Skip to content

[SPARK-27621][ML] Linear Regression - validate training related params such as loss only during fitting phase #24509

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
wants to merge 2 commits into from
Closed

[SPARK-27621][ML] Linear Regression - validate training related params such as loss only during fitting phase #24509

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
5907806
only check training specific params when validateAndTransformSchema i…
May 1, 2019
dfcd014
add unit test for changes to change training related params like loss…
May 1, 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
13 changes: 7 additions & 6 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 @@ -109,12 +109,13 @@ private[regression] trait LinearRegressionParams extends PredictorParams
schema: StructType,
fitting: Boolean,
featuresDataType: DataType): StructType = {
if ($(loss) == Huber) {
require($(solver)!= Normal, "LinearRegression with huber loss doesn't support " +
"normal solver, please change solver to auto or l-bfgs.")
require($(elasticNetParam) == 0.0, "LinearRegression with huber loss only supports " +
s"L2 regularization, but got elasticNetParam = $getElasticNetParam.")

if (fitting) {
if ($(loss) == Huber) {
require($(solver)!= Normal, "LinearRegression with huber loss doesn't support " +
"normal solver, please change solver to auto or l-bfgs.")
require($(elasticNetParam) == 0.0, "LinearRegression with huber loss only supports " +
s"L2 regularization, but got elasticNetParam = $getElasticNetParam.")
}
}
super.validateAndTransformSchema(schema, fitting, featuresDataType)
}
Expand Down
12 changes: 12 additions & 0 deletions 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 @@ -187,6 +187,18 @@ class LinearRegressionSuite extends MLTest with DefaultReadWriteTest with PMMLRe
assert(model.numFeatures === numFeatures)
}

test("linear regression: can transform data with LinearRegressionModel") {
withClue("training related params like loss are only validated during fitting phase") {
val original = new LinearRegression().fit(datasetWithDenseFeature)

val deserialized = new LinearRegressionModel(uid = original.uid,
coefficients = original.coefficients,
intercept = original.intercept)
val output = deserialized.transform(datasetWithDenseFeature)
assert(output.collect().size > 0) // simple assertion to ensure no exception thrown
}
}

test("linear regression: illegal params") {
withClue("LinearRegression with huber loss only supports L2 regularization") {
intercept[IllegalArgumentException] {
Expand Down