/**
* PMX cross operator
*
* @param poblacion Population of chromosomes
* @param newPob New population
* @param sel1 First parent
* @param sel2 Second parent
*/
public void crucePMX(Cromosoma poblacion[], Cromosoma newPob[], int sel1, int sel2) {
int e1, e2;
int limSup, limInf;
int i;
boolean temp[];
temp = new boolean[datosTrain.length];
e1 = Randomize.Randint(0, datosTrain.length - 1);
e2 = Randomize.Randint(0, datosTrain.length - 1);
if (e1 > e2) {
limSup = e1;
limInf = e2;
} else {
limSup = e2;
limInf = e1;
}
for (i = 0; i < datosTrain.length; i++) {
if (i < limInf || i > limSup) temp[i] = poblacion[sel1].getGen(i);
else temp[i] = poblacion[sel2].getGen(i);
}
newPob[0] = new Cromosoma(temp);
for (i = 0; i < datosTrain.length; i++) {
if (i < limInf || i > limSup) temp[i] = poblacion[sel2].getGen(i);
else temp[i] = poblacion[sel1].getGen(i);
}
newPob[1] = new Cromosoma(temp);
} // end-method
/**
* Reinitializes the chromosome by using CHC diverge procedure
*
* @param r R factor of diverge
* @param mejor Best chromosome found so far
* @param prob Probability of setting a gen to 1
*/
public void divergeCHC(double r, Cromosoma mejor, double prob) {
int i;
for (i = 0; i < cuerpo.length; i++) {
if (Randomize.Rand() < r) {
if (Randomize.Rand() < prob) {
cuerpo[i] = true;
} else {
cuerpo[i] = false;
}
} else {
cuerpo[i] = mejor.getGen(i);
}
}
cruzado = true;
} // end-method
/**
* Mutation operator
*
* @param pMutacion1to0 Probability of change 1 to 0
* @param pMutacion0to1 Probability of change 0 to 1
*/
public void mutacion(double pMutacion1to0, double pMutacion0to1) {
int i;
for (i = 0; i < cuerpo.length; i++) {
if (cuerpo[i]) {
if (Randomize.Rand() < pMutacion1to0) {
cuerpo[i] = false;
cruzado = true;
}
} else {
if (Randomize.Rand() < pMutacion0to1) {
cuerpo[i] = true;
cruzado = true;
}
}
}
} // end-method
/**
* Builder. Construct a random chromosome of specified size
*
* @param size Size of the chromosome
*/
public Cromosoma(int size) {
double u;
int i;
cuerpo = new boolean[size];
for (i = 0; i < size; i++) {
u = Randomize.Rand();
if (u < 0.5) {
cuerpo[i] = false;
} else {
cuerpo[i] = true;
}
}
cruzado = true;
valido = true;
} // end-method
public void ejecutar() {
int i, j, l, m;
double alfai;
int nClases;
int claseObt;
boolean marcas[];
boolean notFound;
int init;
int clasSel[];
int baraje[];
int pos, tmp;
String instanciasIN[];
String instanciasOUT[];
long tiempo = System.currentTimeMillis();
/* Getting the number of differents classes */
nClases = 0;
for (i = 0; i < clasesTrain.length; i++) if (clasesTrain[i] > nClases) nClases = clasesTrain[i];
nClases++;
/* Shuffle the train set */
baraje = new int[datosTrain.length];
Randomize.setSeed(semilla);
for (i = 0; i < datosTrain.length; i++) baraje[i] = i;
for (i = 0; i < datosTrain.length; i++) {
pos = Randomize.Randint(i, datosTrain.length - 1);
tmp = baraje[i];
baraje[i] = baraje[pos];
baraje[pos] = tmp;
}
/*
* Inicialization of the flagged instaces vector for a posterior
* elimination
*/
marcas = new boolean[datosTrain.length];
for (i = 0; i < datosTrain.length; i++) marcas[i] = false;
if (datosTrain.length > 0) {
// marcas[baraje[0]] = true; //the first instance is included always
nSel = n_p;
if (nSel < nClases) nSel = nClases;
} else {
System.err.println("Input dataset is empty");
nSel = 0;
}
clasSel = new int[nClases];
System.out.print("Selecting initial neurons... ");
// at least, there must be 1 neuron of each class at the beginning
init = nClases;
for (i = 0; i < nClases && i < datosTrain.length; i++) {
pos = Randomize.Randint(0, datosTrain.length - 1);
tmp = 0;
while ((clasesTrain[pos] != i || marcas[pos]) && tmp < datosTrain.length) {
pos = (pos + 1) % datosTrain.length;
tmp++;
}
if (tmp < datosTrain.length) marcas[pos] = true;
else init--;
// clasSel[i] = i;
}
for (i = init; i < Math.min(nSel, datosTrain.length); i++) {
tmp = 0;
