样例数据
Sarah Sweeney,2002-6-17,2:58,2.58,2:39,2-25,2-55,2:54,2.18,2:55,2:55,2:22,2-21,2.22
需要将数据整理，实现人名+出生日期+成绩的输出
以往的做法是：
def sanitize(time_string):
if '-' in time_string:
splitter = '-'
elif ':' in time_string:
splitter = ':'
else:
return(time_string)
(mins, secs) = time_string.split(splitter)
return(mins + '.' + secs)
def get_coach_data(filename):
try:
with open(filename) as f:
data = f.readline()
return(data.strip().split(','))
except IOError as ioerr:
print('File error: ' + str(ioerr))
return(None)
sarah = get_coach_data('sarah2.txt')
(sarah_name, sarah_dob) = sarah.pop(0), sarah.pop(0)
print(sarah_name + "'s fastest times are: " +
str(sorted(set([sanitize(t) for t in sarah]))[0:3]))
这次加入了字典的做法
字典将数据值与键关联：
key --> value
Name "sarah sweeney"
DOB "2002-6-17"
Times "[2:58,2.58,2:39,2-25,2-55,2:54,2.18,2:55,2:55,2:22,2-21,2.22]"
创建字典的方式可以是
cleese = {} #大括号！！
也可以是
palin = dict()
关联key和value的话是
cleese['Name'] = 'John Cleese' # 一个key 对应一个字符串
或者
cleese['Name'] = ['John Cleese','John Cleese1','John Cleese2','John Cleese3','John Cleese4'] #一个key对应一个list
或者
cleese = {'Name':'abc','Address':'asdasdasda'} #注意是用冒号
另外数据值与key关联后，需要访问数据值里面的某个数据项的话，可以是
cleese['Name'][-1]
类似多维数组使用。
代码改为
#!/usr/bin/python
# -*- coding: utf-8 -*-
def sanitize(time_string):
if '-' in time_string:
splitter = '-'
elif ':' in time_string:
splitter = ':'
else:
return(time_string)
(mins,secs) = time_string.split(splitter)
return (mins + '.' + secs)
def get_coach_data(filename):
try:
with open(filename) as f:
data = f.readline()
return(data.strip().split(','))
except IOError as ioerr:
print('File error:' + str(ioerr))
return(None)
sarah = get_coach_data('sarah2.txt')
sarah_data={}
sarah_data['Name'] = sarah.pop(0) #根据数据结构，第一个数据是名字，第二个是生日，第二个之后是成绩，所以分别将相关数据赋值到字典里面。
sarah_data['DOB'] = sarah.pop(0)
sarah_data['Times'] = sarah
print(sarah_data['Name'] + "'s fastest times are: " + str(sorted(set([sanitize(t) for t in sarah_data['Times']]))[0:3]))
字典的方法优势在于合理使用数据结构。是否知道何时使用列表而何时使用字典，这正式从好的程序员中区分出优秀程序员的一个标准。
字典其实也叫“映射”，“散列”，“关联数组”
为了更加方便的处理多个人的成绩的数据，所以将字典数据转移到函数里面去，直接通过函数生成出字典，并返回需要的数据
#!/usr/bin/python
# -*- coding: utf-8 -*-
def sanitize(time_string):
if '-' in time_string:
splitter = '-'
elif ':' in time_string:
splitter = ':'
else:
return(time_string)
(mins,secs) = time_string.split(splitter)
return (mins + '.' + secs)
def get_coach_data(filename):
try:
with open(filename) as f:
data = f.readline()
templ = data.strip().split(',')
return({'Name':templ.pop(0), #这里就是字典
'DOB':templ.pop(0),
'Times':str(sorted(set([sanitize(t) for t in templ]))[0:3])})
except IOError as ioerr:
print('File error:' + str(ioerr))
return(None)
sarah = get_coach_data('sarah2.txt')
james = get_coach_data('james2.txt')
print(sarah['Name'] + "'s fastest times are: " + sarah['Times'])
这就是将代码和数据打包在一起。特定函数应用特定数据。
更加正规的做法是建立类。
类是面向对象oop编程模型的东西，类的概念在这里不详细描述。
类可以
1.降低复杂性
2.方便维护和扩展
python的类需要有一个self参数，这个参数是用来标识是属于哪个对象实例的
例如：
class Athlete:
def __init__(self,value=0):
self.thing = value #定义这个类的属性thing
def how_big(self) #定义一个方法how_big
return(len(self.thing))
btw：init 是类的python固定实现方法，所以是必须的。
你写的代码 --> python执行的代码
d = Athlete("Holy Grail") Athlete.__init__(d,"Holy Grail")
| | |
类 方法 目标标识符
| | |
d.how_big() Athlete.how_big(d)
代码改为：
def sanitize(time_string):
if '-' in time_string:
splitter = '-'
elif ':' in time_string:
splitter = ':'
else:
return(time_string)
