Github user HyukjinKwon commented on a diff in the pull request: https://github.com/apache/spark/pull/19872#discussion_r154644340 --- Diff: sql/core/src/main/scala/org/apache/spark/sql/RelationalGroupedDataset.scala --- @@ -437,6 +437,37 @@ class RelationalGroupedDataset protected[sql]( df.logicalPlan)) } + + private[sql] def aggInPandas(columns: Seq[Column]): DataFrame = { + val exprs = columns.map(column => column.expr.asInstanceOf[PythonUDF]) + + val groupingNamedExpressions = groupingExprs.map { + case ne: NamedExpression => ne + case other => Alias(other, other.toString)() + } + + val groupingAttributes = groupingNamedExpressions.map(_.toAttribute) + + val child = df.logicalPlan + + val childrenExpressions = exprs.flatMap(expr => + expr.children.map { + case ne: NamedExpression => ne + case other => Alias(other, other.toString)() + }) + + val project = Project(groupingNamedExpressions ++ childrenExpressions, child) + + val udfOutputs = exprs.flatMap(expr => + Seq(AttributeReference(expr.name, expr.dataType)()) + ) --- End diff -- I think this could be inlined.
--- --------------------------------------------------------------------- To unsubscribe, e-mail: reviews-unsubscr...@spark.apache.org For additional commands, e-mail: reviews-h...@spark.apache.org