Changes between Version 10 and Version 11 of Documentation/Reference/GPDL

Timestamp:

07/08/13 15:04:56 (11 years ago)

Author:

gkronber

Comment:

--

Documentation/Reference/GPDL

@@ -5 +5 @@
  * a lot of boiler-plate code has to be written to integrate into the GP framework. 
  * it is necessary to learn the API of the GP system
- * we cannot re-use problem implementations to try different GP systems (e.g. ECJ, HeuristicLab, ...)
+ * problem implementations cannot be re-used to try different GP systems (e.g. ECJ, HeuristicLab, ...)
 
 GPDL separates the implementation of problem details from the intricacies of algorithm implementations. Only the details of the problem are specified in a framework-independent way. A compiler can transform the problem description to source code for different GP systems. This way it will be much easier to implement problems and try to solve them with different GP implementations or even other kinds of solvers!
@@ -23 +23 @@
  * [[source:/branches/HeuristicLab.Problems.GPDL/HeuristicLab.Problems.GPDL.Views/3.4/Resources/multi-output-multiplier.txt|Multi-output multiplier]] 
 
+== Motivating Example: Symbolic Regression ==
+This is a fully self-contained specification of a symbolic regression problem to solve the Poly-10 benchmark problem. This file can be compiler using our reference GPDL compiler for HeuristicLab to create a solver for this problem.
+{{{
+#!csharp
+PROBLEM SymbRegKoza
+CODE <<
+  double[,] x;
+  double[] y;
+  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 x[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;
+  }
+>>
+
+INIT <<
+  // generate 500 case of poly-10 benchmark function
+  int n = 500;
+  variableNames = new string[] {"x1", "x2", "x3", "x4", "x5", "x6", "x7", "x8", "x9", "x10" };
+  var rand = new System.Random();
+  x = new double[n, 10];
+  y = new double[n];
+  for(int row = 0; row < 500; row++) {
+    for(int col = 0; col < 10; col++) {
+      x[row, col] = rand.NextDouble() * 2.0 - 1.0;
+    }
+    y[row] = x[row, 0] * x[row, 1] +
+             x[row, 2] * x[row, 3] +
+             x[row, 4] * x[row, 5] +
+             x[row, 0] * x[row, 6] + x[row, 8] +
+             x[row, 2] * x[row, 5] + x[row, 9];
+  }
+>>
+
+/* non-terminals of the problem */
+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 of the problem: random constants (ERC) and variables */
+TERMINALS
+  ERC<<out double val>> 
+    CONSTRAINTS
+          val IN RANGE <<-100>> .. <<100>>
+  .
+
+  Var<<out string varName>> 
+    CONSTRAINTS
+          varName IN SET <<variableNames>>
+  .
+
+/* grammar rules for the problem with interleaved semantic actions */
+RULES
+  Model<<int row, out double val>> =
+    RPB<<row, out val>> .
+
+  RPB<<int row, out double val>> =                         LOCAL << string varName; >>
+    Addition<<row, out val>>
+    | Subtraction<<row, out val>>
+    | Division<<row, out val>>
+    | Multiplication<<row, out val>>
+    | Var<<out varName>>                                   SEM << val = GetValue(x, varName, row); >>
+    | ERC<<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; >>
+  .
+
+/* objective function */
+MAXIMIZE                                                   /* could also use the keyword MINIMIZE here */
+  << 
+    var rows = System.Linq.Enumerable.Range(0, x.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, y);
+  >>
+END SymbRegKoza.
+}}}
+
 == Syntax Definition ==
  * [[source:/branches/HeuristicLab.Problems.GPDL/SyntaxAnalyzer/GPDef.atg|GPDef.atg (for Coco-2)]]