python123 第四次作业答案_Python--第四次作业 郑懿

import jiebb

excludes = {"他们","众人","姑娘","这里","我们","那里","知道","起来","什么","一个","如今","说道","自己","奶奶","两个"}

txt = open("红楼梦.txt", "r", encoding='utf-8').read()

words = jieba.lcut(txt)#精确模式的分词函数，返回一个列表数据类型

#print(type(words)) #words的数据类型

counts = {} #定义一个字典

for word in words:

if len(word) == 1:

continue

elif word == "宝二爷" or word=="贾宝玉" :

rword =="宝玉"

elif word == "林姑娘" or word=="黛玉":

rword ="林黛玉"

elif word == "宝姑娘" or word =="宝钗":

rword ="薛宝钗"

elif word == "凤姐" or word =="凤姐儿":

rword ="王熙凤"

elif word == "老祖宗" or word == "贾母":

rword = "贾母"

elif word == "芙蓉仙子" or word == "病西施":

rword = "晴雯"

elif word == "史大姑娘" or word =="湘云":

rword ="史湘云"

elif word =="惜春"or word == "贾惜春":

rword ="贾惜春"

elif word =="迎春"or word == "贾迎春":

rword ="贾迎春"

else:

rword = word

counts[rword] = counts.get(rword,0) + 1 #词汇加入字典

for word in excludes:

del(counts[word]) #从字典中删除无用词

items = list(counts.items())#字典转换为列表

#lambda是一个隐函数，是固定写法，以下命令的意思就是按照记录的第2列排序

"""x表示列表中的一个元素，x只是临时起的一个名字，

你可以使用任意的名字"""

items.sort(key=lambda x:x[1], reverse=True)

for i in range(20): #出现的词频统计

word, count = items[i] #将键和值分别赋予列表word和count

print ("{0:<10}{1:>5}".format(word, count))#0:<10左对齐，宽度10，”>5"右对齐