Github user smurching commented on a diff in the pull request:
https://github.com/apache/spark/pull/19666#discussion_r149238185
--- Diff:
mllib/src/main/scala/org/apache/spark/ml/tree/impl/RandomForest.scala ---
@@ -741,17 +678,43 @@ private[spark] object RandomForest extends Logging {
(splits(featureIndex)(bestFeatureSplitIndex),
bestFeatureGainStats)
} else if (binAggregates.metadata.isUnordered(featureIndex)) {
// Unordered categorical feature
- val leftChildOffset =
binAggregates.getFeatureOffset(featureIndexIdx)
- val (bestFeatureSplitIndex, bestFeatureGainStats) =
- Range(0, numSplits).map { splitIndex =>
- val leftChildStats =
binAggregates.getImpurityCalculator(leftChildOffset, splitIndex)
- val rightChildStats =
binAggregates.getParentImpurityCalculator()
- .subtract(leftChildStats)
+ val numBins = binAggregates.metadata.numBins(featureIndex)
+ val featureOffset =
binAggregates.getFeatureOffset(featureIndexIdx)
+
+ val binStatsArray = Array.tabulate(numBins) { binIndex =>
+ binAggregates.getImpurityCalculator(featureOffset, binIndex)
+ }
+ val parentStats = binAggregates.getParentImpurityCalculator()
+
+ var bestGain = Double.NegativeInfinity
+ var bestSet: BitSet = null
+ var bestLeftChildStats: ImpurityCalculator = null
+ var bestRightChildStats: ImpurityCalculator = null
+
+ traverseUnorderedSplits[ImpurityCalculator](numBins, null,
--- End diff --
Could you please add a comment explaining what this does? E.g.:
`// Computes the best split for the current feature, storing the result
across the vars above`
---
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
