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/reduced_native_format.py
+12 -12
View File
@@ -7,24 +7,24 @@ from processing.ner.formats import BaseNameFormatter
class ReducedNativeFormatter(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 ""
# Keep only first native component + surname
reduced_native = native_parts[0] if len(native_parts) > 1 else row['probable_native']
reduced_native = native_parts[0] if len(native_parts) > 1 else row["probable_native"]
full_name = f"{reduced_native} {surname}".strip()
return {
'name': full_name,
'probable_native': reduced_native,
'identify_name': reduced_native,
'probable_surname': surname,
'identify_surname': surname,
'ner_entities': str(self.create_ner_tags(full_name, [reduced_native], surname)),
'transformation_type': self.transformation_type,
**self.compute_derived_attributes(full_name)
"name": full_name,
"probable_native": reduced_native,
"identified_name": reduced_native,
"probable_surname": surname,
"identified_surname": surname,
"ner_entities": str(self.create_ner_tags(full_name, [reduced_native], surname)),
"transformation_type": self.transformation_type,
**self.compute_numeric_features(full_name),
}
@property
def transformation_type(self) -> str:
return 'reduced_native'
return "reduced_native"