ML::Datasets Namespace Reference

Functions
void	make_blobs (const raft::handle_t &handle, float *out, int64_t *labels, int64_t n_rows, int64_t n_cols, int64_t n_clusters, bool row_major=true, const float *centers=nullptr, const float *cluster_std=nullptr, const float cluster_std_scalar=1.f, bool shuffle=true, float center_box_min=-10.f, float center_box_max=10.f, uint64_t seed=0ULL)
void	make_blobs (const raft::handle_t &handle, double *out, int64_t *labels, int64_t n_rows, int64_t n_cols, int64_t n_clusters, bool row_major=true, const double *centers=nullptr, const double *cluster_std=nullptr, const double cluster_std_scalar=1.0, bool shuffle=true, double center_box_min=-10.0, double center_box_max=10.0, uint64_t seed=0ULL)
void	make_blobs (const raft::handle_t &handle, float *out, int *labels, int n_rows, int n_cols, int n_clusters, bool row_major=true, const float *centers=nullptr, const float *cluster_std=nullptr, const float cluster_std_scalar=1.f, bool shuffle=true, float center_box_min=-10.f, float center_box_max=10.0, uint64_t seed=0ULL)
void	make_blobs (const raft::handle_t &handle, double *out, int *labels, int n_rows, int n_cols, int n_clusters, bool row_major=true, const double *centers=nullptr, const double *cluster_std=nullptr, const double cluster_std_scalar=1.0, bool shuffle=true, double center_box_min=-10.0, double center_box_max=10.0, uint64_t seed=0ULL)
void	make_regression (const raft::handle_t &handle, float *out, float *values, int64_t n_rows, int64_t n_cols, int64_t n_informative, float *coef=nullptr, int64_t n_targets=1LL, float bias=0.0f, int64_t effective_rank=-1LL, float tail_strength=0.5f, float noise=0.0f, bool shuffle=true, uint64_t seed=0ULL)
	GPU-equivalent of sklearn.datasets.make_regression as documented at: https://scikit-learn.org/stable/modules/generated/sklearn.datasets.make_regression.html. More...
void	make_regression (const raft::handle_t &handle, double *out, double *values, int64_t n_rows, int64_t n_cols, int64_t n_informative, double *coef=nullptr, int64_t n_targets=1LL, double bias=0.0, int64_t effective_rank=-1LL, double tail_strength=0.5, double noise=0.0, bool shuffle=true, uint64_t seed=0ULL)
void	make_regression (const raft::handle_t &handle, float *out, float *values, int n_rows, int n_cols, int n_informative, float *coef=nullptr, int n_targets=1LL, float bias=0.0f, int effective_rank=-1LL, float tail_strength=0.5f, float noise=0.0f, bool shuffle=true, uint64_t seed=0ULL)
void	make_regression (const raft::handle_t &handle, double *out, double *values, int n_rows, int n_cols, int n_informative, double *coef=nullptr, int n_targets=1LL, double bias=0.0, int effective_rank=-1LL, double tail_strength=0.5, double noise=0.0, bool shuffle=true, uint64_t seed=0ULL)
void	make_arima (const raft::handle_t &handle, float *out, int batch_size, int n_obs, ARIMAOrder order, float scale=1.0f, float noise_scale=0.2f, float intercept_scale=1.0f, uint64_t seed=0ULL)
void	make_arima (const raft::handle_t &handle, double *out, int batch_size, int n_obs, ARIMAOrder order, double scale=1.0, double noise_scale=0.2, double intercept_scale=1.0, uint64_t seed=0ULL)

Function Documentation

make_arima() [1/2]

void ML::Datasets::make_arima	(	const raft::handle_t &	handle,
		double *	out,
		int	batch_size,
		int	n_obs,
		ARIMAOrder	order,
		double	scale = 1.0,
		double	noise_scale = 0.2,
		double	intercept_scale = 1.0,
		uint64_t	seed = 0ULL
	)

make_arima() [2/2]

void ML::Datasets::make_arima	(	const raft::handle_t &	handle,
		float *	out,
		int	batch_size,
		int	n_obs,
		ARIMAOrder	order,
		float	scale = 1.0f,
		float	noise_scale = 0.2f,
		float	intercept_scale = 1.0f,
		uint64_t	seed = 0ULL
	)

Generates a dataset of time series by simulating an ARIMA process of a given order.

