1#
2# Licensed to the Apache Software Foundation (ASF) under one or more
3# contributor license agreements.  See the NOTICE file distributed with
4# this work for additional information regarding copyright ownership.
5# The ASF licenses this file to You under the Apache License, Version 2.0
6# (the "License"); you may not use this file except in compliance with
7# the License.  You may obtain a copy of the License at
8#
9#    http://www.apache.org/licenses/LICENSE-2.0
10#
11# Unless required by applicable law or agreed to in writing, software
12# distributed under the License is distributed on an "AS IS" BASIS,
13# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
14# See the License for the specific language governing permissions and
15# limitations under the License.
16#
17
18"""
19A K-means clustering program using MLlib.
20
21This example requires NumPy (http://www.numpy.org/).
22"""
23from __future__ import print_function
24
25import sys
26
27import numpy as np
28from pyspark import SparkContext
29from pyspark.mllib.clustering import KMeans
30
31
32def parseVector(line):
33    return np.array([float(x) for x in line.split(' ')])
34
35
36if __name__ == "__main__":
37    if len(sys.argv) != 3:
38        print("Usage: kmeans <file> <k>", file=sys.stderr)
39        exit(-1)
40    sc = SparkContext(appName="KMeans")
41    lines = sc.textFile(sys.argv[1])
42    data = lines.map(parseVector)
43    k = int(sys.argv[2])
44    model = KMeans.train(data, k)
45    print("Final centers: " + str(model.clusterCenters))
46    print("Total Cost: " + str(model.computeCost(data)))
47    sc.stop()
48