zhengruifeng commented on code in PR #52581:
URL: https://github.com/apache/spark/pull/52581#discussion_r2425161204
##########
sql/core/src/main/scala/org/apache/spark/sql/execution/python/ArrowAggregatePythonExec.scala:
##########
@@ -180,17 +180,33 @@ case class ArrowAggregatePythonExec(
rows
}
- val columnarBatchIter = new ArrowPythonWithNamedArgumentRunner(
- pyFuncs,
- evalType,
- argMetas,
- aggInputSchema,
- sessionLocalTimeZone,
- largeVarTypes,
- pythonRunnerConf,
- pythonMetrics,
- jobArtifactUUID,
- conf.pythonUDFProfiler).compute(projectedRowIter,
context.partitionId(), context)
+ val runner = if (evalType == PythonEvalType.SQL_GROUPED_AGG_PANDAS_UDF) {
+ new ArrowPythonWithNamedArgumentRunner(
+ pyFuncs,
+ evalType,
+ argMetas,
+ aggInputSchema,
+ sessionLocalTimeZone,
+ largeVarTypes,
+ pythonRunnerConf,
+ pythonMetrics,
+ jobArtifactUUID,
+ conf.pythonUDFProfiler) with GroupedPythonArrowInput
+ } else {
+ new ArrowPythonWithNamedArgumentRunner(
Review Comment:
I am hitting some weird issue in the work on SQL_GROUPED_AGG_ARROW_UDF,
will fix it separately in https://issues.apache.org/jira/browse/SPARK-53867
--
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]
