python/ml/tf_idf_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 HashingTF, IDF, Tokenizer
0022 # $example off$
0023 from pyspark.sql import SparkSession
0024
0025 if __name__ == "__main__":
0026     spark = SparkSession\
0027         .builder\
0028         .appName("TfIdfExample")\
0029         .getOrCreate()
0030
0031     # $example on$
0032     sentenceData = spark.createDataFrame([
0033         (0.0, "Hi I heard about Spark"),
0034         (0.0, "I wish Java could use case classes"),
0035         (1.0, "Logistic regression models are neat")
0036     ], ["label", "sentence"])
0037
0038     tokenizer = Tokenizer(inputCol="sentence", outputCol="words")
0039     wordsData = tokenizer.transform(sentenceData)
0040
0041     hashingTF = HashingTF(inputCol="words", outputCol="rawFeatures", numFeatures=20)
0042     featurizedData = hashingTF.transform(wordsData)
0043     # alternatively, CountVectorizer can also be used to get term frequency vectors
0044
0045     idf = IDF(inputCol="rawFeatures", outputCol="features")
0046     idfModel = idf.fit(featurizedData)
0047     rescaledData = idfModel.transform(featurizedData)
0048
0049     rescaledData.select("label", "features").show()
0050     # $example off$
0051
0052     spark.stop()