ppforest2::sr::SRStrategy Struct Reference

Abstract strategy for computing the split threshold. More...

#include <SRStrategy.hpp>

Public Member Functions
types::Feature	operator() (types::FeatureMatrix const &group_1, types::FeatureMatrix const &group_2, pp::Projector const &projector) const
	Convenience operator: equivalent to threshold().
virtual types::Feature	threshold (types::FeatureMatrix const &group_1, types::FeatureMatrix const &group_2, pp::Projector const &projector) const =0
	Compute the split threshold for two groups.
Public Member Functions inherited from Strategy< SRStrategy >
virtual	~Strategy ()=default
virtual std::string	display_name () const=0
	Human-readable name for display in summaries.
virtual void	to_json (nlohmann::json &j) const=0
	Serialize this strategy's configuration to JSON.

Additional Inherited Members
Public Types inherited from Strategy< SRStrategy >
using	Factory
	Factory function type for deserializing a strategy from JSON.
using	Ptr
Static Public Member Functions inherited from Strategy< SRStrategy >
static Ptr	from_json (nlohmann::json const &j)
	Construct a strategy from its JSON representation.
static bool	register_strategy (std::string const &name, Factory factory)
	Register a concrete strategy for JSON deserialization.

Detailed Description

Abstract strategy for computing the split threshold.

Given the data for two groups and a projection vector, determines the threshold value that separates the groups in the projected space. Concrete subclasses implement different splitting rules (e.g. mean of group means, median-based rules).

Implementations must also provide to_json() for serialization.

Member Function Documentation

operator()()

types::Feature ppforest2::sr::SRStrategy::operator() ( types::FeatureMatrix const & group_1, types::FeatureMatrix const & group_2, pp::Projector const & projector ) const

inline

Convenience operator: equivalent to threshold().

threshold()

virtual types::Feature ppforest2::sr::SRStrategy::threshold ( types::FeatureMatrix const & group_1, types::FeatureMatrix const & group_2, pp::Projector const & projector ) const

pure virtual

Compute the split threshold for two groups.

Parameters

group_1	Feature matrix for the first group (n1 × p).
group_2	Feature matrix for the second group (n2 × p).
projector	Projection vector (p).

Returns

Scalar threshold in the projected space.

Implemented in ppforest2::sr::SRMeanOfMeansStrategy.

---

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

• core/src/models/SRStrategy.hpp