From cdce4e62a5674e2034e5d395578b1a60e3d8c435 Mon Sep 17 00:00:00 2001 From: Dongjoon Hyun Date: Wed, 4 May 2016 14:31:36 -0700 Subject: [SPARK-15031][EXAMPLE] Use SparkSession in Scala/Python/Java example. ## What changes were proposed in this pull request? This PR aims to update Scala/Python/Java examples by replacing `SQLContext` with newly added `SparkSession`. - Use **SparkSession Builder Pattern** in 154(Scala 55, Java 52, Python 47) files. - Add `getConf` in Python SparkContext class: `python/pyspark/context.py` - Replace **SQLContext Singleton Pattern** with **SparkSession Singleton Pattern**: - `SqlNetworkWordCount.scala` - `JavaSqlNetworkWordCount.java` - `sql_network_wordcount.py` Now, `SQLContexts` are used only in R examples and the following two Python examples. The python examples are untouched in this PR since it already fails some unknown issue. - `simple_params_example.py` - `aft_survival_regression.py` ## How was this patch tested? Manual. Author: Dongjoon Hyun Closes #12809 from dongjoon-hyun/SPARK-15031. --- examples/src/main/python/ml/word2vec_example.py | 10 ++++------ 1 file changed, 4 insertions(+), 6 deletions(-) (limited to 'examples/src/main/python/ml/word2vec_example.py') diff --git a/examples/src/main/python/ml/word2vec_example.py b/examples/src/main/python/ml/word2vec_example.py index 53c77feb10..6766a7b6aa 100644 --- a/examples/src/main/python/ml/word2vec_example.py +++ b/examples/src/main/python/ml/word2vec_example.py @@ -17,19 +17,17 @@ from __future__ import print_function -from pyspark import SparkContext -from pyspark.sql import SQLContext # $example on$ from pyspark.ml.feature import Word2Vec # $example off$ +from pyspark.sql import SparkSession if __name__ == "__main__": - sc = SparkContext(appName="Word2VecExample") - sqlContext = SQLContext(sc) + spark = SparkSession.builder.appName("Word2VecExample").getOrCreate() # $example on$ # Input data: Each row is a bag of words from a sentence or document. - documentDF = sqlContext.createDataFrame([ + documentDF = spark.createDataFrame([ ("Hi I heard about Spark".split(" "), ), ("I wish Java could use case classes".split(" "), ), ("Logistic regression models are neat".split(" "), ) @@ -42,4 +40,4 @@ if __name__ == "__main__": print(feature) # $example off$ - sc.stop() + spark.stop() -- cgit v1.2.3