python/mllib/stratified_sampling_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 from pyspark import SparkContext
0021
0022 if __name__ == "__main__":
0023     sc = SparkContext(appName="StratifiedSamplingExample")  # SparkContext
0024
0025     # $example on$
0026     # an RDD of any key value pairs
0027     data = sc.parallelize([(1, 'a'), (1, 'b'), (2, 'c'), (2, 'd'), (2, 'e'), (3, 'f')])
0028
0029     # specify the exact fraction desired from each key as a dictionary
0030     fractions = {1: 0.1, 2: 0.6, 3: 0.3}
0031
0032     approxSample = data.sampleByKey(False, fractions)
0033     # $example off$
0034
0035     for each in approxSample.collect():
0036         print(each)
0037
0038     sc.stop()