blob: 002fc757996488ea0e3ae0fd9de0d74ab231ac94 (
plain) (
blame)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
|
#
# Licensed to the Apache Software Foundation (ASF) under one or more
# contributor license agreements. See the NOTICE file distributed with
# this work for additional information regarding copyright ownership.
# The ASF licenses this file to You under the Apache License, Version 2.0
# (the "License"); you may not use this file except in compliance with
# the License. You may obtain a copy of the License at
#
# http://www.apache.org/licenses/LICENSE-2.0
#
# Unless required by applicable law or agreed to in writing, software
# distributed under the License is distributed on an "AS IS" BASIS,
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
# See the License for the specific language governing permissions and
# limitations under the License.
#
"""
A K-means clustering program using MLlib.
This example requires NumPy (http://www.numpy.org/).
"""
from __future__ import print_function
import sys
import numpy as np
from pyspark import SparkContext
from pyspark.mllib.clustering import KMeans
def parseVector(line):
return np.array([float(x) for x in line.split(' ')])
if __name__ == "__main__":
if len(sys.argv) != 3:
print("Usage: kmeans <file> <k>", file=sys.stderr)
exit(-1)
sc = SparkContext(appName="KMeans")
lines = sc.textFile(sys.argv[1])
data = lines.map(parseVector)
k = int(sys.argv[2])
model = KMeans.train(data, k)
print("Final centers: " + str(model.clusterCenters))
print("Total Cost: " + str(model.computeCost(data)))
sc.stop()
|