public override void CalculateImpactAndReplacementValues(ISymbolicDataAnalysisModel model, ISymbolicExpressionTreeNode node,
IDataAnalysisProblemData problemData, IEnumerable<int> rows, out double impactValue, out double replacementValue, out double newQualityForImpactsCalculation,
double qualityForImpactsCalculation = Double.NaN) {
var classificationModel = (ISymbolicClassificationModel)model;
var classificationProblemData = (IClassificationProblemData)problemData;
if (double.IsNaN(qualityForImpactsCalculation))
qualityForImpactsCalculation = CalculateQualityForImpacts(classificationModel, classificationProblemData, rows);
replacementValue = CalculateReplacementValue(classificationModel, node, classificationProblemData, rows);
var constantNode = new ConstantTreeNode(new Constant()) { Value = replacementValue };
var cloner = new Cloner();
var tempModel = cloner.Clone(classificationModel);
var tempModelNode = (ISymbolicExpressionTreeNode)cloner.GetClone(node);
var tempModelParentNode = tempModelNode.Parent;
int i = tempModelParentNode.IndexOfSubtree(tempModelNode);
tempModelParentNode.RemoveSubtree(i);
tempModelParentNode.InsertSubtree(i, constantNode);
OnlineCalculatorError errorState;
var dataset = classificationProblemData.Dataset;
var targetClassValues = dataset.GetDoubleValues(classificationProblemData.TargetVariable, rows);
var estimatedClassValues = tempModel.GetEstimatedClassValues(dataset, rows);
newQualityForImpactsCalculation = OnlineAccuracyCalculator.Calculate(targetClassValues, estimatedClassValues, out errorState);
if (errorState != OnlineCalculatorError.None) newQualityForImpactsCalculation = 0.0;
impactValue = qualityForImpactsCalculation - newQualityForImpactsCalculation;
}
public ConstantNodeEditDialog(ISymbolicExpressionTreeNode node)
{
InitializeComponent();
oldValueTextBox.TabStop = false; // cannot receive focus using tab key
NewNode = (ConstantTreeNode)node;
InitializeFields();
}
private static void UpdateConstants(ISymbolicExpressionTree tree, double[] constants, bool updateVariableWeights)
{
int i = 0;
foreach (var node in tree.Root.IterateNodesPrefix().OfType <SymbolicExpressionTreeTerminalNode>())
{
ConstantTreeNode constantTreeNode = node as ConstantTreeNode;
VariableTreeNodeBase variableTreeNodeBase = node as VariableTreeNodeBase;
FactorVariableTreeNode factorVarTreeNode = node as FactorVariableTreeNode;
if (constantTreeNode != null)
{
constantTreeNode.Value = constants[i++];
}
else if (updateVariableWeights && variableTreeNodeBase != null)
{
variableTreeNodeBase.Weight = constants[i++];
}
else if (factorVarTreeNode != null)
{
for (int j = 0; j < factorVarTreeNode.Weights.Length; j++)
{
factorVarTreeNode.Weights[j] = constants[i++];
}
}
}
}
private ISymbolicExpressionTreeNode MakeProduct(ConstantTreeNode c, double weight)
{
var mul = new Multiplication();
var prod = mul.CreateTreeNode();
prod.AddSubtree(MakeConstantTreeNode(weight));
prod.AddSubtree(c);
return(prod);
}
private ConstantTreeNode MakeConstantTreeNode(double value)
{
Constant constant = new Constant();
constant.MinValue = value - 1;
constant.MaxValue = value + 1;
ConstantTreeNode constantTreeNode = (ConstantTreeNode)constant.CreateTreeNode();
constantTreeNode.Value = value;
return(constantTreeNode);
}
public InteractiveSymbolicTimeSeriesPrognosisSolutionSimplifierView()
: base() {
InitializeComponent();
this.Caption = "Interactive Time-Series Prognosis Solution Simplifier";
constantNode = ((ConstantTreeNode)new Constant().CreateTreeNode());
ISymbolicExpressionTreeNode root = new ProgramRootSymbol().CreateTreeNode();
ISymbolicExpressionTreeNode start = new StartSymbol().CreateTreeNode();
root.AddSubtree(start);
tempTree = new SymbolicExpressionTree(root);
}
public InteractiveSymbolicTimeSeriesPrognosisSolutionSimplifierView()
: base()
{
InitializeComponent();
this.Caption = "Interactive Time-Series Prognosis Solution Simplifier";
constantNode = ((ConstantTreeNode) new Constant().CreateTreeNode());
ISymbolicExpressionTreeNode root = new ProgramRootSymbol().CreateTreeNode();
ISymbolicExpressionTreeNode start = new StartSymbol().CreateTreeNode();
root.AddSubtree(start);
tempTree = new SymbolicExpressionTree(root);
}
private static void UpdateConstants(ISymbolicExpressionTree tree, double[] constants)
{
int i = 0;
