\n",
     "\n",
@@ -1309,8 +1274,10 @@
   },
   {
    "cell_type": "markdown",
-   "id": "48708410",
-   "metadata": {},
+   "id": "afefdfd6",
+   "metadata": {
+    "editable": true
+   },
    "source": [
     "$$\n",
     "\\sum_{j=1}^J\\sum_{i\\in R_j}(y_i-\\overline{y}_{R_j})^2,\n",
@@ -1319,8 +1286,10 @@
   },
   {
    "cell_type": "markdown",
-   "id": "cd5139ca",
-   "metadata": {},
+   "id": "f5b8dc1d",
+   "metadata": {
+    "editable": true
+   },
    "source": [
     "where $\\overline{y}_{R_j}$  is the mean response for the training observations \n",
     "within box $j$."
@@ -1328,8 +1297,10 @@
   },
   {
    "cell_type": "markdown",
-   "id": "101b6bee",
-   "metadata": {},
+   "id": "ec5a291d",
+   "metadata": {
+    "editable": true
+   },
    "source": [
     "## A top-down approach, recursive binary splitting\n",
     "\n",
@@ -1348,8 +1319,10 @@
   },
   {
    "cell_type": "markdown",
-   "id": "431db8c1",
-   "metadata": {},
+   "id": "58b762b2",
+   "metadata": {
+    "editable": true
+   },
    "source": [
     "## Making a tree\n",
     "\n",
@@ -1359,8 +1332,10 @@
   },
   {
    "cell_type": "markdown",
-   "id": "7b202f38",
-   "metadata": {},
+   "id": "539de439",
+   "metadata": {
+    "editable": true
+   },
    "source": [
     "$$\n",
     "\\left\\{X\\vert x_j < s\\right\\},\n",
@@ -1369,16 +1344,20 @@
   },
   {
    "cell_type": "markdown",
-   "id": "05c33034",
-   "metadata": {},
+   "id": "d8af3fbe",
+   "metadata": {
+    "editable": true
+   },
    "source": [
     "and"
    ]
   },
   {
    "cell_type": "markdown",
-   "id": "1a90ac39",
-   "metadata": {},
+   "id": "becbbdfa",
+   "metadata": {
+    "editable": true
+   },
    "source": [
     "$$\n",
     "\\left\\{X\\vert x_j \\geq s\\right\\},\n",
@@ -1387,16 +1366,20 @@
   },
   {
    "cell_type": "markdown",
-   "id": "9bb1c584",
-   "metadata": {},
+   "id": "9b87b748",
+   "metadata": {
+    "editable": true
+   },
    "source": [
     "so that we obtain the lowest MSE, that is"
    ]
   },
   {
    "cell_type": "markdown",
-   "id": "c9f3bc0f",
-   "metadata": {},
+   "id": "7d61073a",
+   "metadata": {
+    "editable": true
+   },
    "source": [
     "$$\n",
     "\\sum_{i:x_i\\in R_j}(y_i-\\overline{y}_{R_1})^2+\\sum_{i:x_i\\in R_2}(y_i-\\overline{y}_{R_2})^2,\n",
@@ -1405,8 +1388,10 @@
   },
   {
    "cell_type": "markdown",
-   "id": "c27c2ae9",
-   "metadata": {},
+   "id": "d0c9f872",
+   "metadata": {
+    "editable": true
+   },
    "source": [
     "which we want to minimize by considering all predictors\n",
     "$x_1,x_2,\\dots,x_p$.  We consider also all possible values of $s$ for\n",
@@ -1436,8 +1421,10 @@
   },
   {
    "cell_type": "markdown",
-   "id": "64a5be95",
-   "metadata": {},
+   "id": "8356ddf0",
+   "metadata": {
+    "editable": true
+   },
    "source": [
     "## Pruning the tree\n",
     "\n",
@@ -1458,8 +1445,10 @@
   },
   {
    "cell_type": "markdown",
-   "id": "39faa3d8",
-   "metadata": {},
+   "id": "e3bc4531",
