Backport PR #42449: REGR: DataFrame.agg with axis=1, EA dtype, and duplicate index (#42460)

Co-authored-by: Richard Shadrach <[email protected]>

Author: meeseeksmachine

doc/source/whatsnew/v1.3.1.rst

@@ -17,6 +17,7 @@ Fixed regressions
 - Pandas could not be built on PyPy (:issue:`42355`)
 - :class:`DataFrame` constructed with with an older version of pandas could not be unpickled (:issue:`42345`)
 - Performance regression in constructing a :class:`DataFrame` from a dictionary of dictionaries (:issue:`42338`)
+- Fixed regression in :meth:`DataFrame.agg` dropping values when the DataFrame had an Extension Array dtype, a duplicate index, and ``axis=1`` (:issue:`42380`)
 -
 
 .. ---------------------------------------------------------------------------
@@ -25,7 +26,7 @@ Fixed regressions
 
 Bug fixes
 ~~~~~~~~~
--
+- Fixed bug in :meth:`DataFrame.transpose` dropping values when the DataFrame had an Extension Array dtype and a duplicate index (:issue:`42380`)
 -
 
 .. ---------------------------------------------------------------------------

pandas/core/frame.py

@@ -3344,8 +3344,8 @@ def transpose(self, *args, copy: bool = False) -> DataFrame:
             values = self.values
 
             new_values = [arr_type._from_sequence(row, dtype=dtype) for row in values]
-            result = self._constructor(
-                dict(zip(self.index, new_values)), index=self.columns
+            result = type(self)._from_arrays(
+                new_values, index=self.columns, columns=self.index
             )
 
         else:

pandas/tests/apply/test_frame_apply.py

@@ -53,6 +53,17 @@ def test_apply_axis1_with_ea():
     tm.assert_frame_equal(result, expected)
 
 
+@pytest.mark.parametrize(
+    "data, dtype",
+    [(1, None), (1, CategoricalDtype([1])), (Timestamp("2013-01-01", tz="UTC"), None)],
+)
+def test_agg_axis1_duplicate_index(data, dtype):
+    # GH 42380
+    expected = DataFrame([[data], [data]], index=["a", "a"], dtype=dtype)
+    result = expected.agg(lambda x: x, axis=1)
+    tm.assert_frame_equal(result, expected)
+
+
 def test_apply_mixed_datetimelike():
     # mixed datetimelike
     # GH 7778

pandas/tests/base/test_transpose.py

@@ -1,6 +1,10 @@
 import numpy as np
 import pytest
 
+from pandas import (
+    CategoricalDtype,
+    DataFrame,
+)
 import pandas._testing as tm
 
 
@@ -25,3 +29,28 @@ def test_numpy_transpose(index_or_series_obj):
 
     with pytest.raises(ValueError, match=msg):
         np.transpose(obj, axes=1)
+
+
+@pytest.mark.parametrize(
+    "data, transposed_data, index, columns, dtype",
+    [
+        ([[1], [2]], [[1, 2]], ["a", "a"], ["b"], int),
+        ([[1], [2]], [[1, 2]], ["a", "a"], ["b"], CategoricalDtype([1, 2])),
+        ([[1, 2]], [[1], [2]], ["b"], ["a", "a"], int),
+        ([[1, 2]], [[1], [2]], ["b"], ["a", "a"], CategoricalDtype([1, 2])),
+        ([[1, 2], [3, 4]], [[1, 3], [2, 4]], ["a", "a"], ["b", "b"], int),
+        (
+            [[1, 2], [3, 4]],
+            [[1, 3], [2, 4]],
+            ["a", "a"],
+            ["b", "b"],
+            CategoricalDtype([1, 2, 3, 4]),
+        ),
+    ],
+)
+def test_duplicate_labels(data, transposed_data, index, columns, dtype):
+    # GH 42380
+    df = DataFrame(data, index=index, columns=columns, dtype=dtype)
+    result = df.T
+    expected = DataFrame(transposed_data, index=columns, columns=index, dtype=dtype)
+    tm.assert_frame_equal(result, expected)