[MRG+1] FIX AdaBoost ZeroDivisionError in proba #7501 (#8371)

dokato · jnothman · commit fb65a0a4bae0 · 2017-02-21T08:06:39.000+11:00
* FIX AdaBoost ZeroDivisionError in proba #7501 * FIX AdaBoost ZeroDivisionError in proba #7501 - tests corrected * FIX AdaBoost ZeroDivisionError in proba #7501 - tests corrected * FIX #7501 improvements suggested by lesteve introduced * FIX #7501 whats_new file updated * Tweak in rst
diff --git a/doc/whats_new.rst b/doc/whats_new.rst
@@ -153,11 +153,14 @@ Enhancements
 Bug fixes
 .........
 
+   - Fixed a bug where :class:`sklearn.ensemble.AdaBoostClassifier` throws
+     ``ZeroDivisionError`` while fitting data with single class labels.
+     :issue:`7501` by :user:`Dominik Krzeminski <dokato>`.
+
    - Fixed a bug where :func:`sklearn.model_selection.BaseSearchCV.inverse_transform`
      returns self.best_estimator_.transform() instead of self.best_estimator_.inverse_transform()
      :issue:`8344` by :user:`Akshay Gupta <Akshay0724>` 
 
-
    - Fixed a bug where :class:`sklearn.linear_model.RandomizedLasso` and
      :class:`sklearn.linear_model.RandomizedLogisticRegression` breaks for
      sparse input.
diff --git a/sklearn/ensemble/tests/test_weight_boosting.py b/sklearn/ensemble/tests/test_weight_boosting.py
@@ -74,6 +74,15 @@ def predict_proba(self, X):
     assert_array_equal(np.argmax(samme_proba, axis=1), [0, 1, 1, 1])
 
 
+def test_oneclass_adaboost_proba():
+    # Test predict_proba robustness for one class label input.
+    # In response to issue #7501
+    # https://github.com/scikit-learn/scikit-learn/issues/7501
+    y_t = np.ones(len(X))
+    clf = AdaBoostClassifier().fit(X, y_t)
+    assert_array_equal(clf.predict_proba(X), np.ones((len(X), 1)))
+
+
 def test_classification_toy():
     # Check classification on a toy dataset.
     for alg in ['SAMME', 'SAMME.R']:
diff --git a/sklearn/ensemble/weight_boosting.py b/sklearn/ensemble/weight_boosting.py
@@ -756,6 +756,9 @@ def predict_proba(self, X):
         n_classes = self.n_classes_
         X = self._validate_X_predict(X)
 
+        if n_classes == 1:
+            return np.ones((X.shape[0], 1))
+
         if self.algorithm == 'SAMME.R':
             # The weights are all 1. for SAMME.R
             proba = sum(_samme_proba(estimator, n_classes, X)
