Github user mengxr commented on a diff in the pull request: https://github.com/apache/spark/pull/6992#discussion_r33379191 --- Diff: python/pyspark/mllib/clustering.py --- @@ -272,6 +275,94 @@ def train(cls, rdd, k, convergenceTol=1e-3, maxIterations=100, seed=None, initia return GaussianMixtureModel(weight, mvg_obj) +class PowerIterationClusteringModel(JavaModelWrapper, JavaSaveable, JavaLoader): + + """ + .. note:: Experimental + + Model produced by [[PowerIterationClustering]]. + + >>> data = [(0, 1, 1.0), (0, 2, 1.0), (1, 3, 1.0), (2, 3, 1.0), + ... (0, 3, 1.0), (1, 2, 1.0), (0, 4, 0.1)] + >>> rdd = sc.parallelize(data, 2) + >>> model = PowerIterationClustering.train(rdd, 2, 100) + >>> model.k + 2 + >>> sorted(model.assignments().collect()) + [Assignment(id=0, cluster=1), Assignment(id=1, cluster=0), ... + >>> import os, tempfile + >>> path = tempfile.mkdtemp() + >>> model.save(sc, path) + >>> sameModel = PowerIterationClusteringModel.load(sc, path) + >>> sameModel.k + 2 + >>> sorted(sameModel.assignments().collect()) + [Assignment(id=0, cluster=1), Assignment(id=1, cluster=0), ... + >>> from shutil import rmtree + >>> try: + ... rmtree(path) + ... except OSError: + ... pass + """ + + @property + def k(self): + """ + Returns the number of clusters. + """ + return self.call("k") + + def assignments(self): + """ + Returns the cluster assignments of this model. + """ + return self.call("getAssignments").map( + lambda x: (PowerIterationClustering.Assignment(x[0], x[1]))) --- End diff -- minor: `Assignment(x[0], x[1])` -> `Assignment(*x)`
--- 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