Github user dorx commented on a diff in the pull request: https://github.com/apache/spark/pull/1710#discussion_r15681388 --- Diff: mllib/src/main/scala/org/apache/spark/mllib/stat/correlation/SpearmanCorrelation.scala --- @@ -89,20 +89,17 @@ private[stat] object SpearmanCorrelation extends Correlation with Logging { val ranks: RDD[(Long, Double)] = sorted.mapPartitions { iter => // add an extra element to signify the end of the list so that flatMap can flush the last // batch of duplicates - val padded = iter ++ - Iterator[((Double, Long), Long)](((Double.NaN, -1L), -1L)) - var lastVal = 0.0 - var firstRank = 0.0 - val idBuffer = new ArrayBuffer[Long]() + val padded = iter ++ Iterator[((Double, Long), Long)](((Double.NaN, -1L), -1L)) + val firstEntry = padded.next() + var lastVal = firstEntry._1._1 + var firstRank = firstEntry._2.toDouble + val idBuffer = new ArrayBuffer[Long]() += firstEntry._1._2 padded.flatMap { case ((v, id), rank) => - if (v == lastVal && id != Long.MinValue) { + if (v == lastVal && id != Long.MinValue) { --- End diff -- oops that's supposed to be `-1L`
--- 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. ---