RapidLib  v2.0.0
A simple library for interactive machine learning
classification< T > Class Template Reference

#include <classification.h>

Inheritance diagram for classification< T >:
Inheritance graph
Collaboration diagram for classification< T >:
Collaboration graph

Public Types

enum  classificationTypes { knn, svm }
 

Public Member Functions

 classification ()
 
 classification (classificationTypes classificationType)
 
 classification (const std::vector< trainingExample< T > > &trainingSet)
 
 classification (const int &numInputs, const int &numOutputs)
 
 ~classification ()
 
bool train (const std::vector< trainingExample< T > > &trainingSet)
 
std::vector< int > getK ()
 
void setK (const int whichModel, const int newK)
 
- Public Member Functions inherited from modelSet< T >
 modelSet ()
 
virtual ~modelSet ()
 
bool reset ()
 
std::vector< T > run (const std::vector< T > &inputVector)
 
std::string getJSON ()
 
void writeJSON (const std::string &filepath)
 
bool putJSON (const std::string &jsonMessage)
 
bool readJSON (const std::string &filepath)
 

Additional Inherited Members

- Protected Attributes inherited from modelSet< T >
std::vector< baseModel< T > * > myModelSet
 
int numInputs
 
std::vector< std::string > inputNames
 
int numOutputs
 
bool created
 

Detailed Description

template<typename T>
class classification< T >

Class for implementing a set of classification models.

This doesn't do anything modelSet can't do. But, it's simpler and more like wekinator.

Member Enumeration Documentation

§ classificationTypes

template<typename T >
enum classification::classificationTypes
Enumerator
knn 
svm 

Constructor & Destructor Documentation

§ classification() [1/4]

template<typename T >
classification< T >::classification ( )

with no arguments, just make an empty vector

§ classification() [2/4]

template<typename T >
classification< T >::classification ( classificationTypes  classificationType)

speciify classification type

§ classification() [3/4]

template<typename T >
classification< T >::classification ( const std::vector< trainingExample< T > > &  trainingSet)

create based on training set inputs and outputs

§ classification() [4/4]

template<typename T >
classification< T >::classification ( const int &  numInputs,
const int &  numOutputs 
)

create with proper models, but not trained

§ ~classification()

template<typename T >
classification< T >::~classification ( )
inline

destructor

Member Function Documentation

§ getK()

template<typename T >
std::vector< int > classification< T >::getK ( )

Check the K values for each model. This feature is temporary, and will be replaced by a different design.

§ setK()

template<typename T >
void classification< T >::setK ( const int  whichModel,
const int  newK 
)

Get the K values for each model. This feature is temporary, and will be replaced by a different design.

§ train()

template<typename T >
bool classification< T >::train ( const std::vector< trainingExample< T > > &  trainingSet)
virtual

Train on a specified set, causes creation if not created

Reimplemented from modelSet< T >.


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