BUG: fix check_array on pandas Series with custom dtype (eg categorical) (#12706)

jorisvandenbossche · jnothman · commit 4f5dd77d19fc · 2018-12-03T21:25:52.000+11:00
Closes #12699. Related to #12625
diff --git a/doc/whats_new/v0.20.rst b/doc/whats_new/v0.20.rst
@@ -46,6 +46,13 @@ Changelog
   function to return 0 when two all-zero vectors are compared.
   :issue:`12685` by :user:`Thomas Fan <thomasjpfan>`.
 
+:mod:`sklearn.utils`
+....................
+
+- |Fix| Calling :func:`utils.check_array` on `pandas.Series` with categorical
+  data, which raised an error in 0.20.0, now returns the expected output again.
+  :issue:`12699` by `Joris Van den Bossche`_.
+
 .. _changes_0_20_1:
 
 Version 0.20.1
diff --git a/sklearn/utils/tests/test_validation.py b/sklearn/utils/tests/test_validation.py
@@ -701,6 +701,11 @@ def test_check_array_series():
                       warn_on_dtype=True)
     assert_array_equal(res, np.array([1, 2, 3]))
 
+    # with categorical dtype (not a numpy dtype) (GH12699)
+    s = pd.Series(['a', 'b', 'c']).astype('category')
+    res = check_array(s, dtype=None, ensure_2d=False)
+    assert_array_equal(res, np.array(['a', 'b', 'c'], dtype=object))
+
 
 def test_check_dataframe_warns_on_dtype():
     # Check that warn_on_dtype also works for DataFrames.
diff --git a/sklearn/utils/validation.py b/sklearn/utils/validation.py
@@ -477,7 +477,7 @@ def check_array(array, accept_sparse=False, accept_large_sparse=True,
     # check if the object contains several dtypes (typically a pandas
     # DataFrame), and store them. If not, store None.
     dtypes_orig = None
-    if hasattr(array, "dtypes") and len(array.dtypes):
+    if hasattr(array, "dtypes") and hasattr(array.dtypes, '__array__'):
         dtypes_orig = np.array(array.dtypes)
 
     if dtype_numeric:
