Github user dbtsai commented on a diff in the pull request: https://github.com/apache/spark/pull/10702#discussion_r51064615 --- Diff: mllib/src/test/scala/org/apache/spark/ml/regression/LinearRegressionSuite.scala --- @@ -558,6 +575,47 @@ class LinearRegressionSuite } } + test("linear regression model with constant label") { + /* + R code: + for (formula in c(b.const ~ . -1, b.const ~ .)) { + model <- lm(formula, data=df.const.label, weights=w) + print(as.vector(coef(model))) + } + [1] -9.221298 3.394343 + [1] 17 0 0 + */ + val expected = Seq( + Vectors.dense(0.0, -9.221298, 3.394343), + Vectors.dense(17.0, 0.0, 0.0)) + + Seq("auto", "l-bfgs", "normal").foreach { solver => + var idx = 0 + for (fitIntercept <- Seq(false, true)) { + val model = new LinearRegression() + .setFitIntercept(fitIntercept) + .setWeightCol("weight") + .setSolver(solver) + .fit(datasetWithWeightConstantLabel) + val actual = Vectors.dense(model.intercept, model.coefficients(0), model.coefficients(1)) + assert(actual ~== expected(idx) absTol 1e-4) + idx += 1 + } + } + } + + test("regularized linear regression through origin with constant label") { + // The problem is ill-defined if fitIntercept=false, regParam is non-zero and \ + // standardization=true. An exception is thrown in this case. --- End diff -- When `standardization=false`, the problem is still ill-defined since GLMNET always standardizes the labels. That's why you see it in the analytical solution. Let's throw exception when `fitIntercept=false` and `regParam != 0.0`.
--- 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