Python之pandas学习【9】：利用pandas筛选出CSV某几列的数据进行数据处理

import re

import pandas as pd

import time

class jk_jd():

# 方法1:传统for循环

def solution(self,data):

col = ['x','y'] # 定义要筛选的列

data_del = (data,columns=col) # 提取出要筛选的列，装到dataframe中

for i in range(len(data_del['x'])): # 遍历dataFrame中的每一行，进行正则表达式的匹配处理

data_del['x'][i] = ("<br>(.*)", "", data_del['x'][i]) # 删掉<br>后面的所有数据

data_del['x'][i] = ("【(.*?)】","",data_del['x'][i]) # 删掉【】中的所有数据

data_del.to_csv("") # 导出为CSV文件

# 方法2:pandas的map模块方式

def solution1(self,data):

col = ['x','y']

data_dele = (data,columns=col)

data_dele['x'] = data_dele['x'].map(lambda x:("<br>(.*)", "",("【(.*?)】","",x))\

.replace('\t','').replace('\n','').replace(' ',''))

data_dele.to_csv("")

if __name__ == '__main__':

data = pd.read_excel('')

s = jk_jd()

t1 = ()

data_dele = (data)

print('for循环需要时间: ',()-t1)

t2 = ()

data_dele1 = s.solution1(data)

print('map需要时间: ',()-t2)