diff options
Diffstat (limited to 'examples/src/main/python/ml/tokenizer_example.py')
| -rw-r--r-- | examples/src/main/python/ml/tokenizer_example.py | 10 |
1 files changed, 4 insertions, 6 deletions
diff --git a/examples/src/main/python/ml/tokenizer_example.py b/examples/src/main/python/ml/tokenizer_example.py index ce9b225be5..5be4b4cfe3 100644 --- a/examples/src/main/python/ml/tokenizer_example.py +++ b/examples/src/main/python/ml/tokenizer_example.py @@ -17,18 +17,16 @@ from __future__ import print_function -from pyspark import SparkContext -from pyspark.sql import SQLContext # $example on$ from pyspark.ml.feature import Tokenizer, RegexTokenizer # $example off$ +from pyspark.sql import SparkSession if __name__ == "__main__": - sc = SparkContext(appName="TokenizerExample") - sqlContext = SQLContext(sc) + spark = SparkSession.builder.appName("TokenizerExample").getOrCreate() # $example on$ - sentenceDataFrame = sqlContext.createDataFrame([ + sentenceDataFrame = spark.createDataFrame([ (0, "Hi I heard about Spark"), (1, "I wish Java could use case classes"), (2, "Logistic,regression,models,are,neat") @@ -41,4 +39,4 @@ if __name__ == "__main__": # alternatively, pattern="\\w+", gaps(False) # $example off$ - sc.stop() + spark.stop() |