public class LVQ3 extends LVQ2
Modifier and Type | Field and Description |
---|---|
double |
DEFAULT_EPSILON
Default value for the epsilon constant
|
protected double |
epsilon
Epsilon constant (multiplier of the window width)
|
protected double |
epsilonTimesAlpha_0
Epsilon times alpha constant
|
DEFAULT_WINDOW_WIDTH, windowLowerBound, windowWidth
alpha_0, ALPHA_DEFAULT_VALUE, chosenRandomIndex, IALPHA, randomIndexes
initial, initialset, iterations, numberOfPrototypesGenerated
algorithmName, generatedDataSet, SEED, seedDefaultValueList, trainingDataSet
Constructor and Description |
---|
LVQ3(PrototypeSet tDataSet,
int iter,
double pcNprot,
double alpha_0,
double windowWidth,
double epsilon)
Construct a new LVQ3 algorithm.
|
LVQ3(PrototypeSet tDataSet,
int iter,
int nProt,
double alpha_0,
double windowWidth,
double epsilon)
Construct a new LVQ3 algorithm.
|
LVQ3(PrototypeSet tDataSet,
Parameters par)
Construct a new LVQ3 algorithm.
|
LVQ3(PrototypeSet InitialSet,
PrototypeSet tDataSet,
int iter,
int nProt,
double alpha_0,
double windowWidth,
double epsilon)
WITH INITIAL CODE-BOOKS
Construct a new LVQ3 algorithm.
|
Modifier and Type | Method and Description |
---|---|
protected void |
correct(Prototype x,
PrototypeSet tData)
Corrects the instance using a particular method
|
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
3: k Number of neighbors used in the KNN function
|
protected void |
penalize(Prototype m,
Prototype x)
Applies LVQ3-penalization to prototype m
|
protected void |
reward(Prototype m,
Prototype x)
Applies LVQ3-reward to prototype m
|
protected void |
reward2(Prototype m,
Prototype x)
USING EPSILON parameter.
|
extract, initDataSet, initDataSetRandomMode
reduceSet
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
public final double DEFAULT_EPSILON
protected double epsilon
protected double epsilonTimesAlpha_0
public LVQ3(PrototypeSet tDataSet, int iter, int nProt, double alpha_0, double windowWidth, double epsilon)
tDataSet
- Training data set.iter
- Number of iteratios of the algorithm.nProt
- Number of prototypes generated.alpha_0
- Alpha constant.windowWidth
- Window width constant.epsilon
- Epsilon constant.public LVQ3(PrototypeSet InitialSet, PrototypeSet tDataSet, int iter, int nProt, double alpha_0, double windowWidth, double epsilon)
InitialSet
- Initial datasettDataSet
- Training data set.iter
- Number of iteratios of the algorithm.nProt
- Number of prototypes generated.alpha_0
- Alpha constant.windowWidth
- Window width constant.epsilon
- Epsilon constant.public LVQ3(PrototypeSet tDataSet, int iter, double pcNprot, double alpha_0, double windowWidth, double epsilon)
tDataSet
- Training data set.iter
- Number of iteratios of the algorithm.pcNprot
- Number of prototypes generated as percentage of training size.alpha_0
- Alpha constant.windowWidth
- Window width constant.epsilon
- Epsilon constant.public LVQ3(PrototypeSet tDataSet, Parameters par)
tDataSet
- Training data set.par
- Parameters of the algorithm.protected void reward2(Prototype m, Prototype x)
m
- x
- protected void correct(Prototype x, PrototypeSet tData)
public static void main(java.lang.String[] args)
args
- Arguments of the main function.