diff --git a/doc/pub/week38/html/._week38-bs026.html b/doc/pub/week38/html/._week38-bs026.html
index 5fd0e6c7d..a1ad018a3 100644
--- a/doc/pub/week38/html/._week38-bs026.html
+++ b/doc/pub/week38/html/._week38-bs026.html
@@ -262,15 +262,6 @@ X_train, X_test, y_train, y_test = train_tes
logreg = LogisticRegression(solver='lbfgs')
logreg.fit(X_train, y_train)
print("Test set accuracy with Logistic Regression: {:.2f}".format(logreg.score(X_test,y_test)))
-#now scale the data
-from sklearn.preprocessing import StandardScaler
-scaler = StandardScaler()
-scaler.fit(X_train)
-X_train_scaled = scaler.transform(X_train)
-X_test_scaled = scaler.transform(X_test)
-# Logistic Regression
-logreg.fit(X_train_scaled, y_train)
-print("Test set accuracy Logistic Regression with scaled data: {:.2f}".format(logreg.score(X_test_scaled,y_test)))
diff --git a/doc/pub/week38/html/._week38-bs029.html b/doc/pub/week38/html/._week38-bs029.html
index e5254da59..f2011227c 100644
--- a/doc/pub/week38/html/._week38-bs029.html
+++ b/doc/pub/week38/html/._week38-bs029.html
@@ -256,30 +256,21 @@ X_train, X_test, y_train, y_test = train_tes
logreg = LogisticRegression(solver='lbfgs')
logreg.fit(X_train, y_train)
print("Test set accuracy with Logistic Regression: {:.2f}".format(logreg.score(X_test,y_test)))
-#now scale the data
-from sklearn.preprocessing import StandardScaler
-scaler = StandardScaler()
-scaler.fit(X_train)
-X_train_scaled = scaler.transform(X_train)
-X_test_scaled = scaler.transform(X_test)
-# Logistic Regression
-logreg.fit(X_train_scaled, y_train)
-print("Test set accuracy Logistic Regression with scaled data: {:.2f}".format(logreg.score(X_test_scaled,y_test)))
from sklearn.preprocessing import LabelEncoder
from sklearn.model_selection import cross_validate
#Cross validation
-accuracy = cross_validate(logreg,X_test_scaled,y_test,cv=10)['test_score']
+accuracy = cross_validate(logreg,X_test,y_test,cv=10)['test_score']
print(accuracy)
-print("Test set accuracy with Logistic Regression and scaled data: {:.2f}".format(logreg.score(X_test_scaled,y_test)))
+print("Test set accuracy with Logistic Regression: {:.2f}".format(logreg.score(X_test,y_test)))
import scikitplot as skplt
-y_pred = logreg.predict(X_test_scaled)
+y_pred = logreg.predict(X_test)
skplt.metrics.plot_confusion_matrix(y_test, y_pred, normalize=True)
plt.show()
-y_probas = logreg.predict_proba(X_test_scaled)
+y_probas = logreg.predict_proba(X_test)
skplt.metrics.plot_roc(y_test, y_probas)
plt.show()
skplt.metrics.plot_cumulative_gain(y_test, y_probas)
diff --git a/doc/pub/week38/html/week38-reveal.html b/doc/pub/week38/html/week38-reveal.html
index 42a926b75..1ef4b71b3 100644
--- a/doc/pub/week38/html/week38-reveal.html
+++ b/doc/pub/week38/html/week38-reveal.html
@@ -1099,15 +1099,6 @@ X_train, X_test, y_train, y_test = train_test_split(cancer.data,cancer.target,ra
logreg = LogisticRegression(solver='lbfgs')
logreg.fit(X_train, y_train)
print("Test set accuracy with Logistic Regression: {:.2f}".format(logreg.score(X_test,y_test)))
-#now scale the data
-from sklearn.preprocessing import StandardScaler
-scaler = StandardScaler()
-scaler.fit(X_train)
-X_train_scaled = scaler.transform(X_train)
-X_test_scaled = scaler.transform(X_test)
-# Logistic Regression
-logreg.fit(X_train_scaled, y_train)
-print("Test set accuracy Logistic Regression with scaled data: {:.2f}".format(logreg.score(X_test_scaled,y_test)))
@@ -1284,30 +1275,21 @@ X_train, X_test, y_train, y_test = train_test_split(cancer.data,cancer.target,ra
logreg = LogisticRegression(solver='lbfgs')
logreg.fit(X_train, y_train)
print("Test set accuracy with Logistic Regression: {:.2f}".format(logreg.score(X_test,y_test)))
-#now scale the data
-from sklearn.preprocessing import StandardScaler
-scaler = StandardScaler()
-scaler.fit(X_train)
-X_train_scaled = scaler.transform(X_train)
-X_test_scaled = scaler.transform(X_test)
-# Logistic Regression
-logreg.fit(X_train_scaled, y_train)
-print("Test set accuracy Logistic Regression with scaled data: {:.2f}".format(logreg.score(X_test_scaled,y_test)))
