diff --git a/doc/pub/week44/html/._week44-bs033.html b/doc/pub/week44/html/._week44-bs033.html
index 0c9950d88..499a798fb 100644
--- a/doc/pub/week44/html/._week44-bs033.html
+++ b/doc/pub/week44/html/._week44-bs033.html
@@ -349,20 +349,19 @@ infile = open# Read the experimental data with Pandas
from IPython.display import display
-grades = pd.read_csv(infile,names = ('Trend','Sleep','Studied','Grade'))
+grades = pd.read_csv(infile)
grades = pd.DataFrame(grades)
-
+display(grades)
# Features and targets
X = grades.loc[:, grades.columns != 'Grade'].values
y = grades.loc[:, grades.columns == 'Grade'].values
-
+print(X)
# Create the encoder.
encoder = OneHotEncoder(handle_unknown="ignore")
# Assume for simplicity all features are categorical.
encoder.fit(X)
# Apply the encoder.
X = encoder.transform(X)
-print(X)
# Then do a Classification tree
tree_clf = DecisionTreeClassifier(max_depth=2)
tree_clf.fit(X, y)
@@ -376,6 +375,10 @@ export_graphviz(
)
cmd = 'dot -Tpng DataFiles/grade.dot -o DataFiles/grades.png'
os.system(cmd)
+
+
+#data_pandas = pd.DataFrame(data,index=['Frodo','Bilbo','Aragorn','Sam'])
+#df.columns = ['First', 'Second', 'Third', 'Fourth', 'Fifth']
diff --git a/doc/pub/week44/html/week44-reveal.html b/doc/pub/week44/html/week44-reveal.html
index 5a9da24aa..bb43e0325 100644
--- a/doc/pub/week44/html/week44-reveal.html
+++ b/doc/pub/week44/html/week44-reveal.html
@@ -1127,20 +1127,19 @@ infile = open(data_path(# Read the experimental data with Pandas
from IPython.display import display
-grades = pd.read_csv(infile,names = ('Trend','Sleep','Studied','Grade'))
+grades = pd.read_csv(infile)
grades = pd.DataFrame(grades)
-
+display(grades)
# Features and targets
X = grades.loc[:, grades.columns != 'Grade'].values
y = grades.loc[:, grades.columns == 'Grade'].values
-
+print(X)
# Create the encoder.
encoder = OneHotEncoder(handle_unknown="ignore")
# Assume for simplicity all features are categorical.
encoder.fit(X)
# Apply the encoder.
X = encoder.transform(X)
-print(X)
# Then do a Classification tree
tree_clf = DecisionTreeClassifier(max_depth=2)
tree_clf.fit(X, y)
@@ -1154,6 +1153,10 @@ export_graphviz(
)
cmd = 'dot -Tpng DataFiles/grade.dot -o DataFiles/grades.png'
os.system(cmd)
+
+
+#data_pandas = pd.DataFrame(data,index=['Frodo','Bilbo','Aragorn','Sam'])
+#df.columns = ['First', 'Second', 'Third', 'Fourth', 'Fifth']
diff --git a/doc/pub/week44/html/week44-solarized.html b/doc/pub/week44/html/week44-solarized.html
index 287d68911..7635ffc80 100644
--- a/doc/pub/week44/html/week44-solarized.html
+++ b/doc/pub/week44/html/week44-solarized.html
@@ -1137,20 +1137,19 @@ infile = open(data_path(# Read the experimental data with Pandas
from IPython.display import display
-grades = pd.read_csv(infile,names = ('Trend','Sleep','Studied','Grade'))
+grades = pd.read_csv(infile)
grades = pd.DataFrame(grades)
-
+display(grades)
# Features and targets
X = grades.loc[:, grades.columns != 'Grade'].values
y = grades.loc[:, grades.columns == 'Grade'].values
-
+print(X)
# Create the encoder.
encoder = OneHotEncoder(handle_unknown="ignore")
# Assume for simplicity all features are categorical.
encoder.fit(X)
# Apply the encoder.
X = encoder.transform(X)
-print(X)
# Then do a Classification tree
tree_clf = DecisionTreeClassifier(max_depth=2)
tree_clf.fit(X, y)
@@ -1164,6 +1163,10 @@ export_graphviz(
)
cmd = 'dot -Tpng DataFiles/grade.dot -o DataFiles/grades.png'
os.system(cmd)
+
+
+#data_pandas = pd.DataFrame(data,index=['Frodo','Bilbo','Aragorn','Sam'])
+#df.columns = ['First', 'Second', 'Third', 'Fourth', 'Fifth']
diff --git a/doc/pub/week44/html/week44.html b/doc/pub/week44/html/week44.html
index c4bc91cef..e7c71a386 100644
--- a/doc/pub/week44/html/week44.html
+++ b/doc/pub/week44/html/week44.html
@@ -1214,20 +1214,19 @@ infile = open# Read the experimental data with Pandas
from IPython.display import display
-grades = pd.read_csv(infile,names = ('Trend','Sleep','Studied','Grade'))
+grades = pd.read_csv(infile)
grades = pd.DataFrame(grades)
-
+display(grades)
# Features and targets
X = grades.loc[:, grades.columns != 'Grade'].values
y = grades.loc[:, grades.columns == 'Grade'].values
-
+print(X)
# Create the encoder.
encoder = OneHotEncoder(handle_unknown="ignore")
# Assume for simplicity all features are categorical.
encoder.fit(X)
