Github user srowen commented on a diff in the pull request: https://github.com/apache/spark/pull/15018#discussion_r94640811 --- Diff: mllib/src/main/scala/org/apache/spark/mllib/regression/IsotonicRegression.scala --- @@ -328,74 +336,80 @@ class IsotonicRegression private (private var isotonic: Boolean) extends Seriali return Array.empty } - // Pools sub array within given bounds assigning weighted average value to all elements. - def pool(input: Array[(Double, Double, Double)], start: Int, end: Int): Unit = { - val poolSubArray = input.slice(start, end + 1) - val weightedSum = poolSubArray.map(lp => lp._1 * lp._3).sum - val weight = poolSubArray.map(_._3).sum + // Keeps track of the start and end indices of the blocks. if [i, j] is a valid block from + // input(i) to input(j) (inclusive), then blockBounds(i) = j and blockBounds(j) = i + val blockBounds = Array.range(0, input.length) // Initially, each data point is its own block - var i = start - while (i <= end) { - input(i) = (weightedSum / weight, input(i)._2, input(i)._3) - i = i + 1 - } + // Keep track of the sum of weights and sum of weight * y for each block. weights(start) + // gives the values for the block. Entries that are not at the start of a block + // are meaningless. + val weights: Array[(Double, Double)] = input.map { case (y, _, weight) => + require(weight != 0.0) --- End diff -- Are negative weights OK? (you don't need a type on `weight`, but hardly matters)
--- 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