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 +1,87 @@
{
"source_file": "BACTERIO 23138778.pdf",
"total_replacements": 21,
"regex_replacements": 9,
"ner_replacements": 12,
"sweep_replacements": 0,
"entities_found": [
{
"original": "05025000",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "Borne",
"replacement": "[PERSONNE_1]",
"source": "ner",
"score": 0.834625244140625
},
{
"original": "DALLEMANE Carine",
"replacement": "[PERSONNE_2]",
"source": "ner",
"score": 0.9976194500923157
},
{
"original": "VILLETTE Paul-Emile",
"replacement": "[PERSONNE_3]",
"source": "ner",
"score": 0.9971188306808472
},
{
"original": "ALEXANDRE",
"replacement": "[PERSONNE_4]",
"source": "ner",
"score": 0.9367687702178955
},
{
"original": "ALEXANDRE Patrick",
"replacement": "[PERSONNE_5]",
"source": "ner",
"score": 0.9712026715278625
},
{
"original": "] DECOEUR Lucie",
"replacement": "[PERSONNE_6]",
"source": "ner",
"score": 0.9033409953117371
},
{
"original": "[MEDECIN_",
"replacement": "[PERSONNE_7]",
"source": "ner",
"score": 0.962990939617157
},
{
"original": "MONIER Laurie Assistant",
"replacement": "[PERSONNE_8]",
"source": "ner",
"score": 0.8946458697319031
},
{
"original": "GUILLEMAUD Julien",
"replacement": "[MEDECIN_6]",
"source": "ner",
"score": 0.9983097910881042
},
{
"original": "LEYSSENE David",
"replacement": "[MEDECIN_3]",
"source": "ner",
"score": 0.9980430603027344
},
{
"original": "[MEDECIN",
"replacement": "[PERSONNE_9]",
"source": "ner",
"score": 0.946854293346405
},
{
"original": "Jacques Loëb",
"replacement": "[PERSONNE_10]",
"source": "ner",
"score": 0.9593117833137512
}
]
}

View File

@@ -0,0 +1,405 @@
{
"source_file": "CRH 23138778.pdf",
"total_replacements": 338,
"regex_replacements": 152,
"ner_replacements": 14,
"sweep_replacements": 172,
"entities_found": [
{
"original": "10110601324",
"replacement": "[RPPS_1]",
"source": "regex",
"category": "rpps"
},
{
"original": "10101096005",
"replacement": "[RPPS_2]",
"source": "regex",
"category": "rpps"
},
{
"original": "10100163277",
"replacement": "[RPPS_3]",
"source": "regex",
"category": "rpps"
},
{
"original": "10101639580",
"replacement": "[RPPS_4]",
"source": "regex",
"category": "rpps"
},
{
"original": "10004606595",
"replacement": "[RPPS_5]",
"source": "regex",
"category": "rpps"
},
{
"original": "10101480506",
"replacement": "[RPPS_6]",
"source": "regex",
"category": "rpps"
},
{
"original": "10100858090",
"replacement": "[RPPS_7]",
"source": "regex",
"category": "rpps"
},
{
"original": "10102268702",
"replacement": "[RPPS_8]",
"source": "regex",
"category": "rpps"
},
{
"original": "10102272209",
"replacement": "[RPPS_9]",
"source": "regex",
"category": "rpps"
},
{
"original": "10101856135",
"replacement": "[RPPS_10]",
"source": "regex",
"category": "rpps"
},
{
"original": "10002815024",
"replacement": "[RPPS_11]",
"source": "regex",
"category": "rpps"
},
{
"original": "10100817005",
"replacement": "[RPPS_12]",
"source": "regex",
"category": "rpps"
},
{
"original": "10110601324",
"replacement": "[RPPS_1]",
"source": "regex",
"category": "rpps"
},
{
"original": "10101096005",
"replacement": "[RPPS_2]",
"source": "regex",
"category": "rpps"
},
{
"original": "10100163277",
"replacement": "[RPPS_3]",
"source": "regex",
"category": "rpps"
},
{
"original": "10101639580",
"replacement": "[RPPS_4]",
"source": "regex",
"category": "rpps"
},
{
"original": "10004606595",
"replacement": "[RPPS_5]",
"source": "regex",
"category": "rpps"
},
{
"original": "10101480506",
"replacement": "[RPPS_6]",
"source": "regex",
"category": "rpps"
},
{
"original": "10100858090",
"replacement": "[RPPS_7]",
"source": "regex",
"category": "rpps"
},
{
"original": "10102268702",
"replacement": "[RPPS_8]",
"source": "regex",
