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);
}
private static ISymbolicRegressionSolution CreateSymbolicSolution(List <IRegressionModel> models, double nu, IRegressionProblemData problemData)
{
var symbModels = models.OfType <ISymbolicRegressionModel>();
var lowerLimit = symbModels.Min(m => m.LowerEstimationLimit);
var upperLimit = symbModels.Max(m => m.UpperEstimationLimit);
var interpreter = new SymbolicDataAnalysisExpressionTreeLinearInterpreter();
var progRootNode = new ProgramRootSymbol().CreateTreeNode();
var startNode = new StartSymbol().CreateTreeNode();
var addNode = new Addition().CreateTreeNode();
var mulNode = new Multiplication().CreateTreeNode();
var scaleNode = (ConstantTreeNode) new Constant().CreateTreeNode(); // all models are scaled using the same nu
scaleNode.Value = nu;
foreach (var m in symbModels)
{
var relevantPart = m.SymbolicExpressionTree.Root.GetSubtree(0).GetSubtree(0); // skip root and start
addNode.AddSubtree((ISymbolicExpressionTreeNode)relevantPart.Clone());
}
mulNode.AddSubtree(addNode);
mulNode.AddSubtree(scaleNode);
startNode.AddSubtree(mulNode);
progRootNode.AddSubtree(startNode);
var t = new SymbolicExpressionTree(progRootNode);
var combinedModel = new SymbolicRegressionModel(problemData.TargetVariable, t, interpreter, lowerLimit, upperLimit);
var sol = new SymbolicRegressionSolution(combinedModel, problemData);
return(sol);
}
public static IRegressionSolution CreateSymbolicSolution(double[] coeff, IRegressionProblemData problemData)
{
var ds = problemData.Dataset;
var allVariables = problemData.AllowedInputVariables.ToArray();
var doubleVariables = allVariables.Where(ds.VariableHasType <double>);
var factorVariableNames = allVariables.Where(ds.VariableHasType <string>);
var factorVariablesAndValues = ds.GetFactorVariableValues(factorVariableNames, Enumerable.Range(0, ds.Rows)); // must consider all factor values (in train and test set)
List <KeyValuePair <string, IEnumerable <string> > > remainingFactorVariablesAndValues = new List <KeyValuePair <string, IEnumerable <string> > >();
List <double> factorCoeff = new List <double>();
List <string> remainingDoubleVariables = new List <string>();
List <double> doubleVarCoeff = new List <double>();
{
int i = 0;
// find factor varibles & value combinations with non-zero coeff
foreach (var factorVarAndValues in factorVariablesAndValues)
{
var l = new List <string>();
foreach (var factorValue in factorVarAndValues.Value)
{
if (!coeff[i].IsAlmost(0.0))
{
l.Add(factorValue);
factorCoeff.Add(coeff[i]);
}
i++;
}
if (l.Any())
{
remainingFactorVariablesAndValues.Add(new KeyValuePair <string, IEnumerable <string> >(factorVarAndValues.Key, l));
}
}
// find double variables with non-zero coeff
foreach (var doubleVar in doubleVariables)
{
if (!coeff[i].IsAlmost(0.0))
{
remainingDoubleVariables.Add(doubleVar);
doubleVarCoeff.Add(coeff[i]);
}
i++;
}
}
var tree = LinearModelToTreeConverter.CreateTree(
remainingFactorVariablesAndValues, factorCoeff.ToArray(),
remainingDoubleVariables.ToArray(), doubleVarCoeff.ToArray(),
coeff.Last());
SymbolicRegressionSolution solution = new SymbolicRegressionSolution(
new SymbolicRegressionModel(problemData.TargetVariable, tree, new SymbolicDataAnalysisExpressionTreeInterpreter()),
(IRegressionProblemData)problemData.Clone());
solution.Model.Name = "Elastic-net Linear Regression Model";
solution.Name = "Elastic-net Linear Regression Solution";
return(solution);
}
private void transformModelButton_Click(object sender, EventArgs e) {
var mapper = new TransformationToSymbolicTreeMapper();
var transformator = new SymbolicExpressionTreeBacktransformator(mapper);
var transformations = Content.ProblemData.Transformations;
