[hadoop@10 hadoop]$ hadoop fs -put $testfile cosn:// $bucketname/

[root@172 ~]# su hadoop
[hadoop@172 root]$ cd /usr/local/service/spark

from __future__ import print_function

import sys 
from operator import add
from pyspark.sql import SparkSession

if __name__ == "__main__":
    if len(sys.argv) != 3:
        print("Usage: wordcount <file>", file=sys.stderr)
        exit(-1)

    spark = SparkSession\\
        .builder\\
        .appName("PythonWordCount")\\
        .getOrCreate()

    sc = spark.sparkContext

    lines = spark.read.text(sys.argv[1]).rdd.map(lambda r: r[0])
    counts = lines.flatMap(lambda x: x.split(' ')) \\
                  .map(lambda x: (x, 1)) \\
                  .reduceByKey(add)

    output = counts.collect()
    counts.saveAsTextFile(sys.argv[2])

    spark.stop()

[hadoop@10   spark]$   ./bin/spark-submit   --master yarn   ./wordcount.py 
cosn://$bucketname/$yourtestfile cosn:// $bucketname/$output

[hadoop@172 spark]$ hadoop fs -ls cosn:// $bucketname/$output
Found 2 items
-rw-rw-rw- 1 hadoop Hadoop 0 2018-06-29 15:35 cosn:// $bucketname/$output /_SUCCESS
-rw-rw-rw- 1 hadoop Hadoop 2102 2018-06-29 15:34 cosn:// $bucketname/$output /part-00000

[hadoop@172 spark]$ hadoop fs -cat cosn:// $bucketname/$output /part-00000
(u'', 27)
(u'code', 1)
(u'both', 1)
(u'Hadoop', 1)
(u'Bureau', 1)
(u'Department', 1)

[hadoop@10spark]$   ./bin/spark-submit   ./wordcount.py
cosn://$bucketname/$yourtestfile /user/hadoop/$output

[hadoop@10 spark]$  /usr/local/service/hadoop/bin/yarn logs -applicationId $yourId