Struct QDA 

pub struct QDA<F> {
    pub reg_param: F,
}

Quadratic Discriminant Analysis configuration.

Holds hyperparameters. Calling Fit::fit computes per-class means and covariance matrices and returns a FittedQDA.

Type Parameters

• F: The floating-point scalar type (f32 or f64).

Fields

reg_param: F

Regularization parameter for covariance matrices.

Blends each class covariance toward the identity: Sigma_k = (1 - reg) * Sigma_k + reg * I. Must be in [0, 1]. Default: 0.0.

Implementations

impl<F: Float> QDA<F>

pub fn new() -> Self

Create a new QDA with default settings.

Default: reg_param = 0.0.

pub fn with_reg_param(self, reg_param: F) -> Self

Set the regularization parameter.

Trait Implementations

impl<F: Clone> Clone for QDA<F>

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

Returns a duplicate of the value.

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

Performs copy-assignment from source.

impl<F: Debug> Debug for QDA<F>

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

Formats the value using the given formatter.

impl<F: Float> Default for QDA<F>

fn default() -> Self

Returns the “default value” for a type.

impl<F: Float + Send + Sync + ScalarOperand + 'static> Fit<ArrayBase<OwnedRepr<F>, Dim<[usize; 2]>>, ArrayBase<OwnedRepr<usize>, Dim<[usize; 1]>>> for QDA<F>

fn fit( &self, x: &Array2<F>, y: &Array1<usize>, ) -> Result<FittedQDA<F>, FerroError>

Fit the QDA model by computing per-class means and covariances.

Errors

• FerroError::ShapeMismatch — sample count mismatch.
• FerroError::InsufficientSamples — fewer than 2 distinct classes or a class has too few samples.
• FerroError::InvalidParameter — reg_param not in [0, 1].
• FerroError::NumericalInstability — covariance matrix is singular.

type Fitted = FittedQDA<F>

The fitted model type returned by fit.

type Error = FerroError

The error type returned by fit.