Abstract class, defines interface for implementations of one selection step in sequential search type of methods. More...

#include <seq_step.hpp>

Inheritance diagram for FST::Sequential_Step< RETURNTYPE, DIMTYPE, SUBSET, CRITERION >:

Public Types
typedef std::shared_ptr< CRITERION >	PCriterion
	shared pointer to the criterion this step evaluates candidates against
typedef std::shared_ptr< SUBSET >	PSubset
	shared pointer to a feature subset
typedef std::shared_ptr< Result_Tracker< RETURNTYPE, SUBSET > >	PResultTracker
	shared pointer to the result tracker enabled via enable_result_tracking()

Public Member Functions
virtual bool	evaluate_candidates (RETURNTYPE &result, const PSubset sub, const PCriterion crit, const DIMTYPE _generalization_level, std::ostream &os)=0
	Performs one selection step: evaluates the candidate subsets reachable from `sub` and leaves the best of them in `sub`.
virtual std::ostream &	print (std::ostream &os) const
	writes a human-readable identification of the step and its configuration; base default writes nothing
void	enable_result_tracking (PResultTracker tracker)
	assigns a result tracker to this step, i.e., enables logging of all evaluated candidate subsets for future reuse (re-evaluation, etc.)
void	disable_result_tracking ()
	detaches any result tracker (result_tracker_active() then returns false)
bool	result_tracker_active () const
	true if a result tracker was assigned via enable_result_tracking() and not since disabled
void	set_output_detail (OutputDetail detail)
	sets the amount of information that is logged to output stream throughout the course of search
OutputDetail	get_output_detail () const
	the currently configured output detail level
bool	output_normal () const
	true unless output detail is SILENT
bool	output_detailed () const
	true only at the DETAILED output level

Protected Attributes
PResultTracker	_tracker
	the assigned result tracker, or null (see enable_result_tracking()/result_tracker_active())
OutputDetail	_detail
	the output detail level set via set_output_detail(); read by output_normal()/output_detailed()

Friends
std::ostream &	operator<< (std::ostream &os, const Sequential_Step< RETURNTYPE, DIMTYPE, SUBSET, CRITERION > &ss)
	Streams a selection step's print() to `os`.

Detailed Description

template<class RETURNTYPE, typename DIMTYPE, class SUBSET, class CRITERION>
class FST::Sequential_Step< RETURNTYPE, DIMTYPE, SUBSET, CRITERION >

Abstract class, defines interface for implementations of one selection step in sequential search type of methods.

Note: To prevent misunderstanding: _generalization_level here does not relate to classification performance on unknown data, but to "generalization" of sequential steps in the course of search, i.e., the number of features added/removed while generating candidate subsets (higher generalization=more candidates)

Member Function Documentation

◆ evaluate_candidates()

template<class RETURNTYPE, typename DIMTYPE, class SUBSET, class CRITERION>

virtual bool FST::Sequential_Step< RETURNTYPE, DIMTYPE, SUBSET, CRITERION >::evaluate_candidates	(	RETURNTYPE &	result,
		const PSubset	sub,
		const PCriterion	crit,
		const DIMTYPE	_generalization_level,
		std::ostream &	os )

pure virtual

Performs one selection step: evaluates the candidate subsets reachable from sub and leaves the best of them in sub.

This is the extension point of the whole sequential search family - a different candidate-selection strategy (prefiltering, ensemble voting, budgeted sampling, ...) is introduced by implementing this one method.

The candidates are the subsets offered by sub->getFirstCandidateSubset() and sub->getNextCandidateSubset(): those differing from sub in _generalization_level features, added in forward mode and removed in backward mode. An implementation may evaluate all of them or any subset of them, but must leave the chosen candidate in sub and its criterion value in result.

Parameters

result	receives the criterion value of the chosen candidate; meaningful only if true is returned
sub	in: the subset the candidates are generated from; out: the chosen candidate. `sub` doubles as the traversal state, so its contents are modified even when the call returns false
crit	the criterion the candidates are evaluated by; must be non-null and already initialize()d
_generalization_level	number of features added or removed at once (>=1, and at most the number of features)
os	stream the step's progress messages are written to

Returns: false if no candidate subset could be generated at all (nothing left to add or remove), or if a criterion evaluation failed; the caller must then treat the step as not performed

Implemented in FST::Sequential_Step_Ensemble< RETURNTYPE, DIMTYPE, SUBSET, CRITERION >, FST::Sequential_Step_Hybrid< RETURNTYPE, DIMTYPE, SUBSET, CRITERION, FILTERCRITERION >, FST::Sequential_Step_Hybrid< RETURNTYPE, DIMTYPE, SUBSET, CRITERION, CRITERION >, FST::Sequential_Step_Sampled< RETURNTYPE, DIMTYPE, SUBSET, CRITERION, WEIGHTER >, FST::Sequential_Step_Sampled< RETURNTYPE, DIMTYPE, SUBSET, CRITERION, WEIGHTER_SAMPLED >, and FST::Sequential_Step_Straight< RETURNTYPE, DIMTYPE, SUBSET, CRITERION >.

◆ print()

template<class RETURNTYPE, typename DIMTYPE, class SUBSET, class CRITERION>

virtual std::ostream & FST::Sequential_Step< RETURNTYPE, DIMTYPE, SUBSET, CRITERION >::print ( std::ostream & os ) const

inlinevirtual

writes a human-readable identification of the step and its configuration; base default writes nothing

Reimplemented in FST::Sequential_Step_Ensemble< RETURNTYPE, DIMTYPE, SUBSET, CRITERION >, FST::Sequential_Step_Hybrid< RETURNTYPE, DIMTYPE, SUBSET, CRITERION, FILTERCRITERION >, FST::Sequential_Step_Hybrid< RETURNTYPE, DIMTYPE, SUBSET, CRITERION, CRITERION >, FST::Sequential_Step_Sampled< RETURNTYPE, DIMTYPE, SUBSET, CRITERION, WEIGHTER >, FST::Sequential_Step_Sampled< RETURNTYPE, DIMTYPE, SUBSET, CRITERION, WEIGHTER_SAMPLED >, and FST::Sequential_Step_Straight< RETURNTYPE, DIMTYPE, SUBSET, CRITERION >.

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

/Users/psms/dev/devtest1/_src_search/seq_step.hpp

Public Types

Public Member Functions

Protected Attributes

Friends

Detailed Description

Member Function Documentation

◆ evaluate_candidates()

◆ print()