INNER CODE UNIT · Python

process

balapriyac/data-science-tutorials · build-with-python/data-cleaning-n-validation-pipeline/main.py:64

    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
        }


# Example usage
if __name__ == "__main__":
    # Sample messy data
    sample_data = pd.DataFrame({
    'name': ['Tara Jamison', 'Jane Smith', 'Lucy Lee', None, 'Clara Clark','Jane Smith'],
    'age': [25, -5, 25, 35, 150,-5],

View source record →