python3txt删除高频低频词_【基础】练习册10-Python3_高频词统计

#《三国演义》前60回中的高频词统计

import jieba

import os

#1 调取文本，并分词

#os系统设置文件地址可读权限

path1= os.path.expanduser(r"~/Documents/python_project/Auxiliary file/sanguo_60.txt")

article1=open(path1).read()    #读出txt

words=jieba.lcut(article1)

#stopwords用来排除单词的文本

path2= os.path.expanduser(r"~/Documents/python_project/Auxiliary file/stopwords.txt")

stopwords=[line.strip() for line in open(path2,'r').readlines()]

#2 计算

word_freq={}

for word in words:

if (word in stopwords) or len(word)==1:

continue

#同类单词合并

elif word=='孔明' or word=='孔明曰' or word=='诸葛亮':

newword='孔明'

elif word=='曹操' or word=='孟德' or word=='丞相' or word=='主公':

newwordword='曹操'

elif word=='刘备' or word=='玄德' or word=='玄德曰' or word=='大耳儿' or word=='先主':

newword='刘备'

elif word=='云长' or word=='关公' or word=='关羽':

newword='关羽'

elif word=='张飞' or word=='翼德':

newword='张飞'

elif word=='赵云' or word=='子龙':

newword='赵云'

elif word=='后主' or word=='刘禅' or word=='阿斗':

newword='刘禅'

else:

newword=word

# word_freq[word]=word_freq.get(word,0)+1

if newword in word_freq:

word_freq[newword]+=1

else:

word_freq[word]=1

#3： 排序

'''freq_word=[]123

for word,freq in word_freq.items():

freq_word.append((word,freq))'''

freq_word= list(word_freq.items())

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

#4：输入和显示

max_num=eval(input("请输入显示前多少位高频词: "))

for word,freq in freq_word[:max_num]:

print(word,freq)