Python+Hadoop Streaming实现MapReduce（如何给map和reduce的脚本传递参数）

设置参数

#!/bin/bash

hadoop fs -rmr trans_record/result

hadoop jar ./hadoop-streaming-2.0.0-mr1-cdh4.7.0.jar \
        -input $1 \
        -output trans_record/result \
        -file map.py \
        -file reduce.py \
        -mapper "python map.py" \
        -reducer "python reduce.py" \
        -jobconf mapred.reduce.tasks=1 \
        -jobconf mapred.job.name="qianjc_trans_record" \
        -cmdenv "card_start=$2" \
        -cmdenv "card_last=$3" \
        -cmdenv "trans_at=$4"

取参数

#!/usr/bin/env python
# vim: set fileencoding=utf-8
import sys
import os


def main():
    card_start = os.environ.get('card_start')
    card_last = os.environ.get('card_last')
    trans_at = float(os.environ.get('trans_at'))

    for line in sys.stdin:
        detail = line.strip().split(',')
        card = detail[0]
        money = float(detail[17])
        if trans_at == money and card_start == card[1 : 7] and card_last == card[-4 : ]:
            print '%s\t%s' % (line.strip(), detail[1])

if __name__ == '__main__':
    main()