Enum PcaSolver 

pub enum PcaSolver {
    Auto,
    Randomized {
        n_oversamples: usize,
        n_power_iters: usize,
    },
    PowerIteration,
}

Solver strategy for PCA.

Variants

Auto

Automatically select solver based on data size: Randomized if n > 500 and k < 0.8 * min(n, d), else PowerIteration.

Randomized

Randomized SVD (Halko-Martinsson-Tropp).

Fields

n_oversamples: usize

Extra columns for accuracy (default: 10).

n_power_iters: usize

Subspace power iterations for stability (default: 4).

PowerIteration

Legacy power iteration with deflation.

Trait Implementations

impl Clone for PcaSolver

fn clone(&self) -> PcaSolver

Returns a duplicate of the value.

fn clone_from(&mut self, source: &Self)

Performs copy-assignment from source.

impl Debug for PcaSolver

fn fmt(&self, f: &mut Formatter<'_>) -> Result

Formats the value using the given formatter.

impl Default for PcaSolver

fn default() -> PcaSolver

Returns the “default value” for a type.