Pushing the docs for revision for branch: master, commit 25c931a50542cf6ce0d9a31372c91d0e43807773

Author: sklearn-ci

dev/_downloads/plot_pca_vs_fa_model_selection.py

@@ -23,7 +23,6 @@
 by Thomas P. Minka is also compared.
 
 """
-print(__doc__)
 
 # Authors: Alexandre Gramfort
 #          Denis A. Engemann
@@ -38,6 +37,8 @@
 from sklearn.model_selection import cross_val_score
 from sklearn.model_selection import GridSearchCV
 
+print(__doc__)
+
 ###############################################################################
 # Create the data
 
@@ -61,7 +62,7 @@
 
 
 def compute_scores(X):
-    pca = PCA()
+    pca = PCA(svd_solver='full')
     fa = FactorAnalysis()
 
     pca_scores, fa_scores = [], []
@@ -90,7 +91,7 @@ def lw_score(X):
     n_components_pca = n_components[np.argmax(pca_scores)]
     n_components_fa = n_components[np.argmax(fa_scores)]
 
-    pca = PCA(n_components='mle')
+    pca = PCA(svd_solver='full', n_components='mle')
     pca.fit(X)
     n_components_pca_mle = pca.n_components_
 
@@ -105,7 +106,8 @@ def lw_score(X):
     plt.axvline(n_components_pca, color='b',
                 label='PCA CV: %d' % n_components_pca, linestyle='--')
     plt.axvline(n_components_fa, color='r',
-                label='FactorAnalysis CV: %d' % n_components_fa, linestyle='--')
+                label='FactorAnalysis CV: %d' % n_components_fa,
+                linestyle='--')
     plt.axvline(n_components_pca_mle, color='k',
                 label='PCA MLE: %d' % n_components_pca_mle, linestyle='--')
 

dev/_downloads/plot_random_forest_regression_multioutput.py

@@ -0,0 +1,76 @@
+"""
+============================================================
+Comparing random forests and the multi-output meta estimator
+============================================================
+
+An example to compare multi-output regression with random forest and
+the :ref:`multioutput.MultiOutputRegressor <_multiclass>` meta-estimator.
+
+This example illustrates the use of the
+:ref:`multioutput.MultiOutputRegressor <_multiclass>` meta-estimator
+to perform multi-output regression. A random forest regressor is used,
+which supports multi-output regression natively, so the results can be
+compared.
+
+The random forest regressor will only ever predict values within the
+range of observations or closer to zero for each of the targets. As a
+result the predictions are biased towards the centre of the circle.
+
+Using a single underlying feature the model learns both the
+x and y coordinate as output.
+
+"""
+print(__doc__)
+
+# Author: Tim Head <[email protected]>
+#
+# License: BSD 3 clause
+
+import numpy as np
+import matplotlib.pyplot as plt
+from sklearn.ensemble import RandomForestRegressor
+from sklearn.model_selection import train_test_split
+from sklearn.multioutput import MultiOutputRegressor
+
+
+# Create a random dataset
+rng = np.random.RandomState(1)
+X = np.sort(200 * rng.rand(600, 1) - 100, axis=0)
+y = np.array([np.pi * np.sin(X).ravel(), np.pi * np.cos(X).ravel()]).T
+y += (0.5 - rng.rand(*y.shape))
+
+X_train, X_test, y_train, y_test = train_test_split(X, y,
+                                                    train_size=400,
+                                                    random_state=4)
+
+max_depth = 30
+regr_multirf = MultiOutputRegressor(RandomForestRegressor(max_depth=max_depth,
+                                                          random_state=0))
+regr_multirf.fit(X_train, y_train)
+
+regr_rf = RandomForestRegressor(max_depth=max_depth, random_state=2)
+regr_rf.fit(X_train, y_train)
+
+# Predict on new data
+y_multirf = regr_multirf.predict(X_test)
+y_rf = regr_rf.predict(X_test)
+
+# Plot the results
+plt.figure()
+s = 50
+a = 0.4
+plt.scatter(y_test[:, 0], y_test[:, 1],
+            c="navy", s=s, marker="s", alpha=a, label="Data")
+plt.scatter(y_multirf[:, 0], y_multirf[:, 1],
+            c="cornflowerblue", s=s, alpha=a,
+            label="Multi RF score=%.2f" % regr_multirf.score(X_test, y_test))
+plt.scatter(y_rf[:, 0], y_rf[:, 1],
+            c="c", s=s, marker="^", alpha=a,
+            label="RF score=%.2f" % regr_rf.score(X_test, y_test))
+plt.xlim([-6, 6])
+plt.ylim([-6, 6])
+plt.xlabel("target 1")
+plt.ylabel("target 2")
+plt.title("Comparing random forests and the multi-output meta estimator")
+plt.legend()
+plt.show()