/** Creates the total selector's set for get all the possible rules */
private Complejo hazSelectores(Dataset train) {
Complejo almacenSelectores;
int nClases = train.getnclases();
almacenSelectores =
new Complejo(nClases); // Aqui voy a almacenar los selectores (numVariable,operador,valor)
Attribute[] atributos = null;
int num_atributos, type;
Vector nominalValues;
atributos = Attributes.getAttributes();
num_atributos = Attributes.getNumAttributes();
Selector s;
for (int i = 0; i < train.getnentradas(); i++) {
type = atributos[i].getType();
switch (type) {
case 0: // NOMINAL
nominalValues = atributos[i].getNominalValuesList();
// System.out.print("{");
for (int j = 0; j < nominalValues.size(); j++) {
// System.out.print ((String)nominalValues.elementAt(j)+" ");
s = new Selector(i, 0, (String) nominalValues.elementAt(j), true); // [atr,op,valor]
// incluimos tb los valores en double para facilitar algunas funciones
s.setValor((double) j);
almacenSelectores.addSelector(s);
// s.print();
}
// System.out.println("}");
break;
}
// System.out.println(num_atributos);
}
return almacenSelectores;
}
/**
* Checks if a node is legitimate. A node is illegitimate if its hamming distance to a pruned node
* is 1 (this is, the node is a child of a previously pruned node).
*
* @param f node to check its legitimacy
* @return true if the node is legitimate, false otherwise.
*/
private boolean legitimate(boolean f[]) {
boolean feas = true;
for (int i = 0; i < pruned.size() && feas; i++) {
if (hamming(pruned.elementAt(i), f) == 1) feas = false;
}
return feas;
}
/**
* Joins two vectors
*
* @param a First vector
* @param b Second vector
* @return The joint of both vectors
*/
public static Vector<Integer> unionVectores(Vector<Integer> a, Vector<Integer> b) {
int i;
for (i = 0; i < b.size(); i++) {
if (a.contains(new Integer((Integer) (b.elementAt(i)))) == false) {
a.addElement(b.elementAt(i));
}
}
return a;
} // end-method
private String classificationOutput(
myDataset dataset,
int ex,
int data[][],
int classData[],
int infoAttr[],
Vector<Rule> contenedor,
int nClases) {
int j, k, l;
boolean match;
double tmp1, tmp2;
int pos = 0, classPredicted;
double Waip;
int ejemplo[] = new int[data[0].length];
for (j = 0; j < ejemplo.length; j++) {
if (dataset.isMissing(ex, j)) ejemplo[j] = -1;
else ejemplo[j] = dataset.valueExample(ex, j);
}
classPredicted = -1;
Waip = 0;
/*Search a match of the example (following by the container)*/
for (j = contenedor.size() - 1; j >= 0; j--) {
match = true;
for (k = 0; k < contenedor.elementAt(j).getRule().length && match; k++) {
if (ejemplo[contenedor.elementAt(j).getiCondition(k).getAttribute()]
!= contenedor.elementAt(j).getiCondition(k).getValue()) {
match = false;
}
}
if (match) {
tmp1 = Double.NEGATIVE_INFINITY;
for (l = 0; l < nClases; l++) {
tmp2 = 0;
for (k = 0; k < contenedor.elementAt(j).getRule().length; k++) {
tmp2 +=
RuleSet.computeWeightEvidence(
data, classData, contenedor.elementAt(j).getiCondition(k), l, infoAttr);
}
if (tmp2 > tmp1) {
tmp1 = tmp2;
pos = l;
}
}
if (tmp1 > Waip) {
classPredicted = pos;
Waip = tmp1;
}
}
}
if (classPredicted == -1) return "Unclassified";
return dataset.getOutputValue(classPredicted);
}
/** Recursive method for ABB */
private void abb(boolean feat[]) {
boolean[] child;
double measure;
threshold = data.measureIEP(feat);
for (int i = 0; i < cardinalidadCto(feat); i++) {
child = removeOne(feat, i);
measure = data.measureIEP(child);
if (legitimate(child) && measure < threshold) {
if (measure < data.measureIEP(features)) {
// we keep the best found in 'features'
System.arraycopy(child, 0, features, 0, child.length);
}
abb(child);
} else { // we prune this node
pruned.add(child);
}
}
}
/**
* Computes the trueHShaffer distribution from a given parameter.
*
* @param k K parameter
* @param n M value
* @return The trueHShaffer distribution
*/
public static Vector<Integer> trueHShaffer(int k) {
Vector<Integer> number;
int j;
Vector<Integer> tmp, tmp2;
int p;
number = new Vector<Integer>();
tmp = new Vector<Integer>();
if (k <= 1) {
number.addElement(new Integer(0));
} else {
for (j = 1; j <= k; j++) {
tmp = trueHShaffer(k - j);
tmp2 = new Vector<Integer>();
for (p = 0; p < tmp.size(); p++) {
tmp2.addElement(((Integer) (tmp.elementAt(p))).intValue() + (int) combinatoria(2, j));
}
number = unionVectores(number, tmp2);
}
}
return number;
} // end-method
/**
* Obtain all exhaustive comparisons possible from an array of indexes
*
* @param indices A verctos of indexes.
