Struct OnlineStats 

pub struct OnlineStats { /* private fields */ }

Online statistics accumulator using Welford’s algorithm.

Tracks mean, variance, and lag-1 autocorrelation incrementally with O(1) overhead per sample. This is used to detect condition drift between calibration and the adaptive loop.

Example

use tacet_core::statistics::OnlineStats;

let mut stats = OnlineStats::new();
for x in [1.0, 2.0, 3.0, 4.0, 5.0] {
    stats.update(x);
}
let snapshot = stats.finalize();
assert!((snapshot.mean - 3.0).abs() < 1e-10);

Implementations

impl OnlineStats

pub fn new() -> Self

Create a new empty statistics accumulator.

pub fn update(&mut self, x: f64)

Update statistics with a new sample.

Uses Welford’s online algorithm for numerically stable variance computation. Also tracks lag-1 autocorrelation incrementally.

Arguments

• x - The new sample value

pub fn finalize(&self) -> StatsSnapshot

Finalize and return the computed statistics.

Returns

A StatsSnapshot containing mean, variance, and lag-1 autocorrelation. Returns default values (0.0) if insufficient samples.

pub fn count(&self) -> usize

Get the current sample count.

pub fn mean(&self) -> f64

Get the current mean estimate.

pub fn variance(&self) -> f64

Get the current variance estimate (returns 0 if count < 2).

Trait Implementations

impl Clone for OnlineStats

fn clone(&self) -> OnlineStats

Returns a duplicate of the value.

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

Performs copy-assignment from source.

impl Debug for OnlineStats

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

Formats the value using the given formatter.

impl Default for OnlineStats

fn default() -> Self

Returns the “default value” for a type.