python/mllib/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 from pyspark import SparkContext
0021 # $example on$
0022 from pyspark.mllib.feature import HashingTF, IDF
0023 # $example off$
0024
0025 if __name__ == "__main__":
0026     sc = SparkContext(appName="TFIDFExample")  # SparkContext
0027
0028     # $example on$
0029     # Load documents (one per line).
0030     documents = sc.textFile("data/mllib/kmeans_data.txt").map(lambda line: line.split(" "))
0031
0032     hashingTF = HashingTF()
0033     tf = hashingTF.transform(documents)
0034
0035     # While applying HashingTF only needs a single pass to the data, applying IDF needs two passes:
0036     # First to compute the IDF vector and second to scale the term frequencies by IDF.
0037     tf.cache()
0038     idf = IDF().fit(tf)
0039     tfidf = idf.transform(tf)
0040
0041     # spark.mllib's IDF implementation provides an option for ignoring terms
0042     # which occur in less than a minimum number of documents.
0043     # In such cases, the IDF for these terms is set to 0.
0044     # This feature can be used by passing the minDocFreq value to the IDF constructor.
0045     idfIgnore = IDF(minDocFreq=2).fit(tf)
0046     tfidfIgnore = idfIgnore.transform(tf)
0047     # $example off$
0048
0049     print("tfidf:")
0050     for each in tfidf.collect():
0051         print(each)
0052
0053     print("tfidfIgnore:")
0054     for each in tfidfIgnore.collect():
0055         print(each)
0056
0057     sc.stop()