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 +1,8 @@
{
"source_file": "ANAPATH 23148798.pdf",
"total_replacements": 0,
"regex_replacements": 0,
"ner_replacements": 0,
"sweep_replacements": 0,
"entities_found": []
}

View File

@@ -0,0 +1,285 @@
{
"source_file": "CRH 23148798.pdf",
"total_replacements": 173,
"regex_replacements": 114,
"ner_replacements": 12,
"sweep_replacements": 47,
"entities_found": [
{
"original": "10100541860",
"replacement": "[CODE_BARRE_1]",
"source": "regex",
"category": "code_barre"
},
{
"original": "secr.pneumo@ch-cotebasque.fr",
"replacement": "[EMAIL_1]",
"source": "regex",
"category": "email"
},
{
"original": "sschneider@ch-cotebasque.fr",
"replacement": "[EMAIL_2]",
"source": "regex",
"category": "email"
},
{
"original": "msabatini@ch-cotebasque.fr",
"replacement": "[EMAIL_3]",
"source": "regex",
"category": "email"
},
{
"original": "prigaud@ch-cotebasque.fr",
"replacement": "[EMAIL_4]",
"source": "regex",
"category": "email"
},
{
"original": "cnocent@ch-cotebasque.fr",
"replacement": "[EMAIL_5]",
"source": "regex",
"category": "email"
},
{
"original": "jpmathieu@ch-cotebasque.fr",
"replacement": "[EMAIL_6]",
"source": "regex",
"category": "email"
},
{
"original": "lmasse@ch-cotebasque.fr",
"replacement": "[EMAIL_7]",
"source": "regex",
"category": "email"
},
{
"original": "clethrosne@ch-cotebasque.fr",
"replacement": "[EMAIL_8]",
"source": "regex",
"category": "email"
},
{
"original": "dbonnet@ch-cotebasque.fr",
"replacement": "[EMAIL_9]",
"source": "regex",
"category": "email"
},
{
"original": "eabraham@ch-cotebasque.fr",
"replacement": "[EMAIL_10]",
"source": "regex",
"category": "email"
},
{
"original": "eellie@ch-cotebasque.fr",
"replacement": "[EMAIL_11]",
"source": "regex",
"category": "email"
},
{
"original": "secr.pneumo@ch-cotebasque.fr",
"replacement": "[EMAIL_1]",
"source": "regex",
"category": "email"
},
{
"original": "sschneider@ch-cotebasque.fr",
"replacement": "[EMAIL_2]",
"source": "regex",
"category": "email"
},
{
"original": "msabatini@ch-cotebasque.fr",
"replacement": "[EMAIL_3]",
"source": "regex",
"category": "email"
},
{
"original": "prigaud@ch-cotebasque.fr",
"replacement": "[EMAIL_4]",
"source": "regex",
"category": "email"
},
{
"original": "cnocent@ch-cotebasque.fr",
"replacement": "[EMAIL_5]",
"source": "regex",
"category": "email"
},
{
"original": "jpmathieu@ch-cotebasque.fr",
"replacement": "[EMAIL_6]",
"source": "regex",
"category": "email"
},
{
"original": "lmasse@ch-cotebasque.fr",
"replacement": "[EMAIL_7]",
"source": "regex",
"category": "email"
},
{
"original": "clethrosne@ch-cotebasque.fr",
"replacement": "[EMAIL_8]",
"source": "regex",
"category": "email"
},
{
"original": "dbonnet@ch-cotebasque.fr",
"replacement": "[EMAIL_9]",
"source": "regex",
"category": "email"
},
{
"original": "eabraham@ch-cotebasque.fr",
"replacement": "[EMAIL_10]",
"source": "regex",
"category": "email"
},
{
"original": "eellie@ch-cotebasque.fr",
"replacement": "[EMAIL_11]",
"source": "regex",
"category": "email"
},
{
"original": "secr.pneumo@ch-cotebasque.fr",
"replacement": "[EMAIL_1]",
"source": "regex",
"category": "email"
},
{
"original": "sschneider@ch-cotebasque.fr",
"replacement": "[EMAIL_2]",
"source": "regex",
"category": "email"
},
{
"original": "msabatini@ch-cotebasque.fr",
"replacement": "[EMAIL_3]",
"source": "regex",
"category": "email"
},
{
"original": "prigaud@ch-cotebasque.fr",
"replacement": "[EMAIL_4]",
"source": "regex",
"category": "email"
},
{
"original": "cnocent@ch-cotebasque.fr",
"replacement": "[EMAIL_5]",
"source": "regex",
"category": "email"
},
{
"original": "jpmathieu@ch-cotebasque.fr",
"replacement": "[EMAIL_6]",
"source": "regex",
"category": "email"
},
{
"original": "lmasse@ch-cotebasque.fr",
"replacement": "[EMAIL_7]",
"source": "regex",
"category": "email"
},
{
"original": "clethrosne@ch-cotebasque.fr",
"replacement": "[EMAIL_8]",
"source": "regex",
"category": "email"
},
{
"original": "dbonnet@ch-cotebasque.fr",
"replacement": "[EMAIL_9]",
"source": "regex",
"category": "email"
},
{
"original": "eabraham@ch-cotebasque.fr",
"replacement": "[EMAIL_10]",
"source": "regex",
"category": "email"
},
{
"original": "eellie@ch-cotebasque.fr",
"replacement": "[EMAIL_11]",
"source": "regex",
"category": "email"
},
{
"original": "[PATIENT_2",
"replacement": "[PERSONNE_1]",
"source": "ner",
"score": 0.9229361414909363
},
{
"original": "[MEDECIN",
"replacement": "[PERSONNE_2]",
"source": "ner",
"score": 0.9816927909851074
},
{
"original": "[MEDECIN_",
"replacement": "[PERSONNE_3]",
"source": "ner",
"score": 0.99141526222229
},
{
"original": "[MEDEC",
"replacement": "[PERSONNE_4]",
"source": "ner",
"score": 0.8633410334587097
},
{
"original": "[PATIENT",
"replacement": "[PERSONNE_5]",
"source": "ner",
"score": 0.9630032181739807
},
{
"original": "J. LOEB",
"replacement": "[PERSONNE_6]",
"source": "ner",
"score": 0.9365915060043335
},
{
"original": "[MEDECIN_12",
"replacement": "[PERSONNE_7]",
"source": "ner",
"score": 0.9372633099555969
},
{
"original": "Pierre Rigaud",
"replacement": "[MEDECIN_10]",
"source": "ner",
"score": 0.9751806855201721
},
{
"original": "MEDEC",
"replacement": "[PERSONNE_8]",
"source": "ner",
"score": 0.867510974407196
},
{
"original": "ne J. LOEB",
"replacement": "[PERSONNE_9]",
"source": "ner",
"score": 0.8669859170913696
},
{
"original": "Bricker",
"replacement": "[PERSONNE_10]",
"source": "ner",
"score": 0.9593000411987305
},
{
"original": "DE MARI Patrick",
"replacement": "[PERSONNE_11]",
"source": "ner",
"score": 0.9643693566322327
}
]
}

View File

@@ -0,0 +1,369 @@
{
"source_file": "trackare-00263792-23148798_00263792_23148798.pdf",
"total_replacements": 388,
"regex_replacements": 119,
"ner_replacements": 22,
"sweep_replacements": 247,
"entities_found": [
{
"original": "00263792",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "00263792",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "00263792",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "00263792",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "00263792",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "00263792",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "00263792",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "00263792",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "00263792",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "00263792",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "00263792",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "00263792",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "00263792",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "00263792",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "00263792",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "23148798",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23148798",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23148798",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23148798",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23148798",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23148798",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23148798",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23148798",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23148798",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23148798",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23148798",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23148798",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23148798",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23148798",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23148798",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "148067510804448",
"replacement": "[NIR_1]",
"source": "regex",
"category": "nir"
},
{
"original": "148067510804448",
"replacement": "[NIR_1]",
"source": "regex",
"category": "nir"
},
{
"original": "148067510804448",
"replacement": "[NIR_1]",
"source": "regex",
"category": "nir"
},
{
"original": "640000162",
"replacement": "[FINESS]",
"source": "regex",
"category": "finess"
},
{
"original": "75108",
"replacement": "[LIEU_NAISS_2]",
"source": "regex",
"category": "lieu_naissance"
},
{
"original": "75108",
"replacement": "[LIEU_NAISS_2]",
"source": "regex",
"category": "lieu_naissance"
},
{
"original": "75108",
"replacement": "[LIEU_NAISS_2]",
"source": "regex",
"category": "lieu_naissance"
},
{
"original": "PARIS 08",
"replacement": "[LIEU_NAISS_1]",
"source": "regex",
"category": "lieu_naissance"
},
{
"original": "GUILLEMAUD GUILLEMAUD GUILLEMAUD GUILLEMAUD GUILLEMAUD",
"replacement": "[PERSONNE_1]",
"source": "ner",
"score": 0.994825005531311
},
{
"original": "[MEDECIN_16",
"replacement": "[PERSONNE_2]",
"source": "ner",
"score": 0.9235275983810425
},
{
"original": "[MEDECIN_17",
"replacement": "[PERSONNE_3]",
"source": "ner",
"score": 0.9375349283218384
},
{
"original": "[MEDECIN_11",
"replacement": "[PERSONNE_4]",
"source": "ner",
"score": 0.9755138754844666
},
{
"original": "PATRICK",
"replacement": "[PATIENT]",
"source": "ner",
"score": 0.9456043243408203
},
{
"original": "DE MARI",
"replacement": "[PERSONNE_5]",
"source": "ner",
"score": 0.9157589077949524
},
{
"original": "RIGAUD Pierre Signé",
"replacement": "[PERSONNE_6]",
"source": "ner",
"score": 0.9900218844413757
},
{
"original": "Anna Signé",
"replacement": "[PERSONNE_7]",
"source": "ner",
"score": 0.9874547123908997
},
{
"original": "MALECK MAMODE S",
"replacement": "[PERSONNE_8]",
"source": "ner",
"score": 0.9743509888648987
},
{
"original": "MALECK MAMODE Anna Signé",
"replacement": "[PERSONNE_9]",
"source": "ner",
"score": 0.998128354549408
},
{
"original": "MALECK MAMODE",
"replacement": "[PERSONNE_10]",
"source": "ner",
"score": 0.9931924343109131
},
{
"original": "VALETTE Alexandra",
"replacement": "[PERSONNE_11]",
"source": "ner",
"score": 0.984900951385498
},
{
"original": "MALECK MAMODE Anna",
"replacement": "[PERSONNE_12]",
"source": "ner",
"score": 0.9975845217704773
},
{
"original": "Anna",
"replacement": "[PERSONNE]",
"source": "ner",
"score": 0.9269949197769165
},
{
"original": "Anna MALECK MAMODE",
"replacement": "[PERSONNE_13]",
"source": "ner",
"score": 0.9984478950500488
},
{
"original": "Alexia ANDRE",
"replacement": "[PERSONNE_14]",
"source": "ner",
"score": 0.9984251856803894
},
{
"original": "Anna MALECK",
"replacement": "[PERSONNE_15]",
"source": "ner",
"score": 0.9980485439300537
},
{
"original": "Pierre Rigaud",
"replacement": "[MEDECIN_7]",
"source": "ner",
"score": 0.8489577174186707
},
{
"original": "[MEDECIN",
"replacement": "[PERSONNE_16]",
"source": "ner",
"score": 0.9951136708259583
},
{
"original": "[MEDECIN_",
"replacement": "[PERSONNE_17]",
"source": "ner",
"score": 0.9176616072654724
},
{
"original": "LESCARRET Chloe",
"replacement": "[PERSONNE_18]",
"source": "ner",
"score": 0.86967533826828
},
{
"original": "LESCARRET CLAUDE FRANCE",
"replacement": "[PERSONNE_19]",
"source": "ner",
"score": 0.8902583718299866
}
]
}