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 23124458.pdf",
"total_replacements": 25,
"regex_replacements": 10,
"ner_replacements": 12,
"sweep_replacements": 3,
"entities_found": [
{
"original": "23015166",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "ALBISTUR ORTIZ Hegoa",
"replacement": "[PERSONNE_1]",
"source": "ner",
"score": 0.9903602600097656
},
{
"original": "SAURHANET Nelly",
"replacement": "[PERSONNE_2]",
"source": "ner",
"score": 0.9976188540458679
},
{
"original": "GUADAGNIN Emeline",
"replacement": "[PERSONNE_3]",
"source": "ner",
"score": 0.9965705871582031
},
{
"original": "ALBISTUR ORTIZ",
"replacement": "[PERSONNE_4]",
"source": "ner",
"score": 0.9983018636703491
},
{
"original": "Partiel ALBISTUR ORTIZ Hegoa",
"replacement": "[PERSONNE_5]",
"source": "ner",
"score": 0.8802451491355896
},
{
"original": "DECOEUR Lucie",
"replacement": "[MEDECIN_10]",
"source": "ner",
"score": 0.997063398361206
},
{
"original": "[MEDECIN_",
"replacement": "[PERSONNE_6]",
"source": "ner",
"score": 0.9003594517707825
},
{
"original": "MONIER Laurie Assistant",
"replacement": "[PERSONNE_7]",
"source": "ner",
"score": 0.9186714887619019
},
{
"original": "GUILLEMAUD Julien",
"replacement": "[MEDECIN_6]",
"source": "ner",
"score": 0.9982811808586121
},
{
"original": "[MEDECIN",
"replacement": "[PERSONNE_8]",
"source": "ner",
"score": 0.9172883033752441
},
{
"original": "LEYSSENE David",
"replacement": "[MEDECIN_3]",
"source": "ner",
"score": 0.9977222681045532
},
{
"original": "Jacques Loëb",
"replacement": "[PERSONNE_9]",
"source": "ner",
"score": 0.9700530767440796
}
]
}

View File

@@ -0,0 +1,201 @@
{
"source_file": "CRH 23124458.pdf",
"total_replacements": 214,
"regex_replacements": 113,
"ner_replacements": 31,
"sweep_replacements": 70,
"entities_found": [
{
"original": "10004040993",
"replacement": "[CODE_BARRE_1]",
"source": "regex",
"category": "code_barre"
},
{
"original": "[PATIENT_15",
"replacement": "[PERSONNE_1]",
"source": "ner",
"score": 0.9384142756462097
},
{
"original": "[MEDECIN_45",
"replacement": "[PERSONNE_2]",
"source": "ner",
"score": 0.9106758236885071
},
{
"original": "Marie-Elise PICAMILH",
"replacement": "[MEDECIN_23]",
"source": "ner",
"score": 0.9989234805107117
},
{
"original": "[MEDEC",
"replacement": "[PERSONNE_3]",
"source": "ner",
"score": 0.925540566444397
},
{
"original": "] DUBREL Marie",
"replacement": "[PERSONNE_4]",
"source": "ner",
"score": 0.9144536852836609
},
{
"original": "Claudine EMBAREK",
"replacement": "[MEDECIN_5]",
"source": "ner",
"score": 0.9987832307815552
},
{
"original": "Camille OGER",
"replacement": "[MEDECIN_18]",
"source": "ner",
"score": 0.9987993240356445
},
{
"original": "Justine LABAT",
"replacement": "[MEDECIN_16]",
"source": "ner",
"score": 0.9988702535629272
},
{
"original": "Hélène LANGLOIS MEURINNE",
"replacement": "[MEDECIN_65]",
"source": "ner",
"score": 0.9989079236984253
},
{
"original": "] Kaiet ECHEVERRIA-ARRUTY",
"replacement": "[PERSONNE_5]",
"source": "ner",
"score": 0.9724884629249573
},
{
"original": "Fanny HENAFF",
"replacement": "[MEDECIN_11]",
"source": "ner",
"score": 0.9972292184829712
},
{
"original": "[MEDECIN",
"replacement": "[PERSONNE_6]",
"source": "ner",
"score": 0.9640213847160339
},
{
"original": "[MEDECIN_59",
"replacement": "[PERSONNE_7]",
"source": "ner",
"score": 0.9377742409706116
},
{
"original": "[MEDECIN_60",
"replacement": "[PERSONNE_8]",
"source": "ner",
"score": 0.9669840931892395
},
{
"original": "[MEDECIN_61",
"replacement": "[PERSONNE_9]",
"source": "ner",
"score": 0.9713125228881836
},
{
"original": "[MEDECIN_62",
"replacement": "[PERSONNE_10]",
"source": "ner",
"score": 0.9707228541374207
},
{
"original": "[MEDECIN_",
"replacement": "[PERSONNE_11]",
"source": "ner",
"score": 0.995354950428009
},
{
"original": "J. LOEB",
"replacement": "[PERSONNE_12]",
"source": "ner",
"score": 0.8524518013000488
},
{
"original": "[PATIENT_",
"replacement": "[PERSONNE_13]",
"source": "ner",
"score": 0.9974108934402466
},
{
"original": "[PATIENT_12",
"replacement": "[PERSONNE_14]",
"source": "ner",
"score": 0.9495763778686523
},
