Module rusty_machine::learning::glm

Generalized Linear Model module

This model is likely to undergo changes in the near future. These changes will improve the learning algorithm.

Contains implemention of generalized linear models using iteratively reweighted least squares.

The model will automatically add the intercept term to the input data.

Usage

use rusty_machine::learning::glm::{GenLinearModel, Bernoulli};
use rusty_machine::learning::SupModel;
use rusty_machine::linalg::Matrix;
use rusty_machine::linalg::Vector;

let inputs = Matrix::new(4,1,vec![1.0,3.0,5.0,7.0]);
let targets = Vector::new(vec![0.,0.,1.,1.]);

// Construct a GLM with a Bernoulli distribution
// This is equivalent to a logistic regression model.
let mut log_mod = GenLinearModel::new(Bernoulli);

// Train the model
log_mod.train(&inputs, &targets).unwrap();

// Now we'll predict a new point
let new_point = Matrix::new(1,1,vec![10.]);
let output = log_mod.predict(&new_point).unwrap();

// Hopefully we classified our new point correctly!
assert!(output[0] > 0.5, "Our classifier isn't very good!");

Structs

Bernoulli	The Bernoulli regression family.
Binomial	The Binomial regression family.
GenLinearModel	The Generalized Linear Model
Identity	The Identity link function.
Log	The log link function.
Logit	The Logit link function.
Normal	The Normal regression family.
Poisson	The Poisson regression family.

Traits

Criterion	The criterion for the Generalized Linear Model.
LinkFunc	Link functions.