西游记词频统计

import jieba
jieba.setLogLevel(jieba.logging.INFO)
txt = open('西游记.txt', 'r', encoding='gb18030').read()
words = jieba.lcut(txt)
counts = {}
for word in words:
if len(word) == 1:
continue
elif word == "大圣" or word == "老孙" or word == "行者" or word == "孙大圣" or word == "孙行者" or word == "猴王" or word == "悟空" or word == "齐天大圣" or word == "猴子":
rword = "孙悟空"
elif word == "师父" or word == "三藏" or word == "圣僧":
rword = "唐僧"
elif word == "呆子" or word == "八戒" or word == "老猪":
rword = "猪八戒"
elif word == "沙和尚":
rword = "沙僧"
else:
rword = word
counts[rword] = counts.get(rword, 0) + 1
items = list(counts.items())
items.sort(key=lambda x: x[1], reverse=True)
for i in range(20):
word, count = items[i]
print('{0:<10}{1:>5}'.format(word, count))

西游记词频统计

 

上一篇:配置ik分词


下一篇:SQL-索引的合理规划及索引失效