- Sélection et copie de 27 documents représentatifs (10 simples, 12 moyens, 5 complexes) - Outil d'annotation CLI complet (tools/annotation_tool.py) - Guide d'annotation détaillé (docs/annotation_guide.md) - Évaluateur de qualité (evaluation/quality_evaluator.py) * Calcul Précision, Rappel, F1-Score * Identification faux positifs/négatifs * Métriques par type de PII * Export JSON et rapports texte - Scanner de fuite (evaluation/leak_scanner.py) * Détection PII résiduels (CRITIQUE) * Détection nouveaux PII (HAUTE) * Scan métadonnées PDF (MOYENNE) - Benchmark de performance (evaluation/benchmark.py) * Mesure temps de traitement * Mesure CPU/RAM * Export JSON/CSV - Tests unitaires complets pour tous les composants - Documentation complète du module d'évaluation Tâches complétées: - 1.1.1 Sélection de 27 documents (au lieu de 30) - 1.1.2 Outil d'annotation CLI - 1.2.1 Évaluateur de qualité - 1.2.2 Scanner de fuite - 1.2.3 Benchmark de performance Prochaines étapes: - 1.1.3 Annotation des 27 documents (manuel) - 1.1.4 Enrichissement stopwords médicaux - 1.3 Mesure de la baseline
299 lines
11 KiB
JSON
299 lines
11 KiB
JSON
[
|
|
{
|
|
"id": 1,
|
|
"dest_filename": "001_simple_unknown_BACTERIO_23018396.pdf",
|
|
"original_path": "/home/dom/Téléchargements/II-1 Ctrl_T2A_2025_CHCB_DocJustificatifs (1)/148_23018396/BACTERIO 23018396.pdf",
|
|
"folder": "148_23018396",
|
|
"original_filename": "BACTERIO 23018396.pdf",
|
|
"type": "unknown",
|
|
"complexity": "simple",
|
|
"pages": 1,
|
|
"size_mb": 0.04
|
|
},
|
|
{
|
|
"id": 2,
|
|
"dest_filename": "002_simple_unknown_bacterio_476_23159413.pdf",
|
|
"original_path": "/home/dom/Téléchargements/II-1 Ctrl_T2A_2025_CHCB_DocJustificatifs (1)/476_23159413/bacterio 476_23159413.pdf",
|
|
"folder": "476_23159413",
|
|
"original_filename": "bacterio 476_23159413.pdf",
|
|
"type": "unknown",
|
|
"complexity": "simple",
|
|
"pages": 2,
|
|
"size_mb": 0.04
|
|
},
|
|
{
|
|
"id": 3,
|
|
"dest_filename": "003_simple_compte_rendu_CRO_23155084.pdf",
|
|
"original_path": "/home/dom/Téléchargements/II-1 Ctrl_T2A_2025_CHCB_DocJustificatifs (1)/210_23155084/CRO 23155084.pdf",
|
|
"folder": "210_23155084",
|
|
"original_filename": "CRO 23155084.pdf",
|
|
"type": "compte_rendu",
|
|
"complexity": "simple",
|
|
"pages": 1,
|
|
"size_mb": 0.05
|
|
},
|
|
{
|
|
"id": 4,
|
|
"dest_filename": "004_simple_anapath_anapath_53_23224186.redacted_raster.pdf",
|
|
"original_path": "/home/dom/Téléchargements/II-1 Ctrl_T2A_2025_CHCB_DocJustificatifs (1)/anonymise/anapath 53_23224186.redacted_raster.pdf",
|
|
"folder": "anonymise",
|
|
"original_filename": "anapath 53_23224186.redacted_raster.pdf",
|
|
"type": "anapath",
|
|
"complexity": "simple",
|
|
"pages": 1,
|
|
"size_mb": 0.29
|
|
},
|
|
{
|
|
"id": 5,
|
|
"dest_filename": "005_simple_compte_rendu_CRH_23155836.pdf",
|
|
"original_path": "/home/dom/Téléchargements/II-1 Ctrl_T2A_2025_CHCB_DocJustificatifs (1)/212_23155836/CRH 23155836.pdf",
|
|
"folder": "212_23155836",
|
|
"original_filename": "CRH 23155836.pdf",
|
|
"type": "compte_rendu",
|
|
