[PySpark][Minor] Update sql example, so that can read file correctly
To run Spark, default will read file from HDFS if we don't set the schema. Author: linweizhong <linweizhong@huawei.com> Closes #5684 from Sephiroth-Lin/pyspark_example_minor and squashes the following commits: 19fe145 [linweizhong] Update example sql.py, so that can read file correctly
This commit is contained in:
parent
438859eb7c
commit
d874f8b546
|
@ -18,6 +18,7 @@
|
|||
from __future__ import print_function
|
||||
|
||||
import os
|
||||
import sys
|
||||
|
||||
from pyspark import SparkContext
|
||||
from pyspark.sql import SQLContext
|
||||
|
@ -50,7 +51,11 @@ if __name__ == "__main__":
|
|||
|
||||
# A JSON dataset is pointed to by path.
|
||||
# The path can be either a single text file or a directory storing text files.
|
||||
path = os.path.join(os.environ['SPARK_HOME'], "examples/src/main/resources/people.json")
|
||||
if len(sys.argv) < 2:
|
||||
path = "file://" + \
|
||||
os.path.join(os.environ['SPARK_HOME'], "examples/src/main/resources/people.json")
|
||||
else:
|
||||
path = sys.argv[1]
|
||||
# Create a DataFrame from the file(s) pointed to by path
|
||||
people = sqlContext.jsonFile(path)
|
||||
# root
|
||||
|
|
Loading…
Reference in a new issue