Skip to content

[SPARK-20183][ML] Added outlierRatio arg to MLTestingUtils.testOutliersWithSmallWeights #17501

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
jkbradley wants to merge 1 commit into from
Closed

[SPARK-20183][ML] Added outlierRatio arg to MLTestingUtils.testOutliersWithSmallWeights #17501

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
Added outlierRatio arg to MLTestingUtils.testOutliersWithSmallWeights
  • Loading branch information
@jkbradley
jkbradley committed Apr 1, 2017
commit 390233aa2719956832e7ae6253fabef2c8bd6953
2 changes: 1 addition & 1 deletion mllib/src/test/scala/org/apache/spark/ml/classification/LinearSVCSuite.scala
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -164,7 +164,7 @@ class LinearSVCSuite extends SparkFunSuite with MLlibTestSparkContext with Defau
MLTestingUtils.testArbitrarilyScaledWeights[LinearSVCModel, LinearSVC](
dataset.as[LabeledPoint], estimator, modelEquals)
MLTestingUtils.testOutliersWithSmallWeights[LinearSVCModel, LinearSVC](
dataset.as[LabeledPoint], estimator, 2, modelEquals)
dataset.as[LabeledPoint], estimator, 2, modelEquals, outlierRatio = 3)
MLTestingUtils.testOversamplingVsWeighting[LinearSVCModel, LinearSVC](
dataset.as[LabeledPoint], estimator, modelEquals, 42L)
}
Expand Down
2 changes: 1 addition & 1 deletion mllib/src/test/scala/org/apache/spark/ml/classification/LogisticRegressionSuite.scala
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -1874,7 +1874,7 @@ class LogisticRegressionSuite
MLTestingUtils.testArbitrarilyScaledWeights[LogisticRegressionModel, LogisticRegression](
dataset.as[LabeledPoint], estimator, modelEquals)
MLTestingUtils.testOutliersWithSmallWeights[LogisticRegressionModel, LogisticRegression](
dataset.as[LabeledPoint], estimator, numClasses, modelEquals)
dataset.as[LabeledPoint], estimator, numClasses, modelEquals, outlierRatio = 3)
MLTestingUtils.testOversamplingVsWeighting[LogisticRegressionModel, LogisticRegression](
dataset.as[LabeledPoint], estimator, modelEquals, seed)
}
Expand Down
2 changes: 1 addition & 1 deletion mllib/src/test/scala/org/apache/spark/ml/classification/NaiveBayesSuite.scala
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -178,7 +178,7 @@ class NaiveBayesSuite extends SparkFunSuite with MLlibTestSparkContext with Defa
MLTestingUtils.testArbitrarilyScaledWeights[NaiveBayesModel, NaiveBayes](
dataset.as[LabeledPoint], estimatorNoSmoothing, modelEquals)
MLTestingUtils.testOutliersWithSmallWeights[NaiveBayesModel, NaiveBayes](
dataset.as[LabeledPoint], estimatorWithSmoothing, numClasses, modelEquals)
dataset.as[LabeledPoint], estimatorWithSmoothing, numClasses, modelEquals, outlierRatio = 3)
MLTestingUtils.testOversamplingVsWeighting[NaiveBayesModel, NaiveBayes](
dataset.as[LabeledPoint], estimatorWithSmoothing, modelEquals, seed)
}
Expand Down
3 changes: 2 additions & 1 deletion mllib/src/test/scala/org/apache/spark/ml/regression/LinearRegressionSuite.scala
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -842,7 +842,8 @@ class LinearRegressionSuite
MLTestingUtils.testArbitrarilyScaledWeights[LinearRegressionModel, LinearRegression](
datasetWithStrongNoise.as[LabeledPoint], estimator, modelEquals)
MLTestingUtils.testOutliersWithSmallWeights[LinearRegressionModel, LinearRegression](
datasetWithStrongNoise.as[LabeledPoint], estimator, numClasses, modelEquals)
datasetWithStrongNoise.as[LabeledPoint], estimator, numClasses, modelEquals,
outlierRatio = 3)
MLTestingUtils.testOversamplingVsWeighting[LinearRegressionModel, LinearRegression](
datasetWithStrongNoise.as[LabeledPoint], estimator, modelEquals, seed)
}
Expand Down
5 changes: 3 additions & 2 deletions mllib/src/test/scala/org/apache/spark/ml/util/MLTestingUtils.scala
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -260,12 +260,13 @@ object MLTestingUtils extends SparkFunSuite {
data: Dataset[LabeledPoint],
estimator: E with HasWeightCol,
numClasses: Int,
modelEquals: (M, M) => Unit): Unit = {
modelEquals: (M, M) => Unit,
outlierRatio: Int): Unit = {
import data.sqlContext.implicits._
val outlierDS = data.withColumn("weight", lit(1.0)).as[Instance].flatMap {
case Instance(l, w, f) =>
val outlierLabel = if (numClasses == 0) -l else numClasses - l - 1
List.fill(3)(Instance(outlierLabel, 0.0001, f)) ++ List(Instance(l, w, f))
List.fill(outlierRatio)(Instance(outlierLabel, 0.0001, f)) ++ List(Instance(l, w, f))
}
val trueModel = estimator.set(estimator.weightCol, "").fit(data)
val outlierModel = estimator.set(estimator.weightCol, "weight").fit(outlierDS)
Expand Down