113 lines
3.6 KiB
Python
113 lines
3.6 KiB
Python
#!/usr/bin/env python3
|
|
# -*- coding: utf-8 -*-
|
|
"""
|
|
EDS-Pseudo Manager — Interface compatible NerModelManager pour le modèle AP-HP eds-pseudo.
|
|
--------------------------------------------------------------------------------------------
|
|
Utilise edsnlp pour charger le pipeline eds-pseudo (F1=0.97 sur données cliniques AP-HP).
|
|
Mapping des 13 labels EDS-Pseudo vers les clés PLACEHOLDERS du core d'anonymisation.
|
|
|
|
Dépendance : pip install 'edsnlp[ml]>=0.12.0'
|
|
"""
|
|
from __future__ import annotations
|
|
from pathlib import Path
|
|
from typing import Any, Dict, List, Optional
|
|
|
|
try:
|
|
import edsnlp
|
|
_EDSNLP_AVAILABLE = True
|
|
except ImportError:
|
|
edsnlp = None # type: ignore
|
|
_EDSNLP_AVAILABLE = False
|
|
|
|
# Mapping labels EDS-Pseudo → clés PLACEHOLDERS (anonymizer_core)
|
|
EDS_LABEL_MAP: Dict[str, str] = {
|
|
"NOM": "NOM",
|
|
"PRENOM": "NOM",
|
|
"MAIL": "EMAIL",
|
|
"TEL": "TEL",
|
|
"SECU": "NIR",
|
|
"ADRESSE": "ADRESSE",
|
|
"ZIP": "CODE_POSTAL",
|
|
"VILLE": "VILLE",
|
|
"HOPITAL": "ETAB",
|
|
# "DATE": "DATE", # DÉSACTIVÉ: ne masquer que les dates de naissance (Correction 1.3)
|
|
"DATE_NAISSANCE": "DATE_NAISSANCE",
|
|
"IPP": "IPP",
|
|
"NDA": "NDA",
|
|
}
|
|
|
|
# Catalogue affiché dans la GUI
|
|
EDS_MODELS_CATALOG: Dict[str, str] = {
|
|
"EDS-Pseudo AP-HP (edsnlp)": "AP-HP/eds-pseudo-public",
|
|
}
|
|
|
|
|
|
class EdsPseudoManager:
|
|
"""Gestionnaire pour le modèle EDS-Pseudo (edsnlp). Même interface que NerModelManager."""
|
|
|
|
def __init__(self, cache_dir: Optional[Path] = None):
|
|
self.cache_dir = Path(cache_dir) if cache_dir else None
|
|
self.model_id: Optional[str] = None
|
|
self._nlp = None
|
|
self._loaded = False
|
|
|
|
def is_loaded(self) -> bool:
|
|
return self._loaded and self._nlp is not None
|
|
|
|
def load(self, model_id_or_path: str = "AP-HP/eds-pseudo-public") -> None:
|
|
if not _EDSNLP_AVAILABLE:
|
|
raise RuntimeError("edsnlp non disponible. Installez : pip install 'edsnlp[ml]>=0.12.0'")
|
|
self.unload()
|
|
self.model_id = model_id_or_path
|
|
path = Path(model_id_or_path)
|
|
if path.is_dir():
|
|
self._nlp = edsnlp.load(path)
|
|
else:
|
|
self._nlp = edsnlp.load(model_id_or_path)
|
|
self._loaded = True
|
|
|
|
def unload(self) -> None:
|
|
self._nlp = None
|
|
self._loaded = False
|
|
self.model_id = None
|
|
|
|
def models_catalog(self) -> Dict[str, str]:
|
|
return dict(EDS_MODELS_CATALOG)
|
|
|
|
def infer_paragraphs(
|
|
self,
|
|
paragraphs: List[str],
|
|
thresholds: Optional[Any] = None,
|
|
max_length: int = 384,
|
|
stride: int = 128,
|
|
) -> List[List[Dict[str, Any]]]:
|
|
"""Pour chaque paragraphe, retourne une liste d'entités détectées.
|
|
|
|
Chaque entité a les clés : entity_group, word, start, end, score, eds_mapped_key.
|
|
"""
|
|
if not self.is_loaded():
|
|
return [[] for _ in paragraphs]
|
|
|
|
out: List[List[Dict[str, Any]]] = []
|
|
for para in paragraphs:
|
|
if not para.strip():
|
|
out.append([])
|
|
continue
|
|
doc = self._nlp(para)
|
|
ents: List[Dict[str, Any]] = []
|
|
for ent in doc.ents:
|
|
label = ent.label_.upper()
|
|
mapped = EDS_LABEL_MAP.get(label, None)
|
|
if mapped is None:
|
|
continue
|
|
ents.append({
|
|
"entity_group": label,
|
|
"word": ent.text,
|
|
"start": ent.start_char,
|
|
"end": ent.end_char,
|
|
"score": 1.0, # edsnlp ne fournit pas de score de confiance
|
|
"eds_mapped_key": mapped,
|
|
})
|
|
out.append(ents)
|
|
return out
|