import dumbo import re def mapper(key, value): words = re.findall(r'\w+', value) for word in words: yield word, 1 def reducer(key, values): yield key, sum(values) def main(): job = dumbo.Job() job.additer(mapper, reducer) job.addopt('inputformat', 'text') job.addopt('outputformat', 'text') job.addopt('input', '/input/file.txt') job.addopt('output', '/output') job.run() if __name__ == "__main__": main()