Classes
struct	LinearSVMParams

struct	LinearSVMModel

class	SVC
	C-Support Vector Classification. More...

struct	SupportStorage

struct	SvmModel

struct	SvmParameter

class	SmoSolver
	Solve the quadratic optimization problem using two level decomposition and Sequential Minimal Optimization (SMO). More...

class	WorkingSet

Enumerations
enum	SvmType { C_SVC , NU_SVC , EPSILON_SVR , NU_SVR }

Functions
template<typename math_t >
void	svcFit (const raft::handle_t &handle, math_t input, int n_rows, int n_cols, math_t labels, const SvmParameter ¶m, ML::matrix::KernelParams &kernel_params, SvmModel< math_t > &model, const math_t *sample_weight)
	Fit a support vector classifier to the training data. More...

template<typename math_t >
void	svcFitSparse (const raft::handle_t &handle, int indptr, int indices, math_t data, int n_rows, int n_cols, int nnz, math_t labels, const SvmParameter ¶m, ML::matrix::KernelParams &kernel_params, SvmModel< math_t > &model, const math_t *sample_weight)
	Fit a support vector classifier to the training data. More...

template<typename math_t >
void	svcPredict (const raft::handle_t &handle, math_t input, int n_rows, int n_cols, ML::matrix::KernelParams &kernel_params, const SvmModel< math_t > &model, math_t preds, math_t buffer_size, bool predict_class)
	Predict classes or decision function value for samples in input. More...

template<typename math_t >
void	svcPredictSparse (const raft::handle_t &handle, int indptr, int indices, math_t data, int n_rows, int n_cols, int nnz, ML::matrix::KernelParams &kernel_params, const SvmModel< math_t > &model, math_t preds, math_t buffer_size, bool predict_class)
	Predict classes or decision function value for samples in input. More...

template<typename math_t >
void	svmFreeBuffers (const raft::handle_t &handle, SvmModel< math_t > &m)

template<typename math_t >
void	svrFit (const raft::handle_t &handle, math_t X, int n_rows, int n_cols, math_t y, const SvmParameter ¶m, ML::matrix::KernelParams &kernel_params, SvmModel< math_t > &model, const math_t *sample_weight=nullptr)
	Fit a support vector regressor to the training data. More...

template<typename math_t >
void	svrFitSparse (const raft::handle_t &handle, int indptr, int indices, math_t data, int n_rows, int n_cols, int nnz, math_t y, const SvmParameter ¶m, ML::matrix::KernelParams &kernel_params, SvmModel< math_t > &model, const math_t *sample_weight=nullptr)
	Fit a support vector regressor to the training data. More...

Enumeration Type Documentation

◆ SvmType

enum ML::SVM::SvmType

Enumerator
C_SVC
NU_SVC
EPSILON_SVR
NU_SVR

Function Documentation

◆ svcFit()

template<typename math_t >

void ML::SVM::svcFit	(	const raft::handle_t &	handle,
		math_t *	input,
		int	n_rows,
		int	n_cols,
		math_t *	labels,
		const SvmParameter &	param,
		ML::matrix::KernelParams &	kernel_params,
		SvmModel< math_t > &	model,
		const math_t *	sample_weight
	)

Fit a support vector classifier to the training data.

Each row of the input data stores a feature vector. We use the SMO method to fit the SVM.

The output device buffers in model shall be unallocated on entry.

Template Parameters

math_t floating point type

Parameters

[in]	handle	the cuML handle
[in]	input	device pointer for the input data in column major format. Size n_rows x n_cols.
[in]	n_rows	number of rows
[in]	n_cols	number of columns
[in]	labels	device pointer for the labels. Size [n_rows].
[in]	param	parameters for training
[in]	kernel_params	parameters for the kernel function
[out]	model	parameters of the trained model
[in]	sample_weight	optional sample weights, size [n_rows]

◆ svcFitSparse()

template<typename math_t >

void ML::SVM::svcFitSparse	(	const raft::handle_t &	handle,
		int *	indptr,
		int *	indices,
		math_t *	data,
		int	n_rows,
		int	n_cols,
		int	nnz,
		math_t *	labels,
		const SvmParameter &	param,
		ML::matrix::KernelParams &	kernel_params,
		SvmModel< math_t > &	model,
		const math_t *	sample_weight
	)

Fit a support vector classifier to the training data.

Each row of the input data stores a feature vector. We use the SMO method to fit the SVM.

The output device buffers in model shall be unallocated on entry.

Template Parameters

math_t floating point type

Parameters

[in]	handle	the cuML handle
[in]	indptr	device pointer for CSR row positions. Size [n_rows + 1].
[in]	indices	device pointer for CSR column indices. Size [nnz].
[in]	data	device pointer for the CSR data. Size [nnz].
[in]	n_rows	number of rows
[in]	n_cols	number of columns
[in]	nnz	number of stored entries.
[in]	labels	device pointer for the labels. Size [n_rows].
[in]	param	parameters for training
[in]	kernel_params	parameters for the kernel function
[out]	model	parameters of the trained model
[in]	sample_weight	optional sample weights, size [n_rows]

◆ svcPredict()

template<typename math_t >

void ML::SVM::svcPredict	(	const raft::handle_t &	handle,
		math_t *	input,
		int	n_rows,
		int	n_cols,
		ML::matrix::KernelParams &	kernel_params,
		const SvmModel< math_t > &	model,
		math_t *	preds,
		math_t	buffer_size,
		bool	predict_class
	)

Predict classes or decision function value for samples in input.

