python/mllib/hypothesis_testing_kolmogorov_smirnov_test_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 # $example on$
0022 from pyspark.mllib.stat import Statistics
0023 # $example off$
0024
0025 if __name__ == "__main__":
0026     sc = SparkContext(appName="HypothesisTestingKolmogorovSmirnovTestExample")
0027
0028     # $example on$
0029     parallelData = sc.parallelize([0.1, 0.15, 0.2, 0.3, 0.25])
0030
0031     # run a KS test for the sample versus a standard normal distribution
0032     testResult = Statistics.kolmogorovSmirnovTest(parallelData, "norm", 0, 1)
0033     # summary of the test including the p-value, test statistic, and null hypothesis
0034     # if our p-value indicates significance, we can reject the null hypothesis
0035     # Note that the Scala functionality of calling Statistics.kolmogorovSmirnovTest with
0036     # a lambda to calculate the CDF is not made available in the Python API
0037     print(testResult)
0038     # $example off$
0039
0040     sc.stop()