Initial commit

archive/old_scripts/read_pkl.py

@@ -0,0 +1,144 @@
+#!/usr/bin/env python3
+"""
+Script pour lire et afficher le contenu des fichiers .pkl (signatures).
+"""
+
+import sys
+import pickle
+import json
+from pathlib import Path
+import numpy as np
+
+
+def read_pkl_file(pkl_path: Path):
+    """Lit et affiche le contenu d'un fichier .pkl."""
+    print(f"\n{'='*60}")
+    print(f"📄 Fichier: {pkl_path.name}")
+    print(f"{'='*60}")
+    
+    try:
+        with open(pkl_path, 'rb') as f:
+            data = pickle.load(f)
+        
+        if isinstance(data, list):
+            print(f"\n📊 Type: Liste de {len(data)} éléments\n")
+            
+            for i, item in enumerate(data, 1):
+                print(f"--- Action {i} ---")
+                
+                if isinstance(item, dict):
+                    for key, value in item.items():
+                        # Afficher différemment selon le type
+                        if key == 'embedding' and isinstance(value, np.ndarray):
+                            print(f"  {key}: numpy array shape {value.shape}, dtype {value.dtype}")
+                            print(f"    Premiers éléments: {value[:5]}")
+                        elif key == 'screenshot' and value is not None:
+                            if isinstance(value, np.ndarray):
+                                print(f"  {key}: numpy array shape {value.shape}")
+                            else:
+                                print(f"  {key}: {type(value).__name__}")
+                        elif key == 'bbox' and isinstance(value, (list, tuple)):
+                            print(f"  {key}: {value}")
+                        elif isinstance(value, (str, int, float, bool)):
+                            print(f"  {key}: {value}")
+                        elif value is None:
+                            print(f"  {key}: None")
+                        else:
+                            print(f"  {key}: {type(value).__name__}")
+                else:
+                    print(f"  {item}")
+                
+                print()
+        
+        elif isinstance(data, dict):
+            print(f"\n📊 Type: Dictionnaire avec {len(data)} clés\n")
+            
+            for key, value in data.items():
+                if isinstance(value, np.ndarray):
+                    print(f"  {key}: numpy array shape {value.shape}")
+                elif isinstance(value, (list, dict)):
+                    print(f"  {key}: {type(value).__name__} ({len(value)} éléments)")
+                else:
+                    print(f"  {key}: {value}")
+        
+        else:
+            print(f"\n📊 Type: {type(data).__name__}")
+            print(f"\n{data}")
+    
+    except Exception as e:
+        print(f"\n❌ Erreur lors de la lecture: {e}")
+        import traceback
+        traceback.print_exc()
+
+
+def main():
+    """Fonction principale."""
+    if len(sys.argv) < 2:
+        print("Usage: python3 read_pkl.py <fichier.pkl>")
+        print("\nOu pour lire une tâche spécifique:")
+        print("python3 read_pkl.py task_fc1d3e52")
+        print("\nOu pour lister toutes les tâches:")
+        print("python3 read_pkl.py --list")
+        return
+    
+    arg = sys.argv[1]
+    
+    if arg == "--list":
+        # Lister toutes les tâches
+        profiles_dir = Path("geniusia2/data/user_profiles")
+        task_dirs = sorted([d for d in profiles_dir.iterdir() if d.is_dir() and d.name.startswith("task_")])
+        
+        print(f"\n📋 Tâches disponibles ({len(task_dirs)}):\n")
+        
+        for i, task_dir in enumerate(task_dirs, 1):
+            metadata_file = task_dir / "metadata.json"
+            signatures_file = task_dir / "signatures.pkl"
+            
+            if metadata_file.exists():
+                with open(metadata_file, 'r') as f:
+                    metadata = json.load(f)
+                task_name = metadata.get('task_name', 'N/A')
+                obs_count = metadata.get('observation_count', 0)
+            else:
+                task_name = "N/A"
+                obs_count = 0
+            
+            has_sig = "✅" if signatures_file.exists() else "❌"
+            
+            print(f"{i:3d}. {task_dir.name}")
+            print(f"     Nom: {task_name}")
+            print(f"     Observations: {obs_count}")
+            print(f"     Signatures: {has_sig}")
+            print()
+        
+        return
+    
+    # Déterminer le chemin du fichier
+    if arg.startswith("task_"):
+        # C'est un ID de tâche
+        pkl_path = Path(f"geniusia2/data/user_profiles/{arg}/signatures.pkl")
+        
+        # Afficher aussi les métadonnées
+        metadata_path = Path(f"geniusia2/data/user_profiles/{arg}/metadata.json")
+        if metadata_path.exists():
+            print(f"\n{'='*60}")
+            print(f"📋 Métadonnées de {arg}")
+            print(f"{'='*60}\n")
+            
+            with open(metadata_path, 'r') as f:
+                metadata = json.load(f)
+            
+            print(json.dumps(metadata, indent=2, ensure_ascii=False))
+    else:
+        # C'est un chemin de fichier
+        pkl_path = Path(arg)
+    
+    if not pkl_path.exists():
+        print(f"❌ Fichier non trouvé: {pkl_path}")
+        return
+    
+    read_pkl_file(pkl_path)
+
+
+if __name__ == "__main__":
+    main()