import dumbo def mapper(key, value): for word in value.split(): yield word, 1 def reducer(key, values): yield key, sum(values) if __name__ == "__main__": dumbo.run(mapper, reducer) [hadoop] jar = /path/to/hadoop.jar input = /path/to/input/directory output = /path/to/output/directory logdir = /path/to/log/directory rm = /path/to/hadoop-<username>/bin/hadoop fs -rmr %(hdfspath)s hadoop = /path/to/hadoop version = 0.20.1 dumbo start dumbo.conf your_code.py