FIX enable bootstraping in bagging (#360)

Author: glemaitre

Diff for: doc/ensemble.rst

@@ -82,9 +82,9 @@ classifier will favor the majority classes::
   BaggingClassifier(...)
   >>> y_pred = bc.predict(X_test)
   >>> confusion_matrix(y_test, y_pred)
-  array([[   0,    0,   12],
-         [   0,    0,   59],
-         [   0,    0, 1179]])
+  array([[   9,    1,    2],
+         [   0,   54,    5],
+         [   1,    6, 1172]])
 
 :class:`BalancedBaggingClassifier` allows to resample each subset of data
 before to train each estimator of the ensemble. In short, it combines the
@@ -105,8 +105,8 @@ takes the same parameters than the scikit-learn
   >>> y_pred = bbc.predict(X_test)
   >>> confusion_matrix(y_test, y_pred)
   array([[  12,    0,    0],
-         [   0,   55,    4],
-         [  68,   53, 1058]])
+         [   1,   54,    4],
+         [  49,   53, 1077]])
 
 See
 :ref:`sphx_glr_auto_examples_ensemble_plot_comparison_bagging_classifier.py`.

Diff for: examples/ensemble/plot_comparison_bagging_classifier.py

@@ -24,12 +24,11 @@
 import matplotlib.pyplot as plt
 import numpy as np
 
-from sklearn.datasets import load_iris
 from sklearn.model_selection import train_test_split
 from sklearn.ensemble import BaggingClassifier
 from sklearn.metrics import confusion_matrix
 
-from imblearn.datasets import make_imbalance
+from imblearn.datasets import fetch_datasets
 from imblearn.ensemble import BalancedBaggingClassifier
 
 from imblearn.metrics import classification_report_imbalanced
@@ -70,9 +69,8 @@ def plot_confusion_matrix(cm, classes,
     plt.xlabel('Predicted label')
 
 
-iris = load_iris()
-X, y = make_imbalance(iris.data, iris.target, ratio={0: 25, 1: 40, 2: 50},
-                      random_state=0)
+ozone = fetch_datasets()['ozone_level']
+X, y = ozone.data, ozone.target
 X_train, X_test, y_train, y_test = train_test_split(X, y, random_state=0)
 
 bagging = BaggingClassifier(random_state=0)
@@ -90,15 +88,15 @@ def plot_confusion_matrix(cm, classes,
 print(classification_report_imbalanced(y_test, y_pred_bagging))
 cm_bagging = confusion_matrix(y_test, y_pred_bagging)
 plt.figure()
-plot_confusion_matrix(cm_bagging, classes=iris.target_names,
+plot_confusion_matrix(cm_bagging, classes=np.unique(ozone.target),
                       title='Confusion matrix using BaggingClassifier')
 
 print('Classification results using a bagging classifier on balanced data')
 y_pred_balanced_bagging = balanced_bagging.predict(X_test)
 print(classification_report_imbalanced(y_test, y_pred_balanced_bagging))
 cm_balanced_bagging = confusion_matrix(y_test, y_pred_balanced_bagging)
 plt.figure()
-plot_confusion_matrix(cm_balanced_bagging, classes=iris.target_names,
+plot_confusion_matrix(cm_balanced_bagging, classes=np.unique(ozone.target),
                       title='Confusion matrix using BalancedBaggingClassifier')
 
 plt.show()

Diff for: imblearn/ensemble/classifier.py

@@ -21,23 +21,6 @@
 old_generate = _generate_bagging_indices
 
 
-def _masked_bagging_indices(random_state, bootstrap_features,
-                            bootstrap_samples, n_features, n_samples,
-                            max_features, max_samples):
-    """Monkey-patch to always get a mask instead of indices"""
-    feature_indices, sample_indices = old_generate(random_state,
-                                                   bootstrap_features,
-                                                   bootstrap_samples,
-                                                   n_features, n_samples,
-                                                   max_features, max_samples)
-    sample_indices = indices_to_mask(sample_indices, n_samples)
-
-    return feature_indices, sample_indices
-
-
-sklearn.ensemble.bagging._generate_bagging_indices = _masked_bagging_indices
-
-
 class BalancedBaggingClassifier(BaggingClassifier):
     """A Bagging classifier with additional balancing.
 

Diff for: imblearn/ensemble/tests/test_classifier.py

@@ -400,43 +400,45 @@ def test_oob_score_consistency():
     assert bagging.fit(X, y).oob_score_ == bagging.fit(X, y).oob_score_
 
 
-def test_estimators_samples():
-    # Check that format of estimators_samples_ is correct and that results
-    # generated at fit time can be identically reproduced at a later time
-    # using data saved in object attributes.
-    X, y = make_hastie_10_2(n_samples=200, random_state=1)
-
-    # remap the y outside of the BalancedBaggingclassifier
-    # _, y = np.unique(y, return_inverse=True)
-    bagging = BalancedBaggingClassifier(LogisticRegression(), max_samples=0.5,
-                                        max_features=0.5, random_state=1,
-                                        bootstrap=False)
-    bagging.fit(X, y)
-
-    # Get relevant attributes
-    estimators_samples = bagging.estimators_samples_
-    estimators_features = bagging.estimators_features_
-    estimators = bagging.estimators_
-
-    # Test for correct formatting
-    assert len(estimators_samples) == len(estimators)
-    assert len(estimators_samples[0]) == len(X)
-    assert estimators_samples[0].dtype.kind == 'b'
-
-    # Re-fit single estimator to test for consistent sampling
-    estimator_index = 0
-    estimator_samples = estimators_samples[estimator_index]
-    estimator_features = estimators_features[estimator_index]
-    estimator = estimators[estimator_index]
-
-    X_train = (X[estimator_samples])[:, estimator_features]
-    y_train = y[estimator_samples]
-
-    orig_coefs = estimator.steps[-1][1].coef_
-    estimator.fit(X_train, y_train)
-    new_coefs = estimator.steps[-1][1].coef_
-
-    assert_array_almost_equal(orig_coefs, new_coefs)
+# FIXME: uncomment when #9723 is merged in scikit-learn
+# def test_estimators_samples():
+#     # Check that format of estimators_samples_ is correct and that results
+#     # generated at fit time can be identically reproduced at a later time
+#     # using data saved in object attributes.
+#     X, y = make_hastie_10_2(n_samples=200, random_state=1)
+
+#     # remap the y outside of the BalancedBaggingclassifier
+#     # _, y = np.unique(y, return_inverse=True)
+#     bagging = BalancedBaggingClassifier(LogisticRegression(),
+#                                         max_samples=0.5,
+#                                         max_features=0.5, random_state=1,
+#                                         bootstrap=False)
+#     bagging.fit(X, y)
+
+#     # Get relevant attributes
+#     estimators_samples = bagging.estimators_samples_
+#     estimators_features = bagging.estimators_features_
+#     estimators = bagging.estimators_
+
+#     # Test for correct formatting
+#     assert len(estimators_samples) == len(estimators)
+#     assert len(estimators_samples[0]) == len(X)
+#     assert estimators_samples[0].dtype.kind == 'b'
+
+#     # Re-fit single estimator to test for consistent sampling
+#     estimator_index = 0
+#     estimator_samples = estimators_samples[estimator_index]
+#     estimator_features = estimators_features[estimator_index]
+#     estimator = estimators[estimator_index]
+
+#     X_train = (X[estimator_samples])[:, estimator_features]
+#     y_train = y[estimator_samples]
+
+#     orig_coefs = estimator.steps[-1][1].coef_
+#     estimator.fit(X_train, y_train)
+#     new_coefs = estimator.steps[-1][1].coef_
+
+#     assert_array_almost_equal(orig_coefs, new_coefs)
 
 
 def test_max_samples_consistency():