public IMLMethod Decode(IGenome genome)
{
var result = new RBFNetwork(_inputCount, _rbfCount, _outputCount);
var dag = (DoubleArrayGenome) genome;
Array.Copy(dag.Data, 0, result.LongTermMemory, 0, _size);
return result;
}
/// <summary>
/// Create an initial population.
/// </summary>
/// <param name="rnd">Random number generator.</param>
/// <param name="codec">The codec, the type of network to use.</param>
/// <returns>The population.</returns>
public static IPopulation InitPopulation(IGenerateRandom rnd, RBFNetworkGenomeCODEC codec)
{
// Create a RBF network to get the length.
var network = new RBFNetwork(codec.InputCount, codec.RbfCount, codec.OutputCount);
int size = network.LongTermMemory.Length;
// Create a new population, use a single species.
IPopulation result = new BasicPopulation(PopulationSize, new DoubleArrayGenomeFactory(size));
var defaultSpecies = new BasicSpecies {Population = result};
result.Species.Add(defaultSpecies);
// Create a new population of random networks.
for (int i = 0; i < PopulationSize; i++)
{
var genome = new DoubleArrayGenome(size);
network.Reset(rnd);
Array.Copy(network.LongTermMemory, 0, genome.Data, 0, size);
defaultSpecies.Add(genome);
}
// Set the genome factory to use the double array genome.
result.GenomeFactory = new DoubleArrayGenomeFactory(size);
return result;
}
public IMLMethod Decode(IGenome genome)
{
var result = new RBFNetwork(_inputCount, _rbfCount, _outputCount);
var dag = (DoubleArrayGenome)genome;
Array.Copy(dag.Data, 0, result.LongTermMemory, 0, _size);
return(result);
}
public RBFNetworkGenomeCODEC(int inputCount, int rbfCount, int outputCount)
{
_inputCount = inputCount;
_rbfCount = rbfCount;
_outputCount = outputCount;
var temp = new RBFNetwork(inputCount, rbfCount, outputCount);
_size = temp.LongTermMemory.Length;
}
public RBFNetworkGenomeCODEC(int inputCount, int rbfCount, int outputCount)
{
_inputCount = inputCount;
_rbfCount = rbfCount;
_outputCount = outputCount;
var temp = new RBFNetwork(inputCount, rbfCount, outputCount);
_size = temp.LongTermMemory.Length;
}
/// <summary>
/// Prepare a Kaggle submission for Titanic.
/// </summary>
/// <param name="dataPath">The data path.</param>
/// <param name="bestNetwork">The best network.</param>
/// <param name="cross">The cross validated data.</param>
public void Submit(string dataPath, RBFNetwork bestNetwork, CrossValidate cross)
{
String now = new DateTime().ToString("yyyyMMddhhmm");
string trainingPath = Path.Combine(dataPath, TitanicConfig.TrainingFilename);
string testPath = Path.Combine(dataPath, TitanicConfig.TestFilename);
var score = (int) (cross.Score*10000);
string submitPath = Path.Combine(dataPath, "submit-" + now + "_" + score + ".csv");
string submitInfoPath = Path.Combine(dataPath, "submit-" + now + ".txt");
using (var file = new StreamWriter(submitInfoPath))
{
file.WriteLine("Crossvalidation stats:");
for (int i = 0; i < cross.Count; i++)
{
CrossValidateFold fold = cross.Folds[i];
file.WriteLine("Fold #" + (i + 1) + " : Score: " + fold.Score);
}
file.WriteLine("Average Score: " + cross.Score);
file.WriteLine();
file.WriteLine(String.Join(",", bestNetwork.LongTermMemory));
}
var stats = new TitanicStats();
NormalizeTitanic.Analyze(stats, trainingPath);
NormalizeTitanic.Analyze(stats, testPath);
var ids = new List<String>();
IList<BasicData> training = NormalizeTitanic.Normalize(stats, testPath, ids,
TitanicConfig.InputNormalizeLow,
TitanicConfig.InputNormalizeHigh,
TitanicConfig.PredictSurvive,
TitanicConfig.PredictPerish);
int idx = 0;
using (var streamWriter = new StreamWriter(submitPath))
using (var writer = new CsvWriter(streamWriter))
{
writer.WriteField("PassengerId");
writer.WriteField("Survived");
writer.NextRecord();
foreach (BasicData data in training)
{
double[] output = bestNetwork.ComputeRegression(data.Input);
int survived = output[0] > 0.5 ? 1 : 0;
writer.WriteField(ids[idx]);
writer.WriteField(survived);
writer.NextRecord();
idx++;
}
}
}
/// <summary>
/// Train one fold.