{
"original": "Mme [PATIENT_",
"replacement": "[PERSONNE_15]",
"source": "ner",
"score": 0.9424459338188171
},
{
"original": "Mme [PATIENT_16",
"replacement": "[PERSONNE_16]",
"source": "ner",
"score": 0.8734727501869202
},
{
"original": "Dr [MEDECIN_",
"replacement": "[PERSONNE_17]",
"source": "ner",
"score": 0.9693799018859863
},
{
"original": "Caroline DE BARBEYRAC",
"replacement": "[MEDECIN_51]",
"source": "ner",
"score": 0.9971485137939453
},
{
"original": "[MEDECIN_77",
"replacement": "[PERSONNE_18]",
"source": "ner",
"score": 0.9761663675308228
},
{
"original": "[MEDECIN_78",
"replacement": "[PERSONNE_19]",
"source": "ner",
"score": 0.948344349861145
},
{
"original": "[MEDECIN_79",
"replacement": "[PERSONNE_20]",
"source": "ner",
"score": 0.9467739462852478
},
{
"original": "ALBISTUR ORTIZ Hegoa",
"replacement": "[PERSONNE_21]",
"source": "ner",
"score": 0.9914951324462891
},
{
"original": "[MEDECIN_66",
"replacement": "[PERSONNE_22]",
"source": "ner",
"score": 0.9290882349014282
},
{
"original": "[MEDECIN_2",
"replacement": "[PERSONNE_23]",
"source": "ner",
"score": 0.8352255821228027
},
{
"original": "[MEDECIN_83",
"replacement": "[PERSONNE_24]",
"source": "ner",
"score": 0.9006388783454895
}
]
}

View File

@@ -0,0 +1,501 @@
{
"source_file": "trackare-23015166-23124458_23015166_23124458.pdf",
"total_replacements": 748,
"regex_replacements": 147,
"ner_replacements": 30,
"sweep_replacements": 571,
"entities_found": [
{
"original": "23015166",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "23015166",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "23015166",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "23015166",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "23015166",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "23015166",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "23015166",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "23015166",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "23015166",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "23015166",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "23015166",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "23015166",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "23015166",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "23015166",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "23015166",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "23015166",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "23015166",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "23015166",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "23015166",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "23015166",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "23015166",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "23015166",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "23015166",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "23015166",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "23124458",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23124458",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23124458",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23124458",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23124458",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23124458",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23124458",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23124458",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23124458",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23124458",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23124458",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23124458",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23124458",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23124458",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23124458",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23124458",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23124458",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23124458",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23124458",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23124458",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23124458",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23124458",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23124458",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23124458",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "217076410231986",
