chore: add .gitignore

This commit is contained in:
dom
2026-03-05 00:37:34 +01:00
parent da34bdc8d7
commit d2e0fec97d
2087 changed files with 1485338 additions and 14 deletions

View File

@@ -0,0 +1,273 @@
{
"source_file": "CRH 23127286.pdf",
"total_replacements": 221,
"regex_replacements": 104,
"ner_replacements": 10,
"sweep_replacements": 107,
"entities_found": [
{
"original": "10100532760",
"replacement": "[RPPS_1]",
"source": "regex",
"category": "rpps"
},
{
"original": "10100532760",
"replacement": "[RPPS_1]",
"source": "regex",
"category": "rpps"
},
{
"original": "10100532760",
"replacement": "[RPPS_1]",
"source": "regex",
"category": "rpps"
},
{
"original": "10002456746",
"replacement": "[CODE_BARRE_1]",
"source": "regex",
"category": "code_barre"
},
{
"original": "fprevost@ch-cotebasque.fr",
"replacement": "[EMAIL_1]",
"source": "regex",
"category": "email"
},
{
"original": "boui@ch-cotebasque.fr",
"replacement": "[EMAIL_2]",
"source": "regex",
"category": "email"
},
{
"original": "dnivet@ch-cotebasque.fr",
"replacement": "[EMAIL_3]",
"source": "regex",
"category": "email"
},
{
"original": "tkhuong-huu@ch-cotebasque.fr",
"replacement": "[EMAIL_4]",
"source": "regex",
"category": "email"
},
{
"original": "aguilngar@ch-cotebasque.fr",
"replacement": "[EMAIL_5]",
"source": "regex",
"category": "email"
},
{
"original": "fgoutorbe@ch-cotebasque.fr",
"replacement": "[EMAIL_6]",
"source": "regex",
"category": "email"
},
{
"original": "mcboudier@ch-cotebasque.fr",
"replacement": "[EMAIL_7]",
"source": "regex",
"category": "email"
},
{
"original": "mbrugel@ch-cotebasque.fr",
"replacement": "[EMAIL_8]",
"source": "regex",
"category": "email"
},
{
"original": "mboube@ch-cotebasque.fr",
"replacement": "[EMAIL_9]",
"source": "regex",
"category": "email"
},
{
"original": "faudemar@ch-cotebasque.fr",
"replacement": "[EMAIL_10]",
"source": "regex",
"category": "email"
},
{
"original": "fprevost@ch-cotebasque.fr",
"replacement": "[EMAIL_1]",
"source": "regex",
"category": "email"
},
{
"original": "boui@ch-cotebasque.fr",
"replacement": "[EMAIL_2]",
"source": "regex",
"category": "email"
},
{
"original": "dnivet@ch-cotebasque.fr",
"replacement": "[EMAIL_3]",
"source": "regex",
"category": "email"
},
{
"original": "tkhuong-huu@ch-cotebasque.fr",
"replacement": "[EMAIL_4]",
"source": "regex",
"category": "email"
},
{
"original": "aguilngar@ch-cotebasque.fr",
"replacement": "[EMAIL_5]",
"source": "regex",
"category": "email"
},
{
"original": "fgoutorbe@ch-cotebasque.fr",
"replacement": "[EMAIL_6]",
"source": "regex",
"category": "email"
},
{
"original": "mcboudier@ch-cotebasque.fr",
