Struct rustlearn::trees::decision_tree::Hyperparameters

pub struct Hyperparameters {
    // some fields omitted
}

Hyperparameters for a DecisionTree model.

Methods

impl Hyperparameters

fn new(dim: usize) -> Hyperparameters

Creates new Hyperparameters

Examples

use rustlearn::trees::decision_tree::Hyperparameters;

let model = Hyperparameters::new(4)
                            .min_samples_split(5)
                            .max_depth(40)
                            .build();

fn max_features(&mut self, max_features: usize) -> &mut Hyperparameters

Set the maximum number of features to be considered when finding the best split for the decision tree.

Defaults to sqrt(self.dim)

fn min_samples_split(&mut self, min_samples_split: usize) -> &mut Hyperparameters

Set the minimum number of samples that must be present in order for further splitting to take place.

Defaults to 2.

fn max_depth(&mut self, max_depth: usize) -> &mut Hyperparameters

Set the maximum depth of the tree.

Defaults to usize::MAX.

fn rng(&mut self, rng: StdRng) -> &mut Hyperparameters

Set the random number generator used for sampling features to consider at each split.

fn build(&self) -> DecisionTree

Build a binary decision tree model.

fn one_vs_rest(&self) -> OneVsRestWrapper<DecisionTree>

Build a one-vs-rest multi-class decision tree model.

Trait Implementations

impl Decodable for Hyperparameters

fn decode<__D: Decoder>(__arg_0: &mut __D) -> Result<Hyperparameters, __D::Error>

impl Encodable for Hyperparameters

fn encode<__S: Encoder>(&self, __arg_0: &mut __S) -> Result<(), __S::Error>

impl Clone for Hyperparameters

fn clone(&self) -> Hyperparameters

Returns a copy of the value.

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

Performs copy-assignment from source.