Rebuild dev docs at master=0d26d54

Author: sklearn-ci

dev/_downloads/plot_feature_transformation.py

@@ -34,10 +34,10 @@
 from sklearn.linear_model import LogisticRegression
 from sklearn.ensemble import (RandomTreesEmbedding, RandomForestClassifier,
                               GradientBoostingClassifier)
-from sklearn.feature_selection import SelectFromModel
 from sklearn.preprocessing import OneHotEncoder
 from sklearn.cross_validation import train_test_split
 from sklearn.metrics import roc_curve
+from sklearn.pipeline import make_pipeline
 
 n_estimator = 10
 X, y = make_classification(n_samples=80000)
@@ -51,13 +51,13 @@
                                                             test_size=0.5)
 
 # Unsupervised transformation based on totally random trees
-rt = RandomTreesEmbedding(max_depth=3, n_estimators=n_estimator)
-rt_lm = LogisticRegression()
-rt.fit(X_train, y_train)
-rt_lm.fit(SelectFromModel(rt, prefit=True).transform(X_train_lr), y_train_lr)
+rt = RandomTreesEmbedding(max_depth=3, n_estimators=n_estimator,
+	random_state=0)
 
-y_pred_rt = rt_lm.predict_proba(
-	SelectFromModel(rt, prefit=True).transform(X_test))[:, 1]
+rt_lm = LogisticRegression()
+pipeline = make_pipeline(rt, rt_lm)
+pipeline.fit(X_train, y_train)
+y_pred_rt = pipeline.predict_proba(X_test)[:, 1]
 fpr_rt_lm, tpr_rt_lm, _ = roc_curve(y_test, y_pred_rt)
 
 # Supervised transformation based on random forests

dev/_downloads/plot_random_forest_embedding.py

@@ -30,17 +30,14 @@
 from sklearn.datasets import make_circles
 from sklearn.ensemble import RandomTreesEmbedding, ExtraTreesClassifier
 from sklearn.decomposition import TruncatedSVD
-from sklearn.feature_selection import SelectFromModel
 from sklearn.naive_bayes import BernoulliNB
 
 # make a synthetic dataset
 X, y = make_circles(factor=0.5, random_state=0, noise=0.05)
 
 # use RandomTreesEmbedding to transform data
 hasher = RandomTreesEmbedding(n_estimators=10, random_state=0, max_depth=3)
-hasher.fit(X)
-model = SelectFromModel(hasher, prefit=True)
-X_transformed = model.transform(X)
+X_transformed = hasher.fit_transform(X)
 
 # Visualize result using PCA
 pca = TruncatedSVD(n_components=2)

dev/_images/plot_feature_transformation.png

@@ -47,6 +47,6 @@ high-dimensional categorical embedding of the data.
 .. literalinclude:: plot_feature_transformation.py
     :lines: 23-
 
-**Total running time of the example:**  4.56 seconds
-( 0 minutes  4.56 seconds)
+**Total running time of the example:**  4.87 seconds
+( 0 minutes  4.87 seconds)