You are viewing a plain text version of this content. The canonical link for it is here.
Posted to commits@arrow.apache.org by jo...@apache.org on 2024/01/08 16:38:33 UTC
(arrow) branch main updated: GH-39437: [CI][Python] Update pandas tests failing on pandas nightly CI build (#39498)
This is an automated email from the ASF dual-hosted git repository.
jorisvandenbossche pushed a commit to branch main
in repository https://gitbox.apache.org/repos/asf/arrow.git
The following commit(s) were added to refs/heads/main by this push:
new 48f704e2a3 GH-39437: [CI][Python] Update pandas tests failing on pandas nightly CI build (#39498)
48f704e2a3 is described below
commit 48f704e2a3161366661d180e0c2198c00671756c
Author: Alenka Frim <Al...@users.noreply.github.com>
AuthorDate: Mon Jan 8 17:38:26 2024 +0100
GH-39437: [CI][Python] Update pandas tests failing on pandas nightly CI build (#39498)
Update version checks and assertions of pyarrow array equality for pandas failing tests on the CI: [test-conda-python-3.10-pandas-nightly](https://github.com/ursacomputing/crossbow/actions/runs/7391976015/job/20109720695)
* Closes: #39437
Lead-authored-by: AlenkaF <fr...@gmail.com>
Co-authored-by: Alenka Frim <Al...@users.noreply.github.com>
Co-authored-by: Joris Van den Bossche <jo...@gmail.com>
Signed-off-by: Joris Van den Bossche <jo...@gmail.com>
---
python/pyarrow/tests/parquet/test_pandas.py | 10 +++++++---
python/pyarrow/tests/test_pandas.py | 16 ++++++++++++++--
2 files changed, 21 insertions(+), 5 deletions(-)
diff --git a/python/pyarrow/tests/parquet/test_pandas.py b/python/pyarrow/tests/parquet/test_pandas.py
index f194d12876..b5913bf5c6 100644
--- a/python/pyarrow/tests/parquet/test_pandas.py
+++ b/python/pyarrow/tests/parquet/test_pandas.py
@@ -404,6 +404,10 @@ carat cut color clarity depth table price x y z
@pytest.mark.pandas
def test_backwards_compatible_column_metadata_handling(datadir):
+ if Version("2.2.0") <= Version(pd.__version__):
+ # TODO: regression in pandas
+ # https://github.com/pandas-dev/pandas/issues/56775
+ pytest.skip("Regression in pandas 2.2.0")
expected = pd.DataFrame(
{'a': [1, 2, 3], 'b': [.1, .2, .3],
'c': pd.date_range("2017-01-01", periods=3, tz='Europe/Brussels')})
@@ -504,9 +508,9 @@ def test_categories_with_string_pyarrow_dtype(tempdir):
df2 = df2.astype("category")
# categories should be converted to pa.Array
- assert pa.array(df1["x"]) == pa.array(df2["x"])
- assert pa.array(df1["x"].cat.categories.values) == pa.array(
- df2["x"].cat.categories.values)
+ assert pa.array(df1["x"]).to_pylist() == pa.array(df2["x"]).to_pylist()
+ assert pa.array(df1["x"].cat.categories.values).to_pylist() == pa.array(
+ df2["x"].cat.categories.values).to_pylist()
path = str(tempdir / 'cat.parquet')
pq.write_table(pa.table(df1), path)
diff --git a/python/pyarrow/tests/test_pandas.py b/python/pyarrow/tests/test_pandas.py
index 342beaaeb5..3353bebce7 100644
--- a/python/pyarrow/tests/test_pandas.py
+++ b/python/pyarrow/tests/test_pandas.py
@@ -261,6 +261,12 @@ class TestConvertMetadata:
with warnings.catch_warnings():
warnings.simplefilter(action="error")
+ # make_block deprecation in pandas, still under discussion
+ # https://github.com/pandas-dev/pandas/pull/56422
+ # https://github.com/pandas-dev/pandas/issues/40226
+ warnings.filterwarnings(
+ "ignore", "make_block is deprecated", DeprecationWarning
+ )
_check_pandas_roundtrip(df, preserve_index=True)
def test_multiindex_columns(self):
@@ -311,6 +317,12 @@ class TestConvertMetadata:
with warnings.catch_warnings():
warnings.simplefilter(action="error")
+ # make_block deprecation in pandas, still under discussion
+ # https://github.com/pandas-dev/pandas/pull/56422
+ # https://github.com/pandas-dev/pandas/issues/40226
+ warnings.filterwarnings(
+ "ignore", "make_block is deprecated", DeprecationWarning
+ )
_check_pandas_roundtrip(df, preserve_index=True)
def test_integer_index_column(self):
@@ -465,7 +477,7 @@ class TestConvertMetadata:
preserve_index=True)
def test_binary_column_name(self):
- if Version("2.0.0") <= Version(pd.__version__) < Version("2.2.0"):
+ if Version("2.0.0") <= Version(pd.__version__) < Version("2.3.0"):
# TODO: regression in pandas, hopefully fixed in next version
# https://issues.apache.org/jira/browse/ARROW-18394
# https://github.com/pandas-dev/pandas/issues/50127
@@ -3095,7 +3107,7 @@ def _fully_loaded_dataframe_example():
@pytest.mark.parametrize('columns', ([b'foo'], ['foo']))
def test_roundtrip_with_bytes_unicode(columns):
- if Version("2.0.0") <= Version(pd.__version__) < Version("2.2.0"):
+ if Version("2.0.0") <= Version(pd.__version__) < Version("2.3.0"):
# TODO: regression in pandas, hopefully fixed in next version
# https://issues.apache.org/jira/browse/ARROW-18394
# https://github.com/pandas-dev/pandas/issues/50127