double InformationGainCalculator::calculateInformationGain(const DataFrame& df1,
int factorIndex1, const DataFrame& df2, int factorIndex2)
{
assert(df1.isNominal(factorIndex1));
assert(df2.isNominal(factorIndex2));
double hy = _calculateEntropy(df1, factorIndex1);
double hyx = _calculateConditionalEntropy(df1, factorIndex1, df2, factorIndex2);
double gain = hy - hyx;
return gain;
}
double SymmetricUncertaintyCalculator::calculateUncertainty(const DataFrame& df1,
int factorIndex1, const DataFrame& df2, int factorIndex2)
{
assert(df1.isNominal(factorIndex1));
assert(df2.isNominal(factorIndex2));
double hy = _calculateEntropy(df1, factorIndex1);
double hyx = _calculateConditionalEntropy(df1, factorIndex1, df2, factorIndex2);
double gain = hy - hyx;
double hx = _calculateEntropy(df2, factorIndex2);
if (hy + hx == 0.0)
{
return 1.0;
}
double result = 2.0 * (gain / (hy + hx));
return result;
}
void PrincipalComponentsAnalysis::compute(DataFrame& df)
{
if (df.getNumFactors() > 2)
{
// see PrincipalComponentsAnalysisTest
cout << "You realize this hasn't been tested, right?" << endl;
}
Matrix dataMat(df.getNumFactors(), df.getNumDataVectors());
Matrix deviates(df.getNumFactors(), df.getNumDataVectors());
SymmetricMatrix covar(df.getNumFactors());
DiagonalMatrix eigenValues(df.getNumFactors());
Matrix eigenVectors;
ColumnVector means(df.getNumFactors());
means = 0.0;
RowVector h(df.getNumDataVectors());
h = 1.0;
for (unsigned int j = 0; j < df.getNumFactors(); j++)
{
if (df.isNominal(j))
{
throw Tgs::Exception("Only numeric values are supported.");
}
}
for(unsigned int i = 0; i < df.getNumDataVectors(); i++)
{
for (unsigned int j = 0; j < df.getNumFactors(); j++)
{
double v = df.getDataElement(i, j);
if (df.isNull(v))
{
throw Tgs::Exception("Only non-null values are supported.");
}
dataMat.element(j, i) = v;
means.element(j) += v / (double)df.getNumDataVectors();
}
}
try
{
deviates = dataMat - (means * h);
covar << (1.0/(float)df.getNumDataVectors()) * (deviates * deviates.t());
Jacobi::jacobi(covar, eigenValues, eigenVectors);
}
catch (const std::exception&)
{
throw;
}
catch (...)
{
throw Tgs::Exception("Unknown error while calculating PCA");
}
_sortEigens(eigenVectors, eigenValues);
_components.resize(df.getNumFactors());
for (unsigned int v = 0; v < df.getNumFactors(); v++)
{
_components[v].resize(df.getNumFactors());
for (unsigned int d = 0; d < df.getNumFactors(); d++)
{
_components[v][d] = eigenVectors.element(d, v);
}
}
}