+   "metadata": {
+    "editable": true
+   },
    "source": [
     "## Cost complexity pruning\n",
     "\n",
@@ -1468,8 +1457,10 @@
   },
   {
    "cell_type": "markdown",
-   "id": "2ff035cd",
-   "metadata": {},
+   "id": "e0f86657",
+   "metadata": {
+    "editable": true
+   },
    "source": [
     "$$\n",
     "\\sum_{m=1}^{\\overline{T}}\\sum_{i:x_i\\in R_m}(y_i-\\overline{y}_{R_m})^2+\\alpha\\overline{T},\n",
@@ -1478,8 +1469,10 @@
   },
   {
    "cell_type": "markdown",
-   "id": "5052b835",
-   "metadata": {},
+   "id": "240ad8bb",
+   "metadata": {
+    "editable": true
+   },
    "source": [
     "is as small as possible. Here $\\overline{T}$ is \n",
     "the number of terminal nodes of the tree $T$ , $R_m$ is the\n",
@@ -1504,8 +1497,10 @@
   },
   {
    "cell_type": "markdown",
-   "id": "d1c913aa",
-   "metadata": {},
+   "id": "24de8711",
+   "metadata": {
+    "editable": true
+   },
    "source": [
     "## Schematic Regression Procedure\n",
     "\n",
@@ -1528,8 +1523,10 @@
   },
   {
    "cell_type": "markdown",
-   "id": "1d22f123",
-   "metadata": {},
+   "id": "f0b74c5c",
+   "metadata": {
+    "editable": true
+   },
    "source": [
     "## A Classification Tree\n",
     "\n",
@@ -1549,8 +1546,10 @@
   },
   {
    "cell_type": "markdown",
-   "id": "f4607c7f",
-   "metadata": {},
+   "id": "957c9d69",
+   "metadata": {
+    "editable": true
+   },
    "source": [
     "## Growing a classification tree\n",
     "\n",
@@ -1574,8 +1573,10 @@
   },
   {
    "cell_type": "markdown",
-   "id": "426d11f9",
-   "metadata": {},
+   "id": "57a5e827",
+   "metadata": {
+    "editable": true
+   },
    "source": [
     "## Classification tree, how to split nodes\n",
     "\n",
@@ -1591,8 +1592,10 @@
   },
   {
    "cell_type": "markdown",
-   "id": "bcd8045a",
-   "metadata": {},
+   "id": "4193d006",
+   "metadata": {
+    "editable": true
+   },
    "source": [
     "$$\n",
     "p_{mk} = \\frac{1}{N_m}\\sum_{x_i\\in R_m}I(y_i=k).\n",
@@ -1601,8 +1604,10 @@
   },
   {
    "cell_type": "markdown",
-   "id": "f7acadbe",
-   "metadata": {},
+   "id": "65cb0b6b",
+   "metadata": {
+    "editable": true
+   },
    "source": [
     "We let $p_{mk}$ represent the majority class of observations in region\n",
     "$m$. The three most common ways of splitting a node are given by\n",
@@ -1612,8 +1617,10 @@
   },
   {
    "cell_type": "markdown",
-   "id": "fa502d50",
-   "metadata": {},
+   "id": "48b04834",
+   "metadata": {
+    "editable": true
+   },
    "source": [
     "$$\n",
     "p_{mk} = \\frac{1}{N_m}\\sum_{x_i\\in R_m}I(y_i\\ne k) = 1-p_{mk}.\n",
@@ -1622,16 +1629,20 @@
   },
   {
    "cell_type": "markdown",
-   "id": "9e7cf2d2",
-   "metadata": {},
+   "id": "2ccc5c64",
+   "metadata": {
+    "editable": true
+   },
    "source": [
     "* Gini index $g$"
    ]
   },
   {
    "cell_type": "markdown",
-   "id": "7f20d4d1",
-   "metadata": {},
+   "id": "78196ea5",
+   "metadata": {
+    "editable": true
+   },
    "source": [
     "$$\n",
     "g = \\sum_{k=1}^K p_{mk}(1-p_{mk}).\n",
@@ -1640,16 +1651,20 @@
   },
   {
    "cell_type": "markdown",
-   "id": "9b6935c0",
-   "metadata": {},
+   "id": "6f6dad5d",
+   "metadata": {
+    "editable": true
+   },
    "source": [
     "* Information entropy or just entropy $s$"
    ]
   },
   {
    "cell_type": "markdown",
-   "id": "3b764f21",
-   "metadata": {},
+   "id": "4fc9b106",
+   "metadata": {
+    "editable": true
+   },
    "source": [
     "$$\n",
     "s = -\\sum_{k=1}^K p_{mk}\\log{p_{mk}}.\n",
@@ -1658,8 +1673,10 @@
   },
   {
    "cell_type": "markdown",
-   "id": "71374aa3",
-   "metadata": {},
+   "id": "c92702f6",
+   "metadata": {
+    "editable": true
+   },
    "source": [
     "## Visualizing the Tree, Classification"
    ]
@@ -1667,8 +1684,11 @@
   {
    "cell_type": "code",
    "execution_count": 10,
-   "id": "d813600a",
-   "metadata": {},
+   "id": "58fa3eab",
+   "metadata": {
+    "collapsed": false,
+    "editable": true
+   },
    "outputs": [],
    "source": [
     "import os\n",
@@ -1708,8 +1728,10 @@
   },
   {
    "cell_type": "markdown",
-   "id": "a09f52fe",
-   "metadata": {},
+   "id": "2f12bf79",
+   "metadata": {
+    "editable": true
+   },
    "source": [
     "## Visualizing the Tree, The Moons"
    ]
@@ -1717,8 +1739,11 @@
   {
    "cell_type": "code",
    "execution_count": 11,
-   "id": "4d6b976d",
-   "metadata": {},
+   "id": "6987728d",
+   "metadata": {
+    "collapsed": false,
+    "editable": true
+   },
    "outputs": [],
    "source": [
     "# Common imports\n",
@@ -1749,8 +1774,10 @@
   },
   {
    "cell_type": "markdown",
-   "id": "7e9018d8",
-   "metadata": {},
+   "id": "dad046b8",
+   "metadata": {
+    "editable": true
+   },
    "source": [
     "## Other ways of visualizing the trees\n",
     "\n",
@@ -1760,8 +1787,11 @@
   {
    "cell_type": "code",
    "execution_count": 12,
-   "id": "c39e32e3",
-   "metadata": {},
+   "id": "1d4f3161",
+   "metadata": {
+    "collapsed": false,
+    "editable": true
+   },
    "outputs": [],
    "source": [
     "from sklearn.datasets import load_iris\n",
@@ -1775,8 +1805,10 @@
   },
   {
    "cell_type": "markdown",
-   "id": "46ebbfc2",
-   "metadata": {},
+   "id": "0846fdeb",
+   "metadata": {
+    "editable": true
+   },
    "source": [
     "## Printing out as text\n",
     "\n",
@@ -1787,8 +1819,11 @@
   {
    "cell_type": "code",
    "execution_count": 13,
-   "id": "a6934e7f",
-   "metadata": {},
+   "id": "cec3af4a",
+   "metadata": {
+    "collapsed": false,
+    "editable": true
+   },
    "outputs": [],
    "source": [
     "from sklearn.datasets import load_iris\n",
@@ -1803,8 +1838,10 @@
   },
   {
    "cell_type": "markdown",
-   "id": "fe5872b8",
-   "metadata": {},
+   "id": "2c8a67db",
+   "metadata": {
+    "editable": true
+   },
    "source": [
     "## Algorithms for Setting up Decision Trees\n",
     "\n",
@@ -1821,8 +1858,10 @@
   },
   {
    "cell_type": "markdown",
-   "id": "4ae904b8",
-   "metadata": {},