We evaluate the decision function f(x_i). Depending on the parameter predict_class, we either return f(x_i) or the label corresponding to sign(f(x_i)).

The predictions are calculated according to the following formulas:

\[ f(x_i) = \sum_{j=1}^n_support K(x_i, x_j) * dual_coefs[j] + b) \]

pred(x_i) = label[sign(f(x_i))], if predict_class==true, or pred(x_i) = f(x_i), if predict_class==false.

Template Parameters

math_t floating point type

Parameters

	handle	the cuML handle
[in]	input	device pointer for the input data in column major format, size [n_rows x n_cols].
[in]	n_rows	number of rows (input vectors)
[in]	n_cols	number of columns (features)
[in]	kernel_params	parameters for the kernel function
[in]	model	SVM model parameters
[out]	preds	device pointer to store the predicted class labels. Size [n_rows]. Should be allocated on entry.
[in]	buffer_size	size of temporary buffer in MiB
[in]	predict_class	whether to predict class label (true), or just return the decision function value (false)

◆ svcPredictSparse()

template<typename math_t >

void ML::SVM::svcPredictSparse	(	const raft::handle_t &	handle,
		int *	indptr,
		int *	indices,
		math_t *	data,
		int	n_rows,
		int	n_cols,
		int	nnz,
		ML::matrix::KernelParams &	kernel_params,
		const SvmModel< math_t > &	model,
		math_t *	preds,
		math_t	buffer_size,
		bool	predict_class
	)

Predict classes or decision function value for samples in input.

We evaluate the decision function f(x_i). Depending on the parameter predict_class, we either return f(x_i) or the label corresponding to sign(f(x_i)).

The predictions are calculated according to the following formulas:

\[ f(x_i) = \sum_{j=1}^n_support K(x_i, x_j) * dual_coefs[j] + b) \]

pred(x_i) = label[sign(f(x_i))], if predict_class==true, or pred(x_i) = f(x_i), if predict_class==falsee.

Template Parameters

math_t floating point type

Parameters

	handle	the cuML handle
[in]	indptr	device pointer for CSR row positions. Size [n_rows + 1].
[in]	indices	device pointer for CSR column indices. Size [nnz].
[in]	data	device pointer for the CSR data. Size [nnz].
[in]	n_rows	number of rows
[in]	n_cols	number of columns
[in]	nnz	number of stored entries.
[in]	kernel_params	parameters for the kernel function
[in]	model	SVM model parameters
[out]	preds	device pointer to store the predicted class labels. Size [n_rows]. Should be allocated on entry.
[in]	buffer_size	size of temporary buffer in MiB
[in]	predict_class	whether to predict class label (true), or just return the decision function value (false)

◆ svmFreeBuffers()

template<typename math_t >

void ML::SVM::svmFreeBuffers	(	const raft::handle_t &	handle,
		SvmModel< math_t > &	m
	)

Deallocate device buffers in the SvmModel struct.

Parameters

[in]	handle	cuML handle
[in,out]	m	SVM model parameters

◆ svrFit()

template<typename math_t >

void ML::SVM::svrFit	(	const raft::handle_t &	handle,
		math_t *	X,
		int	n_rows,
		int	n_cols,
		math_t *	y,
		const SvmParameter &	param,
		ML::matrix::KernelParams &	kernel_params,
		SvmModel< math_t > &	model,
		const math_t *	sample_weight = `nullptr`
	)

Fit a support vector regressor to the training data.

Each row of the input data stores a feature vector.

The output buffers in model shall be unallocated on entry.

Template Parameters

math_t floating point type

Parameters

[in]	handle	the cuML handle
[in]	X	device pointer for the input data in column major format. Size n_rows x n_cols.
[in]	n_rows	number of rows
[in]	n_cols	number of columns
[in]	y	device pointer for target values. Size [n_rows].
[in]	param	parameters for training
[in]	kernel_params	parameters for the kernel function
[out]	model	parameters of the trained model
[in]	sample_weight	optional sample weights, size [n_rows]

◆ svrFitSparse()

template<typename math_t >

void ML::SVM::svrFitSparse	(	const raft::handle_t &	handle,
		int *	indptr,
		int *	indices,
		math_t *	data,
		int	n_rows,
		int	n_cols,
		int	nnz,
		math_t *	y,
		const SvmParameter &	param,
		ML::matrix::KernelParams &	kernel_params,
		SvmModel< math_t > &	model,
		const math_t *	sample_weight = `nullptr`
	)

Fit a support vector regressor to the training data.

Each row of the input data stores a feature vector.

The output buffers in model shall be unallocated on entry.

Template Parameters

math_t floating point type

Parameters

[in]	handle	the cuML handle
[in]	indptr	device pointer for CSR row positions. Size [n_rows + 1].
[in]	indices	device pointer for CSR column indices. Size [nnz].
[in]	data	device pointer for the CSR data. Size [nnz].
[in]	n_rows	number of rows
[in]	n_cols	number of columns
[in]	nnz	number of stored entries.
[in]	y	device pointer for target values. Size [n_rows].
[in]	param	parameters for training
[in]	kernel_params	parameters for the kernel function
[out]	model	parameters of the trained model
[in]	sample_weight	optional sample weights, size [n_rows]

Classes

Enumerations

Functions

Enumeration Type Documentation

◆ SvmType

Function Documentation

◆ svcFit()

◆ svcFitSparse()

◆ svcPredict()

◆ svcPredictSparse()

◆ svmFreeBuffers()

◆ svrFit()

◆ svrFitSparse()