Skip to content

[SPARK-18608][ML] Fix double-caching in ML algorithms #17014

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-18608][ML] Fix double-caching in ML algorithms #17014

Show file tree
Hide file tree
Changes from 1 commit
Commits
Show all changes
6 commits
Select commit Hold shift + click to select a range
45adf7e
recreate pr
zhengruifeng Mar 31, 2017
208e100
del unused equation
zhengruifeng Jul 6, 2017
936d466
revert Predictor
zhengruifeng Aug 29, 2017
df4d263
create param HasHandlePersistence
zhengruifeng Sep 4, 2017
971e52c
fix
zhengruifeng Sep 4, 2017
f8fa957
fix mima
zhengruifeng Sep 4, 2017
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
revert Predictor
  • Loading branch information
@zhengruifeng
zhengruifeng committed Sep 4, 2017
commit 936d46634c69a8f0f8a546475edd3bfbd501d1e1
7 changes: 0 additions & 7 deletions mllib/src/main/scala/org/apache/spark/ml/Predictor.scala
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -27,7 +27,6 @@ import org.apache.spark.rdd.RDD
import org.apache.spark.sql.{DataFrame, Dataset, Row}
import org.apache.spark.sql.functions._
import org.apache.spark.sql.types.{DataType, DoubleType, StructType}
import org.apache.spark.storage.StorageLevel

/**
* (private[ml]) Trait for parameters for prediction (regression and classification).
Expand Down Expand Up @@ -86,10 +85,6 @@ abstract class Predictor[
M <: PredictionModel[FeaturesType, M]]
extends Estimator[M] with PredictorParams {

protected[spark] var storageLevel = StorageLevel.NONE

protected def handlePersistence = storageLevel == StorageLevel.NONE

/** @group setParam */
def setLabelCol(value: String): Learner = set(labelCol, value).asInstanceOf[Learner]

Expand All @@ -104,8 +99,6 @@ abstract class Predictor[
// Developers only need to implement train().
transformSchema(dataset.schema, logging = true)

storageLevel = dataset.storageLevel

// Cast LabelCol to DoubleType and keep the metadata.
val labelMeta = dataset.schema($(labelCol)).metadata
val labelCasted = dataset.withColumn($(labelCol), col($(labelCol)).cast(DoubleType), labelMeta)
Expand Down
9 changes: 8 additions & 1 deletion mllib/src/main/scala/org/apache/spark/ml/classification/LogisticRegression.scala
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -483,7 +483,14 @@ class LogisticRegression @Since("1.2.0") (
this
}

protected[spark] def train(dataset: Dataset[_]): LogisticRegressionModel = {
override protected[spark] def train(dataset: Dataset[_]): LogisticRegressionModel = {
val handlePersistence = dataset.storageLevel == StorageLevel.NONE
train(dataset, handlePersistence)
}

protected[spark] def train(
dataset: Dataset[_],
handlePersistence: Boolean): LogisticRegressionModel = {
val w = if (!isDefined(weightCol) || $(weightCol).isEmpty) lit(1.0) else col($(weightCol))
val instances: RDD[Instance] =
dataset.select(col($(labelCol)), w, col($(featuresCol))).rdd.map {
Expand Down
1 change: 1 addition & 0 deletions mllib/src/main/scala/org/apache/spark/ml/regression/LinearRegression.scala
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -251,6 +251,7 @@ class LinearRegression @Since("1.3.0") (@Since("1.3.0") override val uid: String
return lrModel
}

val handlePersistence = dataset.storageLevel == StorageLevel.NONE
if (handlePersistence) instances.persist(StorageLevel.MEMORY_AND_DISK)

val (featuresSummarizer, ySummarizer) = {
Expand Down
4 changes: 3 additions & 1 deletion mllib/src/main/scala/org/apache/spark/mllib/classification/LogisticRegression.scala
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -447,8 +447,10 @@ class LogisticRegressionWithLBFGS
// Convert our input into a DataFrame
val spark = SparkSession.builder().sparkContext(input.context).getOrCreate()
val df = spark.createDataFrame(input.map(_.asML))
// Determine if we should cache the DF
val handlePersistence = input.getStorageLevel == StorageLevel.NONE
// Train our model
val mlLogisticRegressionModel = lr.train(df)
val mlLogisticRegressionModel = lr.train(df, handlePersistence)
// convert the model
val weights = Vectors.dense(mlLogisticRegressionModel.coefficients.toArray)
createModel(weights, mlLogisticRegressionModel.intercept)
Expand Down