WeightedLowess Namespace Reference

Namespace for LOWESS functions. More...

Classes
struct	Options
	Options for compute(). More...
struct	PrecomputedWindows
	Precomputed windows for LOWESS smoothing. More...
struct	Results
	Store the smoothing results. More...
class	SortBy
	Utility class for sorting on a covariate. More...

Functions
template<typename Data_ >
void	compute (size_t num_points, const Data_ *x, const PrecomputedWindows< Data_ > &windows, const Data_ *y, Data_ *fitted, Data_ *robust_weights, const Options< Data_ > &opt)
template<typename Data_ >
void	compute (size_t num_points, const Data_ *x, const Data_ *y, Data_ *fitted, Data_ *robust_weights, const Options< Data_ > &opt)
template<typename Data_ >
Results< Data_ >	compute (size_t num_points, const Data_ *x, const Data_ *y, const Options< Data_ > &opt)
template<typename Task_ , class Run_ >
void	parallelize (int num_workers, Task_ num_tasks, Run_ run_task_range)
template<typename Data_ >
PrecomputedWindows< Data_ >	define_windows (size_t num_points, const Data_ *x, const Options< Data_ > &opt)

Detailed Description

Namespace for LOWESS functions.

Function Documentation

compute() [1/3]

template<typename Data_ >

Results< Data_ > WeightedLowess::compute	(	size_t	num_points,
		const Data_ *	x,
		const Data_ *	y,
		const Options< Data_ > &	opt
	)

Run the LOWESS smoother and return a Results object. This avoids the need to instantiate the various output arrays manually.

Template Parameters

Data_

Floating-point type for the data.

Parameters

	num_points	Number of points.
[in]	x	Pointer to an array of num_points x-values, sorted in increasing order. (Consider using SortBy to permute x in-place. Note that the same permutation should be applied to y and, if present, weights in Options::weights.)
[in]	y	Pointer to an array of num_points y-values.
	opt	Further options.

Returns

A Results object containing the fitted values and robustness weights.

compute() [2/3]

template<typename Data_ >

void WeightedLowess::compute	(	size_t	num_points,
		const Data_ *	x,
		const Data_ *	y,
		Data_ *	fitted,
		Data_ *	robust_weights,
		const Options< Data_ > &	opt
	)

LOWESS is a simple, efficient, general-purpose non-parametric smoothing algorithm. It perform weighted linear regressions on subsets of neighboring points, yielding a smooth curve fit to the data.

Template Parameters

Data_

Floating-point type for the data.

Parameters

	num_points	Number of points.
[in]	x	Pointer to an array of num_points x-values, sorted in increasing order. (Consider using SortBy to permute x in-place. Note that the same permutation should be applied to y and, if present, weights in Options::weights.)
[in]	y	Pointer to an array of num_points y-values.
[out]	fitted	Pointer to an output array of length num_points, in which the fitted values of the smoother can be stored.
[out]	robust_weights	Pointer to an output array of length num_points, in which the robustness weights can be stored. This may be NULL if the robustness weights are not needed.
	opt	Further options.

compute() [3/3]

template<typename Data_ >

void WeightedLowess::compute	(	size_t	num_points,
		const Data_ *	x,
		const PrecomputedWindows< Data_ > &	windows,
		const Data_ *	y,
		Data_ *	fitted,
		Data_ *	robust_weights,
		const Options< Data_ > &	opt
	)

Run the LOWESS smoother with precomputed windows. This avoids redundant window calculations when re-using the same x-coordinates across multiple y-coordinate vectors.

Template Parameters

Data_

Floating-point type for the data.

Parameters

	num_points	Number of points.
[in]	x	Pointer to an array of num_points x-values, sorted in increasing order. (Consider using SortBy to permute x in-place. Note that the same permutation should be applied to y, if present, and weights in Options::weights.)
	windows	Precomputed windows, created by calling define_windows() with num_points, x and opt.
[in]	y	Pointer to an array of num_points y-values.
[out]	fitted	Pointer to an output array of length num_points, in which the fitted values of the smoother can be stored.
[out]	robust_weights	Pointer to an output array of length num_points, in which the robustness weights can be stored. This may be NULL if the robustness weights are not needed.
	opt	Further options. This should be the same object that is used in define_windows(). Note that only a subset of options are actually used in this overload, namely Options::weights and Options::iterations.

define_windows()

template<typename Data_ >

PrecomputedWindows< Data_ > WeightedLowess::define_windows	(	size_t	num_points,
		const Data_ *	x,
		const Options< Data_ > &	opt
	)

Precompute the window locations prior to fitting of different y via the corresponding compute() overload. This avoids wasting time in unnecessarily recomputing the same windows for each compute() call.

Template Parameters

Data_

Floating-point type for the data.

Parameters

	num_points	Number of points.
[in]	x	Pointer to an array of num_points x-values, sorted in increasing order. (Consider using SortBy to permute the array in-place before calling this function.)
	opt	Further options. Only a subset of options are actually used here, namely Options::delta, Options::anchors, Options::weights, Options::frequency_weights, Options::span, Options::span_as_proportion, and Options::minimum_width.

parallelize()

template<typename Task_ , class Run_ >

void WeightedLowess::parallelize	(	int	num_workers,
		Task_	num_tasks,
		Run_	run_task_range
	)

Template Parameters

Task_	Integer type for the number of tasks.
Run_	Function to execute a range of tasks.

Parameters

num_workers	Number of workers.
num_tasks	Number of tasks.
run_task_range	Function to iterate over a range of tasks within a worker.

By default, this is an alias to subpar::parallelize_range(). However, if the WEIGHTEDLOWESS_CUSTOM_PARALLEL function-like macro is defined, it is called instead. Any user-defined macro should accept the same arguments as subpar::parallelize_range().