"complexity": "simple",
|
|
"pages": 2,
|
|
"size_mb": 0.14
|
|
},
|
|
{
|
|
"id": 6,
|
|
"dest_filename": "006_simple_anapath_ANAPATH_23142660.pdf",
|
|
"original_path": "/home/dom/Téléchargements/II-1 Ctrl_T2A_2025_CHCB_DocJustificatifs (1)/204_23142660/ANAPATH 23142660.pdf",
|
|
"folder": "204_23142660",
|
|
"original_filename": "ANAPATH 23142660.pdf",
|
|
"type": "anapath",
|
|
"complexity": "simple",
|
|
"pages": 0,
|
|
"size_mb": 0.16
|
|
},
|
|
{
|
|
"id": 7,
|
|
"dest_filename": "007_simple_anapath_ANAPATH_23096332.pdf",
|
|
"original_path": "/home/dom/Téléchargements/II-1 Ctrl_T2A_2025_CHCB_DocJustificatifs (1)/15_23096332/ANAPATH 23096332.pdf",
|
|
"folder": "15_23096332",
|
|
"original_filename": "ANAPATH 23096332.pdf",
|
|
"type": "anapath",
|
|
"complexity": "simple",
|
|
"pages": 1,
|
|
"size_mb": 0.16
|
|
},
|
|
{
|
|
"id": 8,
|
|
"dest_filename": "008_simple_trackare_trackare-14004105-23202435_14004105_23202435.pdf",
|
|
"original_path": "/home/dom/Téléchargements/II-1 Ctrl_T2A_2025_CHCB_DocJustificatifs (1)/80_23202435/trackare-14004105-23202435_14004105_23202435.pdf",
|
|
"folder": "80_23202435",
|
|
"original_filename": "trackare-14004105-23202435_14004105_23202435.pdf",
|
|
"type": "trackare",
|
|
"complexity": "simple",
|
|
"pages": 1,
|
|
"size_mb": 0.11
|
|
},
|
|
{
|
|
"id": 9,
|
|
"dest_filename": "009_simple_compte_rendu_CRO_23051225.pdf",
|
|
"original_path": "/home/dom/Téléchargements/II-1 Ctrl_T2A_2025_CHCB_DocJustificatifs (1)/138_23051225/CRO 23051225.pdf",
|
|
"folder": "138_23051225",
|
|
"original_filename": "CRO 23051225.pdf",
|
|
"type": "compte_rendu",
|
|
"complexity": "simple",
|
|
"pages": 2,
|
|
"size_mb": 0.06
|
|
},
|
|
{
|
|
"id": 10,
|
|
"dest_filename": "010_simple_anapath_ANAPATH_23217289.pdf",
|
|
"original_path": "/home/dom/Téléchargements/II-1 Ctrl_T2A_2025_CHCB_DocJustificatifs (1)/49_23217289/ANAPATH 23217289.pdf",
|
|
"folder": "49_23217289",
|
|
"original_filename": "ANAPATH 23217289.pdf",
|
|
"type": "anapath",
|
|
"complexity": "simple",
|
|
"pages": 1,
|
|
"size_mb": 0.17
|
|
},
|
|
{
|
|
"id": 11,
|
|
"dest_filename": "011_moyen_compte_rendu_CRH_23080179.pdf",
|
|
"original_path": "/home/dom/Téléchargements/II-1 Ctrl_T2A_2025_CHCB_DocJustificatifs (1)/132_23080179/CRH 23080179.pdf",
|
|
"folder": "132_23080179",
|
|
"original_filename": "CRH 23080179.pdf",
|
|
"type": "compte_rendu",
|
|
"complexity": "moyen",
|
|
"pages": 4,
|
|
"size_mb": 0.07
|
|
},
|
|
{
|
|
"id": 12,
|
|
"dest_filename": "012_moyen_compte_rendu_CRH_692_23200418.pdf",
|
|
"original_path": "/home/dom/Téléchargements/II-1 Ctrl_T2A_2025_CHCB_DocJustificatifs (1)/692_23200418/CRH 692_23200418.pdf",
|
|
"folder": "692_23200418",
|
|
"original_filename": "CRH 692_23200418.pdf",
|
|
"type": "compte_rendu",
|
|
"complexity": "moyen",
|
|
"pages": 2,
|
|
"size_mb": 0.59
|
|
},
|
|
{
|
|
"id": 13,
|
|
"dest_filename": "013_moyen_compte_rendu_363_23085243_CRO.pdf",
|
|
"original_path": "/home/dom/Téléchargements/II-1 Ctrl_T2A_2025_CHCB_DocJustificatifs (1)/363_23085243/363_23085243 CRO.pdf",
|
|
"folder": "363_23085243",
