python实现中文词语词频统计_中文口语词汇统计

import jieba

#1.获取文本
with open('book.txt','r',encoding='UTF-8') as fp:
    txt = fp.read()

#2.分词
words = jieba.lcut(txt)
# print(words)

#3.过滤文本
for ch in '，。？！“ ” ；：、》《\n \u3000':
    if ch in words:
        for i in range(words.count(ch)):
            words.remove(ch)
# print(words)

#4.统计词语及个数
counts = {}
for word in words:
    if(len(word)>=2):
        counts[word] = counts.get(word,0) + 1

#5.排序输出
items = list(counts.items())#items()将字典的键值对以元组的形式打包，方便后续进行sort()排序，将元组转化为列表类
print(items)
items.sort(key=lambda x:x[1],reverse=True)
for i in range(20):
    word,count=items[i]
    print('{0:^4}\t{1:^3}'.format(word,count))#冒号前的0和1表示输出值的顺序，冒号后的<表示左对齐，>右对齐，数字代表宽度

1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31