[MRG + 1] Fix ValueError in LabelEncoder when using inverse_transform on unseen labels (#9816)

Charlie Newey · lesteve · commit c554aad456b6 · 2017-09-21T19:21:55.000+02:00
diff --git a/sklearn/preprocessing/label.py b/sklearn/preprocessing/label.py
@@ -130,7 +130,8 @@ def transform(self, y):
         classes = np.unique(y)
         if len(np.intersect1d(classes, self.classes_)) < len(classes):
             diff = np.setdiff1d(classes, self.classes_)
-            raise ValueError("y contains new labels: %s" % str(diff))
+            raise ValueError(
+                    "y contains previously unseen labels: %s" % str(diff))
         return np.searchsorted(self.classes_, y)
 
     def inverse_transform(self, y):
@@ -148,8 +149,9 @@ def inverse_transform(self, y):
         check_is_fitted(self, 'classes_')
 
         diff = np.setdiff1d(y, np.arange(len(self.classes_)))
-        if diff:
-            raise ValueError("y contains new labels: %s" % str(diff))
+        if len(diff):
+            raise ValueError(
+                    "y contains previously unseen labels: %s" % str(diff))
         y = np.asarray(y)
         return self.classes_[y]
 
diff --git a/sklearn/preprocessing/tests/test_label.py b/sklearn/preprocessing/tests/test_label.py
@@ -203,8 +203,10 @@ def test_label_encoder_errors():
 
     # Fail on unseen labels
     le = LabelEncoder()
-    le.fit([1, 2, 3, 1, -1])
-    assert_raises(ValueError, le.inverse_transform, [-1])
+    le.fit([1, 2, 3, -1, 1])
+    msg = "contains previously unseen labels"
+    assert_raise_message(ValueError, msg, le.inverse_transform, [-2])
+    assert_raise_message(ValueError, msg, le.inverse_transform, [-2, -3, -4])
 
 
 def test_sparse_output_multilabel_binarizer():
