BUG-22796 Concat multicolumn tz-aware DataFrame (#23036)

Author: tonytao2012

doc/source/whatsnew/v0.24.0.txt

@@ -892,6 +892,7 @@ Reshaping
 - Bug in :func:`pandas.wide_to_long` when a string is passed to the stubnames argument and a column name is a substring of that stubname (:issue:`22468`)
 - Bug in :func:`merge` when merging ``datetime64[ns, tz]`` data that contained a DST transition (:issue:`18885`)
 - Bug in :func:`merge_asof` when merging on float values within defined tolerance (:issue:`22981`)
+- Bug in :func:`pandas.concat` when concatenating a multicolumn DataFrame with tz-aware data against a DataFrame with a different number of columns (:issue`22796`)
 
 Build Changes
 ^^^^^^^^^^^^^

pandas/core/dtypes/dtypes.py

@@ -546,6 +546,17 @@ def __new__(cls, unit=None, tz=None):
             cls._cache[key] = u
             return u
 
+    @classmethod
+    def construct_array_type(cls):
+        """Return the array type associated with this dtype
+
+        Returns
+        -------
+        type
+        """
+        from pandas import DatetimeIndex
+        return DatetimeIndex
+
     @classmethod
     def construct_from_string(cls, string):
         """ attempt to construct this type from a string, raise a TypeError if

pandas/core/internals/concat.py

@@ -186,6 +186,10 @@ def get_reindexed_values(self, empty_dtype, upcasted_na):
 
                 if getattr(self.block, 'is_datetimetz', False) or \
                         is_datetimetz(empty_dtype):
+                    if self.block is None:
+                        array = empty_dtype.construct_array_type()
+                        missing_arr = array([fill_value], dtype=empty_dtype)
+                        return missing_arr.repeat(self.shape[1])
                     pass
                 elif getattr(self.block, 'is_categorical', False):
                     pass

pandas/tests/frame/test_combine_concat.py

@@ -54,6 +54,38 @@ def test_concat_multiple_tzs(self):
         expected = DataFrame(dict(time=[ts2, ts3]))
         assert_frame_equal(results, expected)
 
+    @pytest.mark.parametrize(
+        't1',
+        [
+            '2015-01-01',
+            pytest.param(pd.NaT, marks=pytest.mark.xfail(
+                reason='GH23037 incorrect dtype when concatenating',
+                strict=True))])
+    def test_concat_tz_NaT(self, t1):
+        # GH 22796
+        # Concating tz-aware multicolumn DataFrames
+        ts1 = Timestamp(t1, tz='UTC')
+        ts2 = Timestamp('2015-01-01', tz='UTC')
+        ts3 = Timestamp('2015-01-01', tz='UTC')
+
+        df1 = DataFrame([[ts1, ts2]])
+        df2 = DataFrame([[ts3]])
+
+        result = pd.concat([df1, df2])
+        expected = DataFrame([[ts1, ts2], [ts3, pd.NaT]], index=[0, 0])
+
+        assert_frame_equal(result, expected)
+
+    def test_concat_tz_not_aligned(self):
+        # GH 22796
+        ts = pd.to_datetime([1, 2]).tz_localize("UTC")
+        a = pd.DataFrame({"A": ts})
+        b = pd.DataFrame({"A": ts, "B": ts})
+        result = pd.concat([a, b], sort=True, ignore_index=True)
+        expected = pd.DataFrame({"A": list(ts) + list(ts),
+                                 "B": [pd.NaT, pd.NaT] + list(ts)})
+        assert_frame_equal(result, expected)
+
     def test_concat_tuple_keys(self):
         # GH 14438
         df1 = pd.DataFrame(np.ones((2, 2)), columns=list('AB'))