File measure_evaluation_sparse.hpp

template<typename ScoreType>
class ISparseEvaluationMeasure : public virtual IClassificationEvaluationMeasure<ScoreType>
#include <measure_evaluation_sparse.hpp>

Defines an interface for all measures that may be used to assess the quality of scores that are predicted for certain examples, which are stored using sparse data structures, by comparing them to the corresponding ground truth labels.

Template Parameters:

ScoreType – The type of the predicted scores

Public Functions

inline virtual ~ISparseEvaluationMeasure() override
virtual ScoreType evaluate(uint32 exampleIndex, const CContiguousView<const uint8> &labelMatrix, const SparseSetView<ScoreType> &scoreMatrix) const = 0

Calculates and returns a numerical score that assesses the quality of predictions for the example at a specific index by comparing them to the corresponding ground truth labels, based on a label matrix that provides random access to the labels of the training examples.

Parameters:

  • exampleIndex – The index of the example for which the predictions should be evaluated

  • labelMatrix – A reference to an object of type CContiguousView that provides random access to the labels of the training examples

  • scoreMatrix – A reference to an object of type SparseSetView that stores the currently predicted scores

Returns:

The numerical score that has been calculated

virtual ScoreType evaluate(uint32 exampleIndex, const BinaryCsrView &labelMatrix, const SparseSetView<ScoreType> &scoreMatrix) const = 0

Calculates and returns a numerical score that assesses the quality of predictions for the example at a specific index by comparing them to the corresponding ground truth labels, based on a label matrix that provides row-wise access to the labels of the training examples.

Parameters:

  • exampleIndex – The index of the example for which the predictions should be evaluated

  • labelMatrix – A reference to an object of type BinaryCsrView that provides row-wise access to the labels of the training examples

  • scoreMatrix – A reference to an object of type SparseSetView that stores the currently predicted scores

Returns:

The numerical score that has been calculated

template<typename ScoreType>
class ISparseEvaluationMeasureFactory : public virtual IClassificationEvaluationMeasureFactory<ScoreType>
#include <measure_evaluation_sparse.hpp>

Defines an interface for all factories that allow to create instances of the type ISparseEvaluationMeasure.

Template Parameters:

ScoreType – The type of the predicted scores

Public Functions

inline virtual ~ISparseEvaluationMeasureFactory() override
virtual std::unique_ptr<ISparseEvaluationMeasure<ScoreType>> createSparseEvaluationMeasure() const = 0

Creates and returns a new object of type ISparseEvaluationMeasure.

Returns:

An unique pointer to an object of type ISparseEvaluationMeasure that has been created

inline virtual std::unique_ptr<IClassificationEvaluationMeasure<ScoreType>> createClassificationEvaluationMeasure() const final override

Creates and returns a new object of type IClassificationEvaluationMeasure.

Returns:

An unique pointer to an object of type IClassificationEvaluationMeasure that has been created