Skip to content

[SPARK-56219][PS][FOLLOW-UP] Keep legacy groupby idxmax and idxmin skipna=False behavior for pandas 2 #55121

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

Closed
ueshin wants to merge 2 commits into from
+17 −26
Closed

[SPARK-56219][PS][FOLLOW-UP] Keep legacy groupby idxmax and idxmin skipna=False behavior for pandas 2 #55121

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
824c72c
Fix groupby idxmax and idxmin skipna=False for pandas 2.2
ueshin Mar 31, 2026
7e2dfa6
Fix.
ueshin Mar 31, 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
33 changes: 11 additions & 22 deletions python/pyspark/pandas/groupby.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -2464,30 +2464,24 @@ def idxmax(self, skipna: bool = True) -> FrameLike:
index = self._psdf._internal.index_spark_column_names[0]
index_spark_type = self._psdf._internal.index_fields[0].spark_type

pd_version = LooseVersion(pd.__version__)

stat_exprs = []
for psser, scol in zip(self._agg_columns, self._agg_columns_scols):
name = psser._internal.data_spark_column_names[0]

if LooseVersion(pd.__version__) < "3.0.0" or skipna:
if pd_version < "3.0.0" or skipna:
order_column = scol.desc_nulls_last()

window = Window.partitionBy(*groupkey_names).orderBy(
order_column, NATURAL_ORDER_COLUMN_NAME
)

has_na_name = "__has_na_{}__".format(name)
sdf = sdf.withColumn(has_na_name, scol.isNull()).withColumn(
sdf = sdf.withColumn(
name,
F.when(F.row_number().over(window) == 1, scol_for(sdf, index)).otherwise(None),
)
if skipna:
stat_exprs.append(F.max(scol_for(sdf, name)).alias(name))
else:
stat_exprs.append(
F.when(F.max(scol_for(sdf, has_na_name)), None)
.otherwise(F.max(scol_for(sdf, name)))
.alias(name)
)
stat_exprs.append(F.max(scol_for(sdf, name)).alias(name))
else:
# pandas 3 skipna=False: raise on any NA, otherwise return all-missing labels
stat_exprs.append(
Expand Down Expand Up @@ -2565,29 +2559,24 @@ def idxmin(self, skipna: bool = True) -> FrameLike:
index = self._psdf._internal.index_spark_column_names[0]
index_spark_type = self._psdf._internal.index_fields[0].spark_type

pd_version = LooseVersion(pd.__version__)

stat_exprs = []
for psser, scol in zip(self._agg_columns, self._agg_columns_scols):
name = psser._internal.data_spark_column_names[0]

if LooseVersion(pd.__version__) < "3.0.0" or skipna:
if pd_version < "3.0.0" or skipna:
order_column = scol.asc_nulls_last()

window = Window.partitionBy(*groupkey_names).orderBy(
order_column, NATURAL_ORDER_COLUMN_NAME
)
has_na_name = "__has_na_{}__".format(name)
sdf = sdf.withColumn(has_na_name, scol.isNull()).withColumn(

sdf = sdf.withColumn(
name,
F.when(F.row_number().over(window) == 1, scol_for(sdf, index)).otherwise(None),
)
if skipna:
stat_exprs.append(F.max(scol_for(sdf, name)).alias(name))
else:
stat_exprs.append(
F.when(F.max(scol_for(sdf, has_na_name)), None)
.otherwise(F.max(scol_for(sdf, name)))
.alias(name)
)
stat_exprs.append(F.max(scol_for(sdf, name)).alias(name))
else:
# pandas 3 skipna=False: raise on any NA, otherwise return all-missing labels
stat_exprs.append(
Expand Down
10 changes: 6 additions & 4 deletions python/pyspark/pandas/tests/groupby/test_index.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -242,23 +242,25 @@ def test_idxmax_idxmin_skipna_false_with_na(self):
with self.subTest(i=i):
psdf = ps.from_pandas(pdf)
if LooseVersion(pd.__version__) < "3.0.0":
# pandas-on-Spark preserves the legacy idxmax/idxmin result for skipna=False.
self.assert_eq(
pdf.groupby(["a"]).idxmax(skipna=False).sort_index(),
pdf.groupby(["a"]).idxmax().sort_index(),
psdf.groupby(["a"]).idxmax(skipna=False).sort_index(),
)
self.assert_eq(
pdf.groupby(["a"]).idxmin(skipna=False).sort_index(),
pdf.groupby(["a"]).idxmin().sort_index(),
psdf.groupby(["a"]).idxmin(skipna=False).sort_index(),
)
self.assert_eq(
pdf.groupby(["a"])["b"].idxmax(skipna=False).sort_index(),
pdf.groupby(["a"])["b"].idxmax().sort_index(),
psdf.groupby(["a"])["b"].idxmax(skipna=False).sort_index(),
)
self.assert_eq(
pdf.groupby(["a"])["b"].idxmin(skipna=False).sort_index(),
pdf.groupby(["a"])["b"].idxmin().sort_index(),
psdf.groupby(["a"])["b"].idxmin(skipna=False).sort_index(),
)
else:
# pandas 3 raises for skipna=False when NA values are present.
with self.assertRaisesRegex(
Exception, "idxmax with skipna=False encountered an NA value"
):
Expand Down