jwjohnson314
diff --git a/‎sklearn/metrics/classification.py
Copy file name to clipboardExpand all lines: sklearn/metrics/classification.py
+8-2Lines changed: 8 additions & 2 deletions b/‎sklearn/metrics/classification.py
Copy file name to clipboardExpand all lines: sklearn/metrics/classification.py
+8-2Lines changed: 8 additions & 2 deletions
diff --git a/‎sklearn/metrics/regression.py
Copy file name to clipboardExpand all lines: sklearn/metrics/regression.py
+5Lines changed: 5 additions & 0 deletions b/‎sklearn/metrics/regression.py
Copy file name to clipboardExpand all lines: sklearn/metrics/regression.py
+5Lines changed: 5 additions & 0 deletions
diff --git a/‎sklearn/metrics/tests/test_common.py
Copy file name to clipboardExpand all lines: sklearn/metrics/tests/test_common.py
+10-4Lines changed: 10 additions & 4 deletions b/‎sklearn/metrics/tests/test_common.py
Copy file name to clipboardExpand all lines: sklearn/metrics/tests/test_common.py
+10-4Lines changed: 10 additions & 4 deletions
@@ -174,6 +174,7 @@ def accuracy_score(y_true, y_pred, normalize=True, sample_weight=None):
 
     # Compute accuracy for each possible representation
     y_type, y_true, y_pred = _check_targets(y_true, y_pred)
+    check_consistent_length(y_true, y_pred, sample_weight)
     if y_type.startswith('multilabel'):
         differing_labels = count_nonzero(y_true - y_pred, axis=1)
         score = differing_labels == 0
@@ -337,7 +338,7 @@ def confusion_matrix(y_true, y_pred, labels=None, sample_weight=None):
     else:
         sample_weight = np.asarray(sample_weight)
 
-    check_consistent_length(sample_weight, y_true, y_pred)
+    check_consistent_length(y_true, y_pred, sample_weight)
 
     n_labels = labels.size
     label_to_ind = dict((y, x) for x, y in enumerate(labels))
@@ -518,6 +519,7 @@ def jaccard_similarity_score(y_true, y_pred, normalize=True,
 
     # Compute accuracy for each possible representation
     y_type, y_true, y_pred = _check_targets(y_true, y_pred)
+    check_consistent_length(y_true, y_pred, sample_weight)
     if y_type.startswith('multilabel'):
         with np.errstate(divide='ignore', invalid='ignore'):
             # oddly, we may get an "invalid" rather than a "divide" error here
@@ -593,6 +595,7 @@ def matthews_corrcoef(y_true, y_pred, sample_weight=None):
     -0.33...
     """
     y_type, y_true, y_pred = _check_targets(y_true, y_pred)
+    check_consistent_length(y_true, y_pred, sample_weight)
     if y_type not in {"binary", "multiclass"}:
         raise ValueError("%s is not supported" % y_type)
 
@@ -1097,6 +1100,7 @@ def precision_recall_fscore_support(y_true, y_pred, beta=1.0, labels=None,
         raise ValueError("beta should be >0 in the F-beta score")
 
     y_type, y_true, y_pred = _check_targets(y_true, y_pred)
+    check_consistent_length(y_true, y_pred, sample_weight)
     present_labels = unique_labels(y_true, y_pred)
 
     if average == 'binary':
@@ -1624,6 +1628,7 @@ def hamming_loss(y_true, y_pred, labels=None, sample_weight=None,
         labels = classes
 
     y_type, y_true, y_pred = _check_targets(y_true, y_pred)
+    check_consistent_length(y_true, y_pred, sample_weight)
 
     if labels is None:
         labels = unique_labels(y_true, y_pred)
@@ -1712,7 +1717,7 @@ def log_loss(y_true, y_pred, eps=1e-15, normalize=True, sample_weight=None,
     The logarithm used is the natural logarithm (base-e).
     """
     y_pred = check_array(y_pred, ensure_2d=False)
-    check_consistent_length(y_pred, y_true)
+    check_consistent_length(y_pred, y_true, sample_weight)
 
     lb = LabelBinarizer()
 
