Struct LogisticRegression 

pub struct LogisticRegression {
    pub weights: Vector,
    pub bias: Vector,
    pub activation_fn: ActivationFn,
    /* private fields */
}

A logistic regression model for binary classification.

This model uses a linear combination of features and weights, followed by an activation function, to predict the probability of an input belonging to a positive class.

Fields

weights: Vector

Model weights for each feature

bias: Vector

Bias term (intercept)

activation_fn: ActivationFn

Activation function used for prediction

Implementations

impl LogisticRegression

pub fn new( n_features: usize, activation_fn: ActivationFn, threshold: f64, ) -> Self

Creates a new LogisticRegression model with the specified number of features and activation function.

Arguments

• n_features - The number of input features
• activation_fn - The activation function to use

Returns

A new LogisticRegression instance with weights initialized to zeros

pub fn builder() -> LogisticRegressionBuilder

Returns a builder for creating LogisticRegression models with custom configurations.

Returns

A new LogisticRegressionBuilder instance

Trait Implementations

impl BaseModel<ArrayBase<OwnedRepr<f64>, Dim<[usize; 2]>>, ArrayBase<OwnedRepr<f64>, Dim<[usize; 1]>>> for LogisticRegression

Implementation of BaseModel trait for LogisticRegression

fn predict(&self, x: &Matrix) -> Result<Vector, ModelError>

Makes binary predictions for the given input data.

Arguments

• x - Input feature matrix

Returns

A vector of predictions (0.0 or 1.0)

fn compute_cost(&self, x: &Matrix, y: &Vector) -> Result<f64, ModelError>

Computes the cost/loss for the given input and expected output.

Arguments

• x - Input feature matrix
• y - Expected output vector

Returns

The computed loss value

impl Builder<LogisticRegression, ArrayBase<OwnedRepr<f64>, Dim<[usize; 2]>>, ArrayBase<OwnedRepr<f64>, Dim<[usize; 1]>>> for LogisticRegressionBuilder

fn build(&self) -> Result<LogisticRegression, ModelError>

Builds and returns a new LogisticRegression model with the configured parameters.

Returns

• Result<LogisticRegression, ModelError> - A new LogisticRegression instance with the specified configuration, or an error if construction fails

impl ClassificationModel<ArrayBase<OwnedRepr<f64>, Dim<[usize; 2]>>, ArrayBase<OwnedRepr<f64>, Dim<[usize; 1]>>> for LogisticRegression

Implementation of ClassificationModel trait for LogisticRegression

fn accuracy(&self, x: &Matrix, y: &Vector) -> Result<f64, ModelError>

Calculates the accuracy of the model on the given data.

Arguments

• x - Input feature matrix
• y - Expected output vector

Returns

The accuracy as a value between 0.0 and 1.0

fn loss(&self, x: &Matrix, y: &Vector) -> Result<f64, ModelError>

Calculates the loss (binary cross-entropy) of the model on the given data.

Arguments

• x - Input feature matrix
• y - Expected output vector

Returns

The computed loss value

fn recall(&self, x: &Matrix, y: &Vector) -> Result<f64, ModelError>

Calculates the recall (sensitivity) of the model on the given data.

Arguments

• x - Input feature matrix
• y - Expected output vector

Returns

The recall as a value between 0.0 and 1.0

fn f1_score(&self, x: &Matrix, y: &Vector) -> Result<f64, ModelError>

Calculates the F1 score of the model on the given data.

Arguments

• x - Input feature matrix
• y - Expected output vector

Returns

The F1 score as a value between 0.0 and 1.0

fn compute_metrics( &self, x: &Matrix, y: &Vector, ) -> Result<ClassificationMetrics, ModelError>

Computes all classification metrics for the model on the given data.

Arguments

• x - Input feature matrix
• y - Expected output vector

Returns

A ClassificationMetrics struct containing accuracy, loss, precision, recall and F1 score

impl Debug for LogisticRegression

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

Formats the value using the given formatter.

impl GradientCollection for LogisticRegression

fn get_gradient<D: Dimension>( &self, key: &str, ) -> Result<ArrayView<'_, f64, D>, ModelError>

Get a reference to a specific gradient with strong typing.

fn set_gradient<D: Dimension>( &mut self, key: &str, value: ArrayView<'_, f64, D>, ) -> Result<(), ModelError>

Set the value of a gradient.

impl OptimizableModel<ArrayBase<OwnedRepr<f64>, Dim<[usize; 2]>>, ArrayBase<OwnedRepr<f64>, Dim<[usize; 1]>>> for LogisticRegression

fn compute_output_gradient( &self, x: &Matrix, y: &Vector, ) -> Result<Vector, ModelError>

Computes the gradient of the loss function with regards to the prediction (dJ/dy)

Arguments

• x - Input feature matrix
• y - Expected output vector

Returns

The gradient vector

fn forward(&self, input: &Matrix) -> Result<Vector, ModelError>

Forward pass through the model.

fn backward(&mut self, input: &Matrix, dz: &Vector) -> Result<(), ModelError>

Backward pass to compute gradients.

impl ParamCollection for LogisticRegression

fn get<D: Dimension>( &self, key: &str, ) -> Result<ArrayView<'_, f64, D>, ModelError>

Get a reference to a specific parameter with strong typing.

fn get_mut<D: Dimension>( &mut self, key: &str, ) -> Result<ArrayViewMut<'_, f64, D>, ModelError>

fn set<D: Dimension>( &mut self, key: &str, value: ArrayView<'_, f64, D>, ) -> Result<(), ModelError>

Set the value of a parameter.

fn param_iter(&self) -> Vec<(&str, ArrayView<'_, f64, IxDyn>)>

Iterate over all parameters.