(mins, secs) = time_string.split(splitter)
return(mins + '.' + secs)
class Athlete:
def __init__(self, a_name, a_dob=None, a_times=[]):
self.name = a_name #通过类的属性来定义name，dob和times
self.dob = a_dob
self.times = a_times
def top3(self):
return(sorted(set([sanitize(t) for t in self.times]))[0:3])
def get_coach_data(filename):
try:
with open(filename) as f:
data = f.readline()
templ = data.strip().split(',')
return(Athlete(templ.pop(0), templ.pop(0), templ))
except IOError as ioerr:
print('File error: ' + str(ioerr))
return(None)
james = get_coach_data('james2.txt')
julie = get_coach_data('julie2.txt')
mikey = get_coach_data('mikey2.txt')
sarah = get_coach_data('sarah2.txt')
print(james.name + "'s fastest times are: " + str(james.top3()))
print(julie.name + "'s fastest times are: " + str(julie.top3()))
print(mikey.name + "'s fastest times are: " + str(mikey.top3()))
print(sarah.name + "'s fastest times are: " + str(sarah.top3()))
科普：
1.通过在各个对象的属性中保留原始数据，可以支持类扩展来满足将来的其他需求。如果处理数据并作为对象初始化代码的一部分，说明你已对程序员将如何使用这个类做出了假设，而日后这些假设肯定会对你造成障碍。
在类里面增加一个灵活的增加成绩数据的函数
可以是增加单个成绩，或是增加多个成绩
单个成绩用add_time，传入的是字符串
多个成绩是add_times，传入的是list
以下是单个成绩的样例：
#!/usr/bin/python
# -*- coding: utf-8 -*-
class Athlete:
def __init__(self,a_name,a_dob=None,a_times=[]):
self.name = a_name
self.dob = a_dob
self.times = a_times
def add_time(self,time_value): #这里就是了。
self.times.append(time_value)
def top3(self):
return (sorted(set([sanitize(t) for t in self.times]))[0:15])
def add_times(self,list_of_times):
self.times.extend(list_of_times)
def sanitize(time_string):
if '-' in time_string:
splitter = '-'
elif ':' in time_string:
splitter = ':'
else:
return(time_string)
(mins,secs) = time_string.split(splitter)
return (mins + '.' + secs)
def get_coach_data(filename):
try:
with open(filename) as f:
data = f.readline()
templ = data.strip().split(',')
return (Athlete(templ.pop(0),templ.pop(0),templ))
except IOError as ioerr:
print('File error:' + str(ioerr))
return(None)
sarah = get_coach_data('sarah2.txt')
sarah.add_time('2.88') #这里调用
print(sarah.name + "'s fastest times are: " + str(sarah.top3())) #输出结果会改变
观察到这个类有点像list，所以有重复制造车轮的嫌疑，并且功能单一，所以决定集成list类
def sanitize(time_string):
if '-' in time_string:
splitter = '-'
elif ':' in time_string:
splitter = ':'
else:
return(time_string)
(mins, secs) = time_string.split(splitter)
return(mins + '.' + secs)
class AthleteList(list): #继续list类，所以这里要写list的名字
def __init__(self, a_name, a_dob=None, a_times=[]):
list.__init__([]) #这里需要初始化list类
self.name = a_name
self.dob = a_dob
self.extend(a_times) #因为集成list类了，所以这里可以直接使用list的extend方法
def top3(self):
return(sorted(set([sanitize(t) for t in self]))[0:3])
def get_coach_data(filename):
try:
with open(filename) as f:
data = f.readline()
templ = data.strip().split(',')
return(AthleteList(templ.pop(0), templ.pop(0), templ))
except IOError as ioerr:
print('File error: ' + str(ioerr))
return(None)
james = get_coach_data('james2.txt')
julie = get_coach_data('julie2.txt')
mikey = get_coach_data('mikey2.txt')
sarah = get_coach_data('sarah2.txt')
print(james.name + "'s fastest times are: " + str(james.top3()))
print(julie.name + "'s fastest times are: " + str(julie.top3()))
print(mikey.name + "'s fastest times are: " + str(mikey.top3()))
print(sarah.name + "'s fastest times are: " + str(sarah.top3()))
原文引用：http://www.godblessyuan.com/2015/05/03/head_first_python_chapter_6_learning/
