diff options
author | Xusen Yin <yinxusen@gmail.com> | 2015-10-26 21:17:53 -0700 |
---|---|---|
committer | Xiangrui Meng <meng@databricks.com> | 2015-10-26 21:17:53 -0700 |
commit | 943d4fa204a827ca8ecc39d9cf04e86890ee9840 (patch) | |
tree | f50ba101226bb1f0c0e11a3cffe00aa4daa166f1 /examples/src/main/python/ml/tf_idf_example.py | |
parent | a150e6c1b03b64a35855b8074b2fe077a6081a34 (diff) | |
download | spark-943d4fa204a827ca8ecc39d9cf04e86890ee9840.tar.gz spark-943d4fa204a827ca8ecc39d9cf04e86890ee9840.tar.bz2 spark-943d4fa204a827ca8ecc39d9cf04e86890ee9840.zip |
[SPARK-11289][DOC] Substitute code examples in ML features extractors with include_example
mengxr https://issues.apache.org/jira/browse/SPARK-11289
I make some changes in ML feature extractors. I.e. TF-IDF, Word2Vec, and CountVectorizer. I add new example code in spark/examples, hope it is the right place to add those examples.
Author: Xusen Yin <yinxusen@gmail.com>
Closes #9266 from yinxusen/SPARK-11289.
Diffstat (limited to 'examples/src/main/python/ml/tf_idf_example.py')
-rw-r--r-- | examples/src/main/python/ml/tf_idf_example.py | 47 |
1 files changed, 47 insertions, 0 deletions
diff --git a/examples/src/main/python/ml/tf_idf_example.py b/examples/src/main/python/ml/tf_idf_example.py new file mode 100644 index 0000000000..c92313378e --- /dev/null +++ b/examples/src/main/python/ml/tf_idf_example.py @@ -0,0 +1,47 @@ +# +# 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.ml.feature import HashingTF, IDF, Tokenizer +# $example off$ +from pyspark.sql import SQLContext + +if __name__ == "__main__": + sc = SparkContext(appName="TfIdfExample") + sqlContext = SQLContext(sc) + + # $example on$ + sentenceData = sqlContext.createDataFrame([ + (0, "Hi I heard about Spark"), + (0, "I wish Java could use case classes"), + (1, "Logistic regression models are neat") + ], ["label", "sentence"]) + tokenizer = Tokenizer(inputCol="sentence", outputCol="words") + wordsData = tokenizer.transform(sentenceData) + hashingTF = HashingTF(inputCol="words", outputCol="rawFeatures", numFeatures=20) + featurizedData = hashingTF.transform(wordsData) + idf = IDF(inputCol="rawFeatures", outputCol="features") + idfModel = idf.fit(featurizedData) + rescaledData = idfModel.transform(featurizedData) + for features_label in rescaledData.select("features", "label").take(3): + print(features_label) + # $example off$ + + sc.stop() |