python/mllib/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 from math import sqrt
0023 # $example off$
0024
0025 from pyspark import SparkContext
0026 # $example on$
0027 from pyspark.mllib.clustering import KMeans, KMeansModel
0028 # $example off$
0029
0030 if __name__ == "__main__":
0031     sc = SparkContext(appName="KMeansExample")  # SparkContext
0032
0033     # $example on$
0034     # Load and parse the data
0035     data = sc.textFile("data/mllib/kmeans_data.txt")
0036     parsedData = data.map(lambda line: array([float(x) for x in line.split(' ')]))
0037
0038     # Build the model (cluster the data)
0039     clusters = KMeans.train(parsedData, 2, maxIterations=10, initializationMode="random")
0040
0041     # Evaluate clustering by computing Within Set Sum of Squared Errors
0042     def error(point):
0043         center = clusters.centers[clusters.predict(point)]
0044         return sqrt(sum([x**2 for x in (point - center)]))
0045
0046     WSSSE = parsedData.map(lambda point: error(point)).reduce(lambda x, y: x + y)
0047     print("Within Set Sum of Squared Error = " + str(WSSSE))
0048
0049     # Save and load model
0050     clusters.save(sc, "target/org/apache/spark/PythonKMeansExample/KMeansModel")
0051     sameModel = KMeansModel.load(sc, "target/org/apache/spark/PythonKMeansExample/KMeansModel")
0052     # $example off$
0053
0054     sc.stop()