public static void TestNewDesign()
{
DiscreteSeriesDatabase <string> allData = LoadRegionsDatabase();
Tuple <DiscreteSeriesDatabase <string>, DiscreteSeriesDatabase <string> > split = allData.SplitDatabase(.8);
DiscreteSeriesDatabase <string> trainingData = split.Item1;
DiscreteSeriesDatabase <string> testData = split.Item2;
IFeatureSynthesizer <string> synth = new RegressorFeatureSynthesizerKmerFrequenciesVarK <string>("region", 8, 2, 100, 3);
//IFeatureSynthesizer<string> synth = new RegressorFeatureSynthesizerKmerFrequencies<string>("region", 4, 10, 100, 3);
//IFeatureSynthesizer<string> synth = new RegressorFeatureSynthesizerFrequencies<string>("region", 4, 10, 100);
synth.Train(trainingData);
Console.WriteLine(synth.ToString());
synth.ScoreModel(testData, 2, "filename");
Console.WriteLine(ClassifyDataSet(synth, testData, "filename")); //TODO may be good to use something unspecifiable in the file syntax such as "filename;"
//Console.WriteLine (allData.DatabaseLatexString("Regional Spanish Database"));
}
public static IFeatureSynthesizer <string> deriveOptimalClassifier()
{
//Load databases
DiscreteSeriesDatabase <string> allData = LoadRegionsDatabase();
Tuple <DiscreteSeriesDatabase <string>, DiscreteSeriesDatabase <string> > split = allData.SplitDatabase(.8);
DiscreteSeriesDatabase <string> trainingData = split.Item1;
DiscreteSeriesDatabase <string> testData = split.Item2;
string cat = "region";
double optimalScore = 0;
IFeatureSynthesizer <string> optimalClassifier = null;
string optimalInfoStr = null;
//Preliminary scan
int[] ks = new int[] { 2, 3, 4 };
//int[] minCutoffs = new int[]{5, 10, 20};
int[] minCutoffs = new int[] { 10 };
int[] kmerCounts = new int[] { 10, 25, 50, 100 };
int[] smoothingAmounts = new int[] { 1, 5, 10 };
string[] colNames = "k minCutoff kmerCount smoothingAmount score".Split(' ');
Console.WriteLine(colNames.FoldToString("", "", ","));
foreach (int k in ks)
{
foreach (int minCutoff in minCutoffs)
{
foreach (int kmerCount in kmerCounts)
{
foreach (int smoothingAmount in smoothingAmounts)
{
IFeatureSynthesizer <string> classifier = new RegressorFeatureSynthesizerKmerFrequenciesVarK <string>(cat, minCutoff, smoothingAmount, kmerCount, k);
classifier.Train(trainingData);
double score = classifier.ScoreModel(testData);
string infoStr = new double[] { k, minCutoff, kmerCount, smoothingAmount, score }.FoldToString("", "", ",");
Console.WriteLine(infoStr);
if (score > optimalScore)
{
optimalScore = score;
optimalClassifier = classifier;
optimalInfoStr = infoStr;
}
}
}
}
}
Console.WriteLine("Optimal Classifier:");
Console.WriteLine(optimalInfoStr);
Console.WriteLine(optimalClassifier);
return(optimalClassifier);
}
