Base class for clustering. More...

#include <shark/Models/Clustering/AbstractClustering.h>

Inheritance diagram for shark::AbstractClustering< InputT >:

Public Types
enum	Feature { HAS_SOFT_MEMBERSHIP = 1 }

typedef InputT	InputType

typedef unsigned int	OutputType

typedef Batch< InputType >::type	BatchInputType

typedef Batch< OutputType >::type	BatchOutputType

typedef TypedFlags< Feature >	Features

typedef TypedFeatureNotAvailableException< Feature >	FeatureNotAvailableException

Public Types inherited from shark::IParameterizable< VectorType >
typedef VectorType	ParameterVectorType

Public Member Functions
const Features &	features () const

virtual void	updateFeatures ()

bool	hasSoftMembershipFunction () const

virtual std::size_t	numberOfClusters () const =0
	return the number of clusters

virtual Shape	inputShape () const =0

virtual unsigned int	hardMembership (InputType const &pattern) const
	Compute best matching cluster.

virtual BatchOutputType	hardMembership (BatchInputType const &patterns) const
	Compute best matching cluster for a batch of inputs.

virtual RealVector	softMembership (InputType const &pattern) const
	Compute cluster membership function.

virtual RealMatrix	softMembership (BatchInputType const &patterns) const
	Compute cluster membership function.

void	read (InArchive &archive)
	empty default implementation of ISerializable::read

void	write (OutArchive &archive) const
	empty default implementation of ISerializable::write

Public Member Functions inherited from shark::INameable
virtual	~INameable ()

virtual std::string	name () const
	returns the name of the object

Public Member Functions inherited from shark::IParameterizable< VectorType >
virtual	~IParameterizable ()

virtual ParameterVectorType	parameterVector () const
	Return the parameter vector.

virtual void	setParameterVector (ParameterVectorType const &newParameters)
	Set the parameter vector.

virtual std::size_t	numberOfParameters () const
	Return the number of parameters.

Public Member Functions inherited from shark::ISerializable
virtual	~ISerializable ()
	Virtual d'tor.

void	load (InArchive &archive, unsigned int version)
	Versioned loading of components, calls read(...).

void	save (OutArchive &archive, unsigned int version) const
	Versioned storing of components, calls write(...).

	BOOST_SERIALIZATION_SPLIT_MEMBER ()

Protected Attributes
Features	m_features

Detailed Description

template<class InputT>
class shark::AbstractClustering< InputT >

Base class for clustering.

: Clustering algorithms vary widely in the data structures on which they operate. For example, simple centroid-based approaches such as k-means are mutually incompatible with tree-based hierarchical clustering. This interface class is the attempt to cast different cluster descriptions into a minimal common interface that is useful for prediction.

: There are at least two common types of predictions made with clusterings. The first one is the assignment of the best matching cluster to a patters, such as in vector quantization or unsupervised clustering. This is often referred to as "hard clustering". The second one is the computation of a membership function ("soft clustering"). The membership of a pattern to a cluster is non-negative, and the total membership should add to one.

: This interface makes minimal assumptions to allow for these types of predictions. It assumes that clusters can be enumbered (identified by an index), and that at least a membership test can be made (hard clustering). It is optional to provide a membership function. Only one of the two interfaces for best matching cluster or membership function need to be implemented, since the best matching cluster can be deduced from the membership function. However, often the best matching cluster can be computed more efficiently than the membership function. In these cases both interface functions should be implemented.

: The purpose of this interface is to act as a common super class to different data structures describing the outcome of a clustering operation. The interface allows all of these data structures to be used in the two clustering model classes: HardClusteringModel and SoftClusteringModel.

Definition at line 97 of file AbstractClustering.h.

Member Typedef Documentation

◆ BatchInputType

template<class InputT >

typedef Batch<InputType>::type shark::AbstractClustering< InputT >::BatchInputType

Definition at line 102 of file AbstractClustering.h.

◆ BatchOutputType

template<class InputT >

typedef Batch<OutputType>::type shark::AbstractClustering< InputT >::BatchOutputType

Definition at line 103 of file AbstractClustering.h.

◆ FeatureNotAvailableException

template<class InputT >

typedef TypedFeatureNotAvailableException<Feature> shark::AbstractClustering< InputT >::FeatureNotAvailableException

Definition at line 108 of file AbstractClustering.h.

◆ Features

template<class InputT >

typedef TypedFlags<Feature> shark::AbstractClustering< InputT >::Features

Definition at line 108 of file AbstractClustering.h.

◆ InputType

template<class InputT >

typedef InputT shark::AbstractClustering< InputT >::InputType

Definition at line 100 of file AbstractClustering.h.

◆ OutputType

template<class InputT >

typedef unsigned int shark::AbstractClustering< InputT >::OutputType

Definition at line 101 of file AbstractClustering.h.

Member Enumeration Documentation

◆ Feature

template<class InputT >

enum shark::AbstractClustering::Feature

Enumerator
HAS_SOFT_MEMBERSHIP

Definition at line 105 of file AbstractClustering.h.

Member Function Documentation

◆ features()

template<class InputT >

const Features & shark::AbstractClustering< InputT >::features ( ) const

inline

Definition at line 108 of file AbstractClustering.h.

◆ hardMembership() [1/2]

template<class InputT >

virtual BatchOutputType shark::AbstractClustering< InputT >::hardMembership ( BatchInputType const & patterns ) const

inlinevirtual

Compute best matching cluster for a batch of inputs.

