a.alfocea
/
Itchy_and_Scratchy
1
0
Fork 0
Code Issues Pull Requests Projects Releases Wiki Activity
Browse Source

Transférer les fichiers vers 'Code_Python'

master
o.messous 3 years ago
parent
454597f270
commit
bde7b26cc8
1 changed files with 112 additions and 0 deletions
Whitespace
Show all changes Ignore whitespace when comparing lines Ignore changes in amount of whitespace Ignore changes in whitespace at EOL
Unified View
Diff Options
Show Stats Download Patch File Download Diff File
  1. 112
      Code_Python/Traitements_donnees.py

112
Code_Python/Traitements_donnees.py
View File

@ -0,0 +1,112 @@
# IMPORTS
import pandas as pd
# Georisque
emission = pd.read_csv("C:/Oumayma/PSB M2/S9/SCRUM/bdd/1. Installations industrielles rejetant des polluants/emissions.csv",error_bad_lines=False, sep=";")
etablissements = pd.read_csv("C:/Oumayma/PSB M2/S9/SCRUM/bdd/1. Installations industrielles rejetant des polluants/etablissements.csv",error_bad_lines=False, sep=";")
Prelevements = pd.read_csv("C:/Oumayma/PSB M2/S9/SCRUM/bdd/1. Installations industrielles rejetant des polluants/Prelevements.csv",error_bad_lines=False, sep=";")
Prod_dechets_dangereux = pd.read_csv("C:/Oumayma/PSB M2/S9/SCRUM/bdd/1. Installations industrielles rejetant des polluants/Prod_dechets_dangereux.csv",error_bad_lines=False, sep=";")
Prod_dechets_non_dangereux = pd.read_csv("C:/Oumayma/PSB M2/S9/SCRUM/bdd/1. Installations industrielles rejetant des polluants/Prod_dechets_non_dangereux.csv",error_bad_lines=False, sep=";")
Trait_dechets_dangereux = pd.read_csv("C:/Oumayma/PSB M2/S9/SCRUM/bdd/1. Installations industrielles rejetant des polluants/Trait_dechets_dangereux.csv",error_bad_lines=False, sep=";")
Trait_dechets_non_dangereux = pd.read_csv("C:/Oumayma/PSB M2/S9/SCRUM/bdd/1. Installations industrielles rejetant des polluants/Trait_dechets_non_dangereux.csv",error_bad_lines=False, sep=";")
# On retire la modalité tota pour le dioxyde de carbone car somme l'ensemble de dioxyde
emission2 = emission.loc[emission['polluant'] != "Dioxyde de carbone (CO2) total (d'origine biomasse et non biomasse)"]
# on garde uniquement les variables necessaires
emission_v = emission2.drop(emission2.columns[[1, 2, 4]], axis=1)
# pas besoin de faire de group by pour la table prelevements
Prelevements_v = Prelevements.drop(Prelevements.columns[[1,2]], axis=1)
Prod_dechets_dangereux_v = Prod_dechets_dangereux.drop(Prod_dechets_dangereux.iloc[:,1:10],1)
Prod_dechets_non_dangereux_v = Prod_dechets_non_dangereux.drop(Prod_dechets_non_dangereux.iloc[:,1:10],1)
Trait_dechets_dangereux_v = Prod_dechets_non_dangereux.drop(Prod_dechets_non_dangereux.iloc[:,1:10],1)
Trait_dechets_non_dangereux_v = Trait_dechets_non_dangereux.drop(Trait_dechets_non_dangereux.iloc[:,1:11],1)
# Rename des variables pour differencier les differentes quantites
emission_v2 = emission_v.rename(columns={'milieu': 'milieu1', 'quantite': 'quantite1'})
Prod_dechets_dangereux_v2 = Prod_dechets_dangereux_v.rename(columns={'quantite': 'quantite_prod_dang'})
Prod_dechets_non_dangereux_v2 = Prod_dechets_non_dangereux_v.rename(columns={'quantite': 'quantite_prod_non_dang'})
Trait_dechets_dangereux_v2 = Trait_dechets_dangereux_v.rename(columns={'quantite': 'quantite_trait_dang'})
Trait_dechets_non_dangereux_v2 = Trait_dechets_non_dangereux_v.rename(columns={'quantite_traitee': 'quantite_trait_non_dang'})
# group by pour n'avoir qu'une ligne par identifiant et milieu
emission_g = emission_v2.groupby(['identifiant', 'milieu1'], as_index=False).sum()
Prod_dechets_dangereux_g = Prod_dechets_dangereux_v2.groupby(['identifiant'], as_index=False).sum()
