Github user sethah commented on a diff in the pull request: https://github.com/apache/spark/pull/13557#discussion_r90132505 --- Diff: python/pyspark/ml/clustering.py --- @@ -316,6 +316,36 @@ def computeCost(self, dataset): """ return self._call_java("computeCost", dataset) + @property + @since("2.1.0") + def hasSummary(self): + """ + Indicates whether a training summary exists for this model instance. + """ + return self._call_java("hasSummary") + + @property + @since("2.1.0") + def summary(self): + """ + Gets summary (e.g. cluster assignments, cluster sizes) of the model trained on the + training set. An exception is thrown if no summary exists. + """ + if self.hasSummary: + return KMeansSummary(self._call_java("summary")) + else: + raise RuntimeError("No training summary available for this %s" % + self.__class__.__name__) + + +class KMeansSummary(ClusteringSummary): + """ + Summary of KMeans. --- End diff -- add `.. note:: Experimental`
--- 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