python/mllib/standard_scaler_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 StandardScaler
0023 from pyspark.mllib.linalg import Vectors
0024 from pyspark.mllib.util import MLUtils
0025 # $example off$
0026
0027 if __name__ == "__main__":
0028     sc = SparkContext(appName="StandardScalerExample")  # SparkContext
0029
0030     # $example on$
0031     data = MLUtils.loadLibSVMFile(sc, "data/mllib/sample_libsvm_data.txt")
0032     label = data.map(lambda x: x.label)
0033     features = data.map(lambda x: x.features)
0034
0035     scaler1 = StandardScaler().fit(features)
0036     scaler2 = StandardScaler(withMean=True, withStd=True).fit(features)
0037
0038     # data1 will be unit variance.
0039     data1 = label.zip(scaler1.transform(features))
0040
0041     # data2 will be unit variance and zero mean.
0042     data2 = label.zip(scaler2.transform(features.map(lambda x: Vectors.dense(x.toArray()))))
0043     # $example off$
0044
0045     print("data1:")
0046     for each in data1.collect():
0047         print(each)
0048
0049     print("data2:")
0050     for each in data2.collect():
0051         print(each)
0052
0053     sc.stop()