Backport PR pandas-dev#53641: BUG: pd.concat dataframes with different datetime64 resolutions

Author: Charlie-XIAO

pandas/core/dtypes/concat.py

@@ -129,7 +129,16 @@ def concat_compat(
         # i.e. isinstance(to_concat[0], ExtensionArray)
         to_concat_eas = cast("Sequence[ExtensionArray]", to_concat)
         cls = type(to_concat[0])
-        return cls._concat_same_type(to_concat_eas)
+        # GH#53640: eg. for datetime array, axis=1 but 0 is default
+        # However, class method `_concat_same_type()` for some classes
+        # may not support the `axis` keyword
+        if ea_compat_axis or axis == 0:
+            return cls._concat_same_type(to_concat_eas)
+        else:
+            return cls._concat_same_type(
+                to_concat_eas,
+                axis=axis,  # type: ignore[call-arg]
+            )
     else:
         to_concat_arrs = cast("Sequence[np.ndarray]", to_concat)
         result = np.concatenate(to_concat_arrs, axis=axis)

pandas/tests/reshape/concat/test_datetimes.py

@@ -19,6 +19,22 @@
 )
 import pandas._testing as tm
 
+UNITS = ["s", "ms", "us", "ns"]
+
+
+@pytest.fixture(params=UNITS)
+def unit(request):
+    return request.param
+
+
+unit2 = unit
+
+
+def _get_finer_unit(unit, unit2):
+    if UNITS.index(unit) >= UNITS.index(unit2):
+        return unit
+    return unit2
+
 
 class TestDatetimeConcat:
     def test_concat_datetime64_block(self):
@@ -305,46 +321,58 @@ def test_concat_tz_series(self):
         result = concat([x, y], ignore_index=True)
         tm.assert_series_equal(result, expected)
 
+    def test_concat_tz_series3(self, unit, unit2):
         # see gh-12217 and gh-12306
         # Concatenating two UTC times
-        first = DataFrame([[datetime(2016, 1, 1)]])
+        first = DataFrame([[datetime(2016, 1, 1)]], dtype=f"M8[{unit}]")
         first[0] = first[0].dt.tz_localize("UTC")
 
-        second = DataFrame([[datetime(2016, 1, 2)]])
+        second = DataFrame([[datetime(2016, 1, 2)]], dtype=f"M8[{unit2}]")
         second[0] = second[0].dt.tz_localize("UTC")
 
         result = concat([first, second])
-        assert result[0].dtype == "datetime64[ns, UTC]"
+        exp_unit = _get_finer_unit(unit, unit2)
+        assert result[0].dtype == f"datetime64[{exp_unit}, UTC]"
 
+    def test_concat_tz_series4(self, unit, unit2):
         # Concatenating two London times
-        first = DataFrame([[datetime(2016, 1, 1)]])
+        first = DataFrame([[datetime(2016, 1, 1)]], dtype=f"M8[{unit}]")
         first[0] = first[0].dt.tz_localize("Europe/London")
 
-        second = DataFrame([[datetime(2016, 1, 2)]])
+        second = DataFrame([[datetime(2016, 1, 2)]], dtype=f"M8[{unit2}]")
         second[0] = second[0].dt.tz_localize("Europe/London")
 
         result = concat([first, second])
-        assert result[0].dtype == "datetime64[ns, Europe/London]"
+        exp_unit = _get_finer_unit(unit, unit2)
+        assert result[0].dtype == f"datetime64[{exp_unit}, Europe/London]"
 
+    def test_concat_tz_series5(self, unit, unit2):
         # Concatenating 2+1 London times
-        first = DataFrame([[datetime(2016, 1, 1)], [datetime(2016, 1, 2)]])
+        first = DataFrame(
+            [[datetime(2016, 1, 1)], [datetime(2016, 1, 2)]], dtype=f"M8[{unit}]"
+        )
         first[0] = first[0].dt.tz_localize("Europe/London")
 
-        second = DataFrame([[datetime(2016, 1, 3)]])
+        second = DataFrame([[datetime(2016, 1, 3)]], dtype=f"M8[{unit2}]")
         second[0] = second[0].dt.tz_localize("Europe/London")
 
         result = concat([first, second])
-        assert result[0].dtype == "datetime64[ns, Europe/London]"
+        exp_unit = _get_finer_unit(unit, unit2)
+        assert result[0].dtype == f"datetime64[{exp_unit}, Europe/London]"
 
-        # Concat'ing 1+2 London times
-        first = DataFrame([[datetime(2016, 1, 1)]])
+    def test_concat_tz_series6(self, unit, unit2):
+        # Concatenating 1+2 London times
+        first = DataFrame([[datetime(2016, 1, 1)]], dtype=f"M8[{unit}]")
         first[0] = first[0].dt.tz_localize("Europe/London")
 
-        second = DataFrame([[datetime(2016, 1, 2)], [datetime(2016, 1, 3)]])
+        second = DataFrame(
+            [[datetime(2016, 1, 2)], [datetime(2016, 1, 3)]], dtype=f"M8[{unit2}]"
+        )
         second[0] = second[0].dt.tz_localize("Europe/London")
 
         result = concat([first, second])
-        assert result[0].dtype == "datetime64[ns, Europe/London]"
+        exp_unit = _get_finer_unit(unit, unit2)
+        assert result[0].dtype == f"datetime64[{exp_unit}, Europe/London]"
 
     def test_concat_tz_series_tzlocal(self):
         # see gh-13583