Github user rxin commented on a diff in the pull request: https://github.com/apache/spark/pull/5842#discussion_r29635785 --- Diff: sql/core/src/main/scala/org/apache/spark/sql/execution/stat/StatFunctions.scala --- @@ -95,4 +97,28 @@ private[sql] object StatFunctions { val counts = collectStatisticalData(df, cols) 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 counts = df.groupBy(col1, col2).agg(col(col1), col(col2), count("*")).take(1e8.toInt) --- End diff -- @brkyvz can you submit a follow up pr to reduce 1e8 to 1e6? 1e8 is too large.
--- 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