pip install dumbo
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)
hadoop '/usr/local/hadoop'
python 'python3'
jobconf 'mapred.reduce.tasks' '10'
