diff --git a/doc/pub/week45/html/._week45-bs012.html b/doc/pub/week45/html/._week45-bs012.html
index 3cc30719e..f3cfc221a 100644
--- a/doc/pub/week45/html/._week45-bs012.html
+++ b/doc/pub/week45/html/._week45-bs012.html
@@ -183,20 +183,13 @@ MathJax.Hub.Config({
from sklearn.ensemble import AdaBoostClassifier
ada_clf = AdaBoostClassifier(
- DecisionTreeClassifier(max_depth=1), n_estimators=200,
- algorithm="SAMME.R", learning_rate=0.5, random_state=42)
+ DecisionTreeClassifier(max_depth=2), n_estimators=200,
+ algorithm="SAMME.R", learning_rate=0.01, random_state=42)
ada_clf.fit(X_train, y_train)
-
-from sklearn.ensemble import AdaBoostClassifier
-
-ada_clf = AdaBoostClassifier(
- DecisionTreeClassifier(max_depth=1), n_estimators=200,
- algorithm="SAMME.R", learning_rate=0.5, random_state=42)
-ada_clf.fit(X_train_scaled, y_train)
-y_pred = ada_clf.predict(X_test_scaled)
+y_pred = ada_clf.predict(X_test)
skplt.metrics.plot_confusion_matrix(y_test, y_pred, normalize=True)
plt.show()
-y_probas = ada_clf.predict_proba(X_test_scaled)
+y_probas = ada_clf.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/week45/html/._week45-bs018.html b/doc/pub/week45/html/._week45-bs018.html
index 7d12fd09c..2787cc51c 100644
--- a/doc/pub/week45/html/._week45-bs018.html
+++ b/doc/pub/week45/html/._week45-bs018.html
@@ -203,7 +203,7 @@ gd_clf.fit(X_train_scaled, y_train)
#Cross validation
accuracy = cross_validate(gd_clf,X_test_scaled,y_test,cv=10)['test_score']
print(accuracy)
-print("Test set accuracy with Random Forests and scaled data: {:.2f}".format(gd_clf.score(X_test_scaled,y_test)))
+print("Test set accuracy with Gradient boosting and scaled data: {:.2f}".format(gd_clf.score(X_test_scaled,y_test)))
import scikitplot as skplt
y_pred = gd_clf.predict(X_test_scaled)
diff --git a/doc/pub/week45/html/._week45-bs021.html b/doc/pub/week45/html/._week45-bs021.html
index c56ba7632..12d57f114 100644
--- a/doc/pub/week45/html/._week45-bs021.html
+++ b/doc/pub/week45/html/._week45-bs021.html
@@ -205,7 +205,7 @@ xg_clf.fit(X_train_scaled,y_train)
y_test = xg_clf.predict(X_test_scaled)
-print("Test set accuracy with Random Forests and scaled data: {:.2f}".format(xg_clf.score(X_test_scaled,y_test)))
+print("Test set accuracy with Gradient Boosting and scaled data: {:.2f}".format(xg_clf.score(X_test_scaled,y_test)))
import scikitplot as skplt
y_pred = xg_clf.predict(X_test_scaled)
diff --git a/doc/pub/week45/html/week45-reveal.html b/doc/pub/week45/html/week45-reveal.html
index cc7ffc03c..d354e426a 100644
--- a/doc/pub/week45/html/week45-reveal.html
+++ b/doc/pub/week45/html/week45-reveal.html
@@ -687,20 +687,13 @@ observations that are missed in the previous iterations.
