Struct LogisticRegressionOutput

pub struct LogisticRegressionOutput<T> {
    pub coefficients: Matrix<T, Dyn, Const<1>, VecStorage<T, Dyn, Const<1>>>,
    pub iterations: usize,
}

Struct to hold the output data for a logistic regression.

Fields

coefficients: Matrix<T, Dyn, Const<1>, VecStorage<T, Dyn, Const<1>>>

The coefficients of the logistic regression, often denoted as b0, b1, b2, …, bn. The first coefficient is the intercept (aka. b0 or alpha).

iterations: usize

Number of iterations required to converge.

Implementations

impl LogisticRegressionOutput<f64>

pub fn predict( &self, input: &Matrix<f64, Dyn, Dyn, VecStorage<f64, Dyn, Dyn>>, ) -> Matrix<f64, Dyn, Const<1>, VecStorage<f64, Dyn, Const<1>>>

Predicts the output for the given input data.

pub fn predict_proba( &self, input: &Matrix<f64, Dyn, Dyn, VecStorage<f64, Dyn, Dyn>>, ) -> Matrix<f64, Dyn, Const<1>, VecStorage<f64, Dyn, Const<1>>>

Compute the probabilities $Pr(output_i=1|input_i,coefficients)$ for the given input data.

pub fn score_misclassification( &self, y: &Matrix<f64, Dyn, Const<1>, VecStorage<f64, Dyn, Const<1>>>, y_hat: &Matrix<f64, Dyn, Const<1>, VecStorage<f64, Dyn, Const<1>>>, ) -> f64

Compute the misclassification rate for given y and y_hat.

Panics

Panics if the shape of y is not equal to the shape of y_hat.

pub fn score_cross_entropy( &self, y: &Matrix<f64, Dyn, Const<1>, VecStorage<f64, Dyn, Const<1>>>, p_hat: &Matrix<f64, Dyn, Const<1>, VecStorage<f64, Dyn, Const<1>>>, ) -> f64

Compute average cross-entropy for given y and p_hat.

Panics

Panics if the shape of y is not equal to the shape of p_hat.

Trait Implementations

impl<T> Clone for LogisticRegressionOutput<T>

where T: Clone,

fn clone(&self) -> LogisticRegressionOutput<T>

Returns a duplicate of the value.

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

Performs copy-assignment from source.

impl<T> Debug for LogisticRegressionOutput<T>

where T: Debug,

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

Formats the value using the given formatter.