Skip to content

[SPARK-58471][ML][CONNECT] Improve TrainValidationSplitModel size estimation #57674

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

Draft
zhengruifeng wants to merge 1 commit into
base: master
Choose a base branch
from
+39 −1
Draft

[SPARK-58471][ML][CONNECT] Improve TrainValidationSplitModel size estimation #57674

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
25 changes: 24 additions & 1 deletion mllib/src/main/scala/org/apache/spark/ml/tuning/TrainValidationSplit.scala
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -38,8 +38,8 @@ import org.apache.spark.ml.util._
import org.apache.spark.ml.util.Instrumentation.instrumented
import org.apache.spark.sql.{DataFrame, Dataset}
import org.apache.spark.sql.types.StructType
import org.apache.spark.util.{SizeEstimator, ThreadUtils}
import org.apache.spark.util.ArrayImplicits._
import org.apache.spark.util.ThreadUtils

/**
* Params for [[TrainValidationSplit]] and [[TrainValidationSplitModel]].
Expand Down Expand Up @@ -293,6 +293,29 @@ class TrainValidationSplitModel private[ml] (
@Since("2.3.0")
def hasSubModels: Boolean = _subModels.isDefined

private[spark] override def estimatedSize: Long = {
var size = estimateMatadataSize(excluded = Seq(
// estimator: Param[Estimator[_]]
estimator,
// estimatorParamMaps: Param[Array[ParamMap]]
estimatorParamMaps,
// evaluator: Param[Evaluator]
evaluator))
// bestModel: Model[_]
size += bestModel.estimatedSize
// validationMetrics: Array[Double]
size += SizeEstimator.estimate(validationMetrics)
// _subModels: Option[Array[Model[_]]]
_subModels.foreach { modelArray =>
modelArray.foreach { model =>
if (model != null) {
size += model.estimatedSize
}
}
}
size
}

@Since("2.0.0")
override def transform(dataset: Dataset[_]): DataFrame = {
transformSchema(dataset.schema, logging = true)
Expand Down
15 changes: 15 additions & 0 deletions mllib/src/test/scala/org/apache/spark/ml/tuning/TrainValidationSplitSuite.scala
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -73,6 +73,21 @@ class TrainValidationSplitSuite
}
}

test("TrainValidationSplitModel estimated size") {
val estimator = new LogisticRegression().setMaxIter(1)
// Initialize the estimator's logger before retaining it in the TrainValidationSplitModel.
estimator.fit(dataset)
val model = new TrainValidationSplit()
.setEstimator(estimator)
.setEstimatorParamMaps(Array(ParamMap.empty))
.setEvaluator(new BinaryClassificationEvaluator())
.fit(dataset)

val maxSize = 16 * 1024
assert(model.estimatedSize < maxSize,
s"Estimation (${model.estimatedSize}) should not include shared runtime state")
}

test("train validation with linear regression") {
val dataset = sc.parallelize(
LinearDataGenerator.generateLinearInput(
Expand Down