Github user jkbradley commented on a diff in the pull request:
https://github.com/apache/spark/pull/14547#discussion_r75523815
--- Diff:
mllib/src/main/scala/org/apache/spark/ml/tree/impl/GradientBoostedTrees.scala
---
@@ -258,11 +258,13 @@ private[spark] object GradientBoostedTrees extends
Logging {
val baseLearnerWeights = new Array[Double](numIterations)
val loss = boostingStrategy.loss
val learningRate = boostingStrategy.learningRate
- // Prepare strategy for individual trees, which use regression with
variance impurity.
+ // Prepare strategy for individual trees, which all use regression.
+ // TODO(vlad17): Changing the strategy here is confusing (especially
using regression for
+ // classification). With the resolution of SPARK-16728, this shouldn't
be necessary.
val treeStrategy = boostingStrategy.treeStrategy.copy
val validationTol = boostingStrategy.validationTol
treeStrategy.algo = OldAlgo.Regression
- treeStrategy.impurity = OldVariance
+ treeStrategy.impurity = boostingStrategy.treeStrategy.impurity
--- End diff --
No need for this line anymore
---
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]
