python/ml/index_to_string_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 IndexToString, StringIndexer
0022 # $example off$
0023 from pyspark.sql import SparkSession
0024
0025 if __name__ == "__main__":
0026     spark = SparkSession\
0027         .builder\
0028         .appName("IndexToStringExample")\
0029         .getOrCreate()
0030
0031     # $example on$
0032     df = spark.createDataFrame(
0033         [(0, "a"), (1, "b"), (2, "c"), (3, "a"), (4, "a"), (5, "c")],
0034         ["id", "category"])
0035
0036     indexer = StringIndexer(inputCol="category", outputCol="categoryIndex")
0037     model = indexer.fit(df)
0038     indexed = model.transform(df)
0039
0040     print("Transformed string column '%s' to indexed column '%s'"
0041           % (indexer.getInputCol(), indexer.getOutputCol()))
0042     indexed.show()
0043
0044     print("StringIndexer will store labels in output column metadata\n")
0045
0046     converter = IndexToString(inputCol="categoryIndex", outputCol="originalCategory")
0047     converted = converter.transform(indexed)
0048
0049     print("Transformed indexed column '%s' back to original string column '%s' using "
0050           "labels in metadata" % (converter.getInputCol(), converter.getOutputCol()))
0051     converted.select("id", "categoryIndex", "originalCategory").show()
0052     # $example off$
0053
0054     spark.stop()