/**
* Computes the distance between two instances (without previous normalization)
*
* @param i First instance
* @param j Second instance
* @return The Euclidean distance between i and j
*/
private double distance(Instance i, Instance j) {
double dist = 0;
int in = 0;
int out = 0;
for (int l = 0; l < nvariables; l++) {
Attribute a = Attributes.getAttribute(l);
direccion = a.getDirectionAttribute();
tipo = a.getType();
if (direccion == Attribute.INPUT) {
if (tipo != Attribute.NOMINAL && !i.getInputMissingValues(in)) {
// real value, apply euclidean distance
dist +=
(i.getInputRealValues(in) - j.getInputRealValues(in))
* (i.getInputRealValues(in) - j.getInputRealValues(in));
} else {
if (!i.getInputMissingValues(in)
&& i.getInputNominalValues(in) != j.getInputNominalValues(in)) dist += 1;
}
in++;
} else {
if (direccion == Attribute.OUTPUT) {
if (tipo != Attribute.NOMINAL && !i.getOutputMissingValues(out)) {
dist +=
(i.getOutputRealValues(out) - j.getOutputRealValues(out))
* (i.getOutputRealValues(out) - j.getOutputRealValues(out));
} else {
if (!i.getOutputMissingValues(out)
&& i.getOutputNominalValues(out) != j.getOutputNominalValues(out)) dist += 1;
}
out++;
}
}
}
return dist;
}
private void normalizarTest() {
int i, j, cont = 0, k;
Instance temp;
boolean hecho;
double caja[];
StringTokenizer tokens;
boolean nulls[];
/* Check if dataset corresponding with a classification problem */
if (Attributes.getOutputNumAttributes() < 1) {
System.err.println(
"This dataset haven´t outputs, so it not corresponding to a classification problem.");
System.exit(-1);
} else if (Attributes.getOutputNumAttributes() > 1) {
System.err.println("This dataset have more of one output.");
System.exit(-1);
}
if (Attributes.getOutputAttribute(0).getType() == Attribute.REAL) {
System.err.println(
"This dataset have an input attribute with floating values, so it not corresponding to a classification problem.");
System.exit(-1);
}
datosTest = new double[test.getNumInstances()][Attributes.getInputNumAttributes()];
clasesTest = new int[test.getNumInstances()];
caja = new double[1];
for (i = 0; i < test.getNumInstances(); i++) {
temp = test.getInstance(i);
nulls = temp.getInputMissingValues();
datosTest[i] = test.getInstance(i).getAllInputValues();
for (j = 0; j < nulls.length; j++) if (nulls[j]) datosTest[i][j] = 0.0;
caja = test.getInstance(i).getAllOutputValues();
clasesTest[i] = (int) caja[0];
for (k = 0; k < datosTest[i].length; k++) {
if (Attributes.getInputAttribute(k).getType() == Attribute.NOMINAL) {
datosTest[i][k] /= Attributes.getInputAttribute(k).getNominalValuesList().size() - 1;
} else {
datosTest[i][k] -= Attributes.getInputAttribute(k).getMinAttribute();
datosTest[i][k] /=
Attributes.getInputAttribute(k).getMaxAttribute()
- Attributes.getInputAttribute(k).getMinAttribute();
}
}
}
}
/**
* Process a dataset file for a clustering problem.
*
* @param nfexamples Name of the dataset file
* @param train The dataset file is for training or for test
* @throws java.io.IOException if there is any semantical, lexical or sintactical error in the
* input file.
