blob: 8365c070e8e56944ee2b641161bab79042634a5a (
plain) (
blame)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
|
import sys
from operator import add
from pyspark.context import SparkContext
if __name__ == "__main__":
if len(sys.argv) < 3:
print >> sys.stderr, \
"Usage: PythonWordCount <master> <file>"
exit(-1)
sc = SparkContext(sys.argv[1], "PythonWordCount")
lines = sc.textFile(sys.argv[2], 1)
counts = lines.flatMap(lambda x: x.split(' ')) \
.map(lambda x: (x, 1)) \
.reduceByKey(add)
output = counts.collect()
for (word, count) in output:
print "%s : %i" % (word, count)
|