Skip to content

GH-48978: [Python] test failures on pandas 3.0 (currently CI on 2.3.3) #48979

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
tadeja wants to merge 5 commits into
base: main
Choose a base branch
from
Open

GH-48978: [Python] test failures on pandas 3.0 (currently CI on 2.3.3) #48979

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
5 commits
Select commit Hold shift + click to select a range
c1bdc3c
Attempt to upgrade pandas to latest
tadeja Jan 25, 2026
84aa343
Test with fastparquet and w/o pytz
tadeja Jan 25, 2026
a5222a6
Test with fastparquet and w/o pytz
tadeja Jan 25, 2026
6f778a4
Fix fromutc and fastparquet failures
tadeja Jan 25, 2026
1bce5ee
Revert to w/o fastparquet and with pytz
tadeja Jan 25, 2026
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
2 changes: 1 addition & 1 deletion ci/scripts/install_pandas.sh
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -40,7 +40,7 @@ if [ "${pandas}" = "upstream_devel" ]; then
elif [ "${pandas}" = "nightly" ]; then
pip install --extra-index-url https://pypi.anaconda.org/scientific-python-nightly-wheels/simple --pre pandas
elif [ "${pandas}" = "latest" ]; then
pip install pandas
pip install --upgrade pandas
else
pip install pandas=="${pandas}"
fi
13 changes: 9 additions & 4 deletions python/pyarrow/tests/parquet/test_basic.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -728,6 +728,7 @@ def test_parquet_file_too_small(tempdir):
@pytest.mark.fastparquet
@pytest.mark.filterwarnings("ignore:RangeIndex:FutureWarning")
@pytest.mark.filterwarnings("ignore:tostring:DeprecationWarning:fastparquet")
@pytest.mark.filterwarnings("ignore:unclosed file:ResourceWarning")
def test_fastparquet_cross_compatibility(tempdir):
fp = pytest.importorskip('fastparquet')

Expand All @@ -751,17 +752,21 @@ def test_fastparquet_cross_compatibility(tempdir):

fp_file = fp.ParquetFile(file_arrow)
df_fp = fp_file.to_pandas()
tm.assert_frame_equal(df, df_fp)
# check_dtype=False: string/categorical dtype handling differs between libraries
tm.assert_frame_equal(df, df_fp, check_dtype=False, check_categorical=False)

# Fastparquet -> arrow
file_fastparquet = str(tempdir / "cross_compat_fastparquet.parquet")
fp.write(file_fastparquet, df)
# fastparquet can't write pandas 3.0 StringDtype
df_for_fp = df.copy()
df_for_fp['a'] = df_for_fp['a'].astype(object)
df_for_fp['f'] = df_for_fp['f'].astype(object)
fp.write(file_fastparquet, df_for_fp)

table_fp = pq.read_pandas(file_fastparquet)
# for fastparquet written file, categoricals comes back as strings
# (no arrow schema in parquet metadata)
df['f'] = df['f'].astype(object)
tm.assert_frame_equal(table_fp.to_pandas(), df)
tm.assert_frame_equal(table_fp.to_pandas(), df_for_fp, check_dtype=False)


@pytest.mark.parametrize('array_factory', [
Expand Down
2 changes: 1 addition & 1 deletion python/pyarrow/tests/test_pandas.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -4956,7 +4956,7 @@ def test_timestamp_as_object_non_nanosecond(resolution, tz, dt):
assert isinstance(result[0], datetime)
if tz:
assert result[0].tzinfo is not None
expected = result[0].tzinfo.fromutc(dt)
expected = dt.replace(tzinfo=timezone.utc).astimezone(result[0].tzinfo)
else:
assert result[0].tzinfo is None
expected = dt
Expand Down
Loading