+   "id": "354c280c",
+   "metadata": {
+    "editable": true
+   },
    "source": [
     "## The CART algorithm for Classification\n",
     "\n",
@@ -1836,8 +1875,10 @@
   },
   {
    "cell_type": "markdown",
-   "id": "d402fb38",
-   "metadata": {},
+   "id": "7228e0b5",
+   "metadata": {
+    "editable": true
+   },
    "source": [
     "$$\n",
     "C(k,t_k) = \\frac{m_{\\mathrm{left}}}{m}G_{\\mathrm{left}}+ \\frac{m_{\\mathrm{right}}}{m}G_{\\mathrm{right}},\n",
@@ -1846,8 +1887,10 @@
   },
   {
    "cell_type": "markdown",
-   "id": "5e5d1a2a",
-   "metadata": {},
+   "id": "67b083e1",
+   "metadata": {
+    "editable": true
+   },
    "source": [
     "where $G_{\\mathrm{left/right}}$ measures the impurity of the left/right subset  and $m_{\\mathrm{left/right}}$\n",
     " is the number of instances in the left/right subset\n",
@@ -1861,8 +1904,10 @@
   },
   {
    "cell_type": "markdown",
-   "id": "8fa11772",
-   "metadata": {},
+   "id": "8fdfcd7f",
+   "metadata": {
+    "editable": true
+   },
    "source": [
     "## The CART algorithm for Regression\n",
     "\n",
@@ -1872,8 +1917,10 @@
   },
   {
    "cell_type": "markdown",
-   "id": "fa5d2104",
-   "metadata": {},
+   "id": "80ef07be",
+   "metadata": {
+    "editable": true
+   },
    "source": [
     "$$\n",
     "C(k,t_k) = \\frac{m_{\\mathrm{left}}}{m}\\mathrm{MSE}_{\\mathrm{left}}+ \\frac{m_{\\mathrm{right}}}{m}\\mathrm{MSE}_{\\mathrm{right}}.\n",
@@ -1882,16 +1929,20 @@
   },
   {
    "cell_type": "markdown",
-   "id": "cd80ff85",
-   "metadata": {},
+   "id": "2b96ed0b",
+   "metadata": {
+    "editable": true
+   },
    "source": [
     "Here the MSE for a specific node is defined as"
    ]
   },
   {
    "cell_type": "markdown",
-   "id": "58529e24",
-   "metadata": {},
+   "id": "31573190",
+   "metadata": {
+    "editable": true
+   },
    "source": [
     "$$\n",
     "\\mathrm{MSE}_{\\mathrm{node}}=\\frac{1}{m_\\mathrm{node}}\\sum_{i\\in \\mathrm{node}}(\\overline{y}_{\\mathrm{node}}-y_i)^2,\n",
@@ -1900,16 +1951,20 @@
   },
   {
    "cell_type": "markdown",
-   "id": "3c3c66cc",
-   "metadata": {},
+   "id": "2bbfe053",
+   "metadata": {
+    "editable": true
+   },
    "source": [
     "with"
    ]
   },
   {
    "cell_type": "markdown",
-   "id": "9464c612",
-   "metadata": {},
+   "id": "e32e4576",
+   "metadata": {
+    "editable": true
+   },
    "source": [
     "$$\n",
     "\\overline{y}_{\\mathrm{node}}=\\frac{1}{m_\\mathrm{node}}\\sum_{i\\in \\mathrm{node}}y_i,\n",
@@ -1918,8 +1973,10 @@
   },
   {
    "cell_type": "markdown",
-   "id": "658d6cc6",
-   "metadata": {},
+   "id": "1ad8a276",
+   "metadata": {
+    "editable": true
+   },
    "source": [
     "the mean value of all observations in a specific node.\n",
     "\n",
@@ -1929,8 +1986,10 @@
   },
   {
    "cell_type": "markdown",
-   "id": "9b6f7b6d",
-   "metadata": {},
+   "id": "21a60563",
+   "metadata": {
+    "editable": true
+   },
    "source": [
     "## Computing the Gini index\n",