* @return A vector with vectors containing all the possible relations between the indexes
*/
@SuppressWarnings("unchecked")
public static Vector<Vector<Relation>> obtainExhaustive(Vector<Integer> indices) {
Vector<Vector<Relation>> result = new Vector<Vector<Relation>>();
int i, j, k;
String binario;
boolean[] number = new boolean[indices.size()];
Vector<Integer> ind1, ind2;
Vector<Relation> set = new Vector<Relation>();
Vector<Vector<Relation>> res1, res2;
Vector<Relation> temp;
Vector<Relation> temp2;
Vector<Relation> temp3;
ind1 = new Vector<Integer>();
ind2 = new Vector<Integer>();
temp = new Vector<Relation>();
temp2 = new Vector<Relation>();
temp3 = new Vector<Relation>();
for (i = 0; i < indices.size(); i++) {
for (j = i + 1; j < indices.size(); j++) {
set.addElement(
new Relation(
((Integer) indices.elementAt(i)).intValue(),
((Integer) indices.elementAt(j)).intValue()));
}
}
if (set.size() > 0) result.addElement(set);
for (i = 1; i < (int) (Math.pow(2, indices.size() - 1)); i++) {
Arrays.fill(number, false);
ind1.removeAllElements();
ind2.removeAllElements();
temp.removeAllElements();
temp2.removeAllElements();
temp3.removeAllElements();
binario = Integer.toString(i, 2);
for (k = 0; k < number.length - binario.length(); k++) {
number[k] = false;
}
for (j = 0; j < binario.length(); j++, k++) {
if (binario.charAt(j) == '1') number[k] = true;
}
for (j = 0; j < number.length; j++) {
if (number[j] == true) {
ind1.addElement(new Integer(((Integer) indices.elementAt(j)).intValue()));
} else {
ind2.addElement(new Integer(((Integer) indices.elementAt(j)).intValue()));
}
}
res1 = obtainExhaustive(ind1);
res2 = obtainExhaustive(ind2);
for (j = 0; j < res1.size(); j++) {
result.addElement(new Vector<Relation>((Vector<Relation>) res1.elementAt(j)));
}
for (j = 0; j < res2.size(); j++) {
result.addElement(new Vector<Relation>((Vector<Relation>) res2.elementAt(j)));
}
for (j = 0; j < res1.size(); j++) {
temp = (Vector<Relation>) ((Vector<Relation>) res1.elementAt(j)).clone();
for (k = 0; k < res2.size(); k++) {
temp2 = (Vector<Relation>) temp.clone();
temp3 = (Vector<Relation>) ((Vector<Relation>) res2.elementAt(k)).clone();
if (((Relation) temp2.elementAt(0)).i < ((Relation) temp3.elementAt(0)).i) {
temp2.addAll((Vector<Relation>) temp3);
result.addElement(new Vector<Relation>(temp2));
} else {
temp3.addAll((Vector<Relation>) temp2);
result.addElement(new Vector<Relation>(temp3));
}
}
}
}
for (i = 0; i < result.size(); i++) {
if (((Vector<Relation>) result.elementAt(i)).toString().equalsIgnoreCase("[]")) {
result.removeElementAt(i);
i--;
}
}
for (i = 0; i < result.size(); i++) {
for (j = i + 1; j < result.size(); j++) {
if (((Vector<Relation>) result.elementAt(i))
.toString()
.equalsIgnoreCase(((Vector<Relation>) result.elementAt(j)).toString())) {
result.removeElementAt(j);
j--;
}
}
}
return result;
} // end-method
/**
* This method runs the multiple comparison tests
*
* @param code A value to codify which post-hoc methods apply
* @param results Array with the results of the methods
* @param algorithmName Array with the name of the methods employed
* @return A string with the contents of the test in LaTeX format
*/
private static String runMultiple(double[][] results, String algorithmName[]) {
int i, j, k;
int posicion;
double mean[][];
MultiplePair orden[][];
MultiplePair rank[][];
boolean encontrado;
int ig;
double sum;
boolean visto[];
Vector<Integer> porVisitar;
double Rj[];
double friedman;
double sumatoria = 0;
double termino1, termino2, termino3;
double iman;
boolean vistos[];
int pos, tmp, counter;
String cad;
double maxVal;
double Pi[];
double ALPHAiHolm[];
