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);
}
public void InfixExpressionParserTestFormatting()
{
var formatter = new InfixExpressionFormatter();
var parser = new InfixExpressionParser();
Console.WriteLine(formatter.Format(parser.Parse("3")));
Console.WriteLine(formatter.Format(parser.Parse("3*3")));
Console.WriteLine(formatter.Format(parser.Parse("3 * 4")));
Console.WriteLine(formatter.Format(parser.Parse("123E-03")));
Console.WriteLine(formatter.Format(parser.Parse("123e-03")));
Console.WriteLine(formatter.Format(parser.Parse("123e+03")));
Console.WriteLine(formatter.Format(parser.Parse("123E+03")));
Console.WriteLine(formatter.Format(parser.Parse("123.0E-03")));
Console.WriteLine(formatter.Format(parser.Parse("123.0e-03")));
Console.WriteLine(formatter.Format(parser.Parse("123.0e+03")));
Console.WriteLine(formatter.Format(parser.Parse("123.0E+03")));
Console.WriteLine(formatter.Format(parser.Parse("123.0E-3")));
Console.WriteLine(formatter.Format(parser.Parse("123.0e-3")));
Console.WriteLine(formatter.Format(parser.Parse("123.0e+3")));
Console.WriteLine(formatter.Format(parser.Parse("123.0E+3")));
Console.WriteLine(formatter.Format(parser.Parse("3.1415+2.0")));
Console.WriteLine(formatter.Format(parser.Parse("3.1415/2.0")));
Console.WriteLine(formatter.Format(parser.Parse("3.1415*2.0")));
Console.WriteLine(formatter.Format(parser.Parse("3.1415-2.0")));
// round-trip
Console.WriteLine(formatter.Format(parser.Parse(formatter.Format(parser.Parse("3.1415-2.0")))));
Console.WriteLine(formatter.Format(parser.Parse("3.1415+(2.0)")));
Console.WriteLine(formatter.Format(parser.Parse("(3.1415+(2.0))")));
Console.WriteLine(formatter.Format(parser.Parse("log(3)")));
Console.WriteLine(formatter.Format(parser.Parse("log(-3)")));
Console.WriteLine(formatter.Format(parser.Parse("exp(3)")));
Console.WriteLine(formatter.Format(parser.Parse("exp(-3)")));
Console.WriteLine(formatter.Format(parser.Parse("sqrt(3)")));
Console.WriteLine(formatter.Format(parser.Parse("sqr((-3))")));
Console.WriteLine(formatter.Format(parser.Parse("3/3+2/2+1/1")));
Console.WriteLine(formatter.Format(parser.Parse("-3+30-2+20-1+10")));
// round trip
Console.WriteLine(formatter.Format(parser.Parse(formatter.Format(parser.Parse("-3+30-2+20-1+10")))));
Console.WriteLine(formatter.Format(parser.Parse("\"x1\"")));
Console.WriteLine(formatter.Format(parser.Parse("\'var name\'")));
Console.WriteLine(formatter.Format(parser.Parse("\"var name\"")));
Console.WriteLine(formatter.Format(parser.Parse("\"1\"")));
Console.WriteLine(formatter.Format(parser.Parse("'var \" name\'")));
Console.WriteLine(formatter.Format(parser.Parse("\"var \' name\"")));
Console.WriteLine(formatter.Format(parser.Parse("\"x1\"*\"x2\"")));
Console.WriteLine(formatter.Format(parser.Parse("\"x1\"*\"x2\"+\"x3\"*\"x4\"")));
Console.WriteLine(formatter.Format(parser.Parse("x1*x2+x3*x4")));
}
public void InfixExpressionParserTestFormatting() {
var formatter = new InfixExpressionFormatter();
var parser = new InfixExpressionParser();
