examples/src/main/python/ml/tf_idf_example.py

#
# 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.
#

# $example on$
from pyspark.ml.feature import HashingTF, IDF, Tokenizer
# $example off$
from pyspark.sql import SparkSession

if __name__ == "__main__":
    spark = SparkSession\
        .builder\
        .appName("TfIdfExample")\
        .getOrCreate()

    # $example on$
    sentenceData = spark.createDataFrame([
        (0.0, "Hi I heard about Spark"),
        (0.0, "I wish Java could use case classes"),
        (1.0, "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)
    # 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)

    rescaledData.select("label", "features").show()
    # $example off$

    spark.stop()