a.alfocea
/
Itchy_and_Scratchy
1
0
Fork 0
Code Issues Pull Requests Projects Releases Wiki Activity
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.
6 Commits
1 Branch
0 Tags
13 MiB
Tree: bde7b26cc8
Branches Tags
${ item.name }
Create tag ${ searchTerm }
Create branch ${ searchTerm }
from 'bde7b26cc8'
${ noResults }
Itchy_and_Scratchy/Code_Python/Traitements_donnees.py

112 lines
6.7 KiB
Raw Normal View History

Transférer les fichiers vers 'Code_Python'
2 years ago
​
​
​
​
​
​
​
​
​
​
​
​
​
​
​
​
​
​
​
​
​
​
​
​
​
​
​
​
​
​
​
​
​
​
​
​
​
​
​
​
​
​
​
​
​
​
​
​
​
​
​
​
​
​
​
​
​
​
​
​
​
​
​
​
​
​
​
​
​
​
​
​
​
​
​
​
​
​
​
​
​
​
​
​
​
​
​
​
​
​
​
​
​
​
​
​
​
​
​
​
​
​
​
​
​
​
​
​
​
​
​
  1. # IMPORTS
  2. import pandas as pd
  4. # Georisque
  6. emission = pd.read_csv("C:/Oumayma/PSB M2/S9/SCRUM/bdd/1. Installations industrielles rejetant des polluants/emissions.csv",error_bad_lines=False, sep=";")
  7. etablissements = pd.read_csv("C:/Oumayma/PSB M2/S9/SCRUM/bdd/1. Installations industrielles rejetant des polluants/etablissements.csv",error_bad_lines=False, sep=";")
  8. Prelevements = pd.read_csv("C:/Oumayma/PSB M2/S9/SCRUM/bdd/1. Installations industrielles rejetant des polluants/Prelevements.csv",error_bad_lines=False, sep=";")
  9. 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=";")
  10. 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=";")
  11. 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=";")
  12. 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=";")
  14. # On retire la modalité tota pour le dioxyde de carbone car somme l'ensemble de dioxyde
  15. emission2 = emission.loc[emission['polluant'] != "Dioxyde de carbone (CO2) total (d'origine biomasse et non biomasse)"]
  18. # on garde uniquement les variables necessaires
  19. emission_v = emission2.drop(emission2.columns[[1, 2, 4]], axis=1)
  20. # pas besoin de faire de group by pour la table prelevements
  21. Prelevements_v = Prelevements.drop(Prelevements.columns[[1,2]], axis=1)
  22. Prod_dechets_dangereux_v = Prod_dechets_dangereux.drop(Prod_dechets_dangereux.iloc[:,1:10],1)
  23. Prod_dechets_non_dangereux_v = Prod_dechets_non_dangereux.drop(Prod_dechets_non_dangereux.iloc[:,1:10],1)
  24. Trait_dechets_dangereux_v = Prod_dechets_non_dangereux.drop(Prod_dechets_non_dangereux.iloc[:,1:10],1)
  25. Trait_dechets_non_dangereux_v = Trait_dechets_non_dangereux.drop(Trait_dechets_non_dangereux.iloc[:,1:11],1)
  27. # Rename des variables pour differencier les differentes quantites
  28. emission_v2 = emission_v.rename(columns={'milieu': 'milieu1', 'quantite': 'quantite1'})
  29. Prod_dechets_dangereux_v2 = Prod_dechets_dangereux_v.rename(columns={'quantite': 'quantite_prod_dang'})
  30. Prod_dechets_non_dangereux_v2 = Prod_dechets_non_dangereux_v.rename(columns={'quantite': 'quantite_prod_non_dang'})
  31. Trait_dechets_dangereux_v2 = Trait_dechets_dangereux_v.rename(columns={'quantite': 'quantite_trait_dang'})
  32. Trait_dechets_non_dangereux_v2 = Trait_dechets_non_dangereux_v.rename(columns={'quantite_traitee': 'quantite_trait_non_dang'})
  35. # group by pour n'avoir qu'une ligne par identifiant et milieu
  36. emission_g = emission_v2.groupby(['identifiant', 'milieu1'], as_index=False).sum()
  37. Prod_dechets_dangereux_g = Prod_dechets_dangereux_v2.groupby(['identifiant'], as_index=False).sum()
  38. Prod_dechets_non_dangereux_g = Prod_dechets_non_dangereux_v2.groupby(['identifiant'], as_index=False).sum()
  39. Trait_dechets_dangereux_g = Trait_dechets_dangereux_v2.groupby(['identifiant'], as_index=False).sum()
