whittaker.h File Reference

Smoothing using Whittaker smoother. More...

#include <stdexcept>
#include <vector>
#include "../misc/diff.h"

Go to the source code of this file.

Functions
const std::vector< double >	sablib::Whittaker (const std::vector< double > &y, const std::vector< double > &w, const double lambda, const unsigned int s=2)
	Performs Whittaker smoothing (std::vector<double> version, with weights).
const std::vector< double >	sablib::Whittaker (const std::vector< double > &y, const double lambda, const unsigned int s=2)
	Performs Whittaker smoothing (std::vector<double> version, without weights).
template<typename Derived>
const Derived::PlainObject	sablib::Whittaker (const Eigen::MatrixBase< Derived > &y, const Eigen::MatrixBase< Derived > &w, const Eigen::SparseMatrix< typename Derived::PlainObject::Scalar > &lambdaDTD)
	Performs Whittaker smoothing.

Detailed Description

Smoothing using Whittaker smoother.

Author

Izadori

References:

• Whittaker, E. T. On A New Method of Graduation. Proc. Edinburgh Math. Soc., 1922, 41, 63-75.
• Eilers, P. A Perfect Smoother. Analytical Chemistry, 2003, 75(14), 3631-3636.

Definition in file whittaker.h.

Function Documentation

Whittaker() [1/3]

template<typename Derived>

const Derived::PlainObject sablib::Whittaker	(	const Eigen::MatrixBase< Derived > &	y,
		const Eigen::MatrixBase< Derived > &	w,
		const Eigen::SparseMatrix< typename Derived::PlainObject::Scalar > &	lambdaDTD )

Performs Whittaker smoothing.

Parameters

y	The input data to be smoothed.
w	Weights for each data point.
lambdaDTD	The matrix used for smoothness (lambda * D' * D).

Returns

The smoothed data.

Definition at line 58 of file whittaker.h.

Whittaker() [2/3]

const std::vector< double > sablib::Whittaker	(	const std::vector< double > &	y,
		const double	lambda,
		const unsigned int	s = 2 )

Performs Whittaker smoothing (std::vector<double> version, without weights).

Parameters

y	The input data to be smoothed.
lambda	Smoothing parameter (larger values lead to more smoothing, but may flatten peaks).
s	The order of the difference (usually s = 1, 2, or 3).

Returns

The smoothed data.

Definition at line 58 of file whittaker.cpp.

Whittaker() [3/3]

const std::vector< double > sablib::Whittaker	(	const std::vector< double > &	y,
		const std::vector< double > &	w,
		const double	lambda,
		const unsigned int	s = 2 )

Performs Whittaker smoothing (std::vector<double> version, with weights).

Parameters

y	The input data to be smoothed.
w	Weights for each data point.
lambda	Smoothing parameter (larger values lead to more smoothing, but may flatten peaks).
s	The order of the difference (usually s = 1, 2, or 3).

Returns

The smoothed data.

Exceptions

std::invalid_argument

One or more parameters wrong.

Definition at line 14 of file whittaker.cpp.