← Back to the chapter · Next detail →

Technical detail · Feature Scaling Lab: Statistical Analysis

Illustrative normalizer selector

The selector classes are illustrative: ZScoreNormalizer and LogTransform are undefined placeholders; RobustScaler and MinMaxScaler require imports from sklearn.preprocessing.

def select_normalizer(data_characteristics):
    """
    Select appropriate normalization based on data characteristics.
    Returns: (normalizer_class, parameters)
    """
    has_outliers = data_characteristics['outlier_rate'] > 0.05
    is_neural_network = data_characteristics['model_type'] == 'neural_network'
    has_mixed_scales = data_characteristics['mixed_feature_scales']
    is_skewed = data_characteristics['skewness'] > 2.0

    if has_outliers:
        return (RobustScaler, {})
    elif is_neural_network:
        return (MinMaxScaler, {'feature_range': (0, 1)})
    elif has_mixed_scales:
        return (ZScoreNormalizer, {})
    elif is_skewed:
        return (LogTransform, {'then_zscore': True})
    else:
        return (MinMaxScaler, {'feature_range': (0, 1)})

# Usage example
characteristics = {
    'outlier_rate': 0.08,  # 8% outliers
    'model_type': 'kmeans',
    'mixed_feature_scales': True,
    'distribution': 'unknown',
    'skewness': 1.2
}

normalizer_class, params = select_normalizer(characteristics)
# Returns: RobustScaler (because outlier_rate > 0.05)

← Back to the chapter · Next detail →