blob: c4d53333a95a94c71fd7d182e5f3c4012266492b (
plain) (
blame)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
|
#
# Licensed to the Apache Software Foundation (ASF) under one or more
# contributor license agreements. See the NOTICE file distributed with
# this work for additional information regarding copyright ownership.
# The ASF licenses this file to You under the Apache License, Version 2.0
# (the "License"); you may not use this file except in compliance with
# the License. You may obtain a copy of the License at
#
# http://www.apache.org/licenses/LICENSE-2.0
#
# Unless required by applicable law or agreed to in writing, software
# distributed under the License is distributed on an "AS IS" BASIS,
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
# See the License for the specific language governing permissions and
# limitations under the License.
#
from __future__ import print_function
from pyspark import SparkContext
# $example on$
from pyspark.mllib.feature import HashingTF, IDF
# $example off$
if __name__ == "__main__":
sc = SparkContext(appName="TFIDFExample") # SparkContext
# $example on$
# Load documents (one per line).
documents = sc.textFile("data/mllib/kmeans_data.txt").map(lambda line: line.split(" "))
hashingTF = HashingTF()
tf = hashingTF.transform(documents)
# While applying HashingTF only needs a single pass to the data, applying IDF needs two passes:
# First to compute the IDF vector and second to scale the term frequencies by IDF.
tf.cache()
idf = IDF().fit(tf)
tfidf = idf.transform(tf)
# spark.mllib's IDF implementation provides an option for ignoring terms
# which occur in less than a minimum number of documents.
# In such cases, the IDF for these terms is set to 0.
# This feature can be used by passing the minDocFreq value to the IDF constructor.
idfIgnore = IDF(minDocFreq=2).fit(tf)
tfidfIgnore = idf.transform(tf)
# $example off$
print("tfidf:")
for each in tfidf.collect():
print(each)
print("tfidfIgnore:")
for each in tfidfIgnore.collect():
print(each)
sc.stop()
|