Struct MDS 

pub struct MDS { /* private fields */ }

Classical Multidimensional Scaling configuration.

Holds hyperparameters for the MDS algorithm. Call Fit::fit to compute the embedding and obtain a FittedMDS.

Implementations

impl MDS

pub fn new(n_components: usize) -> Self

Create a new MDS that embeds into n_components dimensions.

By default the input is treated as a feature matrix (Dissimilarity::Euclidean).

pub fn with_dissimilarity(self, d: Dissimilarity) -> Self

Set the dissimilarity mode.

pub fn n_components(&self) -> usize

Return the configured number of components.

pub fn dissimilarity(&self) -> Dissimilarity

Return the configured dissimilarity mode.

Trait Implementations

impl Clone for MDS

fn clone(&self) -> MDS

Returns a duplicate of the value.

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

Performs copy-assignment from source.

impl Debug for MDS

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

Formats the value using the given formatter.

impl Fit<ArrayBase<OwnedRepr<f64>, Dim<[usize; 2]>>, ()> for MDS

fn fit(&self, x: &Array2<f64>, _y: &()) -> Result<FittedMDS, FerroError>

Fit classical MDS.

Errors

• FerroError::InvalidParameter if n_components is zero or too large.
• FerroError::InsufficientSamples if there are fewer than 2 samples.
• FerroError::ShapeMismatch if Precomputed is set but the matrix is not square.

type Fitted = FittedMDS

The fitted model type returned by fit.

type Error = FerroError

The error type returned by fit.