Skip to content

[SPARK-30398][ML] PCA/RegressionMetrics/RowMatrix avoid unnecessary computation #27059

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 3 commits into from
Closed

[SPARK-30398][ML] PCA/RegressionMetrics/RowMatrix avoid unnecessary computation #27059

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
3 commits
Select commit Hold shift + click to select a range
a5bbf16
init
zhengruifeng Dec 31, 2019
a675881
minimiaze import of ml
zhengruifeng Jan 2, 2020
359a911
move SummarizerBuffer outside of SummaryBuilderImpl
zhengruifeng Jan 2, 2020
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
4 changes: 2 additions & 2 deletions mllib/src/main/scala/org/apache/spark/ml/classification/LinearSVC.scala
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -32,7 +32,7 @@ import org.apache.spark.ml.optim.aggregator.HingeAggregator
import org.apache.spark.ml.optim.loss.{L2Regularization, RDDLossFunction}
import org.apache.spark.ml.param._
import org.apache.spark.ml.param.shared._
import org.apache.spark.ml.stat.SummaryBuilderImpl._
import org.apache.spark.ml.stat._
import org.apache.spark.ml.util._
import org.apache.spark.ml.util.Instrumentation.instrumented
import org.apache.spark.sql.{Dataset, Row}
Expand Down Expand Up @@ -170,7 +170,7 @@ class LinearSVC @Since("2.2.0") (
regParam, maxIter, fitIntercept, tol, standardization, threshold, aggregationDepth)

val (summarizer, labelSummarizer) = instances.treeAggregate(
(createSummarizerBuffer("mean", "std", "count"), new MultiClassSummarizer))(
(Summarizer.createSummarizerBuffer("mean", "std", "count"), new MultiClassSummarizer))(
seqOp = (c: (SummarizerBuffer, MultiClassSummarizer), instance: Instance) =>
(c._1.add(instance.features, instance.weight), c._2.add(instance.label, instance.weight)),
combOp = (c1: (SummarizerBuffer, MultiClassSummarizer),
Expand Down
4 changes: 2 additions & 2 deletions 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 @@ -34,7 +34,7 @@ import org.apache.spark.ml.optim.aggregator.LogisticAggregator
import org.apache.spark.ml.optim.loss.{L2Regularization, RDDLossFunction}
import org.apache.spark.ml.param._
import org.apache.spark.ml.param.shared._
import org.apache.spark.ml.stat.SummaryBuilderImpl._
import org.apache.spark.ml.stat._
import org.apache.spark.ml.util._
import org.apache.spark.ml.util.Instrumentation.instrumented
import org.apache.spark.mllib.evaluation.{BinaryClassificationMetrics, MulticlassMetrics}
Expand Down Expand Up @@ -501,7 +501,7 @@ class LogisticRegression @Since("1.2.0") (
fitIntercept)

val (summarizer, labelSummarizer) = instances.treeAggregate(
(createSummarizerBuffer("mean", "std", "count"), new MultiClassSummarizer))(
(Summarizer.createSummarizerBuffer("mean", "std", "count"), new MultiClassSummarizer))(
seqOp = (c: (SummarizerBuffer, MultiClassSummarizer), instance: Instance) =>
(c._1.add(instance.features, instance.weight), c._2.add(instance.label, instance.weight)),
combOp = (c1: (SummarizerBuffer, MultiClassSummarizer),
Expand Down
4 changes: 2 additions & 2 deletions mllib/src/main/scala/org/apache/spark/ml/regression/AFTSurvivalRegression.scala
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -31,7 +31,7 @@ import org.apache.spark.ml.{Estimator, Model}
import org.apache.spark.ml.linalg.{BLAS, Vector, Vectors, VectorUDT}
import org.apache.spark.ml.param._
import org.apache.spark.ml.param.shared._
import org.apache.spark.ml.stat.SummaryBuilderImpl._
import org.apache.spark.ml.stat._
import org.apache.spark.ml.util._
import org.apache.spark.ml.util.Instrumentation.instrumented
import org.apache.spark.mllib.util.MLUtils
Expand Down Expand Up @@ -215,7 +215,7 @@ class AFTSurvivalRegression @Since("1.6.0") (@Since("1.6.0") override val uid: S
if (handlePersistence) instances.persist(StorageLevel.MEMORY_AND_DISK)

val featuresSummarizer = instances.treeAggregate(
createSummarizerBuffer("mean", "std", "count"))(
Summarizer.createSummarizerBuffer("mean", "std", "count"))(
seqOp = (c: SummarizerBuffer, v: AFTPoint) => c.add(v.features),
combOp = (c1: SummarizerBuffer, c2: SummarizerBuffer) => c1.merge(c2),
depth = $(aggregationDepth)
Expand Down
6 changes: 3 additions & 3 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 @@ -36,7 +36,7 @@ import org.apache.spark.ml.optim.aggregator.{HuberAggregator, LeastSquaresAggreg
import org.apache.spark.ml.optim.loss.{L2Regularization, RDDLossFunction}
import org.apache.spark.ml.param.{DoubleParam, Param, ParamMap, ParamValidators}
import org.apache.spark.ml.param.shared._
import org.apache.spark.ml.stat.SummaryBuilderImpl._
import org.apache.spark.ml.stat._
import org.apache.spark.ml.util._
import org.apache.spark.ml.util.Instrumentation.instrumented
import org.apache.spark.mllib.evaluation.RegressionMetrics
Expand Down Expand Up @@ -358,8 +358,8 @@ class LinearRegression @Since("1.3.0") (@Since("1.3.0") override val uid: String
if (handlePersistence) instances.persist(StorageLevel.MEMORY_AND_DISK)

val (featuresSummarizer, ySummarizer) = instances.treeAggregate(
(createSummarizerBuffer("mean", "std"),
createSummarizerBuffer("mean", "std", "count")))(
(Summarizer.createSummarizerBuffer("mean", "std"),
Summarizer.createSummarizerBuffer("mean", "std", "count")))(
seqOp = (c: (SummarizerBuffer, SummarizerBuffer), instance: Instance) =>
(c._1.add(instance.features, instance.weight),
c._2.add(Vectors.dense(instance.label), instance.weight)),
Expand Down
Loading