aboutsummaryrefslogtreecommitdiff
path: root/python/examples/wordcount.py
diff options
context:
space:
mode:
authorJosh Rosen <joshrosen@eecs.berkeley.edu>2013-01-01 14:48:45 -0800
committerJosh Rosen <joshrosen@eecs.berkeley.edu>2013-01-01 15:05:00 -0800
commitb58340dbd9a741331fc4c3829b08c093560056c2 (patch)
tree52b0e94c47892a8f884b2f80a59ccdb1a428b389 /python/examples/wordcount.py
parent170e451fbdd308ae77065bd9c0f2bd278abf0cb7 (diff)
downloadspark-b58340dbd9a741331fc4c3829b08c093560056c2.tar.gz
spark-b58340dbd9a741331fc4c3829b08c093560056c2.tar.bz2
spark-b58340dbd9a741331fc4c3829b08c093560056c2.zip
Rename top-level 'pyspark' directory to 'python'
Diffstat (limited to 'python/examples/wordcount.py')
-rw-r--r--python/examples/wordcount.py19
1 files changed, 19 insertions, 0 deletions
diff --git a/python/examples/wordcount.py b/python/examples/wordcount.py
new file mode 100644
index 0000000000..857160624b
--- /dev/null
+++ b/python/examples/wordcount.py
@@ -0,0 +1,19 @@
+import sys
+from operator import add
+
+from pyspark 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)