     "\n",
@@ -1971,8 +2030,10 @@
   },
   {
    "cell_type": "markdown",
-   "id": "5b5c739d",
-   "metadata": {},
+   "id": "0caa4189",
+   "metadata": {
+    "editable": true
+   },
    "source": [
     "## Simple Python Code to read in Data and perform Classification"
    ]
@@ -1980,8 +2041,11 @@
   {
    "cell_type": "code",
    "execution_count": 14,
-   "id": "bf151d2a",
-   "metadata": {},
+   "id": "ab4c5d94",
+   "metadata": {
+    "collapsed": false,
+    "editable": true
+   },
    "outputs": [],
    "source": [
     "# Common imports\n",
@@ -2055,8 +2119,10 @@
   },
   {
    "cell_type": "markdown",
-   "id": "057df00a",
-   "metadata": {},
+   "id": "70c2a16d",
+   "metadata": {
+    "editable": true
+   },
    "source": [
     "## Computing the Gini Factor\n",
     "\n",
@@ -2071,8 +2137,11 @@
   {
    "cell_type": "code",
    "execution_count": 15,
-   "id": "f61bba68",
-   "metadata": {},
+   "id": "40e079d4",
+   "metadata": {
+    "collapsed": false,
+    "editable": true
+   },
    "outputs": [],
    "source": [
     "# Split a dataset based on an attribute and an attribute value\n",
@@ -2139,8 +2208,10 @@
   },
   {
    "cell_type": "markdown",
-   "id": "325254ba",
-   "metadata": {},
+   "id": "4095e4a7",
+   "metadata": {
+    "editable": true
+   },
    "source": [
     "## Entropy and the ID3 algorithm\n",
     "\n",
@@ -2176,8 +2247,10 @@
   },
   {
    "cell_type": "markdown",
-   "id": "d0a8f104",
-   "metadata": {},
+   "id": "ef376633",
+   "metadata": {
+    "editable": true
+   },
    "source": [
     "## Cancer Data again now with Decision Trees and other Methods"
    ]
@@ -2185,8 +2258,11 @@
   {
    "cell_type": "code",
    "execution_count": 16,
-   "id": "33b21353",
-   "metadata": {},
+   "id": "118884b2",
+   "metadata": {
+    "collapsed": false,
+    "editable": true
+   },
    "outputs": [],
    "source": [
     "import matplotlib.pyplot as plt\n",
@@ -2234,8 +2310,10 @@
   },
   {
    "cell_type": "markdown",
-   "id": "79890f5e",
-   "metadata": {},
+   "id": "fa9f54b6",
+   "metadata": {
+    "editable": true
+   },
    "source": [
     "## Another example, the moons again"
    ]
@@ -2243,8 +2321,11 @@
   {
    "cell_type": "code",
    "execution_count": 17,
-   "id": "57737ae7",
-   "metadata": {},
+   "id": "205c19aa",
+   "metadata": {
+    "collapsed": false,
+    "editable": true
+   },
    "outputs": [],
    "source": [
     "from __future__ import division, print_function, unicode_literals\n",
@@ -2315,8 +2396,10 @@
   },
   {
    "cell_type": "markdown",
-   "id": "1acbad4c",
-   "metadata": {},
+   "id": "3067d1e9",
+   "metadata": {
+    "editable": true
+   },
    "source": [
     "## Playing around with regions"
    ]
@@ -2324,8 +2407,11 @@
   {
    "cell_type": "code",
    "execution_count": 18,
-   "id": "50621c9c",
-   "metadata": {},
+   "id": "18ca2b62",
+   "metadata": {
+    "collapsed": false,
+    "editable": true
+   },
    "outputs": [],
    "source": [
     "np.random.seed(6)\n",
