You are viewing a plain text version of this content. The canonical link for it is here.
Posted to commits@spark.apache.org by gu...@apache.org on 2025/11/25 23:35:38 UTC
(spark) branch branch-4.1 updated: [SPARK-54482][PYTHON][CONNECT][TESTS] Reeanble `test_apply_in_pandas_returning_column_names_*` for Spark Connect 4.0 client <> master server
This is an automated email from the ASF dual-hosted git repository.
gurwls223 pushed a commit to branch branch-4.1
in repository https://gitbox.apache.org/repos/asf/spark.git
The following commit(s) were added to refs/heads/branch-4.1 by this push:
new 807a6ef07b3d [SPARK-54482][PYTHON][CONNECT][TESTS] Reeanble `test_apply_in_pandas_returning_column_names_*` for Spark Connect 4.0 client <> master server
807a6ef07b3d is described below
commit 807a6ef07b3d34398a4d9be7cae917828f828efa
Author: Ruifeng Zheng <ru...@apache.org>
AuthorDate: Wed Nov 26 08:35:16 2025 +0900
[SPARK-54482][PYTHON][CONNECT][TESTS] Reeanble `test_apply_in_pandas_returning_column_names_*` for Spark Connect 4.0 client <> master server
### What changes were proposed in this pull request?
Fix tests
### Why are the changes needed?
to make CI happy
### Does this PR introduce _any_ user-facing change?
No, test-only
### How was this patch tested?
will monitor the scheduled jobs
### Was this patch authored or co-authored using generative AI tooling?
No
Closes #53209 from zhengruifeng/test_aply_in_pd.
Authored-by: Ruifeng Zheng <ru...@apache.org>
Signed-off-by: Hyukjin Kwon <gu...@apache.org>
(cherry picked from commit 27a4849834406a5bbfb0a0b11ea8b725936baef6)
Signed-off-by: Hyukjin Kwon <gu...@apache.org>
---
.../sql/tests/pandas/test_pandas_grouped_map.py | 34 +++++-----------------
1 file changed, 7 insertions(+), 27 deletions(-)
diff --git a/python/pyspark/sql/tests/pandas/test_pandas_grouped_map.py b/python/pyspark/sql/tests/pandas/test_pandas_grouped_map.py
index f8c646933809..45b18e9414eb 100644
--- a/python/pyspark/sql/tests/pandas/test_pandas_grouped_map.py
+++ b/python/pyspark/sql/tests/pandas/test_pandas_grouped_map.py
@@ -278,37 +278,20 @@ class ApplyInPandasTestsMixin:
):
self._test_apply_in_pandas(lambda key, pdf: key)
- @staticmethod
- def stats_with_column_names(key, pdf):
- # order of column can be different to applyInPandas schema when column names are given
- return pd.DataFrame([(pdf.v.mean(),) + key], columns=["mean", "id"])
-
- @staticmethod
- def stats_with_no_column_names(key, pdf):
- # columns must be in order of applyInPandas schema when no columns given
- return pd.DataFrame([key + (pdf.v.mean(),)])
-
- @unittest.skipIf(
- os.environ.get("SPARK_SKIP_CONNECT_COMPAT_TESTS") == "1", "SPARK-54482: To be reenabled"
- )
def test_apply_in_pandas_returning_column_names(self):
- self._test_apply_in_pandas(ApplyInPandasTestsMixin.stats_with_column_names)
+ self._test_apply_in_pandas(
+ lambda key, pdf: pd.DataFrame([(pdf.v.mean(),) + key], columns=["mean", "id"])
+ )
- @unittest.skipIf(
- os.environ.get("SPARK_SKIP_CONNECT_COMPAT_TESTS") == "1", "SPARK-54482: To be reenabled"
- )
def test_apply_in_pandas_returning_no_column_names(self):
- self._test_apply_in_pandas(ApplyInPandasTestsMixin.stats_with_no_column_names)
+ self._test_apply_in_pandas(lambda key, pdf: pd.DataFrame([key + (pdf.v.mean(),)]))
- @unittest.skipIf(
- os.environ.get("SPARK_SKIP_CONNECT_COMPAT_TESTS") == "1", "SPARK-54482: To be reenabled"
- )
def test_apply_in_pandas_returning_column_names_sometimes(self):
def stats(key, pdf):
if key[0] % 2:
- return ApplyInPandasTestsMixin.stats_with_column_names(key, pdf)
+ return pd.DataFrame([(pdf.v.mean(),) + key], columns=["mean", "id"])
else:
- return ApplyInPandasTestsMixin.stats_with_no_column_names(key, pdf)
+ return pd.DataFrame([key + (pdf.v.mean(),)])
self._test_apply_in_pandas(stats)
@@ -886,7 +869,7 @@ class ApplyInPandasTestsMixin:
def stats(key, pdf):
if key[0] % 2 == 0:
- return ApplyInPandasTestsMixin.stats_with_no_column_names(key, pdf)
+ return pd.DataFrame([key + (pdf.v.mean(),)])
return empty_df
result = (
@@ -903,9 +886,6 @@ class ApplyInPandasTestsMixin:
for row in result:
self.assertEqual(24.5, row[1])
- @unittest.skipIf(
- os.environ.get("SPARK_SKIP_CONNECT_COMPAT_TESTS") == "1", "SPARK-54482: To be reenabled"
- )
def _test_apply_in_pandas_returning_empty_dataframe_error(self, empty_df, error):
with self.quiet():
with self.assertRaisesRegex(PythonException, error):
---------------------------------------------------------------------
To unsubscribe, e-mail: commits-unsubscribe@spark.apache.org
For additional commands, e-mail: commits-help@spark.apache.org