python/mllib/kmeans.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 A K-means clustering program using MLlib.
0020
0021 This example requires NumPy (http://www.numpy.org/).
0022 """
0023 from __future__ import print_function
0024
0025 import sys
0026
0027 import numpy as np
0028 from pyspark import SparkContext
0029 from pyspark.mllib.clustering import KMeans
0030
0031
0032 def parseVector(line):
0033     return np.array([float(x) for x in line.split(' ')])
0034
0035
0036 if __name__ == "__main__":
0037     if len(sys.argv) != 3:
0038         print("Usage: kmeans <file> <k>", file=sys.stderr)
0039         sys.exit(-1)
0040     sc = SparkContext(appName="KMeans")
0041     lines = sc.textFile(sys.argv[1])
0042     data = lines.map(parseVector)
0043     k = int(sys.argv[2])
0044     model = KMeans.train(data, k)
0045     print("Final centers: " + str(model.clusterCenters))
0046     print("Total Cost: " + str(model.computeCost(data)))
0047     sc.stop()