@@ -1985,6 +1990,7 @@ def brier_score_loss(y_true, y_prob, sample_weight=None, pos_label=None):
     y_prob = column_or_1d(y_prob)
     assert_all_finite(y_true)
     assert_all_finite(y_prob)
+    check_consistent_length(y_true, y_prob, sample_weight)
 
     if pos_label is None:
         pos_label = y_true.max()
 
@@ -168,6 +168,7 @@ def mean_absolute_error(y_true, y_pred,
     """
     y_type, y_true, y_pred, multioutput = _check_reg_targets(
         y_true, y_pred, multioutput)
+    check_consistent_length(y_true, y_pred, sample_weight)
     output_errors = np.average(np.abs(y_pred - y_true),
                                weights=sample_weight, axis=0)
     if isinstance(multioutput, string_types):
@@ -236,6 +237,7 @@ def mean_squared_error(y_true, y_pred,
     """
     y_type, y_true, y_pred, multioutput = _check_reg_targets(
         y_true, y_pred, multioutput)
+    check_consistent_length(y_true, y_pred, sample_weight)
     output_errors = np.average((y_true - y_pred) ** 2, axis=0,
                                weights=sample_weight)
     if isinstance(multioutput, string_types):
@@ -306,6 +308,7 @@ def mean_squared_log_error(y_true, y_pred,
     """
     y_type, y_true, y_pred, multioutput = _check_reg_targets(
         y_true, y_pred, multioutput)
+    check_consistent_length(y_true, y_pred, sample_weight)
 
     if not (y_true >= 0).all() and not (y_pred >= 0).all():
         raise ValueError("Mean Squared Logarithmic Error cannot be used when "
@@ -409,6 +412,7 @@ def explained_variance_score(y_true, y_pred,
     """
     y_type, y_true, y_pred, multioutput = _check_reg_targets(
         y_true, y_pred, multioutput)
+    check_consistent_length(y_true, y_pred, sample_weight)
 
     y_diff_avg = np.average(y_true - y_pred, weights=sample_weight, axis=0)
     numerator = np.average((y_true - y_pred - y_diff_avg) ** 2,
@@ -528,6 +532,7 @@ def r2_score(y_true, y_pred, sample_weight=None,
     """
     y_type, y_true, y_pred, multioutput = _check_reg_targets(
         y_true, y_pred, multioutput)
+    check_consistent_length(y_true, y_pred, sample_weight)
 
     if sample_weight is not None:
         sample_weight = column_or_1d(sample_weight)
 
@@ -9,6 +9,7 @@
 from sklearn.datasets import make_multilabel_classification
 from sklearn.preprocessing import LabelBinarizer
 from sklearn.utils.multiclass import type_of_target
+from sklearn.utils.validation import _num_samples
 from sklearn.utils.validation import check_random_state
 from sklearn.utils import shuffle
 
@@ -1005,10 +1006,15 @@ def check_sample_weight_invariance(name, metric, y1, y2):
                 err_msg="%s sample_weight is not invariant "
                         "under scaling" % name)
 
-    # Check that if sample_weight.shape[0] != y_true.shape[0], it raised an
-    # error
-    assert_raises(Exception, metric, y1, y2,
-                  sample_weight=np.hstack([sample_weight, sample_weight]))
+    # Check that if number of samples in y_true and sample_weight are not
+    # equal, meaningful error is raised.
+    error_message = ("Found input variables with inconsistent numbers of "
+                     "samples: [{}, {}, {}]".format(
+                         _num_samples(y1), _num_samples(y2),
+                         _num_samples(sample_weight) * 2))
+    assert_raise_message(ValueError, error_message, metric, y1, y2,
+                         sample_weight=np.hstack([sample_weight,
+                                                  sample_weight]))
 
 
 def test_sample_weight_invariance(n_samples=50):