from sklearn.preprocessing import LabelEncoder
from sklearn.model_selection import cross_validate
#Cross validation
-accuracy = cross_validate(logreg,X_test_scaled,y_test,cv=10)['test_score']
+accuracy = cross_validate(logreg,X_test,y_test,cv=10)['test_score']
print(accuracy)
-print("Test set accuracy with Logistic Regression and scaled data: {:.2f}".format(logreg.score(X_test_scaled,y_test)))
+print("Test set accuracy with Logistic Regression: {:.2f}".format(logreg.score(X_test,y_test)))
import scikitplot as skplt
-y_pred = logreg.predict(X_test_scaled)
+y_pred = logreg.predict(X_test)
skplt.metrics.plot_confusion_matrix(y_test, y_pred, normalize=True)
plt.show()
-y_probas = logreg.predict_proba(X_test_scaled)
+y_probas = logreg.predict_proba(X_test)
skplt.metrics.plot_roc(y_test, y_probas)
plt.show()
skplt.metrics.plot_cumulative_gain(y_test, y_probas)
diff --git a/doc/pub/week38/html/week38-solarized.html b/doc/pub/week38/html/week38-solarized.html
index 839f2af20..b5fa54032 100644
--- a/doc/pub/week38/html/week38-solarized.html
+++ b/doc/pub/week38/html/week38-solarized.html
@@ -1014,15 +1014,6 @@ X_train, X_test, y_train, y_test = train_test_split(cancer.data,cancer.target,ra
logreg = LogisticRegression(solver='lbfgs')
logreg.fit(X_train, y_train)
print("Test set accuracy with Logistic Regression: {:.2f}".format(logreg.score(X_test,y_test)))
-#now scale the data
-from sklearn.preprocessing import StandardScaler
-scaler = StandardScaler()
-scaler.fit(X_train)
-X_train_scaled = scaler.transform(X_train)
-X_test_scaled = scaler.transform(X_test)
-# Logistic Regression
-logreg.fit(X_train_scaled, y_train)
-print("Test set accuracy Logistic Regression with scaled data: {:.2f}".format(logreg.score(X_test_scaled,y_test)))
@@ -1198,30 +1189,21 @@ X_train, X_test, y_train, y_test = train_test_split(cancer.data,cancer.target,ra
logreg = LogisticRegression(solver='lbfgs')
logreg.fit(X_train, y_train)
print("Test set accuracy with Logistic Regression: {:.2f}".format(logreg.score(X_test,y_test)))
-#now scale the data
-from sklearn.preprocessing import StandardScaler
-scaler = StandardScaler()
-scaler.fit(X_train)
-X_train_scaled = scaler.transform(X_train)
-X_test_scaled = scaler.transform(X_test)
-# Logistic Regression
-logreg.fit(X_train_scaled, y_train)
-print("Test set accuracy Logistic Regression with scaled data: {:.2f}".format(logreg.score(X_test_scaled,y_test)))
from sklearn.preprocessing import LabelEncoder
from sklearn.model_selection import cross_validate
#Cross validation
-accuracy = cross_validate(logreg,X_test_scaled,y_test,cv=10)['test_score']
+accuracy = cross_validate(logreg,X_test,y_test,cv=10)['test_score']
print(accuracy)
-print("Test set accuracy with Logistic Regression and scaled data: {:.2f}".format(logreg.score(X_test_scaled,y_test)))
+print("Test set accuracy with Logistic Regression: {:.2f}".format(logreg.score(X_test,y_test)))
import scikitplot as skplt
-y_pred = logreg.predict(X_test_scaled)
+y_pred = logreg.predict(X_test)
skplt.metrics.plot_confusion_matrix(y_test, y_pred, normalize=True)
plt.show()
-y_probas = logreg.predict_proba(X_test_scaled)
+y_probas = logreg.predict_proba(X_test)
skplt.metrics.plot_roc(y_test, y_probas)
plt.show()
skplt.metrics.plot_cumulative_gain(y_test, y_probas)
diff --git a/doc/pub/week38/html/week38.html b/doc/pub/week38/html/week38.html
index ea25103ed..23a6046f5 100644
--- a/doc/pub/week38/html/week38.html
+++ b/doc/pub/week38/html/week38.html
@@ -1091,15 +1091,6 @@ X_train, X_test, y_train, y_test = train_tes
logreg = LogisticRegression(solver='lbfgs')
logreg.fit(X_train, y_train)
print("Test set accuracy with Logistic Regression: {:.2f}".format(logreg.score(X_test,y_test)))
-#now scale the data
-from sklearn.preprocessing import StandardScaler
-scaler = StandardScaler()
-scaler.fit(X_train)
-X_train_scaled = scaler.transform(X_train)
-X_test_scaled = scaler.transform(X_test)
-# Logistic Regression
-logreg.fit(X_train_scaled, y_train)
