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 +1,81 @@
{
"source_file": "BACTERIO 23168633.pdf",
"total_replacements": 25,
"regex_replacements": 10,
"ner_replacements": 11,
"sweep_replacements": 4,
"entities_found": [
{
"original": "20025680",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "KHALLOUKI",
"replacement": "[PERSONNE_1]",
"source": "ner",
"score": 0.9874451756477356
},
{
"original": "SAMIH Soad",
"replacement": "[PERSONNE_2]",
"source": "ner",
"score": 0.9789446592330933
},
{
"original": "MATERNOWSKI Paul Jean",
"replacement": "[PERSONNE_3]",
"source": "ner",
"score": 0.9987320899963379
},
{
"original": "Partiel SAMIH Soad",
"replacement": "[PERSONNE_4]",
"source": "ner",
"score": 0.9819852709770203
},
{
"original": "DECOEUR Lucie",
"replacement": "[MEDECIN_10]",
"source": "ner",
"score": 0.9966906309127808
},
{
"original": "[MEDECIN_",
"replacement": "[PERSONNE_5]",
"source": "ner",
"score": 0.886359691619873
},
{
"original": "MONIER Laurie Assistant",
"replacement": "[PERSONNE_6]",
"source": "ner",
"score": 0.9014897346496582
},
{
"original": "GUILLEMAUD Julien",
"replacement": "[MEDECIN_6]",
"source": "ner",
"score": 0.9982249140739441
},
{
"original": "[MEDECIN",
"replacement": "[PERSONNE_7]",
"source": "ner",
"score": 0.9131426811218262
},
{
"original": "LEYSSENE David",
"replacement": "[MEDECIN_3]",
"source": "ner",
"score": 0.9979294538497925
},
{
"original": "Jacques Loëb",
"replacement": "[PERSONNE_8]",
"source": "ner",
"score": 0.9700453877449036
}
]
}

View File

@@ -0,0 +1,33 @@
{
"source_file": "CRO 23168633.pdf",
"total_replacements": 13,
"regex_replacements": 9,
"ner_replacements": 3,
"sweep_replacements": 1,
"entities_found": [
{
"original": "288099935097217",
"replacement": "[NIR_1]",
"source": "regex",
"category": "nir"
},
{
"original": "Jackson-Pratt",
"replacement": "[PERSONNE_1]",
"source": "ner",
"score": 0.9692654013633728
},
{
"original": "Callot",
"replacement": "[PERSONNE_2]",
"source": "ner",
"score": 0.9455417394638062
},
{
"original": "Veress",
"replacement": "[PERSONNE_3]",
"source": "ner",
"score": 0.9411869049072266
}
]
}

View File

@@ -0,0 +1,663 @@
{
"source_file": "trackare-20025680-23168633_20025680_23168633.pdf",
"total_replacements": 894,
"regex_replacements": 149,
"ner_replacements": 56,
"sweep_replacements": 689,
"entities_found": [
{
"original": "20025680",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "20025680",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "20025680",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "20025680",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "20025680",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "20025680",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "20025680",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "20025680",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "20025680",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "20025680",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "20025680",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "20025680",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "20025680",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "20025680",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "20025680",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "20025680",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "20025680",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "20025680",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "20025680",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "20025680",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "20025680",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "20025680",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "20025680",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "20025680",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "20025680",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "23168633",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23168633",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