viirya commented on code in PR #37390:
URL: https://github.com/apache/spark/pull/37390#discussion_r936250722
##########
sql/core/src/main/scala/org/apache/spark/sql/execution/python/AggregateInPandasExec.scala:
##########
@@ -131,12 +131,13 @@ case class AggregateInPandasExec(
val newIter: Iterator[InternalRow] =
mayAppendUpdatingSessionIterator(iter)
val prunedProj = UnsafeProjection.create(allInputs.toSeq, child.output)
- val grouped = if (groupingExpressions.isEmpty) {
+ val groupedItr = if (groupingExpressions.isEmpty) {
// Use an empty unsafe row as a place holder for the grouping key
Iterator((new UnsafeRow(), newIter))
} else {
GroupedIterator(newIter, groupingExpressions, child.output)
- }.map { case (key, rows) =>
+ }
+ val grouped = groupedItr.map { case (key, rows) =>
(key, rows.map(prunedProj))
}
Review Comment:
This only applies on `GroupedIterator` previously? Looks like both...
--
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]
