红楼梦词云统计

红楼梦词汇频率统计.py

import jieba
txt = open("D:\Pythonworking\Code\红楼梦_正文(第1章-20章).txt", "r", encoding='utf-8').read()
words = jieba.lcut(txt)
counts = {}
for word in words:
if len(word) == 1: # 排除单个字符
continue
else:
counts[word] = counts.get(word,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))