/**
* It generates the output file from a given dataset and stores it in a file
*
* @param dataset myDataset input dataset
* @param filename String the name of the file
*/
private double doOutput(myDataset dataset, String filename, boolean test) {
String output = new String("");
confusionMatrix = new int[dataset.getnClasses()][dataset.getnClasses()];
output = dataset.copyHeader(); // we insert the header in the output file
// We write the output for each example
for (int i = 0; i < dataset.getnData(); i++) {
String clReal = dataset.getOutputAsString(i);
String clPred = classificationOutput(i, test);
confusionMatrix[dataset.getOutputAsInteger(i)][dataset.numericClass(clPred)]++;
output += clReal + " " + clPred + "\n";
}
double acc = 0;
int nClasses = 0;
for (int i = 0; i < confusionMatrix.length; i++) {
int count = 0;
for (int j = 0; j < confusionMatrix[i].length; j++) {
count += confusionMatrix[i][j];
}
if (count > 0) {
acc += 1.0 * confusionMatrix[i][i] / count;
nClasses++;
}
}
Files.writeFile(filename, output);
return acc / nClasses;
// return 1.0*hits/dataset.size();
}
/**
* In this method, all possible post hoc statistical test between more than three algorithms
* results are executed, according to the configuration file
*
* @param code A double that identifies which methods will be applied
* @param nfold A vector of int with fold number by algorithm
* @param algorithms A vector of String with the names of the algorithms
* @param fileName A String with the name of the output file
*/
public static void doMultiple(double data[][], String algorithms[]) {
String outputFileName = Configuration.getPath();
String outputString = new String("");
outputString = header();
outputString += runMultiple(data, algorithms);
Files.writeFile(outputFileName, outputString);
} // end-method
private void generateModel() {
String salida = new String("");
double max_auc = 0;
ArrayList<String> solutions = this.getAllSolutions();
models = new ArrayList<Farchd>();
int nEjemplos = train.getnData();
if (this.instances == this.MAJ) {
nEjemplos = train.getMajority();
}
boolean[] variables = new boolean[train.getnInputs()];
boolean[] ejemplos = new boolean[nEjemplos];
this.weightsAUC = new double[solutions.size() / 2]; // Hay 2 soluciones FS e IS
for (int i = 0, j = 0; i < solutions.size(); i += 2, j++) {
int vars, ejs;
vars = ejs = 0;
variables = decode(solutions.get(i));
ejemplos = decode(solutions.get(i + 1));
for (int l = 0; l < variables.length; l++) {
// variables[j] = solution[j];
if (variables[l]) vars++;
}
for (int l = 0; l < ejemplos.length; l++) {
if (ejemplos[l]) ejs++;
}
try {
Farchd model = new Farchd(train, val, test, variables, ejemplos);
/** ******** */
// double fit = model.getAUCTr();
double auc_tr = model.execute(true);
double auc_tst = model.getAUCTst();
if (auc_tr > max_auc) {
max_auc = auc_tr;
indexBest = j;
}
this.weightsAUC[j] = auc_tr;
salida +=
"Solution[" + j + "]:\t" + vars + "\t" + ejs + "\t" + auc_tr + "\t" + auc_tst + "\n";
/** ******** */
models.add(model);
} catch (Exception e) {
System.err.println("Liada maxima al generar modelo ");
e.printStackTrace(System.err);
System.exit(-1);
}
}
System.out.print(salida);
Files.writeFile(header + "_AUC.txt", salida);
}
/**
* Save network weights to a file
*
* @param file_name Output file name
* @param header header of the data set for which the network has been adjusted to
*/
protected void printNetworkToFile(String file_name, String header) {
// write the header to the file
Files.writeFile(file_name, header);
Files.addToFile(file_name, "Number of neurons: " + nSel + "\n");
for (int i = 0; i < nSel; i++) {
Files.addToFile(file_name, "\nNeuron " + i + "\n");
for (int j = 0; j < conjS[i].length; j++) {
Files.addToFile(file_name, Double.toString(conjS[i][j]) + " ");
}
Files.addToFile(file_name, " Class = " + clasesS[i] + "\n");
}
}
/**
* It generates the output file from a given dataset and stores it in a file
*
* @param dataset myDataset input dataset
* @param filename String the name of the file
*/
private void doOutput(myDataset dataset, String filename) {
int i;
double fuerza;
String output = new String("");
output = dataset.copyHeader(); // we insert the header in the output file
for (i = 0; i < dataset.getnData(); i++) {
fuerza = Output_fuzzy_system(dataset.getExample(i));
output += (dataset.getOutputAsReal(i) + " " + fuerza + " " + "\n");
}
Files.writeFile(filename, output);
}
/** Method interface for Automatic Branch and Bound */
public void ejecutar() {
String resultado;
int i, numFeatures;
Date d;
d = new Date();
resultado =
"RESULTS generated at "
+ String.valueOf((Date) d)
+ " \n--------------------------------------------------\n";
resultado += "Algorithm Name: " + params.nameAlgorithm + "\n";
/* call of ABB algorithm */
runABB();
resultado += "\nPARTITION Filename: " + params.trainFileNameInput + "\n---------------\n\n";
resultado += "Features selected: \n";
for (i = numFeatures = 0; i < features.length; i++)
if (features[i] == true) {
resultado += Attributes.getInputAttribute(i).getName() + " - ";
