Github user yanboliang commented on a diff in the pull request: https://github.com/apache/spark/pull/12402#discussion_r59833733 --- Diff: python/pyspark/ml/clustering.py --- @@ -22,7 +22,151 @@ from pyspark.mllib.common import inherit_doc __all__ = ['BisectingKMeans', 'BisectingKMeansModel', - 'KMeans', 'KMeansModel'] + 'KMeans', 'KMeansModel', 'GaussianMixture', 'GaussianMixtureModel'] + + +class GaussianMixtureModel(JavaModel, JavaMLWritable, JavaMLReadable): + """ + .. note:: Experimental + + Model fitted by GaussianMixtureModel. + + .. versionadded:: 2.0.0 + """ + + @property + @since("2.0.0") + def weights(self): + """ + Weights for each Gaussian distribution in the mixture, where weights[i] is + the weight for Gaussian i, and weights.sum == 1. + """ + return self._call_java("weights") + + @property + @since("2.0.0") + def gaussians(self): + """ + Array of MultivariateGaussian where gaussians[i] represents + the Multivariate Gaussian (Normal) Distribution for Gaussian i. + """ + return self._call_java("gaussians") --- End diff -- Here we should wrapper the return value as ```pyspark.mllib.stat.distribution.MultivariateGaussian```.
--- 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