@@ -2352,8 +2438,10 @@
   },
   {
    "cell_type": "markdown",
-   "id": "5072fa2a",
-   "metadata": {},
+   "id": "3428a271",
+   "metadata": {
+    "editable": true
+   },
    "source": [
     "## Regression trees"
    ]
@@ -2361,8 +2449,11 @@
   {
    "cell_type": "code",
    "execution_count": 19,
-   "id": "27204e27",
-   "metadata": {},
+   "id": "2a8ee09c",
+   "metadata": {
+    "collapsed": false,
+    "editable": true
+   },
    "outputs": [],
    "source": [
     "# Quadratic training set + noise\n",
@@ -2376,8 +2467,11 @@
   {
    "cell_type": "code",
    "execution_count": 20,
-   "id": "09ea5bc1",
-   "metadata": {},
+   "id": "7bd7a8fe",
+   "metadata": {
+    "collapsed": false,
+    "editable": true
+   },
    "outputs": [],
    "source": [
     "from sklearn.tree import DecisionTreeRegressor\n",
@@ -2388,8 +2482,10 @@
   },
   {
    "cell_type": "markdown",
-   "id": "bbb6489c",
-   "metadata": {},
+   "id": "7cd9b121",
+   "metadata": {
+    "editable": true
+   },
    "source": [
     "## Final regressor code"
    ]
@@ -2397,8 +2493,11 @@
   {
    "cell_type": "code",
    "execution_count": 21,
-   "id": "a4b4d9fa",
-   "metadata": {},
+   "id": "9f73e61d",
+   "metadata": {
+    "collapsed": false,
+    "editable": true
+   },
    "outputs": [],
    "source": [
     "from sklearn.tree import DecisionTreeRegressor\n",
@@ -2444,8 +2543,11 @@
   {
    "cell_type": "code",
    "execution_count": 22,
-   "id": "6e37b0b9",
-   "metadata": {},
+   "id": "9217ab82",
+   "metadata": {
+    "collapsed": false,
+    "editable": true
+   },
    "outputs": [],
    "source": [
     "tree_reg1 = DecisionTreeRegressor(random_state=42)\n",
@@ -2480,8 +2582,10 @@
   },
   {
    "cell_type": "markdown",
-   "id": "a234b7c5",
-   "metadata": {},
+   "id": "0b3f13c6",
+   "metadata": {
+    "editable": true
+   },
    "source": [
     "## Pros and cons of trees, pros\n",
     "\n",
@@ -2502,8 +2606,10 @@
   },
   {
    "cell_type": "markdown",
-   "id": "7af4c5e9",
-   "metadata": {},
+   "id": "f0bbefac",
+   "metadata": {
+    "editable": true
+   },
    "source": [
     "## Disadvantages\n",
     "\n",
@@ -2528,8 +2634,10 @@
   },
   {
    "cell_type": "markdown",
-   "id": "cc2a7bf3",
-   "metadata": {},
+   "id": "e902924d",
+   "metadata": {
+    "editable": true
+   },
    "source": [
     "## Ensemble Methods: From a Single Tree to Many Trees and Extreme Boosting, Meet the Jungle of Methods\n",
     "\n",
@@ -2557,8 +2665,10 @@
   },
   {
    "cell_type": "markdown",
-   "id": "6dab3664",
-   "metadata": {},
+   "id": "73f6e3a6",
+   "metadata": {
+    "editable": true
+   },
    "source": [
     "## An Overview of Ensemble Methods\n",
     "\n",
@@ -2571,8 +2681,10 @@
   },
   {
    "cell_type": "markdown",
-   "id": "e124c92b",
-   "metadata": {},
+   "id": "4b2c2032",
+   "metadata": {
+    "editable": true
+   },
    "source": [
     "## Bagging\n",
     "\n",
@@ -2591,8 +2703,10 @@
   },
   {
    "cell_type": "markdown",