# Apply the encoder.
X = encoder.transform(X)
-print(X)
# Then do a Classification tree
tree_clf = DecisionTreeClassifier(max_depth=2)
tree_clf.fit(X, y)
@@ -1241,6 +1240,10 @@ export_graphviz(
)
cmd = 'dot -Tpng DataFiles/grade.dot -o DataFiles/grades.png'
os.system(cmd)
+
+
+#data_pandas = pd.DataFrame(data,index=['Frodo','Bilbo','Aragorn','Sam'])
+#df.columns = ['First', 'Second', 'Third', 'Fourth', 'Fifth']
diff --git a/doc/pub/week44/ipynb/Datafiles/cancer.dot b/doc/pub/week44/ipynb/Datafiles/cancer.dot
index 75af04abe..51d41287e 100644
--- a/doc/pub/week44/ipynb/Datafiles/cancer.dot
+++ b/doc/pub/week44/ipynb/Datafiles/cancer.dot
@@ -6,17 +6,17 @@ edge [fontname="helvetica"] ;
0 -> 1 [labeldistance=2.5, labelangle=45, headlabel="True"] ;
2 [label="worst concave points <= 0.135\ngini = 0.031\nsamples = 253\nvalue = [[249, 4]\n[4, 249]]", fillcolor="#e78946"] ;
1 -> 2 ;
-3 [label="area error <= 48.975\ngini = 0.008\nsamples = 242\nvalue = [[241, 1]\n[1, 241]]", fillcolor="#e5833c"] ;
+3 [label="radius error <= 0.643\ngini = 0.008\nsamples = 242\nvalue = [[241, 1]\n[1, 241]]", fillcolor="#e5833c"] ;
2 -> 3 ;
4 [label="gini = 0.0\nsamples = 239\nvalue = [[239, 0]\n[0, 239]]", fillcolor="#e58139"] ;
3 -> 4 ;
-5 [label="perimeter error <= 4.249\ngini = 0.444\nsamples = 3\nvalue = [[2, 1]\n[1, 2]]", fillcolor="#fdf6f0"] ;
+5 [label="worst compactness <= 0.085\ngini = 0.444\nsamples = 3\nvalue = [[2, 1]\n[1, 2]]", fillcolor="#fdf6f0"] ;
3 -> 5 ;
6 [label="gini = 0.0\nsamples = 1\nvalue = [[0, 1]\n[1, 0]]", fillcolor="#e58139"] ;
5 -> 6 ;
7 [label="gini = 0.0\nsamples = 2\nvalue = [[2, 0]\n[0, 2]]", fillcolor="#e58139"] ;
5 -> 7 ;
-8 [label="mean texture <= 20.84\ngini = 0.397\nsamples = 11\nvalue = [[8, 3]\n[3, 8]]", fillcolor="#fae9dd"] ;
+8 [label="worst texture <= 29.455\ngini = 0.397\nsamples = 11\nvalue = [[8, 3]\n[3, 8]]", fillcolor="#fae9dd"] ;
2 -> 8 ;
9 [label="gini = 0.0\nsamples = 8\nvalue = [[8, 0]\n[0, 8]]", fillcolor="#e58139"] ;
8 -> 9 ;
@@ -34,7 +34,7 @@ edge [fontname="helvetica"] ;
14 -> 15 ;
16 [label="gini = 0.0\nsamples = 11\nvalue = [[11, 0]\n[0, 11]]", fillcolor="#e58139"] ;
15 -> 16 ;
-17 [label="mean smoothness <= 0.086\ngini = 0.32\nsamples = 5\nvalue = [[1, 4]\n[4, 1]]", fillcolor="#f6d5bd"] ;
+17 [label="smoothness error <= 0.005\ngini = 0.32\nsamples = 5\nvalue = [[1, 4]\n[4, 1]]", fillcolor="#f6d5bd"] ;
15 -> 17 ;
18 [label="gini = 0.0\nsamples = 1\nvalue = [[1, 0]\n[0, 1]]", fillcolor="#e58139"] ;
17 -> 18 ;
diff --git a/doc/pub/week44/ipynb/Datafiles/cancer.png b/doc/pub/week44/ipynb/Datafiles/cancer.png
index c0f1f7548..1edd37c90 100644
Binary files a/doc/pub/week44/ipynb/Datafiles/cancer.png and b/doc/pub/week44/ipynb/Datafiles/cancer.png differ
diff --git a/doc/pub/week44/ipynb/Datafiles/ride.dot b/doc/pub/week44/ipynb/Datafiles/ride.dot
index 4e3b65b18..2772fde19 100644
--- a/doc/pub/week44/ipynb/Datafiles/ride.dot
+++ b/doc/pub/week44/ipynb/Datafiles/ride.dot
@@ -1,7 +1,7 @@
digraph Tree {
node [shape=box, style="filled, rounded", color="black", fontname="helvetica"] ;
edge [fontname="helvetica"] ;
-0 [label="X[9] <= 0.5\ngini = 0.48\nsamples = 15\nvalue = [4, 10, 1]", fillcolor="#93f1ba"] ;
+0 [label="X[0] <= 0.5\ngini = 0.48\nsamples = 15\nvalue = [4, 10, 1]", fillcolor="#93f1ba"] ;
1 [label="X[1] <= 0.5\ngini = 0.408\nsamples = 14\nvalue = [4, 10, 0]", fillcolor="#88efb3"] ;
0 -> 1 [labeldistance=2.5, labelangle=45, headlabel="True"] ;
2 [label="gini = 0.48\nsamples = 10\nvalue = [4, 6, 0]", fillcolor="#bdf6d5"] ;
diff --git a/doc/pub/week44/ipynb/ipynb-week44-src.tar.gz b/doc/pub/week44/ipynb/ipynb-week44-src.tar.gz
