aboutsummaryrefslogtreecommitdiff
path: root/examples/src/main/python/parquet_inputformat.py
diff options
context:
space:
mode:
Diffstat (limited to 'examples/src/main/python/parquet_inputformat.py')
-rw-r--r--examples/src/main/python/parquet_inputformat.py12
1 files changed, 9 insertions, 3 deletions
diff --git a/examples/src/main/python/parquet_inputformat.py b/examples/src/main/python/parquet_inputformat.py
index e1fd85b082..2f09f4d573 100644
--- a/examples/src/main/python/parquet_inputformat.py
+++ b/examples/src/main/python/parquet_inputformat.py
@@ -18,7 +18,7 @@ from __future__ import print_function
import sys
-from pyspark import SparkContext
+from pyspark.sql import SparkSession
"""
Read data file users.parquet in local Spark distro:
@@ -47,7 +47,13 @@ if __name__ == "__main__":
exit(-1)
path = sys.argv[1]
- sc = SparkContext(appName="ParquetInputFormat")
+
+ spark = SparkSession\
+ .builder\
+ .appName("ParquetInputFormat")\
+ .getOrCreate()
+
+ sc = spark._sc
parquet_rdd = sc.newAPIHadoopFile(
path,
@@ -59,4 +65,4 @@ if __name__ == "__main__":
for k in output:
print(k)
- sc.stop()
+ spark.stop()