INNER CODE UNIT · Python
validated_row
balapriyac/data-science-tutorials · build-with-python/data-cleaning-n-validation-pipeline/main.py:56
validated_row = DataValidator(**row.to_dict())
valid_rows.append(validated_row.model_dump())
except ValidationError as e:
errors.append({'row': idx, 'errors': str(e)})
self.cleaning_stats['validation_errors'] = len(errors)
return pd.DataFrame(valid_rows), errors
def process(self, df: pd.DataFrame) -> Dict[str, Any]:
"""Main pipeline method"""
cleaned_df = self.clean_data(df.copy())
validated_df, validation_errors = self.validate_data(cleaned_df)
return {
'cleaned_data': validated_df,
'validation_errors': validation_errors,
'stats': self.cleaning_stats
}