Merge pull request scikit-learn#3444 from arjoly/explain-default-score

[MRG+1] ENH + DOC set a default scorer in the multiclass module

Author: GaelVaroquaux

sklearn/base.py

@@ -270,12 +270,16 @@ class ClassifierMixin(object):
     def score(self, X, y, sample_weight=None):
         """Returns the mean accuracy on the given test data and labels.
 
+        In multi-label classification, this is the subset accuracy
+        which is a harsh metric since you require for each sample that
+        each label set be correctly predicted.
+
         Parameters
         ----------
         X : array-like, shape = (n_samples, n_features)
             Test samples.
 
-        y : array-like, shape = (n_samples,)
+        y : array-like, shape = (n_samples) or (n_samples, n_outputs)
             True labels for X.
 
         sample_weight : array-like, shape = [n_samples], optional
@@ -308,7 +312,7 @@ def score(self, X, y, sample_weight=None):
         X : array-like, shape = (n_samples, n_features)
             Test samples.
 
-        y : array-like, shape = (n_samples,)
+        y : array-like, shape = (n_samples) or (n_samples, n_outputs)
             True values for X.
 
         sample_weight : array-like, shape = [n_samples], optional

sklearn/multiclass.py

@@ -376,13 +376,6 @@ def multilabel_(self):
         """Whether this is a multilabel classifier"""
         return self.label_binarizer_.y_type_.startswith('multilabel')
 
-    def score(self, X, y):
-        if self.multilabel_:
-            raise NotImplementedError(
-                "score is not supported for multilabel classifiers")
-        else:
-            return super(OneVsRestClassifier, self).score(X, y)
-
     @property
     def classes_(self):
         return self.label_binarizer_.classes_