File statistics_provider.hpp¶
-
class IStatisticsProvider¶
- #include <statistics_provider.hpp>
Provides access to an object of type
IStatistics.Public Functions
-
inline virtual ~IStatisticsProvider()¶
-
virtual IStatistics &get() const = 0¶
Returns an object of type
IStatistics.- Returns:
A reference to an object of type
IStatistics
-
virtual void switchToRegularRuleEvaluation() = 0¶
Switches the implementation that is used for calculating the predictions of rules, as well their overall quality, to the one that should be used for learning regular rules.
-
virtual void switchToPruningRuleEvaluation() = 0¶
Switches the implementation that is used for calculating the predictions of rules, as well as their overall quality, to the one that should be used for pruning rules.
-
inline virtual ~IStatisticsProvider()¶
-
class IClassificationStatisticsProviderFactory¶
- #include <statistics_provider.hpp>
Defines an interface for all classes that allow to create instances of the class
IStatisticsProviderthat can be used in classification problems.Public Functions
-
inline virtual ~IClassificationStatisticsProviderFactory()¶
-
virtual std::unique_ptr<IStatisticsProvider> create(const CContiguousView<const uint8> &labelMatrix) const = 0¶
Creates and returns a new instance of the class
IStatisticsProvider, based on a label matrix that provides random access to the labels of the training examples.- Parameters:
labelMatrix – A reference to an object of type
CContiguousViewthat provides random access to the labels of the training examples- Returns:
An unique pointer to an object of type
IStatisticsProviderthat has been created
-
virtual std::unique_ptr<IStatisticsProvider> create(const BinaryCsrView &labelMatrix) const = 0¶
Creates and returns a new instance of the class
IStatisticsProvider, based on a sparse label matrix that provides row-wise access to the labels of the training examples.- Parameters:
labelMatrix – A reference to an object of type
BinaryCsrViewthat provides row-wise access to the labels of the training examples- Returns:
An unique pointer to an object of type
IStatisticsProviderthat has been created
-
inline virtual ~IClassificationStatisticsProviderFactory()¶
-
class IRegressionStatisticsProviderFactory¶
- #include <statistics_provider.hpp>
Defines an interface for all classes that allow to create instances of the class
IStatisticsProviderthat can be used in regression problems.Public Functions
-
inline virtual ~IRegressionStatisticsProviderFactory()¶
-
virtual std::unique_ptr<IStatisticsProvider> create(const CContiguousView<const float32> ®ressionMatrix) const = 0¶
Creates and returns a new instance of the class
IStatisticsProvider, based on a regression matrix that provides random access to the regression scores of the training examples.- Parameters:
regressionMatrix – A reference to an object of type
CContiguousViewthat provides random access to the regression scores of the training examples- Returns:
An unique pointer to an object of type
IStatisticsProviderthat has been created
-
virtual std::unique_ptr<IStatisticsProvider> create(const CsrView<const float32> ®ressionMatrix) const = 0¶
Creates and returns a new instance of the class
IStatisticsProvider, based on a regression matrix that provides random access to the regression scores of the training examples.- Parameters:
regressionMatrix – A reference to an object of type
BinaryCsrViewthat provides row-wise access to the regression scores of the training examples- Returns:
An unique pointer to an object of type
IStatisticsProviderthat has been created
-
inline virtual ~IRegressionStatisticsProviderFactory()¶