From 4c7e66dd91dbd2b5f7298911b777f1757d62d839 Mon Sep 17 00:00:00 2001
From: Matt Roeschke <mroeschke@housecanary.com>
Date: Sun, 10 Feb 2019 22:59:26 -0800
Subject: [PATCH 1/5] BUG: groupby.transform retains timezone information
---
pandas/core/groupby/generic.py | 2 +-
pandas/tests/groupby/test_transform.py | 10 ++++++++++
2 files changed, 11 insertions(+), 1 deletion(-)
diff --git a/pandas/core/groupby/generic.py b/pandas/core/groupby/generic.py
index 27e13e86a6e9e..52056a6842ed9 100644
--- a/pandas/core/groupby/generic.py
+++ b/pandas/core/groupby/generic.py
@@ -964,7 +964,7 @@ def _transform_fast(self, func, func_nm):
ids, _, ngroup = self.grouper.group_info
cast = self._transform_should_cast(func_nm)
- out = algorithms.take_1d(func().values, ids)
+ out = algorithms.take_1d(func()._values, ids)
if cast:
out = self._try_cast(out, self.obj)
return Series(out, index=self.obj.index, name=self.obj.name)
diff --git a/pandas/tests/groupby/test_transform.py b/pandas/tests/groupby/test_transform.py
index f120402e6e8ca..52aa0e6da909d 100644
--- a/pandas/tests/groupby/test_transform.py
+++ b/pandas/tests/groupby/test_transform.py
@@ -834,3 +834,13 @@ def demean_rename(x):
tm.assert_frame_equal(result, expected)
result_single = df.groupby('group').value.transform(demean_rename)
tm.assert_series_equal(result_single, expected['value'])
+
+
+def test_groupby_transform_timezone_column():
+ # GH 24198
+ ts = pd.to_datetime('now', utc=True).tz_convert('Asia/Singapore')
+ result = pd.DataFrame({'end_time': [ts], 'id': [1]})
+ result['max_end_time'] = result.groupby('id').end_time.transform(max)
+ expected = pd.DataFrame([[ts, 1, ts]], columns=['end_time', 'id',
+ 'max_end_time'])
+ tm.assert_frame_equal(result, expected)
From 3c5fd19b9dd475ce942ffc5dbce40d65d71ccb71 Mon Sep 17 00:00:00 2001
From: Matt Roeschke <mroeschke@housecanary.com>
Date: Sun, 10 Feb 2019 23:00:25 -0800
Subject: [PATCH 2/5] Add whatsnew
---
doc/source/whatsnew/v0.25.0.rst | 1 +
1 file changed, 1 insertion(+)
diff --git a/doc/source/whatsnew/v0.25.0.rst b/doc/source/whatsnew/v0.25.0.rst
index 4032dc20b2e19..309a9e336f92f 100644
--- a/doc/source/whatsnew/v0.25.0.rst
+++ b/doc/source/whatsnew/v0.25.0.rst
@@ -180,6 +180,7 @@ Reshaping
- Bug in :func:`pandas.merge` adds a string of ``None`` if ``None`` is assigned in suffixes instead of remain the column name as-is (:issue:`24782`).
