feat: enhance logging and memory management across modules

2025-08-13 23:09:05 +02:00
parent 47e52d130c
commit 9601c5e44d
48 changed files with 1004 additions and 773 deletions
@@ -12,13 +12,15 @@ class DataConfig(BaseModel):
        default_factory=lambda: {
            "featured": "names_featured.csv",
            "evaluation": "names_evaluation.csv",
+            "engineered": "names_engineered.csv",
            "males": "names_males.csv",
            "females": "names_females.csv",
            "ner_data": "names_ner.json",
-            "ner_spacy": "names_ner.spacy"
+            "ner_spacy": "names_ner.spacy",
        }
    )
    split_evaluation: bool = False
+    split_by_province: bool = True
    split_by_gender: bool = True
    split_ner_data: bool = True
    evaluation_fraction: float = 0.2