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 = open("三国演义.txt", "r", encoding='utf-8').read()#读取txt文件
words  = jieba.lcut(txt)#使用jieba库进行精确分词
counts = {}#创建字典数据类型
for word in words:#统计词出现的次数
    if len(word) == 1:
        continue
    elif word == "诸葛亮" or word == "孔明曰":
        rword = "孔明"
    elif word == "关公" or word == "云长":
        rword = "关羽"
    elif word == "玄德" or word == "玄德曰":
        rword = "刘备"
    elif word == "孟德" or word == "丞相":
        rword = "曹操"
    else:
        rword = word
    counts[rword] = counts.get(rword,0) + 1
for word in excludes:
    del(counts[word])
items = list(counts.items())
items.sort(key=lambda x:x[1], reverse=True) 
for i in range(5):#输出5个人物
    word, count = items[i]
    print ("{0:<10}{1:>5}".format(word, count))

把需要统计的txt文件放在对应的程序所在目录下！！！