python/ml/onehot_encoder_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 # $example on$
0021 from pyspark.ml.feature import OneHotEncoder
0022 # $example off$
0023 from pyspark.sql import SparkSession
0024
0025 if __name__ == "__main__":
0026     spark = SparkSession\
0027         .builder\
0028         .appName("OneHotEncoderExample")\
0029         .getOrCreate()
0030
0031     # Note: categorical features are usually first encoded with StringIndexer
0032     # $example on$
0033     df = spark.createDataFrame([
0034         (0.0, 1.0),
0035         (1.0, 0.0),
0036         (2.0, 1.0),
0037         (0.0, 2.0),
0038         (0.0, 1.0),
0039         (2.0, 0.0)
0040     ], ["categoryIndex1", "categoryIndex2"])
0041
0042     encoder = OneHotEncoder(inputCols=["categoryIndex1", "categoryIndex2"],
0043                             outputCols=["categoryVec1", "categoryVec2"])
0044     model = encoder.fit(df)
0045     encoded = model.transform(df)
0046     encoded.show()
0047     # $example off$
0048
0049     spark.stop()