diff options
Diffstat (limited to 'examples/src/main/python/ml')
-rw-r--r-- | examples/src/main/python/ml/tf_idf_example.py | 2 |
1 files changed, 2 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 index c92313378e..141324d458 100644 --- a/examples/src/main/python/ml/tf_idf_example.py +++ b/examples/src/main/python/ml/tf_idf_example.py @@ -37,6 +37,8 @@ if __name__ == "__main__": wordsData = tokenizer.transform(sentenceData) hashingTF = HashingTF(inputCol="words", outputCol="rawFeatures", numFeatures=20) featurizedData = hashingTF.transform(wordsData) + # alternatively, CountVectorizer can also be used to get term frequency vectors + idf = IDF(inputCol="rawFeatures", outputCol="features") idfModel = idf.fit(featurizedData) rescaledData = idfModel.transform(featurizedData) |