INNER CODE UNIT · Python

validate_data

balapriyac/data-science-tutorials · build-with-python/data-cleaning-n-validation-pipeline/main.py:49

    def validate_data(self, df: pd.DataFrame) -> pd.DataFrame:
        """Validate each row using Pydantic model"""
        valid_rows = []
        errors = []
        
        for idx, row in df.iterrows():
            try:
                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())

View source record →