Skip to content

[SPARK-28514][ML] Remove the redundant transformImpl method in RF & GBT #25256

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 6 commits into from
Closed

[SPARK-28514][ML] Remove the redundant transformImpl method in RF & GBT #25256

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
6 commits
Select commit Hold shift + click to select a range
db9de7c
init
zhengruifeng Jul 25, 2019
41c0f63
init
zhengruifeng Jul 25, 2019
41ca50d
revert the regression side
zhengruifeng Aug 2, 2019
0136a83
disable transformImpl in classification
zhengruifeng Aug 4, 2019
6c61f60
mark private
zhengruifeng Aug 4, 2019
f6a10d0
not private
zhengruifeng Aug 5, 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
3 changes: 3 additions & 0 deletions mllib/src/main/scala/org/apache/spark/ml/classification/Classifier.scala
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -210,6 +210,9 @@ abstract class ClassificationModel[FeaturesType, M <: ClassificationModel[Featur
outputData.toDF
}

final override def transformImpl(dataset: Dataset[_]): DataFrame =
throw new UnsupportedOperationException(s"transformImpl is not supported in $getClass")

/**
* Predict label for the given features.
* This method is used to implement `transform()` and output [[predictionCol]].
Expand Down
10 changes: 1 addition & 9 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 @@ -34,7 +34,7 @@ import org.apache.spark.ml.util.DefaultParamsReader.Metadata
import org.apache.spark.ml.util.Instrumentation.instrumented
import org.apache.spark.mllib.tree.configuration.{Algo => OldAlgo}
import org.apache.spark.mllib.tree.model.{GradientBoostedTreesModel => OldGBTModel}
import org.apache.spark.sql.{DataFrame, Dataset, Row}
import org.apache.spark.sql.{Dataset, Row}
import org.apache.spark.sql.functions._

/**
Expand Down Expand Up @@ -286,14 +286,6 @@ class GBTClassificationModel private[ml](
@Since("1.4.0")
override def treeWeights: Array[Double] = _treeWeights

override protected def transformImpl(dataset: Dataset[_]): DataFrame = {
val bcastModel = dataset.sparkSession.sparkContext.broadcast(this)
val predictUDF = udf { (features: Any) =>
bcastModel.value.predict(features.asInstanceOf[Vector])
}
dataset.withColumn($(predictionCol), predictUDF(col($(featuresCol))))
}

override def predict(features: Vector): Double = {
// If thresholds defined, use predictRaw to get probabilities, otherwise use optimization
if (isDefined(thresholds)) {
Expand Down
13 changes: 2 additions & 11 deletions 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 @@ -25,7 +25,7 @@ import org.apache.spark.ml.feature.Instance
import org.apache.spark.ml.linalg.{DenseVector, SparseVector, Vector, Vectors}
import org.apache.spark.ml.param.ParamMap
import org.apache.spark.ml.tree._
import org.apache.spark.ml.tree.{RandomForestParams, TreeClassifierParams, TreeEnsembleModel}
import org.apache.spark.ml.tree.{TreeClassifierParams, TreeEnsembleModel}
import org.apache.spark.ml.tree.impl.RandomForest
import org.apache.spark.ml.util._
import org.apache.spark.ml.util.{Identifiable, MetadataUtils}
Expand All @@ -34,8 +34,7 @@ import org.apache.spark.ml.util.Instrumentation.instrumented
import org.apache.spark.mllib.tree.configuration.{Algo => OldAlgo}
import org.apache.spark.mllib.tree.model.{RandomForestModel => OldRandomForestModel}
import org.apache.spark.rdd.RDD
import org.apache.spark.sql.{DataFrame, Dataset}
import org.apache.spark.sql.functions.{col, udf}
import org.apache.spark.sql.Dataset

/**
* <a href="http://en.wikipedia.org/wiki/Random_forest">Random Forest</a> learning algorithm for
Expand Down Expand Up @@ -208,14 +207,6 @@ class RandomForestClassificationModel private[ml] (
@Since("1.4.0")
override def treeWeights: Array[Double] = _treeWeights

override protected def transformImpl(dataset: Dataset[_]): DataFrame = {
val bcastModel = dataset.sparkSession.sparkContext.broadcast(this)
val predictUDF = udf { (features: Any) =>
bcastModel.value.predict(features.asInstanceOf[Vector])
}
dataset.withColumn($(predictionCol), predictUDF(col($(featuresCol))))
}

override protected def predictRaw(features: Vector): Vector = {
// TODO: When we add a generic Bagging class, handle transform there: SPARK-7128
// Classifies using majority votes.
Expand Down