aboutsummaryrefslogtreecommitdiff
path: root/python/examples/wordcount.py
diff options
context:
space:
mode:
authorTathagata Das <tathagata.das1565@gmail.com>2013-01-15 12:08:51 -0800
committerTathagata Das <tathagata.das1565@gmail.com>2013-01-15 12:08:51 -0800
commitcd1521cfdb3c9dd2bf8ced8907afbbbf33893804 (patch)
tree76fce28a2fca3fcfbbc3a7f4c7b0fe82cfc695c7 /python/examples/wordcount.py
parent1638fcb0dce296da22ffc90127d5148a8fab745e (diff)
parentcb867e9ffb2c5e3d65d50c222fcce3631b94e4dd (diff)
downloadspark-cd1521cfdb3c9dd2bf8ced8907afbbbf33893804.tar.gz
spark-cd1521cfdb3c9dd2bf8ced8907afbbbf33893804.tar.bz2
spark-cd1521cfdb3c9dd2bf8ced8907afbbbf33893804.zip
Merge branch 'master' into streaming
Conflicts: core/src/main/scala/spark/rdd/CoGroupedRDD.scala core/src/main/scala/spark/rdd/FilteredRDD.scala docs/_layouts/global.html docs/index.md run
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)