Github user lucio-yz commented on a diff in the pull request:
https://github.com/apache/spark/pull/20472#discussion_r171184500
--- Diff:
mllib/src/main/scala/org/apache/spark/ml/tree/impl/RandomForest.scala ---
@@ -1001,11 +996,18 @@ private[spark] object RandomForest extends Logging {
} else {
val numSplits = metadata.numSplits(featureIndex)
- // get count for each distinct value
- val (valueCountMap, numSamples) =
featureSamples.foldLeft((Map.empty[Double, Int], 0)) {
+ // get count for each distinct value except zero value
+ val (partValueCountMap, partNumSamples) =
featureSamples.foldLeft((Map.empty[Double, Int], 0)) {
--- End diff --
have fixed it.
---
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
