Struct ExponentiallyWeightedMeanRegressor 

pub struct ExponentiallyWeightedMeanRegressor { /* private fields */ }

A regressor that predicts an exponentially weighted mean of targets.

Suitable when recent observations are more relevant than older ones.

Implementations

impl ExponentiallyWeightedMeanRegressor

pub fn new(alpha: f64, config: BaselineConfig) -> Result<Self, RillError>

Create a new EW mean regressor.

alpha must be in (0, 1].

pub const fn alpha(&self) -> f64

The configured alpha.

pub const fn value(&self) -> f64

The current weighted mean.

Trait Implementations

impl Clone for ExponentiallyWeightedMeanRegressor

fn clone(&self) -> ExponentiallyWeightedMeanRegressor

Returns a duplicate of the value.

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

Performs copy-assignment from source.

impl Debug for ExponentiallyWeightedMeanRegressor

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

Formats the value using the given formatter.

impl OnlineRegressor for ExponentiallyWeightedMeanRegressor

fn feature_count(&self) -> usize

The number of features the model expects.

fn samples_seen(&self) -> u64

How many training samples the model has seen so far.

fn predict(&self, _features: &[f64]) -> Result<f64, RillError>

Predict the target for the given feature slice.

fn learn(&mut self, _features: &[f64], target: f64) -> Result<(), RillError>

Update the model using a single labeled sample.

fn reset(&mut self)

Reset the model to its initial state, as if no samples had been seen.