Belle II Software  release-08-01-10
MVAFacetRelationFilter Class Reference

Background facetRelation detection based on MVA. More...

#include <MVAFacetRelationFilter.h>

Inheritance diagram for MVAFacetRelationFilter:
Collaboration diagram for MVAFacetRelationFilter:

Public Types

using Object = typename AFilter::Object
 Type of the object to be analysed.
 

Public Member Functions

 MVAFacetRelationFilter ()
 Constructor initialising the MVAFilter with standard training name for this filter.
 
Weight predict (const Relation< const CDCFacet > &facetRelation) final
 Main filter method returning the weight of the facet relation. More...
 
void exposeParameters (ModuleParamList *moduleParamList, const std::string &prefix) override
 Expose the set of parameters of the filter to the module parameter list.
 
void initialize () override
 Initialize the expert before event processing.
 
void beginRun () override
 Signal to load new run parameters.
 
Weight operator() (const Object &obj) override
 Function to object for its signalness.
 
virtual double predict (const Object &obj)
 Evaluate the mva method.
 
bool needsTruthInformation () override
 Checks if any variables need Monte Carlo information.
 
std::unique_ptr< AVarSetreleaseVarSet () &&
 Steal the set of variables form this filter - filter becomes disfunctional afterwards.
 

Protected Member Functions

AVarSetgetVarSet () const
 Getter for the set of variables.
 
void setVarSet (std::unique_ptr< AVarSet > varSet)
 Setter for the set of variables.
 

Private Types

using Super = MVA< BaseFacetRelationFilter >
 Type of the base class.
 
using AVarSet = BaseVarSet< Object >
 Type of the variable set.
 

Private Attributes

std::string m_identifier
 Database identifier of the expert or weight file name.
 
double m_cutValue
 The cut on the MVA output.
 
std::string m_DBPayloadName
 Name of the DB payload.
 
std::unique_ptr< MVAExpertm_mvaExpert
 MVA Expert to examine the object.
 
std::unique_ptr< AVarSetm_varSet
 Instance of the variable set to be used in the filter.
 

Detailed Description

Background facetRelation detection based on MVA.

Definition at line 30 of file MVAFacetRelationFilter.h.

Member Function Documentation

◆ predict()

Weight predict ( const Relation< const CDCFacet > &  facetRelation)
final

Main filter method returning the weight of the facet relation.

The size of the facetRelation with a small penalty depending on the mva probability.

Definition at line 23 of file MVAFacetRelationFilter.cc.

24 {
25  return -2 - 0.2 * (1 - Super::predict(facetRelation));
26 }
virtual double predict(const Object &obj)
Evaluate the mva method.

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