blob: 38cfac82fbe206c4c5f8f5cde41c93d1cb81ea00 (
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
|
#
# 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.sql import SparkSession
# $example on$
from pyspark.ml.feature import CountVectorizer
# $example off$
if __name__ == "__main__":
spark = SparkSession\
.builder\
.appName("CountVectorizerExample")\
.getOrCreate()
# $example on$
# Input data: Each row is a bag of words with a ID.
df = spark.createDataFrame([
(0, "a b c".split(" ")),
(1, "a b b c a".split(" "))
], ["id", "words"])
# fit a CountVectorizerModel from the corpus.
cv = CountVectorizer(inputCol="words", outputCol="features", vocabSize=3, minDF=2.0)
model = cv.fit(df)
result = model.transform(df)
result.show()
# $example off$
spark.stop()
|