public abstract class GeneticIndividualForSymbRegr extends GeneticIndividual
Class for management of genetic individuals in symbolic regression
Modifier and Type | Field and Description |
---|---|
protected FuzzyRegressor |
m |
protected static double[][] |
X |
protected static FuzzyAlphaCut[][] |
Xfuzzy |
protected static double[] |
Y |
protected static FuzzyAlphaCut[] |
Yfuzzy |
protected static double[] |
Yo |
CUSTOM_CESAR, fitnessType, g, STANDARD
Constructor and Description |
---|
GeneticIndividualForSymbRegr(int tf)
Constructor.
|
Modifier and Type | Method and Description |
---|---|
void |
asignaejemplos(double[][] pX,
double[] pY,
double tolerance)
This method assign examples based on a level of tolerance
|
void |
debug_fitness()
This method is for debug the fitness
|
void |
debug()
This method is for debug
|
double |
fitness()
This method calculates the fitness based in the ECM
|
double[] |
getYo()
This method obtain a crips output that we can compare to punctual models
|
double |
MSE()
This method calculate the mean square error
|
clone, crossover, localOptimization, mutation, parametersFromGenotype, Random
protected static FuzzyAlphaCut[][] Xfuzzy
protected static FuzzyAlphaCut[] Yfuzzy
protected static double[][] X
protected static double[] Y
protected static double[] Yo
protected FuzzyRegressor m
public GeneticIndividualForSymbRegr(int tf)
Constructor. Initializes the type of fitness
tf
- the type of fitnesspublic double fitness() throws invalidFitness
This method calculates the fitness based in the ECM
fitness
in class GeneticIndividual
invalidFitness
- Message is errorpublic void debug_fitness()
This method is for debug the fitness
public void debug()
This method is for debug
debug
in class GeneticIndividual
public void asignaejemplos(double[][] pX, double[] pY, double tolerance)
This method assign examples based on a level of tolerance
pX
- pY
- tolerance
- The level of tolerancepublic double[] getYo()
This method obtain a crips output that we can compare to punctual models
public double MSE()
This method calculate the mean square error