aboutsummaryrefslogtreecommitdiff
path: root/python/examples/wordcount.py
diff options
context:
space:
mode:
authorTathagata Das <tathagata.das1565@gmail.com>2013-02-18 13:26:12 -0800
committerTathagata Das <tathagata.das1565@gmail.com>2013-02-18 13:26:12 -0800
commit6a6e6bda5713ccc6da9ca977321a1fcc6d38a1c1 (patch)
tree3848e9e09a2c8b7537f4a0635ea0a32daee1f9a8 /python/examples/wordcount.py
parent56b9bd197c522f33e354c2e9ad7e76440cf817e9 (diff)
parent8ad561dc7d6475d7b217ec3f57bac3b584fed31a (diff)
downloadspark-6a6e6bda5713ccc6da9ca977321a1fcc6d38a1c1.tar.gz
spark-6a6e6bda5713ccc6da9ca977321a1fcc6d38a1c1.tar.bz2
spark-6a6e6bda5713ccc6da9ca977321a1fcc6d38a1c1.zip
Merge branch 'streaming' into ScrapCode-streaming
Conflicts: streaming/src/main/scala/spark/streaming/dstream/KafkaInputDStream.scala streaming/src/main/scala/spark/streaming/dstream/NetworkInputDStream.scala
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)