Prod_dechets_non_dangereux_g = Prod_dechets_non_dangereux_v2.groupby(['identifiant'], as_index=False).sum()
Trait_dechets_dangereux_g = Trait_dechets_dangereux_v2.groupby(['identifiant'], as_index=False).sum()
Trait_dechets_non_dangereux_g = Trait_dechets_non_dangereux_v2.groupby(['identifiant'], as_index=False).sum()
# Transformation de la table emission pour passer d'une ligne par identifiant et une colonne par milieu
emission_g.loc[emission_g['milieu1'] == 'Air', 'qte_air'] = emission_g['quantite1']
emission_g.loc[emission_g['milieu1'] == 'Sol', 'qte_sol'] = emission_g['quantite1']
emission_g.loc[emission_g['milieu1'] == 'Eau (direct)', 'qte_eau_d'] = emission_g['quantite1']
emission_g.loc[emission_g['milieu1'] == 'Eau (indirect)', 'qte_eau_i'] = emission_g['quantite1']
emission_2 = emission_g.drop(columns=["milieu1", "quantite1"])
emission_g2 = emission_2.groupby(['identifiant'], as_index=False).sum()
# on met l'identifiant en str
etablissements['identifiant'] = etablissements['identifiant'].apply(str)
emission_g2['identifiant'] = emission_g2['identifiant'].apply(str)
Prelevements_v['identifiant'] = Prelevements_v['identifiant'].apply(str)
Prod_dechets_dangereux_g['identifiant'] = Prod_dechets_dangereux_g['identifiant'].apply(str)
Prod_dechets_non_dangereux_g['identifiant'] = Prod_dechets_non_dangereux_g['identifiant'].apply(str)
Trait_dechets_dangereux_g['identifiant'] = Trait_dechets_dangereux_g['identifiant'].apply(str)
Trait_dechets_non_dangereux_g['identifiant'] = Trait_dechets_non_dangereux_g['identifiant'].apply(str)
#Traitement du code postal sur 5 caractères
etablissements['code_postal'] = etablissements['code_postal'].apply(lambda x : str(x).zfill(5))
# Merge
merge1 = etablissements.merge(emission_g2, how='left', on='identifiant')
merge2 = merge1.merge(Prelevements_v, how='left', on='identifiant')
merge3 = merge2.merge(Prod_dechets_dangereux_g, how='left', on='identifiant')
merge4 = merge3.merge(Prod_dechets_non_dangereux_g, how='left', on='identifiant')
merge5 = merge4.merge(Trait_dechets_dangereux_g, how='left', on='identifiant')
merge6 = merge5.merge(Trait_dechets_non_dangereux_g, how='left', on='identifiant')
# verif
emission_g2.info()
emission.describe()
etablissements.info()
etablissements.describe()
Prelevements_v.info()
Prelevements_v.describe()
Prod_dechets_dangereux_g.info()
Prod_dechets_dangereux_g.describe()
Prod_dechets_non_dangereux_g.info()
Prod_dechets_non_dangereux_g.describe()
Trait_dechets_dangereux_g.info()
Trait_dechets_dangereux_g.describe()
Trait_dechets_non_dangereux_g.info()
Trait_dechets_non_dangereux_g.describe()
# Export
emission_g2.to_csv("C:/Oumayma/PSB M2/S9/SCRUM/bdd/1. Installations industrielles rejetant des polluants/emission_final.csv")
etablissements.to_csv("C:/Oumayma/PSB M2/S9/SCRUM/bdd/1. Installations industrielles rejetant des polluants/etablissement_final.csv")
Prelevements_v.to_csv("C:/Oumayma/PSB M2/S9/SCRUM/bdd/1. Installations industrielles rejetant des polluants/Prelevement_final.csv")
Prod_dechets_dangereux_g.to_csv("C:/Oumayma/PSB M2/S9/SCRUM/bdd/1. Installations industrielles rejetant des polluants/Prod_dangereux_final.csv")
Prod_dechets_non_dangereux_g.to_csv("C:/Oumayma/PSB M2/S9/SCRUM/bdd/1. Installations industrielles rejetant des polluants/Prod_non_dangereux_final.csv")
Trait_dechets_dangereux_g.to_csv("C:/Oumayma/PSB M2/S9/SCRUM/bdd/1. Installations industrielles rejetant des polluants/Trait_dechets_dangereux_g.csv")
Trait_dechets_non_dangereux_g.to_csv("C:/Oumayma/PSB M2/S9/SCRUM/bdd/1. Installations industrielles rejetant des polluants/Trait_non_dangereux_final.csv")
merge6.to_csv("C:/Oumayma/PSB M2/S9/SCRUM/bdd/bdd_final.csv")
Write Preview
Loading…
Cancel
Save