python入门基础实例：python文本词频统计

python入门基础实例：python文本词频统计

英文文本：hamlet，统计出现最多的英文单词

代码实现：

#Hamlet词频统计
def getText():
    txt = open("hamlet",'r').read()
    txt = txt.lower() #大写字母转换小写
    for word in '~!@#$%^&*()_+-={}[],./:";<>?':
        txt = txt.replace(word," ")#把多余符号转换为空格
    return txt
hamletTxt = getText()
words = hamletTxt.split() #以空格拆分为列表
counts = {}
for word in words:
    counts[word] = counts.get(word,0) + 1 #以每个词为键，值默认0，,每出现一次累加1
items = list(counts.items())
items.sort(key=lambda x:x[1],reverse=True) #[1]按照第二维排序，reverse=True表示降序
for i in range(10):
    word,count = items[i]
    print("{0:<10}{1:5}".format(word,count))

中文文本：三国，分析人物

import jieba
txt = open("Threekingdoms", 'r', encoding="utf-8").read()
excludes = {'将军','却说','荆州','二人','不可','不能','如此'}
words = jieba.lcut(txt)
counts = {}
for word in words:
    if len(word) == 1:
        continue
    #书中同一人物多个名字统一改为一个名字
    elif word == '诸葛亮' or word == '空明日':
        rword = "孔明"
    elif word == '关公' or word == '云长':
        rword = "关羽"
    elif word == '玄德' or word == '玄德日':
        rword = "刘备"
    elif word == '孟德' or word == '丞相':
        rword = "曹 *** "
    else:
        rword = word
    counts[word] = counts.get(word, 0) + 1
for word in excludes:
    del counts[word]  #去重
items = list(counts.items())
items.sort(key=lambda x:x[1],reverse=True)
for i in range(10):
    word,count = items[i]
    print("{0:<10}{1:>5}".format(word,count))