Parameters

[in]	handle	cuML handle
[out]	out	Generated time series
[in]	batch_size	Batch size
[in]	n_obs	Number of observations per series
[in]	order	ARIMA order
[in]	scale	Scale used to draw the starting values
[in]	noise_scale	Scale used to draw the residuals
[in]	intercept_scale	Scale used to draw the intercept
[in]	seed	Seed for the random number generator

make_regression() [1/4]

void ML::Datasets::make_regression	(	const raft::handle_t &	handle,
		double *	out,
		double *	values,
		int	n_rows,
		int	n_cols,
		int	n_informative,
		double *	coef = nullptr,
		int	n_targets = 1LL,
		double	bias = 0.0,
		int	effective_rank = -1LL,
		double	tail_strength = 0.5,
		double	noise = 0.0,
		bool	shuffle = true,
		uint64_t	seed = 0ULL
	)

make_regression() [2/4]

void ML::Datasets::make_regression	(	const raft::handle_t &	handle,
		double *	out,
		double *	values,
		int64_t	n_rows,
		int64_t	n_cols,
		int64_t	n_informative,
		double *	coef = nullptr,
		int64_t	n_targets = 1LL,
		double	bias = 0.0,
		int64_t	effective_rank = -1LL,
		double	tail_strength = 0.5,
		double	noise = 0.0,
		bool	shuffle = true,
		uint64_t	seed = 0ULL
	)

make_regression() [3/4]

void ML::Datasets::make_regression	(	const raft::handle_t &	handle,
		float *	out,
		float *	values,
		int	n_rows,
		int	n_cols,
		int	n_informative,
		float *	coef = nullptr,
		int	n_targets = 1LL,
		float	bias = 0.0f,
		int	effective_rank = -1LL,
		float	tail_strength = 0.5f,
		float	noise = 0.0f,
		bool	shuffle = true,
		uint64_t	seed = 0ULL
	)

make_regression() [4/4]

void ML::Datasets::make_regression	(	const raft::handle_t &	handle,
		float *	out,
		float *	values,
		int64_t	n_rows,
		int64_t	n_cols,
		int64_t	n_informative,
		float *	coef = nullptr,
		int64_t	n_targets = 1LL,
		float	bias = 0.0f,
		int64_t	effective_rank = -1LL,
		float	tail_strength = 0.5f,
		float	noise = 0.0f,
		bool	shuffle = true,
		uint64_t	seed = 0ULL
	)

GPU-equivalent of sklearn.datasets.make_regression as documented at: https://scikit-learn.org/stable/modules/generated/sklearn.datasets.make_regression.html.

Parameters

[in]	handle	cuML handle
[out]	out	Row-major (samples, features) matrix to store the problem data
[out]	values	Row-major (samples, targets) matrix to store the values for the regression problem
[in]	n_rows	Number of samples
[in]	n_cols	Number of features
[in]	n_informative	Number of informative features (non-zero coefficients)
[out]	coef	Row-major (features, targets) matrix to store the coefficients used to generate the values for the regression problem. If nullptr is given, nothing will be written
[in]	n_targets	Number of targets (generated values per sample)
[in]	bias	A scalar that will be added to the values
[in]	effective_rank	The approximate rank of the data matrix (used to create correlations in the data). -1 is the code to use well-conditioned data
[in]	tail_strength	The relative importance of the fat noisy tail of the singular values profile if effective_rank is not -1
[in]	noise	Standard deviation of the gaussian noise applied to the output
[in]	shuffle	Shuffle the samples and the features
[in]	seed	Seed for the random number generator