public override IOperation InstrumentedApply()
{
var solution = SymbolicExpressionTreeParameter.ActualValue;
double quality;
if (RandomParameter.ActualValue.NextDouble() < ConstantOptimizationProbability.Value)
{
IEnumerable <int> constantOptimizationRows = GenerateRowsToEvaluate(ConstantOptimizationRowsPercentage.Value);
quality = OptimizeConstants(SymbolicDataAnalysisTreeInterpreterParameter.ActualValue, solution, ProblemDataParameter.ActualValue,
constantOptimizationRows, ApplyLinearScalingParameter.ActualValue.Value, ConstantOptimizationIterations.Value, updateVariableWeights: UpdateVariableWeights, lowerEstimationLimit: EstimationLimitsParameter.ActualValue.Lower, upperEstimationLimit: EstimationLimitsParameter.ActualValue.Upper, updateConstantsInTree: UpdateConstantsInTree);
if (ConstantOptimizationRowsPercentage.Value != RelativeNumberOfEvaluatedSamplesParameter.ActualValue.Value)
{
var evaluationRows = GenerateRowsToEvaluate();
quality = SymbolicRegressionSingleObjectivePearsonRSquaredEvaluator.Calculate(SymbolicDataAnalysisTreeInterpreterParameter.ActualValue, solution, EstimationLimitsParameter.ActualValue.Lower, EstimationLimitsParameter.ActualValue.Upper, ProblemDataParameter.ActualValue, evaluationRows, ApplyLinearScalingParameter.ActualValue.Value);
}
}
else
{
var evaluationRows = GenerateRowsToEvaluate();
quality = SymbolicRegressionSingleObjectivePearsonRSquaredEvaluator.Calculate(SymbolicDataAnalysisTreeInterpreterParameter.ActualValue, solution, EstimationLimitsParameter.ActualValue.Lower, EstimationLimitsParameter.ActualValue.Upper, ProblemDataParameter.ActualValue, evaluationRows, ApplyLinearScalingParameter.ActualValue.Value);
}
QualityParameter.ActualValue = new DoubleValue(quality);
return(base.InstrumentedApply());
}
} // maximize R² and minimize average similarity
public override IOperation InstrumentedApply()
{
IEnumerable <int> rows = GenerateRowsToEvaluate();
var solution = SymbolicExpressionTreeParameter.ActualValue;
var problemData = ProblemDataParameter.ActualValue;
var interpreter = SymbolicDataAnalysisTreeInterpreterParameter.ActualValue;
var estimationLimits = EstimationLimitsParameter.ActualValue;
var applyLinearScaling = ApplyLinearScalingParameter.ActualValue.Value;
if (UseConstantOptimization)
{
SymbolicRegressionConstantOptimizationEvaluator.OptimizeConstants(interpreter, solution, problemData, rows, applyLinearScaling, ConstantOptimizationIterations, updateVariableWeights: ConstantOptimizationUpdateVariableWeights, lowerEstimationLimit: estimationLimits.Lower, upperEstimationLimit: estimationLimits.Upper);
}
double r2 = SymbolicRegressionSingleObjectivePearsonRSquaredEvaluator.Calculate(interpreter, solution, estimationLimits.Lower, estimationLimits.Upper, problemData, rows, applyLinearScaling);
if (DecimalPlaces >= 0)
{
r2 = Math.Round(r2, DecimalPlaces);
}
lock (locker) {
if (AverageSimilarityParameter.ActualValue == null)
{
var context = new ExecutionContext(null, SimilarityCalculator, ExecutionContext.Scope.Parent);
SimilarityCalculator.StrictSimilarity = StrictSimilarity;
SimilarityCalculator.Execute(context, CancellationToken);
}
}
var avgSimilarity = AverageSimilarityParameter.ActualValue.Value;
QualitiesParameter.ActualValue = new DoubleArray(new[] { r2, avgSimilarity });
return(base.InstrumentedApply());
}
public override double[] Evaluate(IExecutionContext context, ISymbolicExpressionTree tree, IRegressionProblemData problemData, IEnumerable <int> rows)
{
SymbolicDataAnalysisTreeInterpreterParameter.ExecutionContext = context;
AverageSimilarityParameter.ExecutionContext = context;
EstimationLimitsParameter.ExecutionContext = context;
ApplyLinearScalingParameter.ExecutionContext = context;
var estimationLimits = EstimationLimitsParameter.ActualValue;
var applyLinearScaling = ApplyLinearScalingParameter.ActualValue.Value;
double r2 = SymbolicRegressionSingleObjectivePearsonRSquaredEvaluator.Calculate(SymbolicDataAnalysisTreeInterpreterParameter.ActualValue, tree, estimationLimits.Lower, estimationLimits.Upper, problemData, rows, applyLinearScaling);
lock (locker) {
if (AverageSimilarityParameter.ActualValue == null)
{