"replacement": "[EMAIL_7]",
"source": "regex",
"category": "email"
},
{
"original": "mbrugel@ch-cotebasque.fr",
"replacement": "[EMAIL_8]",
"source": "regex",
"category": "email"
},
{
"original": "mboube@ch-cotebasque.fr",
"replacement": "[EMAIL_9]",
"source": "regex",
"category": "email"
},
{
"original": "faudemar@ch-cotebasque.fr",
"replacement": "[EMAIL_10]",
"source": "regex",
"category": "email"
},
{
"original": "fprevost@ch-cotebasque.fr",
"replacement": "[EMAIL_1]",
"source": "regex",
"category": "email"
},
{
"original": "boui@ch-cotebasque.fr",
"replacement": "[EMAIL_2]",
"source": "regex",
"category": "email"
},
{
"original": "dnivet@ch-cotebasque.fr",
"replacement": "[EMAIL_3]",
"source": "regex",
"category": "email"
},
{
"original": "tkhuong-huu@ch-cotebasque.fr",
"replacement": "[EMAIL_4]",
"source": "regex",
"category": "email"
},
{
"original": "aguilngar@ch-cotebasque.fr",
"replacement": "[EMAIL_5]",
"source": "regex",
"category": "email"
},
{
"original": "fgoutorbe@ch-cotebasque.fr",
"replacement": "[EMAIL_6]",
"source": "regex",
"category": "email"
},
{
"original": "mcboudier@ch-cotebasque.fr",
"replacement": "[EMAIL_7]",
"source": "regex",
"category": "email"
},
{
"original": "mbrugel@ch-cotebasque.fr",
"replacement": "[EMAIL_8]",
"source": "regex",
"category": "email"
},
{
"original": "mboube@ch-cotebasque.fr",
"replacement": "[EMAIL_9]",
"source": "regex",
"category": "email"
},
{
"original": "faudemar@ch-cotebasque.fr",
"replacement": "[EMAIL_10]",
"source": "regex",
"category": "email"
},
{
"original": "[MEDECIN",
"replacement": "[PERSONNE_1]",
"source": "ner",
"score": 0.8818820118904114
},
{
"original": "[PATIENT_",
"replacement": "[PERSONNE_2]",
"source": "ner",
"score": 0.8887837529182434
},
{
"original": "MEDECIN_",
"replacement": "[PERSONNE_3]",
"source": "ner",
"score": 0.9212851524353027
},
{
"original": "Grellety",
"replacement": "[MEDECIN]",
"source": "ner",
"score": 0.9900949597358704
},
{
"original": "[PATIENT_5",
"replacement": "[PERSONNE_4]",
"source": "ner",
"score": 0.9084901809692383
},
{
"original": "[MEDECIN_36",
"replacement": "[PERSONNE_5]",
"source": "ner",
"score": 0.9577557444572449
},
{
"original": "[MEDECIN_21",
"replacement": "[PERSONNE_6]",
"source": "ner",
"score": 0.9718517661094666
},
{
"original": "[MEDECIN_",
"replacement": "[PERSONNE_7]",
"source": "ner",
"score": 0.9900413155555725
},
{
"original": "MEDEC",
"replacement": "[PERSONNE_8]",
"source": "ner",
"score": 0.8308868408203125
},
{
"original": "[MEDECIN_26",
"replacement": "[PERSONNE_9]",
"source": "ner",
"score": 0.9056357145309448
}
]
}