-print("Test set accuracy Logistic Regression with scaled data: {:.2f}".format(logreg.score(X_test_scaled,y_test)))
@@ -1275,30 +1266,21 @@ X_train, X_test, y_train, y_test = train_tes
logreg = LogisticRegression(solver='lbfgs')
logreg.fit(X_train, y_train)
print("Test set accuracy with Logistic Regression: {:.2f}".format(logreg.score(X_test,y_test)))
-#now scale the data
-from sklearn.preprocessing import StandardScaler
-scaler = StandardScaler()
-scaler.fit(X_train)
-X_train_scaled = scaler.transform(X_train)
-X_test_scaled = scaler.transform(X_test)
-# Logistic Regression
-logreg.fit(X_train_scaled, y_train)
-print("Test set accuracy Logistic Regression with scaled data: {:.2f}".format(logreg.score(X_test_scaled,y_test)))
from sklearn.preprocessing import LabelEncoder
from sklearn.model_selection import cross_validate
#Cross validation
-accuracy = cross_validate(logreg,X_test_scaled,y_test,cv=10)['test_score']
+accuracy = cross_validate(logreg,X_test,y_test,cv=10)['test_score']
print(accuracy)
-print("Test set accuracy with Logistic Regression and scaled data: {:.2f}".format(logreg.score(X_test_scaled,y_test)))
+print("Test set accuracy with Logistic Regression: {:.2f}".format(logreg.score(X_test,y_test)))
import scikitplot as skplt
-y_pred = logreg.predict(X_test_scaled)
+y_pred = logreg.predict(X_test)
skplt.metrics.plot_confusion_matrix(y_test, y_pred, normalize=True)
plt.show()
-y_probas = logreg.predict_proba(X_test_scaled)
+y_probas = logreg.predict_proba(X_test)
skplt.metrics.plot_roc(y_test, y_probas)
plt.show()
skplt.metrics.plot_cumulative_gain(y_test, y_probas)
diff --git a/doc/pub/week38/ipynb/ipynb-week38-src.tar.gz b/doc/pub/week38/ipynb/ipynb-week38-src.tar.gz
index 319093a93..ba2f69d5f 100644
Binary files a/doc/pub/week38/ipynb/ipynb-week38-src.tar.gz and b/doc/pub/week38/ipynb/ipynb-week38-src.tar.gz differ
diff --git a/doc/pub/week38/ipynb/week38.ipynb b/doc/pub/week38/ipynb/week38.ipynb
index 31447bdf8..05c5718ef 100644
--- a/doc/pub/week38/ipynb/week38.ipynb
+++ b/doc/pub/week38/ipynb/week38.ipynb
@@ -2,7 +2,7 @@
"cells": [
{
"cell_type": "markdown",
- "id": "01f9b9a8",
+ "id": "9b6cc58f",
"metadata": {
"editable": true
},
@@ -14,7 +14,7 @@
},
{
"cell_type": "markdown",
- "id": "9b2d584e",
+ "id": "feb6e082",
"metadata": {
"editable": true
},
@@ -27,7 +27,7 @@
},
{
"cell_type": "markdown",
- "id": "54a98e9e",
+ "id": "f1643be6",
"metadata": {
"editable": true
},
@@ -53,7 +53,7 @@
},
{
"cell_type": "markdown",
- "id": "225cc16b",
+ "id": "8e000cd8",
"metadata": {
"editable": true
},
@@ -66,7 +66,7 @@
},
{
"cell_type": "markdown",
- "id": "00778aeb",
+ "id": "de44172e",
"metadata": {
"editable": true
},
@@ -78,7 +78,7 @@
},
{
"cell_type": "markdown",
- "id": "db5375f9",
+ "id": "34aaea23",
"metadata": {
"editable": true
},
@@ -88,7 +88,7 @@
},
{
"cell_type": "markdown",
- "id": "27cb052e",
+ "id": "9b68552a",
"metadata": {
"editable": true
},
@@ -101,7 +101,7 @@
},
{
"cell_type": "markdown",
- "id": "b450e9b7",
+ "id": "e5ce9c66",
"metadata": {
"editable": true
},
@@ -111,7 +111,7 @@
},
{
"cell_type": "markdown",
- "id": "5e51429a",
+ "id": "aeb2793c",
"metadata": {
"editable": true
},
@@ -123,7 +123,7 @@
},
{
"cell_type": "markdown",
- "id": "6fd9ad2f",
+ "id": "27cf0fdf",
"metadata": {
"editable": true
},
@@ -136,7 +136,7 @@
},
{
"cell_type": "markdown",
- "id": "059b5eb9",
+ "id": "29e13df8",
"metadata": {
"editable": true
},
@@ -149,7 +149,7 @@
},
{
"cell_type": "markdown",
- "id": "abbf7bb7",
+ "id": "5e179c8e",
"metadata": {
"editable": true
},
@@ -161,7 +161,7 @@
},
{
"cell_type": "markdown",
- "id": "63c1d4d3",
+ "id": "ee14634c",
"metadata": {
"editable": true
},
@@ -173,7 +173,7 @@
},
{
"cell_type": "markdown",
- "id": "3f61ae35",
+ "id": "df00bca6",
"metadata": {
"editable": true
},
@@ -183,7 +183,7 @@
},
{
"cell_type": "markdown",
- "id": "b7470206",
+ "id": "97fb16e3",
"metadata": {
"editable": true
},
@@ -196,7 +196,7 @@
},
{
"cell_type": "markdown",
- "id": "0027c09f",
+ "id": "690e11a6",
"metadata": {
"editable": true
