From 17f7a6e7a28bc50bbd27fcfb9ecf8558d43d28b5 Mon Sep 17 00:00:00 2001
From: Richard Shadrach <rhshadrach@gmail.com>
Date: Thu, 8 Jul 2021 14:10:02 -0400
Subject: [PATCH 1/2] REGR: DataFrame.agg with axis=1, EA dtype, and duplicate
 index

---
 doc/source/whatsnew/v1.3.1.rst         |  3 ++-
 pandas/core/frame.py                   |  4 +---
 pandas/tests/apply/test_frame_apply.py | 11 ++++++++++
 pandas/tests/base/test_transpose.py    | 29 ++++++++++++++++++++++++++
 4 files changed, 43 insertions(+), 4 deletions(-)

diff --git a/doc/source/whatsnew/v1.3.1.rst b/doc/source/whatsnew/v1.3.1.rst
index 9c17a22bf6d52..a06159c110c9b 100644
--- a/doc/source/whatsnew/v1.3.1.rst
+++ b/doc/source/whatsnew/v1.3.1.rst
@@ -16,6 +16,7 @@ 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`)
+- Fixed regression in :meth:`DataFrame.agg` dropping values when the DataFrame had an Extension Array dtype, a duplicate index, and ``axis=1`` (:issue:`42380`)
 -
 
 .. ---------------------------------------------------------------------------
@@ -24,7 +25,7 @@ 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`)
 -
 
 .. ---------------------------------------------------------------------------
diff --git a/pandas/core/frame.py b/pandas/core/frame.py
index 2466154f78294..e0e1022e2047d 100644
--- a/pandas/core/frame.py
+++ b/pandas/core/frame.py
@@ -3338,12 +3338,10 @@ def transpose(self, *args, copy: bool = False) -> DataFrame:
         ):
             # We have EAs with the same dtype. We can preserve that dtype in transpose.
             dtype = dtypes[0]
-            arr_type = dtype.construct_array_type()
             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
+                values.T, index=self.columns, columns=self.index, dtype=dtype
             )
 
         else:
diff --git a/pandas/tests/apply/test_frame_apply.py b/pandas/tests/apply/test_frame_apply.py
index 14266a2c29a7f..995f404dc49d3 100644
--- a/pandas/tests/apply/test_frame_apply.py
+++ b/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
diff --git a/pandas/tests/base/test_transpose.py b/pandas/tests/base/test_transpose.py
index 5ba278368834c..246f33d27476c 100644
--- a/pandas/tests/base/test_transpose.py
+++ b/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)

From 980b185caf97e7f72fb0aaca7db6731c745a992a Mon Sep 17 00:00:00 2001
From: Richard Shadrach <rhshadrach@gmail.com>
Date: Thu, 8 Jul 2021 15:50:27 -0400
Subject: [PATCH 2/2] Use _from_arrays

---
 pandas/core/frame.py | 6 ++++--
 1 file changed, 4 insertions(+), 2 deletions(-)

diff --git a/pandas/core/frame.py b/pandas/core/frame.py
index 6f6e3fdbbf8c1..43adb4df7fcb4 100644
--- a/pandas/core/frame.py
+++ b/pandas/core/frame.py
@@ -3338,10 +3338,12 @@ def transpose(self, *args, copy: bool = False) -> DataFrame:
         ):
             # We have EAs with the same dtype. We can preserve that dtype in transpose.
             dtype = dtypes[0]
+            arr_type = dtype.construct_array_type()
             values = self.values
 
-            result = self._constructor(
-                values.T, index=self.columns, columns=self.index, dtype=dtype
+            new_values = [arr_type._from_sequence(row, dtype=dtype) for row in values]
+            result = type(self)._from_arrays(
+                new_values, index=self.columns, columns=self.index
             )
 
         else: