Struct DecisionTreeClassifier 

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

CART decision tree for classification.

Implementations

impl DecisionTreeClassifier

pub fn new() -> Self

Create a new classifier with default parameters.

pub fn max_depth(self, d: usize) -> Self

Set maximum tree depth.

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

Set minimum samples required to split an internal node.

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

Set minimum samples required in a leaf node.

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

Set maximum features to consider per split (for random forest).

pub fn criterion(self, c: SplitCriterion) -> Self

Set the split criterion.

pub fn class_weight(self, cw: ClassWeight) -> Self

Set class weighting strategy for imbalanced datasets.

When set to ClassWeight::Balanced, minority classes receive higher weight in impurity calculations, improving their recall.

Example

use scry_learn::tree::DecisionTreeClassifier;
use scry_learn::weights::ClassWeight;

let dt = DecisionTreeClassifier::new()
    .class_weight(ClassWeight::Balanced);

pub fn ccp_alpha(self, alpha: f64) -> Self

Set cost-complexity pruning parameter.

Subtrees with effective alpha ≤ ccp_alpha are pruned after tree construction. A value of 0.0 (default) disables pruning. Larger values produce smaller, more regularized trees.

Example

use scry_learn::tree::DecisionTreeClassifier;

let dt = DecisionTreeClassifier::new()
    .ccp_alpha(0.01);

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

Train the decision tree on a dataset.

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

Predict class labels for a feature matrix.

features is row-major: features[sample_idx][feature_idx].

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

Predict class probabilities for a feature matrix.

pub fn feature_importances(&self) -> Result<Vec<f64>>

Get feature importances (sum of weighted impurity decreases).

pub fn flat_tree(&self) -> Option<&FlatTree>

Get the flat tree (for direct access).

pub fn depth(&self) -> usize

Tree depth.

pub fn n_leaves(&self) -> usize

Number of leaf nodes.

pub fn n_features(&self) -> usize

Number of features the model was trained on.

pub fn n_classes(&self) -> usize

Number of classes.

pub fn cost_complexity_pruning_path( &self, data: &Dataset, ) -> Result<(Vec<f64>, Vec<f64>)>

Compute the cost-complexity pruning path for this classifier.

Trains an unpruned tree, then returns (ccp_alphas, total_impurities), a sequence of effective alpha values and the corresponding total tree impurity at each pruning step. Useful for selecting ccp_alpha via the elbow method.

The classifier must be fitted before calling this method.

Trait Implementations

impl CalibrableClassifier for DecisionTreeClassifier

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

Train on a dataset.

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

Predict class labels.

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

Predict class probabilities. Returns [n_samples][n_classes].

fn clone_box(&self) -> Box<dyn CalibrableClassifier>

Clone into a boxed trait object.

impl Clone for DecisionTreeClassifier

fn clone(&self) -> DecisionTreeClassifier

Returns a duplicate of the value.

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

Performs copy-assignment from source.

impl Default for DecisionTreeClassifier

fn default() -> Self

Returns the “default value” for a type.

impl PipelineModel for DecisionTreeClassifier

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

Train the model on a dataset.

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

Predict on row-major feature matrix.

impl Tunable for DecisionTreeClassifier

fn set_param(&mut self, name: &str, _value: ParamValue) -> Result<()>

Apply a named hyperparameter.

fn clone_box(&self) -> Box<dyn Tunable>

Clone this model into a boxed trait object.

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

Train on a dataset.

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

Predict on row-major features.