index 5649744c5..4c52e88e6 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 7c8c7a8ee..8b5e8ac61 100644
--- a/doc/pub/week44/ipynb/week44.ipynb
+++ b/doc/pub/week44/ipynb/week44.ipynb
@@ -2,7 +2,7 @@
"cells": [
{
"cell_type": "markdown",
- "id": "d98e2322",
+ "id": "303fdfce",
"metadata": {
"editable": true
},
@@ -14,7 +14,7 @@
},
{
"cell_type": "markdown",
- "id": "9f95d00e",
+ "id": "89424210",
"metadata": {
"editable": true
},
@@ -29,7 +29,7 @@
},
{
"cell_type": "markdown",
- "id": "1c3184d8",
+ "id": "6177c33f",
"metadata": {
"editable": true
},
@@ -51,7 +51,7 @@
},
{
"cell_type": "markdown",
- "id": "03088d75",
+ "id": "07e99622",
"metadata": {
"editable": true
},
@@ -69,7 +69,7 @@
},
{
"cell_type": "markdown",
- "id": "fb46f0fc",
+ "id": "cec56cc9",
"metadata": {
"editable": true
},
@@ -100,7 +100,7 @@
},
{
"cell_type": "markdown",
- "id": "9acd9dda",
+ "id": "7d8a5e44",
"metadata": {
"editable": true
},
@@ -120,7 +120,7 @@
},
{
"cell_type": "markdown",
- "id": "719a8716",
+ "id": "23a71044",
"metadata": {
"editable": true
},
@@ -134,7 +134,7 @@
},
{
"cell_type": "markdown",
- "id": "6b490bb8",
+ "id": "f241ee74",
"metadata": {
"editable": true
},
@@ -147,7 +147,7 @@
},
{
"cell_type": "markdown",
- "id": "4cb44801",
+ "id": "c428c3b2",
"metadata": {
"editable": true
},
@@ -165,7 +165,7 @@
},
{
"cell_type": "markdown",
- "id": "c17529d5",
+ "id": "b340bd77",
"metadata": {
"editable": true
},
@@ -188,7 +188,7 @@
},
{
"cell_type": "markdown",
- "id": "feb8f6fe",
+ "id": "94c90118",
"metadata": {
"editable": true
},
@@ -211,7 +211,7 @@
},
{
"cell_type": "markdown",
- "id": "5890974d",
+ "id": "c8d71b3f",
"metadata": {
"editable": true
},
@@ -222,7 +222,7 @@
{
"cell_type": "code",
"execution_count": 1,
- "id": "e08d6fa8",
+ "id": "287a7d14",
"metadata": {
"collapsed": false,
"editable": true
@@ -323,7 +323,7 @@
},
{
"cell_type": "markdown",
- "id": "d1daa9c8",
+ "id": "5f44ba61",
"metadata": {
"editable": true
},
@@ -345,7 +345,7 @@
},
{
"cell_type": "markdown",
- "id": "92c73b5a",
+ "id": "76e979a6",
"metadata": {
"editable": true
},
@@ -357,7 +357,7 @@
},
{
"cell_type": "markdown",
- "id": "1e70c569",
+ "id": "79c449fe",
"metadata": {
"editable": true
},
@@ -368,7 +368,7 @@
},
{
"cell_type": "markdown",
- "id": "176bf038",
+ "id": "ea2d207a",
"metadata": {
"editable": true
},
@@ -390,7 +390,7 @@
},
{
"cell_type": "markdown",
- "id": "ad3b71cb",
+ "id": "721908c8",
"metadata": {
"editable": true
},
@@ -403,7 +403,7 @@
},
{
"cell_type": "markdown",
- "id": "5e4c164d",
+ "id": "c47e1ef0",
"metadata": {
"editable": true
},
@@ -415,7 +415,7 @@
},
{
"cell_type": "markdown",
- "id": "89190413",
+ "id": "15b9c732",
"metadata": {
"editable": true
},
@@ -425,7 +425,7 @@
},
{
"cell_type": "markdown",
- "id": "8b31354c",
+ "id": "ef0dc96b",
"metadata": {
"editable": true
},
@@ -437,7 +437,7 @@
},
{
"cell_type": "markdown",
- "id": "f242d32e",
+ "id": "52ddf624",
"metadata": {
"editable": true
},
@@ -447,7 +447,7 @@
},
{
"cell_type": "markdown",
- "id": "aaa6c9de",
+ "id": "e87adb62",
"metadata": {
"editable": true
},
@@ -459,7 +459,7 @@
},
{
"cell_type": "markdown",
- "id": "dbd78a2f",
+ "id": "e5288f89",
"metadata": {
"editable": true
},
@@ -492,7 +492,7 @@
},
{
"cell_type": "markdown",
- "id": "b2cef5e6",
+ "id": "03cdba4b",
"metadata": {
"editable": true
},
@@ -516,7 +516,7 @@
},
{
"cell_type": "markdown",
- "id": "bd447e07",
+ "id": "7f3cca97",
"metadata": {
"editable": true
},
@@ -528,7 +528,7 @@
},
{
"cell_type": "markdown",
- "id": "7a6cc693",
+ "id": "81908085",
"metadata": {
