Python入门程序-文本词频统计

1.Hamlet 英文词频统计

#Hamlet
excludes = {"the","and","of","you","a","i","my","in"}
def getText():
    txt=open("hamlet.txt","r").read()
    txt=txt.lower()
    for ch in '~!@#$%^&*()_+-=[]\;,./<>?:"{}|':
        txt=txt.replace(ch," ")
    return txt
hamletTxt=getText()
words=hamletTxt.split()
counts={}#新建一个字典
for word in words:
    counts [word]=counts.get(word,0)+1  #对单词出现频率进行统计
items=list(counts.items())
items.sort(key=lambda x:x[1],reverse=True)
for i in range(10):
    word,count=items[i] #返回相对应的键值对
    print ("{0:<10}{1:>5}".format(word,count))

2.《三国演义》人物出场统计

#《三国演义》

import jieba
excludes = {"将军","却说","荆州","二人","不可","不能","如此"}
txt =