foreach (var node in tree.Root.IterateNodesPrefix().OfType <SymbolicExpressionTreeTerminalNode>())
{
ConstantTreeNode constantTreeNode = node as ConstantTreeNode;
VariableTreeNode variableTreeNode = node as VariableTreeNode;
if (constantTreeNode != null)
{
constantTreeNode.Value = constants[i++];
}
else if (variableTreeNode != null)
{
variableTreeNode.Weight = constants[i++];
}
}
}
public override void CalculateImpactAndReplacementValues(ISymbolicDataAnalysisModel model, ISymbolicExpressionTreeNode node,
IDataAnalysisProblemData problemData, IEnumerable <int> rows, out double impactValue, out double replacementValue, out double newQualityForImpactsCalculation,
double qualityForImpactsCalculation = Double.NaN)
{
var regressionModel = (ISymbolicRegressionModel)model;
var regressionProblemData = (IRegressionProblemData)problemData;
var dataset = regressionProblemData.Dataset;
var targetValues = dataset.GetDoubleValues(regressionProblemData.TargetVariable, rows);
OnlineCalculatorError errorState;
if (double.IsNaN(qualityForImpactsCalculation))
{
qualityForImpactsCalculation = CalculateQualityForImpacts(regressionModel, regressionProblemData, rows);
}
replacementValue = CalculateReplacementValue(regressionModel, node, regressionProblemData, rows);
var constantNode = new ConstantTreeNode(new Constant())
{
Value = replacementValue
};
var cloner = new Cloner();
var tempModel = cloner.Clone(regressionModel);
var tempModelNode = (ISymbolicExpressionTreeNode)cloner.GetClone(node);
var tempModelParentNode = tempModelNode.Parent;
int i = tempModelParentNode.IndexOfSubtree(tempModelNode);
tempModelParentNode.RemoveSubtree(i);
tempModelParentNode.InsertSubtree(i, constantNode);
var estimatedValues = tempModel.GetEstimatedValues(dataset, rows);
double r = OnlinePearsonsRCalculator.Calculate(targetValues, estimatedValues, out errorState);
if (errorState != OnlineCalculatorError.None)
{
r = 0.0;
}
newQualityForImpactsCalculation = r * r;
impactValue = qualityForImpactsCalculation - newQualityForImpactsCalculation;
}
private TreeNode FillTreeNode(Expression expression)
{
TreeNode treeNode = new NullTreeNode();
if (expression is BinaryExpression binary)
{
treeNode = new BinaryTreeNode()
{
Operator = expression.NodeType,
Left = FillTreeNode(binary.Left),
Right = FillTreeNode(binary.Right),
};
}
else if (expression is MemberExpression)
{
treeNode = new AccessorTreeNode()
{
Accessor = expression.ToString()
};
}
else if (expression is ConstantExpression)
{
treeNode = new ConstantTreeNode()
{
Constant = expression.ToString()
};
}
else if (expression is MethodCallExpression methodCall)
{
treeNode = new MethodCallTreeNode()
{
Method = methodCall.Method.Name,
Arguments = methodCall.Arguments.Select(x => x.ToString()).ToArray(),
Accessor = methodCall.Object.ToString()
};
}
else if (expression is LambdaExpression lambdaExpr)
{
treeNode = FillTreeNode(lambdaExpr.Body);
}
return(treeNode);
}
public static double OptimizeConstants(ISymbolicDataAnalysisExpressionTreeInterpreter interpreter, ISymbolicExpressionTree tree, IRegressionProblemData problemData, IEnumerable <int> rows, bool applyLinearScaling, int maxIterations, bool updateVariableWeights = true, double lowerEstimationLimit = double.MinValue, double upperEstimationLimit = double.MaxValue, bool updateConstantsInTree = true)
{
List <AutoDiff.Variable> variables = new List <AutoDiff.Variable>();
List <AutoDiff.Variable> parameters = new List <AutoDiff.Variable>();
List <string> variableNames = new List <string>();
AutoDiff.Term func;
if (!TryTransformToAutoDiff(tree.Root.GetSubtree(0), variables, parameters, variableNames, updateVariableWeights, out func))
{
throw new NotSupportedException("Could not optimize constants of symbolic expression tree due to not supported symbols used in the tree.");
}
if (variableNames.Count == 0)
{
return(0.0);
}
AutoDiff.IParametricCompiledTerm compiledFunc = func.Compile(variables.ToArray(), parameters.ToArray());
List <SymbolicExpressionTreeTerminalNode> terminalNodes = null;
if (updateVariableWeights)
{
terminalNodes = tree.Root.IterateNodesPrefix().OfType <SymbolicExpressionTreeTerminalNode>().ToList();
}
else
{
terminalNodes = new List <SymbolicExpressionTreeTerminalNode>(tree.Root.IterateNodesPrefix().OfType <ConstantTreeNode>());
}
//extract inital constants
double[] c = new double[variables.Count];
{
c[0] = 0.0;
c[1] = 1.0;