23168633",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23168633",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23168633",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23168633",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23168633",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23168633",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23168633",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23168633",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23168633",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23168633",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23168633",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23168633",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23168633",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23168633",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23168633",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23168633",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23168633",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23168633",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23168633",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23168633",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23168633",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23168633",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23168633",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "640000162",
"replacement": "[FINESS]",
"source": "regex",
"category": "finess"
},
{
"original": "99999",
"replacement": "[LIEU_NAISS_2]",
"source": "regex",
"category": "lieu_naissance"
},
{
"original": "KHALIFA",
"replacement": "[LIEU_NAISS_1]",
"source": "regex",
"category": "lieu_naissance"
},
{
"original": "Jackson",
"replacement": "[PERSONNE_1]",
"source": "ner",
"score": 0.8523516654968262
},
{
"original": "Madame [PATIENT_",
"replacement": "[PERSONNE_2]",
"source": "ner",
"score": 0.9026157259941101
},
{
"original": "BURTIN BURTIN BURTIN BURTIN",
"replacement": "[PERSONNE_3]",
"source": "ner",
"score": 0.9853159785270691
},
{
"original": "MEDECIN_12",
"replacement": "[PERSONNE_4]",
"source": "ner",
"score": 0.8762514591217041
},
{
"original": "MEDECIN_",
"replacement": "[PERSONNE_5]",
"source": "ner",
"score": 0.9532815217971802
},
{
"original": "SOAD",
"replacement": "[PATIENT]",
"source": "ner",
"score": 0.9093731045722961
},
{
"original": "KHALLOUKI",
"replacement": "[PATIENT]",
"source": "ner",
"score": 0.9260910153388977
},
{
"original": "PAUCHET Marine",
"replacement": "[PERSONNE_6]",
"source": "ner",
"score": 0.9961813688278198
},
{
"original": "RIA VANBERSY Garazi",
"replacement": "[PERSONNE_7]",
"source": "ner",
"score": 0.9407550096511841
},
{
"original": "DUPIN Adeline",
"replacement": "[PERSONNE_8]",
"source": "ner",
"score": 0.992453396320343
},
{
"original": "VANBERSY Garazi Réalisé",
"replacement": "[PERSONNE_9]",
"source": "ner",
"score": 0.9936085939407349
},
{
"original": "10MG MATERNOWSKI Paul",
"replacement": "[PERSONNE_10]",
"source": "ner",
"score": 0.971923291683197
},
{
"original": "MG MATERNOWSKI Paul",
"replacement": "[PERSONNE_11]",
"source": "ner",
"score": 0.9467874765396118
},
{
"original": "PHLOROGLUCINOL AR",
"replacement": "[PERSONNE_12]",
"source": "ner",
"score": 0.9668328762054443
},
{
"original": "TAGHVA PASSAND",
"replacement": "[PERSONNE_13]",
"source": "ner",
"score": 0.9980204701423645
},
{
"original": "ECHEVERRIA VANBERSY Garazi",
"replacement": "[PERSONNE_14]",
"source": "ner",
"score": 0.99167400598526
},
{
"original": "CHEVERRIA VANBERSY Garazi",
"replacement": "[PERSONNE_15]",
"source": "ner",
"score": 0.9362767934799194
},
{
"original": "VERRIA VANBERSY Garazi Réalisé",
"replacement": "[PERSONNE_16]",
"source": "ner",
"score": 0.9762164950370789
},
{
"original": "PAUCHET Marine Réalisé",
"replacement": "[PERSONNE_17]",
"source": "ner",
"score": 0.9618291854858398
},
{
"original": "PAUCHET Marine Réalisé — PLAIE-COLLE",
"replacement": "[PERSONNE_18]",
"source": "ner",
"score": 0.984612226486206