/// </summary>
/// <param name="k">The fold id.</param>
/// <param name="fold">The fold.</param>
public void TrainFold(int k, CrossValidateFold fold)
{
int noImprove = 0;
double localBest = 0;
// Get the training and cross validation sets.
IList<BasicData> training = fold.TrainingSet;
IList<BasicData> validation = fold.ValidationSet;
// Create random particles for the RBF.
IGenerateRandom rnd = new MersenneTwisterGenerateRandom();
var particles = new RBFNetwork[TitanicConfig.ParticleCount];
for (int i = 0; i < particles.Length; i++)
{
particles[i] = new RBFNetwork(TitanicConfig.InputFeatureCount, TitanicConfig.RbfCount, 1);
particles[i].Reset(rnd);
}
/**
* Construct a network to hold the best network.
*/
if (_bestNetwork == null)
{
_bestNetwork = new RBFNetwork(TitanicConfig.InputFeatureCount, TitanicConfig.RbfCount, 1);
}
/**
* Setup the scoring function.
*/
IScoreFunction score = new ScoreTitanic(training);
IScoreFunction scoreValidate = new ScoreTitanic(validation);
/**
* Setup particle swarm.
*/
bool done = false;
var train = new TrainPSO(particles, score);
int iterationNumber = 0;
var line = new StringBuilder();
do
{
iterationNumber++;
train.Iteration();
var best = (RBFNetwork) train.BestParticle;
double trainingScore = train.LastError;
double validationScore = scoreValidate.CalculateScore(best);
if (validationScore > _bestScore)
{
Array.Copy(best.LongTermMemory, 0, _bestNetwork.LongTermMemory, 0, best.LongTermMemory.Length);
_bestScore = validationScore;
}
if (validationScore > localBest)
{
noImprove = 0;
localBest = validationScore;
}
else
{
noImprove++;
}
line.Length = 0;
line.Append("Fold #");
line.Append(k + 1);
line.Append(", Iteration #");
line.Append(iterationNumber);
line.Append(": training correct: ");
line.Append(trainingScore);
line.Append(", validation correct: ");
line.Append(validationScore);
line.Append(", no improvement: ");
line.Append(noImprove);
if (noImprove > TitanicConfig.AllowNoImprovement)
{
done = true;
}
Console.WriteLine(line.ToString());
} while (!done);
fold.Score = localBest;
}
/// <summary>
/// Run the example.
/// </summary>
public void Process()
{
// read the iris data from the resources
Assembly assembly = Assembly.GetExecutingAssembly();
Stream res = assembly.GetManifestResourceStream("AIFH_Vol2.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();
IGenerateRandom rnd = new MersenneTwisterGenerateRandom();
// 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, -1, 1);
ds.NormalizeRange(1, -1, 1);
ds.NormalizeRange(2, -1, 1);
ds.NormalizeRange(3, -1, 1);
IDictionary<string, int> species = ds.EncodeOneOfN(4);
var particles = new RBFNetwork[ParticleCount];
for (int i = 0; i < particles.Length; i++)
{
particles[i] = new RBFNetwork(4, 4, 3);
particles[i].Reset(rnd);
}
IList<BasicData> trainingData = ds.ExtractSupervised(0, 4, 4, 3);
IScoreFunction score = new ScoreRegressionData(trainingData);
var train = new TrainPSO(particles, score);
PerformIterations(train, 100000, 0.05, true);
var winner = (RBFNetwork) train.BestParticle;
QueryOneOfN(winner, trainingData, species);
}
/// <summary>
/// Run the example.
/// </summary>
public void Process()
{
// read the iris data from the resources
Assembly assembly = Assembly.GetExecutingAssembly();
Stream res = assembly.GetManifestResourceStream("AIFH_Vol2.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, -1, 1);
ds.NormalizeRange(1, -1, 1);
ds.NormalizeRange(2, -1, 1);
ds.NormalizeRange(3, -1, 1);
IDictionary<string, int> species = ds.EncodeOneOfN(4);
istream.Close();
var network = new RBFNetwork(4, 4, 3);
IList<BasicData> trainingData = ds.ExtractSupervised(0, 4, 4, 3);
IScoreFunction score = new ScoreRegressionData(trainingData);
var train = new ContinuousACO(network, score, 30);
PerformIterations(train, 100000, 0.05, true);
train.FinishTraining();
QueryOneOfN(network, trainingData, species);
}