Struct NMF 

pub struct NMF<F> { /* private fields */ }

Non-negative Matrix Factorization configuration.

Holds hyperparameters for the NMF decomposition. Calling Fit::fit computes the factorization and returns a FittedNMF that can project new data via Transform::transform.

Implementations

impl<F: Float + Send + Sync + 'static> NMF<F>

pub fn new(n_components: usize) -> Self

Create a new NMF that extracts n_components components.

Defaults: max_iter=200, tol=1e-4, solver=MultiplicativeUpdate, init=Random, no random seed.

pub fn with_max_iter(self, max_iter: usize) -> Self

Set the maximum number of iterations.

pub fn with_tol(self, tol: f64) -> Self

Set the convergence tolerance.

pub fn with_solver(self, solver: NMFSolver) -> Self

Set the solver algorithm.

pub fn with_init(self, init: NMFInit) -> Self

Set the initialization strategy.

pub fn with_random_state(self, seed: u64) -> Self

Set the random seed for reproducible results.

pub fn n_components(&self) -> usize

Return the configured number of components.

pub fn max_iter(&self) -> usize

Return the configured maximum iterations.

pub fn tol(&self) -> f64

Return the configured tolerance.

pub fn solver(&self) -> NMFSolver

Return the configured solver.

pub fn init(&self) -> NMFInit

Return the configured initialization strategy.

pub fn random_state(&self) -> Option<u64>

Return the configured random state, if any.

Trait Implementations

impl<F: Clone> Clone for NMF<F>

fn clone(&self) -> NMF<F>

Returns a duplicate of the value.

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

Performs copy-assignment from source.

impl<F: Debug> Debug for NMF<F>

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

Formats the value using the given formatter.

impl<F: Float + Send + Sync + 'static> Fit<ArrayBase<OwnedRepr<F>, Dim<[usize; 2]>>, ()> for NMF<F>

fn fit(&self, x: &Array2<F>, _y: &()) -> Result<FittedNMF<F>, FerroError>

Fit the NMF model by decomposing X ~ W * H.

Errors

• FerroError::InvalidParameter if n_components is zero or exceeds the minimum of n_samples and n_features.
• FerroError::InvalidParameter if any entry of X is negative.
• FerroError::InsufficientSamples if there are zero samples.
• FerroError::ConvergenceFailure if NNDSVD initialization fails.

type Fitted = FittedNMF<F>

The fitted model type returned by fit.

type Error = FerroError

The error type returned by fit.

impl<F: Float + Send + Sync + 'static> PipelineTransformer<F> for NMF<F>

fn fit_pipeline( &self, x: &Array2<F>, _y: &Array1<F>, ) -> Result<Box<dyn FittedPipelineTransformer<F>>, FerroError>

Fit NMF using the pipeline interface.

The y argument is ignored; NMF is unsupervised.

Errors

Propagates errors from Fit::fit.