十六、jieba库的使用

一、jieba库的三种模式

二、常用函数

三、实例

#英文词频统计
def getText():  #定义获取文件函数
    txt = open('哈姆雷特.txt','r').read()   #打开文件，只读模式
    txt = txt.lower()   #将字母全部转换为小写
    for ch in '!"#$%&()*+,-./:;<=>[e-mail][\\]^_‘{|}~':   #将特殊字符替换为空格
        txt = txt.replace(ch,' ')
    return txt
hamletTxt = getText()
words = hamletTxt.split()   #将获取的字符串进行分隔
counts = {}
for word in words:
    counts[word] = counts.get(word,0) +1    #以字典的形式进行词频统计
items = list(counts.items())    #将统计的字典转换为列表
items.sort(key=lambda x:x[1], reverse=True)     #从大到小进行排列
for i in range(10):
    word, count = items[i]
    print('{0:<10}{1:>5}'.format(word,count))

运行结果：
the 1138
and 965
to 754
of 669
you 550
i 542
a 542
my 514
hamlet 462
in 436

#中文词频统计
import jieba
txt = open('三国演义.txt','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
    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(10):
    word, count = items[i]
    print('{0:<10}{1:>5}'.format(word, count))

曹操 1451
孔明 1383
刘备 1252
关羽 784
张飞 358
商议 344
如何 338
主公 331
军士 317
吕布 300