private static IRegressionProblemData Subselect(IRegressionProblemData data, IReadOnlyList <int> training, IReadOnlyList <int> test)
{
var dataset = RegressionTreeUtilities.ReduceDataset(data.Dataset, training.Concat(test).ToList(), data.AllowedInputVariables.ToList(), data.TargetVariable);
var res = new RegressionProblemData(dataset, data.AllowedInputVariables, data.TargetVariable);
res.TrainingPartition.Start = 0;
res.TrainingPartition.End = training.Count;
res.TestPartition.Start = training.Count;
res.TestPartition.End = training.Count + test.Count;
return(res);
}
public IRegressionModel BuildModel(IReadOnlyList <int> rows, RegressionTreeParameters parameters, CancellationToken cancellation, out int numberOfParameters)
{
var reducedData = RegressionTreeUtilities.ReduceDataset(parameters.Data, rows, parameters.AllowedInputVariables.ToArray(), parameters.TargetVariable);
var pd = new RegressionProblemData(reducedData, parameters.AllowedInputVariables.ToArray(), parameters.TargetVariable);
pd.TrainingPartition.Start = 0;
pd.TrainingPartition.End = pd.TestPartition.Start = pd.TestPartition.End = reducedData.Rows;
int numP;
var model = Build(pd, parameters.Random, cancellation, out numP);
if (UseDampening && Dampening > 0.0)
{
model = DampenedModel.DampenModel(model, pd, Dampening);
}
numberOfParameters = numP;
cancellation.ThrowIfCancellationRequested();
return(model);
}
public void Split(RegressionNodeTreeModel tree, IReadOnlyList <int> trainingRows, IScope stateScope, CancellationToken cancellationToken)
{
var regressionTreeParams = (RegressionTreeParameters)stateScope.Variables[DecisionTreeRegression.RegressionTreeParameterVariableName].Value;
var splittingState = (SplittingState)stateScope.Variables[SplittingStateVariableName].Value;
var variables = regressionTreeParams.AllowedInputVariables.ToArray();
var target = regressionTreeParams.TargetVariable;
if (splittingState.Code <= 0)
{
splittingState.nodeQueue.Enqueue(tree.Root);
splittingState.trainingRowsQueue.Enqueue(trainingRows);
splittingState.Code = 1;
}
while (splittingState.nodeQueue.Count != 0)
{
var n = splittingState.nodeQueue.Dequeue();
var rows = splittingState.trainingRowsQueue.Dequeue();
string attr;
double splitValue;
var isLeaf = !DecideSplit(new RegressionProblemData(RegressionTreeUtilities.ReduceDataset(regressionTreeParams.Data, rows, variables, target), variables, target), regressionTreeParams.MinLeafSize, out attr, out splitValue);
if (isLeaf)
{
continue;
}
IReadOnlyList <int> leftRows, rightRows;
RegressionTreeUtilities.SplitRows(rows, regressionTreeParams.Data, attr, splitValue, out leftRows, out rightRows);
n.Split(regressionTreeParams, attr, splitValue, rows.Count);
splittingState.nodeQueue.Enqueue(n.Left);
splittingState.nodeQueue.Enqueue(n.Right);
splittingState.trainingRowsQueue.Enqueue(leftRows);
splittingState.trainingRowsQueue.Enqueue(rightRows);
cancellationToken.ThrowIfCancellationRequested();
}
}
