bernard-ng/drc-ners-nlp
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

feat: enhance logging and memory management across modules

Browse Source
This commit is contained in:
bernard-ng
2025-08-13 23:09:05 +02:00
parent 47e52d130c
commit 9601c5e44d
48 changed files with 1004 additions and 773 deletions
Download Patch File Download Diff File Expand all files Collapse all files
processing/ner/formats/position_flipped_format.py
+11 -11
View File
@@ -7,23 +7,23 @@ 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 ''
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)
"name": full_name,
"probable_native": row["probable_native"],
"identified_name": row["probable_native"],
"probable_surname": surname,
"identified_surname": surname,
"ner_entities": str(self.create_ner_tags(full_name, native_parts, surname)),
"transformation_type": self.transformation_type,
**self.compute_numeric_features(full_name),
}
@property
def transformation_type(self) -> str:
return 'position_flipped'
return "position_flipped"