pos = Randomize.Randint(0, datosTrain.length - 1);
while (marcas[pos]) {
pos = (pos + 1) % datosTrain.length;
tmp++;
}
// if(i<nClases){
// notFound = true;
// do{
// for(j=i-1;j>=0 && notFound;j--){
// if(clasSel[j] == clasesTrain[pos])
// notFound = false;
// }
// if(!notFound)
// pos = Randomize.Randint (0, datosTrain.length-1);
// }while(!notFound);
// }
// clasSel[i] = clasesTrain[pos];
marcas[pos] = true;
init++;
}
nSel = init;
System.out.println("Initial neurons selected: " + nSel);
/* Building of the S set from the flags */
conjS = new double[nSel][datosTrain[0].length];
clasesS = new int[nSel];
for (m = 0, l = 0; m < datosTrain.length; m++) {
if (marcas[m]) { // the instance must be copied to the solution
for (j = 0; j < datosTrain[0].length; j++) {
conjS[l][j] = datosTrain[m][j];
}
clasesS[l] = clasesTrain[m];
l++;
}
}
alfai = alpha;
boolean change = true;
/* Body of the LVQ algorithm. */
// Train the network
for (int it = 0; it < T && change; it++) {
change = false;
alpha = alfai;
for (i = 1; i < datosTrain.length; i++) {
// search for the nearest neuron to training instance
pos = NN(nSel, conjS, datosTrain[baraje[i]]);
// nearest neuron labels correctly the class of training
// instance?
if (clasesS[pos] != clasesTrain[baraje[i]]) { // NO - repel
// the neuron
for (j = 0; j < conjS[pos].length; j++) {
conjS[pos][j] = conjS[pos][j] - alpha * (datosTrain[baraje[i]][j] - conjS[pos][j]);
}
change = true;
} else { // YES - migrate the neuron towards the input vector
for (j = 0; j < conjS[pos].length; j++) {
conjS[pos][j] = conjS[pos][j] + alpha * (datosTrain[baraje[i]][j] - conjS[pos][j]);
}
}
alpha = nu * alpha;
}
// Shuffle again the training partition
baraje = new int[datosTrain.length];
for (i = 0; i < datosTrain.length; i++) baraje[i] = i;
for (i = 0; i < datosTrain.length; i++) {
pos = Randomize.Randint(i, datosTrain.length - 1);
tmp = baraje[i];
baraje[i] = baraje[pos];
baraje[pos] = tmp;
}
}
System.out.println(
"LVQ " + relation + " " + (double) (System.currentTimeMillis() - tiempo) / 1000.0 + "s");
// Classify the train data set
instanciasIN = new String[datosReferencia.length];
instanciasOUT = new String[datosReferencia.length];
for (i = 0; i < datosReferencia.length; i++) {
/* Classify the instance selected in this iteration */
Attribute a = Attributes.getOutputAttribute(0);
int tipo = a.getType();
claseObt = KNN.evaluacionKNN2(1, conjS, clasesS, datosReferencia[i], nClases);
if (tipo != Attribute.NOMINAL) {
instanciasIN[i] = new String(String.valueOf(clasesReferencia[i]));
instanciasOUT[i] = new String(String.valueOf(claseObt));
} else {
instanciasIN[i] = new String(a.getNominalValue(clasesReferencia[i]));
instanciasOUT[i] = new String(a.getNominalValue(claseObt));
}
}
escribeSalida(
ficheroSalida[0], instanciasIN, instanciasOUT, entradas, salida, nEntradas, relation);
// Classify the test data set
normalizarTest();
instanciasIN = new String[datosTest.length];
instanciasOUT = new String[datosTest.length];
for (i = 0; i < datosTest.length; i++) {
/* Classify the instance selected in this iteration */
Attribute a = Attributes.getOutputAttribute(0);
int tipo = a.getType();
claseObt = KNN.evaluacionKNN2(1, conjS, clasesS, datosTest[i], nClases);
if (tipo != Attribute.NOMINAL) {
instanciasIN[i] = new String(String.valueOf(clasesTest[i]));
instanciasOUT[i] = new String(String.valueOf(claseObt));
} else {
instanciasIN[i] = new String(a.getNominalValue(clasesTest[i]));
instanciasOUT[i] = new String(a.getNominalValue(claseObt));
}
}
escribeSalida(
ficheroSalida[1], instanciasIN, instanciasOUT, entradas, salida, nEntradas, relation);
// Print the network to a file
printNetworkToFile(ficheroSalida[2], referencia.getHeader());
}
/**
* The main method of the class that includes the operations of the algorithm. It includes all the
* operations that the algorithm has and finishes when it writes the output information into
* files.