from sklearn.ensemble import AdaBoostClassifier
ada_clf = AdaBoostClassifier(
- DecisionTreeClassifier(max_depth=1), n_estimators=200,
- algorithm="SAMME.R", learning_rate=0.5, random_state=42)
+ DecisionTreeClassifier(max_depth=2), n_estimators=200,
+ algorithm="SAMME.R", learning_rate=0.01, random_state=42)
ada_clf.fit(X_train, y_train)
-
-from sklearn.ensemble import AdaBoostClassifier
-
-ada_clf = AdaBoostClassifier(
- DecisionTreeClassifier(max_depth=1), n_estimators=200,
- algorithm="SAMME.R", learning_rate=0.5, random_state=42)
-ada_clf.fit(X_train_scaled, y_train)
-y_pred = ada_clf.predict(X_test_scaled)
+y_pred = ada_clf.predict(X_test)
skplt.metrics.plot_confusion_matrix(y_test, y_pred, normalize=True)
plt.show()
-y_probas = ada_clf.predict_proba(X_test_scaled)
+y_probas = ada_clf.predict_proba(X_test)
skplt.metrics.plot_roc(y_test, y_probas)
plt.show()
skplt.metrics.plot_cumulative_gain(y_test, y_probas)
@@ -924,7 +917,7 @@ gd_clf.fit(X_train_scaled, y_train)
#Cross validation
accuracy = cross_validate(gd_clf,X_test_scaled,y_test,cv=10)['test_score']
print(accuracy)
-print("Test set accuracy with Random Forests and scaled data: {:.2f}".format(gd_clf.score(X_test_scaled,y_test)))
+print("Test set accuracy with Gradient boosting and scaled data: {:.2f}".format(gd_clf.score(X_test_scaled,y_test)))
import scikitplot as skplt
y_pred = gd_clf.predict(X_test_scaled)
@@ -1077,7 +1070,7 @@ xg_clf.fit(X_train_scaled,y_train)
y_test = xg_clf.predict(X_test_scaled)
-print("Test set accuracy with Random Forests and scaled data: {:.2f}".format(xg_clf.score(X_test_scaled,y_test)))
+print("Test set accuracy with Gradient Boosting and scaled data: {:.2f}".format(xg_clf.score(X_test_scaled,y_test)))
import scikitplot as skplt
y_pred = xg_clf.predict(X_test_scaled)
diff --git a/doc/pub/week45/html/week45-solarized.html b/doc/pub/week45/html/week45-solarized.html
index f0c8aefe5..586a364a6 100644
--- a/doc/pub/week45/html/week45-solarized.html
+++ b/doc/pub/week45/html/week45-solarized.html
@@ -603,20 +603,13 @@ observations that are missed in the previous iterations.
from sklearn.ensemble import AdaBoostClassifier
ada_clf = AdaBoostClassifier(
- DecisionTreeClassifier(max_depth=1), n_estimators=200,
- algorithm="SAMME.R", learning_rate=0.5, random_state=42)
+ DecisionTreeClassifier(max_depth=2), n_estimators=200,
+ algorithm="SAMME.R", learning_rate=0.01, random_state=42)
ada_clf.fit(X_train, y_train)
-
-from sklearn.ensemble import AdaBoostClassifier
-
-ada_clf = AdaBoostClassifier(
- DecisionTreeClassifier(max_depth=1), n_estimators=200,
- algorithm="SAMME.R", learning_rate=0.5, random_state=42)
-ada_clf.fit(X_train_scaled, y_train)
-y_pred = ada_clf.predict(X_test_scaled)
+y_pred = ada_clf.predict(X_test)
skplt.metrics.plot_confusion_matrix(y_test, y_pred, normalize=True)
plt.show()
-y_probas = ada_clf.predict_proba(X_test_scaled)
+y_probas = ada_clf.predict_proba(X_test)
skplt.metrics.plot_roc(y_test, y_probas)
plt.show()
skplt.metrics.plot_cumulative_gain(y_test, y_probas)
@@ -821,7 +814,7 @@ gd_clf.fit(X_train_scaled, y_train)
#Cross validation
accuracy = cross_validate(gd_clf,X_test_scaled,y_test,cv=10)['test_score']
print(accuracy)
-print("Test set accuracy with Random Forests and scaled data: {:.2f}".format(gd_clf.score(X_test_scaled,y_test)))
+print("Test set accuracy with Gradient boosting and scaled data: {:.2f}".format(gd_clf.score(X_test_scaled,y_test)))
import scikitplot as skplt
y_pred = gd_clf.predict(X_test_scaled)
@@ -973,7 +966,7 @@ xg_clf.fit(X_train_scaled,y_train)
y_test = xg_clf.predict(X_test_scaled)
-print("Test set accuracy with Random Forests and scaled data: {:.2f}".format(xg_clf.score(X_test_scaled,y_test)))
+print("Test set accuracy with Gradient Boosting and scaled data: {:.2f}".format(xg_clf.score(X_test_scaled,y_test)))
import scikitplot as skplt
y_pred = xg_clf.predict(X_test_scaled)
diff --git a/doc/pub/week45/html/week45.html b/doc/pub/week45/html/week45.html
index aa93caaed..cfb8545b7 100644
--- a/doc/pub/week45/html/week45.html
+++ b/doc/pub/week45/html/week45.html
@@ -680,20 +680,13 @@ observations that are missed in the previous iterations.
from sklearn.ensemble import AdaBoostClassifier
ada_clf = AdaBoostClassifier(
- DecisionTreeClassifier(max_depth=1), n_estimators=200,
- algorithm="SAMME.R", learning_rate=0.5, random_state=42)
+ DecisionTreeClassifier(max_depth=2), n_estimators=200,
+ algorithm="SAMME.R", learning_rate=0.01, random_state=42)
ada_clf.fit(X_train, y_train)
-
-from sklearn.ensemble import AdaBoostClassifier
-
-ada_clf = AdaBoostClassifier(
- DecisionTreeClassifier(max_depth=1), n_estimators=200,
- algorithm="SAMME.R", learning_rate=0.5, random_state=42)
-ada_clf.fit(X_train_scaled, y_train)
-y_pred = ada_clf.predict(X_test_scaled)
+y_pred = ada_clf.predict(X_test)
skplt.metrics.plot_confusion_matrix(y_test, y_pred, normalize=True)
plt.show()
-y_probas = ada_clf.predict_proba(X_test_scaled)
+y_probas = ada_clf.predict_proba(X_test)
skplt.metrics.plot_roc(y_test, y_probas)
plt.show()
skplt.metrics.plot_cumulative_gain(y_test, y_probas)
@@ -898,7 +891,7 @@ gd_clf.fit(X_train_scaled, y_train)
#Cross validation
accuracy = cross_validate(gd_clf,X_test_scaled,y_test,cv=10)['test_score']
print(accuracy)
-print("Test set accuracy with Random Forests and scaled data: {:.2f}".format(gd_clf.score(X_test_scaled,y_test)))
+print("Test set accuracy with Gradient boosting and scaled data: {:.2f}".format(gd_clf.score(X_test_scaled,y_test)))
import scikitplot as skplt
y_pred = gd_clf.predict(X_test_scaled)
@@ -1050,7 +1043,7 @@ xg_clf.fit(X_train_scaled,y_train)
y_test = xg_clf.predict(X_test_scaled)
-print("Test set accuracy with Random Forests and scaled data: {:.2f}".format(xg_clf.score(X_test_scaled,y_test)))
+print("Test set accuracy with Gradient Boosting and scaled data: {:.2f}".format(xg_clf.score(X_test_scaled,y_test)))
import scikitplot as skplt
y_pred = xg_clf.predict(X_test_scaled)
diff --git a/doc/pub/week45/ipynb/Results/FigureFiles/gdclassiffiercgain.png b/doc/pub/week45/ipynb/Results/FigureFiles/gdclassiffiercgain.png
index ffba89938..9225b1e64 100644
Binary files a/doc/pub/week45/ipynb/Results/FigureFiles/gdclassiffiercgain.png and b/doc/pub/week45/ipynb/Results/FigureFiles/gdclassiffiercgain.png differ
diff --git a/doc/pub/week45/ipynb/Results/FigureFiles/gdclassiffierconfusion.png b/doc/pub/week45/ipynb/Results/FigureFiles/gdclassiffierconfusion.png
index 4722b4d78..95cdc90e8 100644
Binary files a/doc/pub/week45/ipynb/Results/FigureFiles/gdclassiffierconfusion.png and b/doc/pub/week45/ipynb/Results/FigureFiles/gdclassiffierconfusion.png differ
diff --git a/doc/pub/week45/ipynb/Results/FigureFiles/gdclassiffierroc.png b/doc/pub/week45/ipynb/Results/FigureFiles/gdclassiffierroc.png
index 459a202f8..2d9a000ec 100644
Binary files a/doc/pub/week45/ipynb/Results/FigureFiles/gdclassiffierroc.png and b/doc/pub/week45/ipynb/Results/FigureFiles/gdclassiffierroc.png differ
diff --git a/doc/pub/week45/ipynb/Results/FigureFiles/gdregression.png b/doc/pub/week45/ipynb/Results/FigureFiles/gdregression.png
index 1ed660285..c70b1c457 100644
Binary files a/doc/pub/week45/ipynb/Results/FigureFiles/gdregression.png and b/doc/pub/week45/ipynb/Results/FigureFiles/gdregression.png differ
diff --git a/doc/pub/week45/ipynb/Results/FigureFiles/xdclassiffierconfusion.png b/doc/pub/week45/ipynb/Results/FigureFiles/xdclassiffierconfusion.png