*/
public void processClusterDataset(String nfexamples, boolean train) throws IOException {
try {
// Load in memory a dataset that contains a classification problem
IS.readSet(nfexamples, train);
nData = IS.getNumInstances();
nInputs = Attributes.getInputNumAttributes();
nVariables = nInputs + Attributes.getOutputNumAttributes();
if (Attributes.getOutputNumAttributes() != 0) {
System.out.println("This algorithm can not process datasets with outputs");
System.out.println("All outputs will be removed");
}
// Initialize and fill our own tables
X = new double[nData][nInputs];
missing = new boolean[nData][nInputs];
// Maximum and minimum of inputs
iMaximum = new double[nInputs];
iMinimum = new double[nInputs];
// Maximum and minimum for output data
oMaximum = 0;
oMinimum = 0;
// All values are casted into double/integer
nClasses = 0;
for (int i = 0; i < X.length; i++) {
Instance inst = IS.getInstance(i);
for (int j = 0; j < nInputs; j++) {
X[i][j] = IS.getInputNumericValue(i, j);
missing[i][j] = inst.getInputMissingValues(j);
if (X[i][j] > iMaximum[j] || i == 0) {
iMaximum[j] = X[i][j];
}
if (X[i][j] < iMinimum[j] || i == 0) {
iMinimum[j] = X[i][j];
}
}
}
} catch (Exception e) {
System.out.println("DBG: Exception in readSet");
e.printStackTrace();
}
}
private void normalizarReferencia() throws CheckException {
int i, j, cont = 0, k;
Instance temp;
boolean hecho;
double caja[];
StringTokenizer tokens;
boolean nulls[];
/*Check if dataset corresponding with a classification problem*/
if (Attributes.getOutputNumAttributes() < 1) {
throw new CheckException(
"This dataset haven´t outputs, so it not corresponding to a classification problem.");
} else if (Attributes.getOutputNumAttributes() > 1) {
throw new CheckException("This dataset have more of one output.");
}
if (Attributes.getOutputAttribute(0).getType() == Attribute.REAL) {
throw new CheckException(
"This dataset have an input attribute with floating values, so it not corresponding to a classification problem.");
}
datosReferencia = new double[referencia.getNumInstances()][Attributes.getInputNumAttributes()];
clasesReferencia = new int[referencia.getNumInstances()];
caja = new double[1];
/*Get the number of instances that have a null value*/
for (i = 0; i < referencia.getNumInstances(); i++) {
temp = referencia.getInstance(i);
nulls = temp.getInputMissingValues();
datosReferencia[i] = referencia.getInstance(i).getAllInputValues();
for (j = 0; j < nulls.length; j++) if (nulls[j]) datosReferencia[i][j] = 0.0;
caja = referencia.getInstance(i).getAllOutputValues();
clasesReferencia[i] = (int) caja[0];
for (k = 0; k < datosReferencia[i].length; k++) {
if (Attributes.getInputAttribute(k).getType() == Attribute.NOMINAL) {
datosReferencia[i][k] /=
Attributes.getInputAttribute(k).getNominalValuesList().size() - 1;
} else {
datosReferencia[i][k] -= Attributes.getInputAttribute(k).getMinAttribute();
datosReferencia[i][k] /=
Attributes.getInputAttribute(k).getMaxAttribute()
- Attributes.getInputAttribute(k).getMinAttribute();
}
}
}
}
/**
* This function builds the data matrix for reference data and normalizes inputs values
*
* @throws keel.Algorithms.Preprocess.Basic.CheckException Can not be normalized.
*/
protected void normalizar() throws CheckException {
int i, j, k;
Instance temp;
double caja[];
StringTokenizer tokens;
boolean nulls[];
/*Check if dataset corresponding with a classification problem*/
if (Attributes.getOutputNumAttributes() < 1) {
throw new CheckException(
"This dataset haven?t outputs, so it not corresponding to a classification problem.");
} else if (Attributes.getOutputNumAttributes() > 1) {
throw new CheckException("This dataset have more of one output.");
}
if (Attributes.getOutputAttribute(0).getType() == Attribute.REAL) {
throw new CheckException(
"This dataset have an input attribute with floating values, so it not corresponding to a classification problem.");
}
entradas = Attributes.getInputAttributes();
salida = Attributes.getOutputAttribute(0);
nEntradas = Attributes.getInputNumAttributes();
