pengzhon-db commented on code in PR #40736:
URL: https://github.com/apache/spark/pull/40736#discussion_r1164465478
##########
python/pyspark/sql/connect/group.py:
##########
@@ -262,8 +264,44 @@ def applyInPandas(
applyInPandas.__doc__ = PySparkGroupedData.applyInPandas.__doc__
- def applyInPandasWithState(self, *args: Any, **kwargs: Any) -> None:
- raise NotImplementedError("applyInPandasWithState() is not
implemented.")
+ def applyInPandasWithState(
+ self,
+ func: "PandasGroupedMapFunctionWithState",
+ outputStructType: Union[StructType, str],
+ stateStructType: Union[StructType, str],
+ outputMode: str,
+ timeoutConf: str
+ ) -> "DataFrame":
+ from pyspark.sql.connect.udf import UserDefinedFunction
+ from pyspark.sql.connect.dataframe import DataFrame
+
+ udf_obj = UserDefinedFunction(
+ func,
+ returnType=outputStructType,
+ evalType=PythonEvalType.SQL_GROUPED_MAP_PANDAS_UDF_WITH_STATE,
+ )
+
+ output_schema: str = outputStructType.json() if
isinstance(outputStructType, StructType)\
Review Comment:
@WweiL The return type of udf is a bit different. Here I am following the
way how [DataStreamReader handles
schema](https://github.com/apache/spark/blob/007a42b8511b005aabdf45955e504d1f71eb1d25/python/pyspark/sql/connect/streaming/readwriter.py#L61).
The server will parse the schema.
--
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.
To unsubscribe, e-mail: [email protected]
For queries about this service, please contact Infrastructure at:
[email protected]
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