var targetVar = Content.ProblemData.TargetVariable;
var transformedModel = (ISymbolicRegressionModel)transformator.Backtransform(Content.Model, transformations, targetVar);
var transformedSolution = new SymbolicRegressionSolution(transformedModel, (IRegressionProblemData)Content.ProblemData.Clone());
MainFormManager.MainForm.ShowContent(transformedSolution);
}
private void transformModelButton_Click(object sender, EventArgs e)
{
var mapper = new TransformationToSymbolicTreeMapper();
var transformator = new SymbolicExpressionTreeBacktransformator(mapper);
var transformations = Content.ProblemData.Transformations;
var targetVar = Content.ProblemData.TargetVariable;
var transformedModel = (ISymbolicRegressionModel)transformator.Backtransform(Content.Model, transformations, targetVar);
var transformedSolution = new SymbolicRegressionSolution(transformedModel, (IRegressionProblemData)Content.ProblemData.Clone());
MainFormManager.MainForm.ShowContent(transformedSolution);
}
public static ISymbolicRegressionSolution CreateLinearRegressionSolution(IRegressionProblemData problemData, out double rmsError, out double cvRmsError)
{
var dataset = problemData.Dataset;
string targetVariable = problemData.TargetVariable;
IEnumerable <string> allowedInputVariables = problemData.AllowedInputVariables;
IEnumerable <int> rows = problemData.TrainingIndices;
var doubleVariables = allowedInputVariables.Where(dataset.VariableHasType <double>);
var factorVariableNames = allowedInputVariables.Where(dataset.VariableHasType <string>);
var factorVariables = dataset.GetFactorVariableValues(factorVariableNames, rows);
double[,] binaryMatrix = dataset.ToArray(factorVariables, rows);
double[,] doubleVarMatrix = dataset.ToArray(doubleVariables.Concat(new string[] { targetVariable }), rows);
var inputMatrix = binaryMatrix.HorzCat(doubleVarMatrix);
if (inputMatrix.Cast <double>().Any(x => double.IsNaN(x) || double.IsInfinity(x)))
{
throw new NotSupportedException("Linear regression does not support NaN or infinity values in the input dataset.");
}
alglib.linearmodel lm = new alglib.linearmodel();
alglib.lrreport ar = new alglib.lrreport();
int nRows = inputMatrix.GetLength(0);
int nFeatures = inputMatrix.GetLength(1) - 1;
double[] coefficients = new double[nFeatures + 1]; // last coefficient is for the constant
int retVal = 1;
alglib.lrbuild(inputMatrix, nRows, nFeatures, out retVal, out lm, out ar);
if (retVal != 1)
{
throw new ArgumentException("Error in calculation of linear regression solution");
}
rmsError = ar.rmserror;
cvRmsError = ar.cvrmserror;
alglib.lrunpack(lm, out coefficients, out nFeatures);
int nFactorCoeff = binaryMatrix.GetLength(1);
int nVarCoeff = doubleVariables.Count();
var tree = LinearModelToTreeConverter.CreateTree(factorVariables, coefficients.Take(nFactorCoeff).ToArray(),
doubleVariables.ToArray(), coefficients.Skip(nFactorCoeff).Take(nVarCoeff).ToArray(),
@const: coefficients[nFeatures]);
SymbolicRegressionSolution solution = new SymbolicRegressionSolution(new SymbolicRegressionModel(problemData.TargetVariable, tree, new SymbolicDataAnalysisExpressionTreeLinearInterpreter()), (IRegressionProblemData)problemData.Clone());
solution.Model.Name = "Linear Regression Model";
solution.Name = "Linear Regression Solution";
return(solution);
}
public static ISymbolicRegressionSolution CreateLinearRegressionSolution(IRegressionProblemData problemData, out double rmsError, out double cvRmsError)
{
IEnumerable <string> doubleVariables;
IEnumerable <KeyValuePair <string, IEnumerable <string> > > factorVariables;
double[,] inputMatrix;
PrepareData(problemData, out inputMatrix, out doubleVariables, out factorVariables);
