Struct rusty_machine::learning::pca::PCA

pub struct PCA { /* private fields */ }

Principal Component Analysis

• PCA uses rulinalg SVD which is experimental (not yet work for large data)

Implementations

impl PCA

pub fn new(n: usize, center: bool) -> PCA

Constructs untrained PCA model.

Parameters

• n : number of principal components
• center : flag whether centering inputs to be specified.

Examples

use rusty_machine::learning::pca::PCA;

let model = PCA::new(3, true);

pub fn components(&self) -> LearningResult<&Matrix<f64>>

Returns principal components (matrix which contains eigenvectors as columns)

Trait Implementations

impl Debug for PCA

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

Formats the value using the given formatter.

impl Default for PCA

The default PCA.

Parameters:

• n = None (keep all components)
• center = true

Examples

use rusty_machine::learning::pca::PCA;

let model = PCA::default();

fn default() -> Self

Returns the “default value” for a type.

impl UnSupModel<Matrix<f64>, Matrix<f64>> for PCA

Train the model and predict the model output from new data.

fn predict(&self, inputs: &Matrix<f64>) -> LearningResult<Matrix<f64>>

Predict output from inputs.

fn train(&mut self, inputs: &Matrix<f64>) -> LearningResult<()>

Train the model using inputs.