Struct VotingClassifier 

pub struct VotingClassifier<State = Untrained> { /* private fields */ }

Voting Classifier with type-safe state management

A voting classifier is an ensemble meta-algorithm that fits several base classifiers, each on the whole dataset. It then aggregates the individual predictions to form a final prediction.

Examples

use sklears_ensemble::voting::{VotingClassifier, VotingStrategy};
use sklears_ensemble::voting::config::VotingClassifierConfig;

// Create voting classifier with configuration
let config = VotingClassifierConfig {
    voting: VotingStrategy::Soft,
    weights: Some(vec![1.0, 2.0, 1.5]),
    confidence_weighting: true,
    confidence_threshold: 0.8,
    ..Default::default()
};
let classifier = VotingClassifier::new(config);
assert_eq!(classifier.estimators().len(), 0);

Implementations

impl VotingClassifier<Untrained>

pub fn new(config: VotingClassifierConfig) -> Self

Create a new untrained voting classifier

pub fn builder() -> VotingClassifierBuilder

Create a builder for configuring the voting classifier

pub fn add_estimator( &mut self, estimator: Box<dyn EnsembleMember + Send + Sync>, )

Add an estimator to the ensemble

pub fn config(&self) -> &VotingClassifierConfig

Get the current configuration

pub fn estimators(&self) -> &[Box<dyn EnsembleMember + Send + Sync>]

Get the estimators in the ensemble

pub fn optimize_ensemble_size( &self, x: &Array2<Float>, y: &Array1<Float>, ) -> Result<EnsembleSizeRecommendations>

Optimize ensemble size based on training data

pub fn analyze_ensemble_size( &self, x: &Array2<Float>, y: &Array1<Float>, ) -> Result<EnsembleSizeAnalysis>

Analyze ensemble size performance characteristics

impl VotingClassifier<Trained>

pub fn classes(&self) -> &Array1<Float>

Get the classes discovered during training

pub fn n_features_in(&self) -> usize

Get the number of features seen during training

pub fn estimators(&self) -> &[Box<dyn EnsembleMember + Send + Sync>]

Get the estimators in the ensemble

pub fn predict_with_confidence( &self, x: &Array2<Float>, ) -> Result<(Array1<Float>, Array1<Float>)>

Make predictions with confidence scores

pub fn predict_with_confidence_weighting( &self, x: &Array2<Float>, ) -> Result<Array1<Float>>

Make predictions with confidence weighting

pub fn estimator_confidence_scores( &self, x: &Array2<Float>, ) -> Result<Array1<Float>>

Get confidence scores for individual estimators

pub fn predict_proba(&self, x: &Array2<Float>) -> Result<Array2<Float>>

Make probability predictions (if supported by estimators)

pub fn update_weights_dynamically( &mut self, recent_performances: &[Float], ) -> Result<()>

Update ensemble weights dynamically based on performance

pub fn get_ensemble_size_recommendations(&self) -> EnsembleSizeRecommendations

Get ensemble size recommendations

Trait Implementations

impl Debug for VotingClassifier<Untrained>

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

Formats the value using the given formatter.

impl Debug for VotingClassifier<Trained>

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

Formats the value using the given formatter.

impl Default for VotingClassifier<Untrained>

fn default() -> Self

Returns the “default value” for a type.

impl Fit<ArrayBase<OwnedRepr<f64>, Dim<[usize; 2]>>, ArrayBase<OwnedRepr<f64>, Dim<[usize; 1]>>> for VotingClassifier<Untrained>

type Fitted = VotingClassifier<Trained>

The fitted model type

fn fit(self, x: &Array2<Float>, y: &Array1<Float>) -> Result<Self::Fitted>

Fit the model to the provided data with validation

fn fit_with_validation( self, x: &X, y: &Y, _x_val: Option<&X>, _y_val: Option<&Y>, ) -> Result<(Self::Fitted, FitMetrics), SklearsError>

where Self: Sized,

Fit with custom validation and early stopping

impl Predict<ArrayBase<OwnedRepr<f64>, Dim<[usize; 2]>>, ArrayBase<OwnedRepr<f64>, Dim<[usize; 1]>>> for VotingClassifier<Trained>

fn predict(&self, x: &Array2<Float>) -> Result<Array1<Float>>

Make predictions on the provided data

fn predict_with_uncertainty( &self, x: &X, ) -> Result<(Output, UncertaintyMeasure), SklearsError>

Make predictions with confidence intervals