*/
public void run() {
int nPos = 0;
int nNeg = 0;
int i, j, l, m;
int tmp;
int posID;
int positives[];
int overs[];
double conjS[][];
int clasesS[];
int tamS;
long tiempo = System.currentTimeMillis();
/*Count of number of positive and negative examples*/
for (i = 0; i < clasesTrain.length; i++) {
if (clasesTrain[i] == 0) nPos++;
else nNeg++;
}
if (nPos > nNeg) {
tmp = nPos;
nPos = nNeg;
nNeg = tmp;
posID = 1;
} else {
posID = 0;
}
/*Localize the positive instances*/
positives = new int[nPos];
for (i = 0, j = 0; i < clasesTrain.length; i++) {
if (clasesTrain[i] == posID) {
positives[j] = i;
j++;
}
}
/*Obtain the oversampling array taking account the previous array*/
overs = new int[nNeg - nPos];
Randomize.setSeed(semilla);
for (i = 0; i < overs.length; i++) {
tmp = Randomize.Randint(0, nPos - 1);
overs[i] = positives[tmp];
}
tamS = 2 * nNeg;
/*Construction of the S set from the previous vector S*/
conjS = new double[tamS][datosTrain[0].length];
clasesS = new int[tamS];
for (j = 0; j < datosTrain.length; j++) {
for (l = 0; l < datosTrain[0].length; l++) conjS[j][l] = datosTrain[j][l];
clasesS[j] = clasesTrain[j];
}
for (m = 0; j < tamS; j++, m++) {
for (l = 0; l < datosTrain[0].length; l++) conjS[j][l] = datosTrain[overs[m]][l];
clasesS[j] = clasesTrain[overs[m]];
}
System.out.println(
"RandomOverSampling "
+ relation
+ " "
+ (double) (System.currentTimeMillis() - tiempo) / 1000.0
+ "s");
OutputIS.escribeSalida(ficheroSalida[0], conjS, clasesS, entradas, salida, nEntradas, relation);
OutputIS.escribeSalida(ficheroSalida[1], test, entradas, salida, nEntradas, relation);
}
/**
* The main method of the class that includes the operations of the algorithm. It includes all the
* operations that the algorithm has and finishes when it writes the output information into
* files.
*/
public void run() {
int S[];
int i, j, l, m;
int nPos = 0, nNeg = 0;
int posID;
int nClases;
int pos;
int baraje[];
int tmp;
double conjS[][];
int clasesS[];
int tamS = 0;
int claseObt;
int cont;
int busq;
boolean marcas[];
int nSel;
double conjS2[][];
int clasesS2[];
double minDist, dist;
long tiempo = System.currentTimeMillis();
/*CNN PART*/
/*Count of number of positive and negative examples*/
for (i = 0; i < clasesTrain.length; i++) {
if (clasesTrain[i] == 0) nPos++;
else nNeg++;
}
if (nPos > nNeg) {
tmp = nPos;
nPos = nNeg;
nNeg = tmp;
posID = 1;
} else {
posID = 0;
}
/*Inicialization of the candidates set*/
S = new int[datosTrain.length];
for (i = 0; i < S.length; i++) S[i] = Integer.MAX_VALUE;
/*Inserting an element of mayority class*/
Randomize.setSeed(semilla);
pos = Randomize.Randint(0, clasesTrain.length - 1);
while (clasesTrain[pos] == posID) pos = (pos + 1) % clasesTrain.length;
S[tamS] = pos;
tamS++;
/*Insert all subset of minority class*/
for (i = 0; i < clasesTrain.length; i++) {
if (clasesTrain[i] == posID) {
S[tamS] = i;
tamS++;
}
}
/*Algorithm body. We resort randomly the instances of T and compare with the rest of S.
