python/ml/power_iteration_clustering_example.py

0001 #
0002 # Licensed to the Apache Software Foundation (ASF) under one or more
0003 # contributor license agreements.  See the NOTICE file distributed with
0004 # this work for additional information regarding copyright ownership.
0005 # The ASF licenses this file to You under the Apache License, Version 2.0
0006 # (the "License"); you may not use this file except in compliance with
0007 # the License.  You may obtain a copy of the License at
0008 #
0009 #    http://www.apache.org/licenses/LICENSE-2.0
0010 #
0011 # Unless required by applicable law or agreed to in writing, software
0012 # distributed under the License is distributed on an "AS IS" BASIS,
0013 # WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
0014 # See the License for the specific language governing permissions and
0015 # limitations under the License.
0016 #
0017
0018 """
0019 An example demonstrating PowerIterationClustering.
0020 Run with:
0021   bin/spark-submit examples/src/main/python/ml/power_iteration_clustering_example.py
0022 """
0023 # $example on$
0024 from pyspark.ml.clustering import PowerIterationClustering
0025 # $example off$
0026 from pyspark.sql import SparkSession
0027
0028 if __name__ == "__main__":
0029     spark = SparkSession\
0030         .builder\
0031         .appName("PowerIterationClusteringExample")\
0032         .getOrCreate()
0033
0034     # $example on$
0035     df = spark.createDataFrame([
0036         (0, 1, 1.0),
0037         (0, 2, 1.0),
0038         (1, 2, 1.0),
0039         (3, 4, 1.0),
0040         (4, 0, 0.1)
0041     ], ["src", "dst", "weight"])
0042
0043     pic = PowerIterationClustering(k=2, maxIter=20, initMode="degree", weightCol="weight")
0044
0045     # Shows the cluster assignment
0046     pic.assignClusters(df).show()
0047     # $example off$
0048
0049     spark.stop()