Console.WriteLine(formatter.Format(parser.Parse("3")));
Console.WriteLine(formatter.Format(parser.Parse("3*3")));
Console.WriteLine(formatter.Format(parser.Parse("3 * 4")));
Console.WriteLine(formatter.Format(parser.Parse("123E-03") ));
Console.WriteLine(formatter.Format(parser.Parse("123e-03")));
Console.WriteLine(formatter.Format(parser.Parse("123e+03")));
Console.WriteLine(formatter.Format(parser.Parse("123E+03")));
Console.WriteLine(formatter.Format(parser.Parse("123.0E-03")));
Console.WriteLine(formatter.Format(parser.Parse("123.0e-03")));
Console.WriteLine(formatter.Format(parser.Parse("123.0e+03")));
Console.WriteLine(formatter.Format(parser.Parse("123.0E+03")));
Console.WriteLine(formatter.Format(parser.Parse("123.0E-3")));
Console.WriteLine(formatter.Format(parser.Parse("123.0e-3")));
Console.WriteLine(formatter.Format(parser.Parse("123.0e+3")));
Console.WriteLine(formatter.Format(parser.Parse("123.0E+3")));
Console.WriteLine(formatter.Format(parser.Parse("3.1415+2.0")));
Console.WriteLine(formatter.Format(parser.Parse("3.1415/2.0")));
Console.WriteLine(formatter.Format(parser.Parse("3.1415*2.0")));
Console.WriteLine(formatter.Format(parser.Parse("3.1415-2.0")));
// round-trip
Console.WriteLine(formatter.Format(parser.Parse(formatter.Format(parser.Parse("3.1415-2.0")))));
Console.WriteLine(formatter.Format(parser.Parse("3.1415+(2.0)")));
Console.WriteLine(formatter.Format(parser.Parse("(3.1415+(2.0))")));
Console.WriteLine(formatter.Format(parser.Parse("log(3)")));
Console.WriteLine(formatter.Format(parser.Parse("log(-3)")));
Console.WriteLine(formatter.Format(parser.Parse("exp(3)")));
Console.WriteLine(formatter.Format(parser.Parse("exp(-3)")));
Console.WriteLine(formatter.Format(parser.Parse("sqrt(3)")));
Console.WriteLine(formatter.Format(parser.Parse("sqr((-3))")));
Console.WriteLine(formatter.Format(parser.Parse("3/3+2/2+1/1")));
Console.WriteLine(formatter.Format(parser.Parse("-3+30-2+20-1+10")));
// round trip
Console.WriteLine(formatter.Format(parser.Parse(formatter.Format(parser.Parse("-3+30-2+20-1+10")))));
Console.WriteLine(formatter.Format(parser.Parse("\"x1\"")));
Console.WriteLine(formatter.Format(parser.Parse("\'var name\'")));
Console.WriteLine(formatter.Format(parser.Parse("\"var name\"")));
Console.WriteLine(formatter.Format(parser.Parse("\"1\"")));
Console.WriteLine(formatter.Format(parser.Parse("'var \" name\'")));
Console.WriteLine(formatter.Format(parser.Parse("\"var \' name\"")));
Console.WriteLine(formatter.Format(parser.Parse("\"x1\"*\"x2\"")));
Console.WriteLine(formatter.Format(parser.Parse("\"x1\"*\"x2\"+\"x3\"*\"x4\"")));
Console.WriteLine(formatter.Format(parser.Parse("x1*x2+x3*x4")));
}
private string Derive(string expr, string variable)
{
var parser = new InfixExpressionParser();
var formatter = new InfixExpressionFormatter();
var t = parser.Parse(expr);
var tPrime = DerivativeCalculator.Derive(t, variable);
return(formatter.Format(tPrime));
}