double ALPHAiShaffer[];
String ordenAlgoritmos[];
double ordenRankings[];
int order[];
double adjustedP[][];
double SE;
boolean parar;
Vector<Integer> indices = new Vector<Integer>();
Vector<Vector<Relation>> exhaustiveI = new Vector<Vector<Relation>>();
boolean[][] cuadro;
double minPi, tmpPi, maxAPi, tmpAPi;
Relation[] parejitas;
Vector<Integer> T;
int Tarray[];
DecimalFormat nf4 = (DecimalFormat) DecimalFormat.getInstance();
nf4.setMaximumFractionDigits(4);
nf4.setMinimumFractionDigits(0);
DecimalFormatSymbols dfs = nf4.getDecimalFormatSymbols();
dfs.setDecimalSeparator('.');
nf4.setDecimalFormatSymbols(dfs);
DecimalFormat nf6 = (DecimalFormat) DecimalFormat.getInstance();
nf6.setMaximumFractionDigits(6);
nf6.setMinimumFractionDigits(0);
nf6.setDecimalFormatSymbols(dfs);
String out = "";
int nDatasets = Configuration.getNDatasets();
Iman = Configuration.isIman();
Nemenyi = Configuration.isNemenyi();
Bonferroni = Configuration.isBonferroni();
Holm = Configuration.isHolm();
Hoch = Configuration.isHochberg();
Hommel = Configuration.isHommel();
Scha = Configuration.isShaffer();
Berg = Configuration.isBergman();
mean = new double[nDatasets][algorithmName.length];
// Maximize performance
if (Configuration.getObjective() == 1) {
/*Compute the average performance per algorithm for each data set*/
for (i = 0; i < nDatasets; i++) {
for (j = 0; j < algorithmName.length; j++) {
mean[i][j] = results[j][i];
}
}
}
// Minimize performance
else {
double maxValue = Double.MIN_VALUE;
/*Compute the average performance per algorithm for each data set*/
for (i = 0; i < nDatasets; i++) {
for (j = 0; j < algorithmName.length; j++) {
if (results[j][i] > maxValue) {
maxValue = results[j][i];
}
mean[i][j] = (-1.0 * results[j][i]);
}
}
for (i = 0; i < nDatasets; i++) {
for (j = 0; j < algorithmName.length; j++) {
mean[i][j] += maxValue;
}
}
}
/*We use the pareja structure to compute and order rankings*/
orden = new MultiplePair[nDatasets][algorithmName.length];
for (i = 0; i < nDatasets; i++) {
for (j = 0; j < algorithmName.length; j++) {
orden[i][j] = new MultiplePair(j, mean[i][j]);
}
Arrays.sort(orden[i]);
}
/*building of the rankings table per algorithms and data sets*/
rank = new MultiplePair[nDatasets][algorithmName.length];
posicion = 0;
for (i = 0; i < nDatasets; i++) {
for (j = 0; j < algorithmName.length; j++) {
encontrado = false;
for (k = 0; k < algorithmName.length && !encontrado; k++) {
if (orden[i][k].indice == j) {
encontrado = true;
posicion = k + 1;
}
}
rank[i][j] = new MultiplePair(posicion, orden[i][posicion - 1].valor);
}
}
/*In the case of having the same performance, the rankings are equal*/
for (i = 0; i < nDatasets; i++) {
visto = new boolean[algorithmName.length];
porVisitar = new Vector<Integer>();
Arrays.fill(visto, false);
for (j = 0; j < algorithmName.length; j++) {
porVisitar.removeAllElements();
sum = rank[i][j].indice;
visto[j] = true;
ig = 1;
for (k = j + 1; k < algorithmName.length; k++) {
if (rank[i][j].valor == rank[i][k].valor && !visto[k]) {
sum += rank[i][k].indice;
ig++;
porVisitar.add(new Integer(k));
visto[k] = true;
}
}
sum /= (double) ig;
rank[i][j].indice = sum;
for (k = 0; k < porVisitar.size(); k++) {
rank[i][((Integer) porVisitar.elementAt(k)).intValue()].indice = sum;
}
}
}
/*compute the average ranking for each algorithm*/
Rj = new double[algorithmName.length];
for (i = 0; i < algorithmName.length; i++) {
Rj[i] = 0;
for (j = 0; j < nDatasets; j++) {
Rj[i] += rank[j][i].indice / ((double) nDatasets);
}
}
/*Print the average ranking per algorithm*/
out += "\n\nAverage ranks obtained by applying the Friedman procedure\n\n";