|
|
"original_filename": "363_23085243 CRO.pdf",
|
|
"type": "compte_rendu",
|
|
"complexity": "moyen",
|
|
"pages": 2,
|
|
"size_mb": 0.58
|
|
},
|
|
{
|
|
"id": 14,
|
|
"dest_filename": "014_moyen_compte_rendu_CRO_23167029.redacted_raster.pdf",
|
|
"original_path": "/home/dom/Téléchargements/II-1 Ctrl_T2A_2025_CHCB_DocJustificatifs (1)/anonymise/CRO 23167029.redacted_raster.pdf",
|
|
"folder": "anonymise",
|
|
"original_filename": "CRO 23167029.redacted_raster.pdf",
|
|
"type": "compte_rendu",
|
|
"complexity": "moyen",
|
|
"pages": 2,
|
|
"size_mb": 0.65
|
|
},
|
|
{
|
|
"id": 15,
|
|
"dest_filename": "015_moyen_unknown_CONSULTATION_ANESTHESISTE_23139653.pdf",
|
|
"original_path": "/home/dom/Téléchargements/II-1 Ctrl_T2A_2025_CHCB_DocJustificatifs (1)/222_23139653/CONSULTATION ANESTHESISTE 23139653.pdf",
|
|
"folder": "222_23139653",
|
|
"original_filename": "CONSULTATION ANESTHESISTE 23139653.pdf",
|
|
"type": "unknown",
|
|
"complexity": "moyen",
|
|
"pages": 3,
|
|
"size_mb": 0.12
|
|
},
|
|
{
|
|
"id": 16,
|
|
"dest_filename": "016_moyen_compte_rendu_CRH_23149905.pdf",
|
|
"original_path": "/home/dom/Téléchargements/II-1 Ctrl_T2A_2025_CHCB_DocJustificatifs (1)/199_23149905/CRH 23149905.pdf",
|
|
"folder": "199_23149905",
|
|
"original_filename": "CRH 23149905.pdf",
|
|
"type": "compte_rendu",
|
|
"complexity": "moyen",
|
|
"pages": 3,
|
|
"size_mb": 0.15
|
|
},
|
|
{
|
|
"id": 17,
|
|
"dest_filename": "017_moyen_compte_rendu_CRO_23222062.redacted_raster.pdf",
|
|
"original_path": "/home/dom/Téléchargements/II-1 Ctrl_T2A_2025_CHCB_DocJustificatifs (1)/anonymise/CRO 23222062.redacted_raster.pdf",
|
|
"folder": "anonymise",
|
|
"original_filename": "CRO 23222062.redacted_raster.pdf",
|
|
"type": "compte_rendu",
|
|
"complexity": "moyen",
|
|
"pages": 2,
|
|
"size_mb": 0.57
|
|
},
|
|
{
|
|
"id": 18,
|
|
"dest_filename": "018_moyen_compte_rendu_CRH_23042753.pdf",
|
|
"original_path": "/home/dom/Téléchargements/II-1 Ctrl_T2A_2025_CHCB_DocJustificatifs (1)/1_23042753/CRH 23042753.pdf",
|
|
"folder": "1_23042753",
|
|
"original_filename": "CRH 23042753.pdf",
|
|
"type": "compte_rendu",
|
|
"complexity": "moyen",
|
|
"pages": 4,
|
|
"size_mb": 0.15
|
|
},
|
|
{
|
|
"id": 19,
|
|
"dest_filename": "019_moyen_compte_rendu_CRO_332_23049003.pdf",
|
|
"original_path": "/home/dom/Téléchargements/II-1 Ctrl_T2A_2025_CHCB_DocJustificatifs (1)/332_23049003/CRO 332_23049003.pdf",
|
|
"folder": "332_23049003",
|
|
"original_filename": "CRO 332_23049003.pdf",
|
|
"type": "compte_rendu",
|
|
"complexity": "moyen",
|
|
"pages": 2,
|
|
"size_mb": 0.43
|
|
},
|
|
{
|
|
"id": 20,
|
|
"dest_filename": "020_moyen_compte_rendu_CRO_23084754.redacted_raster.pdf",
|
|
"original_path": "/home/dom/Téléchargements/II-1 Ctrl_T2A_2025_CHCB_DocJustificatifs (1)/anonymise/CRO 23084754.redacted_raster.pdf",
|
|
"folder": "anonymise",
|
|
"original_filename": "CRO 23084754.redacted_raster.pdf",
|
|
"type": "compte_rendu",
|
|
"complexity": "moyen",
|
|
"pages": 2,
|
|
"size_mb": 0.46
|
|
},
|
|
{
|
|
"id": 21,
|
|
