HeartSaVioR commented on code in PR #49560:
URL: https://github.com/apache/spark/pull/49560#discussion_r1953966237
##########
sql/connect/server/src/main/scala/org/apache/spark/sql/connect/planner/SparkConnectPlanner.scala:
##########
@@ -1034,6 +1038,49 @@ class SparkConnectPlanner(
.logicalPlan
}
+ private def transformTransformWithStateInPandas(
+ pythonUdf: PythonUDF,
+ groupedDs: RelationalGroupedDataset,
+ rel: proto.GroupMap): LogicalPlan = {
+ val twsInfo = rel.getTransformWithStateInfo
+ val outputSchema = parseSchema(twsInfo.getOutputSchema)
+
+ if (rel.hasInitialInput) {
+ val initialGroupingCols =
rel.getInitialGroupingExpressionsList.asScala.toSeq.map(expr =>
+ Column(transformExpression(expr)))
+
+ val initialStateDs = Dataset
+ .ofRows(session, transformRelation(rel.getInitialInput))
+ .groupBy(initialGroupingCols: _*)
+
+ // Explicitly creating UDF on resolved column to avoid ambiguity of
analysis on initial state
+ // columns and the input columns
+ val resolvedPythonUDF = createUserDefinedPythonFunction(rel.getFunc)
+ .builder(groupedDs.df.logicalPlan.output)
+ .asInstanceOf[PythonUDF]
+
+ groupedDs
Review Comment:
It's not only initialStateDs but UDF as well. It does not seem to help much.
--
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]
