综合练习：词频统计

一、英文词频统计

 1 f=open("text.txt","r")
song=f.read()
f.close()
 
sep=''',.?—!"'''
 
exclude={'the','and','i','in',"i'm",'a','of','an','on','to','with'}
 
for c in sep:
    song=song.replace(c,' ')
 
swl=song.lower().split()
 
swd={}
 
sws=set(swl)-exclude
 
for w in sws:
    swd[w]=swl.count(w)
 
fl=list(swd.items())
 
fl.sort(key = lambda x:x[1],reverse = True)
 
for i in fl:
    print(i)
 
f=open("result.txt","w")
for i in range(20):
    f.write(fl[i][0]+"  "+str(fl[i][1])+"
")
f.close()

二、中文词频统计

import jieba
 
f = open('xiyouji.txt','r', encoding='utf-8')
text = f.read()
f.close()
 
 
import jieba
  
#打开文件
file = open("zgsjtl.txt",'r',encoding="utf-8")
notes = file.read();
file.close();
  
#替换标点符号
sep = '''：。，？！；∶ ．．．“”'''
for i in sep:
    notes = notes.replace(i,' ');
  
notes_list = list(jieba.cut(notes));
  
  
 
exclude =[' ','
','你','嗯','他','和','但','啊','的','来','是','去','在','上','走']
  
notes_dict={}
for w in notes_list:
    notes_dict[w] = notes_dict.get(w,0)+1
  
for w in exclude:
    del (notes_dict[w]);
  
for w in notes_dict:
    print(w,notes_dict[w])
  
  
 
dictList = list(notes_dict.items())
dictList.sort(key=lambda x:x[1],reverse=True);
print(dictList)
  
 
for i in range(20):
    print(dictList[i])
 
outfile = open("top20.txt","a")
for i in range(20):
    outfile.write(dictList[i][0]+" "+str(dictList[i][1])+"
")
outfile.close();