private void EvaluateTest(string expression, Interval expectedResult, Dictionary <string, Interval> variableRanges = null, double lowerDelta = 0, double upperDelta = 0)
{
var parser = new InfixExpressionParser();
var tree = parser.Parse(expression);
var interpreter = new IntervalInterpreter();
Interval result;
if (variableRanges == null)
{
result = interpreter.GetSymbolicExpressionTreeInterval(tree, problemData.Dataset, problemData.AllIndices);
}
else
{
result = interpreter.GetSymbolicExpressionTreeInterval(tree, variableRanges);
}
Assert.AreEqual(expectedResult.LowerBound, result.LowerBound, lowerDelta);
Assert.AreEqual(expectedResult.UpperBound, result.UpperBound, upperDelta);
}
/*
* Creates an ISymbolicExpressionTree out of the list of a model
* It does so by creating a string which will then get parsed by the InfixExpressionParser
*/
private ISymbolicExpressionTree Tree(IEnumerable <BasisFunction> basisFunctions, double[] coeffs, double offset)
{
if (basisFunctions.Count(val => true) != coeffs.Length)
{
throw new ArgumentException();
}
var culture = new CultureInfo("en-US");
var numNumeratorFuncs = ConsiderDenominations ? basisFunctions.Count() / 2 : basisFunctions.Count();
// true if there exists at least 1 coefficient value in the model that is part of the denominator
// (i.e. if there exists at least 1 non-zero value in the second half of the array)
bool withDenom = coeffs.OrderByDescending(val => val).Take(coeffs.Length / 2).ToArray().Any(val => !val.IsAlmost(0.0));
string model = "(" + offset.ToString(culture);
for (int i = 0; i < numNumeratorFuncs; i++)
{
var func = basisFunctions.ElementAt(i);
// only generate nodes for relevant basis functions (those with non-zero coeffs)
if (coeffs[i] != 0)
{
model += " + (" + coeffs[i].ToString(culture) + ") * " + func.Var;
}
}
if (ConsiderDenominations && withDenom)
{
model += ") / (1";
for (int i = numNumeratorFuncs; i < basisFunctions.Count(); i++)
{
var func = basisFunctions.ElementAt(i);
// only generate nodes for relevant basis functions (those with non-zero coeffs)
if (coeffs[i] != 0)
{
model += " + (" + coeffs[i].ToString(culture) + ") * " + func.Var;
}
}
}
model += ")";
InfixExpressionParser p = new InfixExpressionParser();
return(p.Parse(model));
}
public void InfixExpressionParserTestFormatting()
{
var formatter = new InfixExpressionFormatter();
var parser = new InfixExpressionParser();
Console.WriteLine(formatter.Format(parser.Parse("3")));
Console.WriteLine(formatter.Format(parser.Parse("3*3")));
Console.WriteLine(formatter.Format(parser.Parse("3 * 4")));
Console.WriteLine(formatter.Format(parser.Parse("123E-03")));
Console.WriteLine(formatter.Format(parser.Parse("123e-03")));
Console.WriteLine(formatter.Format(parser.Parse("123e+03")));
Console.WriteLine(formatter.Format(parser.Parse("123E+03")));
Console.WriteLine(formatter.Format(parser.Parse("123.0E-03")));
Console.WriteLine(formatter.Format(parser.Parse("123.0e-03")));
Console.WriteLine(formatter.Format(parser.Parse("123.0e+03")));
Console.WriteLine(formatter.Format(parser.Parse("123.0E+03")));