alglib.linearmodel lm = new alglib.linearmodel();
alglib.lrreport ar = new alglib.lrreport();
int nRows = inputMatrix.GetLength(0);
int nFeatures = inputMatrix.GetLength(1) - 1;
int retVal = 1;
alglib.lrbuild(inputMatrix, nRows, nFeatures, out retVal, out lm, out ar);
if (retVal != 1)
{
throw new ArgumentException("Error in calculation of linear regression solution");
}
rmsError = ar.rmserror;
cvRmsError = ar.cvrmserror;
double[] coefficients = new double[nFeatures + 1]; // last coefficient is for the constant
alglib.lrunpack(lm, out coefficients, out nFeatures);
int nFactorCoeff = factorVariables.Sum(kvp => kvp.Value.Count());
int nVarCoeff = doubleVariables.Count();
var tree = LinearModelToTreeConverter.CreateTree(factorVariables, coefficients.Take(nFactorCoeff).ToArray(),
doubleVariables.ToArray(), coefficients.Skip(nFactorCoeff).Take(nVarCoeff).ToArray(),
@const: coefficients[nFeatures]);
SymbolicRegressionSolution solution = new SymbolicRegressionSolution(new SymbolicRegressionModel(problemData.TargetVariable, tree, new SymbolicDataAnalysisExpressionTreeLinearInterpreter()), (IRegressionProblemData)problemData.Clone());
solution.Model.Name = "Linear Regression Model";
solution.Name = "Linear Regression Solution";
return(solution);
}
/// <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);
}
public static ISymbolicRegressionSolution CreateLinearRegressionSolution(IRegressionProblemData problemData, out double rmsError, out double cvRmsError)
{
var dataset = problemData.Dataset;
string targetVariable = problemData.TargetVariable;
IEnumerable <string> allowedInputVariables = problemData.AllowedInputVariables;
IEnumerable <int> rows = problemData.TrainingIndices;
double[,] inputMatrix = AlglibUtil.PrepareInputMatrix(dataset, allowedInputVariables.Concat(new string[] { targetVariable }), rows);
if (inputMatrix.Cast <double>().Any(x => double.IsNaN(x) || double.IsInfinity(x)))
{
throw new NotSupportedException("Linear regression does not support NaN or infinity values in the input dataset.");
}
alglib.linearmodel lm = new alglib.linearmodel();
alglib.lrreport ar = new alglib.lrreport();
int nRows = inputMatrix.GetLength(0);
int nFeatures = inputMatrix.GetLength(1) - 1;
double[] coefficients = new double[nFeatures + 1]; // last coefficient is for the constant
int retVal = 1;
alglib.lrbuild(inputMatrix, nRows, nFeatures, out retVal, out lm, out ar);
if (retVal != 1)
{
throw new ArgumentException("Error in calculation of linear regression solution");
}
rmsError = ar.rmserror;
cvRmsError = ar.cvrmserror;
alglib.lrunpack(lm, out coefficients, out nFeatures);
ISymbolicExpressionTree tree = new SymbolicExpressionTree(new ProgramRootSymbol().CreateTreeNode());
ISymbolicExpressionTreeNode startNode = new StartSymbol().CreateTreeNode();
tree.Root.AddSubtree(startNode);
ISymbolicExpressionTreeNode addition = new Addition().CreateTreeNode();
startNode.AddSubtree(addition);
int col = 0;
foreach (string column in allowedInputVariables)
{
VariableTreeNode vNode = (VariableTreeNode) new HeuristicLab.Problems.DataAnalysis.Symbolic.Variable().CreateTreeNode();
vNode.VariableName = column;
vNode.Weight = coefficients[col];
addition.AddSubtree(vNode);
col++;
}
ConstantTreeNode cNode = (ConstantTreeNode) new Constant().CreateTreeNode();
cNode.Value = coefficients[coefficients.Length - 1];
addition.AddSubtree(cNode);
SymbolicRegressionSolution solution = new SymbolicRegressionSolution(new SymbolicRegressionModel(tree, new SymbolicDataAnalysisExpressionTreeInterpreter()), (IRegressionProblemData)problemData.Clone());
solution.Model.Name = "Linear Regression Model";
solution.Name = "Linear Regression Solution";
return(solution);
}
