/*
* private IEnumerable<TupleStruct<Kmer<Ty>, double>> ExtractUncharacteristicKmersForClass (int classIndex, MultisetKmer<Ty> thisClass, MultisetKmer<Ty> baseline)
* {
* //This will only work with an enormous amount of data for low k.
* }
*/
//Calculation:
//Synthesize features for an item.
//TODO: Enforce contract
public double[] SynthesizeFeatures(DiscreteEventSeries <Ty> item)
{
double[] vals = new double[kmerCount];
MultisetKmer <Ty> ms = item.ToMultisetVarKmer <Ty>(k);
foreach (KeyValuePair <Kmer <Ty>, int> kvp in ms)
{
int index = 0;
if (kmersOntoIndex.TryGetValue(kvp.Key, out index))
{
vals[index] = kvp.Value / (double)ms.Size((int)kvp.Key.Count);
}
}
return(vals);
}
//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));
}