Struct BaggingClassifier 

pub struct BaggingClassifier<F> {
    pub n_estimators: usize,
    pub max_samples: f64,
    pub max_features: f64,
    pub bootstrap: bool,
    pub bootstrap_features: bool,
    pub random_state: Option<u64>,
    pub max_depth: Option<usize>,
    /* private fields */
}

Bootstrap aggregation (bagging) classifier using decision trees.

Each estimator is trained on a bootstrap sample of the data, optionally with a random subset of features. Final predictions are made by majority vote across all estimators.

Type Parameters

• F: The floating-point type (f32 or f64).

Fields

n_estimators: usize

Number of estimators in the ensemble.

max_samples: f64

Fraction of samples to draw for each estimator (default 1.0).

max_features: f64

Fraction of features to draw for each estimator (default 1.0).

bootstrap: bool

Whether to sample with replacement (default true).

bootstrap_features: bool

Whether to sample features with replacement (default false).

random_state: Option<u64>

Random seed for reproducibility.

max_depth: Option<usize>

Maximum depth of each base decision tree. None means unlimited.

Implementations

impl<F: Float> BaggingClassifier<F>

pub fn new() -> Self

Create a new BaggingClassifier with default settings.

Defaults: n_estimators = 10, max_samples = 1.0, max_features = 1.0, bootstrap = true, bootstrap_features = false, random_state = None, max_depth = None.

pub fn with_n_estimators(self, n: usize) -> Self

Set the number of estimators.

pub fn with_max_samples(self, frac: f64) -> Self

Set the fraction of samples to draw per estimator.

pub fn with_max_features(self, frac: f64) -> Self

Set the fraction of features to draw per estimator.

pub fn with_bootstrap(self, bootstrap: bool) -> Self

Set whether to sample with replacement.

pub fn with_bootstrap_features(self, bootstrap_features: bool) -> Self

Set whether to sample features with replacement.

pub fn with_random_state(self, seed: u64) -> Self

Set the random seed for reproducibility.

pub fn with_max_depth(self, max_depth: Option<usize>) -> Self

Set the maximum depth of each base decision tree.

Trait Implementations

impl<F: Clone> Clone for BaggingClassifier<F>

fn clone(&self) -> BaggingClassifier<F>

Returns a duplicate of the value.

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

Performs copy-assignment from source.

impl<F: Debug> Debug for BaggingClassifier<F>

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

Formats the value using the given formatter.

impl<F: Float> Default for BaggingClassifier<F>

fn default() -> Self

Returns the “default value” for a type.

impl<F: Float + Send + Sync + 'static> Fit<ArrayBase<OwnedRepr<F>, Dim<[usize; 2]>>, ArrayBase<OwnedRepr<usize>, Dim<[usize; 1]>>> for BaggingClassifier<F>

fn fit( &self, x: &Array2<F>, y: &Array1<usize>, ) -> Result<FittedBaggingClassifier<F>, FerroError>

Fit the bagging classifier by building n_estimators decision trees in parallel.

Each tree is trained on a (bootstrap) sample of the data with a random subset of features.

Errors

Returns FerroError::ShapeMismatch if x and y have different numbers of samples. Returns FerroError::InsufficientSamples if there are no samples. Returns FerroError::InvalidParameter for invalid hyperparameters.

type Fitted = FittedBaggingClassifier<F>

The fitted model type returned by fit.

type Error = FerroError

The error type returned by fit.

impl<F: Float + ToPrimitive + FromPrimitive + Send + Sync + 'static> PipelineEstimator<F> for BaggingClassifier<F>

fn fit_pipeline( &self, x: &Array2<F>, y: &Array1<F>, ) -> Result<Box<dyn FittedPipelineEstimator<F>>, FerroError>

Fit this estimator on the given data.