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
@@ -7,22 +7,22 @@ from processing.ner.formats import BaseNameFormatter

 class NativeOnlyFormatter(BaseNameFormatter):
    def transform(self, row: pd.Series) -> Dict:
-        native_parts = self.parse_native_components(row['probable_native'])
+        native_parts = self.parse_native_components(row["probable_native"])

        # Only native components
-        full_name = row['probable_native']
+        full_name = row["probable_native"]

        return {
-            'name': full_name,
-            'probable_native': row['probable_native'],
-            'identify_name': row['probable_native'],
-            'probable_surname': '',
-            'identify_surname': '',
-            'ner_entities': str(self.create_ner_tags(full_name, native_parts, '')),
-            'transformation_type': self.transformation_type,
-            **self.compute_derived_attributes(full_name)
+            "name": full_name,
+            "probable_native": row["probable_native"],
+            "identified_name": row["probable_native"],
+            "probable_surname": "",
+            "identified_surname": "",
+            "ner_entities": str(self.create_ner_tags(full_name, native_parts, "")),
+            "transformation_type": self.transformation_type,
+            **self.compute_numeric_features(full_name),
        }

    @property
    def transformation_type(self) -> str:
-        return 'native_only'
+        return "native_only"