Skip to content
Snippets Groups Projects
  • Dongjoon Hyun's avatar
    2c170dd3
    [SPARK-15134][EXAMPLE] Indent SparkSession builder patterns and update... · 2c170dd3
    Dongjoon Hyun authored
    [SPARK-15134][EXAMPLE] Indent SparkSession builder patterns and update binary_classification_metrics_example.py
    
    ## What changes were proposed in this pull request?
    
    This issue addresses the comments in SPARK-15031 and also fix java-linter errors.
    - Use multiline format in SparkSession builder patterns.
    - Update `binary_classification_metrics_example.py` to use `SparkSession`.
    - Fix Java Linter errors (in SPARK-13745, SPARK-15031, and so far)
    
    ## How was this patch tested?
    
    After passing the Jenkins tests and run `dev/lint-java` manually.
    
    Author: Dongjoon Hyun <dongjoon@apache.org>
    
    Closes #12911 from dongjoon-hyun/SPARK-15134.
    2c170dd3
    History
    [SPARK-15134][EXAMPLE] Indent SparkSession builder patterns and update...
    Dongjoon Hyun authored
    [SPARK-15134][EXAMPLE] Indent SparkSession builder patterns and update binary_classification_metrics_example.py
    
    ## What changes were proposed in this pull request?
    
    This issue addresses the comments in SPARK-15031 and also fix java-linter errors.
    - Use multiline format in SparkSession builder patterns.
    - Update `binary_classification_metrics_example.py` to use `SparkSession`.
    - Fix Java Linter errors (in SPARK-13745, SPARK-15031, and so far)
    
    ## How was this patch tested?
    
    After passing the Jenkins tests and run `dev/lint-java` manually.
    
    Author: Dongjoon Hyun <dongjoon@apache.org>
    
    Closes #12911 from dongjoon-hyun/SPARK-15134.
tf_idf_example.py 1.90 KiB
#
# 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

# $example on$
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, "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)
    # 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)
    for features_label in rescaledData.select("features", "label").take(3):
        print(features_label)
    # $example off$

    spark.stop()