/**
* Process the input and compute the statistics of the training data
*
* @return an Input object which holds the statistics about the training data
*/
private Input sIB_ProcessInput() {
double valSum = 0.0;
for (int i = 0; i < m_numInstances; i++) {
valSum = 0.0;
for (int v = 0; v < m_data.instance(i).numValues(); v++) {
valSum += m_data.instance(i).valueSparse(v);
}
if (valSum <= 0) {
if (m_verbose) {
System.out.format("Instance %s sum of value = %s <= 0, removed.\n", i, valSum);
}
m_data.delete(i);
m_numInstances--;
}
}
// get the term-document matrix
Input input = new Input();
input.Py_x = getTransposedNormedMatrix(m_data);
if (m_uniformPrior) {
input.Pyx = input.Py_x.copy();
normalizePrior(m_data);
} else {
input.Pyx = getTransposedMatrix(m_data);
}
input.sumVals = getTotalSum(m_data);
input.Pyx.timesEquals(1 / input.sumVals);
// prior probability of documents, ie. sum the columns from the Pyx matrix
input.Px = new double[m_numInstances];
for (int i = 0; i < m_numInstances; i++) {
for (int j = 0; j < m_numAttributes; j++) {
input.Px[i] += input.Pyx.get(j, i);
}
}
// prior probability of terms, ie. sum the rows from the Pyx matrix
input.Py = new double[m_numAttributes];
for (int i = 0; i < input.Pyx.getRowDimension(); i++) {
for (int j = 0; j < input.Pyx.getColumnDimension(); j++) {
input.Py[i] += input.Pyx.get(i, j);
}
}
MI(input.Pyx, input);
return input;
}