View File

@@ -0,0 +1,39 @@
{
"source_file": "CRO 23127286.pdf",
"total_replacements": 10,
"regex_replacements": 5,
"ner_replacements": 5,
"sweep_replacements": 0,
"entities_found": [
{
"original": "Docteur M. [MEDECIN_",
"replacement": "[PERSONNE_1]",
"source": "ner",
"score": 0.8932886123657227
},
{
"original": "R. DIDAILLER",
"replacement": "[PERSONNE_2]",
"source": "ner",
"score": 0.9741106033325195
},
{
"original": "[MEDECIN_",
"replacement": "[PERSONNE]",
"source": "ner",
"score": 0.9795369505882263
},
{
"original": "ANDRIANAVALOMIONONA",
"replacement": "[PERSONNE_3]",
"source": "ner",
"score": 0.9895805716514587
},
{
"original": "MARC FREYNET",
"replacement": "[PERSONNE_4]",
"source": "ner",
"score": 0.9698001146316528
}
]
}

View File

@@ -0,0 +1,477 @@
{
"source_file": "trackare-21020800-23127286_21020800_23127286.pdf",
"total_replacements": 621,
"regex_replacements": 149,
"ner_replacements": 30,
"sweep_replacements": 442,
"entities_found": [
{
"original": "21020800",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "21020800",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "21020800",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "21020800",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "21020800",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "21020800",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "21020800",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "21020800",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "21020800",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "21020800",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "21020800",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "21020800",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "21020800",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "21020800",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "21020800",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "21020800",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "21020800",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "21020800",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "21020800",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "21020800",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "21020800",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "21020800",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "23127286",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23127286",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23127286",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23127286",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23127286",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23127286",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23127286",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23127286",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23127286",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23127286",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23127286",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23127286",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23127286",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23127286",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23127286",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23127286",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23127286",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23127286",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23127286",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23127286",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23127286",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23127286",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "198041616632053",
"replacement": "[NIR_1]",
"source": "regex",
"category": "nir"
},
{
"original": "640000162",
"replacement": "[FINESS]",
"source": "regex",
"category": "finess"
},
{
"original": "16166",
"replacement": "[LIEU_NAISS_2]",
"source": "regex",
"category": "lieu_naissance"
},
{
"original": "L ISLE D ESPAGNAC",
"replacement": "[LIEU_NAISS_1]",
"source": "regex",
"category": "lieu_naissance"
},
{
"original": "JAOUEN GUILLEMAUD GUILLEMAUD",
"replacement": "[PERSONNE_1]",
"source": "ner",
"score": 0.9917624592781067
},
{
"original": "SABATIER",
"replacement": "[MEDECIN]",
"source": "ner",
"score": 0.9951644539833069
},
{
"original": "Julien",
"replacement": "[MEDECIN]",
"source": "ner",
"score": 0.9701616168022156
},
{
"original": "ABDOMINO-PELVIEN",
"replacement": "[PERSONNE_2]",
"source": "ner",
"score": 0.8821081519126892
},
{
"original": "[MEDECIN_",
"replacement": "[PERSONNE_3]",
"source": "ner",
"score": 0.8898642659187317
},
{
"original": "MARC",
"replacement": "[PATIENT]",
"source": "ner",
"score": 0.8826419711112976
},
{
"original": "FREYNET",
"replacement": "[PATIENT]",
"source": "ner",
"score": 0.8381211161613464
},
{
"original": "LE BAIL Antoine",
"replacement": "[PERSONNE_4]",
"source": "ner",
"score": 0.9329051375389099
},
{
"original": "Anne GELULE",
"replacement": "[PERSONNE_5]",
"source": "ner",
"score": 0.9880611896514893
},
{
"original": "ACTISKENAN 10MG",
"replacement": "[PERSONNE_6]",
"source": "ner",
"score": 0.9340677261352539
},
{
"original": "ACTISKENAN 10MG G",
"replacement": "[PERSONNE_7]",
"source": "ner",
"score": 0.9292653799057007
},
{
"original": "CHEVALIER Lucile Signé",
"replacement": "[PERSONNE_8]",
"source": "ner",
"score": 0.9981847405433655
},
{
"original": "GABON Annabelle",
"replacement": "[PERSONNE_9]",
"source": "ner",
"score": 0.9785335659980774
},
{
"original": "ACTISKENAN",
"replacement": "[PERSONNE]",
"source": "ner",
"score": 0.9911567568778992
},
{
"original": "CHEVALIER",
"replacement": "[MEDECIN]",
"source": "ner",
"score": 0.8535102009773254
},
{
"original": "CHEVALIER Lucile",
"replacement": "[MEDECIN_21]",
"source": "ner",
"score": 0.9970744252204895
},
{
"original": "CHEVALIER DESINFECTION",
"replacement": "[PERSONNE_10]",
"source": "ner",
"score": 0.9824155569076538
},
{
"original": "Lucile BANDELETTE URINAIRE",
"replacement": "[PERSONNE_11]",
"source": "ner",
"score": 0.954784095287323
},
{
"original": "MEDECIN_",
"replacement": "[PERSONNE_12]",
"source": "ner",
"score": 0.9089658856391907
},
{
"original": "Léna MELAINE",
"replacement": "[SOIGNANT_7]",
"source": "ner",
"score": 0.9983986020088196
},
{
"original": "[MEDECIN",
"replacement": "[PERSONNE_13]",
"source": "ner",
"score": 0.8051384091377258
},
{
"original": "Lucile CHEVALIER",
"replacement": "[PERSONNE_14]",
"source": "ner",
"score": 0.9979852437973022
},
{
"original": "SERINGUE",
"replacement": "[PERSONNE_15]",
"source": "ner",
"score": 0.8793030381202698
},
{
"original": "Lucile SERINGUE",
"replacement": "[PERSONNE_16]",
"source": "ner",
"score": 0.9172765612602234
},
{
"original": "Aurore MEURAT",
"replacement": "[SOIGNANT_9]",
"source": "ner",
"score": 0.9986415505409241
},
{
"original": "Jérémy SAUGER",
"replacement": "[PERSONNE_17]",
"source": "ner",
"score": 0.9953994154930115
},
{
"original": "Pujos",
"replacement": "[MEDECIN_2]",
"source": "ner",
"score": 0.9925743937492371
},
{
"original": "MEDECIN_40",
"replacement": "[PERSONNE_18]",
"source": "ner",
"score": 0.9267075061798096
},
{
"original": "Augmentin",
"replacement": "[PERSONNE_19]",
"source": "ner",
"score": 0.8067213892936707
},
{
"original": "vidal rudy",
"replacement": "[PERSONNE_20]",
"source": "ner",
"score": 0.9963701963424683
}
]
}