},
@@ -208,7 +208,7 @@
},
{
"cell_type": "markdown",
- "id": "e6ccfab9",
+ "id": "7d4ee43c",
"metadata": {
"editable": true
},
@@ -220,7 +220,7 @@
},
{
"cell_type": "markdown",
- "id": "1493e160",
+ "id": "e144cb86",
"metadata": {
"editable": true
},
@@ -245,7 +245,7 @@
},
{
"cell_type": "markdown",
- "id": "f03473f8",
+ "id": "41101487",
"metadata": {
"editable": true
},
@@ -261,7 +261,7 @@
},
{
"cell_type": "markdown",
- "id": "5572797b",
+ "id": "9a43004f",
"metadata": {
"editable": true
},
@@ -277,7 +277,7 @@
},
{
"cell_type": "markdown",
- "id": "3c7c5728",
+ "id": "10338aa4",
"metadata": {
"editable": true
},
@@ -291,7 +291,7 @@
},
{
"cell_type": "markdown",
- "id": "01c9d597",
+ "id": "96976c43",
"metadata": {
"editable": true
},
@@ -319,7 +319,7 @@
},
{
"cell_type": "markdown",
- "id": "a8bfb686",
+ "id": "813e651e",
"metadata": {
"editable": true
},
@@ -332,7 +332,7 @@
{
"cell_type": "code",
"execution_count": 1,
- "id": "7dd3414e",
+ "id": "e25cd2a4",
"metadata": {
"collapsed": false,
"editable": true
@@ -434,7 +434,7 @@
},
{
"cell_type": "markdown",
- "id": "04bcdf5c",
+ "id": "81ca6e9d",
"metadata": {
"editable": true
},
@@ -456,7 +456,7 @@
},
{
"cell_type": "markdown",
- "id": "793b68ca",
+ "id": "e460a04c",
"metadata": {
"editable": true
},
@@ -482,7 +482,7 @@
},
{
"cell_type": "markdown",
- "id": "421b431d",
+ "id": "eff62414",
"metadata": {
"editable": true
},
@@ -506,7 +506,7 @@
},
{
"cell_type": "markdown",
- "id": "330d1095",
+ "id": "08f95b11",
"metadata": {
"editable": true
},
@@ -531,7 +531,7 @@
},
{
"cell_type": "markdown",
- "id": "22896257",
+ "id": "f39c8485",
"metadata": {
"editable": true
},
@@ -543,7 +543,7 @@
},
{
"cell_type": "markdown",
- "id": "ecec9745",
+ "id": "4f979e0e",
"metadata": {
"editable": true
},
@@ -561,7 +561,7 @@
},
{
"cell_type": "markdown",
- "id": "9a5f3982",
+ "id": "26761a13",
"metadata": {
"editable": true
},
@@ -579,7 +579,7 @@
},
{
"cell_type": "markdown",
- "id": "c0796f73",
+ "id": "7965a18c",
"metadata": {
"editable": true
},
@@ -590,7 +590,7 @@
},
{
"cell_type": "markdown",
- "id": "8ab40120",
+ "id": "606a7bb7",
"metadata": {
"editable": true
},
@@ -617,7 +617,7 @@
},
{
"cell_type": "markdown",
- "id": "309efb94",
+ "id": "e6ab1a0b",
"metadata": {
"editable": true
},
@@ -630,7 +630,7 @@
{
"cell_type": "code",
"execution_count": 2,
- "id": "c9ff5bb6",
+ "id": "5c8e3ab6",
"metadata": {
"collapsed": false,
"editable": true
@@ -695,7 +695,7 @@
},
{
"cell_type": "markdown",
- "id": "5a81b6f7",
+ "id": "c754cd9c",
"metadata": {
"editable": true
},
@@ -708,7 +708,7 @@
{
"cell_type": "code",
"execution_count": 3,
- "id": "56a13162",
+ "id": "29d363bc",
"metadata": {
"collapsed": false,
"editable": true
@@ -727,7 +727,7 @@
},
{
"cell_type": "markdown",
- "id": "19f4d949",
+ "id": "62267530",
"metadata": {
"editable": true
},
@@ -738,7 +738,7 @@
},
{
"cell_type": "markdown",
- "id": "b9201e8e",
+ "id": "684e8ea9",
"metadata": {
"editable": true
},
@@ -750,7 +750,7 @@
},
{
"cell_type": "markdown",
- "id": "6670cac7",
+ "id": "c95b14a9",
"metadata": {
"editable": true
},
@@ -769,7 +769,7 @@
},
{
"cell_type": "markdown",
- "id": "d0d49800",
+ "id": "e953faf8",
"metadata": {
"editable": true
},
@@ -791,7 +791,7 @@
},
{
"cell_type": "markdown",
- "id": "501a7228",
+ "id": "a1d30328",
"metadata": {
"editable": true
},
@@ -803,7 +803,7 @@
},
{
"cell_type": "markdown",
- "id": "7e80acdf",
+ "id": "76ecaaab",
"metadata": {
"editable": true
},
@@ -813,7 +813,7 @@
},
{
"cell_type": "markdown",
- "id": "9c679fb8",
+ "id": "adf36c53",
"metadata": {
"editable": true
},
@@ -826,7 +826,7 @@
{
"cell_type": "code",
"execution_count": 4,
- "id": "8d9b966d",
+ "id": "23b6715e",
"metadata": {
"collapsed": false,
"editable": true
@@ -891,7 +891,7 @@
},
{
"cell_type": "markdown",
- "id": "b51bf67c",
+ "id": "3839cfe8",
"metadata": {
"editable": true
},
@@ -903,7 +903,7 @@
},
{
"cell_type": "markdown",
- "id": "1c51a404",
+ "id": "7cf1991d",
"metadata": {
"editable": true
},
@@ -918,7 +918,7 @@
},
{
"cell_type": "markdown",