If an instance doesn´t classified correctly, it is inserted in S*/
baraje = new int[datosTrain.length];
for (i = 0; i < datosTrain.length; i++) baraje[i] = i;
for (i = 0; i < datosTrain.length; i++) {
pos = Randomize.Randint(i, clasesTrain.length - 1);
tmp = baraje[i];
baraje[i] = baraje[pos];
baraje[pos] = tmp;
}
for (i = 0; i < datosTrain.length; i++) {
if (clasesTrain[i] != posID) { // only for mayority class instances
/*Construction of the S set from the previous vector S*/
conjS = new double[tamS][datosTrain[0].length];
clasesS = new int[tamS];
for (j = 0; j < tamS; j++) {
for (l = 0; l < datosTrain[0].length; l++) conjS[j][l] = datosTrain[S[j]][l];
clasesS[j] = clasesTrain[S[j]];
}
/*Do KNN to the instance*/
claseObt = KNN.evaluacionKNN(k, conjS, clasesS, datosTrain[baraje[i]], 2);
if (claseObt != clasesTrain[baraje[i]]) { // fail in the class, it is included in S
Arrays.sort(S);
busq = Arrays.binarySearch(S, baraje[i]);
if (busq < 0) {
S[tamS] = baraje[i];
tamS++;
}
}
}
}
/*Construction of the S set from the previous vector S*/
conjS = new double[tamS][datosTrain[0].length];
clasesS = new int[tamS];
for (j = 0; j < tamS; j++) {
for (l = 0; l < datosTrain[0].length; l++) conjS[j][l] = datosTrain[S[j]][l];
clasesS[j] = clasesTrain[S[j]];
}
/*TOMEK LINKS PART*/
/*Inicialization of the instance flagged vector of the S set*/
marcas = new boolean[conjS.length];
for (i = 0; i < conjS.length; i++) {
marcas[i] = true;
}
nSel = conjS.length;
for (i = 0; i < conjS.length; i++) {
minDist = Double.POSITIVE_INFINITY;
pos = 0;
for (j = 0; j < conjS.length; j++) {
if (i != j) {
dist = KNN.distancia(conjS[i], conjS[j]);
if (dist < minDist) {
minDist = dist;
pos = j;
}
}
}
if (clasesS[i] != clasesS[pos]) {
if (clasesS[i] != posID) {
if (marcas[i] == true) {
marcas[i] = false;
nSel--;
}
} else {
if (marcas[pos] == true) {
marcas[pos] = false;
nSel--;
}
}
}
}
/*Construction of the S set from the flags*/
conjS2 = new double[nSel][conjS[0].length];
clasesS2 = new int[nSel];
for (m = 0, l = 0; m < conjS.length; m++) {
if (marcas[m]) { // the instance will evaluate
for (j = 0; j < conjS[0].length; j++) {
conjS2[l][j] = conjS[m][j];
}
clasesS2[l] = clasesS[m];
l++;
}
}
System.out.println(
"CNN_TomekLinks "
+ relation
+ " "
+ (double) (System.currentTimeMillis() - tiempo) / 1000.0
+ "s");
OutputIS.escribeSalida(
ficheroSalida[0], conjS2, clasesS2, entradas, salida, nEntradas, relation);
OutputIS.escribeSalida(ficheroSalida[1], test, entradas, salida, nEntradas, relation);
}
/** Executes the algorithm */
public void ejecutar() {
int i, j, l;
int nClases;
double conjS[][];
double conjR[][];
int conjN[][];
boolean conjM[][];
int clasesS[];
int nSel = 0;
Cromosoma poblacion[];
int ev = 0;
double prob[];
double NUmax = 1.5;
double NUmin = 0.5; // used for lineal ranking
double aux;
double pos1, pos2;
int sel1, sel2, comp1, comp2;
Cromosoma newPob[];
long tiempo = System.currentTimeMillis();
/*Getting the number of different clases*/
nClases = 0;
for (i = 0; i < clasesTrain.length; i++) if (clasesTrain[i] > nClases) nClases = clasesTrain[i];
nClases++;
/*Random inicialization of the population*/
Randomize.setSeed(semilla);
poblacion = new Cromosoma[tamPoblacion];
