shahidki31 commented on a change in pull request #32494: URL: https://github.com/apache/spark/pull/32494#discussion_r631528684
########## File path: sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/plans/logical/statsEstimation/FilterEstimation.scala ########## @@ -225,7 +225,7 @@ case class FilterEstimation(plan: Filter) extends Logging { attr: Attribute, isNull: Boolean, update: Boolean): Option[Double] = { - if (!colStatsMap.contains(attr) || !colStatsMap(attr).hasCountStats) { + if (!colStatsMap.contains(attr) || colStatsMap(attr).nullCount.isEmpty) { Review comment: Ideally this method doesn't require `distinctCount`. Union operator doesn't return `distinctCount`, but it can return `nullCount`. -- 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 --------------------------------------------------------------------- To unsubscribe, e-mail: reviews-unsubscr...@spark.apache.org For additional commands, e-mail: reviews-h...@spark.apache.org