- Bug in :func:`merge` when merging by index name would sometimes result in an incorrectly numbered index (:issue:`24212`)
+- Bug in :meth:`pandas.core.groupby.GroupBy.transform` where applying a function to a timezone aware column would return a timezone naive result (:issue:`24198`)
- :func:`to_records` now accepts dtypes to its `column_dtypes` parameter (:issue:`24895`)
-
From 032e201693ffb80086a6b33a041d6e91832ff20d Mon Sep 17 00:00:00 2001
From: Matt Roeschke <mroeschke@housecanary.com>
Date: Mon, 11 Feb 2019 09:54:42 -0800
Subject: [PATCH 3/5] Move whatsnew to 0.24.2
---
doc/source/whatsnew/v0.24.2.rst | 2 +-
doc/source/whatsnew/v0.25.0.rst | 1 -
2 files changed, 1 insertion(+), 2 deletions(-)
diff --git a/doc/source/whatsnew/v0.24.2.rst b/doc/source/whatsnew/v0.24.2.rst
index b0f287cf0b9f6..0526ae77f87cb 100644
--- a/doc/source/whatsnew/v0.24.2.rst
+++ b/doc/source/whatsnew/v0.24.2.rst
@@ -76,7 +76,7 @@ Bug Fixes
**Reshaping**
--
+- Bug in :meth:`pandas.core.groupby.GroupBy.transform` where applying a function to a timezone aware column would return a timezone naive result (:issue:`24198`)
-
-
diff --git a/doc/source/whatsnew/v0.25.0.rst b/doc/source/whatsnew/v0.25.0.rst
index 309a9e336f92f..4032dc20b2e19 100644
--- a/doc/source/whatsnew/v0.25.0.rst
+++ b/doc/source/whatsnew/v0.25.0.rst
@@ -180,7 +180,6 @@ Reshaping
- Bug in :func:`pandas.merge` adds a string of ``None`` if ``None`` is assigned in suffixes instead of remain the column name as-is (:issue:`24782`).
- Bug in :func:`merge` when merging by index name would sometimes result in an incorrectly numbered index (:issue:`24212`)
-- Bug in :meth:`pandas.core.groupby.GroupBy.transform` where applying a function to a timezone aware column would return a timezone naive result (:issue:`24198`)
- :func:`to_records` now accepts dtypes to its `column_dtypes` parameter (:issue:`24895`)
-
From ab34a5ce6a79d11560a91bd0b5cfd8cadf99dc06 Mon Sep 17 00:00:00 2001
From: Matt Roeschke <mroeschke@housecanary.com>
Date: Mon, 11 Feb 2019 13:48:12 -0800
Subject: [PATCH 4/5] Add more tests
---
pandas/tests/groupby/test_transform.py | 5 +++--
1 file changed, 3 insertions(+), 2 deletions(-)
diff --git a/pandas/tests/groupby/test_transform.py b/pandas/tests/groupby/test_transform.py
index 52aa0e6da909d..19de213903f0a 100644
--- a/pandas/tests/groupby/test_transform.py
+++ b/pandas/tests/groupby/test_transform.py
@@ -836,11 +836,12 @@ def demean_rename(x):
tm.assert_series_equal(result_single, expected['value'])
-def test_groupby_transform_timezone_column():
+@pytest.mark.parametrize('func', [min, max, np.min, np.max])
+def test_groupby_transform_timezone_column(func):
# GH 24198
ts = pd.to_datetime('now', utc=True).tz_convert('Asia/Singapore')
result = pd.DataFrame({'end_time': [ts], 'id': [1]})
- result['max_end_time'] = result.groupby('id').end_time.transform(max)
+ result['max_end_time'] = result.groupby('id').end_time.transform(func)
expected = pd.DataFrame([[ts, 1, ts]], columns=['end_time', 'id',
'max_end_time'])
tm.assert_frame_equal(result, expected)
From dfe61248308350c09bcaa4484ec38372a1e1fcd9 Mon Sep 17 00:00:00 2001
From: Matt Roeschke <mroeschke@housecanary.com>
Date: Mon, 11 Feb 2019 21:12:58 -0800
Subject: [PATCH 5/5] Add first last
---
pandas/tests/groupby/test_transform.py | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/pandas/tests/groupby/test_transform.py b/pandas/tests/groupby/test_transform.py
index 19de213903f0a..b645073fcf72a 100644
--- a/pandas/tests/groupby/test_transform.py
+++ b/pandas/tests/groupby/test_transform.py
@@ -836,7 +836,7 @@ def demean_rename(x):
tm.assert_series_equal(result_single, expected['value'])
-@pytest.mark.parametrize('func', [min, max, np.min, np.max])
+@pytest.mark.parametrize('func', [min, max, np.min, np.max, 'first', 'last'])
def test_groupby_transform_timezone_column(func):
# GH 24198
ts = pd.to_datetime('now', utc=True).tz_convert('Asia/Singapore')