index 7ce4eb554..20b208468 100644
Binary files a/doc/pub/week45/ipynb/Results/FigureFiles/xdclassiffierconfusion.png and b/doc/pub/week45/ipynb/Results/FigureFiles/xdclassiffierconfusion.png differ
diff --git a/doc/pub/week45/ipynb/Results/FigureFiles/xdclassiffierroc.png b/doc/pub/week45/ipynb/Results/FigureFiles/xdclassiffierroc.png
index 9bcef7025..9aa3b15ab 100644
Binary files a/doc/pub/week45/ipynb/Results/FigureFiles/xdclassiffierroc.png and b/doc/pub/week45/ipynb/Results/FigureFiles/xdclassiffierroc.png differ
diff --git a/doc/pub/week45/ipynb/ipynb-week45-src.tar.gz b/doc/pub/week45/ipynb/ipynb-week45-src.tar.gz
index 6adbec2fb..c4147c2ea 100644
Binary files a/doc/pub/week45/ipynb/ipynb-week45-src.tar.gz and b/doc/pub/week45/ipynb/ipynb-week45-src.tar.gz differ
diff --git a/doc/pub/week45/ipynb/week45.ipynb b/doc/pub/week45/ipynb/week45.ipynb
index 3fa52058a..892d48db3 100644
--- a/doc/pub/week45/ipynb/week45.ipynb
+++ b/doc/pub/week45/ipynb/week45.ipynb
@@ -2,7 +2,7 @@
"cells": [
{
"cell_type": "markdown",
- "id": "7a978d39",
+ "id": "0390330f",
"metadata": {
"editable": true
},
@@ -14,7 +14,7 @@
},
{
"cell_type": "markdown",
- "id": "e0283e6d",
+ "id": "ed227e0a",
"metadata": {
"editable": true
},
@@ -29,7 +29,7 @@
},
{
"cell_type": "markdown",
- "id": "a3136428",
+ "id": "a929ebc6",
"metadata": {
"editable": true
},
@@ -57,7 +57,7 @@
},
{
"cell_type": "markdown",
- "id": "e2e0134a",
+ "id": "85e77790",
"metadata": {
"editable": true
},
@@ -68,7 +68,7 @@
{
"cell_type": "code",
"execution_count": 1,
- "id": "2fdb28db",
+ "id": "5e91cc51",
"metadata": {
"collapsed": false,
"editable": true
@@ -168,7 +168,7 @@
},
{
"cell_type": "markdown",
- "id": "eb3a5ee9",
+ "id": "f274de50",
"metadata": {
"editable": true
},
@@ -188,7 +188,7 @@
},
{
"cell_type": "markdown",
- "id": "b793724a",
+ "id": "a3ee5d55",
"metadata": {
"editable": true
},
@@ -202,7 +202,7 @@
},
{
"cell_type": "markdown",
- "id": "f2c22ac4",
+ "id": "2618a55d",
"metadata": {
"editable": true
},
@@ -214,7 +214,7 @@
},
{
"cell_type": "markdown",
- "id": "cbaa4a6f",
+ "id": "597685fa",
"metadata": {
"editable": true
},
@@ -231,7 +231,7 @@
},
{
"cell_type": "markdown",
- "id": "c0ea84be",
+ "id": "8c005547",
"metadata": {
"editable": true
},
@@ -243,7 +243,7 @@
},
{
"cell_type": "markdown",
- "id": "94736458",
+ "id": "f0d95638",
"metadata": {
"editable": true
},
@@ -257,7 +257,7 @@
},
{
"cell_type": "markdown",
- "id": "b41565d5",
+ "id": "e1458787",
"metadata": {
"editable": true
},
@@ -269,7 +269,7 @@
},
{
"cell_type": "markdown",
- "id": "c1b8efd9",
+ "id": "ee5a736f",
"metadata": {
"editable": true
},
@@ -282,7 +282,7 @@
},
{
"cell_type": "markdown",
- "id": "7f7e8a84",
+ "id": "bed00bbe",
"metadata": {
"editable": true
},
@@ -294,7 +294,7 @@
},
{
"cell_type": "markdown",
- "id": "ed8d7b77",
+ "id": "1fe3bb5f",
"metadata": {
"editable": true
},
@@ -304,7 +304,7 @@
},
{
"cell_type": "markdown",
- "id": "4246f00d",
+ "id": "df99ec7e",
"metadata": {
"editable": true
},
@@ -332,7 +332,7 @@
},
{
"cell_type": "markdown",
- "id": "6ccbc0e9",
+ "id": "e4b524c4",
"metadata": {
"editable": true
},
@@ -348,7 +348,7 @@
},
{
"cell_type": "markdown",
- "id": "4b4f4548",
