Github user srowen commented on a diff in the pull request:
https://github.com/apache/spark/pull/13624#discussion_r68391463
--- Diff:
mllib/src/main/scala/org/apache/spark/mllib/tree/model/treeEnsembleModels.scala
---
@@ -151,31 +151,24 @@ class GradientBoostedTreesModel @Since("1.2.0") (
case _ => data
}
- val numIterations = trees.length
- val evaluationArray = Array.fill(numIterations)(0.0)
- val localTreeWeights = treeWeights
-
- var predictionAndError =
GradientBoostedTreesModel.computeInitialPredictionAndError(
- remappedData, localTreeWeights(0), trees(0), loss)
-
- evaluationArray(0) = predictionAndError.values.mean()
-
val broadcastTrees = sc.broadcast(trees)
- (1 until numIterations).foreach { nTree =>
- predictionAndError =
remappedData.zip(predictionAndError).mapPartitions { iter =>
- val currentTree = broadcastTrees.value(nTree)
- val currentTreeWeight = localTreeWeights(nTree)
- iter.map { case (point, (pred, error)) =>
- val newPred = pred + currentTree.predict(point.features) *
currentTreeWeight
- val newError = loss.computeError(newPred, point.label)
- (newPred, newError)
- }
+ val localTreeWeights = treeWeights
+ val treesIndices = trees.indices
+
+ val dataCount = remappedData.count()
+ val evaluation = remappedData
+ .map { (point: LabeledPoint) =>
--- End diff --
This block could use similar changes to the ones above for consistency
---
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 [email protected] or file a JIRA ticket
with INFRA.
---
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
