Pandora
Pandora source code navigator
Loading...
Searching...
No Matches
MvaPfoCharacterisationAlgorithm.h
Go to the documentation of this file.
1
8#ifndef LAR_MVA_PFO_CHARACTERISATION_ALGORITHM_H
9#define LAR_MVA_PFO_CHARACTERISATION_ALGORITHM_H 1
10
12
15
18
20
21namespace lar_content
22{
23
27template <typename T>
29{
30public:
35
36protected:
37 virtual bool IsClearTrack(const pandora::ParticleFlowObject *const pPfo) const;
38 virtual bool IsClearTrack(const pandora::Cluster *const pCluster) const;
40
42
45
48
51
58 unsigned int m_minCaloHitsCut;
67
68 std::string m_caloHitListName;
70
73 std::string m_mvaFileName;
74 std::string m_mvaName;
77
79
80private:
86 bool PassesFiducialCut(const pandora::CartesianVector &vertex) const;
87};
88
91
92} // namespace lar_content
93
94#endif // #ifndef LAR_MVA_PFO_CHARACTERISATION_ALGORITHM_H
Header file for the lar adaptive boosted decision tree class.
Header file for the lar monte carlo particle helper helper class.
Header file for the lar support vector machine class.
Header file defining relevant internal typedefs, sort and string conversion functions.
Header file for the pfo characterisation base algorithm class.
Header file for the track shower id feature tools.
std::map< std::string, MvaFeatureTool< Ts... > * > FeatureToolMap
pandora::StringVector m_algorithmToolNamesNoChargeInfo
Vector of strings saving feature tool order for use in feature calculation (missing W view)
pandora::StatusCode ReadSettings(const pandora::TiXmlHandle xmlHandle)
Read the algorithm settings.
float m_minProbabilityCut
The minimum probability to label a cluster as track-like.
PfoCharacterisationFeatureTool::FeatureToolMap m_featureToolMapThreeD
FeatureToolMap as a map for 3D info.
std::string m_trainingOutputFile
The training output file.
std::string m_mvaNameNoChargeInfo
The name of the mva to find for PFOs missing the W view, and thus charge info.
bool m_applyReconstructabilityChecks
Whether to apply reconstructability checks during training.
std::string m_filePathEnvironmentVariable
The environment variable providing a list of paths to mva files.
bool m_enableProbability
Whether to use probabilities instead of binary classification.
pandora::StringVector m_algorithmToolNames
Vector of strings saving feature tool order for use in feature calculation.
bool m_testBeamMode
Whether the training set is from a test beam experiment.
std::string m_mvaFileNameNoChargeInfo
The mva input file for PFOs missing the W view, and thus charge info.
PfoCharacterisationFeatureTool::FeatureToolMap m_featureToolMapNoChargeInfo
FeatureToolMap as a map for missing W view.
virtual bool IsClearTrack(const pandora::ParticleFlowObject *const pPfo) const
Whether pfo is identified as a clear track.
ClusterCharacterisationFeatureTool::FeatureToolMap m_featureToolMap
The feature tool map.
bool m_persistFeatures
Whether to write the features to the properties map.
std::string m_caloHitListName
Name of input calo hit list.
unsigned int m_minCaloHitsCut
The minimum number of calo hits to qualify as a track.
LArMCParticleHelper::PrimaryParameters m_primaryParameters
The mc particle primary selection parameters.
bool m_applyFiducialCut
Whether to apply a fiducial volume cut during training.
std::string m_mcParticleListName
Name of input MC particle list.
bool PassesFiducialCut(const pandora::CartesianVector &vertex) const
Checks if the interaction vertex is within the fiducial volume.
CartesianVector class.
Cluster class.
Definition Cluster.h:31
ParticleFlowObject class.
MvaPfoCharacterisationAlgorithm< AdaBoostDecisionTree > BdtPfoCharacterisationAlgorithm
MvaPfoCharacterisationAlgorithm< SupportVectorMachine > SvmPfoCharacterisationAlgorithm
std::vector< std::string > StringVector
StatusCode
The StatusCode enum.