python/mllib/hypothesis_testing_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.linalg import Matrices, Vectors
0023 from pyspark.mllib.regression import LabeledPoint
0024 from pyspark.mllib.stat import Statistics
0025 # $example off$
0026
0027 if __name__ == "__main__":
0028     sc = SparkContext(appName="HypothesisTestingExample")
0029
0030     # $example on$
0031     vec = Vectors.dense(0.1, 0.15, 0.2, 0.3, 0.25)  # a vector composed of the frequencies of events
0032
0033     # compute the goodness of fit. If a second vector to test against
0034     # is not supplied as a parameter, the test runs against a uniform distribution.
0035     goodnessOfFitTestResult = Statistics.chiSqTest(vec)
0036
0037     # summary of the test including the p-value, degrees of freedom,
0038     # test statistic, the method used, and the null hypothesis.
0039     print("%s\n" % goodnessOfFitTestResult)
0040
0041     mat = Matrices.dense(3, 2, [1.0, 3.0, 5.0, 2.0, 4.0, 6.0])  # a contingency matrix
0042
0043     # conduct Pearson's independence test on the input contingency matrix
0044     independenceTestResult = Statistics.chiSqTest(mat)
0045
0046     # summary of the test including the p-value, degrees of freedom,
0047     # test statistic, the method used, and the null hypothesis.
0048     print("%s\n" % independenceTestResult)
0049
0050     obs = sc.parallelize(
0051         [LabeledPoint(1.0, [1.0, 0.0, 3.0]),
0052          LabeledPoint(1.0, [1.0, 2.0, 0.0]),
0053          LabeledPoint(1.0, [-1.0, 0.0, -0.5])]
0054     )  # LabeledPoint(label, feature)
0055
0056     # The contingency table is constructed from an RDD of LabeledPoint and used to conduct
0057     # the independence test. Returns an array containing the ChiSquaredTestResult for every feature
0058     # against the label.
0059     featureTestResults = Statistics.chiSqTest(obs)
0060
0061     for i, result in enumerate(featureTestResults):
0062         print("Column %d:\n%s" % (i + 1, result))
0063     # $example off$
0064
0065     sc.stop()