protected int NN(int nSel, double conj[][], double ejemplo[]) {
double mindist, dist;
int nneigh = -1;
mindist = Double.POSITIVE_INFINITY;
for (int i = 0; i < nSel; i++) {
dist = KNN.distancia(conj[i], ejemplo);
if (dist < mindist) {
mindist = dist;
nneigh = i;
}
}
return nneigh;
}
int nextNeighbour(boolean marcas[], double datos[][], int ej, Vector<Integer> vecinos) {
int i, j, k;
int pos = -1;
double distmin = Double.POSITIVE_INFINITY;
double distancia;
double centroid[];
double prototipo[];
/*Computation of the previous centroid*/
centroid = new double[datos[0].length];
prototipo = new double[datos[0].length];
for (j = 0; j < datos[0].length; j++) {
centroid[j] = 0;
for (k = 0; k < vecinos.size(); k++) {
centroid[j] += datos[vecinos.elementAt(k).intValue()][j];
}
}
for (i = 0; i < datos.length; i++) {
if (marcas[i] && i != ej) {
for (j = 0; j < datos[0].length; j++) {
prototipo[j] = centroid[j] + datos[i][j];
prototipo[j] /= (vecinos.size() + 1);
}
distancia = KNN.distancia(datos[ej], prototipo);
if (distancia < distmin) {
distmin = distancia;
pos = i;
}
}
}
return pos;
}
/**
* 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);
}
/**
* Evaluates a chromosome
*
* @param datos Reference to the training set
* @param real Reference to the training set (real valued)
* @param nominal Reference to the training set (nominal valued)
* @param nulos Reference to the training set (null values)
* @param clases Output attribute of each instance
* @param alfa Alpha value of the fitness function
* @param kNeigh Number of neighbors for the KNN algorithm
* @param nClases Number of classes of the problem
* @param distanceEu True= Euclidean distance; False= HVDM
*/
public void evalua(
double datos[][],
double real[][],
int nominal[][],
boolean nulos[][],
int clases[],
double alfa,
int kNeigh,
int nClases,
boolean distanceEu) {
int i, j, l, m;
int aciertos = 0;
double M, s;
double conjS[][];
double conjR[][];
int conjN[][];
boolean conjM[][];
int clasesS[];
int vecinos[];
int claseObt;
int vecinoCercano;
double dist, minDist;
M = (double) datos.length;
s = (double) genesActivos();
if (kNeigh > 1) {
vecinos = new int[kNeigh];
conjS = new double[(int) s][datos[0].length];
conjR = new double[(int) s][datos[0].length];
conjN = new int[(int) s][datos[0].length];
conjM = new boolean[(int) s][datos[0].length];
clasesS = new int[(int) s];
for (j = 0, l = 0; j < datos.length; j++) {
if (cuerpo[j]) { // the instance must be copied to the solution
for (m = 0; m < datos[j].length; m++) {
conjS[l][m] = datos[j][m];
conjR[l][m] = real[j][m];
conjN[l][m] = nominal[j][m];
conjM[l][m] = nulos[j][m];
}
clasesS[l] = clases[j];
l++;
}
}
for (i = 0; i < datos.length; i++) {
claseObt =
KNN.evaluacionKNN2(
kNeigh,
conjS,
conjR,
conjN,
conjM,
clasesS,
datos[i],
real[i],
nominal[i],
nulos[i],
nClases,
distanceEu,
vecinos);
if (claseObt >= 0) if (clases[i] == claseObt) aciertos++;
}
} else {
for (i = 0; i < datos.length; i++) {
vecinoCercano = -1;
minDist = Double.POSITIVE_INFINITY;
for (j = 0; j < datos.length; j++) {
if (cuerpo[j]) { // It is in S
dist =
KNN.distancia(
datos[i],
real[i],
nominal[i],
nulos[i],
datos[j],
real[j],
nominal[j],
nulos[j],
distanceEu);
if (dist < minDist && dist != 0) {
minDist = dist;
vecinoCercano = j;
}
}
}
if (vecinoCercano >= 0) if (clases[i] == clases[vecinoCercano]) aciertos++;
}
}
calidad = ((double) (aciertos) / M) * alfa * 100.0;
calidad += ((1.0 - alfa) * 100.0 * (M - s) / M);
cruzado = false;
} // end-method
