|
||||
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.sql import SparkSession 0021 # $example on$ 0022 from pyspark.ml.feature import Binarizer 0023 # $example off$ 0024 0025 if __name__ == "__main__": 0026 spark = SparkSession\ 0027 .builder\ 0028 .appName("BinarizerExample")\ 0029 .getOrCreate() 0030 0031 # $example on$ 0032 continuousDataFrame = spark.createDataFrame([ 0033 (0, 0.1), 0034 (1, 0.8), 0035 (2, 0.2) 0036 ], ["id", "feature"]) 0037 0038 binarizer = Binarizer(threshold=0.5, inputCol="feature", outputCol="binarized_feature") 0039 0040 binarizedDataFrame = binarizer.transform(continuousDataFrame) 0041 0042 print("Binarizer output with Threshold = %f" % binarizer.getThreshold()) 0043 binarizedDataFrame.show() 0044 # $example off$ 0045 0046 spark.stop()
[ Source navigation ] | [ Diff markup ] | [ Identifier search ] | [ general search ] |
This page was automatically generated by the 2.1.0 LXR engine. The LXR team |