"editable": true
},
@@ -540,7 +540,7 @@
},
{
"cell_type": "markdown",
- "id": "5ca7a58b",
+ "id": "00b84717",
"metadata": {
"editable": true
},
@@ -568,7 +568,7 @@
},
{
"cell_type": "markdown",
- "id": "dc2385e7",
+ "id": "9cb838a8",
"metadata": {
"editable": true
},
@@ -594,7 +594,7 @@
},
{
"cell_type": "markdown",
- "id": "61fb7288",
+ "id": "c77af063",
"metadata": {
"editable": true
},
@@ -617,7 +617,7 @@
},
{
"cell_type": "markdown",
- "id": "9a02c899",
+ "id": "ab9b5809",
"metadata": {
"editable": true
},
@@ -644,7 +644,7 @@
},
{
"cell_type": "markdown",
- "id": "15a2080f",
+ "id": "237b53b5",
"metadata": {
"editable": true
},
@@ -663,7 +663,7 @@
},
{
"cell_type": "markdown",
- "id": "35093975",
+ "id": "7f0692e9",
"metadata": {
"editable": true
},
@@ -675,7 +675,7 @@
},
{
"cell_type": "markdown",
- "id": "eca91c0b",
+ "id": "96b4cc20",
"metadata": {
"editable": true
},
@@ -688,7 +688,7 @@
},
{
"cell_type": "markdown",
- "id": "5efd9a2b",
+ "id": "3c47a735",
"metadata": {
"editable": true
},
@@ -700,7 +700,7 @@
},
{
"cell_type": "markdown",
- "id": "772f8fad",
+ "id": "668bb7e6",
"metadata": {
"editable": true
},
@@ -710,7 +710,7 @@
},
{
"cell_type": "markdown",
- "id": "015e0c30",
+ "id": "c5bd680f",
"metadata": {
"editable": true
},
@@ -722,7 +722,7 @@
},
{
"cell_type": "markdown",
- "id": "e483d862",
+ "id": "b83d5433",
"metadata": {
"editable": true
},
@@ -732,7 +732,7 @@
},
{
"cell_type": "markdown",
- "id": "76daf24d",
+ "id": "4f78a0fe",
"metadata": {
"editable": true
},
@@ -744,7 +744,7 @@
},
{
"cell_type": "markdown",
- "id": "20ce5b46",
+ "id": "a440adc9",
"metadata": {
"editable": true
},
@@ -755,7 +755,7 @@
{
"cell_type": "code",
"execution_count": 2,
- "id": "1eccbfd3",
+ "id": "6e4efeb9",
"metadata": {
"collapsed": false,
"editable": true
@@ -799,7 +799,7 @@
},
{
"cell_type": "markdown",
- "id": "bcb30334",
+ "id": "0006059d",
"metadata": {
"editable": true
},
@@ -810,7 +810,7 @@
{
"cell_type": "code",
"execution_count": 3,
- "id": "372ae619",
+ "id": "2600e2b7",
"metadata": {
"collapsed": false,
"editable": true
@@ -845,7 +845,7 @@
},
{
"cell_type": "markdown",
- "id": "754e81f0",
+ "id": "545efc0a",
"metadata": {
"editable": true
},
@@ -858,7 +858,7 @@
{
"cell_type": "code",
"execution_count": 4,
- "id": "db2ea071",
+ "id": "a67593ad",
"metadata": {
"collapsed": false,
"editable": true
@@ -876,7 +876,7 @@
},
{
"cell_type": "markdown",
- "id": "35af5b50",
+ "id": "784a8c90",
"metadata": {
"editable": true
},
@@ -890,7 +890,7 @@
{
"cell_type": "code",
"execution_count": 5,
- "id": "95a27cb4",
+ "id": "98309efc",
"metadata": {
"collapsed": false,
"editable": true
@@ -909,7 +909,7 @@
},
{
"cell_type": "markdown",
- "id": "fe5fc8fd",
+ "id": "800d4fd7",
"metadata": {
"editable": true
},
@@ -929,7 +929,7 @@
},
{
"cell_type": "markdown",
- "id": "3c2850c2",
+ "id": "a783a947",
"metadata": {
"editable": true
},
@@ -946,7 +946,7 @@
},
{
"cell_type": "markdown",
- "id": "f28005ca",
+ "id": "d9c975db",
"metadata": {
"editable": true
},
@@ -958,7 +958,7 @@
},
{
"cell_type": "markdown",
- "id": "09b3ddeb",
+ "id": "56c0aa6d",
"metadata": {
"editable": true
},
@@ -975,7 +975,7 @@
},
{
"cell_type": "markdown",
- "id": "58611816",
+ "id": "3f47228e",
"metadata": {
"editable": true
},
@@ -988,7 +988,7 @@
},
{
"cell_type": "markdown",
- "id": "2d49e0d6",
+ "id": "9b713480",
"metadata": {
"editable": true
},
@@ -1000,7 +1000,7 @@
},
{
"cell_type": "markdown",
- "id": "a0aba8b0",
+ "id": "9bda577d",
"metadata": {
"editable": true
},
@@ -1010,7 +1010,7 @@
},
{
"cell_type": "markdown",
- "id": "3837f01d",
+ "id": "d2af50de",