"dest_filename": "021_moyen_compte_rendu_CRO_23201117.redacted_raster.pdf",
|
|
"original_path": "/home/dom/Téléchargements/II-1 Ctrl_T2A_2025_CHCB_DocJustificatifs (1)/anonymise/CRO 23201117.redacted_raster.pdf",
|
|
"folder": "anonymise",
|
|
"original_filename": "CRO 23201117.redacted_raster.pdf",
|
|
"type": "compte_rendu",
|
|
"complexity": "moyen",
|
|
"pages": 1,
|
|
"size_mb": 0.33
|
|
},
|
|
{
|
|
"id": 22,
|
|
"dest_filename": "022_moyen_compte_rendu_cro2_516_23187028.pdf",
|
|
"original_path": "/home/dom/Téléchargements/II-1 Ctrl_T2A_2025_CHCB_DocJustificatifs (1)/516_23187028/cro2 516_23187028.pdf",
|
|
"folder": "516_23187028",
|
|
"original_filename": "cro2 516_23187028.pdf",
|
|
"type": "compte_rendu",
|
|
"complexity": "moyen",
|
|
"pages": 1,
|
|
"size_mb": 0.3
|
|
},
|
|
{
|
|
"id": 23,
|
|
"dest_filename": "023_complexe_compte_rendu_CRH_23102610.pdf",
|
|
"original_path": "/home/dom/Téléchargements/II-1 Ctrl_T2A_2025_CHCB_DocJustificatifs (1)/153_23102610/CRH 23102610.pdf",
|
|
"folder": "153_23102610",
|
|
"original_filename": "CRH 23102610.pdf",
|
|
"type": "compte_rendu",
|
|
"complexity": "complexe",
|
|
"pages": 9,
|
|
"size_mb": 0.14
|
|
},
|
|
{
|
|
"id": 24,
|
|
"dest_filename": "024_complexe_trackare_trackare-17001141-23066188_17001141_23066188.pdf",
|
|
"original_path": "/home/dom/Téléchargements/II-1 Ctrl_T2A_2025_CHCB_DocJustificatifs (1)/115_23066188/trackare-17001141-23066188_17001141_23066188.pdf",
|
|
"folder": "115_23066188",
|
|
"original_filename": "trackare-17001141-23066188_17001141_23066188.pdf",
|
|
"type": "trackare",
|
|
"complexity": "complexe",
|
|
"pages": 19,
|
|
"size_mb": 0.21
|
|
},
|
|
{
|
|
"id": 25,
|
|
"dest_filename": "025_complexe_trackare_trackare-02016820-23095226_02016820_23095226.pdf",
|
|
"original_path": "/home/dom/Téléchargements/II-1 Ctrl_T2A_2025_CHCB_DocJustificatifs (1)/400_23095226/trackare-02016820-23095226_02016820_23095226.pdf",
|
|
"folder": "400_23095226",
|
|
"original_filename": "trackare-02016820-23095226_02016820_23095226.pdf",
|
|
"type": "trackare",
|
|
"complexity": "complexe",
|
|
"pages": 31,
|
|
"size_mb": 0.29
|
|
},
|
|
{
|
|
"id": 26,
|
|
"dest_filename": "026_complexe_trackare_trackare-15000536-23074384_15000536_23074384.pdf",
|
|
"original_path": "/home/dom/Téléchargements/II-1 Ctrl_T2A_2025_CHCB_DocJustificatifs (1)/343_23074384/trackare-15000536-23074384_15000536_23074384.pdf",
|
|
"folder": "343_23074384",
|
|
"original_filename": "trackare-15000536-23074384_15000536_23074384.pdf",
|
|
"type": "trackare",
|
|
"complexity": "complexe",
|
|
"pages": 25,
|
|
"size_mb": 0.25
|
|
},
|
|
{
|
|
"id": 27,
|
|
"dest_filename": "027_complexe_trackare_trackare-10027557-23183041_10027557_23183041.pdf",
|
|
"original_path": "/home/dom/Téléchargements/II-1 Ctrl_T2A_2025_CHCB_DocJustificatifs (1)/45_23183041/trackare-10027557-23183041_10027557_23183041.pdf",
|
|
"folder": "45_23183041",
|
|
"original_filename": "trackare-10027557-23183041_10027557_23183041.pdf",
|
|
"type": "trackare",
|
|
"complexity": "complexe",
|
|
"pages": 20,
|
|
"size_mb": 0.25
|
|
}
|
|
] |