2.1 PySpark 2.2 Dask 2.3 Joblib python import dumbo def mapper(key, value): words = value.split() for word in words: yield word, 1 def reducer(key, values): yield key, sum(values) if __name__ == '__main__': dumbo.run(mapper, reducer) json { "hadoop_home": "/path/to/hadoop", "hadoop_conf": "/path/to/hadoop/conf" }