Github user rxin commented on a diff in the pull request: https://github.com/apache/spark/pull/5842#discussion_r29553037 --- Diff: sql/core/src/main/scala/org/apache/spark/sql/execution/stat/StatFunctions.scala --- @@ -77,4 +78,42 @@ private[sql] object StatFunctions { }) counts.cov } + + /** Generate a table of frequencies for the elements of two columns. */ + private[sql] def crossTabulate(df: DataFrame, col1: String, col2: String): DataFrame = { + val tableName = s"${col1}_$col2" + val distinctCol2 = df.select(col2).distinct.collect().sortBy(_.get(0).toString) --- End diff -- use dataframe's own group by and count; don't use the rdd one. df one will get a lot faster with tungsten over time.
--- If your project is set up for it, you can reply to this email and have your reply appear on GitHub as well. If your project does not have this feature enabled and wishes so, or if the feature is enabled but not working, please contact infrastructure at infrastruct...@apache.org or file a JIRA ticket with INFRA. --- --------------------------------------------------------------------- To unsubscribe, e-mail: reviews-unsubscr...@spark.apache.org For additional commands, e-mail: reviews-h...@spark.apache.org