: This function should be overriden by sub-classes to compute the cluster best matching the input pattern. The (typically slow) default implementation is to return the arg max of the soft membership function for every pattern.

Reimplemented in shark::HierarchicalClustering< InputT >.

Definition at line 142 of file AbstractClustering.h.

References shark::batchSize(), SHARK_ASSERT, and shark::AbstractClustering< InputT >::softMembership().

◆ hardMembership() [2/2]

template<class InputT >

virtual unsigned int shark::AbstractClustering< InputT >::hardMembership ( InputType const & pattern ) const

inlinevirtual

Compute best matching cluster.

: This function should be overriden by sub-classes to compute the cluster best matching the input pattern. The (typically slow) default implementation is to create a batch of size 1 and return the result of the batch call to hardMembership

Definition at line 129 of file AbstractClustering.h.

References shark::getBatchElement(), and shark::AbstractClustering< InputT >::hardMembership().

Referenced by shark::HardClusteringModel< InputT >::eval(), shark::HardClusteringModel< InputT >::eval(), and shark::AbstractClustering< InputT >::hardMembership().

◆ hasSoftMembershipFunction()

template<class InputT >

bool shark::AbstractClustering< InputT >::hasSoftMembershipFunction ( ) const

inline

Tests whether the clustering can compute a (soft) member ship function, describing the membership of a sample to the different clusters.

Definition at line 113 of file AbstractClustering.h.

References shark::AbstractClustering< InputT >::HAS_SOFT_MEMBERSHIP, and shark::AbstractClustering< InputT >::m_features.

Referenced by shark::SoftClusteringModel< InputT >::SoftClusteringModel().

◆ inputShape()

template<class InputT >

virtual Shape shark::AbstractClustering< InputT >::inputShape ( ) const

pure virtual

Implemented in shark::Centroids, and shark::HierarchicalClustering< InputT >.

Referenced by shark::HardClusteringModel< InputT >::inputShape(), and shark::SoftClusteringModel< InputT >::inputShape().

◆ numberOfClusters()

template<class InputT >

virtual std::size_t shark::AbstractClustering< InputT >::numberOfClusters ( ) const

pure virtual

return the number of clusters

Implemented in shark::Centroids, and shark::HierarchicalClustering< InputT >.

Referenced by shark::HardClusteringModel< InputT >::outputShape(), and shark::SoftClusteringModel< InputT >::outputShape().

◆ read()

template<class InputT >

void shark::AbstractClustering< InputT >::read ( InArchive & archive )

inlinevirtual

empty default implementation of ISerializable::read

Reimplemented from shark::ISerializable.

Reimplemented in shark::Centroids.

Definition at line 178 of file AbstractClustering.h.

◆ softMembership() [1/2]

template<class InputT >

virtual RealMatrix shark::AbstractClustering< InputT >::softMembership ( BatchInputType const & patterns ) const

inlinevirtual

Compute cluster membership function.

: This function should be overriden by sub-classes to compute the membership of a pattern to the clusters. This default implementation throws an exception.

Reimplemented in shark::Centroids.

Definition at line 173 of file AbstractClustering.h.

References shark::AbstractClustering< InputT >::HAS_SOFT_MEMBERSHIP, and SHARK_FEATURE_EXCEPTION.

◆ softMembership() [2/2]

template<class InputT >

virtual RealVector shark::AbstractClustering< InputT >::softMembership ( InputType const & pattern ) const

inlinevirtual

Compute cluster membership function.

: This function should be overriden by sub-classes to compute the membership of a pattern to the clusters. The default implementation creates a batch of size 1 and calls the batched version. If this is not overriden, an xception is thrown.

Reimplemented in shark::Centroids.

Definition at line 162 of file AbstractClustering.h.

References shark::AbstractClustering< InputT >::softMembership().

Referenced by shark::SoftClusteringModel< InputT >::eval(), shark::SoftClusteringModel< InputT >::eval(), shark::AbstractClustering< InputT >::hardMembership(), and shark::AbstractClustering< InputT >::softMembership().

◆ updateFeatures()

template<class InputT >

virtual void shark::AbstractClustering< InputT >::updateFeatures ( )

inlinevirtual

Definition at line 108 of file AbstractClustering.h.

◆ write()

template<class InputT >

void shark::AbstractClustering< InputT >::write ( OutArchive & archive ) const

inlinevirtual

empty default implementation of ISerializable::write

Reimplemented from shark::ISerializable.

Reimplemented in shark::Centroids.

Definition at line 181 of file AbstractClustering.h.

Member Data Documentation

◆ m_features

template<class InputT >

Features shark::AbstractClustering< InputT >::m_features

protected

Definition at line 108 of file AbstractClustering.h.

Referenced by shark::AbstractClustering< InputT >::hasSoftMembershipFunction().

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

include/shark/Models/Clustering/AbstractClustering.h

Public Types

Public Member Functions

Protected Attributes

Detailed Description

Member Typedef Documentation

◆ BatchInputType

◆ BatchOutputType

◆ FeatureNotAvailableException

◆ Features

◆ InputType

◆ OutputType

Member Enumeration Documentation

◆ Feature

Member Function Documentation

◆ features()

◆ hardMembership() [1/2]

◆ hardMembership() [2/2]

◆ hasSoftMembershipFunction()

◆ inputShape()

◆ numberOfClusters()

◆ read()

◆ softMembership() [1/2]

◆ softMembership() [2/2]

◆ updateFeatures()

◆ write()

Member Data Documentation

◆ m_features