复合数据类型，英文词频统计

#列表
list=[‘Hello‘,‘World‘]
print(list)
#增加
list.append(‘!‘)
print(list)
list.insert(1,"My")
print(list)
#删除
list.pop(1)
print(list)
#修改
list[1]=‘Python‘
print(list)
#查找
print(list[1])
#遍历
for i in list:
    print(i)

#元组
tup=(‘Hello‘, ‘World‘)
print(tup)
#查找
print(tup[1])
#遍历
for i in tup:
    print(i)

#字典
dict={‘Panda‘:12,‘Dog‘:20}
print(dict)

#增加
dict[‘Cat‘]=16
print(dict)
#删除
dict.pop("Cat")
print(dict)
#修改
dict[‘Dog‘]=12
print(dict)
#查找
print("Dog:",dict[‘Dog‘])
#遍历
for i in dict:
    print(i)

#集合
set={"Baidu","TaoBao"}
print(set)
#增加
set.add("YaHu")
print(set)
#删除
set.remove("YaHu")
print(set)
#遍历
for i in set:
    print(i)

import pandas as pd
import stopwords

stopwords=stopwords.get_stopwords(‘english‘)
f=open("Crimes and Punishments.txt","r",encoding="utf-8")
str=f.read()
f.close()
remove="，,—-。？.()?!‘’"
str=str.lower()
dict={}
for i in remove:
    str=str.replace(i," ")
list=str.split()
for word in list:
    if word not in stopwords:
        dict[word]=list.count(word)
d=sorted(dict.items(), reverse=True, key=lambda d:d[1])
for l in range(20):
    print(d[l][0],"--",d[l][1])
pd.DataFrame(data=d).to_csv(‘words.csv‘,encoding=‘utf-8‘)