"category": "rpps"
},
{
"original": "10102272209",
"replacement": "[RPPS_9]",
"source": "regex",
"category": "rpps"
},
{
"original": "10101856135",
"replacement": "[RPPS_10]",
"source": "regex",
"category": "rpps"
},
{
"original": "10002815024",
"replacement": "[RPPS_11]",
"source": "regex",
"category": "rpps"
},
{
"original": "10100817005",
"replacement": "[RPPS_12]",
"source": "regex",
"category": "rpps"
},
{
"original": "10110601324",
"replacement": "[RPPS_1]",
"source": "regex",
"category": "rpps"
},
{
"original": "10101096005",
"replacement": "[RPPS_2]",
"source": "regex",
"category": "rpps"
},
{
"original": "10100163277",
"replacement": "[RPPS_3]",
"source": "regex",
"category": "rpps"
},
{
"original": "10101639580",
"replacement": "[RPPS_4]",
"source": "regex",
"category": "rpps"
},
{
"original": "10004606595",
"replacement": "[RPPS_5]",
"source": "regex",
"category": "rpps"
},
{
"original": "10101480506",
"replacement": "[RPPS_6]",
"source": "regex",
"category": "rpps"
},
{
"original": "10100858090",
"replacement": "[RPPS_7]",
"source": "regex",
"category": "rpps"
},
{
"original": "10102268702",
"replacement": "[RPPS_8]",
"source": "regex",
"category": "rpps"
},
{
"original": "10102272209",
"replacement": "[RPPS_9]",
"source": "regex",
"category": "rpps"
},
{
"original": "10101856135",
"replacement": "[RPPS_10]",
"source": "regex",
"category": "rpps"
},
{
"original": "10002815024",
"replacement": "[RPPS_11]",
"source": "regex",
"category": "rpps"
},
{
"original": "10100817005",
"replacement": "[RPPS_12]",
"source": "regex",
"category": "rpps"
},
{
"original": "10110601324",
"replacement": "[RPPS_1]",
"source": "regex",
"category": "rpps"
},
{
"original": "10101096005",
"replacement": "[RPPS_2]",
"source": "regex",
"category": "rpps"
},
{
"original": "10100163277",
"replacement": "[RPPS_3]",
"source": "regex",
"category": "rpps"
},
{
"original": "10101639580",
"replacement": "[RPPS_4]",
"source": "regex",
"category": "rpps"
},
{
"original": "10004606595",
"replacement": "[RPPS_5]",
"source": "regex",
"category": "rpps"
},
{
"original": "10101480506",
"replacement": "[RPPS_6]",
"source": "regex",
"category": "rpps"
},
{
"original": "10100858090",
"replacement": "[RPPS_7]",
"source": "regex",
"category": "rpps"
},
{
"original": "10102268702",
"replacement": "[RPPS_8]",
"source": "regex",
"category": "rpps"
},
{
"original": "10102272209",
"replacement": "[RPPS_9]",
"source": "regex",
"category": "rpps"
},
{
"original": "10002815024",
"replacement": "[RPPS_11]",
"source": "regex",
"category": "rpps"
},
{
"original": "10100817005",
"replacement": "[RPPS_12]",
"source": "regex",
"category": "rpps"
},
{
"original": "10100858090",
"replacement": "[RPPS_7]",
"source": "regex",
"category": "code_barre"
},
{
"original": "secr.medint@ch-cotebasque.fr",
"replacement": "[EMAIL_1]",
"source": "regex",
"category": "email"
},
{
"original": "secr.medint@ch-cotebasque.fr",
"replacement": "[EMAIL_1]",
"source": "regex",
"category": "email"
},
{
"original": "secr.medint@ch-cotebasque.fr",
"replacement": "[EMAIL_1]",
"source": "regex",
"category": "email"
},
{
"original": "secr.medint@ch-cotebasque.fr",
"replacement": "[EMAIL_1]",
"source": "regex",
"category": "email"
},
{
"original": "Dr [MEDECIN_",
"replacement": "[PERSONNE_1]",
"source": "ner",
"score": 0.9013031721115112
},
{
"original": "Stéphane MARCE",
"replacement": "[MEDECIN_3]",
"source": "ner",
"score": 0.9959986805915833
},
{
"original": "[MEDECIN",
"replacement": "[PERSONNE_2]",
"source": "ner",
"score": 0.9695279002189636
},
{
"original": "[MEDECIN_28",
"replacement": "[PERSONNE_3]",
"source": "ner",
"score": 0.9301411509513855
},
{
"original": "[MEDECIN_32",
"replacement": "[PERSONNE_4]",
"source": "ner",
