Github user mengxr commented on a diff in the pull request: https://github.com/apache/spark/pull/4986#discussion_r26355062 --- Diff: mllib/src/test/scala/org/apache/spark/mllib/clustering/GaussianMixtureSuite.scala --- @@ -138,4 +126,36 @@ class GaussianMixtureSuite extends FunSuite with MLlibTestSparkContext { assert(sparseGMM.gaussians(0).sigma ~== Esigma(0) absTol 1E-3) assert(sparseGMM.gaussians(1).sigma ~== Esigma(1) absTol 1E-3) } + + test("model save / load") { + val data = GaussianTestData.data + + val gmm = new GaussianMixture().setK(2).setSeed(0).run(data) + val tempDir = Utils.createTempDir() + val path = tempDir.toURI.toString + + try { + gmm.save(sc, path) + val sameModel = GaussianMixtureModel.load(sc, path) + assert(sameModel.k === gmm.k) + (0 until sameModel.k).foreach { i => + assert(sameModel.gaussians(i).mu === gmm.gaussians(i).mu) + assert(sameModel.gaussians(i).sigma === gmm.gaussians(i).sigma) + } + } finally { + Utils.deleteRecursively(tempDir) + } + } + + object GaussianTestData { + + val data = sc.parallelize(Array( --- End diff -- `sc` is initialized when `test` is called. But there is no guarantee from the API about when `data` is called. `GaussianTestData` may not be necessary. Use `lazy val data = ...` directly.
--- 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