+ "id": "19c819b0",
"metadata": {
"editable": true
},
@@ -360,7 +360,7 @@
},
{
"cell_type": "markdown",
- "id": "f5434423",
+ "id": "8d109790",
"metadata": {
"editable": true
},
@@ -371,7 +371,7 @@
},
{
"cell_type": "markdown",
- "id": "a4c33651",
+ "id": "ee081a3a",
"metadata": {
"editable": true
},
@@ -383,7 +383,7 @@
},
{
"cell_type": "markdown",
- "id": "d25fd438",
+ "id": "b2bae97d",
"metadata": {
"editable": true
},
@@ -393,7 +393,7 @@
},
{
"cell_type": "markdown",
- "id": "261f7514",
+ "id": "5223b5c2",
"metadata": {
"editable": true
},
@@ -405,7 +405,7 @@
},
{
"cell_type": "markdown",
- "id": "ee46c495",
+ "id": "ce26055f",
"metadata": {
"editable": true
},
@@ -415,7 +415,7 @@
},
{
"cell_type": "markdown",
- "id": "4b6cf657",
+ "id": "fc99c7cc",
"metadata": {
"editable": true
},
@@ -427,7 +427,7 @@
},
{
"cell_type": "markdown",
- "id": "07fd8905",
+ "id": "3a9d23a2",
"metadata": {
"editable": true
},
@@ -437,7 +437,7 @@
},
{
"cell_type": "markdown",
- "id": "17699be3",
+ "id": "760e7406",
"metadata": {
"editable": true
},
@@ -449,7 +449,7 @@
},
{
"cell_type": "markdown",
- "id": "91046f02",
+ "id": "40c20004",
"metadata": {
"editable": true
},
@@ -463,7 +463,7 @@
},
{
"cell_type": "markdown",
- "id": "b886c010",
+ "id": "9b3e0a3b",
"metadata": {
"editable": true
},
@@ -479,7 +479,7 @@
},
{
"cell_type": "markdown",
- "id": "b5f82299",
+ "id": "2130f355",
"metadata": {
"editable": true
},
@@ -491,7 +491,7 @@
},
{
"cell_type": "markdown",
- "id": "9843cd00",
+ "id": "e0dd6c3b",
"metadata": {
"editable": true
},
@@ -507,7 +507,7 @@
},
{
"cell_type": "markdown",
- "id": "1090524c",
+ "id": "2caa0cd9",
"metadata": {
"editable": true
},
@@ -519,7 +519,7 @@
},
{
"cell_type": "markdown",
- "id": "f3088911",
+ "id": "5c322d03",
"metadata": {
"editable": true
},
@@ -529,7 +529,7 @@
},
{
"cell_type": "markdown",
- "id": "4ba3fedb",
+ "id": "43bc091e",
"metadata": {
"editable": true
},
@@ -541,7 +541,7 @@
},
{
"cell_type": "markdown",
- "id": "6e447640",
+ "id": "74f9b600",
"metadata": {
"editable": true
},
@@ -553,7 +553,7 @@
},
{
"cell_type": "markdown",
- "id": "a114cfe7",
+ "id": "8fa9b8d2",
"metadata": {
"editable": true
},
@@ -565,7 +565,7 @@
},
{
"cell_type": "markdown",
- "id": "a00f5ba6",
+ "id": "c5fb7346",
"metadata": {
"editable": true
},
@@ -576,7 +576,7 @@
},
{
"cell_type": "markdown",
- "id": "ea0be85b",
+ "id": "6265022d",
"metadata": {
"editable": true
},
@@ -588,7 +588,7 @@
},
{
"cell_type": "markdown",
- "id": "a65ab9b7",
+ "id": "9427f3b7",
"metadata": {
"editable": true
},
@@ -599,7 +599,7 @@
},
{
"cell_type": "markdown",
- "id": "b7cffa99",
+ "id": "41e09593",
"metadata": {
"editable": true
},
@@ -611,7 +611,7 @@
},
{
"cell_type": "markdown",
- "id": "081d507c",
+ "id": "4e5d6ddd",
"metadata": {
"editable": true
},
@@ -621,7 +621,7 @@
},
{
"cell_type": "markdown",
- "id": "6e734ee3",
+ "id": "ceaf8ca9",
"metadata": {
"editable": true
},
@@ -633,7 +633,7 @@
},
{
"cell_type": "markdown",
- "id": "ee564d2c",
+ "id": "fdfb1c53",
"metadata": {
"editable": true
},
@@ -645,7 +645,7 @@
},
{
"cell_type": "markdown",
- "id": "a9cc2890",
+ "id": "3c2001ad",
"metadata": {
"editable": true
},
@@ -657,7 +657,7 @@
},
{
"cell_type": "markdown",
- "id": "3a89610f",
