feat: enhance logging and memory management across modules

core/config/annotation_config.py

@@ -1,5 +1,6 @@
 from pydantic import BaseModel
 
+
 class NERConfig(BaseModel):
     """NER annotation configuration"""
 

core/config/data_config.py

@@ -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