var ctx = new ExecutionContext(null, SimilarityCalculator, context.Scope.Parent);
SimilarityCalculator.StrictSimilarity = StrictSimilarity;
SimilarityCalculator.Execute(context, CancellationToken);
}
}
var avgSimilarity = AverageSimilarityParameter.ActualValue.Value;
SymbolicDataAnalysisTreeInterpreterParameter.ExecutionContext = null;
EstimationLimitsParameter.ExecutionContext = null;
ApplyLinearScalingParameter.ExecutionContext = null;
return(new[] { r2, avgSimilarity });
}
public static double[] Calculate(ISymbolicDataAnalysisExpressionTreeInterpreter interpreter, ISymbolicExpressionTree solution, double lowerEstimationLimit, double upperEstimationLimit, IRegressionProblemData problemData, IEnumerable <int> rows, bool applyLinearScaling, int decimalPlaces)
{
double r2 = SymbolicRegressionSingleObjectivePearsonRSquaredEvaluator.Calculate(interpreter, solution, lowerEstimationLimit, upperEstimationLimit, problemData, rows, applyLinearScaling);
if (decimalPlaces >= 0)
{
r2 = Math.Round(r2, decimalPlaces);
}
return(new double[2] {
r2, SymbolicDataAnalysisModelComplexityCalculator.CalculateComplexity(solution)
});
}
public static double[] Calculate(ISymbolicDataAnalysisExpressionTreeInterpreter interpreter, ISymbolicExpressionTree solution, double lowerEstimationLimit, double upperEstimationLimit, IRegressionProblemData problemData, IEnumerable <int> rows, bool applyLinearScaling, int decimalPlaces)
{
double r2 = SymbolicRegressionSingleObjectivePearsonRSquaredEvaluator.Calculate(interpreter, solution, lowerEstimationLimit, upperEstimationLimit, problemData, rows, applyLinearScaling);
if (decimalPlaces >= 0)
{
r2 = Math.Round(r2, decimalPlaces);
}
return(new double[2] {
r2, solution.IterateNodesPostfix().OfType <IVariableTreeNode>().Count()
}); // count the number of variables
}
public static double[] Calculate(ISymbolicDataAnalysisExpressionTreeInterpreter interpreter, ISymbolicExpressionTree solution, double lowerEstimationLimit, double upperEstimationLimit, IRegressionProblemData problemData, IEnumerable <int> rows, bool applyLinearScaling, int decimalPlaces)
{
double r2 = SymbolicRegressionSingleObjectivePearsonRSquaredEvaluator.Calculate(interpreter, solution, lowerEstimationLimit, upperEstimationLimit, problemData, rows, applyLinearScaling);
if (decimalPlaces >= 0)
{
r2 = Math.Round(r2, decimalPlaces);
}
return(new double[2] {
r2, solution.IterateNodesPostfix().Sum(n => n.GetLength())
}); // sum of the length of the whole sub-tree for each node
}
public override double Evaluate(IExecutionContext context, ISymbolicExpressionTree tree, IRegressionProblemData problemData, IEnumerable <int> rows)
{
SymbolicDataAnalysisTreeInterpreterParameter.ExecutionContext = context;
EstimationLimitsParameter.ExecutionContext = context;
ApplyLinearScalingParameter.ExecutionContext = context;
// Pearson R² evaluator is used on purpose instead of the const-opt evaluator,
// because Evaluate() is used to get the quality of evolved models on
// different partitions of the dataset (e.g., best validation model)
double r2 = SymbolicRegressionSingleObjectivePearsonRSquaredEvaluator.Calculate(SymbolicDataAnalysisTreeInterpreterParameter.ActualValue, tree, EstimationLimitsParameter.ActualValue.Lower, EstimationLimitsParameter.ActualValue.Upper, problemData, rows, ApplyLinearScalingParameter.ActualValue.Value);
SymbolicDataAnalysisTreeInterpreterParameter.ExecutionContext = null;
EstimationLimitsParameter.ExecutionContext = null;
ApplyLinearScalingParameter.ExecutionContext = null;
return(r2);
}
protected SymbolicRegressionSingleObjectivePearsonRSquaredEvaluator(SymbolicRegressionSingleObjectivePearsonRSquaredEvaluator original, Cloner cloner)
: base(original, cloner)
{
}
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 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, Action <double[], double, object> iterationCallback = null, EvaluationsCounter counter = null)
{
// numeric constants in the tree become variables for constant opt
// variables in the tree become parameters (fixed values) for constant opt
// for each parameter (variable in the original tree) we store the
// variable name, variable value (for factor vars) and lag as a DataForVariable object.
