Struct MultinomialNaiveBayes 

pub struct MultinomialNaiveBayes { /* private fields */ }

Online Multinomial Naive Bayes classifier.

Designed for count features (non-negative values). Uses Laplace smoothing. Commonly used for text classification with word counts.

Examples

use rill_ml::models::MultinomialNaiveBayes;
use rill_ml::OnlineBinaryClassifier;

let mut model = MultinomialNaiveBayes::new(3, Default::default()).unwrap();
model.learn(&[2.0, 1.0, 0.0], true).unwrap();
model.learn(&[0.0, 1.0, 3.0], false).unwrap();
let proba = model.predict_proba(&[1.0, 1.0, 0.0]).unwrap();
assert!(proba > 0.0 && proba < 1.0);

Implementations

impl MultinomialNaiveBayes

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

Create a new Multinomial Naive Bayes classifier.

feature_count must be greater than zero.

Trait Implementations

impl Clone for MultinomialNaiveBayes

fn clone(&self) -> MultinomialNaiveBayes

Returns a duplicate of the value.

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

Performs copy-assignment from source.

impl Debug for MultinomialNaiveBayes

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

Formats the value using the given formatter.

impl OnlineBinaryClassifier for MultinomialNaiveBayes

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_proba(&self, features: &[f64]) -> Result<f64, RillError>

Predict the probability of the positive class.

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

Update the model using a single labeled sample.

fn reset(&mut self)

Reset the model to its initial state.

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

Predict the boolean class label using a 0.5 threshold.