Console.WriteLine(formatter.Format(parser.Parse("123.0E-3")));
Console.WriteLine(formatter.Format(parser.Parse("123.0e-3")));
Console.WriteLine(formatter.Format(parser.Parse("123.0e+3")));
Console.WriteLine(formatter.Format(parser.Parse("123.0E+3")));
Console.WriteLine(formatter.Format(parser.Parse("3.1415+2.0")));
Console.WriteLine(formatter.Format(parser.Parse("3.1415/2.0")));
Console.WriteLine(formatter.Format(parser.Parse("3.1415*2.0")));
Console.WriteLine(formatter.Format(parser.Parse("3.1415-2.0")));
// round-trip
Console.WriteLine(formatter.Format(parser.Parse(formatter.Format(parser.Parse("3.1415-2.0")))));
Console.WriteLine(formatter.Format(parser.Parse("3.1415+(2.0)")));
Console.WriteLine(formatter.Format(parser.Parse("(3.1415+(2.0))")));
Console.WriteLine(formatter.Format(parser.Parse("log(3)")));
Console.WriteLine(formatter.Format(parser.Parse("log(-3)")));
Console.WriteLine(formatter.Format(parser.Parse("exp(3)")));
Console.WriteLine(formatter.Format(parser.Parse("exp(-3)")));
Console.WriteLine(formatter.Format(parser.Parse("sqrt(3)")));
Console.WriteLine(formatter.Format(parser.Parse("sqr((-3))")));
Console.WriteLine(formatter.Format(parser.Parse("3/3+2/2+1/1")));
Console.WriteLine(formatter.Format(parser.Parse("-3+30-2+20-1+10")));
// round trip
Console.WriteLine(formatter.Format(parser.Parse(formatter.Format(parser.Parse("-3+30-2+20-1+10")))));
Console.WriteLine(formatter.Format(parser.Parse("\"x1\"")));
Console.WriteLine(formatter.Format(parser.Parse("\'var name\'")));
Console.WriteLine(formatter.Format(parser.Parse("\"var name\"")));
Console.WriteLine(formatter.Format(parser.Parse("\"1\"")));
Console.WriteLine(formatter.Format(parser.Parse("'var \" name\'")));
Console.WriteLine(formatter.Format(parser.Parse("\"var \' name\"")));
Console.WriteLine(formatter.Format(parser.Parse("\"x1\"*\"x2\"")));
Console.WriteLine(formatter.Format(parser.Parse("\"x1\"*\"x2\"+\"x3\"*\"x4\"")));
Console.WriteLine(formatter.Format(parser.Parse("x1*x2+x3*x4")));
Console.WriteLine(formatter.Format(parser.Parse("POW(3, 2)")));
Console.WriteLine(formatter.Format(parser.Parse("POW(3.1, 2.1)")));
Console.WriteLine(formatter.Format(parser.Parse("POW(3.1 , 2.1)")));
Console.WriteLine(formatter.Format(parser.Parse("POW(3.1 ,2.1)")));
Console.WriteLine(formatter.Format(parser.Parse("POW(-3.1 , - 2.1)")));
Console.WriteLine(formatter.Format(parser.Parse("ROOT(3, 2)")));
Console.WriteLine(formatter.Format(parser.Parse("ROOT(3.1, 2.1)")));
Console.WriteLine(formatter.Format(parser.Parse("ROOT(3.1 , 2.1)")));
Console.WriteLine(formatter.Format(parser.Parse("ROOT(3.1 ,2.1)")));
Console.WriteLine(formatter.Format(parser.Parse("ROOT(-3.1 , - 2.1)")));
Console.WriteLine(formatter.Format(parser.Parse("IF(GT( 0, 1), 1, 0)")));
Console.WriteLine(formatter.Format(parser.Parse("IF(LT(0,1), 1 , 0)")));
Console.WriteLine(formatter.Format(parser.Parse("LAG(x, 1)")));
Console.WriteLine(formatter.Format(parser.Parse("LAG(x, -1)")));
Console.WriteLine(formatter.Format(parser.Parse("LAG(x, +1)")));
