python/mllib/bisecting_k_means_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 from __future__ import print_function
0019
0020 # $example on$
0021 from numpy import array
0022 # $example off$
0023
0024 from pyspark import SparkContext
0025 # $example on$
0026 from pyspark.mllib.clustering import BisectingKMeans
0027 # $example off$
0028
0029 if __name__ == "__main__":
0030     sc = SparkContext(appName="PythonBisectingKMeansExample")  # SparkContext
0031
0032     # $example on$
0033     # Load and parse the data
0034     data = sc.textFile("data/mllib/kmeans_data.txt")
0035     parsedData = data.map(lambda line: array([float(x) for x in line.split(' ')]))
0036
0037     # Build the model (cluster the data)
0038     model = BisectingKMeans.train(parsedData, 2, maxIterations=5)
0039
0040     # Evaluate clustering
0041     cost = model.computeCost(parsedData)
0042     print("Bisecting K-means Cost = " + str(cost))
0043     # $example off$
0044
0045     sc.stop()