- "id": "cbf6af49",
+ "id": "6e63b9c3",
"metadata": {
"editable": true
},
@@ -930,7 +930,7 @@
},
{
"cell_type": "markdown",
- "id": "33d715da",
+ "id": "c63deda3",
"metadata": {
"editable": true
},
@@ -942,7 +942,7 @@
},
{
"cell_type": "markdown",
- "id": "4d84e4e9",
+ "id": "f089f4ce",
"metadata": {
"editable": true
},
@@ -959,7 +959,7 @@
},
{
"cell_type": "markdown",
- "id": "5a082750",
+ "id": "740b7c95",
"metadata": {
"editable": true
},
@@ -973,7 +973,7 @@
},
{
"cell_type": "markdown",
- "id": "b428d69d",
+ "id": "b691f753",
"metadata": {
"editable": true
},
@@ -983,7 +983,7 @@
},
{
"cell_type": "markdown",
- "id": "e6c999a2",
+ "id": "ccba3e2a",
"metadata": {
"editable": true
},
@@ -995,7 +995,7 @@
},
{
"cell_type": "markdown",
- "id": "4fff502a",
+ "id": "4a4a463d",
"metadata": {
"editable": true
},
@@ -1007,7 +1007,7 @@
},
{
"cell_type": "markdown",
- "id": "70a31849",
+ "id": "5e696c81",
"metadata": {
"editable": true
},
@@ -1019,7 +1019,7 @@
},
{
"cell_type": "markdown",
- "id": "d55b6884",
+ "id": "eb8391a5",
"metadata": {
"editable": true
},
@@ -1030,7 +1030,7 @@
},
{
"cell_type": "markdown",
- "id": "ed38348a",
+ "id": "880eabac",
"metadata": {
"editable": true
},
@@ -1042,7 +1042,7 @@
},
{
"cell_type": "markdown",
- "id": "3490a7db",
+ "id": "1a0c6988",
"metadata": {
"editable": true
},
@@ -1053,7 +1053,7 @@
},
{
"cell_type": "markdown",
- "id": "b4ccac01",
+ "id": "7c986c18",
"metadata": {
"editable": true
},
@@ -1069,7 +1069,7 @@
},
{
"cell_type": "markdown",
- "id": "9a34f855",
+ "id": "893c76d0",
"metadata": {
"editable": true
},
@@ -1081,7 +1081,7 @@
},
{
"cell_type": "markdown",
- "id": "ce050728",
+ "id": "a3d337cd",
"metadata": {
"editable": true
},
@@ -1091,7 +1091,7 @@
},
{
"cell_type": "markdown",
- "id": "09414ce2",
+ "id": "e08c3654",
"metadata": {
"editable": true
},
@@ -1103,7 +1103,7 @@
},
{
"cell_type": "markdown",
- "id": "65034766",
+ "id": "be71402c",
"metadata": {
"editable": true
},
@@ -1118,7 +1118,7 @@
},
{
"cell_type": "markdown",
- "id": "cd0ed2fc",
+ "id": "29289290",
"metadata": {
"editable": true
},
@@ -1130,7 +1130,7 @@
},
{
"cell_type": "markdown",
- "id": "49672afd",
+ "id": "ce4f1c86",
"metadata": {
"editable": true
},
@@ -1141,7 +1141,7 @@
},
{
"cell_type": "markdown",
- "id": "c374232e",
+ "id": "66d6122a",
"metadata": {
"editable": true
},
@@ -1153,7 +1153,7 @@
},
{
"cell_type": "markdown",
- "id": "5af3f525",
+ "id": "961c87da",
"metadata": {
"editable": true
},
@@ -1165,7 +1165,7 @@
},
{
"cell_type": "markdown",
- "id": "475962a3",
+ "id": "7450aac7",
"metadata": {
"editable": true
},
@@ -1177,7 +1177,7 @@
},
{
"cell_type": "markdown",
- "id": "a06c5f81",
+ "id": "0bdcc1db",
"metadata": {
"editable": true
},
@@ -1187,7 +1187,7 @@
},
{
"cell_type": "markdown",
- "id": "6f5c6473",
+ "id": "52db5546",
"metadata": {
"editable": true
},
@@ -1199,7 +1199,7 @@
},
{
"cell_type": "markdown",
- "id": "b02ad88e",
+ "id": "db40e363",
"metadata": {
"editable": true
},
@@ -1213,7 +1213,7 @@
},
{
"cell_type": "markdown",
- "id": "7eb3fa57",
+ "id": "be991823",
"metadata": {
"editable": true
},
@@ -1225,7 +1225,7 @@
},
{
"cell_type": "markdown",
- "id": "9ca19d51",
+ "id": "e392a560",
"metadata": {
"editable": true
},
@@ -1235,7 +1235,7 @@
},
{
"cell_type": "markdown",
- "id": "3b71224c",
+ "id": "c84dbff0",
"metadata": {
"editable": true
},
@@ -1247,7 +1247,7 @@
},
{
"cell_type": "markdown",
- "id": "16bcf436",
+ "id": "9defcb1e",
"metadata": {
"editable": true
},
@@ -1257,7 +1257,7 @@
},
{
"cell_type": "markdown",
- "id": "36612ae6",
+ "id": "e6cbbd89",
"metadata": {
"editable": true
},
@@ -1269,7 +1269,7 @@
},
{
"cell_type": "markdown",
- "id": "d954f69b",
+ "id": "30546ca8",
"metadata": {
"editable": true
},
@@ -1280,7 +1280,7 @@
},
{
"cell_type": "markdown",
- "id": "8b3327c4",
+ "id": "74a63af9",
"metadata": {
"editable": true
},
@@ -1303,7 +1303,7 @@
},
{
"cell_type": "markdown",
- "id": "de7c9ae7",
+ "id": "1d599351",
"metadata": {
"editable": true
},
@@ -1315,7 +1315,7 @@
},
{
"cell_type": "markdown",
