Generates subsets of data that contain only the most relevant features for predicting the labels. The train method of this class produces a ranked ordering of the feature attributes by training a single-layer neural network, and deselecting the weakest attribute until all attributes have been deselected. The transform method uses only the highest-ranked attributes. More...

#include <GTransform.h>

Inheritance diagram for GClasses::GAttributeSelector:

Public Member Functions
	GAttributeSelector (size_t labelDims, size_t targetFeatures)

	GAttributeSelector (GDomNode *pNode, GLearnerLoader &ll)

virtual	~GAttributeSelector ()

std::vector< size_t > &	ranks ()
	Returns a list of attributes in ranked-order. Most important attributes are first. Weakest attributes are last. (The results are undefined until after train is called.) More...

virtual GDomNode *	serialize (GDom *pDoc) const
	Marshal this object into a DOM, which can then be converted to a variety of serial formats. More...

void	setSeed (size_t seed)
	Sets a random seed to use with this attribute selector. More...

GRelation *	setTargetFeatures (size_t n)
	Specifies the number of features to select. (This method must be called after train.) More...

virtual void	transform (const double pIn, double pOut)
	See the comment for GIncrementalTransform::transform. More...

virtual void	untransform (const double pIn, double pOut)
	Throws an exception (because this transform cannot be reversed). More...

virtual void	untransformToDistribution (const double pIn, GPrediction pOut)
	Throws an exception (because this transform cannot be reversed). More...

Public Member Functions inherited from GClasses::GIncrementalTransform
	GIncrementalTransform ()

	GIncrementalTransform (GDomNode *pNode, GLearnerLoader &ll)

virtual	~GIncrementalTransform ()

const GRelation &	after () const
	Returns a relation object describing the data after it is transformed. More...

const GRelation &	before () const
	Returns a relation object describing the data before it is transformed. More...

double *	innerBuf ()
	Returns a buffer of sufficient size to store an inner (transformed) vector. The caller should not to delete the buffer. The same buffer will be returned each time. More...

virtual GMatrix *	reduce (const GMatrix &in)
	This calls train, then calls transformBatch, and returns the result. More...

void	setAfter (GRelation *pRel)
	Sets the after relation. Takes ownership of pRel. More...

void	setBefore (GRelation *pRel)
	Sets the before relation. Takes ownership of pRel. More...

void	train (const GMatrix &data)
	Trains the transform on the data in pData. (This method may be a no-op for transformations that always behave in the same manner.) More...

void	train (const GRelation &pRelation)
	"Trains" the transform without any data. More...

virtual GMatrix *	transformBatch (const GMatrix &in)
	This assumes that train has already been called, and transforms all the rows in in returning the resulting matrix. The caller is responsible for deleting the new matrix. More...

virtual GMatrix *	untransformBatch (const GMatrix &in)
	This assumes train was previously called, and untransforms all the rows in pIn and returns the results. More...

Public Member Functions inherited from GClasses::GTransform
	GTransform ()

	GTransform (GDomNode *pNode, GLearnerLoader &ll)

virtual	~GTransform ()

Static Public Member Functions
static void	test ()

Static Public Member Functions inherited from GClasses::GIncrementalTransform
static void	test ()
	Performs unit tests for this class. Throws an exception if there is a failure. More...

Protected Member Functions
virtual GRelation *	trainInner (const GMatrix &data)
	See the comment for GIncrementalTransform::train. More...

virtual GRelation *	trainInner (const GRelation &relation)
	Throws an exception (because this transform cannot be trained without data) More...

Protected Member Functions inherited from GClasses::GIncrementalTransform
virtual GDomNode *	baseDomNode (GDom pDoc, const char szClassName) const
	Child classes should use this in their implementation of serialize. More...

Protected Attributes
size_t	m_labelDims

std::vector< size_t >	m_ranks

size_t	m_seed

size_t	m_targetFeatures

Detailed Description

Generates subsets of data that contain only the most relevant features for predicting the labels. The train method of this class produces a ranked ordering of the feature attributes by training a single-layer neural network, and deselecting the weakest attribute until all attributes have been deselected. The transform method uses only the highest-ranked attributes.

Constructor & Destructor Documentation

GClasses::GAttributeSelector::GAttributeSelector	(	size_t	labelDims,
		size_t	targetFeatures
	)

inline

GClasses::GAttributeSelector::GAttributeSelector	(	GDomNode *	pNode,
		GLearnerLoader &	ll
	)

virtual GClasses::GAttributeSelector::~GAttributeSelector ( )

inlinevirtual

Member Function Documentation

std::vector<size_t>& GClasses::GAttributeSelector::ranks ( )

inline

Returns a list of attributes in ranked-order. Most important attributes are first. Weakest attributes are last. (The results are undefined until after train is called.)

virtual GDomNode* GClasses::GAttributeSelector::serialize ( GDom * pDoc ) const

virtual

Marshal this object into a DOM, which can then be converted to a variety of serial formats.

Implements GClasses::GIncrementalTransform.

void GClasses::GAttributeSelector::setSeed ( size_t seed )

inline

Sets a random seed to use with this attribute selector.

GRelation* GClasses::GAttributeSelector::setTargetFeatures ( size_t n )

Specifies the number of features to select. (This method must be called after train.)

static void GClasses::GAttributeSelector::test ( )

static

virtual GRelation* GClasses::GAttributeSelector::trainInner ( const GMatrix & data )

protectedvirtual

See the comment for GIncrementalTransform::train.

Implements GClasses::GIncrementalTransform.

virtual GRelation* GClasses::GAttributeSelector::trainInner ( const GRelation & relation )

protectedvirtual

Throws an exception (because this transform cannot be trained without data)

Implements GClasses::GIncrementalTransform.

virtual void GClasses::GAttributeSelector::transform	(	const double *	pIn,
		double *	pOut
	)

virtual

See the comment for GIncrementalTransform::transform.

Implements GClasses::GIncrementalTransform.

virtual void GClasses::GAttributeSelector::untransform	(	const double *	pIn,
		double *	pOut
	)

inlinevirtual

Throws an exception (because this transform cannot be reversed).

Implements GClasses::GIncrementalTransform.

virtual void GClasses::GAttributeSelector::untransformToDistribution	(	const double *	pIn,
		GPrediction *	pOut
	)

inlinevirtual

Throws an exception (because this transform cannot be reversed).

Implements GClasses::GIncrementalTransform.

Member Data Documentation

size_t GClasses::GAttributeSelector::m_labelDims

protected

std::vector<size_t> GClasses::GAttributeSelector::m_ranks

protected

size_t GClasses::GAttributeSelector::m_seed

protected

size_t GClasses::GAttributeSelector::m_targetFeatures

protected

Public Member Functions

Static Public Member Functions

Protected Member Functions

Protected Attributes

Detailed Description

Constructor & Destructor Documentation

Member Function Documentation

Member Data Documentation