[ https://issues.apache.org/jira/browse/SPARK-19144?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=15813971#comment-15813971 ]
Yanbo Liang commented on SPARK-19144: ------------------------------------- cc [~sethah] > Add test for GaussianMixture with distributed decompositions > ------------------------------------------------------------ > > Key: SPARK-19144 > URL: https://issues.apache.org/jira/browse/SPARK-19144 > Project: Spark > Issue Type: Test > Components: ML > Reporter: Yanbo Liang > Priority: Minor > > {code} > test("check distributed decomposition") { > val k = 5 > val d = decompositionData.head.size > assert(GaussianMixture.shouldDistributeGaussians(k, d)) > val gmm = new > GaussianMixture().setK(k).setSeed(seed).fit(decompositionDataset) > assert(gmm.getK === k) > } > {code} > In ML {{GaussianMixtureSuite}}, the above test only check that when we > distribute the computation that it produces a model, but does not check that > it produces a correct model. > It should have, but depends on {{GaussianMixture}} can be set with > initialModel (SPARK-15785), otherwise, this algorithm seems incapable of > learning even this very contrived example. After that was resolved, we can > add a correctness test in the above case. -- This message was sent by Atlassian JIRA (v6.3.4#6332) --------------------------------------------------------------------- To unsubscribe, e-mail: issues-unsubscr...@spark.apache.org For additional commands, e-mail: issues-h...@spark.apache.org