【大数据作业二】字符串操作，英文词频统计预处理

作业要求来自：https://edu.cnblogs.com/campus/gzcc/GZCC-16SE2/homework/2646

1.字符串操作：

  • 解析身份证号：生日、性别、出生地等。
  • 凯撒密码编码与解码
  • 网址观察与批量生成

解析身份证号：

 1 ID = input('请输入十八位身份证号码(只限广州市内): ')
 2 if len(ID) == 18:
 3     print("你的身份证号码是 " + ID)
 4 else:
 5     print("错误的身份证号码")
 6 
 7 ID_add = ID[0:4]
 8 ID_area=ID[4:6]
 9 ID_birth = ID[6:14]
10 ID_sex = ID[14:17]
11 ID_check = ID[17]
12 
13 # ID_add是身份证中的区域代码，如果有一个行政区划代码字典，就可以用获取大致地址#
14 
15 year = ID_birth[0:4]
16 moon = ID_birth[4:6]
17 day = ID_birth[6:8]
18 print("生日: " + year + '年' + moon + '月' + day + '日')
19 
20 if ID_area == 16:
21     print('地区：萝岗区')
22 if ID_area == '06':
23     print('地区：天河区')
24 if ID_area == '03':
25     print('地区：荔湾区')
26 if ID_area == '04':
27     print('地区：越秀区')
28 if ID_area == '05':
29     print('地区：海珠区')
30 if ID_area == '07':
31     print('地区：芳村区')
32 if ID_area == 11:
33     print('地区：白云区')
34 if ID_area == 12:
35     print('地区：黄埔区')
36 if ID_area == 13:
37     print('地区：番禺区')
38 if ID_area == 14:
39     print('地区：花都区')
40 if ID_area == 15:
41     print('地区：南沙区')
42 if ID_area == '02':
43     print("地区：东山区")
44 
45 
46 if int(ID_sex) % 2 == 0:
47     print('性别：女')
48 else:
49     print('性别：男')
50 
51 # 此部分应为错误判断，如果错误就不应有上面的输出，如何实现？#
52 W = [7, 9, 10, 5, 8, 4, 2, 1, 6, 3, 7, 9, 10, 5, 8, 4, 2]
53 ID_num = [18, 17, 16, 15, 14, 13, 12, 11, 10, 9, 8, 7, 6, 5, 4, 3, 2]
54 ID_CHECK = ['1', '0', 'X', '9', '8', '7', '6', '5', '4', '3', '2']
55 ID_aXw = 0
56 for i in range(len(W)):
57     ID_aXw = ID_aXw + int(ID[i]) * W[i]
58 
59 ID_Check = ID_aXw % 11
60 if ID_check == ID_CHECK[ID_Check]:
61     print('正确的身份证号码:{}'.format(ID))
62 else:
63     print('错误的身份证号码')
View Code

显示结果：

 

凯撒密码编码与解码：

 1 plaincode=input('')
 2 for i in plaincode:
 3     print(chr(ord(i)+3),end='')
 4 plaincode=input('')
 5 s=ord('a')
 6 t=ord('z')
 7 for i in plaincode:
 8     if s<= ord(i)<=t:
 9         print(chr(s+(ord(i)-s+3)%26), end='')
10     else:
11         print(i,end='')

显示结果：

 

网址观察：

1 #引入第三方库，并用as取别名
2 import  webbrowser as web
3 url='http://news.gzcc.cn/html/xiaoyuanxinwen/'
4 web.open_new_tab(url)
5 for i in range(2,4):
6     web.open_new_tab('http://news.gzcc.cn/html/xiaoyuanxinwen/'+str(i)+'.html')

显示结果：

网址批量生成：

1 for i in range(2,10):
2     url='http://news.gzcc.cn/html/xiaoyuanxinwen/{}.html'.format(i)
3     print(url)

显示结果：

 

2.英文词频统计预处理

  • 下载一首英文的歌词或文章或小说
  • 将所有大写转换为小写
  • 将所有其他做分隔符（,.？！）替换为空格
  • 分隔出一个一个的单词
  • 并统计单词出现的次数。

英文词频统计：

 1 text='''When the bundle was
 2 nestled in her
 3 arms and she moved 
 4 the fold of cloth to look 
 5 upon his tiny face, she gasped. 
 6 The doctor turned quickly 
 7 and looked out the tall 
 8 hospital window. The baby 
 9 had been born without ears.'''
10 print(text.split())
11 print(text.count('the'),text.count('The'))

显示结果：

大小写转换及统计：

 1 text='''When the bundle was
 2 nestled in her
 3 arms and she moved 
 4 the fold of cloth to look 
 5 upon his tiny face, she gasped. 
 6 The doctor turned quickly 
 7 and looked out the tall 
 8 hospital window. The baby 
 9 had been born without ears.'''
10 text=text.lower()
11 sep='.,'
12 for s in sep:
13     text=text.replace(s,' ')
14 print(text.split())
15 print(text.count('the'),text.count('The'))

显示结果：

将文章改成txt模式打开：

1 f = open(r'F:\python\thee.txt','r')
2 text=f.read()
3 print(text)
4 f.close()

显示结果：

posted on 2019-03-04 16:13  makky  阅读(223)  评论(0)  编辑  收藏  举报

导航