"score": 0.9407869577407837
},
{
"original": "J. LOEB",
"replacement": "[PERSONNE_5]",
"source": "ner",
"score": 0.878480851650238
},
{
"original": "[MEDECIN_57",
"replacement": "[PERSONNE_6]",
"source": "ner",
"score": 0.9403043985366821
},
{
"original": "[MEDECIN_22",
"replacement": "[PERSONNE_7]",
"source": "ner",
"score": 0.9527907967567444
},
{
"original": "[MEDECIN_23",
"replacement": "[PERSONNE_8]",
"source": "ner",
"score": 0.9620316624641418
},
{
"original": "[MEDECIN_26",
"replacement": "[PERSONNE_9]",
"source": "ner",
"score": 0.9150679707527161
},
{
"original": "[MEDECIN_27",
"replacement": "[PERSONNE_10]",
"source": "ner",
"score": 0.9694771766662598
},
{
"original": "[MEDECIN_61",
"replacement": "[PERSONNE_11]",
"source": "ner",
"score": 0.9451074600219727
},
{
"original": "[MEDECIN_",
"replacement": "[PERSONNE]",
"source": "ner",
"score": 0.9825130105018616
},
{
"original": "ALEXANDRE Patrick",
"replacement": "[PERSONNE_12]",
"source": "ner",
"score": 0.9208989143371582
}
]
}

View File

@@ -0,0 +1,459 @@
{
"source_file": "trackare-05025000-23138778_05025000_23138778.pdf",
"total_replacements": 427,
"regex_replacements": 144,
"ner_replacements": 26,
"sweep_replacements": 257,
"entities_found": [
{
"original": "05025000",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "05025000",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "05025000",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "05025000",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "05025000",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "05025000",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "05025000",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "05025000",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "05025000",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "05025000",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "05025000",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "05025000",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "05025000",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "05025000",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "05025000",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "05025000",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "05025000",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "05025000",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "05025000",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "05025000",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "05025000",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "23138778",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23138778",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23138778",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23138778",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23138778",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23138778",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23138778",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23138778",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23138778",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23138778",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23138778",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23138778",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23138778",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23138778",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23138778",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23138778",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23138778",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23138778",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23138778",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23138778",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23138778",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "156049935079880",