Console.WriteLine(formatter.Format(parser.Parse("x * LAG('x', +1)")));
Console.WriteLine(formatter.Format(parser.Parse("x [1.0] * y")));
Console.WriteLine(formatter.Format(parser.Parse("x [1.0, 2.0] * y [1.0, 2.0]")));
Console.WriteLine(formatter.Format(parser.Parse("x[1] * y")));
Console.WriteLine(formatter.Format(parser.Parse("x[1, 2] * y [1, 2]")));
Console.WriteLine(formatter.Format(parser.Parse("x [+1.0] * y")));
Console.WriteLine(formatter.Format(parser.Parse("x [-1.0] * y")));
Console.WriteLine(formatter.Format(parser.Parse("x [-1.0, -2.0] * y [+1.0, +2.0]")));
Console.WriteLine(formatter.Format(parser.Parse("x='bla' * y")));
Console.WriteLine(formatter.Format(parser.Parse("x = 'bla'")));
Console.WriteLine(formatter.Format(parser.Parse("x = \"bla\"")));
Console.WriteLine(formatter.Format(parser.Parse("1.0 * x = bla")));
Console.WriteLine(formatter.Format(parser.Parse("-1.0 * x = bla")));
Console.WriteLine(formatter.Format(parser.Parse("+1.0 * \"x\" = bla + y = \"bla2\"")));
}
public void DeriveExpressions()
{
var formatter = new InfixExpressionFormatter();
var parser = new InfixExpressionParser();
Assert.AreEqual("0", Derive("3", "x"));
Assert.AreEqual("1", Derive("x", "x"));
Assert.AreEqual("10", Derive("10*x", "x"));
Assert.AreEqual("10", Derive("x*10", "x"));
Assert.AreEqual("(2*'x')", Derive("x*x", "x"));
Assert.AreEqual("((('x' * 'x') * 2) + ('x' * 'x'))", Derive("x*x*x", "x")); // simplifier does not merge (x*x)*2 + x*x to 3*x*x
Assert.AreEqual("0", Derive("10*x", "y"));
Assert.AreEqual("20", Derive("10*x+20*y", "y"));
Assert.AreEqual("6", Derive("2*3*x", "x"));
Assert.AreEqual("(10*'y')", Derive("10*x*y+20*y", "x"));
Assert.AreEqual("(1 / (SQR('x') * (-1)))", Derive("1/x", "x"));
Assert.AreEqual("('y' / (SQR('x') * (-1)))", Derive("y/x", "x"));
Assert.AreEqual("((((-2*'x') + (-1)) * ('a' + 'b')) / SQR(('x' + ('x' * 'x'))))",
Derive("(a+b)/(x+x*x)", "x"));
Assert.AreEqual("((((-2*'x') + (-1)) * ('a' + 'b')) / SQR(('x' + SQR('x'))))", Derive("(a+b)/(x+SQR(x))", "x"));
Assert.AreEqual("EXP('x')", Derive("exp(x)", "x"));
Assert.AreEqual("(EXP((3*'x')) * 3)", Derive("exp(3*x)", "x"));
Assert.AreEqual("(1 / 'x')", Derive("log(x)", "x"));
Assert.AreEqual("(1 / 'x')", Derive("log(3*x)", "x")); // 3 * 1/(3*x)
Assert.AreEqual("(1 / ('x' + (0.333333333333333*'y')))", Derive("log(3*x+y)", "x")); // simplifier does not try to keep fractions
Assert.AreEqual("(1 / (SQRT(((3*'x') + 'y')) * 0.666666666666667))", Derive("sqrt(3*x+y)", "x")); // 3 / (2 * sqrt(3*x+y)) = 1 / ((2/3) * sqrt(3*x+y))
Assert.AreEqual("(COS((3*'x')) * 3)", Derive("sin(3*x)", "x"));
Assert.AreEqual("(SIN((3*'x')) * (-3))", Derive("cos(3*x)", "x"));
Assert.AreEqual("(1 / (SQR(COS((3*'x'))) * 0.333333333333333))", Derive("tan(3*x)", "x")); // diff(tan(f(x)), x) = 1.0 / cos²(f(x)), simplifier puts constant factor into the denominator
Assert.AreEqual("((9*'x') / ABS((3*'x')))", Derive("abs(3*x)", "x"));
Assert.AreEqual("(SQR('x') * 3)", Derive("cube(x)", "x"));
Assert.AreEqual("(1 / (SQR(CUBEROOT('x')) * 3))", Derive("cuberoot(x)", "x"));
