Struct SparsePolynomialFeatures 

pub struct SparsePolynomialFeatures<State = Untrained> {
    pub degree: u32,
    pub interaction_only: bool,
    pub include_bias: bool,
    pub sparsity_strategy: SparsityStrategy,
    pub sparse_format: SparseFormat,
    pub sparsity_threshold: Float,
    /* private fields */
}

Sparse Polynomial Features

Generates polynomial features using sparse matrix representations for memory-efficient computation, especially useful for high-dimensional polynomial feature spaces with many zero values.

Parameters

• degree - Maximum degree of polynomial features (default: 2)
• interaction_only - Include only interaction features (default: false)
• include_bias - Include bias column (default: true)
• sparsity_strategy - Strategy for enforcing sparsity
• sparse_format - Internal sparse matrix format
• sparsity_threshold - Minimum absolute value to keep (for automatic sparsity)

Examples

use sklears_kernel_approximation::sparse_polynomial::{SparsePolynomialFeatures, SparsityStrategy};
use sklears_core::traits::{Transform, Fit, Untrained}
use scirs2_core::ndarray::array;

let X = array![[1.0, 2.0], [3.0, 4.0]];

let sparse_poly = SparsePolynomialFeatures::new(2)
    .sparsity_strategy(SparsityStrategy::Absolute(0.1));
let fitted_sparse = sparse_poly.fit(&X, &()).unwrap();
let X_transformed = fitted_sparse.transform(&X).unwrap();

SparsePolynomialFeatures

Fields

degree: u32

Maximum degree of polynomial features

interaction_only: bool

Include only interaction features

include_bias: bool

Include bias column

sparsity_strategy: SparsityStrategy

Sparsity enforcement strategy

sparse_format: SparseFormat

Sparse matrix format

sparsity_threshold: Float

Automatic sparsity threshold

Implementations

impl SparsePolynomialFeatures<Untrained>

pub fn new(degree: u32) -> Self

Create a new sparse polynomial features transformer

pub fn interaction_only(self, interaction_only: bool) -> Self

Set interaction_only parameter

pub fn include_bias(self, include_bias: bool) -> Self

Set include_bias parameter

pub fn sparsity_strategy(self, strategy: SparsityStrategy) -> Self

Set sparsity strategy

pub fn sparse_format(self, format: SparseFormat) -> Self

Set sparse matrix format

pub fn sparsity_threshold(self, threshold: Float) -> Self

Set automatic sparsity threshold

impl SparsePolynomialFeatures<Trained>

pub fn n_input_features(&self) -> usize

Get the number of input features

pub fn n_output_features(&self) -> usize

Get the number of output features

pub fn powers(&self) -> &[Vec<u32>]

Get the powers for each feature

pub fn feature_indices(&self) -> &HashMap<Vec<u32>, usize>

Get the feature indices mapping

pub fn transform_sparse(&self, x: &Array2<Float>) -> Result<SparseMatrix>

Transform and return as sparse matrix (more efficient for sparse data)

pub fn memory_efficiency( &self, x: &Array2<Float>, ) -> Result<(usize, usize, Float)>

Estimate memory usage compared to dense representation

Trait Implementations

impl<State: Clone> Clone for SparsePolynomialFeatures<State>

fn clone(&self) -> SparsePolynomialFeatures<State>

Returns a duplicate of the value.

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

Performs copy-assignment from source.

impl<State: Debug> Debug for SparsePolynomialFeatures<State>

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

Formats the value using the given formatter.

impl Estimator for SparsePolynomialFeatures<Untrained>

type Config = ()

Configuration type for the estimator

type Error = SklearsError

Error type for the estimator

type Float = f64

The numeric type used by this estimator

fn config(&self) -> &Self::Config

Get estimator configuration

fn validate_config(&self) -> Result<(), SklearsError>

Validate estimator configuration with detailed error context

fn check_compatibility( &self, n_samples: usize, n_features: usize, ) -> Result<(), SklearsError>

Check if estimator is compatible with given data dimensions

fn metadata(&self) -> EstimatorMetadata

Get estimator metadata

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

type Fitted = SparsePolynomialFeatures<Trained>

The fitted model type

fn fit(self, x: &Array2<Float>, _y: &()) -> Result<Self::Fitted>

Fit the model to the provided data with validation

fn fit_with_validation( self, x: &X, y: &Y, _x_val: Option<&X>, _y_val: Option<&Y>, ) -> Result<(Self::Fitted, FitMetrics), SklearsError>

where Self: Sized,

Fit with custom validation and early stopping

impl Transform<ArrayBase<OwnedRepr<f64>, Dim<[usize; 2]>>> for SparsePolynomialFeatures<Trained>

fn transform(&self, x: &Array2<Float>) -> Result<Array2<Float>>

Transform the input data