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);
}