feat: Benchmark de performance baseline - 2.62s/doc moyen, 92% dans objectif

tools/show_batch_summary.py

@@ -0,0 +1,85 @@
+#!/usr/bin/env python3
+"""
+Affiche un résumé des résultats du batch d'anonymisation.
+"""
+import json
+import sys
+from pathlib import Path
+from collections import Counter
+
+def show_summary():
+    """Affiche le résumé du batch."""
+    
+    baseline_dir = Path("tests/ground_truth/pdfs/baseline_anonymized")
+    results_file = baseline_dir / "batch_results.json"
+    
+    if not results_file.exists():
+        print(f"✗ Fichier de résultats non trouvé: {results_file}")
+        return 1
+    
+    with open(results_file, 'r', encoding='utf-8') as f:
+        data = json.load(f)
+    
+    # Statistiques globales
+    print("="*80)
+    print("RÉSUMÉ DU BATCH D'ANONYMISATION")
+    print("="*80)
+    
+    print(f"\n📅 Date: {data['date']}")
+    print(f"📄 Documents traités: {data['success_count']}/{data['total_documents']}")
+    print(f"🔍 PII détectés: {data['total_pii']:,}")
+    print(f"⏱️  Temps total: {data['total_time_s']:.2f}s")
+    print(f"⏱️  Temps moyen: {data['avg_time_s']:.2f}s par document")
+    
+    # Analyser les résultats
+    successful = [r for r in data['results'] if r.get('success')]
+    failed = [r for r in data['results'] if not r.get('success')]
+    
+    if successful:
+        times = [r['time_s'] for r in successful]
+        pii_counts = [r['pii_count'] for r in successful]
+        
+        print(f"\n📊 Statistiques de temps:")
+        print(f"   - Min: {min(times):.2f}s")
+        print(f"   - Max: {max(times):.2f}s")
+        print(f"   - Médiane: {sorted(times)[len(times)//2]:.2f}s")
+        
+        print(f"\n📊 Statistiques de PII:")
+        print(f"   - Min: {min(pii_counts)}")
+        print(f"   - Max: {max(pii_counts):,}")
+        print(f"   - Médiane: {sorted(pii_counts)[len(pii_counts)//2]}")
+        print(f"   - Moyenne: {sum(pii_counts)/len(pii_counts):.1f}")
+    
+    # Top 5 documents les plus complexes
+    if successful:
+        print(f"\n🏆 Top 5 documents les plus complexes (par PII):")
+        top5 = sorted(successful, key=lambda x: x['pii_count'], reverse=True)[:5]
+        for i, r in enumerate(top5, 1):
+            print(f"   {i}. {r['pdf']}")
+            print(f"      → {r['pii_count']:,} PII en {r['time_s']:.2f}s")
+    
+    # Top 5 documents les plus rapides
+    if successful:
+        print(f"\n⚡ Top 5 documents les plus rapides:")
+        fastest = sorted(successful, key=lambda x: x['time_s'])[:5]
+        for i, r in enumerate(fastest, 1):
+            print(f"   {i}. {r['pdf']}")
+            print(f"      → {r['time_s']:.2f}s ({r['pii_count']} PII)")
+    
+    # Échecs
+    if failed:
+        print(f"\n⚠️  Échecs ({len(failed)}):")
+        for r in failed:
+            error = r.get('error', 'Unknown error')
+            if not error:
+                error = "PDF protégé par mot de passe"
+            print(f"   - {r['pdf']}")
+            print(f"     → {error}")
+    
+    print("\n" + "="*80)
+    
+    return 0
+
+
+if __name__ == "__main__":
+    sys.exit(show_summary())