feat: implement NER dataset feature engineering with multiple transformation formats

2025-08-12 00:11:46 +02:00
parent d5a4aaaf4a
commit 3977d5c313
9 changed files with 439 additions and 0 deletions
@@ -0,0 +1,29 @@
+from typing import Dict
+
+import pandas as pd
+
+from processing.ner.formats import BaseNameFormatter
+
+
+class PositionFlippedFormatter(BaseNameFormatter):
+    def transform(self, row: pd.Series) -> Dict:
+        native_parts = self.parse_native_components(row['probable_native'])
+        surname = row['probable_surname'] if pd.notna(row['probable_surname']) else ''
+
+        # Flip order: surname + native components
+        full_name = f"{surname} {row['probable_native']}".strip()
+
+        return {
+            'name': full_name,
+            'probable_native': row['probable_native'],
+            'identify_name': row['probable_native'],
+            'probable_surname': surname,
+            'identify_surname': surname,
+            'ner_entities': str(self.create_ner_tags(full_name, native_parts, surname)),
+            'transformation_type': self.transformation_type,
+            **self.compute_derived_attributes(full_name)
+        }
+
+    @property
+    def transformation_type(self) -> str:
+        return 'position_flipped'