Script Python permettant de nettoyer et préparer nos données csv.
You can not select more than 25 topics Topics must start with a letter or number, can include dashes ('-') and can be up to 35 characters long.

16 lines
395 B

import panda as pd
import numpy as np
import csv
import re
#Afficher les tableaux de données
datafram = pd.read_csv(r"C:\Users\luigg\Data_cleaning\Table_final.csv")
datafram.head(5)
#Supprimer les doublons dans excel
nouvelle_table = datafram.drop_duplicates(
subset = ['order_id', 'customer_id'],
keep = 'last').reset_index(drop = True)
#Afficher la nouvelle table
print(nouvelle_table)