lti::crispDecisionTree::multivariateCrispDecisionFunction Class Reference

This class implements a multivariate decision. More...

#include <ltiCrispDecisionTree.h>

Inheritance diagram for lti::crispDecisionTree::multivariateCrispDecisionFunction:

[legend]

Collaboration diagram for lti::crispDecisionTree::multivariateCrispDecisionFunction:

[legend]

List of all members.

Public Member Functions
	multivariateCrispDecisionFunction ()
	multivariateCrispDecisionFunction (const dvector &w, const double &thresh)
	multivariateCrispDecisionFunction (const multivariateCrispDecisionFunction &other)
	~multivariateCrispDecisionFunction ()
const char *	getTypeName () const
multivariateCrispDecisionFunction &	copy (const multivariateCrispDecisionFunction &other)
multivariateCrispDecisionFunction &	operator= (const multivariateCrispDecisionFunction &other)
virtual crispDecisionFunction *	clone () const
virtual bool	apply (const dvector &data) const
void	setCondition (const dvector &w, const double &thresh)
virtual bool	write (ioHandler &handler, const bool complete=true) const
virtual bool	read (ioHandler &handler, const bool complete=true)
Protected Attributes
dvector	weights
double	threshold

---

Detailed Description

This class implements a multivariate decision.

The apply method is true, if the following condition is met.

with the data, a weighting vector and the threshold.

Thus, each node performs an arbitrary linear seperation of the remaining feature space.

---

Constructor & Destructor Documentation

lti::crispDecisionTree::multivariateCrispDecisionFunction::multivariateCrispDecisionFunction

(

)

default constructor

lti::crispDecisionTree::multivariateCrispDecisionFunction::multivariateCrispDecisionFunction	(	const dvector &	w,
		const double &	thresh
	)

New decision function with the given parameters.

Parameters:

	w	the weighting vector for the data.
	thresh	the threshold for the weighted sum

lti::crispDecisionTree::multivariateCrispDecisionFunction::multivariateCrispDecisionFunction

(

const multivariateCrispDecisionFunction &

other

)

copy constructor

Parameters:

other

the multivariateCrispDecisionFunction object to be copied

lti::crispDecisionTree::multivariateCrispDecisionFunction::~multivariateCrispDecisionFunction

(

)

destructor

---

Member Function Documentation

virtual bool lti::crispDecisionTree::multivariateCrispDecisionFunction::apply

(

const dvector &

data

)

const [virtual]

Evaluate the condition implemented in the cdf.

Parameters:

data

value to be evaluated

Returns:

true if it meets the condition (left), false if not

Implements lti::crispDecisionTree::crispDecisionFunction.

virtual crispDecisionFunction* lti::crispDecisionTree::multivariateCrispDecisionFunction::clone

(

)

const [virtual]

returns a pointer to a clone of the multivariateCrispDecisionFunction

Implements lti::crispDecisionTree::crispDecisionFunction.

multivariateCrispDecisionFunction& lti::crispDecisionTree::multivariateCrispDecisionFunction::copy

(

const multivariateCrispDecisionFunction &

other

)

copy the contents of a multivariateCrispDecisionFunction object

Parameters:

other

the multivariateCrispDecisionFunction object to be copied

Returns:

a reference to this multivariateCrispDecisionFunction object

Reimplemented from lti::crispDecisionTree::crispDecisionFunction.

const char* lti::crispDecisionTree::multivariateCrispDecisionFunction::getTypeName

(

)

const [virtual]

returns name of this type

Reimplemented from lti::crispDecisionTree::crispDecisionFunction.

multivariateCrispDecisionFunction& lti::crispDecisionTree::multivariateCrispDecisionFunction::operator=

(

const multivariateCrispDecisionFunction &

other

)

copy the contents of a multivariateCrispDecisionFunction object

Parameters:

other

the multivariateCrispDecisionFunction object to be copied

Returns:

a reference to this multivariateCrispDecisionFunction object

Reimplemented from lti::crispDecisionTree::crispDecisionFunction.

virtual bool lti::crispDecisionTree::multivariateCrispDecisionFunction::read	(	ioHandler &	handler,
		const bool	complete = true
	)			[virtual]

read the multivariateCrispDecisionFunction from the given ioHandler

Parameters:

	handler	the ioHandler to be used
	complete	if true (the default) the enclosing begin/end will be also written, otherwise only the data block will be written.

Returns:

true if write was successful

Reimplemented from lti::crispDecisionTree::crispDecisionFunction.

void lti::crispDecisionTree::multivariateCrispDecisionFunction::setCondition	(	const dvector &	w,
		const double &	thresh
	)

Sets the condition to be tested.

Parameters:

	w	the weighting vector for the data.
	thresh	the threshold for the weightes sum

virtual bool lti::crispDecisionTree::multivariateCrispDecisionFunction::write	(	ioHandler &	handler,
		const bool	complete = true
	)			const [virtual]

write the multivariateCrispDecisionFunction in the given ioHandler

Parameters:

	handler	the ioHandler to be used
	complete	if true (the default) the enclosing begin/end will be also written, otherwise only the data block will be written.

Returns:

true if write was successful

Reimplemented from lti::crispDecisionTree::crispDecisionFunction.

---

Member Data Documentation

double lti::crispDecisionTree::multivariateCrispDecisionFunction::threshold [protected]

Threshold against which the data is tested in the given dimension.

dvector lti::crispDecisionTree::multivariateCrispDecisionFunction::weights [protected]

the weighting vector

---

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

• ltiCrispDecisionTree.h