综合练习：词频统计

Posted 2020-10-28 黄文麒

1.英文词频统

f = open(‘lyric.txt‘,‘r‘)
lyric = f.read()
f.close()
 
 
punctuation = ‘‘‘,.?/:;‘"‘‘‘
a = {‘in‘,‘on‘,‘with‘,‘by‘,‘for‘,‘at‘,‘about‘,‘under‘,‘of‘,‘i‘,‘a‘,‘is‘,‘its‘,‘so‘,‘and‘,‘dont‘,‘it‘,‘to‘,‘ill‘,‘the‘}
for i in punctuation:
    lyric = lyric.replace(i,‘‘)
result = lyric.lower().lstrip().rstrip()
tempwords = result.split()
print(tempwords)
count = {}
words = list(set(tempwords)-a)
 
print(words)
print(result)
 
for i in range(0,len(words)):
    count[words[i]]=result.count(str(words[i]))
    print(‘单词  ‘+ words[i] + ‘ 的出现次数为：‘+str(result.count(words[i])))
 
for i in count:
    print(i)
    print(count[i])
 
countList = list(count.items())
countList.sort(key=lambda x:x[1],reverse=True)
print(countList)
 
f = open(‘lyricCount.txt‘,‘a‘)
for i in range(20):
    f.write(countList[i][0]+‘:‘+str(countList[i][1])+‘\n‘)
f.close()

 

2.中文词频统计

import jieba
 
 
f = open(‘sanguoyanyi.txt‘, ‘r‘,encoding=‘utf-8‘)
text = f.read()
f.close()
 
jieba.add_word(‘曹操‘)
jieba.add_word(‘诸葛亮‘)
jieba.add_word(‘孔明‘)
punctuation = ‘‘‘，。‘’“”：；（）！？、 ‘‘‘
a = {‘的‘,‘\n‘,‘\u3000‘,‘曰‘,‘之‘,‘不‘,‘人‘,‘军‘,‘操‘,‘一‘,‘将‘,
     ‘大‘,‘马‘,‘来‘,‘德‘,‘有‘,‘于‘,‘下‘,‘兵‘,‘此‘,
     ‘玄‘,‘公‘,‘见‘,‘为‘,‘何‘,‘中‘,‘而‘,‘可‘,‘吾‘,
     ‘出‘,‘也‘,‘以‘,‘与‘,‘上‘,‘后‘,‘今‘,‘其‘,‘去‘,
     ‘日‘,‘明‘,‘言‘}
for i in punctuation:
    text = text.replace(i, ‘‘)
print(list(jieba.cut(text)))
tempwords = list(jieba.cut(text))
print(tempwords)
count = {}
words = list(set(tempwords) - a)
print(words)
 
 
for i in range(0, len(words)):
    count[words[i]] = text.count(str(words[i]))
 
 
countList = list(count.items())
countList.sort(key=lambda x: x[1], reverse=True)
print(countList)
 
f = open(‘zzzCount.txt‘, ‘a‘)
for i in range(20):
    f.write(countList[i][0] + ‘:‘ + str(countList[i][1]) + ‘\n‘)
f.close()