import pandas as pd
import csv
#替换列名,格式: ’原列名’:’新列名’,
colName = {
}
#按列筛选
def save_columns_to(src_file, mid_file, columns=None):
df = pd.read_csv(src_file)
df[columns].to_csv(mid_file, index=None)
#更换列名
def changeColName(mid_file,columns):
all_data = pd.read_csv(mid_file,encoding='ANSI') #csv问价为ANSI格式,UTF-8可能会乱码
columns = all_data.columns
all_data.rename(columns=lambda x: colName.get(x, x), inplace = True)
all_data.to_csv(mid_file,encoding='ANSI')
#按行属性筛选
def selectRow(mid_file,dst_file):
with open(mid_file, 'r', newline='') as csv_in_file:
with open(dst_file, 'w', newline='') as csv_out_file:
filereader = csv.reader(csv_in_file)
filewriter = csv.writer(csv_out_file)
header = next(filereader)#读取第一行列名
filewriter.writerow(header)
for row_list in filereader:
supplier = str(row_list[3]).strip()#0为第一列,3为第四列
if supplier == '':#筛选条件
filewriter.writerow(row_list)
if __name__ == '__main__':
src_file=r''#待处理文件
mid_file=r''#提取出指定列的文件
dst_file=r''#在指定列的文件的基础上进行筛选的文件,需要提前创建
columns = []#需要提取的列
save_columns_to(src_file, mid_file, columns)
changeColName(mid_file,columns)
selectRow(mid_file,dst_file)
01-06
9930
![](https://csdnimg.cn/release/blogv2/dist/pc/img/readCountWhite.png)
07-28
7893
![](https://csdnimg.cn/release/blogv2/dist/pc/img/readCountWhite.png)
05-21
“相关推荐”对你有帮助么?
-
非常没帮助
-
没帮助
-
一般
-
有帮助
-
非常有帮助
提交