"replacement": "[NIR_1]",
"source": "regex",
"category": "nir"
},
{
"original": "640000162",
"replacement": "[FINESS]",
"source": "regex",
"category": "finess"
},
{
"original": "64102",
"replacement": "[LIEU_NAISS_2]",
"source": "regex",
"category": "lieu_naissance"
},
{
"original": "BAYONNE",
"replacement": "[LIEU_NAISS_1]",
"source": "regex",
"category": "lieu_naissance"
},
{
"original": "HEGOA ALBISTUR ORTIZ",
"replacement": "[PERSONNE_1]",
"source": "ner",
"score": 0.9892328977584839
},
{
"original": "MEDECIN_",
"replacement": "[PERSONNE_2]",
"source": "ner",
"score": 0.8462562561035156
},
{
"original": "GUILLEMAUD GUILLEMAUD JAOUEN",
"replacement": "[PERSONNE_3]",
"source": "ner",
"score": 0.9990389347076416
},
{
"original": "David LEYSSENE",
"replacement": "[PERSONNE_4]",
"source": "ner",
"score": 0.9984779357910156
},
{
"original": "[MEDECIN_",
"replacement": "[PERSONNE_5]",
"source": "ner",
"score": 0.899258553981781
},
{
"original": "Streptococcus",
"replacement": "[PERSONNE_6]",
"source": "ner",
"score": 0.9294036030769348
},
{
"original": "Staphylococcus",
"replacement": "[PERSONNE_7]",
"source": "ner",
"score": 0.8922439813613892
},
{
"original": "HEGOA",
"replacement": "[PATIENT]",
"source": "ner",
"score": 0.9634947180747986
},
{
"original": "ALBISTUR ORTIZ",
"replacement": "[PERSONNE_8]",
"source": "ner",
"score": 0.9959861040115356
},
{
"original": "GARLITO Justine",
"replacement": "[PERSONNE_9]",
"source": "ner",
"score": 0.9972106218338013
},
{
"original": "EGGER Justine",
"replacement": "[PERSONNE_10]",
"source": "ner",
"score": 0.9827560186386108
},
{
"original": "GUADAGNIN Signé",
"replacement": "[PERSONNE_11]",
"source": "ner",
"score": 0.9682253003120422
},
{
"original": "GARLITO Justine S",
"replacement": "[PERSONNE_12]",
"source": "ner",
"score": 0.968344509601593
},
{
"original": "GUADAGNIN S",
"replacement": "[PERSONNE_13]",
"source": "ner",
"score": 0.987592875957489
},
{
"original": "Emeline SURV",
"replacement": "[PERSONNE_14]",
"source": "ner",
"score": 0.9946624636650085
},
{
"original": "SURV",
"replacement": "[PERSONNE]",
"source": "ner",
"score": 0.9121637344360352
},
{
"original": "GUADAGNIN",
"replacement": "[MEDECIN]",
"source": "ner",
"score": 0.9890344142913818
},
{
"original": "GUADAGNIN Emeline Signé",
"replacement": "[PERSONNE_15]",
"source": "ner",
"score": 0.9984012246131897
},
{
"original": "GUADAGNIN Emeline",
"replacement": "[MEDECIN_13]",
"source": "ner",
"score": 0.9960675239562988
},
{
"original": "Caroline KT",
"replacement": "[PERSONNE_16]",
"source": "ner",
"score": 0.8856193423271179
},
{
"original": "Justine VVP",
"replacement": "[PERSONNE_17]",
"source": "ner",
"score": 0.9734970331192017
},
{
"original": "Emeline S",
"replacement": "[PERSONNE_18]",
"source": "ner",
"score": 0.8612241744995117
},
{
"original": "Emeline",
"replacement": "[MEDECIN]",
"source": "ner",
"score": 0.9430866241455078
},
{
"original": "Emeline Signé",
"replacement": "[PERSONNE_19]",
"source": "ner",
"score": 0.8903361558914185
},
{
"original": "Emeline GUADAGNIN",
"replacement": "[PERSONNE_20]",
"source": "ner",
"score": 0.997286319732666
},
{
"original": "Justine EGGER",
"replacement": "[PERSONNE_21]",
"source": "ner",
"score": 0.9843853116035461
},
{
"original": "[MEDECIN_2",
"replacement": "[PERSONNE_22]",
"source": "ner",
"score": 0.8746642470359802
},
{
"original": "Lise TEITON",
"replacement": "[SOIGNANT_10]",
"source": "ner",
"score": 0.9924712181091309
},
{
"original": "Kaiet",
"replacement": "[PERSONNE_23]",
"source": "ner",
"score": 0.9384632706642151
},
{
"original": "Clara SAUTERON",
"replacement": "[PERSONNE_24]",
"source": "ner",
"score": 0.9653941988945007
}
]
}