feat(supervisor): all

src/agents/l3_classifier.py

@@ -2,48 +2,55 @@ import joblib
 from fastapi import HTTPException
 
 class Classifier:
-    def __init__(self, model_path: str = "src/models/new_l3.joblib"):
+    def __init__(self, model_path: str = "src/models/l2_XGBOOST_Supervisor_V5.joblib"):
         try:
             saved = joblib.load(model_path)
             self.model = saved["model"]
-            self.scaler = saved.get("scaler", None)
-            self.features = saved.get("features", None)
+            self.scaler = saved.get("scaler", None)  # certains modèles peuvent ne pas avoir de scaler
+            self.features = [
+                "Header_Length",
+                "Time_To_Live",
+                "Rate",
+                "Tot sum",
+                "Tot size",
+                "Min",
+                "Max",
+                "AVG",
+                "Std",
+                "Variance",
+                "IAT",
+                "Number",
+                "syn_ratio",
+                "ack_ratio",
+                "fin_ratio",
+                "rst_ratio",
+                "mean_pkt_size",
+                "pkt_size_range",
+                "pkt_size_ratio",
+                "mean_iat",
+                "pkt_rate",
+                "throughput",
+                "bytes_per_sec",
+                "coef_var",
+                "tcp_udp_ratio",
+                "flag_entropy",
+            ]
         except FileNotFoundError:
             raise HTTPException(status_code=500, detail=f"Modèle '{model_path}' introuvable")
         except Exception as e:
             raise HTTPException(status_code=500, detail=f"Erreur lors du chargement du modèle: {e}")
 
-        def predict(self, data):
-            try:
-                if self.features is None:
-                    raise HTTPException(status_code=500, detail="Liste des features du modèle introuvable")
-
-                # Sélectionner uniquement les features utilisées lors de l'entraînement
-                X = data[self.features]
-
-                # Standardisation si scaler présent
-                if self.scaler is not None:
-                    X = self.scaler.transform(X)
-
-                # Prédictions
-                preds = self.model.predict(X)
-                return preds.tolist()
-            except KeyError as e:
-                raise HTTPException(status_code=500, detail=f"Colonne manquante dans les données: {e}")
-            except Exception as e:
-                raise HTTPException(status_code=500, detail=f"Erreur lors de la prédiction: {e}")
-
-    # def predict(self, data):
-    #     try:
-    #         # Préparer les features
-    #         X = data[self.features]
+    def predict(self, data):
+        try:
+            # Préparer les features
+            X = data[self.features]
 
-    #         # Standardisation si scaler présent
-    #         if self.scaler is not None:
-    #             X = self.scaler.transform(X)
+            # Appliquer le scaler si existant
+            if self.scaler is not None:
+                X = self.scaler.transform(X)
 
-    #         # Prédictions
-    #         preds = self.model.predict(X)
-    #         return preds.tolist()
-    #     except Exception as e:
-    #         raise HTTPException(status_code=500, detail=f"Erreur lors de la prédiction: {e}")
+            # Prédictions
+            preds = self.model.predict(X)
+            return preds.tolist()
+        except Exception as e:
+            raise HTTPException(status_code=500, detail=f"Erreur lors de la prédiction: {e}")

src/models/{new_l3.joblib → l2_XGBOOST_Supervisor_V5.joblib}

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:512720ca01cca3fb1fb7477ebd5eb373df1b679a76a7ed45640aa22489261f56
-size 16758
+oid sha256:c8caea236ddbefbb6c23910847204d2020a5be9209ce52be0da4f00ad2e49239
+size 8368

src/services/report.py

@@ -37,3 +37,4 @@ def summarize_predictions(pred_func: Callable, data) -> Dict:
         "normal_ratio": normal_ratio,
         "predictions": predictions
     }
+