for (i = 0; i < tamPoblacion; i++) poblacion[i] = new Cromosoma(datosTrain.length);
/*Initial evaluation of the population*/
for (i = 0; i < tamPoblacion; i++)
poblacion[i].evalua(
datosTrain,
realTrain,
nominalTrain,
nulosTrain,
clasesTrain,
alfa,
kNeigh,
nClases,
distanceEu);
if (torneo) {
while (ev < nEval) {
newPob = new Cromosoma[2];
/*Binary tournament selection*/
comp1 = Randomize.Randint(0, tamPoblacion - 1);
do {
comp2 = Randomize.Randint(0, tamPoblacion - 1);
} while (comp2 == comp1);
if (poblacion[comp1].getCalidad() > poblacion[comp2].getCalidad()) sel1 = comp1;
else sel1 = comp2;
comp1 = Randomize.Randint(0, tamPoblacion - 1);
do {
comp2 = Randomize.Randint(0, tamPoblacion - 1);
} while (comp2 == comp1);
if (poblacion[comp1].getCalidad() > poblacion[comp2].getCalidad()) sel2 = comp1;
else sel2 = comp2;
if (Randomize.Rand() < pCruce) { // there is cross
crucePMX(poblacion, newPob, sel1, sel2);
} else { // there is not cross
newPob[0] = new Cromosoma(datosTrain.length, poblacion[sel1]);
newPob[1] = new Cromosoma(datosTrain.length, poblacion[sel2]);
}
/*Mutation of the cromosomes*/
for (i = 0; i < 2; i++) newPob[i].mutacion(pMutacion1to0, pMutacion0to1);
/*Evaluation of the population*/
for (i = 0; i < 2; i++)
if (!(newPob[i].estaEvaluado())) {
newPob[i].evalua(
datosTrain,
realTrain,
nominalTrain,
nulosTrain,
clasesTrain,
alfa,
kNeigh,
nClases,
distanceEu);
ev++;
}
/*Replace the two worst*/
Arrays.sort(poblacion);
poblacion[tamPoblacion - 2] = new Cromosoma(datosTrain.length, newPob[0]);
poblacion[tamPoblacion - 1] = new Cromosoma(datosTrain.length, newPob[1]);
}
} else {
/*Get the probabilities of lineal ranking in case of not use binary tournament*/
prob = new double[tamPoblacion];
for (i = 0; i < tamPoblacion; i++) {
aux = (double) (NUmax - NUmin) * ((double) i / (tamPoblacion - 1));
prob[i] = (double) (1.0 / (tamPoblacion)) * (NUmax - aux);
}
for (i = 1; i < tamPoblacion; i++) prob[i] = prob[i] + prob[i - 1];
while (ev < nEval) {
/*Sort the population by quality criterion*/
Arrays.sort(poblacion);
newPob = new Cromosoma[2];
pos1 = Randomize.Rand();
pos2 = Randomize.Rand();
for (j = 0; j < tamPoblacion && prob[j] < pos1; j++) ;
sel1 = j;
for (j = 0; j < tamPoblacion && prob[j] < pos2; j++) ;
sel2 = j;
if (Randomize.Rand() < pCruce) { // there is cross
crucePMX(poblacion, newPob, sel1, sel2);
} else { // there is not cross
newPob[0] = new Cromosoma(datosTrain.length, poblacion[sel1]);
newPob[1] = new Cromosoma(datosTrain.length, poblacion[sel2]);
}
/*Mutation of the cromosomes*/
for (i = 0; i < 2; i++) newPob[i].mutacion(pMutacion1to0, pMutacion0to1);
/*Evaluation of the population*/
for (i = 0; i < 2; i++)
if (!(newPob[i].estaEvaluado())) {
newPob[i].evalua(
datosTrain,
realTrain,
nominalTrain,
nulosTrain,
clasesTrain,
alfa,
kNeigh,
nClases,
distanceEu);
ev++;
}
/*Replace the two worst*/
poblacion[tamPoblacion - 2] = new Cromosoma(datosTrain.length, newPob[0]);
poblacion[tamPoblacion - 1] = new Cromosoma(datosTrain.length, newPob[1]);
}
}
nSel = poblacion[0].genesActivos();
/*Building of S set from the best cromosome obtained*/
conjS = new double[nSel][datosTrain[0].length];
conjR = new double[nSel][datosTrain[0].length];
conjN = new int[nSel][datosTrain[0].length];
