app1

app.py

@@ -119,9 +119,6 @@ def load_raw_data() -> pd.DataFrame:
     )
     return pd.read_csv(url, sep=";")
 
-# ────────────────────────────────────────────────
-# 2) FONCTION D’ENTRAÎNEMENT + PRÉDICTIONS
-# ────────────────────────────────────────────────
 
 os.environ["MLFLOW_DEFAULT_ARTIFACT_ROOT"] = os.getenv("MLFLOW_DEFAULT_ARTIFACT_ROOT")  # S3
 os.environ["AWS_ACCESS_KEY_ID"] = os.getenv("AWS_ACCESS_KEY_ID")
@@ -227,118 +224,6 @@ def train_model_and_predict(df_raw: pd.DataFrame) -> pd.DataFrame:
     df_map = df[["latitude", "longitude", "ville"] + list(horizons.values())].copy()
     return df_map
 
-
-
-
-
-
-
-# @st.cache_resource(show_spinner="⚙️ Entraînement du modèle…", ttl=None)
-# def train_model_and_predict(df_raw: pd.DataFrame) -> pd.DataFrame:
-#     """Retourne df_map prêt pour la carte avec les colonnes
-#        proba_7j, proba_30j, …, proba_180j."""
-#     # a) Nettoyage
-#     df = df_raw.copy()
-#     df = df.rename(columns={"Feu prévu": "event", "décompte": "duration"})
-#     df["event"] = df["event"].astype(bool)
-#     df["duration"] = df["duration"].fillna(0)
-
-#     # b) Features
-#     features = [
-#         "moyenne precipitations mois", "moyenne temperature mois",
-#         "moyenne evapotranspiration mois", "moyenne vitesse vent année",
-#         "moyenne vitesse vent mois", "moyenne temperature année",
-#         "RR", "UM", "ETPMON", "TN", "TX", "Nombre de feu par an",
-#         "Nombre de feu par mois", "jours_sans_pluie", "jours_TX_sup_30",
-#         "ETPGRILLE_7j", "compteur jours vers prochain feu",
-#         "compteur feu log", "Année", "Mois",
-#         "moyenne precipitations année", "moyenne evapotranspiration année",
-#     ]
-#     features = [f for f in features if f in df.columns]
-
-#     # c) split + Surv
-#     y_struct = Surv.from_dataframe("event", "duration", df)
-#     X_train, X_test, y_train, y_test = train_test_split(
-#         df[features], y_struct, test_size=0.3, random_state=42
-#     )
-#     ev_train, du_train = y_train["event"], y_train["duration"]
-#     ev_test, du_test = y_test["event"], y_test["duration"]
-
-#     # d) Pipeline XGBSurv
-#     pipe = Pipeline([
-#         ("imputer", SimpleImputer(strategy="median")),
-#         ("scaler", StandardScaler()),
-#         ("xgb", XGBRegressor(
-#             objective="survival:cox",
-#             n_estimators=100,
-#             learning_rate=0.05,
-#             max_depth=3,
-#             tree_method="hist",
-#             random_state=42,
-#         )),
-#     ])
-#     pipe.fit(X_train, du_train, xgb__sample_weight=ev_train)
-
-#     # e) Affiche C-index dans la sidebar
-#     log_hr_test = pipe.predict(X_test)
-#     c_index = concordance_index_censored(ev_test, du_test, log_hr_test)[0]
-#     st.sidebar.write(f"**C-index (test)** : {c_index:.3f}")
-
-#     # f) Estimation du baseline hazard (Cox factice)
-#     df_fake = pd.DataFrame({
-#         "duration": du_train,
-#         "event": ev_train,
-#         "const": 1,
-#     })
-#     dmat = DMatrix(df_fake[["const"]])
-#     dmat.set_float_info("label", df_fake["duration"])
-#     dmat.set_float_info("label_lower_bound", df_fake["duration"])
-#     dmat.set_float_info("label_upper_bound", df_fake["duration"])
-#     dmat.set_float_info("weight", df_fake["event"])
-#     bst_fake = xgb_train(
-#         params={
-#             "objective": "survival:cox",
-#             "eval_metric": "cox-nloglik",
-#             "learning_rate": 0.1,
-#             "max_depth": 1,
-#             "verbosity": 0,
-#         },
-#         dtrain=dmat,
-#         num_boost_round=100,
-#     )
-#     log_hr_fake = bst_fake.predict(dmat)
-
-#     df_risque = pd.DataFrame({
-#         "duration": du_train,
-#         "event": ev_train,
-#         "log_risque": log_hr_fake + np.random.normal(0, 1e-4, size=len(log_hr_fake)),
-#     })
-#     cph = CoxPHFitter()
-#     cph.fit(df_risque, duration_col="duration", event_col="event", show_progress=False)
-
-#     baseline_cumhaz = cph.baseline_cumulative_hazard_
-
-#     def S0(t: int) -> float:
-#         """Survie de base S0(t) = exp(-H0(t))."""
-#         idx = baseline_cumhaz.index
-#         if t in idx:
-#             H0 = baseline_cumhaz.loc[t].values[0]
-#         else:
-#             H0 = baseline_cumhaz.loc[idx[idx <= t]].iloc[-1, 0]
-#         return float(np.exp(-H0))
-
-#     horizons = {7: "proba_7j", 30: "proba_30j", 60: "proba_60j",
-#                 90: "proba_90j", 180: "proba_180j"}
-
-#     log_hr_all = pipe.predict(df[features])
-#     HR = np.exp(log_hr_all)
-
-#     for t, col in horizons.items():
-#         df[col] = 1 - (S0(t) ** HR)   # P(event ≤ t)
-
-#     df_map = df[["latitude", "longitude", "ville"] + list(horizons.values())].copy()
-#     return df_map
-
 # ─────────────────────────────────────────��──────
 # 3) AFFICHAGE SUR LA PAGE « Accueil »
 # ────────────────────────────────────────────────