public void Learn_3statefullyconnectedgraph_aHMMfittedtothedata()
{
// Arrange
int[] symbols = Enumerable.Range(0, 41).ToArray();
List<int[]> obs = new List<int[]>();
Random rnd = new Random();
for (int i = 0; i < 10; i++)
{
obs.Add(symbols.OrderBy(x => rnd.Next()).ToArray());
}
SequenceData sd = new SequenceData(0);
sd.AddSequences(obs);
sd.SaveAddedSequences();
PadawanLearner pwl = new PadawanLearner();
pwl.Initialise(null, 0);
// Act
pwl.Learn(sd, null, null);
//pwl.Learn(sd);
double result = pwl.CalculateProbability(obs[2]);
// Assert
Assert.IsTrue(0.9 < result && result < 1.0);
}
public Tuple<SequenceData, SequenceData> RandomSplit(double ratio, int random_seed) {
SequenceData part1 = new SequenceData(NumSymbols);
SequenceData part2 = new SequenceData(NumSymbols);
List<int[]> shuffled = sequence_list.Select(e => e).ToList();
Utilities.Shuffle(shuffled, random_seed);
int size_part1 = (int)(shuffled.Count * ratio);
for (int i = 0; i < shuffled.Count; i++) {
if (i < size_part1)
part1.AddSequence(shuffled[i]);
else
part2.AddSequence(shuffled[i]);
}
part1.SaveAddedSequences();
part2.SaveAddedSequences();
return new Tuple<SequenceData, SequenceData>(part1, part2);
}
public static SequenceData LoadSequences(string file) {
string[] lines = System.IO.File.ReadAllLines(file);
//parse number of different symbols
int num_symbols = Int32.Parse(lines[0].Split(' ')[1]);
SequenceData seqData = new SequenceData(num_symbols);
//parse sequences
for (int i = 1; i < lines.Length; i++) {
string[] currentSeqStr = lines[i].Split(' ');
//skip first element on each line, which contains the length of the sequence
int[] currentSeq = currentSeqStr.Skip(1).Select(p => Int32.Parse(p)).ToArray();
seqData.AddSequence(currentSeq);
}
seqData.SaveAddedSequences();
return seqData;
}
public Tuple<SequenceData, SequenceData> RandomSplit(int trainingDataSize, int validationDataSize, int randomSeed)
{
SequenceData trainingData = new SequenceData(NumSymbols);
SequenceData validaitonData = new SequenceData(NumSymbols);
List<int[]> shuffled = sequence_list.ToList();
Utilities.Shuffle(shuffled, randomSeed);
trainingData.AddSequences(sequence_list.Take(trainingDataSize));
validaitonData.AddSequences(sequence_list.Skip(sequence_list.Count - validationDataSize).Take(validationDataSize));
trainingData.SaveAddedSequences();
validaitonData.SaveAddedSequences();
return new Tuple<SequenceData, SequenceData>(trainingData, validaitonData);
}