protected override void Run(CancellationToken cancellationToken) {
// Set up the algorithm
if (SetSeedRandomly) Seed = new System.Random().Next();
var rand = new MersenneTwister((uint)Seed);
// Set up the results display
var iterations = new IntValue(0);
Results.Add(new Result("Iterations", iterations));
var table = new DataTable("Qualities");
table.Rows.Add(new DataRow("R² (train)"));
table.Rows.Add(new DataRow("R² (test)"));
Results.Add(new Result("Qualities", table));
var curLoss = new DoubleValue();
var curTestLoss = new DoubleValue();
Results.Add(new Result("R² (train)", curLoss));
Results.Add(new Result("R² (test)", curTestLoss));
var runCollection = new RunCollection();
if (StoreRuns)
Results.Add(new Result("Runs", runCollection));
// init
var problemData = Problem.ProblemData;
var targetVarName = problemData.TargetVariable;
var activeVariables = problemData.AllowedInputVariables.Concat(new string[] { problemData.TargetVariable });
var modifiableDataset = new ModifiableDataset(
activeVariables,
activeVariables.Select(v => problemData.Dataset.GetDoubleValues(v).ToList()));
var trainingRows = problemData.TrainingIndices;
var testRows = problemData.TestIndices;
var yPred = new double[trainingRows.Count()];
var yPredTest = new double[testRows.Count()];
var y = problemData.Dataset.GetDoubleValues(problemData.TargetVariable, problemData.TrainingIndices).ToArray();
var curY = problemData.Dataset.GetDoubleValues(problemData.TargetVariable, problemData.TrainingIndices).ToArray();
var yTest = problemData.Dataset.GetDoubleValues(problemData.TargetVariable, problemData.TestIndices).ToArray();
var curYTest = problemData.Dataset.GetDoubleValues(problemData.TargetVariable, problemData.TestIndices).ToArray();
var nu = Nu;
var mVars = (int)Math.Ceiling(M * problemData.AllowedInputVariables.Count());
var rRows = (int)Math.Ceiling(R * problemData.TrainingIndices.Count());
var alg = RegressionAlgorithm;
List<IRegressionModel> models = new List<IRegressionModel>();
try {
// Loop until iteration limit reached or canceled.
for (int i = 0; i < Iterations; i++) {
cancellationToken.ThrowIfCancellationRequested();
modifiableDataset.RemoveVariable(targetVarName);
modifiableDataset.AddVariable(targetVarName, curY.Concat(curYTest));
SampleTrainingData(rand, modifiableDataset, rRows, problemData.Dataset, curY, problemData.TargetVariable, problemData.TrainingIndices); // all training indices from the original problem data are allowed
var modifiableProblemData = new RegressionProblemData(modifiableDataset,
problemData.AllowedInputVariables.SampleRandomWithoutRepetition(rand, mVars),
problemData.TargetVariable);
modifiableProblemData.TrainingPartition.Start = 0;
modifiableProblemData.TrainingPartition.End = rRows;
modifiableProblemData.TestPartition.Start = problemData.TestPartition.Start;
modifiableProblemData.TestPartition.End = problemData.TestPartition.End;
if (!TrySetProblemData(alg, modifiableProblemData))
throw new NotSupportedException("The algorithm cannot be used with GBM.");
IRegressionModel model;
IRun run;
// try to find a model. The algorithm might fail to produce a model. In this case we just retry until the iterations are exhausted
if (TryExecute(alg, rand.Next(), RegressionAlgorithmResult, out model, out run)) {
int row = 0;
// update predictions for training and test
// update new targets (in the case of squared error loss we simply use negative residuals)
foreach (var pred in model.GetEstimatedValues(problemData.Dataset, trainingRows)) {
yPred[row] = yPred[row] + nu * pred;
curY[row] = y[row] - yPred[row];
row++;
}
row = 0;
foreach (var pred in model.GetEstimatedValues(problemData.Dataset, testRows)) {
yPredTest[row] = yPredTest[row] + nu * pred;
curYTest[row] = yTest[row] - yPredTest[row];
row++;
}
// determine quality
OnlineCalculatorError error;
var trainR = OnlinePearsonsRCalculator.Calculate(yPred, y, out error);
var testR = OnlinePearsonsRCalculator.Calculate(yPredTest, yTest, out error);
// iteration results
curLoss.Value = error == OnlineCalculatorError.None ? trainR * trainR : 0.0;
curTestLoss.Value = error == OnlineCalculatorError.None ? testR * testR : 0.0;
models.Add(model);
}
if (StoreRuns)
runCollection.Add(run);
table.Rows["R² (train)"].Values.Add(curLoss.Value);
table.Rows["R² (test)"].Values.Add(curTestLoss.Value);
iterations.Value = i + 1;
}
// produce solution
if (CreateSolution) {
// when all our models are symbolic models we can easily combine them to a single model
if (models.All(m => m is ISymbolicRegressionModel)) {
Results.Add(new Result("Solution", CreateSymbolicSolution(models, Nu, (IRegressionProblemData)problemData.Clone())));
}
// just produce an ensemble solution for now (TODO: correct scaling or linear regression for ensemble model weights)
var ensembleSolution = CreateEnsembleSolution(models, (IRegressionProblemData)problemData.Clone());
Results.Add(new Result("EnsembleSolution", ensembleSolution));
}
}
finally {
// reset everything
alg.Prepare(true);
}
}
