Data Analysis学习笔记 --- python数据清洗矢量处理字符串

# -*- coding=utf-8 -*-import numpy as npimport pandas as pdimport re#vectorizationdata = pd.Series({'li':'[e-mail]', 'wang':'[e-mail]', 'chen':'[e-mail]', 'zhao':'[e-mail]', 'sun':'[e-mail]'})print(data)#containsprint(data.str.contains('0'))#get need stringdata = pd.Series({'li':'[e-mail]', 'wang':'[e-mail]', 'chen':'[e-mail]', 'zhao':'[e-mail]', 'sun':'[e-mail]'})pattern = re.compile(r'(\d*)@([a-z]+)\.([a-z]{2,4})')result = data.str.match(pattern)print(result)#get pre_emailprint(result.str.get(0))#get email donameprint(result.str.get(1))

结果：