Trait forust_ml::splitter::Splitter

source · 
pub trait Splitter {
    // Required methods
    fn get_constraint(&self, feature: &usize) -> Option<&Constraint>;
    fn get_gamma(&self) -> f32;
    fn get_l2(&self) -> f32;
    fn get_learning_rate(&self) -> f32;
    fn evaluate_split(
        &self,
        left_gradient: f32,
        left_hessian: f32,
        right_gradient: f32,
        right_hessian: f32,
        missing_gradient: f32,
        missing_hessian: f32,
        lower_bound: f32,
        upper_bound: f32,
        parent_weight: f32,
        constraint: Option<&Constraint>
    ) -> Option<(NodeInfo, NodeInfo, MissingInfo)>;
    fn handle_split_info(
        &self,
        split_info: SplitInfo,
        n_nodes: &usize,
        node: &mut SplittableNode,
        index: &mut [usize],
        data: &Matrix<'_, u16>,
        cuts: &JaggedMatrix<f64>,
        grad: &[f32],
        hess: &[f32],
        parallel: bool
    ) -> Vec<SplittableNode>;

    // Provided methods
    fn new_leaves_added(&self) -> usize { ... }
    fn clean_up_splits(&self, _tree: &mut Tree) { ... }
    fn best_split(&self, node: &SplittableNode) -> Option<SplitInfo> { ... }
    fn best_feature_split(
        &self,
        node: &SplittableNode,
        feature: usize
    ) -> Option<SplitInfo> { ... }
    fn split_node(
        &self,
        n_nodes: &usize,
        node: &mut SplittableNode,
        index: &mut [usize],
        data: &Matrix<'_, u16>,
        cuts: &JaggedMatrix<f64>,
        grad: &[f32],
        hess: &[f32],
        parallel: bool
    ) -> Vec<SplittableNode> { ... }
}

Required Methods§

source

fn get_constraint(&self, feature: &usize) -> Option<&Constraint>

source

fn get_gamma(&self) -> f32

source

fn get_l2(&self) -> f32

source

fn get_learning_rate(&self) -> f32

source

fn evaluate_split( &self, left_gradient: f32, left_hessian: f32, right_gradient: f32, right_hessian: f32, missing_gradient: f32, missing_hessian: f32, lower_bound: f32, upper_bound: f32, parent_weight: f32, constraint: Option<&Constraint> ) -> Option<(NodeInfo, NodeInfo, MissingInfo)>

Evaluate a split, returning the node info for the left, and right splits, as well as the node info the missing data of a feature.

source

fn handle_split_info( &self, split_info: SplitInfo, n_nodes: &usize, node: &mut SplittableNode, index: &mut [usize], data: &Matrix<'_, u16>, cuts: &JaggedMatrix<f64>, grad: &[f32], hess: &[f32], parallel: bool ) -> Vec<SplittableNode>

Handle the split info, creating the children nodes, this function will return a vector of new splitable nodes, that can be added to the growable stack, and further split, or converted to leaf nodes.

Provided Methods§

source

fn new_leaves_added(&self) -> usize

When a split happens, how many leaves will the tree increase by? For example, if a binary split happens, the split will increase the number of leaves by 1, if a ternary split happens, the number of leaves will increase by 2.

source

fn clean_up_splits(&self, _tree: &mut Tree)

Perform any post processing on the tree that is relevant for the specific splitter, empty default implementation so that it can be called even if it’s not used.

source

fn best_split(&self, node: &SplittableNode) -> Option<SplitInfo>

Find the best possible split, considering all feature histograms. If we wanted to add Column sampling, this is probably where we would need to do it, otherwise, it would be at the tree level.

source

fn best_feature_split( &self, node: &SplittableNode, feature: usize ) -> Option<SplitInfo>

source

fn split_node( &self, n_nodes: &usize, node: &mut SplittableNode, index: &mut [usize], data: &Matrix<'_, u16>, cuts: &JaggedMatrix<f64>, grad: &[f32], hess: &[f32], parallel: bool ) -> Vec<SplittableNode>

Split the node, if we cant find a best split, we will need to return an empty vector, this node is a leaf.

Implementors§