字符串、文件操作和英文词频统计预处理

这个作业的要求来自于：https://edu.cnblogs.com/campus/gzcc/GZCC-16SE2/homework/2620。

1.字符串操作：

• 解析身份证号：生日、性别、出生地等。

   代码如下：

# -*- coding: utf-8 -*-
"""
Spyder Editor

This is a temporary script file.
"""
ID = input('请输入十八位身份证号码: ')
if len(ID) == 18:
    print("你的身份证号码是 " + ID)
else:
    print("错误的身份证号码")

ID_add = ID[0:6]
ID_birth = ID[6:14]
ID_sex = ID[14:17]
ID_check = ID[17]

# 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#

year = ID_birth[0:4]
moon = ID_birth[4:6]
day = ID_birth[6:8]
print("生日: " + year + '年' + moon + '月' + day + '日')

if int(ID_sex) % 2 == 0:
    print('性别：女')
else:
    print('性别：男')

# 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？#
W = [7, 9, 10, 5, 8, 4, 2, 1, 6, 3, 7, 9, 10, 5, 8, 4, 2]
ID_num = [18, 17, 16, 15, 14, 13, 12, 11, 10, 9, 8, 7, 6, 5, 4, 3, 2]
ID_CHECK = ['1', '0', 'X', '9', '8', '7', '6', '5', '4', '3', '2']
ID_aXw = 0
for i in range(len(W)):
    ID_aXw = ID_aXw + int(ID[i]) * W[i]

   运行结果如下图：

• 凯撒密码编码与解码

   凯撒加密法，或称恺撒加密、恺撒变换、变换加密，是一种最简单且最广为人知的加密技术。它是一种替换加密的技术，明文中的所有字母都在字母表上向后（或向前）按照一个固定数目进行偏移后被替换成密文。

   代码如下：

def change(c,i):
    c = c.lower()
    num = ord(c)
    if num >= 97 and num <= 122:
        num = 97 + ((num - 97) + i) % 26
    return chr(num)


def kaisa_jiami(string,i):
    string_new = ''
    for s in string:
        string_new += change(s,i)
    print(string_new)
    return string_new

def kaisa_jiemi(string):
    for i in range(25):
        print('\n', i, '\n')
        i += 1
        kaisa_jiami(string,i)


def main():
    print('请选择需要的操作：')
    print('1：凯撒加密')
    print('2：凯撒解密')
    choice = input()
    if choice == '1':
        string = input('请输入需要加密的字符串：')
        num = int(input('请输入需要偏移的位数：'))
        kaisa_jiami(string,num)
    elif choice == '2':
        string = input('请输入需要解密的字符串：')
        kaisa_jiemi(string)
    else:
        print('输入错误，请重试！')
        main()

if __name__ == '__main__':
    main()

   运行结果如下图：

  

• 网址观察与批量生成

       代码如下：

import urllib.request

url="https://blog.csdn.net/qq_33160790"
req=urllib.request.Request(url)
resp=urllib.request.urlopen(req)
data=resp.read().decode('utf-8')

print(data)

   运行结果如下图：

---

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，保存为utf8文件。
• 从文件读出字符串。
• 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。

      代码如下：

article ='''
Big data analytics and business analytics
by Duan, Lian; Xiong, Ye
Over the past few decades, with the development of automatic identification, data capture and storage technologies, 
people generate data much faster and collect data much bigger than ever before in business, science, engineering, education and other areas. 
Big data has emerged as an important area of study for both practitioners and researchers. 
It has huge impacts on data-related problems. 
In this paper, we identify the key issues related to big data analytics and then investigate its applications specifically related to business problems.
'''

split = article.split()
print(split)

#使用空格替换标点符号
article = article.replace(",","").replace(".","").replace(":","").replace(";","").replace("?","")


#大写字母转换成小写字母
exchange = article.lower();
print(exchange)

#生成单词列表
list = exchange.split()
print(list)

#生成词频统计
dic = {}
for i in list:
    count = list.count(i)
    dic[i] = count
print(dic)

#排除特定单词
word = {'and','the','with','in','by','its','for','of','an','to'}
for i in word:
    del(dic[i])
print(dic)

#排序
dic1= sorted(dic.items(),key=lambda d:d[1],reverse= True)
print(dic1)

#输出词频最大的前十位单词
for i in range(10):
    print(dic1[i])

   运行结果如下图：

---

3.文件操作

• 同一目录下相对路径。

   首先在同一目录下创建 123.txt 文件，代码和运行结果如下图：

• 绝对路径。

   首先在D盘文件夹 PythonPractise 下创建 record.txt 文件：

   代码和运行结果如下图：

---