Struct petal_decomposition::Pca

pub struct Pca<A> where
    A: Scalar,  { /* fields omitted */ }

Principal component analysis.

This reduces the dimensionality of the input data using Singular Value Decomposition (SVD). The data is centered for each feature before applying SVD.

Examples

use petal_decomposition::Pca;

let x = ndarray::arr2(&[[0_f64, 0_f64], [1_f64, 1_f64], [2_f64, 2_f64]]);
let y = Pca::new(1).fit_transform(&x).unwrap();  // [-2_f64.sqrt(), 0_f64, 2_f64.sqrt()]
assert!((y[(0, 0)].abs() - 2_f64.sqrt()).abs() < 1e-8);
assert!(y[(1, 0)].abs() < 1e-8);
assert!((y[(2, 0)].abs() - 2_f64.sqrt()).abs() < 1e-8);

Implementations

impl<A> Pca<A> where
    A: Scalar + Lapack,
    A::Real: ScalarOperand, 

#[must_use]pub fn new(n_components: usize) -> Self

Creates a PCA model with the given number of components.

#[must_use]pub fn n_components(&self) -> usize

Returns the number of components.

#[must_use]pub fn singular_values(&self) -> &Array1<A::Real>

Returns sigular values.

#[must_use]pub fn explained_variance_ratio(&self) -> Array1<A::Real>

Returns the ratio of explained variance for each component.

pub fn fit<S>(
    &mut self,
    input: &ArrayBase<S, Ix2>
) -> Result<(), DecompositionError> where
    S: Data<Elem = A>, 

Fits the model with input.

Errors

• DecompositionError::InvalidInput if any of the dimensions of input is less than the number of components.
• DecompositionError::LinalgError if the underlying Singular Vector Decomposition routine fails.

pub fn transform<S>(
    &self,
    input: &ArrayBase<S, Ix2>
) -> Result<Array2<A>, DecompositionError> where
    S: Data<Elem = A>, 

Applies dimensionality reduction to input.

Errors

• DecompositionError::InvalidInput if the number of features in input does not match that of the training data.

pub fn fit_transform<S>(
    &mut self,
    input: &ArrayBase<S, Ix2>
) -> Result<Array2<A>, DecompositionError> where
    S: Data<Elem = A>, 

Fits the model with input and apply the dimensionality reduction on input.

This is equivalent to calling both fit and transform for the same input, but more efficient.

Errors

Returns DecompositionError::LinalgError if the underlying Singular Vector Decomposition routine fails.