Skip to content

[SPARK-26153][ML] GBT & RandomForest avoid unnecessary first job to compute numFeatures #23123

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 1 commit into from
Closed

[SPARK-26153][ML] GBT & RandomForest avoid unnecessary first job to compute numFeatures #23123

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
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
5 changes: 3 additions & 2 deletions mllib/src/main/scala/org/apache/spark/ml/classification/GBTClassifier.scala
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -180,7 +180,6 @@ class GBTClassifier @Since("1.4.0") (
(convert2LabeledPoint(dataset), null)
}

val numFeatures = trainDataset.first().features.size
val boostingStrategy = super.getOldBoostingStrategy(categoricalFeatures, OldAlgo.Classification)

val numClasses = 2
Expand All @@ -196,7 +195,6 @@ class GBTClassifier @Since("1.4.0") (
maxDepth, maxBins, maxIter, maxMemoryInMB, minInfoGain, minInstancesPerNode,
seed, stepSize, subsamplingRate, cacheNodeIds, checkpointInterval, featureSubsetStrategy,
validationIndicatorCol)
instr.logNumFeatures(numFeatures)
instr.logNumClasses(numClasses)

val (baseLearners, learnerWeights) = if (withValidation) {
Expand All @@ -206,6 +204,9 @@ class GBTClassifier @Since("1.4.0") (
GradientBoostedTrees.run(trainDataset, boostingStrategy, $(seed), $(featureSubsetStrategy))
}

val numFeatures = baseLearners.head.numFeatures
instr.logNumFeatures(numFeatures)

new GBTClassificationModel(uid, baseLearners, learnerWeights, numFeatures)
}

Expand Down
2 changes: 1 addition & 1 deletion mllib/src/main/scala/org/apache/spark/ml/classification/RandomForestClassifier.scala
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -142,7 +142,7 @@ class RandomForestClassifier @Since("1.4.0") (
.run(oldDataset, strategy, getNumTrees, getFeatureSubsetStrategy, getSeed, Some(instr))
.map(_.asInstanceOf[DecisionTreeClassificationModel])

val numFeatures = oldDataset.first().features.size
val numFeatures = trees.head.numFeatures
instr.logNumClasses(numClasses)
instr.logNumFeatures(numFeatures)
new RandomForestClassificationModel(uid, trees, numFeatures, numClasses)
Expand Down
6 changes: 4 additions & 2 deletions mllib/src/main/scala/org/apache/spark/ml/regression/GBTRegressor.scala
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -165,15 +165,13 @@ class GBTRegressor @Since("1.4.0") (@Since("1.4.0") override val uid: String)
} else {
(extractLabeledPoints(dataset), null)
}
val numFeatures = trainDataset.first().features.size
val boostingStrategy = super.getOldBoostingStrategy(categoricalFeatures, OldAlgo.Regression)

instr.logPipelineStage(this)
instr.logDataset(dataset)
instr.logParams(this, labelCol, featuresCol, predictionCol, impurity, lossType,
maxDepth, maxBins, maxIter, maxMemoryInMB, minInfoGain, minInstancesPerNode,
seed, stepSize, subsamplingRate, cacheNodeIds, checkpointInterval, featureSubsetStrategy)
instr.logNumFeatures(numFeatures)

val (baseLearners, learnerWeights) = if (withValidation) {
GradientBoostedTrees.runWithValidation(trainDataset, validationDataset, boostingStrategy,
Expand All @@ -182,6 +180,10 @@ class GBTRegressor @Since("1.4.0") (@Since("1.4.0") override val uid: String)
GradientBoostedTrees.run(trainDataset, boostingStrategy,
$(seed), $(featureSubsetStrategy))
}

val numFeatures = baseLearners.head.numFeatures
instr.logNumFeatures(numFeatures)

new GBTRegressionModel(uid, baseLearners, learnerWeights, numFeatures)
}

Expand Down
2 changes: 1 addition & 1 deletion mllib/src/main/scala/org/apache/spark/ml/regression/RandomForestRegressor.scala
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -133,7 +133,7 @@ class RandomForestRegressor @Since("1.4.0") (@Since("1.4.0") override val uid: S
.run(oldDataset, strategy, getNumTrees, getFeatureSubsetStrategy, getSeed, Some(instr))
.map(_.asInstanceOf[DecisionTreeRegressionModel])

val numFeatures = oldDataset.first().features.size
val numFeatures = trees.head.numFeatures
instr.logNamedValue(Instrumentation.loggerTags.numFeatures, numFeatures)
new RandomForestRegressionModel(uid, trees, numFeatures)
}
Expand Down