+ "id": "caddc076",
"metadata": {
"editable": true
},
@@ -669,7 +669,7 @@
},
{
"cell_type": "markdown",
- "id": "a2b97b3f",
+ "id": "bd6ceda0",
"metadata": {
"editable": true
},
@@ -679,7 +679,7 @@
},
{
"cell_type": "markdown",
- "id": "edd6b448",
+ "id": "2d13c739",
"metadata": {
"editable": true
},
@@ -691,7 +691,7 @@
},
{
"cell_type": "markdown",
- "id": "6e5b95b5",
+ "id": "b0bf2d85",
"metadata": {
"editable": true
},
@@ -701,7 +701,7 @@
},
{
"cell_type": "markdown",
- "id": "3e656f64",
+ "id": "a903716f",
"metadata": {
"editable": true
},
@@ -713,7 +713,7 @@
},
{
"cell_type": "markdown",
- "id": "871fb2d1",
+ "id": "5759332b",
"metadata": {
"editable": true
},
@@ -723,7 +723,7 @@
},
{
"cell_type": "markdown",
- "id": "80d6e316",
+ "id": "926af936",
"metadata": {
"editable": true
},
@@ -735,7 +735,7 @@
},
{
"cell_type": "markdown",
- "id": "939363d6",
+ "id": "4b2ec03e",
"metadata": {
"editable": true
},
@@ -745,7 +745,7 @@
},
{
"cell_type": "markdown",
- "id": "70e5b39d",
+ "id": "4adaec50",
"metadata": {
"editable": true
},
@@ -757,7 +757,7 @@
},
{
"cell_type": "markdown",
- "id": "1394fd74",
+ "id": "33247b99",
"metadata": {
"editable": true
},
@@ -767,7 +767,7 @@
},
{
"cell_type": "markdown",
- "id": "6909eec6",
+ "id": "459b88e8",
"metadata": {
"editable": true
},
@@ -779,7 +779,7 @@
},
{
"cell_type": "markdown",
- "id": "d7b56142",
+ "id": "fb1c0ed4",
"metadata": {
"editable": true
},
@@ -799,7 +799,7 @@
},
{
"cell_type": "markdown",
- "id": "a31c3041",
+ "id": "16fab3df",
"metadata": {
"editable": true
},
@@ -811,7 +811,7 @@
},
{
"cell_type": "markdown",
- "id": "a771e5f4",
+ "id": "c3a727d8",
"metadata": {
"editable": true
},
@@ -821,7 +821,7 @@
},
{
"cell_type": "markdown",
- "id": "9a9c96d1",
+ "id": "53dbd815",
"metadata": {
"editable": true
},
@@ -837,7 +837,7 @@
},
{
"cell_type": "markdown",
- "id": "07323be9",
+ "id": "41b2997e",
"metadata": {
"editable": true
},
@@ -849,7 +849,7 @@
},
{
"cell_type": "markdown",
- "id": "3c996e3d",
+ "id": "c5fe12ab",
"metadata": {
"editable": true
},
@@ -877,7 +877,7 @@
},
{
"cell_type": "markdown",
- "id": "39637844",
+ "id": "2473e65c",
"metadata": {
"editable": true
},
@@ -890,7 +890,7 @@
{
"cell_type": "code",
"execution_count": 2,
- "id": "76903ecb",
+ "id": "d8294a5a",
"metadata": {
"collapsed": false,
"editable": true
@@ -900,20 +900,13 @@
"from sklearn.ensemble import AdaBoostClassifier\n",
"\n",
"ada_clf = AdaBoostClassifier(\n",
- " DecisionTreeClassifier(max_depth=1), n_estimators=200,\n",
- " algorithm=\"SAMME.R\", learning_rate=0.5, random_state=42)\n",
+ " DecisionTreeClassifier(max_depth=2), n_estimators=200,\n",
+ " algorithm=\"SAMME.R\", learning_rate=0.01, random_state=42)\n",
"ada_clf.fit(X_train, y_train)\n",
- "\n",
- "from sklearn.ensemble import AdaBoostClassifier\n",
- "\n",
- "ada_clf = AdaBoostClassifier(\n",
- " DecisionTreeClassifier(max_depth=1), n_estimators=200,\n",
- " algorithm=\"SAMME.R\", learning_rate=0.5, random_state=42)\n",
- "ada_clf.fit(X_train_scaled, y_train)\n",
- "y_pred = ada_clf.predict(X_test_scaled)\n",
+ "y_pred = ada_clf.predict(X_test)\n",
"skplt.metrics.plot_confusion_matrix(y_test, y_pred, normalize=True)\n",
"plt.show()\n",
- "y_probas = ada_clf.predict_proba(X_test_scaled)\n",