conjM = new boolean[nSel][datosTrain[0].length];
clasesS = new int[nSel];
for (i = 0, l = 0; i < datosTrain.length; i++) {
if (poblacion[0].getGen(i)) { // the instance must be copied to the solution
for (j = 0; j < datosTrain[0].length; j++) {
conjS[l][j] = datosTrain[i][j];
conjR[l][j] = realTrain[i][j];
conjN[l][j] = nominalTrain[i][j];
conjM[l][j] = nulosTrain[i][j];
}
clasesS[l] = clasesTrain[i];
l++;
}
}
System.out.println(
"SGA " + relation + " " + (double) (System.currentTimeMillis() - tiempo) / 1000.0 + "s");
OutputIS.escribeSalida(
ficheroSalida[0], conjR, conjN, conjM, clasesS, entradas, salida, nEntradas, relation);
OutputIS.escribeSalida(ficheroSalida[1], test, entradas, salida, nEntradas, relation);
} // end-method
public void ejecutar() {
int i, j, l, m, o;
int nClases;
int claseObt;
boolean marcas[];
double conjS[][];
int clasesS[];
int eleS[], eleT[];
int bestAc, aciertos;
int temp[];
int pos, tmp;
long tiempo = System.currentTimeMillis();
/*Getting the number of different classes*/
nClases = 0;
for (i = 0; i < clasesTrain.length; i++) if (clasesTrain[i] > nClases) nClases = clasesTrain[i];
nClases++;
/*Inicialization of the flagged instance vector of the S set*/
marcas = new boolean[datosTrain.length];
for (i = 0; i < datosTrain.length; i++) marcas[i] = false;
/*Allocate memory for the random selection*/
m = (int) ((porcentaje * datosTrain.length) / 100.0);
eleS = new int[m];
eleT = new int[datosTrain.length - m];
temp = new int[datosTrain.length];
for (i = 0; i < datosTrain.length; i++) temp[i] = i;
/** Random distribution of elements in each set */
Randomize.setSeed(semilla);
for (i = 0; i < eleS.length; i++) {
pos = Randomize.Randint(i, datosTrain.length - 1);
tmp = temp[i];
temp[i] = temp[pos];
temp[pos] = tmp;
eleS[i] = temp[i];
}
for (i = 0; i < eleT.length; i++) {
pos = Randomize.Randint(m + i, datosTrain.length - 1);
tmp = temp[m + i];
temp[m + i] = temp[pos];
temp[pos] = tmp;
eleT[i] = temp[m + i];
}
for (i = 0; i < eleS.length; i++) marcas[eleS[i]] = true;
/*Building of the S set from the flags*/
conjS = new double[m][datosTrain[0].length];
clasesS = new int[m];
for (o = 0, l = 0; o < datosTrain.length; o++) {
if (marcas[o]) { // the instance will be evaluated
for (j = 0; j < datosTrain[0].length; j++) {
conjS[l][j] = datosTrain[o][j];
}
clasesS[l] = clasesTrain[o];
l++;
}
}
/*Evaluation of the S set*/
bestAc = 0;
for (i = 0; i < datosTrain.length; i++) {
claseObt = KNN.evaluacionKNN2(k, conjS, clasesS, datosTrain[i], nClases);
if (claseObt == clasesTrain[i]) // correct clasification
bestAc++;
}
/*Body of the ENNRS algorithm. Change the S set in each iteration for instances
of the T set until get a complete sustitution*/
for (i = 0; i < n; i++) {
/*Preparation the set to interchange*/
for (j = 0; j < eleS.length; j++) {
pos = Randomize.Randint(j, eleT.length - 1);
tmp = eleT[j];
eleT[j] = eleT[pos];
eleT[pos] = tmp;
}
/*Interchange of instances*/
for (j = 0; j < eleS.length; j++) {
tmp = eleS[j];
eleS[j] = eleT[j];
eleT[j] = tmp;
marcas[eleS[j]] = true;
marcas[eleT[j]] = false;
}
/*Building of the S set from the flags*/
for (o = 0, l = 0; o < datosTrain.length; o++) {
if (marcas[o]) { // the instance will evaluate
for (j = 0; j < datosTrain[0].length; j++) {