-   "id": "4b4e1bdc",
-   "metadata": {},
+   "id": "8bbfa991",
+   "metadata": {
+    "editable": true
+   },
    "source": [
     "## More bagging\n",
     "\n",
@@ -2621,8 +2735,10 @@
   },
   {
    "cell_type": "markdown",
-   "id": "88532ae8",
-   "metadata": {},
+   "id": "a0ee40c7",
+   "metadata": {
+    "editable": true
+   },
    "source": [
     "## Simple Voting Example, head or tail"
    ]
@@ -2630,8 +2746,11 @@
   {
    "cell_type": "code",
    "execution_count": 23,
-   "id": "323b85f3",
-   "metadata": {},
+   "id": "9d71a00f",
+   "metadata": {
+    "collapsed": false,
+    "editable": true
+   },
    "outputs": [],
    "source": [
     "heads_proba = 0.51\n",
@@ -2651,8 +2770,10 @@
   },
   {
    "cell_type": "markdown",
-   "id": "e6bb8780",
-   "metadata": {},
+   "id": "bd4ba90d",
+   "metadata": {
+    "editable": true
+   },
    "source": [
     "## Using the Voting Classifier"
    ]
@@ -2660,8 +2781,11 @@
   {
    "cell_type": "code",
    "execution_count": 24,
-   "id": "24db5c31",
-   "metadata": {},
+   "id": "d4c3e9d8",
+   "metadata": {
+    "collapsed": false,
+    "editable": true
+   },
    "outputs": [],
    "source": [
     "from sklearn.model_selection import train_test_split\n",
@@ -2711,8 +2835,10 @@
   },
   {
    "cell_type": "markdown",
-   "id": "6da7ff1c",
-   "metadata": {},
+   "id": "2a5acbf8",
+   "metadata": {
+    "editable": true
+   },
    "source": [
     "## Please, not the moons again! Voting and Bagging"
    ]
@@ -2720,8 +2846,11 @@
   {
    "cell_type": "code",
    "execution_count": 25,
-   "id": "01d8c987",
-   "metadata": {},
+   "id": "e1831a75",
+   "metadata": {
+    "collapsed": false,
+    "editable": true
+   },
    "outputs": [],
    "source": [
     "from sklearn.model_selection import train_test_split\n",
@@ -2747,8 +2876,11 @@
   {
    "cell_type": "code",
    "execution_count": 26,
-   "id": "c2060cb7",
-   "metadata": {},
+   "id": "793e7482",
+   "metadata": {
+    "collapsed": false,
+    "editable": true
+   },
    "outputs": [],
    "source": [
     "from sklearn.metrics import accuracy_score\n",
@@ -2762,8 +2894,11 @@
   {
    "cell_type": "code",
    "execution_count": 27,
-   "id": "49c1fcbc",
-   "metadata": {},
+   "id": "1f391b0d",
+   "metadata": {
+    "collapsed": false,
+    "editable": true
+   },
    "outputs": [],
    "source": [
     "log_clf = LogisticRegression(random_state=42)\n",
@@ -2779,8 +2914,11 @@
   {
    "cell_type": "code",
    "execution_count": 28,
-   "id": "fa9a8f7a",
-   "metadata": {},
+   "id": "4e3b40bb",
+   "metadata": {
+    "collapsed": false,
+    "editable": true
+   },
    "outputs": [],
    "source": [
     "from sklearn.metrics import accuracy_score\n",
@@ -2793,8 +2931,10 @@
   },
   {
    "cell_type": "markdown",
-   "id": "019149a3",
-   "metadata": {},
+   "id": "1180219b",
+   "metadata": {
+    "editable": true
+   },
    "source": [
     "## Bagging Examples"
    ]
@@ -2802,8 +2942,11 @@
   {
    "cell_type": "code",
    "execution_count": 29,
