Struct LinearRegression 

pub struct LinearRegression { /* private fields */ }

Online linear regression model.

Examples

use rill_ml::{
    models::{LinearRegression, LinearRegressionConfig},
    optim::{Optimizer, SgdConfig},
    loss::RegressionLoss,
    OnlineRegressor,
};

let feature_count = 2;
let mut model = LinearRegression::new(
    feature_count,
    LinearRegressionConfig {
        optimizer: Optimizer::sgd(feature_count, SgdConfig {
            learning_rate: 0.1,
            l2: 0.0,
        }).unwrap(),
        loss: RegressionLoss::default(),
    },
).unwrap();

let prediction = model.predict(&[1.0, 2.0]).unwrap();
model.learn(&[1.0, 2.0], 3.0).unwrap();

Implementations

impl LinearRegression

pub fn new( feature_count: usize, config: LinearRegressionConfig, ) -> Result<Self, RillError>

Create a new linear regression model.

The optimizer’s feature count must match feature_count.

pub fn weights(&self) -> &[f64]

The learned weights.

pub const fn intercept(&self) -> f64

The learned intercept (bias).

Trait Implementations

impl Clone for LinearRegression

fn clone(&self) -> LinearRegression

Returns a duplicate of the value.

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

Performs copy-assignment from source.

impl Debug for LinearRegression

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

Formats the value using the given formatter.

impl OnlineRegressor for LinearRegression

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.