diff options
Diffstat (limited to 'examples/src/main/python/ml/tf_idf_example.py')
-rw-r--r-- | examples/src/main/python/ml/tf_idf_example.py | 10 |
1 files changed, 4 insertions, 6 deletions
diff --git a/examples/src/main/python/ml/tf_idf_example.py b/examples/src/main/python/ml/tf_idf_example.py index 141324d458..25df8166ef 100644 --- a/examples/src/main/python/ml/tf_idf_example.py +++ b/examples/src/main/python/ml/tf_idf_example.py @@ -17,18 +17,16 @@ 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 +from pyspark.sql import SparkSession if __name__ == "__main__": - sc = SparkContext(appName="TfIdfExample") - sqlContext = SQLContext(sc) + spark = SparkSession.builder.appName("TfIdfExample").getOrCreate() # $example on$ - sentenceData = sqlContext.createDataFrame([ + sentenceData = spark.createDataFrame([ (0, "Hi I heard about Spark"), (0, "I wish Java could use case classes"), (1, "Logistic regression models are neat") @@ -46,4 +44,4 @@ if __name__ == "__main__": print(features_label) # $example off$ - sc.stop() + spark.stop() |