python简单词频统计

词频统计

简单英语词频统计

# 词频:单词出现的次数


f = open(r'D:上海Python11期视频预科班hamlet.txt','r',encoding='utf8')
data = f.read().lower()
# print(data)
data_split = data.split(' ')
# print(data_split)

count_dict = {}
for word in data_split:
    if word not in count_dict:
        count_dict[word] = 1
    else:
        count_dict[word] += 1

# print(count_dict)
def func(i):
    return i[1]

lt = list(count_dict.items())
lt.sort(key=func)

lt.reverse()

for i in lt[0:10]:
    print(f'{i[0]:^7}{i[1]^5}')

简单中文词频统计

import jieba

f = open(r'F:pythonxm7.19day06	hreekingdoms.txt','r',encoding='utf8')

data = f.read()

data_jieba = jieba.lcut(data)

count_dict = {}
for word in data_jieba :
    if len(word) == 1 :
        continue

    if word in {"次日","引兵","军马","左右","将军", "却说", "荆州", "二人","如何","军士","不可", "不能", "如此", "商议"}:
        continue
    if '曰' in word :
        word = word.replace('曰','')
    if word == '玄德' :
        word = '刘备'
    # if word == '孔明曰':
    #     word = '孔明'
    # elif word == '玄德曰':
    #     word = '玄德'
    if word in count_dict :
        count_dict[word] += 1
    else:
        count_dict[word] = 1
def func(i):
    return i[1]
data_list = list(count_dict.items())

data_list.sort(key=func)
data_list.reverse()
for i in data_list[0:10] :
    print(f'{i[0]:^4}{i[1] ^ 6}')

作　　者：豆瓣酱瓣豆
出　　处：https://www.cnblogs.com/chenziqing/
查看其它博文请点击：https://www.cnblogs.com/chenziqing/
声援博主：如果您觉得文章对您有帮助，可以点击文章右下角【推荐】一下。您的鼓励是博主的最大动力！

微信: