zhengruifeng commented on code in PR #38318:
URL: https://github.com/apache/spark/pull/38318#discussion_r1006439147
##########
connector/connect/src/main/scala/org/apache/spark/sql/connect/planner/SparkConnectPlanner.scala:
##########
@@ -93,6 +96,19 @@ class SparkConnectPlanner(plan: proto.Relation, session:
SparkSession) {
transformRelation(rel.getInput))
}
+ private def transformDataFrameFunction(rel: proto.DataFrameFunction):
LogicalPlan = {
+ val child = transformRelation(rel.getInput)
+
+ rel.getFunctionCase match {
+ case proto.DataFrameFunction.FunctionCase.SUMMARY =>
+ StatFunctions
+ .summary(Dataset.ofRows(session, child),
rel.getSummary.getStatisticsList.asScala.toSeq)
Review Comment:
@cloud-fan the old `df.summary` eagerly compute the statistics and always
return a `LocalRelation`
--
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]