  40. Trait_dechets_non_dangereux_g = Trait_dechets_non_dangereux_v2.groupby(['identifiant'], as_index=False).sum()
  42. # Transformation de la table emission pour passer d'une ligne par identifiant et une colonne par milieu
  43. emission_g.loc[emission_g['milieu1'] == 'Air', 'qte_air'] = emission_g['quantite1']
  44. emission_g.loc[emission_g['milieu1'] == 'Sol', 'qte_sol'] = emission_g['quantite1']
  45. emission_g.loc[emission_g['milieu1'] == 'Eau (direct)', 'qte_eau_d'] = emission_g['quantite1']
  46. emission_g.loc[emission_g['milieu1'] == 'Eau (indirect)', 'qte_eau_i'] = emission_g['quantite1']
  48. emission_2 = emission_g.drop(columns=["milieu1", "quantite1"])
  49. emission_g2 = emission_2.groupby(['identifiant'], as_index=False).sum()
  52. # on met l'identifiant en str
  54. etablissements['identifiant'] = etablissements['identifiant'].apply(str)
  55. emission_g2['identifiant'] = emission_g2['identifiant'].apply(str)
  56. Prelevements_v['identifiant'] = Prelevements_v['identifiant'].apply(str)
  57. Prod_dechets_dangereux_g['identifiant'] = Prod_dechets_dangereux_g['identifiant'].apply(str)
  58. Prod_dechets_non_dangereux_g['identifiant'] = Prod_dechets_non_dangereux_g['identifiant'].apply(str)
  59. Trait_dechets_dangereux_g['identifiant'] = Trait_dechets_dangereux_g['identifiant'].apply(str)
  60. Trait_dechets_non_dangereux_g['identifiant'] = Trait_dechets_non_dangereux_g['identifiant'].apply(str)
  62. #Traitement du code postal sur 5 caractères
  63. etablissements['code_postal'] = etablissements['code_postal'].apply(lambda x : str(x).zfill(5))
  66. # Merge
  67. merge1 = etablissements.merge(emission_g2, how='left', on='identifiant')
  68. merge2 = merge1.merge(Prelevements_v, how='left', on='identifiant')
  69. merge3 = merge2.merge(Prod_dechets_dangereux_g, how='left', on='identifiant')
  70. merge4 = merge3.merge(Prod_dechets_non_dangereux_g, how='left', on='identifiant')
  71. merge5 = merge4.merge(Trait_dechets_dangereux_g, how='left', on='identifiant')
  72. merge6 = merge5.merge(Trait_dechets_non_dangereux_g, how='left', on='identifiant')
  76. # verif
  77. emission_g2.info()
  78. emission.describe()
  80. etablissements.info()
  81. etablissements.describe()
  83. Prelevements_v.info()
  84. Prelevements_v.describe()
  86. Prod_dechets_dangereux_g.info()
  87. Prod_dechets_dangereux_g.describe()
  89. Prod_dechets_non_dangereux_g.info()
  90. Prod_dechets_non_dangereux_g.describe()
  92. Trait_dechets_dangereux_g.info()
  93. Trait_dechets_dangereux_g.describe()
  95. Trait_dechets_non_dangereux_g.info()
  96. Trait_dechets_non_dangereux_g.describe()
  98. # Export
  100. emission_g2.to_csv("C:/Oumayma/PSB M2/S9/SCRUM/bdd/1. Installations industrielles rejetant des polluants/emission_final.csv")
  101. etablissements.to_csv("C:/Oumayma/PSB M2/S9/SCRUM/bdd/1. Installations industrielles rejetant des polluants/etablissement_final.csv")
  102. Prelevements_v.to_csv("C:/Oumayma/PSB M2/S9/SCRUM/bdd/1. Installations industrielles rejetant des polluants/Prelevement_final.csv")
  103. Prod_dechets_dangereux_g.to_csv("C:/Oumayma/PSB M2/S9/SCRUM/bdd/1. Installations industrielles rejetant des polluants/Prod_dangereux_final.csv")
  104. 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")
  105. Trait_dechets_dangereux_g.to_csv("C:/Oumayma/PSB M2/S9/SCRUM/bdd/1. Installations industrielles rejetant des polluants/Trait_dechets_dangereux_g.csv")
  106. 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")
  108. merge6.to_csv("C:/Oumayma/PSB M2/S9/SCRUM/bdd/bdd_final.csv")