From 2b2f4138c0dba918d523c84bc7cc6a5b48be8b49 Mon Sep 17 00:00:00 2001 From: Haotian Sun Date: Fri, 24 Jul 2026 00:13:06 +0000 Subject: [PATCH] [SPARK-58312][PYTHON] Remove unnecessary type: ignore comments in pyspark.sql.udf and group --- python/pyspark/sql/group.py | 14 ++++++++------ python/pyspark/sql/udf.py | 9 ++++----- 2 files changed, 12 insertions(+), 11 deletions(-) diff --git a/python/pyspark/sql/group.py b/python/pyspark/sql/group.py index 3c6f241f2948e..221105d96783a 100644 --- a/python/pyspark/sql/group.py +++ b/python/pyspark/sql/group.py @@ -15,6 +15,8 @@ # limitations under the License. # +# mypy: disable-error-code="empty-body" + import sys from typing import Callable, List, Optional, TYPE_CHECKING, overload, Dict, Union, cast, Tuple @@ -189,7 +191,7 @@ def agg(self, *exprs: Union[Column, Dict[str, str]]) -> "DataFrame": return DataFrame(jdf, self.session) @dfapi - def count(self) -> "DataFrame": # type: ignore[empty-body] + def count(self) -> "DataFrame": """Counts the number of records for each group. .. versionadded:: 1.3.0 @@ -223,7 +225,7 @@ def count(self) -> "DataFrame": # type: ignore[empty-body] """ @df_varargs_api - def mean(self, *cols: str) -> DataFrame: # type: ignore[empty-body] + def mean(self, *cols: str) -> DataFrame: """Computes average values for each numeric columns for each group. :func:`mean` is an alias for :func:`avg`. @@ -240,7 +242,7 @@ def mean(self, *cols: str) -> DataFrame: # type: ignore[empty-body] """ @df_varargs_api - def avg(self, *cols: str) -> "DataFrame": # type: ignore[empty-body] + def avg(self, *cols: str) -> "DataFrame": """Computes average values for each numeric columns for each group. :func:`mean` is an alias for :func:`avg`. @@ -291,7 +293,7 @@ def avg(self, *cols: str) -> "DataFrame": # type: ignore[empty-body] """ @df_varargs_api - def max(self, *cols: str) -> "DataFrame": # type: ignore[empty-body] + def max(self, *cols: str) -> "DataFrame": """Computes the max value for each numeric columns for each group. .. versionadded:: 1.3.0 @@ -335,7 +337,7 @@ def max(self, *cols: str) -> "DataFrame": # type: ignore[empty-body] """ @df_varargs_api - def min(self, *cols: str) -> "DataFrame": # type: ignore[empty-body] + def min(self, *cols: str) -> "DataFrame": """Computes the min value for each numeric column for each group. .. versionadded:: 1.3.0 @@ -384,7 +386,7 @@ def min(self, *cols: str) -> "DataFrame": # type: ignore[empty-body] """ @df_varargs_api - def sum(self, *cols: str) -> DataFrame: # type: ignore[empty-body] + def sum(self, *cols: str) -> DataFrame: """Computes the sum for each numeric columns for each group. .. versionadded:: 1.3.0 diff --git a/python/pyspark/sql/udf.py b/python/pyspark/sql/udf.py index e586c560deeb4..7dbdc212dc6df 100644 --- a/python/pyspark/sql/udf.py +++ b/python/pyspark/sql/udf.py @@ -707,22 +707,21 @@ def register( "SQL_GROUPED_AGG_PANDAS_ITER_UDF or SQL_GROUPED_AGG_ARROW_ITER_UDF" }, ) - source_udf = _create_udf( + register_udf = UserDefinedFunction( f.func, returnType=f.returnType, name=name, evalType=f.evalType, deterministic=f.deterministic, ) - register_udf = source_udf._unwrapped # type: ignore[attr-defined] - return_udf = register_udf + return_udf: "UserDefinedFunctionLike" = register_udf else: if returnType is None: returnType = StringType() - return_udf = _create_udf( + register_udf = UserDefinedFunction( f, returnType=returnType, evalType=PythonEvalType.SQL_BATCHED_UDF, name=name ) - register_udf = return_udf._unwrapped # type: ignore[attr-defined] + return_udf = register_udf._wrapped() self.sparkSession._jsparkSession.udf().registerPython(name, register_udf._judf) return return_udf