Skip to content

[SPARK-9612][ML] Add instance weight support for GBTs #25926

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Closed
zhengruifeng wants to merge 9 commits into from
Closed

[SPARK-9612][ML] Add instance weight support for GBTs #25926

Changes from 1 commit
Commits
Show all changes
9 commits
Select commit Hold shift + click to select a range
68a3169
init
zhengruifeng Sep 5, 2019
fc9c6cc
update
zhengruifeng Sep 12, 2019
51f9b99
update
zhengruifeng Sep 25, 2019
d4a7a15
update test
zhengruifeng Sep 25, 2019
7ec15ed
nit: mappartitions -> map
zhengruifeng Sep 26, 2019
8e5fc7b
address some comments
zhengruifeng Oct 8, 2019
e3c9372
revert err msg in testsuite
zhengruifeng Oct 8, 2019
23f27a5
update Instance scope
zhengruifeng Oct 8, 2019
3000397
address comments
zhengruifeng Oct 16, 2019
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
Prev Previous commit
Next Next commit
nit: mappartitions -> map
  • Loading branch information
@zhengruifeng
zhengruifeng committed Oct 23, 2019
commit 7ec15ed271b8a1b714c06599fff79b462e1dda21
5 changes: 2 additions & 3 deletions mllib/src/main/scala/org/apache/spark/ml/tree/impl/GradientBoostedTrees.scala
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -134,12 +134,11 @@ private[spark] object GradientBoostedTrees extends Logging {
treeWeight: Double,
tree: DecisionTreeRegressionModel,
loss: OldLoss): RDD[(Double, Double)] = {
data.zip(predictionAndError).mapPartitions { iter =>
iter.map { case (Instance(label, _, features), (pred, _)) =>
data.zip(predictionAndError).map {
case (Instance(label, _, features), (pred, _)) =>
Copy link
Contributor

@imatiach-msft imatiach-msft Oct 7, 2019

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

same thing here - it seems like we are ignoring the weight column but intuitively it seems like it should be included, could you explain the reasoning behind it being excluded here?

Copy link
Contributor

@imatiach-msft imatiach-msft Oct 7, 2019

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

oh, reading some of the other code this looks like unweighted error. That seems very confusing. I think we could improve this code structure a bit more.

val newPred = updatePrediction(features, pred, tree, treeWeight)
val newError = loss.computeError(newPred, label)
(newPred, newError)
}
}
}

Expand Down