Struct linfa_reduction::pca::Pca

pub struct Pca<F> { /* fields omitted */ }

Fitted Principal Component Analysis model

The model contains the mean and hyperplane for the projection of data.

Example

use linfa::traits::{Fit, Predict};
use linfa_reduction::Pca;

let dataset = linfa_datasets::iris();

// apply PCA projection along a line which maximizes the spread of the data
let embedding = Pca::params(1)
    .fit(&dataset).unwrap();

// reduce dimensionality of the dataset
let dataset = embedding.predict(dataset);

Implementations

impl Pca<f64>

pub fn params(embedding_size: usize) -> PcaParams

Create default parameter set

Parameters

• embedding_size: the target dimensionality

pub fn explained_variance(&self) -> Array1<f64>

Return the amount of explained variance per element

pub fn explained_variance_ratio(&self) -> Array1<f64>

Return the normalized amount of explained variance per element

pub fn singular_values(&self) -> &Array1<f64>

Return the singular values

Trait Implementations

impl<F: Clone> Clone for Pca<F>

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

Returns a copy of the value.

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

Performs copy-assignment from source.

impl<F: Debug> Debug for Pca<F>

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

Formats the value using the given formatter.

impl<F: Float, D: Data<Elem = F>> PredictRef<ArrayBase<D, Dim<[usize; 2]>>, ArrayBase<OwnedRepr<F>, Dim<[usize; 2]>>> for Pca<F>

fn predict_ref<'a>(&'a self, records: &ArrayBase<D, Ix2>) -> Array2<F>

impl<F: Float, D: Data<Elem = F>, T> Transformer<DatasetBase<ArrayBase<D, Dim<[usize; 2]>>, T>, DatasetBase<ArrayBase<OwnedRepr<F>, Dim<[usize; 2]>>, T>> for Pca<F>

fn transform(
    &self,
    ds: DatasetBase<ArrayBase<D, Ix2>, T>
) -> DatasetBase<Array2<F>, T>