tokens = new StringTokenizer(training.getHeader(), " \n\r");
tokens.nextToken();
relation = tokens.nextToken();
datosTrain = new double[training.getNumInstances()][Attributes.getInputNumAttributes()];
clasesTrain = new int[training.getNumInstances()];
caja = new double[1];
nulosTrain = new boolean[training.getNumInstances()][Attributes.getInputNumAttributes()];
nominalTrain = new int[training.getNumInstances()][Attributes.getInputNumAttributes()];
realTrain = new double[training.getNumInstances()][Attributes.getInputNumAttributes()];
for (i = 0; i < training.getNumInstances(); i++) {
temp = training.getInstance(i);
nulls = temp.getInputMissingValues();
datosTrain[i] = training.getInstance(i).getAllInputValues();
for (j = 0; j < nulls.length; j++)
if (nulls[j]) {
datosTrain[i][j] = 0.0;
nulosTrain[i][j] = true;
}
caja = training.getInstance(i).getAllOutputValues();
clasesTrain[i] = (int) caja[0];
for (k = 0; k < datosTrain[i].length; k++) {
if (Attributes.getInputAttribute(k).getType() == Attribute.NOMINAL) {
nominalTrain[i][k] = (int) datosTrain[i][k];
datosTrain[i][k] /= Attributes.getInputAttribute(k).getNominalValuesList().size() - 1;
} else {
realTrain[i][k] = datosTrain[i][k];
datosTrain[i][k] -= Attributes.getInputAttribute(k).getMinAttribute();
datosTrain[i][k] /=
Attributes.getInputAttribute(k).getMaxAttribute()
- Attributes.getInputAttribute(k).getMinAttribute();
if (Double.isNaN(datosTrain[i][k])) {
datosTrain[i][k] = realTrain[i][k];
}
}
}
}
datosTest = new double[test.getNumInstances()][Attributes.getInputNumAttributes()];
clasesTest = new int[test.getNumInstances()];
caja = new double[1];
for (i = 0; i < test.getNumInstances(); i++) {
temp = test.getInstance(i);
nulls = temp.getInputMissingValues();
datosTest[i] = test.getInstance(i).getAllInputValues();
for (j = 0; j < nulls.length; j++)
if (nulls[j]) {
datosTest[i][j] = 0.0;
}
caja = test.getInstance(i).getAllOutputValues();
clasesTest[i] = (int) caja[0];
}
} // end-method
/**
* Process a dataset file for a classification problem.
*
* @param nfejemplos Name of the dataset file
* @param train The dataset file is for training or for test
* @throws java.io.IOException if there is any semantical, lexical or sintactical error in the
* input file.
*/
public void processClassifierDataset(String nfejemplos, boolean train) throws IOException {
try {
// Load in memory a dataset that contains a classification problem
IS.readSet(nfejemplos, train);
nData = IS.getNumInstances();
nInputs = Attributes.getInputNumAttributes();
nVariables = nInputs + Attributes.getOutputNumAttributes();
// Check that there is only one output variable and
// it is nominal
if (Attributes.getOutputNumAttributes() > 1) {
System.out.println("This algorithm can not process MIMO datasets");
System.out.println("All outputs but the first one will be removed");
}
boolean noOutputs = false;
if (Attributes.getOutputNumAttributes() < 1) {
System.out.println("This algorithm can not process datasets without outputs");
System.out.println("Zero-valued output generated");
noOutputs = true;
}
// Initialize and fill our own tables
X = new double[nData][nInputs];
missing = new boolean[nData][nInputs];
C = new int[nData];
// Maximum and minimum of inputs
iMaximum = new double[nInputs];
iMinimum = new double[nInputs];
// Maximum and minimum for output data
oMaximum = 0;
oMinimum = 0;
// All values are casted into double/integer
nClasses = 0;
for (int i = 0; i < X.length; i++) {
Instance inst = IS.getInstance(i);
for (int j = 0; j < nInputs; j++) {
X[i][j] = IS.getInputNumericValue(i, j);
missing[i][j] = inst.getInputMissingValues(j);
if (X[i][j] > iMaximum[j] || i == 0) {
iMaximum[j] = X[i][j];
}
if (X[i][j] < iMinimum[j] || i == 0) {
iMinimum[j] = X[i][j];
}
}
if (noOutputs) {
C[i] = 0;
} else {
C[i] = (int) IS.getOutputNumericValue(i, 0);
}
if (C[i] > nClasses) {
nClasses = C[i];
}
}
nClasses++;
System.out.println("Number of classes=" + nClasses);
} catch (Exception e) {
System.out.println("DBG: Exception in readSet");
e.printStackTrace();
}
}
/** 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);
}
}