out +=
"\\begin{table}[!htp]\n"
+ "\\centering\n"
+ "\\begin{tabular}{|c|c|}\\hline\n"
+ "Algorithm&Ranking\\\\\\hline\n";
for (i = 0; i < algorithmName.length; i++) {
out += (String) algorithmName[i] + " & " + nf4.format(Rj[i]) + "\\\\\n";
}
out += "\\hline\n\\end{tabular}\n\\caption{Average Rankings of the algorithms}\n\\end{table}";
/*Compute the Friedman statistic*/
termino1 =
(12 * (double) nDatasets)
/ ((double) algorithmName.length * ((double) algorithmName.length + 1));
termino2 =
(double) algorithmName.length
* ((double) algorithmName.length + 1)
* ((double) algorithmName.length + 1)
/ (4.0);
for (i = 0; i < algorithmName.length; i++) {
sumatoria += Rj[i] * Rj[i];
}
friedman = (sumatoria - termino2) * termino1;
out +=
"\n\nFriedman statistic considering reduction performance (distributed according to chi-square with "
+ (algorithmName.length - 1)
+ " degrees of freedom: "
+ nf6.format(friedman)
+ ".\n\n";
double pFriedman;
pFriedman = ChiSq(friedman, (algorithmName.length - 1));
System.out.print("P-value computed by Friedman Test: " + pFriedman + ".\\newline\n\n");
/*Compute the Iman-Davenport statistic*/
if (Iman) {
iman = ((nDatasets - 1) * friedman) / (nDatasets * (algorithmName.length - 1) - friedman);
out +=
"Iman and Davenport statistic considering reduction performance (distributed according to F-distribution with "
+ (algorithmName.length - 1)
+ " and "
+ (algorithmName.length - 1) * (nDatasets - 1)
+ " degrees of freedom: "
+ nf6.format(iman)
+ ".\n\n";
double pIman;
pIman = FishF(iman, (algorithmName.length - 1), (algorithmName.length - 1) * (nDatasets - 1));
System.out.print("P-value computed by Iman and Daveport Test: " + pIman + ".\\newline\n\n");
}
termino3 =
Math.sqrt(
(double) algorithmName.length
* ((double) algorithmName.length + 1)
/ (6.0 * (double) nDatasets));
out += "\n\n\\pagebreak\n\n";
/** ********** NxN COMPARISON ************* */
out += "\\section{Post hoc comparisons}";
out +=
"\n\nResults achieved on post hoc comparisons for $\\alpha = 0.05$, $\\alpha = 0.10$ and adjusted p-values.\n\n";
/*Compute the unadjusted p_i value for each comparison alpha=0.05*/
Pi = new double[(int) combinatoria(2, algorithmName.length)];
ALPHAiHolm = new double[(int) combinatoria(2, algorithmName.length)];
ALPHAiShaffer = new double[(int) combinatoria(2, algorithmName.length)];
ordenAlgoritmos = new String[(int) combinatoria(2, algorithmName.length)];
ordenRankings = new double[(int) combinatoria(2, algorithmName.length)];
order = new int[(int) combinatoria(2, algorithmName.length)];
parejitas = new Relation[(int) combinatoria(2, algorithmName.length)];
T = new Vector<Integer>();
T = trueHShaffer(algorithmName.length);
Tarray = new int[T.size()];
for (i = 0; i < T.size(); i++) {
Tarray[i] = ((Integer) T.elementAt(i)).intValue();
}
Arrays.sort(Tarray);
SE = termino3;
vistos = new boolean[(int) combinatoria(2, algorithmName.length)];
for (i = 0, k = 0; i < algorithmName.length; i++) {
for (j = i + 1; j < algorithmName.length; j++, k++) {
ordenRankings[k] = Math.abs(Rj[i] - Rj[j]);
ordenAlgoritmos[k] = (String) algorithmName[i] + " vs. " + (String) algorithmName[j];
parejitas[k] = new Relation(i, j);
}
}
Arrays.fill(vistos, false);
for (i = 0; i < ordenRankings.length; i++) {
for (j = 0; vistos[j] == true; j++) ;
pos = j;
maxVal = ordenRankings[j];
for (j = j + 1; j < ordenRankings.length; j++) {
if (vistos[j] == false && ordenRankings[j] > maxVal) {
pos = j;
maxVal = ordenRankings[j];
}
}
vistos[pos] = true;
order[i] = pos;
}
/*Computing the logically related hypotheses tests (Shaffer and Bergmann-Hommel)*/
pos = 0;
tmp = Tarray.length - 1;