"metadata": {
"editable": true
},
@@ -1022,7 +1022,7 @@
},
{
"cell_type": "markdown",
- "id": "ffd106d5",
+ "id": "eff1087c",
"metadata": {
"editable": true
},
@@ -1032,7 +1032,7 @@
},
{
"cell_type": "markdown",
- "id": "4e9a3380",
+ "id": "6a4fcf67",
"metadata": {
"editable": true
},
@@ -1044,7 +1044,7 @@
},
{
"cell_type": "markdown",
- "id": "2c98346f",
+ "id": "0af59d3c",
"metadata": {
"editable": true
},
@@ -1057,7 +1057,7 @@
},
{
"cell_type": "markdown",
- "id": "5af6dd83",
+ "id": "36d5b7e1",
"metadata": {
"editable": true
},
@@ -1072,7 +1072,7 @@
},
{
"cell_type": "markdown",
- "id": "049c6c06",
+ "id": "ff15cbfd",
"metadata": {
"editable": true
},
@@ -1098,7 +1098,7 @@
},
{
"cell_type": "markdown",
- "id": "d28ee51e",
+ "id": "6fda730a",
"metadata": {
"editable": true
},
@@ -1126,7 +1126,7 @@
},
{
"cell_type": "markdown",
- "id": "9aedec9e",
+ "id": "91027fc4",
"metadata": {
"editable": true
},
@@ -1143,7 +1143,7 @@
},
{
"cell_type": "markdown",
- "id": "249904b8",
+ "id": "d0e22658",
"metadata": {
"editable": true
},
@@ -1157,7 +1157,7 @@
},
{
"cell_type": "markdown",
- "id": "ffc84821",
+ "id": "fbf239d1",
"metadata": {
"editable": true
},
@@ -1173,7 +1173,7 @@
},
{
"cell_type": "markdown",
- "id": "aaef2ea7",
+ "id": "7ba39338",
"metadata": {
"editable": true
},
@@ -1184,7 +1184,7 @@
{
"cell_type": "code",
"execution_count": 6,
- "id": "985f7f61",
+ "id": "6c1105f2",
"metadata": {
"collapsed": false,
"editable": true
@@ -1231,20 +1231,19 @@
"\n",
"# Read the experimental data with Pandas\n",
"from IPython.display import display\n",
- "grades = pd.read_csv(infile,names = ('Trend','Sleep','Studied','Grade'))\n",
+ "grades = pd.read_csv(infile)\n",
"grades = pd.DataFrame(grades)\n",
- "\n",
+ "display(grades)\n",
"# Features and targets\n",
"X = grades.loc[:, grades.columns != 'Grade'].values\n",
"y = grades.loc[:, grades.columns == 'Grade'].values\n",
- "\n",
+ "print(X)\n",
"# Create the encoder.\n",
"encoder = OneHotEncoder(handle_unknown=\"ignore\")\n",
"# Assume for simplicity all features are categorical.\n",
"encoder.fit(X) \n",
"# Apply the encoder.\n",
"X = encoder.transform(X)\n",
- "print(X)\n",
"# Then do a Classification tree\n",
"tree_clf = DecisionTreeClassifier(max_depth=2)\n",
"tree_clf.fit(X, y)\n",
@@ -1257,12 +1256,16 @@
" filled=True\n",
")\n",
"cmd = 'dot -Tpng DataFiles/grade.dot -o DataFiles/grades.png'\n",
- "os.system(cmd)"
+ "os.system(cmd)\n",
+ "\n",
+ "\n",
+ "#data_pandas = pd.DataFrame(data,index=['Frodo','Bilbo','Aragorn','Sam'])\n",
+ "#df.columns = ['First', 'Second', 'Third', 'Fourth', 'Fifth']"
]
},
{
"cell_type": "markdown",
- "id": "9255005b",
+ "id": "d902592f",
"metadata": {
"editable": true
},
@@ -1306,7 +1309,7 @@
},
{
"cell_type": "markdown",
- "id": "3e22f450",
+ "id": "63daa840",
"metadata": {
"editable": true
},
@@ -1317,7 +1320,7 @@
{
"cell_type": "code",
"execution_count": 7,
- "id": "a760bd54",
+ "id": "25b57fe3",
"metadata": {
"collapsed": false,
"editable": true
@@ -1395,7 +1398,7 @@
},
{
"cell_type": "markdown",
- "id": "7e0995e4",
+ "id": "c82a4c31",
"metadata": {
"editable": true
},
@@ -1413,7 +1416,7 @@
{
"cell_type": "code",
"execution_count": 8,
- "id": "52b6994b",
+ "id": "66b02746",
"metadata": {
"collapsed": false,
"editable": true
@@ -1484,7 +1487,7 @@
},
{
"cell_type": "markdown",
- "id": "08d47f8e",
+ "id": "dde9cc81",
"metadata": {
"editable": true
},
@@ -1495,7 +1498,7 @@
{
"cell_type": "code",
"execution_count": 9,
- "id": "e7bb262f",
+ "id": "3891adc6",
"metadata": {
"collapsed": false,
"editable": true
@@ -1570,7 +1573,7 @@
},
{
