INNER CODE UNIT · Python

validate_email

balapriyac/data-science-tutorials · build-with-python/data-cleaning-n-validation-pipeline/main.py:22

    def validate_email(cls, v):
        if v and '@' not in v:
            raise ValueError('Invalid email format')
        return v

class DataPipeline:
    def __init__(self):
        self.cleaning_stats = {'duplicates_removed': 0, 'nulls_handled': 0, 'validation_errors': 0}
    
    def clean_data(self, df: pd.DataFrame) -> pd.DataFrame:
        """Clean the dataset by handling duplicates and missing values"""
        initial_rows = len(df)
        
        # Remove duplicates
        df = df.drop_duplicates()
        self.cleaning_stats['duplicates_removed'] = initial_rows - len(df)
        
        # Handle missing values

View source record →