d80tb7 commented on a change in pull request #24981: [SPARK-27463][PYTHON] Support Dataframe Cogroup via Pandas UDFs URL: https://github.com/apache/spark/pull/24981#discussion_r315761355
########## File path: sql/core/src/main/scala/org/apache/spark/sql/execution/python/FlatMapGroupsInPandasExec.scala ########## @@ -75,88 +71,23 @@ case class FlatMapGroupsInPandasExec( override protected def doExecute(): RDD[InternalRow] = { val inputRDD = child.execute() - val chainedFunc = Seq(ChainedPythonFunctions(Seq(pandasFunction))) - val sessionLocalTimeZone = conf.sessionLocalTimeZone - val pythonRunnerConf = ArrowUtils.getPythonRunnerConfMap(conf) - - // Deduplicate the grouping attributes. - // If a grouping attribute also appears in data attributes, then we don't need to send the - // grouping attribute to Python worker. If a grouping attribute is not in data attributes, - // then we need to send this grouping attribute to python worker. - // - // We use argOffsets to distinguish grouping attributes and data attributes as following: - // - // argOffsets[0] is the length of grouping attributes - // argOffsets[1 .. argOffsets[0]+1] is the arg offsets for grouping attributes - // argOffsets[argOffsets[0]+1 .. ] is the arg offsets for data attributes - - val dataAttributes = child.output.drop(groupingAttributes.length) - val groupingIndicesInData = groupingAttributes.map { attribute => - dataAttributes.indexWhere(attribute.semanticEquals) - } - - val groupingArgOffsets = new ArrayBuffer[Int] - val nonDupGroupingAttributes = new ArrayBuffer[Attribute] - val nonDupGroupingSize = groupingIndicesInData.count(_ == -1) - - // Non duplicate grouping attributes are added to nonDupGroupingAttributes and Review comment: So the comments are definitely still needed as the mechanism is essentially the same and this is somewhat complex. These comments have moved to BasePandasGroupExec.resolveArgOffsets- the wording has changed slightly but I think all the same information is there. If you think anything is missing or not clear please let me know and I'll be happy to amend. ---------------------------------------------------------------- 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