6 changed files with 1564 additions and 0 deletions
-
70Colonnes.py
-
16Doublons.py
-
1386Table_final.csv
-
19Values.py
-
69main.py
-
4requirements.txt
@ -0,0 +1,70 @@ |
|||||
|
#Importation des données dont nous aurons besoin |
||||
|
from typing import List |
||||
|
import pandas as pd |
||||
|
import numpy as np |
||||
|
import requests |
||||
|
import csv |
||||
|
import re |
||||
|
|
||||
|
#Afficher les tableaux de données |
||||
|
datafram : pd.read_csv("C:\\Users\\luigg\\Data_cleaning\\Table_final.csv") |
||||
|
datafram.head(5) |
||||
|
|
||||
|
#Supprimer les colonnes inutilisées ou non pertinentes |
||||
|
to_drop : [''identifiant |
||||
|
','adresse |
||||
|
','commune |
||||
|
','coordonnees_x |
||||
|
','coordonnees_y |
||||
|
','code_epsg |
||||
|
','code_ape |
||||
|
','libelle_ape |
||||
|
','code_eprtr |
||||
|
','libelle_eprtr |
||||
|
','sigleUniteLegale_imp |
||||
|
','activitePrincipaleUniteLegale_imp |
||||
|
','Catégorie_entreprise_imp |
||||
|
','numeroVoieEtablissement_imp |
||||
|
','typeVoieEtablissement_imp |
||||
|
','libelleVoieEtablissement_imp |
||||
|
','libelleCommuneEtablissement_imp |
||||
|
','codeCommuneEtablissement_imp |
||||
|
','adresse_imp |
||||
|
','geo_imp |
||||
|
','com_code_imp |
||||
|
','code_commune_imp |
||||
|
','Code Officiel_EPCI_imp |
||||
|
','Code_Officiel_region_imp |
||||
|
','codenaffix_imp |
||||
|
','Intitule_NAF_imp |
||||
|
','groupe_imp |
||||
|
','division_imp |
||||
|
','nom_etablissement_tndan |
||||
|
','code_operation_eliminatio_valorisation_tndan |
||||
|
','libelle_operation_eliminatio_valorisation_tndan |
||||
|
','code_departement_tndan |
||||
|
','pays_tndan |
||||
|
','pays_pdan |
||||
|
','code_dechet_pdan |
||||
|
','libelle_dechet_pdan |
||||
|
','quantite_pdan |
||||
|
','unite_pdan |
||||
|
','code_operation_eliminatio_valorisation_pndan |
||||
|
','libelle_operation_eliminatio_valorisation_pndan |
||||
|
','code_departement_pndan |
||||
|
','pays_pndan |
||||
|
','code_dechet_pndan |
||||
|
','libelle_dechet_pndan |
||||
|
','quantite_pndan |
||||
|
','unite_pndan |
||||
|
','code_operation_eliminatio_valorisation_tdan |
||||
|
','libelle_operation_eliminatio_valorisation_tdan |
||||
|
','code_departement_tdan |
||||
|
','pays_tdan |
||||
|
','code_dechet_tdan |
||||
|
','libelle_dechet_tdan |
||||
|
'] |
||||
|
|
||||
|
datafram.drop(to_drop, inplace = True, axis = 1) |
||||
|
datafram.head(5) |
||||
|
|
||||
@ -0,0 +1,16 @@ |
|||||
|
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) |
||||
1386
Table_final.csv
File diff suppressed because it is too large
View File
File diff suppressed because it is too large
View File
@ -0,0 +1,19 @@ |
|||||
|
import pandas as pd |
||||
|
import numpy as np |
||||
|
import csv |
||||
|
|
||||
|
#Afficher les tableaux de données |
||||
|
table = pd.read_csv("C:\Users\luigg\Data_cleaning\Table_final.csv") |
||||
|
table.head(5) |
||||
|
|
||||
|
#Remplacer les valeurs des lignes |
||||
|
|
||||
|
Replace_values = {0: 'Non', 1: 'Oui'} |
||||
|
|
||||
|
table = table.replace({"engagement_manifeste_imp |
||||
|
","engagement_data_imp |
||||
|
","prelevements_eaux_souterraines_pre |
||||
|
","prelevements_mer_pre |
||||
|
": replace_values}) |
||||
|
|
||||
|
table.head(5) |
||||
@ -0,0 +1,69 @@ |
|||||
|
#Importation des données dont nous aurons besoin |
||||
|
import pandas as pd |
||||
|
import numpy as np |
||||
|
import csv |
||||
|
import re |
||||
|
|
||||
|
#Afficher les tableaux de données |
||||
|
df = pd.read_csv("C:\Users\luigg\Data_cleaning\Table_final.csv") |
||||
|
df.head(5) |
||||
|
|
||||
|
#Supprimer les colonnes inutilisées ou non pertinentes |
||||
|
|
||||
|
to_drop = ['identifiant |
||||
|
','adresse |
||||
|
','commune |
||||
|
','coordonnees_x |
||||
|
','coordonnees_y |
||||
|
','code_epsg |
||||
|
','code_ape |
||||
|
','libelle_ape |
||||
|
','code_eprtr |
||||
|
','libelle_eprtr |
||||
|
','sigleUniteLegale_imp |
||||
|
','activitePrincipaleUniteLegale_imp |
||||
|
','Catégorie_entreprise_imp |
||||
|
','numeroVoieEtablissement_imp |
||||
|
','typeVoieEtablissement_imp |
||||
|
','libelleVoieEtablissement_imp |
||||
|
','libelleCommuneEtablissement_imp |
||||
|
','codeCommuneEtablissement_imp |
||||
|
','adresse_imp |
||||
|
','geo_imp |
||||
|
','com_code_imp |
||||
|
','code_commune_imp |
||||
|
','Code Officiel_EPCI_imp |
||||
|
','Code_Officiel_region_imp |
||||
|
','codenaffix_imp |
||||
|
','Intitule_NAF_imp |
||||
|
','groupe_imp |
||||
|
','division_imp |
||||
|
','nom_etablissement_tndan |
||||
|
','code_operation_eliminatio_valorisation_tndan |
||||
|
','libelle_operation_eliminatio_valorisation_tndan |
||||
|
','code_departement_tndan |
||||
|
','pays_tndan |
||||
|
','pays_pdan |
||||
|
','code_dechet_pdan |
||||
|
','libelle_dechet_pdan |
||||
|
','quantite_pdan |
||||
|
','unite_pdan |
||||
|
','code_operation_eliminatio_valorisation_pndan |
||||
|
','libelle_operation_eliminatio_valorisation_pndan |
||||
|
','code_departement_pndan |
||||
|
','pays_pndan |
||||
|
','code_dechet_pndan |
||||
|
','libelle_dechet_pndan |
||||
|
','quantite_pndan |
||||
|
','unite_pndan |
||||
|
','code_operation_eliminatio_valorisation_tdan |
||||
|
','libelle_operation_eliminatio_valorisation_tdan |
||||
|
','code_departement_tdan |
||||
|
','pays_tdan |
||||
|
','code_dechet_tdan |
||||
|
','libelle_dechet_tdan |
||||
|
'] |
||||
|
|
||||
|
df.drop(to_drop, inplace = True, axis = 1) |
||||
|
df.head(5) |
||||
|
|
||||
@ -0,0 +1,4 @@ |
|||||
|
pandas |
||||
|
numpy |
||||
|
csv |
||||
|
re |
||||
Write
Preview
Loading…
Cancel
Save
Reference in new issue