BUG: concat on axis=0 with categorical (GH10177)

Sebastian Pölsterl · Sebastian Pölsterl · commit 023fc371cc90 · 2015-06-27T17:27:12.000+02:00
diff --git a/doc/source/whatsnew/v0.17.0.txt b/doc/source/whatsnew/v0.17.0.txt
@@ -103,4 +103,4 @@ Bug Fixes
 - Bug that caused segfault when resampling an empty Series (:issue:`10228`)
 - Bug in ``DatetimeIndex`` and ``PeriodIndex.value_counts`` resets name from its result, but retains in result's ``Index``. (:issue:`10150`)
 
-
+- Bug in `pandas.concat` with ``axis=0`` when column is of dtype ``category`` (:issue:`10177`)
diff --git a/pandas/core/internals.py b/pandas/core/internals.py
@@ -4133,7 +4133,7 @@ def get_empty_dtype_and_na(join_units):
         else:
             return np.dtype(np.bool_), None
     elif 'category' in upcast_classes:
-        return com.CategoricalDtype(), np.nan
+        return np.dtype(np.object_), np.nan
     elif 'float' in upcast_classes:
         return np.dtype(np.float64), np.nan
     elif 'datetime' in upcast_classes:
diff --git a/pandas/tests/test_categorical.py b/pandas/tests/test_categorical.py
@@ -2967,6 +2967,24 @@ def test_pickle_v0_15_2(self):
         #
         self.assert_categorical_equal(cat, pd.read_pickle(pickle_path))
 
+    def test_concat_categorical(self):
+        # See GH 10177
+        df1 = pd.DataFrame(np.arange(18).reshape(6, 3), columns=["a", "b", "c"])
+
+        df2 = pd.DataFrame(np.arange(14).reshape(7, 2), columns=["a", "c"])
+        df2['h'] = pd.Series(pd.Categorical(["one", "one", "two", "one", "two", "two", "one"]))
+
+        df_concat = pd.concat((df1, df2), axis=0).reset_index(drop=True)
+
+        df_expected = pd.DataFrame({'a': [0, 3, 6, 9, 12, 15, 0, 2, 4, 6, 8, 10, 12],
+                                    'b': [1, 4, 7, 10, 13, 16, np.nan, np.nan, np.nan, np.nan, np.nan, np.nan, np.nan],
+                                    'c': [2, 5, 8, 11, 14, 17, 1, 3, 5, 7, 9, 11, 13]})
+        df_expected['h'] = pd.Series(pd.Categorical([None, None, None, None, None, None,
+                                                     "one", "one", "two", "one", "two", "two", "one"]))
+
+        tm.assert_frame_equal(df_expected, df_concat)
+
+
 
 if __name__ == '__main__':
     import nose
