update

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)