blob: ca19c0ccb60c8872a27d16257d93d359960d6ab2 (
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
|
#
# 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.
#
from __future__ import print_function
from pyspark import SparkContext
# $example on$
from pyspark.mllib.clustering import PowerIterationClustering, PowerIterationClusteringModel
# $example off$
if __name__ == "__main__":
sc = SparkContext(appName="PowerIterationClusteringExample") # SparkContext
# $example on$
# Load and parse the data
data = sc.textFile("data/mllib/pic_data.txt")
similarities = data.map(lambda line: tuple([float(x) for x in line.split(' ')]))
# Cluster the data into two classes using PowerIterationClustering
model = PowerIterationClustering.train(similarities, 2, 10)
model.assignments().foreach(lambda x: print(str(x.id) + " -> " + str(x.cluster)))
# Save and load model
model.save(sc, "target/org/apache/spark/PythonPowerIterationClusteringExample/PICModel")
sameModel = PowerIterationClusteringModel\
.load(sc, "target/org/apache/spark/PythonPowerIterationClusteringExample/PICModel")
# $example off$
sc.stop()
|