private static SymbolicExpressionTreeNode MirrorTree(RegressionNodeModel regressionNode, IDictionary <int, RegressionNodeModel> dict,
IDictionary <int, IReadOnlyList <int> > trainingLeafRows,
IDictionary <int, IReadOnlyList <int> > testLeafRows,
IntValue nextId, IDataset data, IReadOnlyList <int> trainingRows, IReadOnlyList <int> testRows)
{
if (regressionNode.IsLeaf)
{
var i = nextId.Value++;
dict.Add(i, regressionNode);
trainingLeafRows.Add(i, trainingRows);
testLeafRows.Add(i, testRows);
return(new SymbolicExpressionTreeNode(new TextSymbol("Model " + i + "\n(" + trainingRows.Count + "/" + testRows.Count + ")")));
}
var pftext = "\npf = " + regressionNode.PruningStrength.ToString("0.###");
var text = regressionNode.SplitAttribute + " <= " + regressionNode.SplitValue.ToString("0.###");
if (!double.IsNaN(regressionNode.PruningStrength))
{
text += pftext;
}
var textNode = new SymbolicExpressionTreeNode(new TextSymbol(text));
IReadOnlyList <int> lTrainingRows, rTrainingRows;
IReadOnlyList <int> lTestRows, rTestRows;
RegressionTreeUtilities.SplitRows(trainingRows, data, regressionNode.SplitAttribute, regressionNode.SplitValue, out lTrainingRows, out rTrainingRows);
RegressionTreeUtilities.SplitRows(testRows, data, regressionNode.SplitAttribute, regressionNode.SplitValue, out lTestRows, out rTestRows);
textNode.AddSubtree(MirrorTree(regressionNode.Left, dict, trainingLeafRows, testLeafRows, nextId, data, lTrainingRows, lTestRows));
textNode.AddSubtree(MirrorTree(regressionNode.Right, dict, trainingLeafRows, testLeafRows, nextId, data, rTrainingRows, rTestRows));
return(textNode);
}
public void FillLeafs(RegressionNodeTreeModel tree, IReadOnlyList <int> trainingRows, IDataset data)
{
var helperQueue = new Queue <RegressionNodeModel>();
var trainingHelperQueue = new Queue <IReadOnlyList <int> >();
nodeQueue.Clear();
trainingRowsQueue.Clear();
helperQueue.Enqueue(tree.Root);
trainingHelperQueue.Enqueue(trainingRows);
while (helperQueue.Count != 0)
{
var n = helperQueue.Dequeue();
var t = trainingHelperQueue.Dequeue();
if (n.IsLeaf)
{
nodeQueue.Enqueue(n);
trainingRowsQueue.Enqueue(t);
continue;
}
IReadOnlyList <int> leftTraining, rightTraining;
RegressionTreeUtilities.SplitRows(t, data, n.SplitAttribute, n.SplitValue, out leftTraining, out rightTraining);
helperQueue.Enqueue(n.Left);
helperQueue.Enqueue(n.Right);
trainingHelperQueue.Enqueue(leftTraining);
trainingHelperQueue.Enqueue(rightTraining);
}
}
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();
}
}
