python/mllib/normalizer_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.feature import Normalizer
0023 from pyspark.mllib.util import MLUtils
0024 # $example off$
0025
0026 if __name__ == "__main__":
0027     sc = SparkContext(appName="NormalizerExample")  # SparkContext
0028
0029     # $example on$
0030     data = MLUtils.loadLibSVMFile(sc, "data/mllib/sample_libsvm_data.txt")
0031     labels = data.map(lambda x: x.label)
0032     features = data.map(lambda x: x.features)
0033
0034     normalizer1 = Normalizer()
0035     normalizer2 = Normalizer(p=float("inf"))
0036
0037     # Each sample in data1 will be normalized using $L^2$ norm.
0038     data1 = labels.zip(normalizer1.transform(features))
0039
0040     # Each sample in data2 will be normalized using $L^\infty$ norm.
0041     data2 = labels.zip(normalizer2.transform(features))
0042     # $example off$
0043
0044     print("data1:")
0045     for each in data1.collect():
0046         print(each)
0047
0048     print("data2:")
0049     for each in data2.collect():
0050         print(each)
0051
0052     sc.stop()