keel.Algorithms.Instance_Generation.BTS3

Class BTS3Generator

java.lang.Object

keel.Algorithms.Instance_Generation.Basic.PrototypeGenerator

keel.Algorithms.Instance_Generation.BTS3.BTS3Generator

public class BTS3Generator
extends PrototypeGenerator

Prototoype generator by the Boostrap algorithm (BST3)

Author:

diegoj

Field Summary

Fields

Modifier and Type	Field and Description
protected int	nearestNeighbors Size of the merged data set.
protected int	numberOfPrototypesGenerated Size of the generated set.
protected int	randomTrials Number of bootstrapings of the algorithm.

Fields inherited from class keel.Algorithms.Instance_Generation.Basic.PrototypeGenerator

algorithmName, generatedDataSet, SEED, seedDefaultValueList, trainingDataSet

Constructor Summary

Constructors

Constructor and Description
BTS3Generator(PrototypeSet _trainingDataSet, double percSize, int nearestNeighbors, int trials) Constructor
BTS3Generator(PrototypeSet _trainingDataSet, int Np, int nearestNeighbors, int trials) Constructor
BTS3Generator(PrototypeSet _trainingDataSet, Parameters parameters) Constructor

Method Summary

Modifier and Type	Method and Description
static void	main(java.lang.String[] args) General main for all the prototoype generators Arguments: 0: Filename with the training data set to be condensed. 1: Filename wich will contain the test data set 2: Seed of the random generator. 3: Number of prototypes to be generated. 4: Nearest-Neighbors used in the internal KNN use. 5: Random Trials (number of bootstrappings performed).
PrototypeSet	reduceSet() Reduce the training data set by the Hamamoto et al.

Methods inherited from class keel.Algorithms.Instance_Generation.Basic.PrototypeGenerator

absoluteAccuracy, absoluteAccuracyAndError, absoluteAccuracyKNN, accuracy, accuracy2, desordenar_vector_sin, desordenar_vector, execute, generateReducedDataSet, getResultingAccuracy, getResultingAccuracy, getResults, getResultsOfAccuracy, getResultsOfAccuracy, getSeed, getSetSizeFromPercentage, getSetSizeFromPercentage, getTime, inic_vector_sin, inic_vector, saveResultsOfAccuracyIn, saveResultsOfAccuracyIn, selecRandomSet, setSeed, showResultsOfAccuracy, showResultsOfAccuracy

Methods inherited from class java.lang.Object

clone, equals, finalize, getClass, hashCode, notify, notifyAll, toString, wait, wait, wait

Field Detail

numberOfPrototypesGenerated

protected int numberOfPrototypesGenerated

Size of the generated set.

randomTrials

protected int randomTrials

Number of bootstrapings of the algorithm.

nearestNeighbors

protected int nearestNeighbors

Size of the merged data set.

Constructor Detail

BTS3Generator

public BTS3Generator(PrototypeSet _trainingDataSet,
                     Parameters parameters)

Constructor

Parameters:

_trainingDataSet - Traning data set.

parameters - Parameters of the algorithm.

BTS3Generator

public BTS3Generator(PrototypeSet _trainingDataSet,
                     int Np,
                     int nearestNeighbors,
                     int trials)

Constructor

Parameters:

_trainingDataSet - Traning data set.

Np - Number of prototypes to be generated.

nearestNeighbors - Nearest-neighbors used to assign class to each prototype generated.

trials - Random trials to be performed during execution.

BTS3Generator

public BTS3Generator(PrototypeSet _trainingDataSet,
                     double percSize,
                     int nearestNeighbors,
                     int trials)

Constructor

Parameters:

_trainingDataSet - Traning data set.

percSize - Percentage of the size of training set that will be the reduced set.

nearestNeighbors - Nearest-neighbors used to assign class to each prototype generated.

trials - Random trials to be performed during execution.

Method Detail

reduceSet

public PrototypeSet reduceSet()

Reduce the training data set by the Hamamoto et al. Bootstrap method

Overrides:

reduceSet in class PrototypeGenerator

Returns:

Reduced prototype data set that is the condensed input data set.

main

public static void main(java.lang.String[] args)

General main for all the prototoype generators Arguments: 0: Filename with the training data set to be condensed. 1: Filename wich will contain the test data set 2: Seed of the random generator. 3: Number of prototypes to be generated. 4: Nearest-Neighbors used in the internal KNN use. 5: Random Trials (number of bootstrappings performed).

Parameters:

args - Arguments of the main function.