复合数据类型，英文词频统计

列表_增加
list = [‘a‘, ‘b‘, 5564, ‘c‘]
 
print ("原始列表 : ", list)
list.append(‘3658‘)
print ("增加元素 : ", list)

列表_删除：
list = [‘a‘, ‘b‘, 5564, ‘c‘]
 
print ("原始列表 : ", list)
del list[2]
print ("删除第三个元素 : ", list)

列表_修改
list = [‘a‘, ‘b‘, 5564, ‘c‘]
 
print ("原始列表 : ", list)
list[2] = ‘d‘
print ("修改第三个元素 : ", list)

列表_查询
list = [‘a‘, ‘b‘, 5564, ‘c‘]
 
print ("原始列表 : ", list)
print ("第三个元素为 : ", list[2])

元组_增加
list1 = (‘a‘, ‘b‘, 5564, ‘c‘)
list2 = (‘d‘, ‘e‘)
print ("原始列表 : ", list1)
list1 += list2
print ("增加后列表 : ", list1)

元组_删除
del list1;
会将整个元组删除。。

元组_修改
元组中的元素值是不允许修改的

元组_查询
list = (‘a‘, ‘b‘, 5564, ‘c‘,‘d‘, ‘e‘)

print ("原始列表 : ", list)

print ("查询第三个元素 : ", list[2])
print ("查询倒数第三个元素 : ", list[-2])
print ("查询第三个到第五个元素 : ", list[2:4])

字典_增加
dict1 = {‘a‘: ‘b‘, ‘c‘: 5564}
dict2 = {‘d‘: ‘e‘ }
 
dict1.update(dict2)
print ("将字典 dict2 加入字典 dict1 : ", dict1)

字典_删除
dict = {‘a‘: ‘b‘, ‘c‘: 5564}

print ("原始字典 dict : ", dict)
del dict[‘a‘] # 删除键 ‘a‘
print ("删除字典 dict 键 ‘a‘ : ", dict)

dict.clear()     # 清空字典
del dict         # 删除字典

字典_修改
dict = {‘a‘: ‘b‘, ‘c‘: 5564}

print ("原始字典 dict : ", dict)
dict[‘a‘] = 1
print ("修改字典 dict 键 ‘a‘ 的值: ", dict)

字典_查询
dict = {‘a‘: ‘b‘, ‘c‘: 5564}

print ("原始字典 dict : ", dict)
print ("查询字典 dict 键 ‘a‘ 的值: ", dict[‘a‘])

集合_增加
JH = {‘a‘, ‘b‘, ‘c‘, 5564}

print ("原始集合 JH : ", JH)
JH.add(‘d‘)
print ("添加‘d’: ", JH)

集合_查询
JH = {‘a‘, ‘b‘, ‘c‘, 5564}

print ("原始集合 JH : ", JH)
print ("查询‘b’: ", ‘b‘ in JH)

XinXi = open(r"..\bd\venv\GeCi\geci.txt",‘r‘,encoding="utf8")
Stop = open(r"..\bd\stops.txt",‘r‘)
stops = Stop.read()
GeCi= XinXi.read()
XinXi.close()
Stop.close()

GeCi_ist = GeCi.replace(‘\n‘, ‘‘).replace(‘,‘, ‘‘).replace(‘(‘, ‘‘).replace(‘)‘, ‘‘).lower().split()
stops1 = stops.replace(‘\n‘, ‘‘).replace(‘,‘, ‘‘).replace(‘"‘, ‘‘).lower().split()
stops2 = stops.replace(‘\n‘, ‘‘).replace(‘,‘, ‘‘).replace(‘"‘, ‘‘).replace("‘", ‘‘).lower().split()
ZiDian = {}

for str in GeCi_ist:
    if str in ZiDian.keys():
        ZiDian[str] = ZiDian[str] + 1
    else:
        ZiDian[str] = 1

del ZiDian["\ufeffi‘m"]

for x in stops2:
    ZiDian.pop(x,"")

for x in stops1:
    ZiDian.pop(x,"")


ZiDian = sorted(ZiDian.items(),key=lambda x:x[1],reverse=True)


for i in ZiDian[0:20]:
    print(i)
import pandas as pd
pd.DataFrame(data=ZiDian).to_csv(r‘C:\Users\14537\Desktop\1234.csv‘, encoding=‘utf-8‘)