Struct ConfusionMatrix 

pub struct ConfusionMatrix { /* private fields */ }

Confusion matrix for multi-class classification.

Implementations

impl ConfusionMatrix

pub fn new(num_classes: usize) -> Self

Create a new confusion matrix.

Arguments

• num_classes - Number of classes

pub fn compute( predictions: &ArrayView<'_, f64, Ix2>, targets: &ArrayView<'_, f64, Ix2>, ) -> TrainResult<Self>

Compute confusion matrix from predictions and targets.

Arguments

• predictions - Model predictions (one-hot or class probabilities)
• targets - True labels (one-hot encoded)

Returns

Confusion matrix

pub fn matrix(&self) -> &Vec<Vec<usize>>

Get the confusion matrix.

pub fn get(&self, true_class: usize, pred_class: usize) -> usize

Get value at (true_class, pred_class).

pub fn precision_per_class(&self) -> Vec<f64>

Compute per-class precision.

pub fn recall_per_class(&self) -> Vec<f64>

Compute per-class recall.

pub fn f1_per_class(&self) -> Vec<f64>

Compute per-class F1 scores.

pub fn accuracy(&self) -> f64

Compute overall accuracy.

pub fn total_predictions(&self) -> usize

Get total number of predictions.

Trait Implementations

impl Clone for ConfusionMatrix

fn clone(&self) -> ConfusionMatrix

Returns a duplicate of the value.

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

Performs copy-assignment from source.

impl Debug for ConfusionMatrix

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

Formats the value using the given formatter.

impl Display for ConfusionMatrix

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

Formats the value using the given formatter.