Struct FittedQDA 

pub struct FittedQDA<F> { /* private fields */ }

Fitted Quadratic Discriminant Analysis model.

Stores per-class means, covariance inverses, and priors. Implements Predict to produce class labels.

Implementations

impl<F: Float> FittedQDA<F>

pub fn means(&self) -> Vec<&Array1<F>>

Returns the class means, one per class.

impl<F: Float + ScalarOperand + Send + Sync + 'static> FittedQDA<F>

pub fn predict_proba(&self, x: &Array2<F>) -> Result<Array2<F>, FerroError>

Predict per-class probabilities. Mirrors sklearn QuadraticDiscriminantAnalysis.predict_proba.

Computes softmax over the per-class quadratic discriminants δ_c(x) = -½ log|Σ_c| - ½ (x-μ_c)ᵀ Σ_c⁻¹ (x-μ_c) + log π_c. Returns shape (n_samples, n_classes); rows sum to 1.

Errors

Returns FerroError::ShapeMismatch if the number of features does not match the fitted model.

pub fn predict_log_proba(&self, x: &Array2<F>) -> Result<Array2<F>, FerroError>

Element-wise log of predict_proba.

Errors

Forwards any error from predict_proba.

pub fn decision_function(&self, x: &Array2<F>) -> Result<Array2<F>, FerroError>

Per-class quadratic discriminant scores. Mirrors sklearn QuadraticDiscriminantAnalysis.decision_function. Returns shape (n_samples, n_classes) with δ_c(x) = -½ log|Σ_c| - ½ (x-μ_c)ᵀ Σ_c⁻¹ (x-μ_c) + log π_c. argmax of each row agrees with Predict.

Errors

Returns FerroError::ShapeMismatch if the number of features does not match the fitted model.

Trait Implementations

impl<F: Clone> Clone for FittedQDA<F>

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

Returns a duplicate of the value.

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

Performs copy-assignment from source.

impl<F: Debug> Debug for FittedQDA<F>

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

Formats the value using the given formatter.

impl<F: Float + Send + Sync + ScalarOperand + 'static> HasClasses for FittedQDA<F>

fn classes(&self) -> &[usize]

Returns the sorted list of unique class labels.

fn n_classes(&self) -> usize

Returns the number of distinct classes.

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

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

Predict class labels for the given feature matrix.

Selects the class with the largest log-posterior for each sample.

Errors

Returns FerroError::ShapeMismatch if the number of features does not match the fitted model.

type Output = ArrayBase<OwnedRepr<usize>, Dim<[usize; 1]>>

The prediction output type (e.g., ndarray::Array1<F> or ndarray::Array1<usize>).

type Error = FerroError

The error type returned by predict.