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 +1,123 @@
{
"source_file": "CRH 23158603.pdf",
"total_replacements": 111,
"regex_replacements": 87,
"ner_replacements": 9,
"sweep_replacements": 15,
"entities_found": [
{
"original": "10101431459",
"replacement": "[CODE_BARRE_1]",
"source": "regex",
"category": "code_barre"
},
{
"original": "secr.hdjcancero@ch-cotebasque.fr",
"replacement": "[EMAIL_1]",
"source": "regex",
"category": "email"
},
{
"original": "secr.oncogenetique@ch-cotebasque.fr",
"replacement": "[EMAIL_2]",
"source": "regex",
"category": "email"
},
{
"original": "secr.onco@ch-cotebasque.fr",
"replacement": "[EMAIL_3]",
"source": "regex",
"category": "email"
},
{
"original": "secr.hdjcancero@ch-cotebasque.fr",
"replacement": "[EMAIL_1]",
"source": "regex",
"category": "email"
},
{
"original": "secr.oncogenetique@ch-cotebasque.fr",
"replacement": "[EMAIL_2]",
"source": "regex",
"category": "email"
},
{
"original": "secr.onco@ch-cotebasque.fr",
"replacement": "[EMAIL_3]",
"source": "regex",
"category": "email"
},
{
"original": "secr.hdjcancero@ch-cotebasque.fr",
"replacement": "[EMAIL_1]",
"source": "regex",
"category": "email"
},
{
"original": "secr.oncogenetique@ch-cotebasque.fr",
"replacement": "[EMAIL_2]",
"source": "regex",
"category": "email"
},
{
"original": "secr.onco@ch-cotebasque.fr",
"replacement": "[EMAIL_3]",
"source": "regex",
"category": "email"
},
{
"original": "[MEDECIN_1",
"replacement": "[PERSONNE_1]",
"source": "ner",
"score": 0.9435539245605469
},
{
"original": "J. LOEB",
"replacement": "[PERSONNE_2]",
"source": "ner",
"score": 0.949508547782898
},
{
"original": "[PATIENT",
"replacement": "[PERSONNE_3]",
"source": "ner",
"score": 0.99375319480896
},
{
"original": "[MEDECIN_23",
"replacement": "[PERSONNE_4]",
"source": "ner",
"score": 0.9633160829544067
},
{
"original": "[MEDECIN_33",
"replacement": "[PERSONNE_5]",
"source": "ner",
"score": 0.9121456742286682
},
{
"original": "[MEDECIN_",
"replacement": "[PERSONNE_6]",
"source": "ner",
"score": 0.9834473729133606
},
{
"original": "[MEDECIN_34",
"replacement": "[PERSONNE_7]",
"source": "ner",
"score": 0.9395136833190918
},
{
"original": "[PATIENT_",
"replacement": "[PERSONNE_8]",
"source": "ner",
"score": 0.9452975988388062
},
{
"original": "POCHULU Jean",
"replacement": "[PERSONNE_9]",
"source": "ner",
"score": 0.9842320680618286
}
]
}

View File

@@ -0,0 +1,375 @@
{
"source_file": "trackare-22028007-23158603_22028007_23158603.pdf",
"total_replacements": 455,
"regex_replacements": 133,
"ner_replacements": 23,
"sweep_replacements": 299,
"entities_found": [
{
"original": "22028007",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "22028007",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "22028007",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "22028007",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "22028007",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "22028007",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "22028007",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "22028007",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "22028007",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "22028007",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "22028007",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "22028007",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "22028007",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "22028007",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "22028007",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "22028007",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "22028007",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "23158603",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23158603",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23158603",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23158603",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23158603",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23158603",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23158603",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23158603",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23158603",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23158603",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23158603",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23158603",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23158603",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23158603",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23158603",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23158603",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23158603",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "640000162",
"replacement": "[FINESS]",
"source": "regex",
"category": "finess"
},
{
"original": "99999",
"replacement": "[LIEU_NAISS_1]",
"source": "regex",
"category": "lieu_naissance"
},
{
"original": "99999",
"replacement": "[LIEU_NAISS_1]",
"source": "regex",
"category": "lieu_naissance"
},
{
"original": "BAYONNE",
"replacement": "[ADRESSE_2]",
"source": "regex",
"category": "lieu_naissance"
},
{
"original": "biologiste GUILLEMAUD",
"replacement": "[PERSONNE_1]",
"source": "ner",
"score": 0.9580286145210266
},
{
"original": "MOUZA Virgile",
"replacement": "[PERSONNE_2]",
"source": "ner",
"score": 0.996135413646698
},
{
"original": "Marie Pierre SERAULT",
"replacement": "[PERSONNE_3]",
"source": "ner",
"score": 0.9987727403640747
},
{
"original": "GOLDZAK Guillaume",
"replacement": "[PERSONNE_4]",
"source": "ner",
"score": 0.9897658228874207
},
{
"original": "LAROSA Emilie S",
"replacement": "[PERSONNE_5]",
"source": "ner",
"score": 0.9089062809944153
},
{
"original": "SINCALBRE Elorri",
"replacement": "[PERSONNE_6]",
"source": "ner",
"score": 0.9676617980003357
},
{
"original": "GOLDZAK Guillaume S",
"replacement": "[PERSONNE_7]",
"source": "ner",
"score": 0.9462111592292786
},
{
"original": "LAROSA Emilie",
"replacement": "[MEDECIN_22]",
"source": "ner",
"score": 0.9860962629318237
},
{
"original": "Elorri",
"replacement": "[PERSONNE]",
"source": "ner",
"score": 0.9641438126564026
},
{
"original": "SERAULT",
"replacement": "[PERSONNE]",
"source": "ner",
"score": 0.9359474182128906
},
{
"original": "Marie Pierre",
"replacement": "[PERSONNE_8]",
"source": "ner",
"score": 0.9787043333053589
},
{
"original": "LAROSA",
"replacement": "[MEDECIN]",
"source": "ner",
"score": 0.8669082522392273
},
{
"original": "F LARTIGUE AS",
"replacement": "[PERSONNE_9]",
"source": "ner",
"score": 0.9087257981300354
},
{
"original": "Etienne JAMES",
"replacement": "[PERSONNE_10]",
"source": "ner",
"score": 0.9870474338531494
},
{
"original": "Marina MUNIZ",
"replacement": "[PERSONNE_11]",
"source": "ner",
"score": 0.9955011010169983
},
{
"original": "DAGUERRE",
"replacement": "[MEDECIN]",
"source": "ner",
"score": 0.810282289981842
},
{
"original": "[MEDECIN_32",
"replacement": "[PERSONNE_12]",
"source": "ner",
"score": 0.8645762205123901
},
{
"original": "[MEDECIN_",
"replacement": "[PERSONNE_13]",
"source": "ner",
"score": 0.9751281142234802
},
{
"original": "GOLDZAK",
"replacement": "[MEDECIN_6]",
"source": "ner",
"score": 0.953009307384491
},
{
"original": "[MEDECIN",
"replacement": "[PERSONNE_14]",
"source": "ner",
"score": 0.9725476503372192
},
{
"original": "MEDECIN_",
"replacement": "[PERSONNE_15]",
"source": "ner",
"score": 0.8115683794021606
},
{
"original": "MEDECIN_32",
"replacement": "[PERSONNE_16]",
"source": "ner",
"score": 0.8919872641563416
},
{
"original": "POCHULU Marie",
"replacement": "[PERSONNE_17]",
"source": "ner",
"score": 0.9577308893203735
}
]
}