conjS[l][j] = datosTrain[o][j];
}
clasesS[l] = clasesTrain[o];
l++;
}
}
/*Evaluation of the S set*/
aciertos = 0;
for (j = 0; j < datosTrain.length; j++) {
claseObt = KNN.evaluacionKNN2(k, conjS, clasesS, datosTrain[j], nClases);
if (claseObt == clasesTrain[j]) // correct clasification
aciertos++;
}
if (aciertos > bestAc) { // keep S
bestAc = aciertos;
} else { // undo changes
for (j = 0; j < eleS.length; j++) {
tmp = eleS[j];
eleS[j] = eleT[j];
eleT[j] = tmp;
marcas[eleS[j]] = true;
marcas[eleT[j]] = false;
}
}
}
/*Building of the S set from the flags*/
/*Building of the S set from the flags*/
for (o = 0, l = 0; o < datosTrain.length; o++) {
if (marcas[o]) { // the instance will evaluate
for (j = 0; j < datosTrain[0].length; j++) {
conjS[l][j] = datosTrain[o][j];
}
clasesS[l] = clasesTrain[o];
l++;
}
}
System.out.println(
"ENNRS " + relation + " " + (double) (System.currentTimeMillis() - tiempo) / 1000.0 + "s");
// COn conjS me vale.
int trainRealClass[][];
int trainPrediction[][];
trainRealClass = new int[datosTrain.length][1];
trainPrediction = new int[datosTrain.length][1];
// Working on training
for (i = 0; i < datosTrain.length; i++) {
trainRealClass[i][0] = clasesTrain[i];
trainPrediction[i][0] = KNN.evaluate(datosTrain[i], conjS, nClases, clasesS, this.k);
}
KNN.writeOutput(ficheroSalida[0], trainRealClass, trainPrediction, entradas, salida, relation);
// Working on test
int realClass[][] = new int[datosTest.length][1];
int prediction[][] = new int[datosTest.length][1];
// Check time
for (i = 0; i < realClass.length; i++) {
realClass[i][0] = clasesTest[i];
prediction[i][0] = KNN.evaluate(datosTest[i], conjS, nClases, clasesS, this.k);
}
KNN.writeOutput(ficheroSalida[1], realClass, prediction, entradas, salida, relation);
}
/** Process the training and test files provided in the parameters file to the constructor. */
public void process() {
// declarations
double[] outputs;
double[] outputs2;
Instance neighbor;
double dist, mean;
int actual;
Randomize rnd = new Randomize();
Instance ex;
gCenter kmeans = null;
int iterations = 0;
double E;
double prevE;
int totalMissing = 0;
boolean allMissing = true;
rnd.setSeed(semilla);
// PROCESS
try {
// Load in memory a dataset that contains a classification problem
IS.readSet(input_train_name, true);
int in = 0;
int out = 0;
ndatos = IS.getNumInstances();
nvariables = Attributes.getNumAttributes();
nentradas = Attributes.getInputNumAttributes();
nsalidas = Attributes.getOutputNumAttributes();
X = new String[ndatos][nvariables]; // matrix with transformed data
kmeans = new gCenter(K, ndatos, nvariables);
timesSeen = new FreqList[nvariables];
mostCommon = new String[nvariables];
// first, we choose k 'means' randomly from all
// instances
totalMissing = 0;
for (int i = 0; i < ndatos; i++) {
Instance inst = IS.getInstance(i);
if (inst.existsAnyMissingValue()) totalMissing++;
}
if (totalMissing == ndatos) allMissing = true;
else allMissing = false;
for (int numMeans = 0; numMeans < K; numMeans++) {
do {
actual = (int) (ndatos * rnd.Rand());
ex = IS.getInstance(actual);
} while (ex.existsAnyMissingValue() && !allMissing);
kmeans.copyCenter(ex, numMeans);
}
// now, iterate adjusting clusters' centers and
// instances to them
prevE = 0;
