Github user dbtsai commented on a diff in the pull request: https://github.com/apache/spark/pull/8013#discussion_r36719832 --- Diff: mllib/src/test/scala/org/apache/spark/ml/regression/LinearRegressionSuite.scala --- @@ -505,4 +505,455 @@ class LinearRegressionSuite extends SparkFunSuite with MLlibTestSparkContext { .zip(testSummary.residuals.select("residuals").collect()) .forall { case (Row(r1: Double), Row(r2: Double)) => r1 ~== r2 relTol 1E-5 } } + + test("Robust params") { + ParamsSuite.checkParams((new LinearRegression).setRobust(true)) + val model = new LinearRegressionModel("RobustReg", Vectors.dense(0.0), 0.0) + ParamsSuite.checkParams(model) + } + + test("Robust regression: default params") { + val lir = (new LinearRegression).setRobust(true) + assert(lir.getLabelCol === "label") + assert(lir.getFeaturesCol === "features") + assert(lir.getPredictionCol === "prediction") + assert(lir.getRegParam === 0.0) + assert(lir.getElasticNetParam === 0.0) + assert(lir.getFitIntercept) + assert(lir.getStandardization) + val model = lir.fit(dataset) + model.transform(dataset) + .select("label", "prediction") + .collect() + assert(model.getFeaturesCol === "features") + assert(model.getPredictionCol === "prediction") + assert(model.intercept !== 0.0) + assert(model.hasParent) + } + + test("Robust regression with intercept without regularization") { + val trainer1 = (new LinearRegression).setRobust(true) + // The result should be the same regardless of standardization without regularization + val trainer2 = (new LinearRegression).setRobust(true).setStandardization(false) + val model1 = trainer1.fit(dataset) + val model2 = trainer2.fit(dataset) + + /* + Using the following R code to load the data and train the model using glmnet package. + --- End diff -- Why do you test with `GLMNET`? Is it because all the data in this test suite doesn't have outliner? Can you have a test with outliner proving this algorithm works?
--- If your project is set up for it, you can reply to this email and have your reply appear on GitHub as well. If your project does not have this feature enabled and wishes so, or if the feature is enabled but not working, please contact infrastructure at infrastruct...@apache.org or file a JIRA ticket with INFRA. --- --------------------------------------------------------------------- To unsubscribe, e-mail: reviews-unsubscr...@spark.apache.org For additional commands, e-mail: reviews-h...@spark.apache.org