source: branches/HeuristicLab.Problems.GrammaticalOptimization/HeuristicLab.Problems.GrammaticalOptimization/SymbolicRegressionPoly10Problem.cs @ 11742

using System;
using System.Collections.Generic;
using System.Linq;
using System.Security;
using System.Security.AccessControl;
using System.Text;
using HeuristicLab.Common;

namespace HeuristicLab.Problems.GrammaticalOptimization {
  public class SymbolicRegressionPoly10Problem : IProblem {
    //    private const string grammarString = @"
    //    G(E):
    //    E -> V | V+E | V-E | V*E | (E)
    //    V -> a .. j 
    //    ";
    private const string grammarString = @"
    G(E):
    E -> a | b | c | d | e | f | g | h | i | j | a+E | b+E | c+E | d+E | e+E | f+E | g+E | h+E | i+E | j+E | a*E | b*E | c*E | d*E | e*E | f*E | g*E | h*E | i*E | j*E
    ";


    private readonly IGrammar grammar;

    private readonly int N;
    private readonly double[][] x;
    private readonly double[] y;

    public SymbolicRegressionPoly10Problem() {
      this.grammar = new Grammar(grammarString);

      this.N = 500;
      this.x = new double[N][];
      this.y = new double[N];

      GenerateData();
    }

    private void GenerateData() {
      // generate data with fixed seed to make sure that data is always the same
      var rand = new Random(31415);
      for (int i = 0; i < N; i++) {
        x[i] = new double[10];
        for (int j = 0; j < 10; j++) {
          x[i][j] = rand.NextDouble() * 2 - 1;
        }
        // poly-10 no noise
        /* a*b + c*d + e*f + a*g*i + c*f*j */
        y[i] = x[i][0] * x[i][1] +
               x[i][2] * x[i][3] +
               x[i][4] * x[i][5] +
               x[i][0] * x[i][6] * x[i][8] +
               x[i][2] * x[i][5] * x[i][9];
      }
    }

    public double BestKnownQuality(int maxLen) {
      // for now only an upper bound is returned, ideally we have an R² of 1.0
      // the optimal R² can only be reached for sentences of at least 23 symbols
      return 1.0;
    }

    public IGrammar Grammar {
      get { return grammar; }
    }

    public double Evaluate(string sentence) {
      var interpreter = new ExpressionInterpreter();
      return HeuristicLab.Common.Extensions.RSq(y, Enumerable.Range(0, N).Select(i => interpreter.Interpret(sentence, x[i])).ToArray());
    }



    // right now only + and * is supported
    public string CanonicalRepresentation(string terminalPhrase) {
      var terms = terminalPhrase.Split('+');
      return string.Join("+", terms.Select(term => string.Join("", term.Replace("*", "").OrderBy(ch => ch)))
        .OrderBy(term => term));
    }
  }
}