Struct petal_decomposition::FastIca

source · [−]

pub struct FastIca<A, R = Pcg> where
    A: Scalar,
    R: Rng,  { /* private fields */ }

Expand description

Independent component analysis using the FastICA algorithm.

Examples

use petal_decomposition::FastIcaBuilder;

let x = ndarray::arr2(&[[0_f64, 0_f64], [1_f64, 1_f64], [1_f64, -1_f64]]);
let mut ica = FastIcaBuilder::new().build();
let y = ica.fit_transform(&x).unwrap();

Implementations

source

impl<A> FastIca<A, Pcg> where
A: Scalar,

source

pub fn new() -> Self

Creates an ICA model with a random seed.

It uses a PCG random number generator (the XSL 128/64 (MCG) variant on a 64-bit CPU and the XSH RR 64/32 (LCG) variant on a 32-bit CPU), initialized with a randomly-generated seed.

source

pub fn with_seed(seed: u128) -> Self

Creates an ICA model with the given seed for random number generation.

It uses a PCG random number generator (the XSL 128/64 (MCG) variant on a 64-bit CPU and the XSH RR 64/32 (LCG) variant on a 32-bit CPU). Use with_rng for a different random number generator.

source

impl<A, R> FastIca<A, R> where
A: Scalar,
R: Rng,

source

pub fn with_rng(rng: R) -> Self

Creates an ICA model with the given random number generator.

source

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

Fits the model with input.

Errors

DecompositionError::InvalidInput if the layout of input is incompatible with LAPACK.
DecompositionError::LinalgError if the underlying Singular Vector Decomposition routine fails.

source

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

Applies ICA to input.

Errors

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

source

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

Fits the model with input and apply ICA on input.

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

Errors

DecompositionError::InvalidInput if the layout of input is incompatible with LAPACK.
DecompositionError::LinalgError if the underlying Singular Vector Decomposition routine fails.