for (i = 0; i < order.length; i++) {
Pi[i] = 2 * CDF_Normal.normp((-1) * Math.abs((ordenRankings[order[i]]) / SE));
ALPHAiHolm[i] = 0.05 / ((double) order.length - (double) i);
ALPHAiShaffer[i] = 0.05 / ((double) order.length - (double) Math.max(pos, i));
if (i == pos && Pi[i] <= ALPHAiShaffer[i]) {
tmp--;
pos = (int) combinatoria(2, algorithmName.length) - Tarray[tmp];
}
}
out += "\\subsection{P-values for $\\alpha=0.05$}\n\n";
int count = 4;
if (Holm) {
count++;
}
if (Scha) {
count++;
}
out +=
"\\begin{table}[!htp]\n\\centering\\scriptsize\n"
+ "\\begin{tabular}{"
+ printC(count)
+ "}\n"
+ "$i$&algorithms&$z=(R_0 - R_i)/SE$&$p$";
if (Holm) {
out += "&Holm";
}
if (Scha) {
out += "&Shaffer";
}
out += "\\\\\n\\hline";
for (i = 0; i < order.length; i++) {
out +=
(order.length - i)
+ "&"
+ ordenAlgoritmos[order[i]]
+ "&"
+ nf6.format(Math.abs((ordenRankings[order[i]]) / SE))
+ "&"
+ nf6.format(Pi[i]);
if (Holm) {
out += "&" + nf6.format(ALPHAiHolm[i]);
}
if (Scha) {
out += "&" + nf6.format(ALPHAiShaffer[i]);
}
out += "\\\\\n";
}
out +=
"\\hline\n"
+ "\\end{tabular}\n\\caption{P-values Table for $\\alpha=0.05$}\n"
+ "\\end{table}";
/*Compute the rejected hipotheses for each test*/
if (Nemenyi) {
out +=
"Nemenyi's procedure rejects those hypotheses that have a p-value $\\le"
+ nf6.format(0.05 / (double) (order.length))
+ "$.\n\n";
}
if (Holm) {
parar = false;
for (i = 0; i < order.length && !parar; i++) {
if (Pi[i] > ALPHAiHolm[i]) {
out +=
"Holm's procedure rejects those hypotheses that have a p-value $\\le"
+ nf6.format(ALPHAiHolm[i])
+ "$.\n\n";
parar = true;
}
}
}
if (Scha) {
parar = false;
for (i = 0; i < order.length && !parar; i++) {
if (Pi[i] <= ALPHAiShaffer[i]) {
out +=
"Shaffer's procedure rejects those hypotheses that have a p-value $\\le"
+ nf6.format(ALPHAiShaffer[i])
+ "$.\n\n";
parar = true;
}
}
}
/*For Bergmann-Hommel's procedure, 9 algorithms could suppose intense computation*/
if (algorithmName.length <= MAX_ALGORITHMS) {
for (i = 0; i < algorithmName.length; i++) {
indices.add(new Integer(i));
}
exhaustiveI = obtainExhaustive(indices);
cuadro = new boolean[algorithmName.length][algorithmName.length];
for (i = 0; i < algorithmName.length; i++) {
Arrays.fill(cuadro[i], false);
}
for (i = 0; i < exhaustiveI.size(); i++) {
minPi =
2
* CDF_Normal.normp(
(-1)
* Math.abs(
Rj[
((Relation)
((Vector<Relation>) exhaustiveI.elementAt(i))
.elementAt(0))
.i]
- Rj[
((Relation)
((Vector<Relation>) exhaustiveI.elementAt(i))
.elementAt(0))
.j])
/ SE);
for (j = 1; j < ((Vector<Relation>) exhaustiveI.elementAt(i)).size(); j++) {
tmpPi =
2
* CDF_Normal.normp(
(-1)
* Math.abs(
Rj[
((Relation)
((Vector<Relation>) exhaustiveI.elementAt(i))
.elementAt(j))
.i]
- Rj[
((Relation)
((Vector<Relation>) exhaustiveI.elementAt(i))
.elementAt(j))
.j])
/ SE);
if (tmpPi < minPi) {
minPi = tmpPi;
}
}
if (minPi > (0.05 / ((double) ((Vector<Relation>) exhaustiveI.elementAt(i)).size()))) {
for (j = 0; j < ((Vector<Relation>) exhaustiveI.elementAt(i)).size(); j++) {
cuadro[((Relation) ((Vector<Relation>) exhaustiveI.elementAt(i)).elementAt(j)).i][
((Relation) ((Vector<Relation>) exhaustiveI.elementAt(i)).elementAt(j)).j] =
true;
}
}
}
if (Berg) {
cad = "";
cad += "Bergmann's procedure rejects these hypotheses:\n\n";
cad += "\\begin{itemize}\n\n";
counter = 0;
for (i = 0; i < cuadro.length; i++) {
for (j = i + 1; j < cuadro.length; j++) {
if (cuadro[i][j] == false) {
cad += "\\item " + algorithmName[i] + " vs. " + algorithmName[j] + "\n\n";
counter++;
}
}
}
cad += "\\end{itemize}\n\n";
if (counter > 0) {
out += cad;
} else {
out += "Bergmann's procedure does not reject any hypotheses.\n\n";
