public void TestRandomize()
{
var algo = new TrialAlgo();
var anneal = new TrainAnneal(algo, new TrialScore());
anneal.PerformRandomize(algo.LongTermMemory);
anneal.FinishTraining();
Assert.AreEqual(0, algo.LongTermMemory[0], AIFH.DefaultPrecision);
}
/// <summary>
/// Run the example.
/// </summary>
public void Process()
{
// read the iris data from the resources
Assembly assembly = Assembly.GetExecutingAssembly();
var res = assembly.GetManifestResourceStream("AIFH_Vol3.Resources.iris.csv");
// did we fail to read the resouce
if (res == null)
{
Console.WriteLine("Can't read iris data from embedded resources.");
return;
}
// load the data
var istream = new StreamReader(res);
DataSet ds = DataSet.Load(istream);
istream.Close();
// The following ranges are setup for the Iris data set. If you wish to normalize other files you will
// need to modify the below function calls other files.
ds.NormalizeRange(0, 0, 1);
ds.NormalizeRange(1, 0, 1);
ds.NormalizeRange(2, 0, 1);
ds.NormalizeRange(3, 0, 1);
IDictionary <String, int> species = ds.EncodeOneOfN(4);
IList <BasicData> trainingData = ds.ExtractSupervised(0, 4, 4, 3);
var network = new RBFNetwork(4, 4, 2);
network.Reset(new MersenneTwisterGenerateRandom());
IScoreFunction score = new ScoreRegressionData(trainingData);
var train = new TrainAnneal(network, score);
PerformIterations(train, 100000, 0.01, true);
QueryOneOfN(network, trainingData, species);
}
public void TestIterations()
{
var anneal = new TrainAnneal(new TrialAlgo(), new TrialScore(), 10, 400, 0.0001)
{
Cycles = 10
};
Assert.AreEqual(400, anneal.CoolingSchedule(), AIFH.DefaultPrecision);
Assert.AreEqual(400, anneal.StartingTemperature, AIFH.DefaultPrecision);
Assert.AreEqual(0.0001, anneal.EndingTemperature, AIFH.DefaultPrecision);
Assert.AreEqual(10, anneal.Cycles);
Assert.AreEqual(0, anneal.CurrentTemperature, AIFH.DefaultPrecision);
Assert.AreEqual(0, anneal.K);
Assert.AreEqual(false, anneal.Done);
Assert.AreEqual(true, double.IsInfinity(anneal.LastError));
Assert.AreEqual(0, anneal.LastProbability, AIFH.DefaultPrecision);
anneal.Iteration();
Assert.AreEqual(true, anneal.LastError > 0);
Assert.AreEqual(87.46896591546223, anneal.CurrentTemperature, AIFH.DefaultPrecision);
Assert.AreEqual(1, anneal.K);
Assert.AreEqual(false, anneal.Done);
for (int i = 0; i < 9; i++)
{
anneal.Iteration();
}
Assert.AreEqual(true, anneal.Done);
Assert.AreEqual(9.999999999999E-5, anneal.CurrentTemperature, AIFH.DefaultPrecision);
Assert.AreEqual(10, anneal.K);
}
public void TestAnneal()
{
var anneal = new TrainAnneal(new TrialAlgo(), new TrialScore());
PerformTest(anneal);
}
public void TestGetStatus()
{
var anneal = new TrainAnneal(new TrialAlgo(), new TrialScore());
Assert.AreEqual("k=0,kMax=1000,t=0,prob=0", anneal.Status);
}
public void TestBasic()
{
var anneal = new TrainAnneal(new TrialAlgo(), new TrialScore());
Assert.AreEqual(400, anneal.CoolingSchedule(), AIFH.DefaultPrecision);
}