iterations = 0;
do {
for (int i = 0; i < ndatos; i++) {
Instance inst = IS.getInstance(i);
kmeans.setClusterOf(inst, i);
}
// set new centers
kmeans.recalculateCenters(IS);
// compute RMSE
E = 0;
for (int i = 0; i < ndatos; i++) {
Instance inst = IS.getInstance(i);
E += kmeans.distance(inst, kmeans.getClusterOf(i));
}
iterations++;
// System.out.println(iterations+"\t"+E);
if (Math.abs(prevE - E) == 0) iterations = maxIter;
else prevE = E;
} while (E > minError && iterations < maxIter);
for (int i = 0; i < ndatos; i++) {
Instance inst = IS.getInstance(i);
in = 0;
out = 0;
for (int j = 0; j < nvariables; j++) {
Attribute a = Attributes.getAttribute(j);
direccion = a.getDirectionAttribute();
tipo = a.getType();
if (direccion == Attribute.INPUT) {
if (tipo != Attribute.NOMINAL && !inst.getInputMissingValues(in)) {
X[i][j] = new String(String.valueOf(inst.getInputRealValues(in)));
} else {
if (!inst.getInputMissingValues(in)) X[i][j] = inst.getInputNominalValues(in);
else {
actual = kmeans.getClusterOf(i);
X[i][j] = new String(kmeans.valueAt(actual, j));
}
}
in++;
} else {
if (direccion == Attribute.OUTPUT) {
if (tipo != Attribute.NOMINAL && !inst.getOutputMissingValues(out)) {
X[i][j] = new String(String.valueOf(inst.getOutputRealValues(out)));
} else {
if (!inst.getOutputMissingValues(out)) X[i][j] = inst.getOutputNominalValues(out);
else {
actual = kmeans.getClusterOf(i);
X[i][j] = new String(kmeans.valueAt(actual, j));
}
}
out++;
}
}
}
}
} catch (Exception e) {
System.out.println("Dataset exception = " + e);
e.printStackTrace();
System.exit(-1);
}
write_results(output_train_name);
/** ************************************************************************************ */
// does a test file associated exist?
if (input_train_name.compareTo(input_test_name) != 0) {
try {
// Load in memory a dataset that contains a classification problem
IStest.readSet(input_test_name, false);
int in = 0;
int out = 0;
ndatos = IStest.getNumInstances();
nvariables = Attributes.getNumAttributes();
nentradas = Attributes.getInputNumAttributes();
nsalidas = Attributes.getOutputNumAttributes();
for (int i = 0; i < ndatos; i++) {
Instance inst = IStest.getInstance(i);
in = 0;
out = 0;
for (int j = 0; j < nvariables; j++) {
Attribute a = Attributes.getAttribute(j);
direccion = a.getDirectionAttribute();
tipo = a.getType();
if (direccion == Attribute.INPUT) {
if (tipo != Attribute.NOMINAL && !inst.getInputMissingValues(in)) {
X[i][j] = new String(String.valueOf(inst.getInputRealValues(in)));
} else {
if (!inst.getInputMissingValues(in)) X[i][j] = inst.getInputNominalValues(in);
else {
actual = kmeans.getClusterOf(i);
X[i][j] = new String(kmeans.valueAt(actual, j));
}
}
in++;
} else {
if (direccion == Attribute.OUTPUT) {
if (tipo != Attribute.NOMINAL && !inst.getOutputMissingValues(out)) {
X[i][j] = new String(String.valueOf(inst.getOutputRealValues(out)));
} else {
if (!inst.getOutputMissingValues(out)) X[i][j] = inst.getOutputNominalValues(out);
else {
actual = kmeans.getClusterOf(i);
X[i][j] = new String(kmeans.valueAt(actual, j));
}
}
out++;
}
}
}
}
} catch (Exception e) {
System.out.println("Dataset exception = " + e);
e.printStackTrace();
System.exit(-1);
}
write_results(output_test_name);
}
}