"cell_type": "markdown",
- "id": "253c4fc0",
+ "id": "20e12c6d",
"metadata": {
"editable": true
},
@@ -1581,7 +1584,7 @@
{
"cell_type": "code",
"execution_count": 10,
- "id": "90b7f896",
+ "id": "937ee4a0",
"metadata": {
"collapsed": false,
"editable": true
@@ -1612,7 +1615,7 @@
},
{
"cell_type": "markdown",
- "id": "48e28e54",
+ "id": "05262e92",
"metadata": {
"editable": true
},
@@ -1623,7 +1626,7 @@
{
"cell_type": "code",
"execution_count": 11,
- "id": "1c4239fe",
+ "id": "2f5aa1d2",
"metadata": {
"collapsed": false,
"editable": true
@@ -1641,7 +1644,7 @@
{
"cell_type": "code",
"execution_count": 12,
- "id": "31178820",
+ "id": "d0431be6",
"metadata": {
"collapsed": false,
"editable": true
@@ -1656,7 +1659,7 @@
},
{
"cell_type": "markdown",
- "id": "dd6a7eaa",
+ "id": "b7efc61a",
"metadata": {
"editable": true
},
@@ -1667,7 +1670,7 @@
{
"cell_type": "code",
"execution_count": 13,
- "id": "079592b6",
+ "id": "5c00cb35",
"metadata": {
"collapsed": false,
"editable": true
@@ -1717,7 +1720,7 @@
{
"cell_type": "code",
"execution_count": 14,
- "id": "96eaa015",
+ "id": "03b39894",
"metadata": {
"collapsed": false,
"editable": true
@@ -1756,7 +1759,7 @@
},
{
"cell_type": "markdown",
- "id": "84fe3854",
+ "id": "d71f0ce9",
"metadata": {
"editable": true
},
@@ -1780,7 +1783,7 @@
},
{
"cell_type": "markdown",
- "id": "187d746e",
+ "id": "4ad744d7",
"metadata": {
"editable": true
},
@@ -1808,7 +1811,7 @@
},
{
"cell_type": "markdown",
- "id": "aeb79b8e",
+ "id": "919de051",
"metadata": {
"editable": true
},
@@ -1839,7 +1842,7 @@
},
{
"cell_type": "markdown",
- "id": "928bbe7b",
+ "id": "b2e868f1",
"metadata": {
"editable": true
},
@@ -1855,7 +1858,7 @@
},
{
"cell_type": "markdown",
- "id": "73027143",
+ "id": "e790cf95",
"metadata": {
"editable": true
},
@@ -1879,7 +1882,7 @@
},
{
"cell_type": "markdown",
- "id": "18f0c929",
+ "id": "9cd3580f",
"metadata": {
"editable": true
},
@@ -1910,7 +1913,7 @@
},
{
"cell_type": "markdown",
- "id": "ccef5549",
+ "id": "47969bcd",
"metadata": {
"editable": true
},
@@ -1921,7 +1924,7 @@
{
"cell_type": "code",
"execution_count": 15,
- "id": "e229b9ba",
+ "id": "67de73ef",
"metadata": {
"collapsed": false,
"editable": true
@@ -1969,7 +1972,7 @@
},
{
"cell_type": "markdown",
- "id": "b3767e7c",
+ "id": "606e8c8e",
"metadata": {
"editable": true
},
@@ -1980,7 +1983,7 @@
{
"cell_type": "code",
"execution_count": 16,
- "id": "afb5135b",
+ "id": "b107a1cf",
"metadata": {
"collapsed": false,
"editable": true
@@ -2014,7 +2017,7 @@
},
{
"cell_type": "markdown",
- "id": "a472c59e",
+ "id": "6abdb36a",
"metadata": {
"editable": true
},
@@ -2027,7 +2030,7 @@
{
"cell_type": "code",
"execution_count": 17,
- "id": "6c1dd58b",
+ "id": "00bce4fc",
"metadata": {
"collapsed": false,
"editable": true
@@ -2080,7 +2083,7 @@
},
{
"cell_type": "markdown",
- "id": "40f4a4b7",
+ "id": "dbbf0823",
"metadata": {
"editable": true
},
@@ -2091,7 +2094,7 @@
{
"cell_type": "code",
"execution_count": 18,
- "id": "c853270d",
+ "id": "deee652c",
"metadata": {
"collapsed": false,
"editable": true
@@ -2121,7 +2124,7 @@
{
"cell_type": "code",
"execution_count": 19,
- "id": "0bbadee8",
+ "id": "4f831127",
"metadata": {
"collapsed": false,
"editable": true
@@ -2139,7 +2142,7 @@
{
"cell_type": "code",
"execution_count": 20,
- "id": "64392209",
+ "id": "4f0ede67",
"metadata": {
"collapsed": false,
"editable": true
@@ -2159,7 +2162,7 @@
{
"cell_type": "code",
"execution_count": 21,
- "id": "462868aa",
+ "id": "a6234319",
"metadata": {
"collapsed": false,
"editable": true
@@ -2176,7 +2179,7 @@
},
{
"cell_type": "markdown",
- "id": "c7cc4f29",