}
}
}
out += "\\pagebreak\n\n";
out += "\\subsection{P-values for $\\alpha=0.10$}\n\n";
/*Compute the unadjusted p_i value for each comparison alpha=0.10*/
Pi = new double[(int) combinatoria(2, algorithmName.length)];
ALPHAiHolm = new double[(int) combinatoria(2, algorithmName.length)];
ALPHAiShaffer = new double[(int) combinatoria(2, algorithmName.length)];
ordenAlgoritmos = new String[(int) combinatoria(2, algorithmName.length)];
ordenRankings = new double[(int) combinatoria(2, algorithmName.length)];
order = new int[(int) combinatoria(2, algorithmName.length)];
SE = termino3;
vistos = new boolean[(int) combinatoria(2, algorithmName.length)];
for (i = 0, k = 0; i < algorithmName.length; i++) {
for (j = i + 1; j < algorithmName.length; j++, k++) {
ordenRankings[k] = Math.abs(Rj[i] - Rj[j]);
ordenAlgoritmos[k] = (String) algorithmName[i] + " vs. " + (String) algorithmName[j];
}
}
Arrays.fill(vistos, false);
for (i = 0; i < ordenRankings.length; i++) {
for (j = 0; vistos[j] == true; j++) ;
pos = j;
maxVal = ordenRankings[j];
for (j = j + 1; j < ordenRankings.length; j++) {
if (vistos[j] == false && ordenRankings[j] > maxVal) {
pos = j;
maxVal = ordenRankings[j];
}
}
vistos[pos] = true;
order[i] = pos;
}
/*Computing the logically related hypotheses tests (Shaffer and Bergmann-Hommel)*/
pos = 0;
tmp = Tarray.length - 1;
for (i = 0; i < order.length; i++) {
Pi[i] = 2 * CDF_Normal.normp((-1) * Math.abs((ordenRankings[order[i]]) / SE));
ALPHAiHolm[i] = 0.1 / ((double) order.length - (double) i);
ALPHAiShaffer[i] = 0.1 / ((double) order.length - (double) Math.max(pos, i));
if (i == pos && Pi[i] <= ALPHAiShaffer[i]) {
tmp--;
pos = (int) combinatoria(2, algorithmName.length) - Tarray[tmp];
}
}
count = 4;
if (Holm) {
count++;
}
if (Scha) {
count++;
}
out +=
"\\begin{table}[!htp]\n\\centering\\scriptsize\n"
+ "\\begin{tabular}{"
+ printC(count)
+ "}\n"
+ "$i$&algorithms&$z=(R_0 - R_i)/SE$&$p$";
if (Holm) {
out += "&Holm";
}
if (Scha) {
out += "&Shaffer";
}
out += "\\\\\n\\hline";
for (i = 0; i < order.length; i++) {
out +=
(order.length - i)
+ "&"
+ ordenAlgoritmos[order[i]]
+ "&"
+ nf6.format(Math.abs((ordenRankings[order[i]]) / SE))
+ "&"
+ nf6.format(Pi[i]);
if (Holm) {
out += "&" + nf6.format(ALPHAiHolm[i]);
}
if (Scha) {
out += "&" + nf6.format(ALPHAiShaffer[i]);
}
out += "\\\\\n";
}
out +=
"\\hline\n"
+ "\\end{tabular}\n\\caption{P-values Table for $\\alpha=0.10$}\n"
+ "\\end{table}";
/*Compute the rejected hipotheses for each test*/
if (Nemenyi) {
out +=
"Nemenyi's procedure rejects those hypotheses that have a p-value $\\le"
+ nf6.format(0.10 / (double) (order.length))
+ "$.\n\n";
}
if (Holm) {
parar = false;
for (i = 0; i < order.length && !parar; i++) {
if (Pi[i] > ALPHAiHolm[i]) {
out +=
"Holm's procedure rejects those hypotheses that have a p-value $\\le"
+ nf6.format(ALPHAiHolm[i])
+ "$.\n\n";
parar = true;
}
}
}
if (Scha) {
parar = false;
for (i = 0; i < order.length && !parar; i++) {
if (Pi[i] <= ALPHAiShaffer[i]) {
out +=
"Shaffer's procedure rejects those hypotheses that have a p-value $\\le"
+ nf6.format(ALPHAiShaffer[i])
+ "$.\n\n";
parar = true;
}
}
}
/*For Bergmann-Hommel's procedure, 9 algorithms could suppose intense computation*/
if (algorithmName.length <= MAX_ALGORITHMS) {
indices.removeAllElements();
for (i = 0; i < algorithmName.length; i++) {
indices.add(new Integer(i));
}
exhaustiveI = obtainExhaustive(indices);
cuadro = new boolean[algorithmName.length][algorithmName.length];
for (i = 0; i < algorithmName.length; i++) {
Arrays.fill(cuadro[i], false);
}
for (i = 0; i < exhaustiveI.size(); i++) {
minPi =
2
* CDF_Normal.normp(
