cloud-fan commented on a change in pull request #26509: [SPARK-29427][SQL] Add
API to convert RelationalGroupedDataset to KeyValueGroupedDataset
URL: https://github.com/apache/spark/pull/26509#discussion_r346692869
##########
File path:
sql/core/src/main/scala/org/apache/spark/sql/RelationalGroupedDataset.scala
##########
@@ -129,6 +132,32 @@ class RelationalGroupedDataset protected[sql](
(inputExpr: Expression) => exprToFunc(inputExpr)
}
+ /**
+ * Returns a `KeyValueGroupedDataset` where the data is grouped by the
grouping expressions
+ * of current `RelationalGroupedDataset`.
+ *
+ * @since 3.0.0
+ */
+ def keyAs[U : Encoder]: KeyValueGroupedDataset[U, T] = {
+ val keyEncoder = encoderFor[U]
+ val aliasedGrps = groupingExprs.map { g =>
+ g.transformDown {
+ case u: UnresolvedAttribute => df.resolve(u.name)
+ }
+ }.map(alias)
+ val additionalCols = aliasedGrps.filter(g =>
!df.logicalPlan.outputSet.contains(g.toAttribute))
+ val qe = Dataset.ofRows(
+ df.sparkSession,
+ Project(df.logicalPlan.output ++ additionalCols,
df.logicalPlan)).queryExecution
Review comment:
`groupingAttributes` is private in `KeyValueGroupedDataset`
----------------------------------------------------------------
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.
For queries about this service, please contact Infrastructure at:
us...@infra.apache.org
With regards,
Apache Git Services
---------------------------------------------------------------------
To unsubscribe, e-mail: reviews-unsubscr...@spark.apache.org
For additional commands, e-mail: reviews-h...@spark.apache.org
