python/ml/chi_square_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 """
0019 An example for Chi-square hypothesis testing.
0020 Run with:
0021   bin/spark-submit examples/src/main/python/ml/chi_square_test_example.py
0022 """
0023 from __future__ import print_function
0024
0025 from pyspark.sql import SparkSession
0026 # $example on$
0027 from pyspark.ml.linalg import Vectors
0028 from pyspark.ml.stat import ChiSquareTest
0029 # $example off$
0030
0031 if __name__ == "__main__":
0032     spark = SparkSession \
0033         .builder \
0034         .appName("ChiSquareTestExample") \
0035         .getOrCreate()
0036
0037     # $example on$
0038     data = [(0.0, Vectors.dense(0.5, 10.0)),
0039             (0.0, Vectors.dense(1.5, 20.0)),
0040             (1.0, Vectors.dense(1.5, 30.0)),
0041             (0.0, Vectors.dense(3.5, 30.0)),
0042             (0.0, Vectors.dense(3.5, 40.0)),
0043             (1.0, Vectors.dense(3.5, 40.0))]
0044     df = spark.createDataFrame(data, ["label", "features"])
0045
0046     r = ChiSquareTest.test(df, "features", "label").head()
0047     print("pValues: " + str(r.pValues))
0048     print("degreesOfFreedom: " + str(r.degreesOfFreedom))
0049     print("statistics: " + str(r.statistics))
0050     # $example off$
0051
0052     spark.stop()