第四次作业——完整的中英文词频统计

fo = open(‘novel.txt‘,‘r‘,encoding=‘utf-8‘) #读取文件
str = fo.read()
fo.close()
print(str)

str = str.lower() #全部转为小写

sep = ‘.,:;?!‘  #删除特殊字符
for a in sep:
    str = str.replace(a,‘ ‘)
print(str)

strlist = str.split() #分割字符
print(len(strlist),strlist)

strset = set(strlist) #将字符转为列表
print(len(strset),strset)

se = {‘a‘,‘the‘,‘and‘,‘we‘,‘you‘,‘of‘,‘si‘,‘s‘,‘ter‘,‘to‘}   #删除无语义词
strsete =strset-se   
print(strsete)

strdict = {}   #单词计数字典
for word in strset:
    strdict[word] = strlist.count(word)
print(len(strdict),strdict)

for word in strset:  #单词计数集合
    strdict[word] = strlist.count(word)
print(len(strdict),strdict)

wordlist = list(strdict.items())
wordlist.sort(key=lambda  x:x[1],reverse=True)     #用lambda函数排序
print(strlist)

for i in range(20):   #输出TOP（20）
    print(wordlist[i])