-   "id": "a02e00f8",
-   "metadata": {},
+   "id": "491ecd58",
+   "metadata": {
+    "collapsed": false,
+    "editable": true
+   },
    "outputs": [],
    "source": [
     "from sklearn.ensemble import BaggingClassifier\n",
@@ -2819,8 +2962,11 @@
   {
    "cell_type": "code",
    "execution_count": 30,
-   "id": "bc7e2764",
-   "metadata": {},
+   "id": "0ac9524d",
+   "metadata": {
+    "collapsed": false,
+    "editable": true
+   },
    "outputs": [],
    "source": [
     "from sklearn.metrics import accuracy_score\n",
@@ -2830,8 +2976,11 @@
   {
    "cell_type": "code",
    "execution_count": 31,
-   "id": "7bfa639b",
-   "metadata": {},
+   "id": "d335bc9a",
+   "metadata": {
+    "collapsed": false,
+    "editable": true
+   },
    "outputs": [],
    "source": [
     "tree_clf = DecisionTreeClassifier(random_state=42)\n",
@@ -2843,8 +2992,11 @@
   {
    "cell_type": "code",
    "execution_count": 32,
-   "id": "6c10e2e2",
-   "metadata": {},
+   "id": "a89a9e6d",
+   "metadata": {
+    "collapsed": false,
+    "editable": true
+   },
    "outputs": [],
    "source": [
     "from matplotlib.colors import ListedColormap\n",
@@ -2878,8 +3030,10 @@
   },
   {
    "cell_type": "markdown",
-   "id": "cd2e758f",
-   "metadata": {},
+   "id": "9fe3e801",
+   "metadata": {
+    "editable": true
+   },
    "source": [
     "## Making your own Bootstrap: Changing the Level of the Decision Tree\n",
     "\n",
@@ -2890,8 +3044,11 @@
   {
    "cell_type": "code",
    "execution_count": 33,
-   "id": "558a8eb8",
-   "metadata": {},
+   "id": "7b755579",
+   "metadata": {
+    "collapsed": false,
+    "editable": true
+   },
    "outputs": [],
    "source": [
     "\n",
@@ -2955,25 +3112,7 @@
    ]
   }
  ],
- "metadata": {
-  "kernelspec": {
-   "display_name": "Python 3",
-   "language": "python",
-   "name": "python3"
-  },
-  "language_info": {
-   "codemirror_mode": {
-    "name": "ipython",
-    "version": 3
-   },
-   "file_extension": ".py",
-   "mimetype": "text/x-python",
-   "name": "python",
-   "nbconvert_exporter": "python",
-   "pygments_lexer": "ipython3",
-   "version": "3.8.8"
-  }
- },
+ "metadata": {},
  "nbformat": 4,
  "nbformat_minor": 5
 }
diff --git a/doc/src/week44/week44.do.txt b/doc/src/week44/week44.do.txt
index 0f8a9588e..e37b16772 100644
--- a/doc/src/week44/week44.do.txt
+++ b/doc/src/week44/week44.do.txt
@@ -9,6 +9,7 @@ DATE: today
 * Thursday: Wrapping up PCA from last week, Clustering and basics of decision trees, classification and regression algorithms
   * "Video of Lecture":"https://www.uio.no/studier/emner/matnat/fys/FYS-STK3155/h21/forelesningsvideoer/LectureNovember4.mp4?vrtx=view-as-webpage"
 * Friday: Decision trees, voting models and bagging
+  * "Video of Lecture":"https://www.uio.no/studier/emner/matnat/fys/FYS-STK3155/h21/forelesningsvideoer/LectureNovember5.mp4?vrtx=view-as-webpage"
 
 !bblock Videos
 o "Video on Decision trees":"https://www.youtube.com/watch?v=RmajweUFKvM&ab_channel=Simplilearn"