},
{
"original": "Marie Helene DUHALDE",
"replacement": "[PERSONNE_19]",
"source": "ner",
"score": 0.9991152286529541
},
{
"original": "JOEST Loïc",
"replacement": "[PERSONNE_20]",
"source": "ner",
"score": 0.9970272183418274
},
{
"original": "JOEST Loïc Réalisé",
"replacement": "[PERSONNE_21]",
"source": "ner",
"score": 0.8305507898330688
},
{
"original": "A VANBERSY Garazi",
"replacement": "[PERSONNE_22]",
"source": "ner",
"score": 0.8404524922370911
},
{
"original": "MATERNOWSKI Paul",
"replacement": "[PERSONNE_23]",
"source": "ner",
"score": 0.9942271113395691
},
{
"original": "SERESTA",
"replacement": "[PERSONNE_24]",
"source": "ner",
"score": 0.9926958084106445
},
{
"original": "PHLOROGLUCINOL",
"replacement": "[PERSONNE]",
"source": "ner",
"score": 0.9971251487731934
},
{
"original": "VANBERSY Garazi",
"replacement": "[PERSONNE_25]",
"source": "ner",
"score": 0.9987702369689941
},
{
"original": "PUJOS Marion",
"replacement": "[PERSONNE_26]",
"source": "ner",
"score": 0.9408779740333557
},
{
"original": "TAGHVA PASSAND Goudarz",
"replacement": "[PERSONNE_27]",
"source": "ner",
"score": 0.9987245798110962
},
{
"original": "TAGHVA",
"replacement": "[PERSONNE]",
"source": "ner",
"score": 0.9942665100097656
},
{
"original": "Goudarz",
"replacement": "[PERSONNE]",
"source": "ner",
"score": 0.9437001347541809
},
{
"original": "rub Goudarz",
"replacement": "[PERSONNE_28]",
"source": "ner",
"score": 0.8216049075126648
},
{
"original": "Marine REDON",
"replacement": "[PERSONNE_29]",
"source": "ner",
"score": 0.8926295638084412
},
{
"original": "Marine PLAIE-C",
"replacement": "[PERSONNE_30]",
"source": "ner",
"score": 0.8194146156311035
},
{
"original": "DUHALDE ONGLES",
"replacement": "[PERSONNE_31]",
"source": "ner",
"score": 0.9121792316436768
},
{
"original": "Helene PROTHESES",
"replacement": "[PERSONNE_32]",
"source": "ner",
"score": 0.9903044104576111
},
{
"original": "Marie BIJOUX",
"replacement": "[PERSONNE_33]",
"source": "ner",
"score": 0.9550992250442505
},
{
"original": "DUHALDE VERIF",
"replacement": "[PERSONNE_34]",
"source": "ner",
"score": 0.8374776244163513
},
{
"original": "DUHALDE Marie",
"replacement": "[PERSONNE_35]",
"source": "ner",
"score": 0.9859578013420105
},
{
"original": "Helene TOILETTE HIBISCRUB",
"replacement": "[PERSONNE_36]",
"source": "ner",
"score": 0.9009492993354797
},
{
"original": "DUHALDE Marie TOILETTE",
"replacement": "[PERSONNE_37]",
"source": "ner",
"score": 0.839920163154602
},
{
"original": "Helene TOILETTE BETASCRUB",
"replacement": "[PERSONNE_38]",
"source": "ner",
"score": 0.8865741491317749
},
{
"original": "Marie TOILETTE DOUCHE",
"replacement": "[PERSONNE_39]",
"source": "ner",
"score": 0.947348952293396
},
{
"original": "Loïc JOEST",
"replacement": "[PERSONNE_40]",
"source": "ner",
"score": 0.9921822547912598
},
{
"original": "DUPIN Marie",
"replacement": "[PERSONNE_41]",
"source": "ner",
"score": 0.818916380405426
},
{
"original": "Helene BLOC",
"replacement": "[PERSONNE_42]",
"source": "ner",
"score": 0.9898597598075867
},
{
"original": "Helene fois",
"replacement": "[PERSONNE_43]",
"source": "ner",
"score": 0.9833483695983887
},
{
"original": "VANBERSY Marie",
"replacement": "[PERSONNE_44]",
"source": "ner",
"score": 0.9899392127990723
},
{
"original": "Goudarz TAGHVA PASSAND",
"replacement": "[PERSONNE_45]",
"source": "ner",
"score": 0.9989483952522278
},
{
"original": "Paul Jean MATERNOWSKI",
"replacement": "[PERSONNE_46]",
"source": "ner",
"score": 0.9989637732505798
},
{
"original": "Marion PUJOS",
"replacement": "[SOIGNANT_10]",
"source": "ner",
"score": 0.9902686476707458
},
{
"original": "Paul Jean",
"replacement": "[PERSONNE_47]",
"source": "ner",
"score": 0.8922203183174133
},
{
"original": "VANBERSY Goudarz",
"replacement": "[PERSONNE_48]",
"source": "ner",
"score": 0.8099955916404724
},
{
"original": "Nolwenn BARRE",
"replacement": "[PERSONNE_49]",
"source": "ner",
"score": 0.9672141075134277
},
{
"original": "MATERNOWSKI",
"replacement": "[PERSONNE]",
"source": "ner",
"score": 0.9882259368896484
}
]
}