// A dictionary is used to find parameters
double[] initialConstants;
var parameters = new List <TreeToAutoDiffTermConverter.DataForVariable>();
TreeToAutoDiffTermConverter.ParametricFunction func;
TreeToAutoDiffTermConverter.ParametricFunctionGradient func_grad;
if (!TreeToAutoDiffTermConverter.TryConvertToAutoDiff(tree, updateVariableWeights, applyLinearScaling, out parameters, out initialConstants, out func, out func_grad))
{
throw new NotSupportedException("Could not optimize constants of symbolic expression tree due to not supported symbols used in the tree.");
}
if (parameters.Count == 0)
{
return(0.0); // gkronber: constant expressions always have a R² of 0.0
}
var parameterEntries = parameters.ToArray(); // order of entries must be the same for x
//extract inital constants
double[] c;
if (applyLinearScaling)
{
c = new double[initialConstants.Length + 2];
c[0] = 0.0;
c[1] = 1.0;
Array.Copy(initialConstants, 0, c, 2, initialConstants.Length);
}
else
{
c = (double[])initialConstants.Clone();
}
double originalQuality = SymbolicRegressionSingleObjectivePearsonRSquaredEvaluator.Calculate(interpreter, tree, lowerEstimationLimit, upperEstimationLimit, problemData, rows, applyLinearScaling);
if (counter == null)
{
counter = new EvaluationsCounter();
}
var rowEvaluationsCounter = new EvaluationsCounter();
alglib.lsfitstate state;
alglib.lsfitreport rep;
int retVal;
IDataset ds = problemData.Dataset;
double[,] x = new double[rows.Count(), parameters.Count];
int row = 0;
foreach (var r in rows)
{
int col = 0;
foreach (var info in parameterEntries)
{
if (ds.VariableHasType <double>(info.variableName))
{
x[row, col] = ds.GetDoubleValue(info.variableName, r + info.lag);
}
else if (ds.VariableHasType <string>(info.variableName))
{
x[row, col] = ds.GetStringValue(info.variableName, r) == info.variableValue ? 1 : 0;
}
else
{
throw new InvalidProgramException("found a variable of unknown type");
}
col++;
}
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(func);
alglib.ndimensional_pgrad function_cx_1_grad = CreatePGrad(func_grad);
alglib.ndimensional_rep xrep = (p, f, obj) => iterationCallback(p, f, obj);
try {
alglib.lsfitcreatefg(x, y, c, n, m, k, false, out state);
alglib.lsfitsetcond(state, 0.0, 0.0, maxIterations);
alglib.lsfitsetxrep(state, iterationCallback != null);
//alglib.lsfitsetgradientcheck(state, 0.001);
alglib.lsfitfit(state, function_cx_1_func, function_cx_1_grad, xrep, rowEvaluationsCounter);
alglib.lsfitresults(state, out retVal, out c, out rep);
} catch (ArithmeticException) {
return(originalQuality);
} catch (alglib.alglibexception) {
return(originalQuality);
}
counter.FunctionEvaluations += rowEvaluationsCounter.FunctionEvaluations / n;
counter.GradientEvaluations += rowEvaluationsCounter.GradientEvaluations / n;
//retVal == -7 => constant optimization failed due to wrong gradient
if (retVal != -7)
{
if (applyLinearScaling)
{
var tmp = new double[c.Length - 2];
Array.Copy(c, 2, tmp, 0, tmp.Length);
UpdateConstants(tree, tmp, updateVariableWeights);
}
else
{
UpdateConstants(tree, c, updateVariableWeights);
}
}
var quality = SymbolicRegressionSingleObjectivePearsonRSquaredEvaluator.Calculate(interpreter, tree, lowerEstimationLimit, upperEstimationLimit, problemData, rows, applyLinearScaling);
if (!updateConstantsInTree)
{
UpdateConstants(tree, initialConstants, updateVariableWeights);
}
if (originalQuality - quality > 0.001 || double.IsNaN(quality))
{
UpdateConstants(tree, initialConstants, updateVariableWeights);
return(originalQuality);
}
return(quality);
}
protected SymbolicRegressionSingleObjectivePearsonRSquaredEvaluator(SymbolicRegressionSingleObjectivePearsonRSquaredEvaluator original, Cloner cloner)
: base(original, cloner) {
}
