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))

标签：ch,word,--,items,分布式计算,getText,词频,counts,txt
来源： https://www.cnblogs.com/fkqs/p/15599084.html