(-1)
* Math.abs(
Rj[
((Relation)
((Vector<Relation>) exhaustiveI.elementAt(i))
.elementAt(0))
.i]
- Rj[
((Relation)
((Vector<Relation>) exhaustiveI.elementAt(i))
.elementAt(0))
.j])
/ SE);
for (j = 1; j < ((Vector<Relation>) exhaustiveI.elementAt(i)).size(); j++) {
tmpPi =
2
* CDF_Normal.normp(
(-1)
* Math.abs(
Rj[
((Relation)
((Vector<Relation>) exhaustiveI.elementAt(i))
.elementAt(j))
.i]
- Rj[
((Relation)
((Vector<Relation>) exhaustiveI.elementAt(i))
.elementAt(j))
.j])
/ SE);
if (tmpPi < minPi) {
minPi = tmpPi;
}
}
if (minPi > 0.1 / ((double) ((Vector<Relation>) exhaustiveI.elementAt(i)).size())) {
for (j = 0; j < ((Vector<Relation>) exhaustiveI.elementAt(i)).size(); j++) {
cuadro[((Relation) ((Vector<Relation>) exhaustiveI.elementAt(i)).elementAt(j)).i][
((Relation) ((Vector<Relation>) exhaustiveI.elementAt(i)).elementAt(j)).j] =
true;
}
}
}
if (Berg) {
cad = "";
cad += "Bergmann's procedure rejects these hypotheses:\n\n";
cad += "\\begin{itemize}\n\n";
counter = 0;
for (i = 0; i < cuadro.length; i++) {
for (j = i + 1; j < cuadro.length; j++) {
if (cuadro[i][j] == false) {
cad += "\\item " + algorithmName[i] + " vs. " + algorithmName[j] + "\n\n";
counter++;
}
}
}
cad += "\\end{itemize}\n\n";
if (counter > 0) {
out += cad;
} else {
out += "Bergmann's procedure does not reject any hypotheses.\n\n";
}
}
}
out += "\\pagebreak\n\n";
/** ********** ADJUSTED P-VALUES NxN COMPARISON ************* */
out += "\\subsection{Adjusted p-values}\n\n";
adjustedP = new double[Pi.length][4];
pos = 0;
tmp = Tarray.length - 1;
for (i = 0; i < adjustedP.length; i++) {
adjustedP[i][0] = Pi[i] * (double) (adjustedP.length);
adjustedP[i][1] = Pi[i] * (double) (adjustedP.length - i);
adjustedP[i][2] = Pi[i] * ((double) adjustedP.length - (double) Math.max(pos, i));
if (i == pos) {
tmp--;
pos = (int) combinatoria(2, algorithmName.length) - Tarray[tmp];
}
if (algorithmName.length <= MAX_ALGORITHMS) {
maxAPi = Double.MIN_VALUE;
minPi = Double.MAX_VALUE;
for (j = 0; j < exhaustiveI.size(); j++) {
if (exhaustiveI.elementAt(j).toString().contains(parejitas[order[i]].toString())) {
minPi =
2
* CDF_Normal.normp(
(-1)
* Math.abs(
Rj[
((Relation)
((Vector<Relation>) exhaustiveI.elementAt(j))
.elementAt(0))
.i]
- Rj[
((Relation)
((Vector<Relation>) exhaustiveI.elementAt(j))
.elementAt(0))
.j])
/ SE);
for (k = 1; k < ((Vector<Relation>) exhaustiveI.elementAt(j)).size(); k++) {
tmpPi =
2
* CDF_Normal.normp(
(-1)
* Math.abs(
Rj[
((Relation)
((Vector<Relation>) exhaustiveI.elementAt(j))
.elementAt(k))
.i]
- Rj[
((Relation)
((Vector<Relation>) exhaustiveI.elementAt(j))
.elementAt(k))
.j])
/ SE);
if (tmpPi < minPi) {
minPi = tmpPi;
}
}
tmpAPi = minPi * (double) (((Vector<Relation>) exhaustiveI.elementAt(j)).size());
if (tmpAPi > maxAPi) {
maxAPi = tmpAPi;
}
}
}
adjustedP[i][3] = maxAPi;
}
}
for (i = 1; i < adjustedP.length; i++) {
if (adjustedP[i][1] < adjustedP[i - 1][1]) adjustedP[i][1] = adjustedP[i - 1][1];
if (adjustedP[i][2] < adjustedP[i - 1][2]) adjustedP[i][2] = adjustedP[i - 1][2];
if (adjustedP[i][3] < adjustedP[i - 1][3]) adjustedP[i][3] = adjustedP[i - 1][3];
}
count = 3;
if (Nemenyi) {
count++;
}
if (Holm) {
count++;
}
if (Scha) {
count++;
}
if (Berg) {
count++;
}
out +=
"\\begin{table}[!htp]\n\\centering\\scriptsize\n"
+ "\\begin{tabular}{"
+ printC(count)
+ "}\n"
+ "i&hypothesis&unadjusted $p$";
if (Nemenyi) {
out += "&$p_{Neme}$";
}
if (Holm) {
out += "&$p_{Holm}$";
}
if (Scha) {
out += "&$p_{Shaf}$";
}
if (Berg) {
out += "&$p_{Berg}$";
}
out += "\\\\\n\\hline";
for (i = 0; i < Pi.length; i++) {
out +=
(i + 1)
+ "&"
+ algorithmName[parejitas[order[i]].i]
+ " vs ."
