BUG: Allow 'apply' to be used with non-numpy-dtype DataFrames

Addresses issue in #12244 in which a non-numpy-dtype for
DataFrame.values causes a `TypeError` to be thrown in the `reduce ==
True` case for `DataFrame.apply`.  Resolved by first passing
`DataFrame.values` through `Series` initialization and taking its
`values` attribute, which is an `ndarray` and hence will have a valid
`dtype`.  Note that the output of `apply` will still have the original
`dtype`.

Author: gfyoung <gfyoung17@gmail.com>

Closes #12284 from gfyoung/df_apply_tz_aware and squashes the following commits:

b18b74f [gfyoung] BUG: Allow apply to be used with non-numpy-dtype DataFrames

Author: gfyoung

doc/source/whatsnew/v0.18.0.txt

@@ -968,4 +968,7 @@ Bug Fixes
 - Bug in ``.skew`` and ``.kurt`` due to roundoff error for highly similar values (:issue:`11974`)
 
 - Bug in ``buffer_rd_bytes`` src->buffer could be freed more than once if reading failed, causing a segfault (:issue:`12098`)
+
 - Bug in ``crosstab`` where arguments with non-overlapping indexes would return a ``KeyError`` (:issue:`10291`)
+
+- Bug in ``DataFrame.apply`` in which reduction was not being prevented for cases in which ``dtype`` was not a numpy dtype (:issue:`12244`)

pandas/core/frame.py

@@ -4072,22 +4072,24 @@ def _apply_standard(self, func, axis, ignore_failures=False, reduce=True):
         # this only matters if the reduction in values is of different dtype
         # e.g. if we want to apply to a SparseFrame, then can't directly reduce
         if reduce:
-
             values = self.values
 
-            # Create a dummy Series from an empty array
-            index = self._get_axis(axis)
-            empty_arr = np.empty(len(index), dtype=values.dtype)
-            dummy = Series(empty_arr, index=self._get_axis(axis),
-                           dtype=values.dtype)
+            # we cannot reduce using non-numpy dtypes,
+            # as demonstrated in gh-12244
+            if not is_internal_type(values):
+                # Create a dummy Series from an empty array
+                index = self._get_axis(axis)
+                empty_arr = np.empty(len(index), dtype=values.dtype)
+                dummy = Series(empty_arr, index=self._get_axis(axis),
+                               dtype=values.dtype)
 
-            try:
-                labels = self._get_agg_axis(axis)
-                result = lib.reduce(values, func, axis=axis, dummy=dummy,
-                                    labels=labels)
-                return Series(result, index=labels)
-            except Exception:
-                pass
+                try:
+                    labels = self._get_agg_axis(axis)
+                    result = lib.reduce(values, func, axis=axis, dummy=dummy,
+                                        labels=labels)
+                    return Series(result, index=labels)
+                except Exception:
+                    pass
 
         dtype = object if self._is_mixed_type else None
         if axis == 0:

pandas/tests/frame/test_apply.py

@@ -400,3 +400,19 @@ def test_applymap(self):
         result = df.applymap(str)
         for f in ['datetime', 'timedelta']:
             self.assertEqual(result.loc[0, f], str(df.loc[0, f]))
+
+    # See gh-12244
+    def test_apply_non_numpy_dtype(self):
+        df = DataFrame({'dt': pd.date_range(
+            "2015-01-01", periods=3, tz='Europe/Brussels')})
+        result = df.apply(lambda x: x)
+        assert_frame_equal(result, df)
+
+        result = df.apply(lambda x: x + pd.Timedelta('1day'))
+        expected = DataFrame({'dt': pd.date_range(
+            "2015-01-02", periods=3, tz='Europe/Brussels')})
+        assert_frame_equal(result, expected)
+
+        df = DataFrame({'dt': ['a', 'b', 'c', 'a']}, dtype='category')
+        result = df.apply(lambda x: x)
+        assert_frame_equal(result, df)