Skip to content

[SPARK-58214][PYTHON] Consolidate VALUE_NOT_PEARSON into VALUE_NOT_ALLOWED #57366

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
zhengruifeng wants to merge 2 commits into from
Closed

[SPARK-58214][PYTHON] Consolidate VALUE_NOT_PEARSON into VALUE_NOT_ALLOWED #57366

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
c2c10e5
[WIP][PYTHON] Use VALUE_NOT_ALLOWED for corr
zhengruifeng Jul 20, 2026
ec9c86e
[WIP][PYTHON] Simplify corr error test
zhengruifeng Jul 20, 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
5 changes: 0 additions & 5 deletions python/pyspark/errors/error-conditions.json
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -1208,11 +1208,6 @@
"Value for `<arg_name>` must be a non-empty string, got '<arg_value>'."
]
},
"VALUE_NOT_PEARSON": {
"message": [
"Value for `<arg_name>` only supports 'pearson', got '<arg_value>'."
]
},
"VALUE_NOT_PLAIN_COLUMN_REFERENCE": {
"message": [
"Value `<val>` in `<field_name>` should be a plain column reference such as `df.col` or `col('column')`."
Expand Down
4 changes: 2 additions & 2 deletions python/pyspark/sql/classic/dataframe.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -1693,8 +1693,8 @@ def corr(self, col1: str, col2: str, method: Optional[str] = None) -> float:
method = "pearson"
if not method == "pearson":
raise PySparkValueError(
errorClass="VALUE_NOT_PEARSON",
messageParameters={"arg_name": "method", "arg_value": method},
errorClass="VALUE_NOT_ALLOWED",
messageParameters={"arg_name": "method", "allowed_values": "['pearson']"},
)
return self._jdf.stat().corr(col1, col2, method)

Expand Down
4 changes: 2 additions & 2 deletions python/pyspark/sql/connect/dataframe.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -1663,8 +1663,8 @@ def corr(self, col1: str, col2: str, method: Optional[str] = None) -> float:
method = "pearson"
if not method == "pearson":
raise PySparkValueError(
errorClass="VALUE_NOT_PEARSON",
messageParameters={"arg_name": "method", "arg_value": method},
errorClass="VALUE_NOT_ALLOWED",
messageParameters={"arg_name": "method", "allowed_values": "['pearson']"},
)
table, _ = DataFrame(
plan.StatCorr(child=self._plan, col1=col1, col2=col2, method=method),
Expand Down
15 changes: 8 additions & 7 deletions python/pyspark/sql/tests/connect/test_connect_stat.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -214,13 +214,14 @@ def test_stat_corr(self):
"arg_type": "int",
},
)
with self.assertRaises(ValueError) as context:
(self.connect.read.table(self.tbl_name2).stat.corr("col1", "col3", "spearman"),)
self.assertTrue(
"Currently only the calculation of the Pearson Correlation "
+ "coefficient is supported."
in str(context.exception)
)
with self.assertRaises(PySparkValueError) as pe:
self.connect.read.table(self.tbl_name2).stat.corr("col1", "col3", "spearman")

self.check_error(
exception=pe.exception,
errorClass="VALUE_NOT_ALLOWED",
messageParameters={"arg_name": "method", "allowed_values": "['pearson']"},
)

def test_stat_approx_quantile(self):
# SPARK-41069: Test the stat.approxQuantile method
Expand Down