+ algorithmName[parejitas[order[i]].j]
+ "&"
+ nf6.format(Pi[i]);
if (Nemenyi) {
out += "&" + nf6.format(adjustedP[i][0]);
}
if (Holm) {
out += "&" + nf6.format(adjustedP[i][1]);
}
if (Scha) {
out += "&" + nf6.format(adjustedP[i][2]);
}
if (Berg) {
out += "&" + nf6.format(adjustedP[i][3]);
}
out += "\\\\\n";
}
out += "\\hline\n" + "\\end{tabular}\n\\caption{Adjusted $p$-values}\n" + "\\end{table}\n\n";
out += "\\end{landscape}\n\\end{document}";
return out;
} // end-method
/** It launches the algorithm */
public void execute() {
int i, j, k, l;
int t;
int ele;
double prob[];
double aux;
double NUmax = 1.5; // used for lineal ranking
double NUmin = 0.5; // used for lineal ranking
double pos1, pos2;
int sel1, sel2;
int data[][];
int infoAttr[];
int classData[];
Vector<Rule> contenedor = new Vector<Rule>();
Vector<Rule> conjR = new Vector<Rule>();
Rule tmpRule;
Condition tmpCondition[] = new Condition[1];
RuleSet population[];
RuleSet hijo1, hijo2;
if (somethingWrong) { // We do not execute the program
System.err.println("An error was found, the data-set has numerical values.");
System.err.println("Aborting the program");
// We should not use the statement: System.exit(-1);
} else {
Randomize.setSeed(seed);
nClasses = train.getnClasses();
/*Build the nominal data information*/
infoAttr = new int[train.getnInputs()];
for (i = 0; i < infoAttr.length; i++) {
infoAttr[i] = train.numberValues(i);
}
data = new int[train.getnData()][train.getnInputs()];
for (i = 0; i < data.length; i++) {
for (j = 0; j < data[i].length; j++) {
if (train.isMissing(i, j)) data[i][j] = -1;
else data[i][j] = train.valueExample(i, j);
}
}
classData = new int[train.getnData()];
for (i = 0; i < classData.length; i++) {
classData[i] = train.getOutputAsInteger(i);
}
/*Find first-order rules which result interesting*/
for (i = 0; i < nClasses; i++) {
for (j = 0; j < infoAttr.length; j++) {
for (k = 0; k < infoAttr[j]; k++) {
tmpCondition[0] = new Condition(j, k);
tmpRule = new Rule(tmpCondition);
if (Math.abs(computeAdjustedResidual(data, classData, tmpRule, i)) > 1.96) {
if (!contenedor.contains(tmpRule)) {
contenedor.add(tmpRule);
conjR.add(tmpRule);
}
}
}
}
}
// Construct the Baker selection roulette
prob = new double[popSize];
for (j = 0; j < popSize; j++) {
aux = (double) (NUmax - NUmin) * ((double) j / (popSize - 1));
prob[j] = (double) (1.0 / (popSize)) * (NUmax - aux);
}
for (j = 1; j < popSize; j++) prob[j] = prob[j] + prob[j - 1];
/*Steady-State Genetic Algorithm*/
ele = 2;
population = new RuleSet[popSize];
while (conjR.size() >= 2) {
t = 0;
System.out.println("Producing rules of level " + ele);
for (i = 0; i < population.length; i++) {
population[i] = new RuleSet(conjR);
population[i].computeFitness(data, classData, infoAttr, contenedor, nClasses);
}
Arrays.sort(population);
while (t < numGenerations && !population[0].equals(population[popSize - 1])) {
System.out.println("Generation " + t);
t++;
/*Baker's selection*/
pos1 = Randomize.Rand();
pos2 = Randomize.Rand();
for (l = 0; l < popSize && prob[l] < pos1; l++) ;
sel1 = l;
for (l = 0; l < popSize && prob[l] < pos2; l++) ;
sel2 = l;
hijo1 = new RuleSet(population[sel1]);
hijo2 = new RuleSet(population[sel2]);
if (Randomize.Rand() < pCross) {
RuleSet.crossover1(hijo1, hijo2);
} else {
RuleSet.crossover2(hijo1, hijo2);
}
RuleSet.mutation(hijo1, conjR, pMut, data, classData, infoAttr, contenedor, nClasses);
RuleSet.mutation(hijo2, conjR, pMut, data, classData, infoAttr, contenedor, nClasses);
hijo1.computeFitness(data, classData, infoAttr, contenedor, nClasses);
hijo2.computeFitness(data, classData, infoAttr, contenedor, nClasses);
population[popSize - 2] = new RuleSet(hijo1);
population[popSize - 1] = new RuleSet(hijo2);
Arrays.sort(population);
}
/*Decode function*/
ele++;
conjR.removeAllElements();
System.out.println(
"Fitness of the best chromosome in rule level " + ele + ": " + population[0].fitness);
for (i = 0; i < population[0].getRuleSet().length; i++) {
if (Math.abs(computeAdjustedResidual(data, classData, population[0].getRule(i), i))
> 1.96) {
if (validarRegla(population[0].getRule(i))
&& !contenedor.contains(population[0].getRule(i))) {
contenedor.add(population[0].getRule(i));
conjR.add(population[0].getRule(i));
}
}
}
}
// Finally we should fill the training and test output files
doOutput(this.val, this.outputTr, data, classData, infoAttr, contenedor, nClasses);
doOutput(this.test, this.outputTst, data, classData, infoAttr, contenedor, nClasses);
/*Print the rule obtained*/
for (i = contenedor.size() - 1; i >= 0; i--) {
if (reglaPositiva(
this.train, data, classData, infoAttr, nClasses, contenedor.elementAt(i))) {
Fichero.AnadirtoFichero(outputRule, contenedor.elementAt(i).toString(train));
Fichero.AnadirtoFichero(
outputRule,
" -> "
+ consecuente(
this.train, data, classData, infoAttr, nClasses, contenedor.elementAt(i))
+ "\n");
}
}
System.out.println("Algorithm Finished");
}
}