From fcdd69260ec75c180f4d727ff2625ca9bf0bdad7 Mon Sep 17 00:00:00 2001 From: Zheng RuiFeng Date: Wed, 13 Apr 2016 13:56:23 -0700 Subject: [SPARK-14509][DOC] Add python CountVectorizerExample ## What changes were proposed in this pull request? Add python CountVectorizerExample ## How was this patch tested? manual tests Author: Zheng RuiFeng Closes #11917 from zhengruifeng/cv_pe. --- .../src/main/python/ml/count_vectorizer_example.py | 44 ++++++++++++++++++++++ 1 file changed, 44 insertions(+) create mode 100644 examples/src/main/python/ml/count_vectorizer_example.py (limited to 'examples/src/main') diff --git a/examples/src/main/python/ml/count_vectorizer_example.py b/examples/src/main/python/ml/count_vectorizer_example.py new file mode 100644 index 0000000000..e839f645f7 --- /dev/null +++ b/examples/src/main/python/ml/count_vectorizer_example.py @@ -0,0 +1,44 @@ +# +# 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 +from pyspark.sql import SQLContext +# $example on$ +from pyspark.ml.feature import CountVectorizer +# $example off$ + +if __name__ == "__main__": + sc = SparkContext(appName="CountVectorizerExample") + sqlContext = SQLContext(sc) + + # $example on$ + # Input data: Each row is a bag of words with a ID. + df = sqlContext.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() + # $example off$ + + sc.stop() -- cgit v1.2.3