Files
anonymisation/tests/ground_truth/analysis/medical_stopwords_candidates.json

283 lines
4.6 KiB
JSON

{
"extraction_date": "2026-03-02",
"total_detections": 3846,
"unique_terms": 316,
"frequent_terms_count": 196,
"medical_terms_count": 7,
"top_50_frequent": [
{
"term": "lucie",
"count": 188,
"is_medical": false
},
{
"term": "schmitt",
"count": 185,
"is_medical": false
},
{
"term": "masse",
"count": 170,
"is_medical": false
},
{
"term": "laurence",
"count": 138,
"is_medical": false
},
{
"term": "belleau",
"count": 135,
"is_medical": false
},
{
"term": "céline",
"count": 124,
"is_medical": false
},
{
"term": "justine",
"count": 96,
"is_medical": false
},
{
"term": "burg",
"count": 96,
"is_medical": false
},
{
"term": "schneider",
"count": 90,
"is_medical": false
},
{
"term": "sophie",
"count": 74,
"is_medical": false
},
{
"term": "aguer",
"count": 74,
"is_medical": false
},
{
"term": "kasparian",
"count": 68,
"is_medical": false
},
{
"term": "alexandra",
"count": 64,
"is_medical": false
},
{
"term": "valette",
"count": 63,
"is_medical": false
},
{
"term": "buccale",
"count": 61,
"is_medical": false
},
{
"term": "samuel",
"count": 61,
"is_medical": false
},
{
"term": "bannier",
"count": 60,
"is_medical": false
},
{
"term": "grihault",
"count": 60,
"is_medical": false
},
{
"term": "pedia",
"count": 59,
"is_medical": false
},
{
"term": "françois",
"count": 57,
"is_medical": false
},
{
"term": "quentin",
"count": 57,
"is_medical": false
},
{
"term": "cazenave",
"count": 55,
"is_medical": false
},
{
"term": "bedouet",
"count": 46,
"is_medical": false
},
{
"term": "jean",
"count": 44,
"is_medical": false
},
{
"term": "hurtado",
"count": 44,
"is_medical": false
},
{
"term": "droit",
"count": 43,
"is_medical": true
},
{
"term": "jean-pierre",
"count": 39,
"is_medical": false
},
{
"term": "echelle",
"count": 37,
"is_medical": false
},
{
"term": "glasgow",
"count": 37,
"is_medical": false
},
{
"term": "carriere",
"count": 35,
"is_medical": false
},
{
"term": "juliette",
"count": 35,
"is_medical": false
},
{
"term": "txomin",
"count": 33,
"is_medical": false
},
{
"term": "maternowski",
"count": 31,
"is_medical": false
},
{
"term": "cuillere",
"count": 29,
"is_medical": false
},
{
"term": "cafe",
"count": 29,
"is_medical": false
},
{
"term": "vomissements",
"count": 26,
"is_medical": false
},
{
"term": "gournay",
"count": 26,
"is_medical": false
},
{
"term": "eva",
"count": 25,
"is_medical": false
},
{
"term": "enf",
"count": 24,
"is_medical": false
},
{
"term": "marie-line",
"count": 24,
"is_medical": false
},
{
"term": "picamilh",
"count": 23,
"is_medical": false
},
{
"term": "eneko",
"count": 23,
"is_medical": false
},
{
"term": "bronswick",
"count": 22,
"is_medical": false
},
{
"term": "larrouy",
"count": 20,
"is_medical": false
},
{
"term": "elodie",
"count": 20,
"is_medical": false
},
{
"term": "preremplie",
"count": 18,
"is_medical": false
},
{
"term": "infectieuses",
"count": 16,
"is_medical": false
},
{
"term": "petriat",
"count": 16,
"is_medical": false
},
{
"term": "cotyle",
"count": 16,
"is_medical": false
},
{
"term": "sylvie",
"count": 15,
"is_medical": false
}
],
"medical_terms_by_category": {
"Titres/Fonctions": [
"droit",
"droite"
],
"Pathologies": [
"anastomose"
],
"Termes généraux": [
"colique",
"hilaire",
"urologique",
"vasculaire"
]
},
"all_medical_terms": [
"anastomose",
"colique",
"droit",
"droite",
"hilaire",
"urologique",
"vasculaire"
]
}