Github user andrewor14 commented on a diff in the pull request: https://github.com/apache/spark/pull/2839#discussion_r19051180 --- Diff: core/src/main/scala/org/apache/spark/rdd/PairRDDFunctions.scala --- @@ -238,8 +238,15 @@ class PairRDDFunctions[K, V](self: RDD[(K, V)]) @deprecated("Use reduceByKeyLocally", "1.0.0") def reduceByKeyToDriver(func: (V, V) => V): Map[K, V] = reduceByKeyLocally(func) - /** Count the number of elements for each key, and return the result to the master as a Map. */ - def countByKey(): Map[K, Long] = self.map(_._1).countByValue() + /** + * Count the number of elements for each key, collecting the results to a local Map. + * + * Note that this method should only be used if the resulting map is expected to be small, as + * the whole thing is loaded into the driver's memory. + * To handle very large results, consider using rdd.mapValues(_ => 1).reduceByKey(_ + _), which + * returns an RDD[T, Long] instead of a map. + */ + def countByKey(): Map[K, Long] = self.mapValues(_ => 1L).reduceByKey(_ + _).collect.toMap --- End diff -- think you need `collect()`
--- 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