python去掉excel重复行

import pandas as pd

#csv

fp = pd.read_csv('D:\\dir\\file.csv')

new_fp = fp.drop_duplicates();

new_fp.to_csv('tmp.csv')

new_fp.to_excel('tmp.xlsx')

 

#excel

import pandas as pd

fp = pd.read_excel('D:\\dir\\file.xlsx', 'Sheet1')

new_fp = fp.drop_duplicates('column_name') #column name of excel Sheet

new_fp.to_excel('D:\\dir\\tmp.xlsx')

new_fp.to_csv('D:\\dir\\tmp.csv')