[MRG+2] Fixed assumption fit attribute means object is estimator. (scikit-learn#8418)

drkatnz · NelleV · commit 9db2e5f81260 · 2017-08-11T09:31:30.000-07:00
diff --git a/sklearn/utils/tests/test_validation.py b/sklearn/utils/tests/test_validation.py
@@ -15,6 +15,7 @@
 from sklearn.utils.testing import assert_warns_message
 from sklearn.utils.testing import assert_warns
 from sklearn.utils.testing import ignore_warnings
+from sklearn.utils.testing import SkipTest
 from sklearn.utils import as_float_array, check_array, check_symmetric
 from sklearn.utils import check_X_y
 from sklearn.utils.mocking import MockDataFrame
@@ -501,3 +502,15 @@ def test_check_consistent_length():
     assert_raises_regexp(TypeError, 'estimator', check_consistent_length,
                          [1, 2], RandomForestRegressor())
     # XXX: We should have a test with a string, but what is correct behaviour?
+
+
+def test_check_dataframe_fit_attribute():
+    # check pandas dataframe with 'fit' column does not raise error
+    # https://github.com/scikit-learn/scikit-learn/issues/8415
+    try:
+        import pandas as pd
+        X = np.array([[1, 2, 3], [4, 5, 6], [7, 8, 9]])
+        X_df = pd.DataFrame(X, columns=['a', 'b', 'fit'])
+        check_consistent_length(X_df)
+    except ImportError:
+        raise SkipTest("Pandas not found")
diff --git a/sklearn/utils/validation.py b/sklearn/utils/validation.py
@@ -92,7 +92,7 @@ def _is_arraylike(x):
 
 def _num_samples(x):
     """Return number of samples in array-like x."""
-    if hasattr(x, 'fit'):
+    if hasattr(x, 'fit') and callable(x.fit):
         # Don't get num_samples from an ensembles length!
         raise TypeError('Expected sequence or array-like, got '
                         'estimator %s' % x)