protected override void Run(CancellationToken cancellationToken)
{
// Set up the algorithm
if (SetSeedRandomly)
{
Seed = RandomSeedGenerator.GetSeed();
}
var rand = new MersenneTwister((uint)Seed);
// Set up the results display
var iterations = new IntValue(0);
Results.Add(new Result("Iterations", iterations));
var table = new DataTable("Qualities");
table.Rows.Add(new DataRow("R² (train)"));
table.Rows.Add(new DataRow("R² (test)"));
Results.Add(new Result("Qualities", table));
var curLoss = new DoubleValue();
var curTestLoss = new DoubleValue();
Results.Add(new Result("R² (train)", curLoss));
Results.Add(new Result("R² (test)", curTestLoss));
var runCollection = new RunCollection();
if (StoreRuns)
{
Results.Add(new Result("Runs", runCollection));
}
// init
var problemData = Problem.ProblemData;
var targetVarName = problemData.TargetVariable;
var activeVariables = problemData.AllowedInputVariables.Concat(new string[] { problemData.TargetVariable });
var modifiableDataset = new ModifiableDataset(
activeVariables,
activeVariables.Select(v => problemData.Dataset.GetDoubleValues(v).ToList()));
var trainingRows = problemData.TrainingIndices;
var testRows = problemData.TestIndices;
var yPred = new double[trainingRows.Count()];
var yPredTest = new double[testRows.Count()];
var y = problemData.Dataset.GetDoubleValues(problemData.TargetVariable, problemData.TrainingIndices).ToArray();
var curY = problemData.Dataset.GetDoubleValues(problemData.TargetVariable, problemData.TrainingIndices).ToArray();
var yTest = problemData.Dataset.GetDoubleValues(problemData.TargetVariable, problemData.TestIndices).ToArray();
var curYTest = problemData.Dataset.GetDoubleValues(problemData.TargetVariable, problemData.TestIndices).ToArray();
var nu = Nu;
var mVars = (int)Math.Ceiling(M * problemData.AllowedInputVariables.Count());
var rRows = (int)Math.Ceiling(R * problemData.TrainingIndices.Count());
var alg = RegressionAlgorithm;
List <IRegressionModel> models = new List <IRegressionModel>();
try {
// Loop until iteration limit reached or canceled.
for (int i = 0; i < Iterations; i++)
{
cancellationToken.ThrowIfCancellationRequested();
modifiableDataset.RemoveVariable(targetVarName);
modifiableDataset.AddVariable(targetVarName, curY.Concat(curYTest).ToList());
SampleTrainingData(rand, modifiableDataset, rRows, problemData.Dataset, curY, problemData.TargetVariable, problemData.TrainingIndices); // all training indices from the original problem data are allowed
var modifiableProblemData = new RegressionProblemData(modifiableDataset,
problemData.AllowedInputVariables.SampleRandomWithoutRepetition(rand, mVars),
problemData.TargetVariable);
modifiableProblemData.TrainingPartition.Start = 0;
modifiableProblemData.TrainingPartition.End = rRows;
modifiableProblemData.TestPartition.Start = problemData.TestPartition.Start;
modifiableProblemData.TestPartition.End = problemData.TestPartition.End;
if (!TrySetProblemData(alg, modifiableProblemData))
{
throw new NotSupportedException("The algorithm cannot be used with GBM.");
}
IRegressionModel model;
IRun run;
// try to find a model. The algorithm might fail to produce a model. In this case we just retry until the iterations are exhausted
if (TryExecute(alg, rand.Next(), RegressionAlgorithmResult, out model, out run))
{
int row = 0;
// update predictions for training and test
// update new targets (in the case of squared error loss we simply use negative residuals)
foreach (var pred in model.GetEstimatedValues(problemData.Dataset, trainingRows))
{
yPred[row] = yPred[row] + nu * pred;
curY[row] = y[row] - yPred[row];
row++;
}
row = 0;
foreach (var pred in model.GetEstimatedValues(problemData.Dataset, testRows))
{
yPredTest[row] = yPredTest[row] + nu * pred;
curYTest[row] = yTest[row] - yPredTest[row];
row++;
}
// determine quality
OnlineCalculatorError error;
var trainR = OnlinePearsonsRCalculator.Calculate(yPred, y, out error);
var testR = OnlinePearsonsRCalculator.Calculate(yPredTest, yTest, out error);
// iteration results
curLoss.Value = error == OnlineCalculatorError.None ? trainR * trainR : 0.0;
curTestLoss.Value = error == OnlineCalculatorError.None ? testR * testR : 0.0;
models.Add(model);
}
if (StoreRuns)
{
runCollection.Add(run);
}
table.Rows["R² (train)"].Values.Add(curLoss.Value);
table.Rows["R² (test)"].Values.Add(curTestLoss.Value);
iterations.Value = i + 1;
}
// produce solution
if (CreateSolution)
{
// when all our models are symbolic models we can easily combine them to a single model
if (models.All(m => m is ISymbolicRegressionModel))
{
Results.Add(new Result("Solution", CreateSymbolicSolution(models, Nu, (IRegressionProblemData)problemData.Clone())));
}
// just produce an ensemble solution for now (TODO: correct scaling or linear regression for ensemble model weights)
var ensembleSolution = CreateEnsembleSolution(models, (IRegressionProblemData)problemData.Clone());
Results.Add(new Result("EnsembleSolution", ensembleSolution));
}
}
finally {
// reset everything
alg.Prepare(true);
}
}
