python/ml/vector_indexer_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 VectorIndexer
0022 # $example off$
0023 from pyspark.sql import SparkSession
0024
0025 if __name__ == "__main__":
0026     spark = SparkSession\
0027         .builder\
0028         .appName("VectorIndexerExample")\
0029         .getOrCreate()
0030
0031     # $example on$
0032     data = spark.read.format("libsvm").load("data/mllib/sample_libsvm_data.txt")
0033
0034     indexer = VectorIndexer(inputCol="features", outputCol="indexed", maxCategories=10)
0035     indexerModel = indexer.fit(data)
0036
0037     categoricalFeatures = indexerModel.categoryMaps
0038     print("Chose %d categorical features: %s" %
0039           (len(categoricalFeatures), ", ".join(str(k) for k in categoricalFeatures.keys())))
0040
0041     # Create new column "indexed" with categorical values transformed to indices
0042     indexedData = indexerModel.transform(data)
0043     indexedData.show()
0044     # $example off$
0045
0046     spark.stop()