ppforest2 v0.1.0
Projection Pursuit Decision Trees and Random Forests
Loading...
Searching...
No Matches
ppforest2::VariableImportance Struct Reference

Grouped result of the three variable importance measures. More...

#include <VariableImportance.hpp>

Public Attributes

types::FeatureVector permuted
 
types::FeatureVector projections
 
types::FeatureVector scale
 
types::FeatureVector weighted_projections
 

Detailed Description

Grouped result of the three variable importance measures.

For single trees only projections and scale are populated; permuted and weighted_projections remain empty (size 0).

// Forest — all three measures:
auto vi1 = variable_importance_permuted(forest, x, y, seed: 0);
auto vi2 = variable_importance_projections(forest, x.cols());
// Single tree — projection-based only:
auto vi = variable_importance_projections(tree, x.cols());
types::FeatureVector variable_importance_projections(Forest const &forest, int n_vars, types::FeatureVector const *scale=nullptr)
VI2 — Projections importance (forest).
types::FeatureVector variable_importance_weighted_projections(Forest const &forest, types::FeatureMatrix const &x, types::ResponseVector const &y, types::FeatureVector const *scale=nullptr)
VI3 — Weighted projections importance.
types::FeatureVector variable_importance_permuted(Forest const &forest, types::FeatureMatrix const &x, types::ResponseVector const &y, int seed=0)
VI1 — Permuted importance.
See also
variable_importance_permuted, variable_importance_projections, variable_importance_weighted_projections

Member Data Documentation

◆ permuted

types::FeatureVector ppforest2::VariableImportance::permuted

◆ projections

types::FeatureVector ppforest2::VariableImportance::projections

◆ scale

types::FeatureVector ppforest2::VariableImportance::scale

◆ weighted_projections

types::FeatureVector ppforest2::VariableImportance::weighted_projections

The documentation for this struct was generated from the following file: