public void TrainModelRatios(MultisetKmer <A> baselineClass, MultisetKmer <A> thisClass)
{
List <KeyValuePair <Kmer <A>, double> > rawModel = new List <KeyValuePair <Kmer <A>, double> >();
int totalCount = 0;
foreach (Kmer <A> key in thisClass.Keys)
{
int thisCount = thisClass.getCount(key);
totalCount += thisCount;
if (thisCount > regressor.minSignificantCount)
{
double thisFrac = thisClass.GetKeyFrac(key);
double baseFrac = baselineClass.GetKeyFracLaplace(key, regressor.smoothingAmount);
if (thisFrac > baseFrac)
{
rawModel.Add(key, thisFrac / baseFrac);
}
}
}
regressor.finalizeModel(rawModel, totalCount);
}
//Extract characteristic kmers (top n more common than baseline that occur at least q times).
private IEnumerable <TupleStruct <Kmer <Ty>, double> > ExtractCharacteristicKmersForClass(int classIndex, MultisetKmer <Ty> thisClass, MultisetKmer <Ty> baseline)
{
List <TupleStruct <Kmer <Ty>, double> > thisClassCharacteristicKmersStore = new List <TupleStruct <Kmer <Ty>, double> >();
foreach (KeyValuePair <Kmer <Ty>, int> kvp in thisClass)
{
if (kvp.Value > minKmerCount)
{
double thisFreq = kvp.Value / (double)thisClass.Size(kvp.Key.Count);
double baseFreq = baseline.GetKeyFracLaplace(kvp.Key, smoothingAmt);
//Console.WriteLine ("Class: " + classIndex + " Kmer: " + kvp.Value + ", class freq " + thisFreq + ", base freq " + baseFreq);
//TODO: Advanced logic.
if (thisFreq > baseFreq)
{
double kmerValue = thisFreq / baseFreq - 1;
//Console.WriteLine ("Adding kmer " + kvp.Key + " weight " + kmerValue + " for class " + classIndex);
thisClassCharacteristicKmersStore.Add(new TupleStruct <Kmer <Ty>, double>(kvp.Key, kmerValue));
}
}
}
return(thisClassCharacteristicKmersStore.OrderByDescending(tup => Math.Abs(tup.Item2)).Take((int)kmersToTake));
}