ENH do not catch warning in check_estimators_empty_data_messages

ogrisel · ogrisel · commit 1c03c8b0eda3 · 2015-02-25T15:48:41.000+01:00
diff --git a/sklearn/utils/estimator_checks.py b/sklearn/utils/estimator_checks.py
@@ -348,25 +348,24 @@ def check_estimators_dtypes(name, Estimator):
 
 
 def check_estimators_empty_data_messages(name, Estimator, multi_output=False):
-    with warnings.catch_warnings(record=True):
-        e = Estimator()
-        set_fast_parameters(e)
-        set_random_state(e, 1)
-
-        X_zero_samples = np.empty(0).reshape(0, 3)
-        # The precise message can change depending on whether X or y is
-        # validated first. Let us test the type of exception only:
-        assert_raises(ValueError, e.fit, X_zero_samples, [])
-
-        X_zero_features = np.empty(0).reshape(3, 0)
-        # the following y should be accepted by both classifiers and regressors
-        # and ignored by unsupervised models
-        if multi_output:
-            y = np.array([[1, 1], [0, 1], [0, 1]])
-        else:
-            y = [1, 0, 1]
-        msg = "0 feature(s) (shape=(3, 0)) while a minimum of 1 is required."
-        assert_raise_message(ValueError, msg, e.fit, X_zero_features, y)
+    e = Estimator()
+    set_fast_parameters(e)
+    set_random_state(e, 1)
+
+    X_zero_samples = np.empty(0).reshape(0, 3)
+    # The precise message can change depending on whether X or y is
+    # validated first. Let us test the type of exception only:
+    assert_raises(ValueError, e.fit, X_zero_samples, [])
+
+    X_zero_features = np.empty(0).reshape(3, 0)
+    # the following y should be accepted by both classifiers and regressors
+    # and ignored by unsupervised models
+    if multi_output:
+        y = np.array([[1, 1], [0, 1], [0, 1]])
+    else:
+        y = [1, 0, 1]
+    msg = "0 feature(s) (shape=(3, 0)) while a minimum of 1 is required."
+    assert_raise_message(ValueError, msg, e.fit, X_zero_features, y)
 
 
 def check_estimators_nan_inf(name, Estimator):
