Struct ExponentiallyWeightedMean 

pub struct ExponentiallyWeightedMean { /* private fields */ }

Exponentially weighted moving average.

alpha must satisfy 0 < alpha <= 1. Smaller values give more weight to the past; alpha = 1 reduces to a LastValue-like tracker.

Examples

use rill_ml::stats::ExponentiallyWeightedMean;
use rill_ml::OnlineStatistic;

let mut ew = ExponentiallyWeightedMean::new(0.5).unwrap();
ew.update(10.0).unwrap();
ew.update(20.0).unwrap();
// 10.0, then 0.5*20 + 0.5*10 = 15.0
assert!((ew.value() - 15.0).abs() < 1e-12);

Implementations

impl ExponentiallyWeightedMean

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

Create a new exponentially weighted mean accumulator.

Returns an error if alpha is not in (0, 1].

pub const fn alpha(&self) -> f64

The configured alpha.

pub const fn value(&self) -> f64

Current weighted mean, or 0.0 if no observations have been seen.

pub const fn count(&self) -> u64

Number of observations seen so far.

Trait Implementations

impl Clone for ExponentiallyWeightedMean

fn clone(&self) -> ExponentiallyWeightedMean

Returns a duplicate of the value.

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

Performs copy-assignment from source.

impl Debug for ExponentiallyWeightedMean

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

Formats the value using the given formatter.

impl OnlineStatistic for ExponentiallyWeightedMean

fn update(&mut self, value: f64) -> Result<(), RillError>

Update the statistic with a new observation.

fn samples_seen(&self) -> u64

How many observations have been incorporated.

fn reset(&mut self)

Reset the statistic.