让python在hadoop上跑起来

#!/usr/bin/env python
import sys

for line in sys.stdin: # 遍历读入数据的每一行
  
  line = line.strip() # 将行尾行首的空格去除
  words = line.split() #按空格将句子分割成单个单词
  for word in words:
    print '%s\t%s' %(word, 1)

#!/usr/bin/env python

from operator import itemgetter
import sys

current_word = None # 为当前单词
current_count = 0 # 当前单词频数
word = None

for line in sys.stdin:
  words = line.strip() # 去除字符串首尾的空白字符
  word, count = words.split('\t') # 按照制表符分隔单词和数量
  
  try:
    count = int(count) # 将字符串类型的‘1'转换为整型1
  except ValueError:
    continue

  if current_word == word: # 如果当前的单词等于读入的单词
    current_count += count # 单词频数加1
  else:
    if current_word: # 如果当前的单词不为空则打印其单词和频数
      print '%s\t%s' %(current_word, current_count) 
    current_count = count # 否则将读入的单词赋值给当前单词，且更新频数
    current_word = word

if current_word == word:
  print '%s\t%s' %(current_word, current_count)

echo "foo foo quux labs foo bar zoo zoo hying" | /home/wuying/mapper.py | sort -k 1,1 | /home/wuying/reducer.py

# echo是将后面“foo ****”字符串输出，并利用管道符“|”将输出数据作为mapper.py这个脚本的输入数据，并将mapper.py的数据输入到reducer.py中，其中参数sort -k 1,1是将reducer的输出内容按照第一列的第一个字母的ASCII码值进行升序排序

$ mkdir -p tmp/gutenberg
$ cd tmp/gutenberg
$ wget http://www.gutenberg.org/ebooks/20417.txt.utf-8
$ wget http://www.gutenberg.org/files/5000/5000-8.txt
$ wget http://www.gutenberg.org/ebooks/4300.txt.utf-8

 $ hdfs dfs -mkdir /user/${whoami}/input # 在hdfs上的该用户目录下创建一个输入文件的文件夹
 $ hdfs dfs -put /home/wuying/tmp/gutenberg/*.txt /user/${whoami}/input # 上传文档到hdfs上的输入文件夹中

$ cd $HADOOP_HOME
$ find ./ -name "*streaming*"

$ vi ~/.bashrc # 打开环境变量配置文件
# 在里面写入streaming路径
export STREAM=$HADOOP_HOME/share/hadoop/tools/lib/hadoop-streaming-*.jar

hadoop jar $STREAM \
-files ./mapper.py,./reducer.py \
-mapper ./mapper.py \
-reducer ./reducer.py \
-input /user/$(whoami)/input/*.txt \
-output /user/$(whoami)/output