理解MapReduce

Posted 2020-11-04 370蔡轩

1.用Python编写WordCount程序并提交任务

程序	WordCount
输入	一个包含大量单词的文本文件
输出	文件中每个单词及其出现次数（频数），并按照单词字母顺序排序，每个单词和其频数占一行，单词和频数之间有间隔

import sys
for i in stdin:
     i = i.strip()
     words = i.split()
     for word in words:
         print ‘%s\t%s‘ % (word,1)

from operator import itemgetter
import sys
  
current_word = None
current_count = 0
word = None
  
for line in sys.stdin:
    line = line.strip()
    word, count = line.split(‘\t‘, 1)
    try:
        count = int(count)
    except ValueError:
        continue
    if current_word == word:
        current_count += count
    else:
        if current_word:
            print "%s\t%s" % (current_word, current_count)
        current_count = count
        current_word = word
  
if word == current_word:
    print "%s\t%s" % (current_word, current_count)

chmod a+x /home/hadoop/wc/mapper.py
chmod a+x /home/hadoop/wc/reducer.py