Skip to content

[SPARK-29816][MLLIB] Missing persist in mllib.evaluation.BinaryClassificationMetrics.recallByThreshold() #26447

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
amanomer wants to merge 2 commits into from
Closed

[SPARK-29816][MLLIB] Missing persist in mllib.evaluation.BinaryClassificationMetrics.recallByThreshold() #26447

Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
84406fa
Initial commit
amanomer Nov 9, 2019
23726f9
Changed RDD which is to be persisted
amanomer Nov 9, 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
7 changes: 5 additions & 2 deletions mllib/src/main/scala/org/apache/spark/mllib/evaluation/BinaryClassificationMetrics.scala
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -165,13 +165,15 @@ class BinaryClassificationMetrics @Since("3.0.0") (
confusions: RDD[(Double, BinaryConfusionMatrix)]) = {
// Create a bin for each distinct score value, count weighted positives and
// negatives within each bin, and then sort by score values in descending order.
val counts = scoreLabelsWeight.combineByKey(
val binnedWeights = scoreLabelsWeight.combineByKey(
createCombiner = (labelAndWeight: (Double, Double)) =>
new BinaryLabelCounter(0.0, 0.0) += (labelAndWeight._1, labelAndWeight._2),
mergeValue = (c: BinaryLabelCounter, labelAndWeight: (Double, Double)) =>
c += (labelAndWeight._1, labelAndWeight._2),
mergeCombiners = (c1: BinaryLabelCounter, c2: BinaryLabelCounter) => c1 += c2
).sortByKey(ascending = false)
)
binnedWeights.persist()
Copy link
Member

@MaxGekk MaxGekk Nov 9, 2019

Choose a reason for hiding this comment

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

Could you explain why do you persist binnedWeights but not counts? As I can see binnedWeights is used only once ... or I missed something?

Copy link
Contributor Author

@amanomer amanomer Nov 9, 2019

Choose a reason for hiding this comment

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

Rdd scoreAndLabels.combineByKey is found to be used more than one time, as mentioned in SPARK-29816.
I think, counts rdd is constructed over scoreAndLabels.combineByKey after action sortByKey. counts is indirectly dependent on scoreAndLabels.combineByKey i.e, binnedWeights?

val counts = binnedWeights.sortByKey(ascending = false)

val binnedCounts =
// Only down-sample if bins is > 0
Expand Down Expand Up @@ -207,6 +209,7 @@ class BinaryClassificationMetrics @Since("3.0.0") (
}
}

binnedWeights.unpersist()
val agg = binnedCounts.values.mapPartitions { iter =>
val agg = new BinaryLabelCounter()
iter.foreach(agg += _)
Expand Down