+ "id": "27964504",
"metadata": {
"editable": true
},
@@ -2198,7 +2201,7 @@
},
{
"cell_type": "markdown",
- "id": "2b2ce4e3",
+ "id": "a014fe49",
"metadata": {
"editable": true
},
@@ -2230,7 +2233,7 @@
},
{
"cell_type": "markdown",
- "id": "35e0799b",
+ "id": "44189d88",
"metadata": {
"editable": true
},
@@ -2244,7 +2247,7 @@
{
"cell_type": "code",
"execution_count": 22,
- "id": "08fb064e",
+ "id": "3d81803f",
"metadata": {
"collapsed": false,
"editable": true
@@ -2313,7 +2316,7 @@
},
{
"cell_type": "markdown",
- "id": "0d70c652",
+ "id": "1eabd234",
"metadata": {
"editable": true
},
@@ -2336,7 +2339,7 @@
},
{
"cell_type": "markdown",
- "id": "c2b8b4e1",
+ "id": "d39aa2d2",
"metadata": {
"editable": true
},
@@ -2348,7 +2351,7 @@
},
{
"cell_type": "markdown",
- "id": "88dd33a9",
+ "id": "c5d99442",
"metadata": {
"editable": true
},
@@ -2373,7 +2376,7 @@
},
{
"cell_type": "markdown",
- "id": "bc8aefa6",
+ "id": "5e11503c",
"metadata": {
"editable": true
},
@@ -2399,7 +2402,7 @@
},
{
"cell_type": "markdown",
- "id": "8d897dc6",
+ "id": "3af7a38e",
"metadata": {
"editable": true
},
@@ -2410,7 +2413,7 @@
{
"cell_type": "code",
"execution_count": 23,
- "id": "6fc7304c",
+ "id": "d8858b60",
"metadata": {
"collapsed": false,
"editable": true
@@ -2482,7 +2485,7 @@
},
{
"cell_type": "markdown",
- "id": "d0f24483",
+ "id": "19019bbb",
"metadata": {
"editable": true
},
@@ -2498,7 +2501,7 @@
},
{
"cell_type": "markdown",
- "id": "be364340",
+ "id": "c7f1b6d0",
"metadata": {
"editable": true
},
@@ -2509,7 +2512,7 @@
{
"cell_type": "code",
"execution_count": 24,
- "id": "fc9dfe70",
+ "id": "62a22d27",
"metadata": {
"collapsed": false,
"editable": true
@@ -2524,7 +2527,7 @@
{
"cell_type": "code",
"execution_count": 25,
- "id": "27fe4303",
+ "id": "3943a3d6",
"metadata": {
"collapsed": false,
"editable": true
diff --git a/doc/src/week44/Programs/DataFiles/grade.dot b/doc/src/week44/Programs/DataFiles/grade.dot
new file mode 100644
index 000000000..dfcc5ea10
--- /dev/null
+++ b/doc/src/week44/Programs/DataFiles/grade.dot
@@ -0,0 +1,13 @@
+digraph Tree {
+node [shape=box, style="filled, rounded", color="black", fontname="helvetica"] ;
+edge [fontname="helvetica"] ;
+0 [label="X[0] <= 0.5\ngini = 0.48\nsamples = 10\nvalue = [6, 4]", fillcolor="#f6d5bd"] ;
+1 [label="X[5] <= 0.5\ngini = 0.444\nsamples = 6\nvalue = [2, 4]", fillcolor="#9ccef2"] ;
+0 -> 1 [labeldistance=2.5, labelangle=45, headlabel="True"] ;
+2 [label="gini = 0.0\nsamples = 2\nvalue = [2, 0]", fillcolor="#e58139"] ;
+1 -> 2 ;
+3 [label="gini = 0.0\nsamples = 4\nvalue = [0, 4]", fillcolor="#399de5"] ;
+1 -> 3 ;
+4 [label="gini = 0.0\nsamples = 4\nvalue = [4, 0]", fillcolor="#e58139"] ;
+0 -> 4 [labeldistance=2.5, labelangle=-45, headlabel="False"] ;
+}
\ No newline at end of file
diff --git a/doc/src/week44/Programs/DataFiles/grades.csv b/doc/src/week44/Programs/DataFiles/grades.csv
new file mode 100644
index 000000000..2f3e97e30
--- /dev/null
+++ b/doc/src/week44/Programs/DataFiles/grades.csv
@@ -0,0 +1,13 @@
+Trend,Sleep,Studied,Grade
+1,0,1,1
+0,1,0,0
+1,0,1,1
+1,1,1,1
+0,0,1,0
+1,0,0,0
+0,1,1,0
+0,0,1,0
+1,0,0,0
+1,1,1,1
+
+
diff --git a/doc/src/week44/Programs/DataFiles/grades.png b/doc/src/week44/Programs/DataFiles/grades.png
new file mode 100644
index 000000000..aa8851b18
Binary files /dev/null and b/doc/src/week44/Programs/DataFiles/grades.png differ
diff --git a/doc/src/week44/Programs/grades.csv b/doc/src/week44/Programs/grades.csv
new file mode 100644
index 000000000..634017e6e
--- /dev/null
+++ b/doc/src/week44/Programs/grades.csv
@@ -0,0 +1,13 @@
+Trend,Sleep,Studied,Grade,
