diff options
author | Xiangrui Meng <meng@databricks.com> | 2016-03-21 17:42:30 -0700 |
---|---|---|
committer | Xiangrui Meng <meng@databricks.com> | 2016-03-21 17:42:30 -0700 |
commit | 43ef1e52bfe359f0f051a607a8dc77cc3b269508 (patch) | |
tree | 8b03ce50a036b684c8cb5fe0c92dc2dfa350ab90 /examples/src/main/python/mllib/hypothesis_testing_example.py | |
parent | 3f49e0766f3a369a44e14632de68c657773b7a27 (diff) | |
download | spark-43ef1e52bfe359f0f051a607a8dc77cc3b269508.tar.gz spark-43ef1e52bfe359f0f051a607a8dc77cc3b269508.tar.bz2 spark-43ef1e52bfe359f0f051a607a8dc77cc3b269508.zip |
Revert "[SPARK-13019][DOCS] Replace example code in mllib-statistics.md using include_example"
This reverts commit 1af8de200c4d3357bcb09e7bbc6deece00e885f2.
Diffstat (limited to 'examples/src/main/python/mllib/hypothesis_testing_example.py')
-rw-r--r-- | examples/src/main/python/mllib/hypothesis_testing_example.py | 65 |
1 files changed, 0 insertions, 65 deletions
diff --git a/examples/src/main/python/mllib/hypothesis_testing_example.py b/examples/src/main/python/mllib/hypothesis_testing_example.py deleted file mode 100644 index e566ead0d3..0000000000 --- a/examples/src/main/python/mllib/hypothesis_testing_example.py +++ /dev/null @@ -1,65 +0,0 @@ -# -# 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.linalg import Matrices, Vectors -from pyspark.mllib.regression import LabeledPoint -from pyspark.mllib.stat import Statistics -# $example off$ - -if __name__ == "__main__": - sc = SparkContext(appName="HypothesisTestingExample") - - # $example on$ - vec = Vectors.dense(0.1, 0.15, 0.2, 0.3, 0.25) # a vector composed of the frequencies of events - - # compute the goodness of fit. If a second vector to test against - # is not supplied as a parameter, the test runs against a uniform distribution. - goodnessOfFitTestResult = Statistics.chiSqTest(vec) - - # summary of the test including the p-value, degrees of freedom, - # test statistic, the method used, and the null hypothesis. - print("%s\n" % goodnessOfFitTestResult) - - mat = Matrices.dense(3, 2, [1.0, 3.0, 5.0, 2.0, 4.0, 6.0]) # a contingency matrix - - # conduct Pearson's independence test on the input contingency matrix - independenceTestResult = Statistics.chiSqTest(mat) - - # summary of the test including the p-value, degrees of freedom, - # test statistic, the method used, and the null hypothesis. - print("%s\n" % independenceTestResult) - - obs = sc.parallelize( - [LabeledPoint(1.0, [1.0, 0.0, 3.0]), - LabeledPoint(1.0, [1.0, 2.0, 0.0]), - LabeledPoint(1.0, [-1.0, 0.0, -0.5])] - ) # LabeledPoint(feature, label) - - # The contingency table is constructed from an RDD of LabeledPoint and used to conduct - # the independence test. Returns an array containing the ChiSquaredTestResult for every feature - # against the label. - featureTestResults = Statistics.chiSqTest(obs) - - for i, result in enumerate(featureTestResults): - print("Column %d:\n%s" % (i + 1, result)) - # $example off$ - - sc.stop() |