"replacement": "[NIR_1]",
"source": "regex",
"category": "nir"
},
{
"original": "156049935079880",
"replacement": "[NIR_1]",
"source": "regex",
"category": "nir"
},
{
"original": "156049935079880",
"replacement": "[NIR_1]",
"source": "regex",
"category": "nir"
},
{
"original": "640000162",
"replacement": "[FINESS]",
"source": "regex",
"category": "finess"
},
{
"original": "99350",
"replacement": "[LIEU_NAISS_2]",
"source": "regex",
"category": "lieu_naissance"
},
{
"original": "99350",
"replacement": "[LIEU_NAISS_2]",
"source": "regex",
"category": "lieu_naissance"
},
{
"original": "CASABLANCA",
"replacement": "[LIEU_NAISS_1]",
"source": "regex",
"category": "lieu_naissance"
},
{
"original": "BURTIN",
"replacement": "[PERSONNE_1]",
"source": "ner",
"score": 0.9879215359687805
},
{
"original": "David LEYSSENE",
"replacement": "[PERSONNE_2]",
"source": "ner",
"score": 0.9970812797546387
},
{
"original": "MEDECIN_",
"replacement": "[PERSONNE_3]",
"source": "ner",
"score": 0.8782854080200195
},
{
"original": "PATRICK",
"replacement": "[PATIENT]",
"source": "ner",
"score": 0.921959400177002
},
{
"original": "ALEXANDRE",
"replacement": "[PATIENT]",
"source": "ner",
"score": 0.9067844152450562
},
{
"original": "SCANNER THORACO-ABDOMINO-PELVIEN",
"replacement": "[PERSONNE_4]",
"source": "ner",
"score": 0.805446445941925
},
{
"original": "VILLETTE Paul-Emile",
"replacement": "[PERSONNE_5]",
"source": "ner",
"score": 0.996815025806427
},
{
"original": "ILLETTE Paul-Emile Signé",
"replacement": "[PERSONNE_6]",
"source": "ner",
"score": 0.9780977964401245
},
{
"original": "VILLETTE Paul-Emile Signé",
"replacement": "[PERSONNE_7]",
"source": "ner",
"score": 0.9977920055389404
},
{
"original": "Bernadette",
"replacement": "[PERSONNE_8]",
"source": "ner",
"score": 0.9749005436897278
},
{
"original": "MAYA",
"replacement": "[PERSONNE_9]",
"source": "ner",
"score": 0.9772871136665344
},
{
"original": "Bernadette S",
"replacement": "[PERSONNE_10]",
"source": "ner",
"score": 0.9612787961959839
},
{
"original": "MAYA PATIENT L",
"replacement": "[PERSONNE_11]",
"source": "ner",
"score": 0.8045231699943542
},
{
"original": "VILLETTE",
"replacement": "[PERSONNE]",
"source": "ner",
"score": 0.9600419402122498
},
{
"original": "Paul-Emile AVIS",
"replacement": "[PERSONNE_12]",
"source": "ner",
"score": 0.9514685273170471
},
{
"original": "Paul-Emile VILLETTE",
"replacement": "[PERSONNE_13]",
"source": "ner",
"score": 0.9988292455673218
},
{
"original": "[MEDECIN",
"replacement": "[PERSONNE_14]",
"source": "ner",
"score": 0.9908351898193359
},
{
"original": "Maore MARTINEZ",
"replacement": "[PERSONNE_15]",
"source": "ner",
"score": 0.9966427683830261
},
{
"original": "Maria Del",
"replacement": "[PERSONNE_16]",
"source": "ner",
"score": 0.9784214496612549
},
{
"original": "[MEDECIN_3",
"replacement": "[PERSONNE_17]",
"source": "ner",
"score": 0.8680185079574585
},
{
"original": "Paul-Emile",
"replacement": "[PERSONNE]",
"source": "ner",
"score": 0.9331222772598267
},
{
"original": "QUILLACQ",
"replacement": "[PERSONNE_18]",
"source": "ner",
"score": 0.9334832429885864
},
{
"original": "[MEDECIN_36",
"replacement": "[PERSONNE_19]",
"source": "ner",
"score": 0.9609699249267578
},
{
"original": "[MEDECIN_",
"replacement": "[PERSONNE_20]",
"source": "ner",
"score": 0.9630196690559387
},
{
"original": "Alexis HAMON",
"replacement": "[PERSONNE_21]",
"source": "ner",
"score": 0.9896292686462402
},
{
"original": "J. LOEB",
"replacement": "[PERSONNE_22]",
"source": "ner",
"score": 0.8015127778053284
}
]
}