npstat::LogisticRegressionOnKDTree< Point, Numeric, BooleanFunctor > Class Template Reference

#include <LocalLogisticRegression.hh>

Inheritance diagram for npstat::LogisticRegressionOnKDTree< Point, Numeric, BooleanFunctor >:

Public Member Functions
	LogisticRegressionOnKDTree (const KDTree< Point, Numeric > &dataTree, const BooleanFunctor &pointPassesOrFails, const QuadraticOrthoPolyND &poly, bool calculateLikelihoodGradient)
const KDTree< Point, Numeric > &	getDataTree () const
virtual void	clear ()
virtual double	result ()
virtual void	process (const Point &value)
Public Member Functions inherited from npstat::LogisticRegressionBase< Numeric >
	LogisticRegressionBase (const QuadraticOrthoPolyND &poly, bool calculateLikelihoodGradient)
unsigned	dim () const
const QuadraticOrthoPolyND &	getPoly () const
bool	calculatingGradient () const
const std::vector< double > &	lastCoeffs () const
void	getGradient (double *buffer, unsigned bufLen) const
double	getPassCount () const
double	getFailCount () const
void	setRegressionBox (const BoxND< Numeric > &box)
void	setLinearMapping (const double *location, const double *scale, unsigned locationAndScaleArraySize)
double	calculateLogLikelihood (const double *coeffs, unsigned nCoeffs)

Additional Inherited Members
Protected Member Functions inherited from npstat::LogisticRegressionBase< Numeric >
void	resetAccumulators ()
Protected Attributes inherited from npstat::LogisticRegressionBase< Numeric >
const QuadraticOrthoPolyND &	poly_
BoxND< Numeric >	regressionBox_
std::vector< double >	location_
std::vector< double >	scale_
std::vector< double >	coords_
std::vector< double >	coeffs_
std::vector< double >	gradBuffer_
std::vector< long double >	gradient_
long double	logli_
long double	passCount_
long double	failCount_
const double	minlog_
const double	maxlog_
const unsigned	mydim_
const bool	calcGradient_

Detailed Description

template<class Point, class Numeric, class BooleanFunctor>
class npstat::LogisticRegressionOnKDTree< Point, Numeric, BooleanFunctor >

Logistic regression on data samples arranged into k-d trees

Constructor & Destructor Documentation

LogisticRegressionOnKDTree()

template<class Point , class Numeric , class BooleanFunctor >

npstat::LogisticRegressionOnKDTree< Point, Numeric, BooleanFunctor >::LogisticRegressionOnKDTree	(	const KDTree< Point, Numeric > &	dataTree,
		const BooleanFunctor &	pointPassesOrFails,
		const QuadraticOrthoPolyND &	poly,
		bool	calculateLikelihoodGradient
	)

Constructor arguments are as follows:

dataTree – the tree of data points.

pointPassesOrFails – a functor that tells us whether the point "passes" (observed value of 1) or "fails" (observed value of 0).

poly – the set of orthogonal polynomials used to construct the local regression surface.

calculateLikelihoodGradient – flag which tells whether the code should calculate the gradient of log-likelihood with respect to coefficients of the local polynomial.

This object will not own "dataTree" or "poly" objects. These objects must still exist when the LogisticRegressionOnKDTree object is in use. The point selection functor will be copied.

Member Function Documentation

clear()

template<class Point , class Numeric , class BooleanFunctor >

virtual void npstat::LogisticRegressionOnKDTree< Point, Numeric, BooleanFunctor >::clear ( )

inlinevirtual

Method from AbsVisitor we have to implement

Implements npstat::AbsVisitor< Point, double >.

getDataTree()

template<class Point , class Numeric , class BooleanFunctor >

const KDTree<Point,Numeric>& npstat::LogisticRegressionOnKDTree< Point, Numeric, BooleanFunctor >::getDataTree ( ) const

inline

Inspect the data

process()

template<class Point , class Numeric , class BooleanFunctor >

virtual void npstat::LogisticRegressionOnKDTree< Point, Numeric, BooleanFunctor >::process ( const Point &  value )

virtual

Process one array point

Implements npstat::AbsVisitor< Point, double >.

result()

template<class Point , class Numeric , class BooleanFunctor >

virtual double npstat::LogisticRegressionOnKDTree< Point, Numeric, BooleanFunctor >::result ( )

inlinevirtual

Return the result at the end of array processing

Implements npstat::AbsVisitor< Point, double >.

---

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

• stat/LocalLogisticRegression.hh