Module dimensionality 

Dimensionality reduction (ISL ch 12, PRML ch 12). Built on linear_algebra (eigen/SVD). Feeds the engine’s 10D→5D NQuin relevance router.

• pca — Principal Component Analysis (covariance eigendecomposition).

Probabilistic PCA / kernel PCA and PCR/PLS regression land here next (build order in stats_plan.md).

Re-exports

pub use pca::fit as fit_pca;

pub use pca::Pca;

pub use som::Som;

Modules

pca

Principal Component Analysis (ISL ch 12, PRML ch 12) — the eigendecomposition of the feature covariance, reusing linear_algebra::{gemm, eigen} (no new solver). Mission note: PCA is the principled way to choose the engine’s 10D→5D NQuin relevance projection.

som

Self-Organizing Map (CI-SKM ch 3) — a topology-preserving projection of a high-dimensional space onto a 2-D grid of neurons. Nearby inputs map to nearby grid cells, so it lays out a semantic space for the 10D→5D relevance router (complementing PCA: SOM preserves neighbourhood topology, not just variance). Kernel-class AllPairs (the best-matching-unit search). Deterministic per seed.