ppforest2 v0.1.0
Projection Pursuit Decision Trees and Random Forests
Loading...
Searching...
No Matches
Cutpoint.hpp
Go to the documentation of this file.
1#pragma once
2
3#include "models/strategies/Strategy.hpp"
4#include "stats/Stats.hpp"
5
13namespace ppforest2 {
14 struct NodeContext;
15}
16
17namespace ppforest2::cutpoint {
23 class Cutpoint : public Strategy<Cutpoint> {
24 public:
31 void locate(NodeContext& ctx, stats::RNG& rng) const;
32
33 protected:
35 virtual void compute(NodeContext& ctx, stats::RNG& rng) const = 0;
36 };
37
39 Cutpoint::Ptr mean_of_means();
40}
Strategy
CRTP base class providing self-registration for strategy types.
Definition Strategy.hpp:93
Strategy< Cutpoint >::Ptr
std::shared_ptr< Cutpoint > Ptr
Definition Strategy.hpp:95
ppforest2::cutpoint::Cutpoint
Abstract strategy for computing the split cutpoint.
Definition Cutpoint.hpp:23
ppforest2::cutpoint::Cutpoint::locate
void locate(NodeContext &ctx, stats::RNG &rng) const
Locate the split cutpoint and store it in the context.
ppforest2::cutpoint::Cutpoint::compute
virtual void compute(NodeContext &ctx, stats::RNG &rng) const =0
Subclass implementation of cutpoint computation.
ppforest2::cutpoint
Definition Cutpoint.hpp:17
ppforest2::cutpoint::mean_of_means
Cutpoint::Ptr mean_of_means()
Factory function for mean-of-means split cutpoint.
ppforest2::stats::RNG
pcg32 RNG
Definition Stats.hpp:24
ppforest2
Binarization strategies for multiclass-to-binary reduction.
Definition Benchmark.hpp:25
ppforest2::NodeContext
Mutable context accumulating intermediate results during node training.
Definition NodeContext.hpp:20