nupes-elections/nupes/scripts/legislatives2022/import_candidats.py

import csv
import datetime

from sqlalchemy import Engine, select
from sqlalchemy.orm import Session
from tqdm import tqdm

from nupes.cache import get_file
from nupes.models import Genre
from nupes.models.legislatives2022 import BlocLegislatives2022, NuanceLegislatives2022, CandidatLegislatives2022


def creer_blocs(engine: Engine, verbose: bool = False) -> None:
    blocs = [
        {"id": 1, "nom": "Gauche", "couleur": "#BB1840"},
        {"id": 2, "nom": "Droite libérale", "couleur": "#FFEB00"},
        {"id": 3, "nom": "Droite conservatrice", "couleur": "#0066CC"},
        {"id": 4, "nom": "Extrême droite", "couleur": "#404040"},
        {"id": 5, "nom": "Autres", "couleur": "#DCBFA3"}
    ]

    with Session(engine) as session:
        for bloc_dict in blocs:
            if bloc := session.execute(select(BlocLegislatives2022).filter_by(id=bloc_dict["id"])).scalar_one_or_none():
                bloc.nom = bloc_dict["nom"]
                bloc.couleur = bloc_dict["couleur"]
            else:
                session.add(BlocLegislatives2022(**bloc_dict))

        session.commit()


def creer_nuances(engine: Engine, verbose: bool = False) -> None:
    nuances = [
        {"code": "DXG", "nom": "Divers extrême gauche", "couleur": "#BB0000", "bloc_id": 1},
        {"code": "RDG", "nom": "Parti radical de gauche", "couleur": "#FFD1DC", "bloc_id": 1},
        {"code": "NUP", "nom": "Nouvelle union populaire écologique et sociale", "couleur": "#E4032E", "bloc_id": 1},
        {"code": "DVG", "nom": "Divers gauche", "couleur": "#FFC0C0", "bloc_id": 1},
        {"code": "ECO", "nom": "Écologistes", "couleur": "#77FF77", "bloc_id": 5},
        {"code": "DIV", "nom": "Divers", "couleur": "#DCDCDC", "bloc_id": 5},
        {"code": "REG", "nom": "Régionalistes", "couleur": "#DCBFA3", "bloc_id": 5},
        {"code": "ENS", "nom": "Ensemble ! (Majorité présidentielle)", "couleur": "#FFEB00", "bloc_id": 2},
        {"code": "DVC", "nom": "Divers centre", "couleur": "#FAC577", "bloc_id": 2},
        {"code": "UDI", "nom": "Union des Démocrates et Indépendants", "couleur": "#00FFFF", "bloc_id": 3},
        {"code": "LR", "nom": "Les Républicains", "couleur": "#0066CC", "bloc_id": 3},
        {"code": "DVD", "nom": "Divers droite", "couleur": "#26C4EC", "bloc_id": 3},
        {"code": "DSV", "nom": "Droite souverainiste", "couleur": "#8040C0", "bloc_id": 4},
        {"code": "REC", "nom": "Reconquête !", "couleur": "#404040", "bloc_id": 4},
        {"code": "RN", "nom": "Rassemblement national", "couleur": "#0D378A", "bloc_id": 4},
        {"code": "DXD", "nom": "Divers extrême droite", "couleur": "#404040", "bloc_id": 4},
    ]

    with Session(engine) as session:
        for nuance_dict in nuances:
            if nuance := session.execute(select(NuanceLegislatives2022)
                                         .filter_by(code=nuance_dict["code"])).scalar_one_or_none():
                nuance.nom = nuance_dict["nom"]
                nuance.couleur = nuance_dict["couleur"]
                nuance.bloc_id = nuance_dict["bloc_id"]
            else:
                session.add(NuanceLegislatives2022(**nuance_dict))

        session.commit()


def importer_candidats(engine: Engine, verbose: bool = False) -> None:
    DATASET_URL = "https://www.data.gouv.fr/fr/datasets/r/c79af2f3-1733-4df3-be37-caebacbc1321"
    file = get_file(DATASET_URL, "candidats_legislatives_2022.tsv")

    with file.open('r', encoding="ISO-8859-1") as f:
        with Session(engine) as session:
            reader = csv.DictReader(f, delimiter='\t')
            for line in tqdm(reader, desc="Candidat⋅es", disable=not verbose):
                line: dict[str, str]
                numero_panneau = int(line.get("N° panneau"))
                code_dpt = line.get("Code du département")

                match code_dpt:
                    case "ZA":
                        code_dpt = "971"
                    case "ZB":
                        code_dpt = "972"
                    case "ZC":
                        code_dpt = "973"
                    case "ZD":
                        code_dpt = "974"
                    case "ZS":
                        code_dpt = "975"
                    case "ZM":
                        code_dpt = "976"
                    case "ZX":
                        code_dpt = "977"
                    case "ZW":
                        code_dpt = "986"
                    case "ZP":
                        code_dpt = "987"
                    case "ZN":
                        code_dpt = "988"

                code_circo = line.get("Code circonscription")
                circo_id = f"{code_dpt}-{code_circo}"

                nuance_id = line.get("Nuance candidat")
                nuance = session.execute(select(NuanceLegislatives2022).filter_by(code=nuance_id)).scalar_one()

                if candidat := session.execute(select(CandidatLegislatives2022)
                                               .filter_by(circonscription_id=circo_id, numero=numero_panneau)) \
                        .scalar_one_or_none():
                    candidat.nuance_id = line['Nuance candidat']
                    candidat.bloc_id = nuance.bloc_id
                    candidat.nom = line['Nom candidat']
                    candidat.prenom = line['Prénom candidat']
                    candidat.sexe = CandidatLegislatives2022.Genre(line['Sexe candidat'])
                    candidat.date_naissance = datetime.datetime.strptime(line['Date naissance candidat'],
                                                                         "%d/%m/%Y").date()
                    candidat.profession = line['Profession candidat']
                    candidat.sortant = line['Le candidat est sortant'] == "Oui"
                    candidat.nom_suppleance = line['Nom remplaçant']
                    candidat.prenom_suppleance = line['Prénom remplaçant']
                    candidat.sexe_suppleance = CandidatLegislatives2022.Genre(line['Sexe remplaçant'])
                    candidat.date_naissance_suppleance = datetime.datetime.strptime(line['Date naiss. remplaçant'],
                                                                                    "%d/%m/%Y").date()
                    candidat.sortant = line['Le remplaçant est sortant'] == "Oui"
                else:
                    candidat = CandidatLegislatives2022(
                        circonscription_id=circo_id,
                        numero=numero_panneau,
                        nuance_id=nuance_id,
                        bloc_id=nuance.bloc_id,
                        nom=line['Nom candidat'],
                        prenom=line['Prénom candidat'],
                        sexe=Genre(line['Sexe candidat']).name,
                        date_naissance=datetime.datetime.strptime(line['Date naissance candidat'], "%d/%m/%Y").date(),
                        profession=line['Profession candidat'],
                        sortant=line['Le candidat est sortant'] == "Oui",
                        nom_suppleance=line['Nom remplaçant'],
                        prenom_suppleance=line['Prénom remplaçant'],
                        sexe_suppleance=Genre(line['Sexe remplaçant']).name,
                        date_naissance_suppleance=datetime.datetime.strptime(line['Date naiss. remplaçant'],
                                                                             "%d/%m/%Y").date(),
                        sortant_suppleance=line['Le remplaçant est sortant'] == "Oui",
                    )
                    session.add(candidat)

            session.commit()


def run(engine: Engine, verbose: bool = False) -> None:
    creer_blocs(engine, verbose)
    creer_nuances(engine, verbose)
    importer_candidats(engine, verbose)