source: branches/HeuristicLab.Problems.GrammaticalOptimization/HeuristicLab.Problems.GrammaticalOptimization.SymbReg/SymbolicRegressionProblem.cs @ 11747

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

namespace HeuristicLab.Problems.GrammaticalOptimization.SymbReg {
  // provides bridge to HL regression problem instances
  public class SymbolicRegressionProblem : IProblem {
    private const string grammarString = @"
        G(E):
        E -> V | V+E | V-E | V*E | (E)
        V -> <variables>
        ";


    private readonly IGrammar grammar;
    private readonly ExpressionInterpreter interpreter;

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


    public SymbolicRegressionProblem(string partOfName) {
      var instanceProvider = new RegressionRealWorldInstanceProvider();
      var dds = instanceProvider.GetDataDescriptors().OfType<RegressionDataDescriptor>();

      var problemData = instanceProvider.LoadData(dds.Single(ds => ds.Name.Contains(partOfName)));

      this.N = problemData.TrainingIndices.Count();
      this.d = problemData.AllowedInputVariables.Count();
      if (d > 26) throw new NotSupportedException(); // we only allow single-character terminal symbols so far
      this.x = new double[N][];
      this.y = problemData.Dataset.GetDoubleValues(problemData.TargetVariable, problemData.TrainingIndices).ToArray();

      int i = 0;
      foreach (var r in problemData.TrainingIndices) {
        x[i] = new double[d];
        int j = 0;
        foreach (var inputVariable in problemData.AllowedInputVariables) {
          x[i][j++] = problemData.Dataset.GetDoubleValue(inputVariable, r);
        }
        i++;
      }

      char firstVar = 'a';
      char lastVar = Convert.ToChar(Convert.ToByte('a') + d - 1);
      this.grammar = new Grammar(grammarString.Replace("<variables>", firstVar + " .. " + lastVar));
      this.interpreter = new ExpressionInterpreter();

    }


    public double BestKnownQuality(int maxLen) {
      // for now only an upper bound is returned, ideally we have an R² of 1.0
      return 1.0;
    }

    public IGrammar Grammar {
      get { return grammar; }
    }

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


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