Struct RandomForest 

pub struct RandomForest {
    pub trees: Vec<DecisionTree>,
    pub n_classes: usize,
}

A bagged ensemble of decision trees.

Fields

trees: Vec<DecisionTree>

Individual trees in the ensemble.

n_classes: usize

Number of distinct class labels.

Implementations

impl RandomForest

pub fn train(features: &[Vec<f64>], labels: &[usize], n_trees: usize) -> Self

Train a random forest on labelled feature data.

Uses bootstrap sampling (simple cyclic resampling for determinism in the absence of an RNG) and builds each tree with max_depth = 5.

pub fn predict(&self, features: &[f64]) -> usize

Predict the class for a feature vector using majority vote.

Trait Implementations

impl Clone for RandomForest

fn clone(&self) -> RandomForest

Returns a duplicate of the value.

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

Performs copy-assignment from source.

impl Debug for RandomForest

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

Formats the value using the given formatter.