/**
* Computes average class values for each attribute and value
*
* @throws Exception
*/
private void computeAverageClassValues() throws Exception {
double totalCounts, sum;
M5Instance instance;
double[] counts;
double[][] avgClassValues = new double[getInputFormat().numAttributes()][0];
m_Indices = new int[getInputFormat().numAttributes()][0];
for (int j = 0; j < getInputFormat().numAttributes(); j++) {
M5Attribute att = getInputFormat().attribute(j);
if (att.isNominal()) {
avgClassValues[j] = new double[att.numValues()];
counts = new double[att.numValues()];
for (int i = 0; i < getInputFormat().numInstances(); i++) {
instance = getInputFormat().instance(i);
if (!instance.classIsMissing() && (!instance.isMissing(j))) {
counts[(int) instance.value(j)] += instance.weight();
avgClassValues[j][(int) instance.value(j)] += instance.weight() * instance.classValue();
}
}
sum = M5StaticUtils.sum(avgClassValues[j]);
totalCounts = M5StaticUtils.sum(counts);
if (M5StaticUtils.gr(totalCounts, 0)) {
for (int k = 0; k < att.numValues(); k++) {
if (M5StaticUtils.gr(counts[k], 0)) {
avgClassValues[j][k] /= (double) counts[k];
} else {
avgClassValues[j][k] = sum / (double) totalCounts;
}
}
}
m_Indices[j] = M5StaticUtils.sort(avgClassValues[j]);
}
}
}
/** Set the output format if the class is numeric. */
private void setOutputFormatNumeric() {
if (m_Indices == null) {
setOutputFormat(null);
return;
}
M5Vector newAtts;
int newClassIndex;
StringBuffer attributeName;
M5Instances outputFormat;
M5Vector vals;
// Compute new attributes
newClassIndex = getInputFormat().classIndex();
newAtts = new M5Vector();
for (int j = 0; j < getInputFormat().numAttributes(); j++) {
M5Attribute att = getInputFormat().attribute(j);
if ((!att.isNominal()) || (j == getInputFormat().classIndex())) {
newAtts.addElement(att.copy());
} else {
if (j < getInputFormat().classIndex()) {
newClassIndex += att.numValues() - 2;
}
// Compute values for new attributes
for (int k = 1; k < att.numValues(); k++) {
attributeName = new StringBuffer(att.name() + "=");
for (int l = k; l < att.numValues(); l++) {
if (l > k) {
attributeName.append(',');
}
attributeName.append(att.value(m_Indices[j][l]));
}
if (m_Numeric) {
newAtts.addElement(new M5Attribute(attributeName.toString()));
} else {
vals = new M5Vector(2);
vals.addElement("f");
vals.addElement("t");
newAtts.addElement(new M5Attribute(attributeName.toString(), vals));
}
}
}
}
outputFormat = new M5Instances(getInputFormat().relationName(), newAtts, 0);
outputFormat.setClassIndex(newClassIndex);
setOutputFormat(outputFormat);
}
/**
* Convert a single instance over if the class is nominal. The converted instance is added to the
* end of the output queue.
*
* @param instance the instance to convert
*/
private void convertInstanceNominal(M5Instance instance) {
double[] vals = new double[outputFormatPeek().numAttributes()];
int attSoFar = 0;
for (int j = 0; j < getInputFormat().numAttributes(); j++) {
M5Attribute att = getInputFormat().attribute(j);
if ((!att.isNominal()) || (j == getInputFormat().classIndex())) {
vals[attSoFar] = instance.value(j);
attSoFar++;
} else {
if (att.numValues() <= 2) {
vals[attSoFar] = instance.value(j);
attSoFar++;
} else {
if (instance.isMissing(j)) {
for (int k = 0; k < att.numValues(); k++) {
vals[attSoFar + k] = instance.value(j);
}
} else {
for (int k = 0; k < att.numValues(); k++) {
if (k == (int) instance.value(j)) {
vals[attSoFar + k] = 1;
} else {
vals[attSoFar + k] = 0;
}
}
}
attSoFar += att.numValues();
}
}
}
M5Instance inst = null;
if (instance instanceof M5SparseInstance) {
inst = new M5SparseInstance(instance.weight(), vals);
} else {
inst = new M5Instance(instance.weight(), vals);
}
copyStringValues(
inst,
false,
instance.dataset(),
getInputStringIndex(),
getOutputFormat(),
getOutputStringIndex());
inst.setDataset(getOutputFormat());
push(inst);
}