Assert.AreEqual("0", Derive("(a+b)/(x+SQR(x))", "y")); // df(a,b,x) / dy = 0
Assert.AreEqual("('a' * 'b' * 'c')", Derive("a*b*c*d", "d"));
Assert.AreEqual("('a' / ('b' * 'c' * SQR('d') * (-1)))", Derive("a/b/c/d", "d"));
Assert.AreEqual("('x' * ((SQR(TANH(SQR('x'))) * (-1)) + 1) * 2)", Derive("tanh(sqr(x))", "x")); // (2*'x'*(1 - SQR(TANH(SQR('x'))))
{
// special case: Inv(x) using only one argument to the division symbol
// f(x) = 1/x
var root = new ProgramRootSymbol().CreateTreeNode();
var start = new StartSymbol().CreateTreeNode();
var div = new Division().CreateTreeNode();
var varNode = (VariableTreeNode)(new Variable().CreateTreeNode());
varNode.Weight = 1.0;
varNode.VariableName = "x";
div.AddSubtree(varNode);
start.AddSubtree(div);
root.AddSubtree(start);
var t = new SymbolicExpressionTree(root);
Assert.AreEqual("(1 / (SQR('x') * (-1)))",
formatter.Format(DerivativeCalculator.Derive(t, "x")));
}
{
// special case: multiplication with only one argument
var root = new ProgramRootSymbol().CreateTreeNode();
var start = new StartSymbol().CreateTreeNode();
var mul = new Multiplication().CreateTreeNode();
var varNode = (VariableTreeNode)(new Variable().CreateTreeNode());
varNode.Weight = 3.0;
varNode.VariableName = "x";
mul.AddSubtree(varNode);
start.AddSubtree(mul);
root.AddSubtree(start);
var t = new SymbolicExpressionTree(root);
Assert.AreEqual("3",
formatter.Format(DerivativeCalculator.Derive(t, "x")));
}
{
// division with multiple arguments
// div(x, y, z) is interpreted as (x / y) / z
var root = new ProgramRootSymbol().CreateTreeNode();
var start = new StartSymbol().CreateTreeNode();
var div = new Division().CreateTreeNode();
var varNode1 = (VariableTreeNode)(new Variable().CreateTreeNode());
varNode1.Weight = 3.0;
varNode1.VariableName = "x";
var varNode2 = (VariableTreeNode)(new Variable().CreateTreeNode());
varNode2.Weight = 4.0;
varNode2.VariableName = "y";
var varNode3 = (VariableTreeNode)(new Variable().CreateTreeNode());
varNode3.Weight = 5.0;
varNode3.VariableName = "z";
div.AddSubtree(varNode1); div.AddSubtree(varNode2); div.AddSubtree(varNode3);
start.AddSubtree(div);
root.AddSubtree(start);
var t = new SymbolicExpressionTree(root);
Assert.AreEqual("(('y' * 'z' * 60) / (SQR('y') * SQR('z') * 400))", // actually 3 / (4y 5z) but simplifier is not smart enough to cancel numerator and denominator
// 60 y z / y² z² 20² == 6 / y z 40 == 3 / y z 20
formatter.Format(DerivativeCalculator.Derive(t, "x")));
Assert.AreEqual("(('x' * 'z' * (-60)) / (SQR('y') * SQR('z') * 400))", // actually 3x * -(4 5 z) / (4y 5z)² = -3x / (20 y² z)
// -3 4 5 x z / 4² y² 5² z² = -60 x z / 20² z² y² == -60 x z / y² z² 20²
formatter.Format(DerivativeCalculator.Derive(t, "y")));
Assert.AreEqual("(('x' * 'y' * (-60)) / (SQR('y') * SQR('z') * 400))",
formatter.Format(DerivativeCalculator.Derive(t, "z")));
}
}
/// <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 BottomUpSimilarityCalculatorTest()
{
var parser = new InfixExpressionParser();
}
