文本词频统计

文本词频统计

词频：单词出现的次数

# 统计英文：
f = open('F:\实习\python\hamlet','r',encoding='utf8')
data = f.read().lower()
data_split = data.split(' ')

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

def func(i):
    return i[1]
lt = list(count_dict.items())
lt.sort(key = func)

lt.reverse()            # 运行结果由大到小排列
for i in lt[0:10]:
    print(f'{i[0]:^7}{i[1]^5}')

# 统计中文：
import jieba            # 导入一个jieba库,用来分词
f = open(r'F:\实习\python\0719\threekingdoms','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 {"将军", "却说", "荆州", "二人", "不可", "不能", "如此"}:
        continue
    if '曰' in word:
        word = word.replace('曰','')
    if word not 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()
print(data_list)

转载于:https://www.cnblogs.com/yushan1/p/11213414.html