Expand description
Data scaling utilities
This module provides comprehensive data scaling and normalization implementations including standard scaling (z-score normalization), min-max scaling, robust scaling with quantiles, max absolute value scaling, L1/L2 normalization, unit vector scaling, feature-wise scaling, outlier-aware scaling, kernel centering, polynomial feature generation, power transformations, quantile transformations, SIMD-optimized implementations, streaming scalers, adaptive scalers, categorical feature encoding, mixed-type scaling, and high-performance preprocessing pipelines. All algorithms have been refactored into focused modules for better maintainability and comply with SciRS2 Policy.
Structs§
- Feature
Wise Scaler - Placeholder FeatureWiseScaler for API compatibility
- Feature
Wise Scaler Config - FeatureWiseScaler configuration
- MaxAbs
Scaler - Placeholder MaxAbsScaler for API compatibility
- MinMax
Scaler - Placeholder MinMaxScaler for API compatibility
- Normalizer
- Placeholder Normalizer for API compatibility
- Outlier
Aware Scaler - Placeholder OutlierAwareScaler for API compatibility
- Outlier
Aware Scaler Config - OutlierAwareScaler configuration
- Outlier
Scaling Stats - Outlier scaling statistics
- Robust
Scaler - Placeholder RobustScaler for API compatibility
- Standard
Scaler - Placeholder StandardScaler for API compatibility
- Unit
Vector Scaler - Placeholder UnitVectorScaler for API compatibility
- Unit
Vector Scaler Config - UnitVectorScaler configuration
Enums§
- Norm
Type - Norm types for vector normalization
- Outlier
Aware Scaling Strategy - Outlier-aware scaling strategies
- Robust
Statistic - Robust statistics for scaling
- Scaling
Method - Scaling methods