- "id": "218e5036",
+ "id": "17c74317",
"metadata": {
"editable": true
},
@@ -1325,7 +1325,7 @@
},
{
"cell_type": "markdown",
- "id": "a14de229",
+ "id": "cb140f50",
"metadata": {
"editable": true
},
@@ -1337,7 +1337,7 @@
},
{
"cell_type": "markdown",
- "id": "a5320746",
+ "id": "30c5af0c",
"metadata": {
"editable": true
},
@@ -1354,7 +1354,7 @@
},
{
"cell_type": "markdown",
- "id": "2e8bc59a",
+ "id": "53398d26",
"metadata": {
"editable": true
},
@@ -1364,7 +1364,7 @@
},
{
"cell_type": "markdown",
- "id": "2b4d2b1f",
+ "id": "e9e4e259",
"metadata": {
"editable": true
},
@@ -1379,7 +1379,7 @@
{
"cell_type": "code",
"execution_count": 5,
- "id": "55f63368",
+ "id": "025cdea2",
"metadata": {
"collapsed": false,
"editable": true
@@ -1401,21 +1401,12 @@
"# Logistic Regression\n",
"logreg = LogisticRegression(solver='lbfgs')\n",
"logreg.fit(X_train, y_train)\n",
- "print(\"Test set accuracy with Logistic Regression: {:.2f}\".format(logreg.score(X_test,y_test)))\n",
- "#now scale the data\n",
- "from sklearn.preprocessing import StandardScaler\n",
- "scaler = StandardScaler()\n",
- "scaler.fit(X_train)\n",
- "X_train_scaled = scaler.transform(X_train)\n",
- "X_test_scaled = scaler.transform(X_test)\n",
- "# Logistic Regression\n",
- "logreg.fit(X_train_scaled, y_train)\n",
- "print(\"Test set accuracy Logistic Regression with scaled data: {:.2f}\".format(logreg.score(X_test_scaled,y_test)))"
+ "print(\"Test set accuracy with Logistic Regression: {:.2f}\".format(logreg.score(X_test,y_test)))"
]
},
{
"cell_type": "markdown",
- "id": "0bd96349",
+ "id": "bfc34b20",
"metadata": {
"editable": true
},
@@ -1429,7 +1420,7 @@
{
"cell_type": "code",
"execution_count": 6,
- "id": "316d64e8",
+ "id": "088a7483",
"metadata": {
"collapsed": false,
"editable": true
@@ -1474,7 +1465,7 @@
},
{
"cell_type": "markdown",
- "id": "a334759c",
+ "id": "7ad11dbc",
"metadata": {
"editable": true
},
@@ -1499,7 +1490,7 @@
{
"cell_type": "code",
"execution_count": 7,
- "id": "93302b72",
+ "id": "71de4ea1",
"metadata": {
"collapsed": false,
"editable": true
@@ -1511,7 +1502,7 @@
},
{
"cell_type": "markdown",
- "id": "71d73535",
+ "id": "deb75069",
"metadata": {
"editable": true
},
@@ -1522,7 +1513,7 @@
{
"cell_type": "code",
"execution_count": 8,
- "id": "84ce38f5",
+ "id": "9ef1c15c",
"metadata": {
"collapsed": false,
"editable": true
@@ -1534,7 +1525,7 @@
},
{
"cell_type": "markdown",
- "id": "14f81ffb",
+ "id": "68e3ee8a",
"metadata": {
"editable": true
},
@@ -1547,7 +1538,7 @@
},
{
"cell_type": "markdown",
- "id": "88524ac4",
+ "id": "fc5968c2",
"metadata": {
"editable": true
},
@@ -1558,7 +1549,7 @@
{
"cell_type": "code",
"execution_count": 9,
- "id": "a158ed70",
+ "id": "9d75a60c",
"metadata": {
"collapsed": false,
"editable": true
@@ -1581,30 +1572,21 @@
"logreg = LogisticRegression(solver='lbfgs')\n",
"logreg.fit(X_train, y_train)\n",
"print(\"Test set accuracy with Logistic Regression: {:.2f}\".format(logreg.score(X_test,y_test)))\n",
- "#now scale the data\n",
- "from sklearn.preprocessing import StandardScaler\n",
- "scaler = StandardScaler()\n",
- "scaler.fit(X_train)\n",
- "X_train_scaled = scaler.transform(X_train)\n",
- "X_test_scaled = scaler.transform(X_test)\n",
- "# Logistic Regression\n",
- "logreg.fit(X_train_scaled, y_train)\n",
- "print(\"Test set accuracy Logistic Regression with scaled data: {:.2f}\".format(logreg.score(X_test_scaled,y_test)))\n",
"\n",
"\n",
"from sklearn.preprocessing import LabelEncoder\n",
"from sklearn.model_selection import cross_validate\n",
"#Cross validation\n",
- "accuracy = cross_validate(logreg,X_test_scaled,y_test,cv=10)['test_score']\n",
+ "accuracy = cross_validate(logreg,X_test,y_test,cv=10)['test_score']\n",
"print(accuracy)\n",
- "print(\"Test set accuracy with Logistic Regression and scaled data: {:.2f}\".format(logreg.score(X_test_scaled,y_test)))\n",
+ "print(\"Test set accuracy with Logistic Regression: {:.2f}\".format(logreg.score(X_test,y_test)))\n",
"\n",
"\n",
"import scikitplot as skplt\n",
