BUG: Fix issue with datetime[ns, tz] input in Block.setitem GH32395

doc/source/whatsnew/v1.1.0.rst

@@ -365,6 +365,7 @@ Indexing
 - Bug in :meth:`DataFrame.lookup` incorrectly raising an ``AttributeError`` when ``frame.index`` or ``frame.columns`` is not unique; this will now raise a ``ValueError`` with a helpful error message (:issue:`33041`)
 - Bug in :meth:`DataFrame.iloc.__setitem__` creating a new array instead of overwriting ``Categorical`` values in-place (:issue:`32831`)
 - Bug in :meth:`DataFrame.copy` _item_cache not invalidated after copy causes post-copy value updates to not be reflected (:issue:`31784`)
+- Fixed regression in :meth:`DataFrame.loc`, :meth:`Series.loc` throwing an error when a ``datetime64[ns, tz]`` value is provided (:issue:`32395`)
 
 Missing
 ^^^^^^^

pandas/core/internals/blocks.py

@@ -818,6 +818,7 @@ def setitem(self, indexer, value):
 
         # coerce if block dtype can store value
         values = self.values
+
         if self._can_hold_element(value):
             # We only get here for non-Extension Blocks, so _try_coerce_args
             #  is only relevant for DatetimeBlock and TimedeltaBlock
@@ -849,8 +850,10 @@ def setitem(self, indexer, value):
         if is_extension_array_dtype(getattr(value, "dtype", None)):
             # We need to be careful not to allow through strings that
             #  can be parsed to EADtypes
+            is_ea_value = True
             arr_value = value
         else:
+            is_ea_value = False
             arr_value = np.array(value)
 
         if transpose:
@@ -878,6 +881,11 @@ def setitem(self, indexer, value):
             values[indexer] = value
             return self.make_block(Categorical(self.values, dtype=arr_value.dtype))
 
+        elif exact_match and is_ea_value:
+            # GH#32395 if we're going to replace the values entirely, just
+            #  substitute in the new array
+            return self.make_block(arr_value)
+
         # if we are an exact match (ex-broadcasting),
         # then use the resultant dtype
         elif exact_match:

pandas/tests/indexing/test_loc.py

@@ -1,4 +1,5 @@
 """ test label based indexing with loc """
+from datetime import timezone
 from io import StringIO
 import re
 