int i = 2;
foreach (var node in terminalNodes)
{
ConstantTreeNode constantTreeNode = node as ConstantTreeNode;
VariableTreeNode variableTreeNode = node as VariableTreeNode;
if (constantTreeNode != null)
{
c[i++] = constantTreeNode.Value;
}
else if (updateVariableWeights && variableTreeNode != null)
{
c[i++] = variableTreeNode.Weight;
}
}
}
double[] originalConstants = (double[])c.Clone();
double originalQuality = SymbolicRegressionSingleObjectivePearsonRSquaredEvaluator.Calculate(interpreter, tree, lowerEstimationLimit, upperEstimationLimit, problemData, rows, applyLinearScaling);
alglib.lsfitstate state;
alglib.lsfitreport rep;
int info;
IDataset ds = problemData.Dataset;
double[,] x = new double[rows.Count(), variableNames.Count];
int row = 0;
foreach (var r in rows)
{
for (int col = 0; col < variableNames.Count; col++)
{
x[row, col] = ds.GetDoubleValue(variableNames[col], r);
}
row++;
}
double[] y = ds.GetDoubleValues(problemData.TargetVariable, rows).ToArray();
int n = x.GetLength(0);
int m = x.GetLength(1);
int k = c.Length;
alglib.ndimensional_pfunc function_cx_1_func = CreatePFunc(compiledFunc);
alglib.ndimensional_pgrad function_cx_1_grad = CreatePGrad(compiledFunc);
try {
alglib.lsfitcreatefg(x, y, c, n, m, k, false, out state);
alglib.lsfitsetcond(state, 0.0, 0.0, maxIterations);
//alglib.lsfitsetgradientcheck(state, 0.001);
alglib.lsfitfit(state, function_cx_1_func, function_cx_1_grad, null, null);
alglib.lsfitresults(state, out info, out c, out rep);
}
catch (ArithmeticException) {
return(originalQuality);
}
catch (alglib.alglibexception) {
return(originalQuality);
}
//info == -7 => constant optimization failed due to wrong gradient
if (info != -7)
{
UpdateConstants(tree, c.Skip(2).ToArray(), updateVariableWeights);
}
var quality = SymbolicRegressionSingleObjectivePearsonRSquaredEvaluator.Calculate(interpreter, tree, lowerEstimationLimit, upperEstimationLimit, problemData, rows, applyLinearScaling);
if (!updateConstantsInTree)
{
UpdateConstants(tree, originalConstants.Skip(2).ToArray(), updateVariableWeights);
}
if (originalQuality - quality > 0.001 || double.IsNaN(quality))
{
UpdateConstants(tree, originalConstants.Skip(2).ToArray(), updateVariableWeights);
return(originalQuality);
}
return(quality);
}
public ConstantNodeEditDialog(ISymbolicExpressionTreeNode node) {
InitializeComponent();
oldValueTextBox.TabStop = false; // cannot receive focus using tab key
NewNode = (ConstantTreeNode)node;
InitializeFields();
}
private ISymbolicExpressionTreeNode MakeProduct(ConstantTreeNode c, double weight) {
var mul = new Multiplication();
var prod = mul.CreateTreeNode();
prod.AddSubtree(MakeConstantTreeNode(weight));
prod.AddSubtree(c);
return prod;
}
private static ITimeSeriesPrognosisSolution CreateAutoRegressiveSolution(ITimeSeriesPrognosisProblemData problemData, int timeOffset, out double rmsError, out double cvRmsError)
{
string targetVariable = problemData.TargetVariable;
double[,] inputMatrix = new double[problemData.TrainingPartition.Size, timeOffset + 1];
var targetValues = problemData.Dataset.GetDoubleValues(targetVariable).ToList();
for (int i = 0, row = problemData.TrainingPartition.Start; i < problemData.TrainingPartition.Size; i++, row++)
{
for (int col = 0; col < timeOffset; col++)
{
inputMatrix[i, col] = targetValues[row - col - 1];
}
}
// set target values in last column
for (int i = 0; i < inputMatrix.GetLength(0); i++)
{
inputMatrix[i, timeOffset] = targetValues[i + problemData.TrainingPartition.Start];
}
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);
for (int i = 0; i < timeOffset; i++)
{
LaggedVariableTreeNode node = (LaggedVariableTreeNode) new LaggedVariable().CreateTreeNode();
node.VariableName = targetVariable;
node.Weight = coefficients[i];
node.Lag = (i + 1) * -1;
addition.AddSubtree(node);
}
ConstantTreeNode cNode = (ConstantTreeNode) new Constant().CreateTreeNode();
cNode.Value = coefficients[coefficients.Length - 1];
addition.AddSubtree(cNode);
var interpreter = new SymbolicTimeSeriesPrognosisExpressionTreeInterpreter(problemData.TargetVariable);
var model = new SymbolicTimeSeriesPrognosisModel(problemData.TargetVariable, tree, interpreter);
var solution = model.CreateTimeSeriesPrognosisSolution((ITimeSeriesPrognosisProblemData)problemData.Clone());
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);
}