python/ml/count_vectorizer_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.sql import SparkSession
0021 # $example on$
0022 from pyspark.ml.feature import CountVectorizer
0023 # $example off$
0024
0025 if __name__ == "__main__":
0026     spark = SparkSession\
0027         .builder\
0028         .appName("CountVectorizerExample")\
0029         .getOrCreate()
0030
0031     # $example on$
0032     # Input data: Each row is a bag of words with a ID.
0033     df = spark.createDataFrame([
0034         (0, "a b c".split(" ")),
0035         (1, "a b b c a".split(" "))
0036     ], ["id", "words"])
0037
0038     # fit a CountVectorizerModel from the corpus.
0039     cv = CountVectorizer(inputCol="words", outputCol="features", vocabSize=3, minDF=2.0)
0040
0041     model = cv.fit(df)
0042
0043     result = model.transform(df)
0044     result.show(truncate=False)
0045     # $example off$
0046
0047     spark.stop()