+ "y_probas = ada_clf.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",
@@ -922,7 +915,7 @@
},
{
"cell_type": "markdown",
- "id": "ca8755d2",
+ "id": "978e8480",
"metadata": {
"editable": true
},
@@ -940,7 +933,7 @@
},
{
"cell_type": "markdown",
- "id": "f0463b3c",
+ "id": "a523f5cf",
"metadata": {
"editable": true
},
@@ -953,7 +946,7 @@
},
{
"cell_type": "markdown",
- "id": "8b514ec6",
+ "id": "2f8962b5",
"metadata": {
"editable": true
},
@@ -965,7 +958,7 @@
},
{
"cell_type": "markdown",
- "id": "423db9ff",
+ "id": "b589f52f",
"metadata": {
"editable": true
},
@@ -975,7 +968,7 @@
},
{
"cell_type": "markdown",
- "id": "06b275d6",
+ "id": "6789a65a",
"metadata": {
"editable": true
},
@@ -987,7 +980,7 @@
},
{
"cell_type": "markdown",
- "id": "4ca06fe0",
+ "id": "5b79bf7a",
"metadata": {
"editable": true
},
@@ -997,7 +990,7 @@
},
{
"cell_type": "markdown",
- "id": "da5754bd",
+ "id": "e29a5715",
"metadata": {
"editable": true
},
@@ -1009,7 +1002,7 @@
},
{
"cell_type": "markdown",
- "id": "c0f54e05",
+ "id": "76985d66",
"metadata": {
"editable": true
},
@@ -1022,7 +1015,7 @@
},
{
"cell_type": "markdown",
- "id": "9152ac2b",
+ "id": "0856533f",
"metadata": {
"editable": true
},
@@ -1034,7 +1027,7 @@
},
{
"cell_type": "markdown",
- "id": "a4d9623f",
+ "id": "62fddf2a",
"metadata": {
"editable": true
},
@@ -1046,7 +1039,7 @@
},
{
"cell_type": "markdown",
- "id": "5c95acd3",
+ "id": "793e5b50",
"metadata": {
"editable": true
},
@@ -1058,7 +1051,7 @@
},
{
"cell_type": "markdown",
- "id": "08667505",
+ "id": "ef01915e",
"metadata": {
"editable": true
},
@@ -1068,7 +1061,7 @@
},
{
"cell_type": "markdown",
- "id": "95940c93",
+ "id": "9ad855b9",
"metadata": {
"editable": true
},
@@ -1080,7 +1073,7 @@
},
{
"cell_type": "markdown",
- "id": "888345e6",
+ "id": "c9ecda21",
"metadata": {
"editable": true
},
@@ -1090,7 +1083,7 @@
},
{
"cell_type": "markdown",
- "id": "3aa4d471",
+ "id": "bb743a44",
"metadata": {
"editable": true
},
@@ -1106,7 +1099,7 @@
},
{
"cell_type": "markdown",
- "id": "7778dcfd",
+ "id": "dcabad2c",
"metadata": {
"editable": true
},
@@ -1118,7 +1111,7 @@
},
{
"cell_type": "markdown",
- "id": "70b44d33",
+ "id": "3203ed8a",
"metadata": {
"editable": true
},
@@ -1139,7 +1132,7 @@
},
{
"cell_type": "markdown",
- "id": "4ca117e7",
+ "id": "72d87e5d",
"metadata": {
"editable": true
},
@@ -1150,7 +1143,7 @@
{
"cell_type": "code",
"execution_count": 3,
- "id": "2039b018",
+ "id": "6952ec4a",
"metadata": {
"collapsed": false,
"editable": true
@@ -1202,7 +1195,7 @@
},
{
"cell_type": "markdown",
- "id": "6db0b31b",
+ "id": "541e23cb",
"metadata": {
"editable": true
},
@@ -1213,7 +1206,7 @@
{
"cell_type": "code",
"execution_count": 4,
- "id": "de26bfe7",
+ "id": "20ea1ea2",
"metadata": {
"collapsed": false,
"editable": true
@@ -1246,7 +1239,7 @@
"#Cross validation\n",
"accuracy = cross_validate(gd_clf,X_test_scaled,y_test,cv=10)['test_score']\n",
"print(accuracy)\n",
- "print(\"Test set accuracy with Random Forests and scaled data: {:.2f}\".format(gd_clf.score(X_test_scaled,y_test)))\n",
+ "print(\"Test set accuracy with Gradient boosting and scaled data: {:.2f}\".format(gd_clf.score(X_test_scaled,y_test)))\n",
"\n",
"import scikitplot as skplt\n",
