python/mllib/kernel_density_estimation_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 KernelDensity
0023 # $example off$
0024
0025 if __name__ == "__main__":
0026     sc = SparkContext(appName="KernelDensityEstimationExample")  # SparkContext
0027
0028     # $example on$
0029     # an RDD of sample data
0030     data = sc.parallelize([1.0, 1.0, 1.0, 2.0, 3.0, 4.0, 5.0, 5.0, 6.0, 7.0, 8.0, 9.0, 9.0])
0031
0032     # Construct the density estimator with the sample data and a standard deviation for the Gaussian
0033     # kernels
0034     kd = KernelDensity()
0035     kd.setSample(data)
0036     kd.setBandwidth(3.0)
0037
0038     # Find density estimates for the given values
0039     densities = kd.estimate([-1.0, 2.0, 5.0])
0040     # $example off$
0041
0042     print(densities)
0043
0044     sc.stop()