从零学python系列之数据处理编程实例（二）

在上一节从零学python系列之数据处理编程实例（一）的基础上数据发生了变化，文件中除了学生的成绩外，新增了学生姓名和出生年月的信息，因此将要成变成：分别根据姓名输出每个学生的无重复的前三个最好成绩和出生年月

数据准备：分别建立四个文本文件

james2.txt James Lee,2002-3-14,2-34,3:21,2.34,2.45,3.01,2:01,2:01,3:10,2-22

julie2.txt Julie Jones,2002-8-17,2.59,2.11,2:11,2:23,3-10,2-23,3:10,3.21,3-21

mikey2.txt Mikey McManus,2002-2-24,2:22,3.01,3:01,3.02,3:02,3.02,3:22,2.49,2:38

sarah2.txt Sarah Sweeney,2002-6-17,2:58,2.58,2:39,2-25,2-55,2:54,2.18,2:55,2:55

在上一节基础上，修改部分代码，将新要求实现如下：

复制代码 代码如下:
import os
print(os.getcwd())
os.chdir(C:\Python33\HeadFirstPython\hfpy_code\chapter6) #将工作空间修改为文件所在的目录

#定义函数get_filedata从文件中取值
def get_filedata(filename):
try:
with open(filename) as f: #with语句打开和自动关闭文件
data=f.readline() #从文件中逐行读取字符
data_list=data.strip().split(,) #将字符间的空格清除后，用逗号分隔字符
return({
name : data_list.pop(0),
date_of_birth : data_list.pop(0),
times : str(sorted(set([modify_time_format(s) for s in data_list]))[0:3])
}) #使用字典将关联的姓名，出生年月，时间键和值进行存储并返回
except IOError as ioerr:
print (File Error + str(ioerr)) #异常处理，打印错误
return (None)

#定义函数modify_time_format将所有文件中的时分表达方式统一为“分.秒”
def modify_time_format(time_string):
if - in time_string:
splitter=-
elif : in time_string:
splitter=:
else:
splitter=.
(mins, secs)=time_string.split(splitter) #用分隔符splitter分隔字符后分别存入mins和secs
return (mins+ . +secs)

#定义函数get_prev_three返回文件中排名前三的不重复的时间成绩
def get_prev_three(filename):
new_list=[modify_time_format(each_t) for each_t in get_filedata(filename)] #采用列表推导将统一时分表达方式后的记录生成新的列表
delete_repetition=set(new_list) #采用集合set函数删除新列表中重复项，并生成新的集合
in_order=sorted(delete_repetition) #采用复制排序sorted函数对无重复性的新集合进行排序
return (in_order[0:3])

#输出james的排名前三的不重复成绩和出生年月
james = get_filedata(james2.txt)
print (james[name]+s fastest times are: + james[times])
print (james[name] + s birthday is: + james[date_of_birth])

#输出julie的排名前三的不重复成绩和出生年月
julie = get_filedata(julie2.txt)
print (julie[name]+s fastest times are: + julie[times])
print (julie[name] + s birthday is: + julie[date_of_birth])

#输出mikey的排名前三的不重复成绩和出生年月
mikey = get_filedata(mikey2.txt)
print (mikey[name]+s fastest times are: + mikey[times])
print (mikey[name] + s birthday is: + mikey[date_of_birth])

#输出sarah的排名前三的不重复成绩和出生年月
sarah = get_filedata(sarah2.txt)
print (sarah[name]+s fastest times are: + sarah[times])
print (sarah[name] + s birthday is: + sarah[date_of_birth])

通过建立继承内置list的类AthleteList，将方法定义在类中实现相同功能：

复制代码 代码如下:
import os
print(os.getcwd())
os.chdir(C:\Python33\HeadFirstPython\hfpy_code\chapter6) #将工作空间修改为文件所在的目录

#定义类AthleteList继承python内置的list
class AthleteList(list):
def __init__(self, name, dob=None, times=[]):
list.__init__([])
self.dob=dob
self.extend(times)
def get_prev_three(self):
return (sorted(set([modify_time_format(t) for t in self]))[0:3])

def get_filedata(filename):
try:
with open(filename) as f: #with语句打开和自动关闭文件
data=f.readline() #从文件中逐行读取字符
data_list=data.strip().split(,) #将字符间的空格清除后，用逗号分隔字符
return(
AthleteList(data_list.pop(0), data_list.pop(0), data_list)
) #使用字典将关联的姓名，出生年月，时间键和值进行存储并返回
except IOError as ioerr:
print (File Error + str(ioerr)) #异常处理，打印错误
return (None)

def modify_time_format(time_string):
if - in time_string:
splitter=-
elif : in time_string:
splitter=:
else:
splitter=.
(mins, secs)=time_string.split(splitter) #用分隔符splitter分隔字符后分别存入mins和secs
return (mins+ . +secs)

james = get_filedata(james2.txt)
print (james.name+s fastest times are: + str(james.get_prev_three()))

julie = get_filedata(julie2.txt)
print (julie.name+s fastest times are: + str(julie.get_prev_three()))

mikey = get_filedata(mikey2.txt)
print (mikey.name+s fastest times are: + str(mikey.get_prev_three()))

sarah = get_filedata(sarah2.txt)
print (sarah.name+s fastest times are: + str(sarah.get_prev_three()))