+1,0,1,1,
+0,1,0,0,
+1,0,1,1,
+1,1,1,1,
+0,0,1,0,
+1,0,0,0,
+0,1,1,0,
+0,0,1,0,
+1,0,0,0,
+1,1,1,1,
+
+
diff --git a/doc/src/week44/Programs/grades.py b/doc/src/week44/Programs/grades.py
new file mode 100644
index 000000000..fc8f00c38
--- /dev/null
+++ b/doc/src/week44/Programs/grades.py
@@ -0,0 +1,70 @@
+# Common imports
+import numpy as np
+import pandas as pd
+import matplotlib.pyplot as plt
+from sklearn.tree import DecisionTreeClassifier
+from sklearn.model_selection import train_test_split
+from sklearn.tree import export_graphviz
+from sklearn.preprocessing import StandardScaler, OneHotEncoder
+from sklearn.compose import ColumnTransformer
+from IPython.display import Image
+from pydot import graph_from_dot_data
+import os
+
+# Where to save the figures and data files
+PROJECT_ROOT_DIR = "Results"
+FIGURE_ID = "Results/FigureFiles"
+DATA_ID = "DataFiles/"
+
+if not os.path.exists(PROJECT_ROOT_DIR):
+ os.mkdir(PROJECT_ROOT_DIR)
+
+if not os.path.exists(FIGURE_ID):
+ os.makedirs(FIGURE_ID)
+
+if not os.path.exists(DATA_ID):
+ os.makedirs(DATA_ID)
+
+def image_path(fig_id):
+ return os.path.join(FIGURE_ID, fig_id)
+
+def data_path(dat_id):
+ return os.path.join(DATA_ID, dat_id)
+
+def save_fig(fig_id):
+ plt.savefig(image_path(fig_id) + ".png", format='png')
+
+infile = open(data_path("grades.csv"),'r')
+
+# Read the experimental data with Pandas
+from IPython.display import display
+grades = pd.read_csv(infile)#, names = ('Trend','Sleep','Studied','Grade'))
+grades = pd.DataFrame(grades)
+display(grades)
+# Features and targets
+X = grades.loc[:, grades.columns != 'Grade'].values
+y = grades.loc[:, grades.columns == 'Grade'].values
+print(X)
+# Create the encoder.
+encoder = OneHotEncoder(handle_unknown="ignore")
+# Assume for simplicity all features are categorical.
+encoder.fit(X)
+# Apply the encoder.
+X = encoder.transform(X)
+# Then do a Classification tree
+tree_clf = DecisionTreeClassifier(max_depth=2)
+tree_clf.fit(X, y)
+print("Train set accuracy with Decision Tree: {:.2f}".format(tree_clf.score(X,y)))
+#transfer to a decision tree graph
+export_graphviz(
+ tree_clf,
+ out_file="DataFiles/grade.dot",
+ rounded=True,
+ filled=True
+)
+cmd = 'dot -Tpng DataFiles/grade.dot -o DataFiles/grades.png'
+os.system(cmd)
+
+
+#data_pandas = pd.DataFrame(data,index=['Frodo','Bilbo','Aragorn','Sam'])
+#df.columns = ['First', 'Second', 'Third', 'Fourth', 'Fifth']
diff --git a/doc/src/week44/week44.do.txt b/doc/src/week44/week44.do.txt
index f6dc433a1..9b7c7063e 100644
--- a/doc/src/week44/week44.do.txt
+++ b/doc/src/week44/week44.do.txt
@@ -734,20 +734,19 @@ infile = open(data_path("grades.csv"),'r')
# Read the experimental data with Pandas
from IPython.display import display
-grades = pd.read_csv(infile,names = ('Trend','Sleep','Studied','Grade'))
+grades = pd.read_csv(infile)
grades = pd.DataFrame(grades)
-
+display(grades)
# Features and targets
X = grades.loc[:, grades.columns != 'Grade'].values
y = grades.loc[:, grades.columns == 'Grade'].values
-
+print(X)
# Create the encoder.
encoder = OneHotEncoder(handle_unknown="ignore")
# Assume for simplicity all features are categorical.
encoder.fit(X)
# Apply the encoder.
X = encoder.transform(X)
-print(X)
# Then do a Classification tree
tree_clf = DecisionTreeClassifier(max_depth=2)
tree_clf.fit(X, y)
@@ -761,6 +760,11 @@ export_graphviz(
)
cmd = 'dot -Tpng DataFiles/grade.dot -o DataFiles/grades.png'
os.system(cmd)
+
+
+#data_pandas = pd.DataFrame(data,index=['Frodo','Bilbo','Aragorn','Sam'])
+#df.columns = ['First', 'Second', 'Third', 'Fourth', 'Fifth']
+
!ec