/**
* 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;
}
/** 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);
}
}