// builds a model and uses the scaled predictions to rack up a confusion matrix, for comparison
private static void ConfirmPredictions(string sdfile, int truePos, int trueNeg, int falsePos, int falseNeg)
{
WriteLine($"[{sdfile}] comparing confusion matrix");
var molecules = new List <IAtomContainer>();
var activities = new List <bool>();
var model = new Bayesian(CircularFingerprinterClass.ECFP6, 1024);
try
{
using (var ins = ResourceLoader.GetAsStream("NCDK.Data.CDD." + sdfile))
{
var rdr = new EnumerableSDFReader(ins, ChemObjectBuilder.Instance);
foreach (var mol in rdr)
{
bool actv = "true" == (string)mol.GetProperties()["Active"];
molecules.Add(mol);
activities.Add(actv);
model.AddMolecule(mol, actv);
}
}
}
catch (CDKException)
{
throw;
}
catch (Exception ex)
{
throw new CDKException("Test failed", ex);
}
model.Build();
model.ValidateLeaveOneOut();
// build the confusion matrix
int gotTP = 0, gotTN = 0, gotFP = 0, gotFN = 0;
for (int n = 0; n < molecules.Count; n++)
{
double pred = model.ScalePredictor(model.Predict(molecules[n]));
bool actv = activities[n];
if (pred >= 0.5)
{
if (actv)
{
gotTP++;
}
else
{
gotFP++;
}
}
else
{
if (actv)
{
gotFN++;
}
else
{
gotTN++;
}
}
}
WriteLine(" True Positives: got=" + gotTP + " require=" + truePos);
WriteLine(" Negatives: got=" + gotTN + " require=" + trueNeg);
WriteLine(" False Positives: got=" + gotFP + " require=" + falsePos);
WriteLine(" Negatives: got=" + gotFN + " require=" + falseNeg);
if (gotTP != truePos || gotTN != trueNeg || gotFP != falsePos || gotFN != falseNeg)
{
throw new CDKException("Confusion matrix mismatch");
}
}