@@ -1106,3 +1107,133 @@ def test_loc_with_period_index_indexer():
     tm.assert_frame_equal(df, df.loc[list(idx)])
     tm.assert_frame_equal(df.iloc[0:5], df.loc[idx[0:5]])
     tm.assert_frame_equal(df, df.loc[list(idx)])
+
+
+def test_loc_setitem_df_datetime64tz_full_column_with_index():
+    # GH#32395 ea assignments with an index raise TypeError
+    expected = pd.DataFrame(
+        pd.date_range("2020-01-01", "2020-01-06", 6, tz=timezone.utc), columns=["data"]
+    )
+    result = pd.DataFrame(index=expected.index)
+    result.loc[expected.index, "data"] = expected["data"]
+    tm.assert_frame_equal(expected, result)
+
+
+def test_loc_setitem_df_datetime64tz_slice():
+    # GH#32395 ea assignments with an index raise TypeError
+    df = pd.DataFrame(
+        pd.date_range("2020-01-01", "2020-01-06", 6, tz=timezone.utc), columns=["data"]
+    )
+    result = pd.DataFrame(index=df.index)
+    expected = pd.DataFrame(
+        [
+            pd.Timestamp("2020-01-01", tz=timezone.utc),
+            pd.Timestamp("2020-01-02", tz=timezone.utc),
+            pd.Timestamp("2020-01-03", tz=timezone.utc),
+            pd.NaT,
+            pd.NaT,
+            pd.NaT,
+        ],
+        columns=["data"],
+        dtype="object",
+    )
+    result.loc[df.index[:3], "data"] = df["data"][:3]
+    tm.assert_frame_equal(expected, result)
+
+
+def test_loc_setitem_series_datetime64tz_full_with_index():
+    # GH#32395 ea assignments with an index raise TypeError
+    expected = pd.Series(
+        pd.date_range("2020-01-01", "2020-01-06", 6, tz=timezone.utc), name="data"
+    )
+    result = pd.Series(index=expected.index, dtype="object", name="data")
+    result.loc[expected.index] = expected
+    tm.assert_series_equal(expected, result)
+
+
+def test_loc_setitem_series_datetime64tz_slice():
+    # GH#32395 ea assignments with an index raise TypeError
+    dates = pd.date_range("2020-01-01", "2020-01-06", 6, tz=timezone.utc)
+    s1 = pd.Series(dates, name="data")
+    result = pd.Series(index=s1.index, dtype="object", name="data")
+    expected = pd.Series(dates, name="data", dtype="object")
+    expected[-3:] = pd.NaT
+    result.loc[s1.index[:3]] = s1[:3]
+    tm.assert_series_equal(expected, result)
+
+
+def test_loc_setitem_series_timedelta64_full_with_index():
+    # GH#32395 ea assignments with an index raise TypeError
+    expected = pd.Series(pd.timedelta_range(start="1 day", periods=4), name="data")
+    result = pd.Series(index=expected.index, dtype="object", name="data")
+    result.loc[expected.index] = expected
+    tm.assert_series_equal(expected, result)
+
+
+def test_loc_setitem_df_period_full_column_with_index():
+    # GH#32395 ea assignments with an index raise TypeError
+    expected = pd.DataFrame(
+        pd.period_range(start="2020Q1", periods=5), columns=["data"]
+    )
+    result = pd.DataFrame(index=expected.index)
+    result.loc[expected.index, "data"] = expected["data"]
+    tm.assert_frame_equal(expected, result)
+
+
+def test_loc_setitem_series_interval_full_with_index():
+    # GH#32395 ea assignments with an index raise TypeError
+    expected = pd.Series(pd.interval_range(start=0, end=5), name="data")
+    result = pd.Series(index=expected.index, dtype="object", name="data")
+    result.loc[expected.index] = expected
+    tm.assert_series_equal(expected, result)
+
+
+def test_loc_setitem_df_sparse_full_column_with_index():
+    # GH#32395 ea assignments with an index raise TypeError
+    expected = pd.DataFrame(np.random.randn(100), columns=["data"])
+    expected.iloc[5:95] = np.nan
+    expected = expected.astype(pd.SparseDtype("int", np.nan))
+    result = pd.DataFrame(index=expected.index)
+    result.loc[expected.index, "data"] = expected["data"]
+    tm.assert_frame_equal(expected, result)
+
+
+def test_loc_setitem_series_categorical_full_with_index():
+    # GH#32395 ea assignments with an index raise TypeError
+    expected = pd.Series(pd.Categorical([1] * 10 + [2] * 5 + [3] * 10), name="data")
+    result = pd.Series(index=expected.index, dtype="object", name="data")
+    result.loc[expected.index] = expected
+    tm.assert_series_equal(expected, result)
+
+
+def test_loc_setitem_series_categorical_slice():
+    # GH#32395 ea assignments with an index raise TypeError
+    s1 = pd.Series(pd.Categorical([1] * 10 + [2] * 5 + [3] * 10), name="data")
+    result = pd.Series(index=s1.index, dtype="object", name="data")
+    expected = pd.Series(
+        pd.Categorical([1] * 10 + [2] * 5 + [np.nan] * 10), name="data", dtype=object
+    )
+    result.loc[s1.index[:15]] = s1[:15]
+    tm.assert_series_equal(expected, result)
+
+
+def test_loc_setitem_df_interval_slice():
+    # GH#32395 ea assignments with an index raise TypeError
+    intervals = pd.interval_range(start=0, end=5)
+    df = pd.DataFrame(intervals, columns=["data"])
+    result = pd.DataFrame(index=df.index)
+    expected = pd.DataFrame(intervals, columns=["data"], dtype="object")
+    expected.data[-2:] = np.nan
+    result.loc[df.index[:3], "data"] = df["data"][:3]
+    tm.assert_frame_equal(expected, result)
+
+
+def test_loc_setitem_series_period_slice():
+    # GH#32395 ea assignments with an index raise TypeError
+    periods = pd.period_range(start="2020Q1", periods=5)
+    s1 = pd.Series(periods, name="data")
+    result = pd.Series(index=s1.index, dtype="object", name="data")
+    expected = pd.Series(periods, name="data", dtype=object,)
+    expected[-2:] = np.nan
+    result.loc[s1.index[:3]] = s1[:3]
+    tm.assert_series_equal(expected, result)