svm_classifier::OneVsOneStrategy Class Reference

One-vs-One (OvO) multiclass strategy. More...

#include <multiclass_strategy.hpp>

Inheritance diagram for svm_classifier::OneVsOneStrategy:

Collaboration diagram for svm_classifier::OneVsOneStrategy:

Public Member Functions
	OneVsOneStrategy ()
	Constructor.
	~OneVsOneStrategy () override
	Destructor.
TrainingMetrics	fit (const torch::Tensor &X, const torch::Tensor &y, const KernelParameters &params, DataConverter &converter) override
	Train the multiclass classifier.
std::vector< int >	predict (const torch::Tensor &X, DataConverter &converter) override
	Predict class labels.
std::vector< std::vector< double > >	predict_proba (const torch::Tensor &X, DataConverter &converter) override
	Predict class probabilities.
std::vector< std::vector< double > >	decision_function (const torch::Tensor &X, DataConverter &converter) override
	Get decision function values.
std::vector< int >	get_classes () const override
	Get unique class labels.
bool	supports_probability () const override
	Check if the model supports probability prediction.
int	get_n_classes () const override
	Get number of classes.
MulticlassStrategy	get_strategy_type () const override
	Get strategy type.
Public Member Functions inherited from svm_classifier::MulticlassStrategyBase
virtual	~MulticlassStrategyBase ()=default
	Virtual destructor.

Additional Inherited Members
Protected Attributes inherited from svm_classifier::MulticlassStrategyBase
std::vector< int >	classes_
	Unique class labels.
bool	is_trained_ = false
	Whether the model is trained.

Detailed Description

One-vs-One (OvO) multiclass strategy.

Definition at line 171 of file multiclass_strategy.hpp.

Member Function Documentation

decision_function()

std::vector< std::vector< double > > svm_classifier::OneVsOneStrategy::decision_function ( const torch::Tensor &  X, DataConverter &  converter  )

overridevirtual

Get decision function values.

Parameters

X	Feature tensor of shape (n_samples, n_features)
converter	Data converter instance

Returns

Decision function values

Implements svm_classifier::MulticlassStrategyBase.

fit()

TrainingMetrics svm_classifier::OneVsOneStrategy::fit ( const torch::Tensor &  X, const torch::Tensor &  y, const KernelParameters &  params, DataConverter &  converter  )

overridevirtual

Train the multiclass classifier.

Parameters

X	Feature tensor of shape (n_samples, n_features)
y	Target tensor of shape (n_samples,)
params	Kernel parameters
converter	Data converter instance

Returns

Training metrics

Implements svm_classifier::MulticlassStrategyBase.

get_classes()

std::vector< int > svm_classifier::OneVsOneStrategy::get_classes ( ) const

inlineoverridevirtual

Get unique class labels.

Returns

Vector of unique class labels

Implements svm_classifier::MulticlassStrategyBase.

Definition at line 197 of file multiclass_strategy.hpp.

get_n_classes()

int svm_classifier::OneVsOneStrategy::get_n_classes ( ) const

inlineoverridevirtual

Get number of classes.

Returns

Number of classes

Implements svm_classifier::MulticlassStrategyBase.

Definition at line 201 of file multiclass_strategy.hpp.

get_strategy_type()

MulticlassStrategy svm_classifier::OneVsOneStrategy::get_strategy_type ( ) const

inlineoverridevirtual

Get strategy type.

Returns

Multiclass strategy type

Implements svm_classifier::MulticlassStrategyBase.

Definition at line 203 of file multiclass_strategy.hpp.

predict()

std::vector< int > svm_classifier::OneVsOneStrategy::predict ( const torch::Tensor &  X, DataConverter &  converter  )

overridevirtual

Predict class labels.

Parameters

X	Feature tensor of shape (n_samples, n_features)
converter	Data converter instance

Returns

Predicted class labels

Implements svm_classifier::MulticlassStrategyBase.

predict_proba()

std::vector< std::vector< double > > svm_classifier::OneVsOneStrategy::predict_proba ( const torch::Tensor &  X, DataConverter &  converter  )

overridevirtual

Predict class probabilities.

Parameters

X	Feature tensor of shape (n_samples, n_features)
converter	Data converter instance

Returns

Class probabilities for each sample

Implements svm_classifier::MulticlassStrategyBase.

supports_probability()

bool svm_classifier::OneVsOneStrategy::supports_probability ( ) const

overridevirtual

Check if the model supports probability prediction.

Returns

True if probabilities are supported

Implements svm_classifier::MulticlassStrategyBase.

---

The documentation for this class was generated from the following file:

• include/svm_classifier/multiclass_strategy.hpp