08 分布式计算MapReduce--词频统计

def getText():
    txt=open("D:\\test.txt","r").read()
    txt=txt.lower()
    punctuation = r"""!"#$%&'()*+,-./:;<=>?@[\]^_`{|}~“”？，！【】（）、。：；’‘……￥·"""
    for ch in punctuation:
        txt=txt.replace(ch,"")
    return txt

hamletTxt=getText()
words=hamletTxt.split()
counts={}
for word in words:
    counts[word]=counts.get(word,0)+1
items=list(counts.items())
items.sort(key=lambda x:x[1],reverse=True)
for i in range(100):
    word,count=items[i]
    print("{0:<10}{1:>5}".format(word,count))

#!/usr/bin/env python
import sys
for line in sys.stdin:
    line = line.strip()
    words=line.split()
    for word in words:
        print("{}\t{}".format(word,1))

#!/usr/bin/env python
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)

2.3分布式运行自带词频统计示例

• 启动HDFS与YARN
  

• 准备待处理文件
   
• 上传HDFS
  

• 运行hadoop-mapreduce-examples-2.7.1.jar
  

• 查看结果

2.4 分布式运行自写的词频统计

• • 

    

     
• 停止HDFS与YARN