|
||||
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 from __future__ import print_function 0019 0020 from pyspark import SparkContext 0021 # $example on$ 0022 from pyspark.mllib.clustering import PowerIterationClustering, PowerIterationClusteringModel 0023 # $example off$ 0024 0025 if __name__ == "__main__": 0026 sc = SparkContext(appName="PowerIterationClusteringExample") # SparkContext 0027 0028 # $example on$ 0029 # Load and parse the data 0030 data = sc.textFile("data/mllib/pic_data.txt") 0031 similarities = data.map(lambda line: tuple([float(x) for x in line.split(' ')])) 0032 0033 # Cluster the data into two classes using PowerIterationClustering 0034 model = PowerIterationClustering.train(similarities, 2, 10) 0035 0036 model.assignments().foreach(lambda x: print(str(x.id) + " -> " + str(x.cluster))) 0037 0038 # Save and load model 0039 model.save(sc, "target/org/apache/spark/PythonPowerIterationClusteringExample/PICModel") 0040 sameModel = PowerIterationClusteringModel\ 0041 .load(sc, "target/org/apache/spark/PythonPowerIterationClusteringExample/PICModel") 0042 # $example off$ 0043 0044 sc.stop()
[ Source navigation ] | [ Diff markup ] | [ Identifier search ] | [ general search ] |
This page was automatically generated by the 2.1.0 LXR engine. The LXR team |