Delete old useless function

src/1-processing.py

-import pandas as pd
-import os
-import pyproj
-
-def lambert93_to_wgs84(x, y):
-    """Convertit des coordonnées Lambert 93 en latitude et longitude WGS 84."""
-    try:
-        x, y = float(x), float(y)
-        transformer = pyproj.Transformer.from_crs("EPSG:2154", "EPSG:4326", always_xy=True)
-        lon, lat = transformer.transform(x, y)
-        return lat, lon
-    except ValueError:
-        return None, None
-
-def charger_donnees(date):
-    """Charge et nettoie les données UDI_RES et UDI_PLV."""
-    file_path_res = f"data/raw/UDI_RES_{date}.txt"
-    file_path_plv = f"data/raw/UDI_PLV_{date}.txt"
-    
-    if not os.path.exists(file_path_res) or not os.path.exists(file_path_plv):
-        print(f"Fichiers manquants pour {date}, passage...")
-        return False
-    
-    # Chargement des données UDI_RES
-    columns_res = [
-        "cddept", "referenceprel", "cdparametre", "rsana", "cdunitereferencesiseeaux", "cdunitereference", "rqana",
-        "rssigne", "representativite"
-    ]
-    data_res = pd.read_csv(file_path_res, sep=",", dtype=str)
-    data_res = data_res[columns_res].copy()
-    
-    # Conversion des valeurs numériques de rqana
-    data_res['rqana'] = pd.to_numeric(data_res['rqana'].str.extract(r'(\d+)', expand=False), errors='coerce')
-    
-    output_res = f"data/processed/res{date}.csv"
-    data_res.to_csv(output_res, index=False)
-    
-    # Chargement des données UDI_PLV
-    columns_plv = [
-        "cddept", "inseecommune", "nomcommune", "cdreseau", "cdpointsurv", "nompointsurv",
-        "referenceprel", "dateprel", "finaliteprel", "conclusionprel", "cdtypeeau",
-        "plvconformitebacterio", "plvconformitechimique", "plvconformiterefbacterio",
-        "plvconformiterefchimique", "coord_x", "coord_y"
-    ]
-    data_plv = pd.read_csv(file_path_plv, sep=",", dtype=str)
-    data_plv = data_plv[columns_plv].copy()
-    
-    # Conversion des coordonnées
-    data_plv[['coord_x', 'coord_y']] = data_plv.apply(
-        lambda row: lambert93_to_wgs84(row['coord_x'], row['coord_y']),
-        axis=1, result_type='expand'
-    )
-    
-    output_plv = f"data/processed/plv{date}.csv"
-    data_plv.to_csv(output_plv, index=False)
-    
-    return True
-
-def jointure(date):
-    """Jointure des fichiers RES et PLV."""
-    res_path = f"data/processed/res{date}.csv"
-    plv_path = f"data/processed/plv{date}.csv"
-    
-    if not os.path.exists(res_path) or not os.path.exists(plv_path):
-        print(f"Fichiers intermédiaires manquants pour {date}, passage...")
-        return False
-    
-    data_res = pd.read_csv(res_path, dtype=str)
-    data_plv = pd.read_csv(plv_path, dtype=str)
-    
-    # Vérification des références avant la jointure
-    data_res['referenceprel'] = data_res['referenceprel'].astype(str).str.strip()
-    data_plv['referenceprel'] = data_plv['referenceprel'].astype(str).str.strip()
-    
-    data = pd.merge(data_res, data_plv, on="referenceprel", how="outer", indicator=True)
-    
-    print(data["_merge"].value_counts())
-    
-    output_path = f"data/processed/Table{date}.csv"
-    data.drop(columns=['_merge'], inplace=True)
-    data.to_csv(output_path, index=False)
-    
-    return True
-
-def supprimer_donnees(date):
-    """Supprime les fichiers temporaires uniquement si la jointure a réussi."""
-    table_path = f"data/processed/Table{date}.csv"
-    if os.path.exists(table_path):
-        os.remove(f"data/processed/res{date}.csv")
-        os.remove(f"data/processed/plv{date}.csv")
-
-dates = ["20240" + str(i) for i in range(1, 10)] + ["2024" + str(i) for i in range(10, 13)]
-processed_dates = []
-
-for date in dates:
-    print(f"Processing data for {date}")
-    if charger_donnees(date):
-        if jointure(date):
-            supprimer_donnees(date)
-            processed_dates.append(date)
-            print(f"Data for {date} processed")
-        else:
-            print(f"Jointure échouée pour {date}")
-    else:
-        print(f"Chargement échoué pour {date}")
-
-def jointure_finale():
-    """Concatène toutes les tables intermédiaires en une seule table finale."""
-    paths = [f"data/processed/Table{date}.csv" for date in processed_dates]
-    valid_paths = [path for path in paths if os.path.exists(path)]
-    
-    if not valid_paths:
-        print("Aucun fichier de jointure valide, fin du processus.")
-        return
-    
-    data = pd.concat([pd.read_csv(path, dtype=str) for path in valid_paths], ignore_index=True)
-    data.to_csv("data/processed/Table2024.csv", index=False)
-    print("Table finale sauvegardée.")
-
-jointure_finale()
\ No newline at end of file