"y_pred = gd_clf.predict(X_test_scaled)\n",
@@ -1264,7 +1257,7 @@
},
{
"cell_type": "markdown",
- "id": "98629401",
+ "id": "3743f453",
"metadata": {
"editable": true
},
@@ -1287,7 +1280,7 @@
},
{
"cell_type": "markdown",
- "id": "70f7d4cc",
+ "id": "0a0e233f",
"metadata": {
"editable": true
},
@@ -1298,7 +1291,7 @@
{
"cell_type": "code",
"execution_count": 5,
- "id": "01dab946",
+ "id": "09ac4619",
"metadata": {
"collapsed": false,
"editable": true
@@ -1350,7 +1343,7 @@
},
{
"cell_type": "markdown",
- "id": "f132426b",
+ "id": "b6b421c6",
"metadata": {
"editable": true
},
@@ -1363,7 +1356,7 @@
{
"cell_type": "code",
"execution_count": 6,
- "id": "7bed8a59",
+ "id": "69a4d95f",
"metadata": {
"collapsed": false,
"editable": true
@@ -1397,7 +1390,7 @@
"\n",
"y_test = xg_clf.predict(X_test_scaled)\n",
"\n",
- "print(\"Test set accuracy with Random Forests and scaled data: {:.2f}\".format(xg_clf.score(X_test_scaled,y_test)))\n",
+ "print(\"Test set accuracy with Gradient Boosting and scaled data: {:.2f}\".format(xg_clf.score(X_test_scaled,y_test)))\n",
"\n",
"import scikitplot as skplt\n",
"y_pred = xg_clf.predict(X_test_scaled)\n",
diff --git a/doc/src/week45/week45.do.txt b/doc/src/week45/week45.do.txt
index 410d6fce0..bdd276b58 100644
--- a/doc/src/week45/week45.do.txt
+++ b/doc/src/week45/week45.do.txt
@@ -420,20 +420,13 @@ Using _Scikit-Learn_ it is easy to apply the adaptive boosting algorithm, as don
from sklearn.ensemble import AdaBoostClassifier
ada_clf = AdaBoostClassifier(
- DecisionTreeClassifier(max_depth=1), n_estimators=200,
- algorithm="SAMME.R", learning_rate=0.5, random_state=42)
+ DecisionTreeClassifier(max_depth=2), n_estimators=200,
+ algorithm="SAMME.R", learning_rate=0.01, random_state=42)
ada_clf.fit(X_train, y_train)
-
-from sklearn.ensemble import AdaBoostClassifier
-
-ada_clf = AdaBoostClassifier(
- DecisionTreeClassifier(max_depth=1), n_estimators=200,
- algorithm="SAMME.R", learning_rate=0.5, random_state=42)
-ada_clf.fit(X_train_scaled, y_train)
-y_pred = ada_clf.predict(X_test_scaled)
+y_pred = ada_clf.predict(X_test)
skplt.metrics.plot_confusion_matrix(y_test, y_pred, normalize=True)
plt.show()
-y_probas = ada_clf.predict_proba(X_test_scaled)
+y_probas = ada_clf.predict_proba(X_test)
skplt.metrics.plot_roc(y_test, y_probas)
plt.show()
skplt.metrics.plot_cumulative_gain(y_test, y_probas)
@@ -606,7 +599,7 @@ gd_clf.fit(X_train_scaled, y_train)
#Cross validation
accuracy = cross_validate(gd_clf,X_test_scaled,y_test,cv=10)['test_score']
print(accuracy)
-print("Test set accuracy with Random Forests and scaled data: {:.2f}".format(gd_clf.score(X_test_scaled,y_test)))
+print("Test set accuracy with Gradient boosting and scaled data: {:.2f}".format(gd_clf.score(X_test_scaled,y_test)))
import scikitplot as skplt
y_pred = gd_clf.predict(X_test_scaled)
@@ -720,7 +713,7 @@ xg_clf.fit(X_train_scaled,y_train)
y_test = xg_clf.predict(X_test_scaled)
-print("Test set accuracy with Random Forests and scaled data: {:.2f}".format(xg_clf.score(X_test_scaled,y_test)))
+print("Test set accuracy with Gradient Boosting and scaled data: {:.2f}".format(xg_clf.score(X_test_scaled,y_test)))
import scikitplot as skplt
y_pred = xg_clf.predict(X_test_scaled)