numFeatures++;
}
resultado +=
"\n\n"
+ String.valueOf(numFeatures)
+ " features of "
+ Attributes.getInputNumAttributes()
+ "\n\n";
resultado +=
"Error in test (using train for prediction): "
+ String.valueOf(data.validacionCruzada(features))
+ "\n";
resultado +=
"Error in test (using test for prediction): "
+ String.valueOf(data.LVOTest(features))
+ "\n";
resultado += "---------------\n";
System.out.println("Experiment completed successfully");
/* creates the new training and test datasets only with the selected features */
Files.writeFile(params.extraFileNameOutput, resultado);
data.generarFicherosSalida(params.trainFileNameOutput, params.testFileNameOutput, features);
}
/**
* It generates the output file from a given dataset and stores it in a file
*
* @param dataset myDataset input dataset
* @param filename String the name of the file
* @return The classification accuracy
*/
private double doOutput(myDataset dataset, String filename) {
String output = new String("");
int hits = 0;
output = dataset.copyHeader(); // we insert the header in the output file
// We write the output for each example
for (int i = 0; i < dataset.getnData(); i++) {
// for classification:
String classOut = this.classificationOutput(dataset.getExample(i));
output += dataset.getOutputAsString(i) + " " + classOut + "\n";
if (dataset.getOutputAsString(i).equalsIgnoreCase(classOut)) {
hits++;
}
}
Files.writeFile(filename, output);
return (1.0 * hits / dataset.size());
}
/** It launches the algorithm */
public void execute() {
int i, j, num;
double fitness, fitness2;
if (somethingWrong) { // We do not execute the program
System.err.println(
"An error was found, either the data-set have numerical values or missing values.");
System.err.println("Aborting the program");
// We should not use the statement: System.exit(-1);
} else {
// We do here the algorithm's operations
Randomize.setSeed(semilla);
/* Generation of the initial population */
System.out.println("Creating the initial population.");
initializePopulation();
Gen = 0;
GenSincambio = 0;
Bestperformance = -1.0;
/* Main of the genetic algorithm */
System.out.println("Starting the evolutionary process.");
do {
/* First, all rules' fitness is set to 0 */
for (i = 0; i < tamPoblacion; i++) {
Poblacion.get(i).fitness = 0.0;
Poblacion.get(i).n_SistemasDifusos = 0;
}
/* Then Nf fuzzy system are created */
for (i = 0; i < Nf; i++) {
/* A fuzzy system containing Nr rules from the population is created */
Create_fuzzy_system();
/* The fitness asociated to this fuzzy system is calculated */
fitness = Evaluate_fuzzy_system();
/* The fitness value is accumulated among the rules in the fuzzy system */
Accumulate_fitness_fuzzy_system(fitness);
/* If the fitness of the current fuzzy system outperforms the best evolved one,
we update this last one */
if (fitness > Bestperformance) {
Bestperformance = fitness;
GenSincambio = -1;
BestSistemaDifuso.clear();
for (j = 0; j < Nr; j++) {
Individual indi = new Individual(Poblacion.get(vectorNr[j]));
BestSistemaDifuso.add(indi);
}
}
}
/* The accumulated fitness value of each individual in the population is divided
by the number of times it has been selected */
for (i = 0; i < tamPoblacion; i++) {
if (Poblacion.get(i).n_SistemasDifusos != 0) {
Poblacion.get(i).fitness /= Poblacion.get(i).n_SistemasDifusos;
} else {
Poblacion.get(i).fitness = 0.0;
}
/* Now we count the number of parameter used in the consequent, in order to
give a better fitness to those rules with a lower number of parameters */
num = 0;
for (j = 0; j < entradas; j++) {
if (Poblacion.get(i).consecuente[j] != 0.0) {
num++;
}
}
if (Poblacion.get(i).consecuente[entradas] != 0.0) {
num++;
}
Poblacion.get(i).fitness /= (K + num);
}
/* we increment the counter of the number of generations */
Gen++;
GenSincambio++;
if (GenSincambio == numGenMigration) {
/* Migration stage: half of the population (the worst one) is radomly generated again
to increase the searching ability of the genetic process */
System.out.println(
"Migrating half of the population in order to restart the evolutionary process.");
Migration();
GenSincambio = 0;
} else {
/* Reproduction stage (includes crossover) */
Reproduction();
/* Mutation */
Mutation();
}
System.out.println("Iteration: " + Gen + ". Best fitness: " + (1.0 / Bestperformance));
} while (Gen <= numGeneraciones);
String salida = new String("");
salida += Print_Population();
SistemaDifuso.clear();
for (i = 0; i < Nr; i++) {
Individual indi = new Individual(BestSistemaDifuso.get(i));
SistemaDifuso.add(indi);
}
salida += "MSE Training:\t" + (1.0 / Bestperformance) + "%\n";
salida += "MSE Test:\t\t" + Evaluate_best_fuzzy_system_in_test() + "%\n\n";
Files.writeFile(outputBC, salida);
doOutput(this.val, this.outputTr);
doOutput(this.test, this.outputTst);
System.out.println("Algorithm Finished.");
}
}
/** Outputs contents of CMAR rule linked list (if any) */
public void outputCMARrules(String filename) {
String stringOut = new String("");
stringOut = outputRules(startCMARrulelist);
Files.writeFile(filename, stringOut);
}