File statistics_provider_decomposable_sparse.hpp

namespace boosting
template<typename StatisticType>
class SparseDecomposableClassificationStatisticsProviderFactory : public IClassificationStatisticsProviderFactory
#include <statistics_provider_decomposable_sparse.hpp>

Allows to create instances of the class IStatisticsProvider that can be used in classification problems and provide access to an object of type IDecomposableStatistics using sparse data structures for storing the statistics.

Template Parameters:

StatisticType – The type of the statistics

Public Functions

SparseDecomposableClassificationStatisticsProviderFactory(std::unique_ptr<ISparseDecomposableClassificationLossFactory<StatisticType>> lossFactoryPtr, std::unique_ptr<ISparseEvaluationMeasureFactory<StatisticType>> evaluationMeasureFactoryPtr, std::unique_ptr<ISparseDecomposableRuleEvaluationFactory> regularRuleEvaluationFactoryPtr, std::unique_ptr<ISparseDecomposableRuleEvaluationFactory> pruningRuleEvaluationFactoryPtr, MultiThreadingSettings multiThreadingSettings)
Parameters:

  • lossFactoryPtr – An unique pointer to an object of type ISparseDecomposableClassificationLossFactory that allows to create implementations of the loss function that should be used for calculating gradients and Hessians

  • evaluationMeasureFactoryPtr – An unique pointer to an object of type ISparseEvaluationMeasureFactory that allows to create implementations of the evaluation measure that should be used for assessing the quality of predictions

  • regularRuleEvaluationFactoryPtr – An unique pointer to an object of type ISparseDecomposableRuleEvaluationFactory that should be used for calculating the predictions, as well as corresponding quality scores, of all remaining rules

  • pruningRuleEvaluationFactoryPtr – An unique pointer to an object of type ISparseDecomposableRuleEvaluationFactory that should be used for calculating the predictions, as well as corresponding quality scores, when pruning rules

  • multiThreadingSettings – An object of type MultiThreadingSettings that stores the settings to be used for calculating the initial statistics in parallel

std::unique_ptr<IStatisticsProvider> create(const CContiguousView<const uint8> &labelMatrix) const override

See also

IClassificationStatisticsProviderFactory::create

std::unique_ptr<IStatisticsProvider> create(const BinaryCsrView &labelMatrix) const override

See also

IClassificationStatisticsProviderFactory::create

Private Members

const std::unique_ptr<ISparseDecomposableClassificationLossFactory<StatisticType>> lossFactoryPtr_
const std::unique_ptr<ISparseEvaluationMeasureFactory<StatisticType>> evaluationMeasureFactoryPtr_
const std::unique_ptr<ISparseDecomposableRuleEvaluationFactory> regularRuleEvaluationFactoryPtr_
const std::unique_ptr<ISparseDecomposableRuleEvaluationFactory> pruningRuleEvaluationFactoryPtr_
const MultiThreadingSettings multiThreadingSettings_