python/mllib/summary_statistics_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 import numpy as np
0023
0024 from pyspark.mllib.stat import Statistics
0025 # $example off$
0026
0027 if __name__ == "__main__":
0028     sc = SparkContext(appName="SummaryStatisticsExample")  # SparkContext
0029
0030     # $example on$
0031     mat = sc.parallelize(
0032         [np.array([1.0, 10.0, 100.0]), np.array([2.0, 20.0, 200.0]), np.array([3.0, 30.0, 300.0])]
0033     )  # an RDD of Vectors
0034
0035     # Compute column summary statistics.
0036     summary = Statistics.colStats(mat)
0037     print(summary.mean())  # a dense vector containing the mean value for each column
0038     print(summary.variance())  # column-wise variance
0039     print(summary.numNonzeros())  # number of nonzeros in each column
0040     # $example off$
0041
0042     sc.stop()