File transformation_probability_marginalized.hpp¶
-
namespace boosting
-
class MarginalizedProbabilityTransformation : public boosting::IProbabilityTransformation¶
- #include <transformation_probability_marginalized.hpp>
An implementation of the class
IProbabilityTransformation
that transforms aggregated scores into marginalized probability estimates.Public Functions
-
MarginalizedProbabilityTransformation(const LabelVectorSet &labelVectorSet, std::unique_ptr<IJointProbabilityFunction> jointProbabilityFunctionPtr)¶
- Parameters:
labelVectorSet – A reference to an object of type
LabelVectorSet
that stores all known label vectorsjointProbabilityFunctionPtr – An unique pointer to an object of type
JointProbabilityFunction
that should be used to transform regression scores that are predicted for individual labels into probabilities
-
virtual void apply(View<float64>::const_iterator scoresBegin, View<float64>::const_iterator scoresEnd, View<float64>::iterator probabilitiesBegin, View<float64>::iterator probabilitiesEnd) const override¶
Transforms aggregated scores into probability estimates.
- Parameters:
scoresBegin – An iterator to the beginning of the aggregated scores
scoresEnd – An iterator to the end of the the aggregated scores
probabilitiesBegin – An iterator to the beginning of the probabilities
probabilitiesEnd – An iterator to the end of the probabilities
Private Members
-
const LabelVectorSet &labelVectorSet_¶
-
const std::unique_ptr<IJointProbabilityFunction> jointProbabilityFunctionPtr_¶
-
MarginalizedProbabilityTransformation(const LabelVectorSet &labelVectorSet, std::unique_ptr<IJointProbabilityFunction> jointProbabilityFunctionPtr)¶
-
class MarginalizedProbabilityTransformation : public boosting::IProbabilityTransformation¶