Adjust model comparison script to correctly process network logs

Correct logic in `compare_models.py` to pass raw network logs to the detection method, ensuring correct feature extraction and preventing a 'timestamp' KeyError.

Replit-Commit-Author: Agent
Replit-Commit-Session-Id: 7a657272-55ba-4a79-9a2e-f1ed9bc7a528
Replit-Commit-Checkpoint-Type: full_checkpoint
Replit-Commit-Event-Id: ecdb452a-13bf-4c0b-8da9-eebbafd63834
Replit-Commit-Screenshot-Url: https://storage.googleapis.com/screenshot-production-us-central1/449cf7c4-c97a-45ae-8234-e5c5b8d6a84f/7a657272-55ba-4a79-9a2e-f1ed9bc7a528/RJGlbTt

attached_assets/Pasted--python-compare-models-py-WARNING-Extended-Isolation-Forest-not-available-using-standard-IF--1764060191039_1764060191039.txt

@@ -0,0 +1,55 @@
+ python compare_models.py
+[WARNING] Extended Isolation Forest not available, using standard IF
+
+================================================================================
+  IDS MODEL COMPARISON - DB Current vs Hybrid Detector v2.0.0
+================================================================================
+
+[1] Caricamento detection esistenti dal database...
+   Trovate 50 detection nel database
+
+[2] Caricamento nuovo Hybrid Detector (v2.0.0)...
+[HYBRID] Ensemble classifier loaded
+[HYBRID] Models loaded (version: latest)
+[HYBRID] Selected features: 18/25
+[HYBRID] Mode: Hybrid (IF + Ensemble)
+   ✅ Hybrid Detector caricato (18 feature selezionate)
+
+[3] Rianalisi di 50 IP con nuovo modello Hybrid...
+   (Questo può richiedere alcuni minuti...)
+
+   [1/50] Analisi IP: 185.203.25.138
+      Current: score=100.0, type=ddos, blocked=False
+Traceback (most recent call last):
+  File "/opt/ids/python_ml/venv/lib64/python3.11/site-packages/pandas/core/indexes/base.py", line 3790, in get_loc
+    return self._engine.get_loc(casted_key)
+           ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
+  File "index.pyx", line 152, in pandas._libs.index.IndexEngine.get_loc
+  File "index.pyx", line 181, in pandas._libs.index.IndexEngine.get_loc
+  File "pandas/_libs/hashtable_class_helper.pxi", line 7080, in pandas._libs.hashtable.PyObjectHashTable.get_item
+  File "pandas/_libs/hashtable_class_helper.pxi", line 7088, in pandas._libs.hashtable.PyObjectHashTable.get_item
+KeyError: 'timestamp'
+
+The above exception was the direct cause of the following exception:
+
+Traceback (most recent call last):
+  File "/opt/ids/python_ml/compare_models.py", line 265, in <module>
+    main()
+  File "/opt/ids/python_ml/compare_models.py", line 184, in main
+    comparison = reanalyze_with_hybrid(detector, ip, old_det)
+                 ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
+  File "/opt/ids/python_ml/compare_models.py", line 118, in reanalyze_with_hybrid
+    result = detector.detect(ip_features)
+             ^^^^^^^^^^^^^^^^^^^^^^^^^^^^
+  File "/opt/ids/python_ml/ml_hybrid_detector.py", line 507, in detect
+    features_df = self.extract_features(logs_df)
+                  ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
+  File "/opt/ids/python_ml/ml_hybrid_detector.py", line 98, in extract_features
+    logs_df['timestamp'] = pd.to_datetime(logs_df['timestamp'])
+                                          ~~~~~~~^^^^^^^^^^^^^
+  File "/opt/ids/python_ml/venv/lib64/python3.11/site-packages/pandas/core/frame.py", line 3893, in __getitem__
+    indexer = self.columns.get_loc(key)
+              ^^^^^^^^^^^^^^^^^^^^^^^^^
+  File "/opt/ids/python_ml/venv/lib64/python3.11/site-packages/pandas/core/indexes/base.py", line 3797, in get_loc
+    raise KeyError(key) from err
+KeyError: 'timestamp'

python_ml/compare_models.py

@@ -105,21 +105,14 @@ def reanalyze_with_hybrid(detector, ip_address, old_detection):
     
     df = pd.DataFrame(logs)
     
-    # Feature extraction (come nel detector)
+    # Il metodo detect() fa già l'extraction delle feature internamente
-    features_df = detector.extract_features(df)
+    # Passiamo direttamente i log grezzi
-    
+    result = detector.detect(df, mode='all')  # mode='all' per vedere tutti i risultati
-    if len(features_df) == 0:
-        return None
-    
-    # Prendi le feature dell'IP aggregato
-    ip_features = features_df.iloc[0:1]
-    
-    # Rianalizza con nuovo modello
-    result = detector.detect(ip_features)
     
     if not result or len(result) == 0:
         return None
     
+    # Il detector raggruppa per source_ip, quindi dovrebbe esserci 1 risultato
     new_detection = result[0]
     
     # Confronto