source: branches/HeuristicLab.Problems.GPDL/examples/symbreg HEAL.txt @ 9430

PROBLEM SymbReg

CODE <<
  double[,] inputValues;
  double[] targetValues;
  string[] variableNames;
  Dictionary<string,int> nameToCol;
  
  double GetValue(double[,] data, string varName, int row) {
    if(nameToCol == null) {
      /* init mapping */
      nameToCol = new Dictionary<string, int>();
      for(int i=0; i<variableNames.Length; i++) {
        nameToCol[variableNames[i]] = i;
      }
    }
    return data[row, nameToCol[varName]];
  }

  double RSquared(IEnumerable<double> xs, IEnumerable<double> ys) {
     HeuristicLab.Problems.DataAnalysis.OnlineCalculatorError error;
     var r2 = HeuristicLab.Problems.DataAnalysis.OnlinePearsonsRSquaredCalculator.Calculate(xs, ys, out error);
     if(error == HeuristicLab.Problems.DataAnalysis.OnlineCalculatorError.None) return r2;
     else return 0.0;
  }
  

  void LoadData(string fileName, out double[,] inputValues, out string[] variableNames, out double[] target) {
    var prov = new HeuristicLab.Problems.Instances.DataAnalysis.RegressionRealWorldInstanceProvider();
    var dd = prov.GetDataDescriptors().OfType<HeuristicLab.Problems.Instances.DataAnalysis.Housing>().Single();
    var problemData = prov.LoadData(dd);    
    
    inputValues = new double[problemData.TrainingIndices.Count(), problemData.AllowedInputVariables.Count()];
    foreach(var r in problemData.TrainingIndices) {
       int i=0;
       foreach(var v in problemData.AllowedInputVariables) {
          inputValues[r, i++] = problemData.Dataset.GetDoubleValue(v, r);
       }
    }
    variableNames = problemData.AllowedInputVariables.ToArray();
    target = problemData.Dataset.GetDoubleValues(problemData.TargetVariable, problemData.TrainingIndices).ToArray();
  }
>>

INIT <<
  LoadData("filename.csv", out inputValues, out variableNames, out targetValues);
>>

NONTERMINALS
  Model<<int row, out double val>>.
  RPB<<int row, out double val>>.
  Addition<<int row, out double val>>.
  Subtraction<<int row, out double val>>.
  Multiplication<<int row, out double val>>.
  Division<<int row, out double val>>.

TERMINALS
  Const<<out double val>> 
    CONSTRAINTS
      val IN RANGE <<-100>> .. <<100>>
  .
  Var<<out string varName, out double weight>>  
    CONSTRAINTS
      varName IN SET <<variableNames>>
      weight IN RANGE <<-100>> .. <<100>>
  .

RULES
  Model<<int row, out double val>> =                       
    RPB<<row, out val>> .
    
  RPB<<int row, out double val>> =                         LOCAL << string varName; double w; >> 
    Addition<<row, out val>>
    | Subtraction<<row, out val>>
    | Division<<row, out val>>
    | Multiplication<<row, out val>>                       
    | Var<<out varName, out w>>                            SEM << val = w * GetValue(inputValues, varName, row); >>
    | Const<<out val>>
  .

  Addition<<int row, out double val>> =                    LOCAL << double x1, x2; >>
    RPB<<row, out x1>> RPB<<row, out x2>>                  SEM << val = x1 + x2; >>
  .
  Subtraction<<int row, out double val>> =                 LOCAL << double x1, x2; >>
    RPB<<row, out x1>> RPB<<row, out x2>>                  SEM << val = x1 - x2; >>
  .
  Division<<int row, out double val>> =                    LOCAL << double x1, x2; >>
    RPB<<row, out x1>> RPB<<row, out x2>>                  SEM << val = x1 / x2; >>
  .
  Multiplication<<int row, out double val>> =              LOCAL << double x1, x2; >>
    RPB<<row, out x1>> RPB<<row, out x2>>                  SEM << val = x1 * x2; >>
  .

MAXIMIZE                                                   /* could also use the keyword MINIMIZE here */
  << 
    var rows = System.Linq.Enumerable.Range(0, inputValues.GetLength(0));
    var predicted = rows.Select(r => {
      double result;
      Model(r, out result);                                /* we can call the root symbol directly */
      return result;
    });
    return RSquared(predicted, targetValues);
  >>
END SymbReg.