不管是谁，只要处理过由用户提交的调查数据，就能明白这种乱七八糟的数据是怎么一回事。为了得到一组能用于分析工作的格式统一的字符串，需要做很多事情：去除空白符、删除各种标点符号、正确的大写格式等。做法之一是使用内建的字符串方法和正则表达式re模块：
一般写法
states = [' Alabama ', 'Georgia!', 'Georgia', 'georgia', 'FlOrIda',
'south carolina##', 'West virginia?']
import re
def clean_strings(strings): # 一般对数据的处理步骤
result = []
for value in strings:
value = value.strip()
value = re.sub('[!#?]', '', value)
value = value.title()
result.append(value)
return result
In [173]: clean_strings(states)
Out[173]:
['Alabama',
'Georgia',
'Georgia',
'Georgia',
'Florida',
'South Carolina',
'West Virginia']推荐写法
def remove_punctuation(value):
return re.sub('[!#?]', '', value)
clean_ops = [str.strip, remove_punctuation, str.title] # 函数也是对象
def clean_strings(strings, ops):
result = []
for value in strings:
for function in ops:
value = function(value)
result.append(value)
return result
In [175]: clean_strings(states, clean_ops)
Out[175]:
['Alabama',
'Georgia',
'Georgia',
'Georgia',
'Florida',
'South Carolina',
'West Virginia']
# 或者
In [176]: for x in map(remove_punctuation, states): #
.....: print(x)
Alabama
Georgia
Georgia
georgia
FlOrIda
south carolina
West virginia