protected override void UpdateModel(ISymbolicExpressionTree tree)
{
var model = new SymbolicRegressionModel(Content.ProblemData.TargetVariable, tree, Content.Model.Interpreter, Content.Model.LowerEstimationLimit, Content.Model.UpperEstimationLimit);
model.Scale(Content.ProblemData);
Content.Model = model;
}
public static ISymbolicRegressionSolution CreateRegressionSolution(IRegressionProblemData problemData, string modelStructure, int maxIterations)
{
var parser = new InfixExpressionParser();
var tree = parser.Parse(modelStructure);
var simplifier = new SymbolicDataAnalysisExpressionTreeSimplifier();
if (!SymbolicRegressionConstantOptimizationEvaluator.CanOptimizeConstants(tree))
{
throw new ArgumentException("The optimizer does not support the specified model structure.");
}
var interpreter = new SymbolicDataAnalysisExpressionTreeLinearInterpreter();
SymbolicRegressionConstantOptimizationEvaluator.OptimizeConstants(interpreter, tree, problemData, problemData.TrainingIndices,
applyLinearScaling: false, maxIterations: maxIterations,
updateVariableWeights: false, updateConstantsInTree: true);
var scaledModel = new SymbolicRegressionModel(problemData.TargetVariable, tree, (ISymbolicDataAnalysisExpressionTreeInterpreter)interpreter.Clone());
scaledModel.Scale(problemData);
SymbolicRegressionSolution solution = new SymbolicRegressionSolution(scaledModel, (IRegressionProblemData)problemData.Clone());
solution.Model.Name = "Regression Model";
solution.Name = "Regression Solution";
return(solution);
}
protected override void UpdateModel(ISymbolicExpressionTree tree) {
var model = new SymbolicRegressionModel(Content.ProblemData.TargetVariable, tree, Content.Model.Interpreter, Content.Model.LowerEstimationLimit, Content.Model.UpperEstimationLimit);
model.Scale(Content.ProblemData);
Content.Model = model;
}
/// <summary>
/// Fits a model to the data by optimizing the numeric constants.
/// Model is specified as infix expression containing variable names and numbers.
/// The starting point for the numeric constants is initialized randomly if a random number generator is specified (~N(0,1)). Otherwise the user specified constants are
/// used as a starting point.
/// </summary>-
/// <param name="problemData">Training and test data</param>
/// <param name="modelStructure">The function as infix expression</param>
/// <param name="maxIterations">Number of constant optimization iterations (using Levenberg-Marquardt algorithm)</param>
/// <param name="random">Optional random number generator for random initialization of numeric constants.</param>
/// <returns></returns>
public static ISymbolicRegressionSolution CreateRegressionSolution(IRegressionProblemData problemData, string modelStructure, int maxIterations, bool applyLinearScaling, IRandom rand = null)
{
var parser = new InfixExpressionParser();
var tree = parser.Parse(modelStructure);
// parser handles double and string variables equally by creating a VariableTreeNode
// post-process to replace VariableTreeNodes by FactorVariableTreeNodes for all string variables
var factorSymbol = new FactorVariable();
factorSymbol.VariableNames =
problemData.AllowedInputVariables.Where(name => problemData.Dataset.VariableHasType <string>(name));
factorSymbol.AllVariableNames = factorSymbol.VariableNames;
factorSymbol.VariableValues =
factorSymbol.VariableNames.Select(name =>
new KeyValuePair <string, Dictionary <string, int> >(name,
problemData.Dataset.GetReadOnlyStringValues(name).Distinct()
.Select((n, i) => Tuple.Create(n, i))
.ToDictionary(tup => tup.Item1, tup => tup.Item2)));
foreach (var parent in tree.IterateNodesPrefix().ToArray())
{
for (int i = 0; i < parent.SubtreeCount; i++)
{
var varChild = parent.GetSubtree(i) as VariableTreeNode;
var factorVarChild = parent.GetSubtree(i) as FactorVariableTreeNode;
if (varChild != null && factorSymbol.VariableNames.Contains(varChild.VariableName))
{
parent.RemoveSubtree(i);
var factorTreeNode = (FactorVariableTreeNode)factorSymbol.CreateTreeNode();
factorTreeNode.VariableName = varChild.VariableName;
factorTreeNode.Weights =
factorTreeNode.Symbol.GetVariableValues(factorTreeNode.VariableName).Select(_ => 1.0).ToArray();
// weight = 1.0 for each value
parent.InsertSubtree(i, factorTreeNode);
}
else if (factorVarChild != null && factorSymbol.VariableNames.Contains(factorVarChild.VariableName))
{
if (factorSymbol.GetVariableValues(factorVarChild.VariableName).Count() != factorVarChild.Weights.Length)
{
throw new ArgumentException(
string.Format("Factor variable {0} needs exactly {1} weights",
factorVarChild.VariableName,
factorSymbol.GetVariableValues(factorVarChild.VariableName).Count()));
}
parent.RemoveSubtree(i);
var factorTreeNode = (FactorVariableTreeNode)factorSymbol.CreateTreeNode();
factorTreeNode.VariableName = factorVarChild.VariableName;
factorTreeNode.Weights = factorVarChild.Weights;
parent.InsertSubtree(i, factorTreeNode);
}
}
}
if (!SymbolicRegressionConstantOptimizationEvaluator.CanOptimizeConstants(tree))
{
throw new ArgumentException("The optimizer does not support the specified model structure.");
}
// initialize constants randomly
if (rand != null)
{
foreach (var node in tree.IterateNodesPrefix().OfType <ConstantTreeNode>())
{
double f = Math.Exp(NormalDistributedRandom.NextDouble(rand, 0, 1));
double s = rand.NextDouble() < 0.5 ? -1 : 1;
node.Value = s * node.Value * f;
}
}
var interpreter = new SymbolicDataAnalysisExpressionTreeLinearInterpreter();
SymbolicRegressionConstantOptimizationEvaluator.OptimizeConstants(interpreter, tree, problemData, problemData.TrainingIndices,
applyLinearScaling: applyLinearScaling, maxIterations: maxIterations,
updateVariableWeights: false, updateConstantsInTree: true);
var model = new SymbolicRegressionModel(problemData.TargetVariable, tree, (ISymbolicDataAnalysisExpressionTreeInterpreter)interpreter.Clone());
if (applyLinearScaling)
{
model.Scale(problemData);
}
SymbolicRegressionSolution solution = new SymbolicRegressionSolution(model, (IRegressionProblemData)problemData.Clone());
solution.Model.Name = "Regression Model";
solution.Name = "Regression Solution";
return(solution);
}