- "y_pred = logreg.predict(X_test_scaled)\n",
+ "y_pred = logreg.predict(X_test)\n",
"skplt.metrics.plot_confusion_matrix(y_test, y_pred, normalize=True)\n",
"plt.show()\n",
- "y_probas = logreg.predict_proba(X_test_scaled)\n",
+ "y_probas = logreg.predict_proba(X_test)\n",
"skplt.metrics.plot_roc(y_test, y_probas)\n",
"plt.show()\n",
"skplt.metrics.plot_cumulative_gain(y_test, y_probas)\n",
@@ -1613,7 +1595,7 @@
},
{
"cell_type": "markdown",
- "id": "cc5dd2e0",
+ "id": "71683297",
"metadata": {
"editable": true
},
@@ -1634,7 +1616,7 @@
},
{
"cell_type": "markdown",
- "id": "7e06a234",
+ "id": "d67bbe66",
"metadata": {
"editable": true
},
@@ -1651,7 +1633,7 @@
},
{
"cell_type": "markdown",
- "id": "009644a6",
+ "id": "17da7a33",
"metadata": {
"editable": true
},
@@ -1666,7 +1648,7 @@
},
{
"cell_type": "markdown",
- "id": "2f7d0511",
+ "id": "22f4e585",
"metadata": {
"editable": true
},
@@ -1676,7 +1658,7 @@
},
{
"cell_type": "markdown",
- "id": "b4e7310e",
+ "id": "c474dfed",
"metadata": {
"editable": true
},
@@ -1692,7 +1674,7 @@
},
{
"cell_type": "markdown",
- "id": "024b05ac",
+ "id": "39d0b596",
"metadata": {
"editable": true
},
@@ -1704,7 +1686,7 @@
},
{
"cell_type": "markdown",
- "id": "e2186ca7",
+ "id": "f46b6e1a",
"metadata": {
"editable": true
},
@@ -1715,7 +1697,7 @@
},
{
"cell_type": "markdown",
- "id": "e6b5e00a",
+ "id": "8586240f",
"metadata": {
"editable": true
},
@@ -1727,7 +1709,7 @@
},
{
"cell_type": "markdown",
- "id": "39688a20",
+ "id": "9991aa94",
"metadata": {
"editable": true
},
@@ -1737,7 +1719,7 @@
},
{
"cell_type": "markdown",
- "id": "ec69bb49",
+ "id": "bbed64bb",
"metadata": {
"editable": true
},
@@ -1751,7 +1733,7 @@
},
{
"cell_type": "markdown",
- "id": "a9843445",
+ "id": "35fbc807",
"metadata": {
"editable": true
},
@@ -1763,7 +1745,7 @@
},
{
"cell_type": "markdown",
- "id": "2ce9f333",
+ "id": "cdd83e70",
"metadata": {
"editable": true
},
@@ -1773,7 +1755,7 @@
},
{
"cell_type": "markdown",
- "id": "2e2053a4",
+ "id": "206402c4",
"metadata": {
"editable": true
},
@@ -1785,7 +1767,7 @@
},
{
"cell_type": "markdown",
- "id": "36e5c401",
+ "id": "2593e4aa",
"metadata": {
"editable": true
},
@@ -1797,7 +1779,7 @@
},
{
"cell_type": "markdown",
- "id": "598f01a4",
+ "id": "a7bda816",
"metadata": {
"editable": true
},
@@ -1817,7 +1799,7 @@
},
{
"cell_type": "markdown",
- "id": "9aa04bc4",
+ "id": "6d52d02a",
"metadata": {
"editable": true
},
@@ -1833,7 +1815,7 @@
},
{
"cell_type": "markdown",
- "id": "68fc4862",
+ "id": "96e8e1e8",
"metadata": {
"editable": true
},
@@ -1849,7 +1831,7 @@
},
{
"cell_type": "markdown",
- "id": "80682dbe",
+ "id": "241635ea",
"metadata": {
"editable": true
},
@@ -1860,7 +1842,7 @@
},
{
"cell_type": "markdown",
- "id": "960c62bb",
+ "id": "b080ce92",
"metadata": {
"editable": true
},
@@ -1872,7 +1854,7 @@
},
{
"cell_type": "markdown",
- "id": "54236f7d",
+ "id": "566c46f6",
"metadata": {
"editable": true
},
@@ -1882,7 +1864,7 @@
},
{
"cell_type": "markdown",
- "id": "95a844a7",
+ "id": "6d98b19d",
"metadata": {
"editable": true
},
@@ -1894,7 +1876,7 @@
},
{
"cell_type": "markdown",
- "id": "63603bc3",
+ "id": "dcee8294",
"metadata": {
"editable": true
},
@@ -1904,7 +1886,7 @@
},
{
"cell_type": "markdown",
- "id": "d53e2b6f",
+ "id": "bd3fec65",
"metadata": {
"editable": true
},
@@ -1916,7 +1898,7 @@
},
{
"cell_type": "markdown",
- "id": "969ecf1e",
+ "id": "9306b085",
"metadata": {
"editable": true
},
@@ -1938,7 +1920,7 @@
},
{
"cell_type": "markdown",
- "id": "c2086b82",
+ "id": "1d1b5609",
"metadata": {
"editable": true
},
@@ -1951,7 +1933,7 @@
},
{
"cell_type": "markdown",
- "id": "e91068bc",
+ "id": "3cc3e31c",
"metadata": {
"editable": true
},
@@ -1964,7 +1946,7 @@
},
{
"cell_type": "markdown",
- "id": "580a218c",
+ "id": "8ce77450",
"metadata": {
"editable": true
},
@@ -1974,7 +1956,7 @@
},
{
"cell_type": "markdown",
- "id": "7a1f9d80",
+ "id": "38a173fa",
"metadata": {
"editable": true
},
@@ -1992,7 +1974,7 @@
},
{
"cell_type": "markdown",
- "id": "f107bea2",
+ "id": "582122d4",
"metadata": {
