Struct VotingClassifier 

#[non_exhaustive]
pub struct VotingClassifier { /* private fields */ }

Combines multiple classifiers via voting.

In Voting::Hard mode, each estimator votes for a class and the majority wins. In Voting::Soft mode, predicted probabilities are averaged and the class with the highest average probability is selected.

Examples

use scry_learn::ensemble::{VotingClassifier, Voting};
use scry_learn::tree::DecisionTreeClassifier;

let vc = VotingClassifier::new(vec![
    Box::new(DecisionTreeClassifier::new().max_depth(3)),
    Box::new(DecisionTreeClassifier::new().max_depth(5)),
    Box::new(DecisionTreeClassifier::new().max_depth(7)),
]).voting(Voting::Hard);

Implementations

impl VotingClassifier

pub fn new(estimators: Vec<Box<dyn EnsembleClassifier>>) -> Self

Create a new voting classifier with the given base estimators.

pub fn voting(self, v: Voting) -> Self

Set the voting strategy (default: Voting::Hard).

pub fn weights(self, w: Vec<f64>) -> Self

Set weights for each estimator (default: equal weights).

pub fn fit(&mut self, data: &Dataset) -> Result<()>

Fit all base estimators on the given dataset.

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

Predict class labels via voting.

Trait Implementations

impl Clone for VotingClassifier

fn clone(&self) -> VotingClassifier

Returns a duplicate of the value.

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

Performs copy-assignment from source.

impl Debug for VotingClassifier

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

Formats the value using the given formatter.