"editable": true
},
@@ -2002,7 +1984,7 @@
},
{
"cell_type": "markdown",
- "id": "a590a21f",
+ "id": "f4ab9e0f",
"metadata": {
"editable": true
},
@@ -2017,7 +1999,7 @@
},
{
"cell_type": "markdown",
- "id": "53ed5eef",
+ "id": "08553f22",
"metadata": {
"editable": true
},
@@ -2027,7 +2009,7 @@
},
{
"cell_type": "markdown",
- "id": "10d5b0d4",
+ "id": "97800ce0",
"metadata": {
"editable": true
},
@@ -2041,7 +2023,7 @@
},
{
"cell_type": "markdown",
- "id": "892162ee",
+ "id": "cce9f325",
"metadata": {
"editable": true
},
@@ -2051,7 +2033,7 @@
},
{
"cell_type": "markdown",
- "id": "bf468d83",
+ "id": "2496a4fa",
"metadata": {
"editable": true
},
@@ -2065,7 +2047,7 @@
},
{
"cell_type": "markdown",
- "id": "974a49d8",
+ "id": "9b8d1328",
"metadata": {
"editable": true
},
@@ -2080,7 +2062,7 @@
},
{
"cell_type": "markdown",
- "id": "71eed422",
+ "id": "8d020128",
"metadata": {
"editable": true
},
@@ -2097,7 +2079,7 @@
},
{
"cell_type": "markdown",
- "id": "d9842711",
+ "id": "00bff419",
"metadata": {
"editable": true
},
@@ -2109,7 +2091,7 @@
},
{
"cell_type": "markdown",
- "id": "7c1fb5fe",
+ "id": "baef7006",
"metadata": {
"editable": true
},
@@ -2123,7 +2105,7 @@
},
{
"cell_type": "markdown",
- "id": "d17bc954",
+ "id": "793bb2cd",
"metadata": {
"editable": true
},
@@ -2138,7 +2120,7 @@
},
{
"cell_type": "markdown",
- "id": "ee6cf8aa",
+ "id": "6a906c4d",
"metadata": {
"editable": true
},
@@ -2150,7 +2132,7 @@
},
{
"cell_type": "markdown",
- "id": "b6da9be5",
+ "id": "4d57ab93",
"metadata": {
"editable": true
},
@@ -2161,7 +2143,7 @@
},
{
"cell_type": "markdown",
- "id": "0df5d09e",
+ "id": "c0097132",
"metadata": {
"editable": true
},
@@ -2189,7 +2171,7 @@
},
{
"cell_type": "markdown",
- "id": "d33c17a9",
+ "id": "67f74f58",
"metadata": {
"editable": true
},
diff --git a/doc/src/week38/week38.do.txt b/doc/src/week38/week38.do.txt
index 03503aa70..a121a6835 100644
--- a/doc/src/week38/week38.do.txt
+++ b/doc/src/week38/week38.do.txt
@@ -770,15 +770,6 @@ print(X_test.shape)
logreg = LogisticRegression(solver='lbfgs')
logreg.fit(X_train, y_train)
print("Test set accuracy with Logistic Regression: {:.2f}".format(logreg.score(X_test,y_test)))
-#now scale the data
-from sklearn.preprocessing import StandardScaler
-scaler = StandardScaler()
-scaler.fit(X_train)
-X_train_scaled = scaler.transform(X_train)
-X_test_scaled = scaler.transform(X_test)
-# Logistic Regression
-logreg.fit(X_train_scaled, y_train)
-print("Test set accuracy Logistic Regression with scaled data: {:.2f}".format(logreg.score(X_test_scaled,y_test)))
!ec
!split
@@ -875,30 +866,21 @@ print(X_test.shape)
logreg = LogisticRegression(solver='lbfgs')
logreg.fit(X_train, y_train)
print("Test set accuracy with Logistic Regression: {:.2f}".format(logreg.score(X_test,y_test)))
-#now scale the data
-from sklearn.preprocessing import StandardScaler
-scaler = StandardScaler()
-scaler.fit(X_train)
-X_train_scaled = scaler.transform(X_train)
-X_test_scaled = scaler.transform(X_test)
-# Logistic Regression
-logreg.fit(X_train_scaled, y_train)
-print("Test set accuracy Logistic Regression with scaled data: {:.2f}".format(logreg.score(X_test_scaled,y_test)))
from sklearn.preprocessing import LabelEncoder
from sklearn.model_selection import cross_validate
#Cross validation
-accuracy = cross_validate(logreg,X_test_scaled,y_test,cv=10)['test_score']
+accuracy = cross_validate(logreg,X_test,y_test,cv=10)['test_score']
print(accuracy)
-print("Test set accuracy with Logistic Regression and scaled data: {:.2f}".format(logreg.score(X_test_scaled,y_test)))
+print("Test set accuracy with Logistic Regression: {:.2f}".format(logreg.score(X_test,y_test)))
import scikitplot as skplt
-y_pred = logreg.predict(X_test_scaled)
+y_pred = logreg.predict(X_test)
skplt.metrics.plot_confusion_matrix(y_test, y_pred, normalize=True)
plt.show()
-y_probas = logreg.predict_proba(X_test_scaled)
+y_probas = logreg.predict_proba(X_test)
skplt.metrics.plot_roc(y_test, y_probas)
plt.show()
skplt.metrics.plot_cumulative_gain(y_test, y_probas)