Changeset 11902 for branches/HeuristicLab.Problems.GrammaticalOptimization

Timestamp:

02/05/15 10:33:12 (10 years ago)

Author:

gkronber

Message:

#2283: preparations for transformation of expressions to canonical form

Location:

branches/HeuristicLab.Problems.GrammaticalOptimization

Files:

• HeuristicLab.Common/ExpressionExtender.cs (added)
• HeuristicLab.Common/HeuristicLab.Common.csproj (modified) (1 diff)
• HeuristicLab.Problems.GrammaticalOptimization.SymbReg/SymbolicRegressionProblem.cs (modified) (9 diffs)
• Test/Test.csproj (modified) (2 diffs)
• Test/TestCanonicalExpressions.cs (added)

branches/HeuristicLab.Problems.GrammaticalOptimization/HeuristicLab.Common/HeuristicLab.Common.csproj

@@ -36 +36 @@
   <ItemGroup>
     <Compile Include="ConsoleEx.cs" />
+    <Compile Include="ExpressionExtender.cs" />
     <Compile Include="Extensions.cs" />
     <Compile Include="MostRecentlyUsedCache.cs" />

branches/HeuristicLab.Problems.GrammaticalOptimization/HeuristicLab.Problems.GrammaticalOptimization.SymbReg/SymbolicRegressionProblem.cs

@@ -19 +19 @@
   public class SymbolicRegressionProblem : ISymbolicExpressionTreeProblem {
 
+    // C represents Koza-style ERC (the symbol is the index of the ERC), the values are initialized below
     private const string grammarString = @"
         G(E):
@@ -25 +26 @@
         V -> <variables>
         ";
-    // C represents Koza-style ERC (the symbol is the index of the ERC), the values are initialized below
+
+    // when using constant opt optimal constants are generated in the evaluation step so we don't need them in the grammar
+    private const string grammarConstOptString = @"
+        G(E):
+        E -> V | V+E | V*E | V%E | (E) 
+        V -> <variables>
+        ";
 
     // S .. Sum (+), N .. Neg. sum (-), P .. Product (*), D .. Division (%)
@@ -38 +45 @@
         V -> <variables>
         ";
+    private const string treeGrammarConstOptString = @"
+        G(E):
+        E -> V | S | P | D 
+        S -> EE | EEE
+        P -> EE | EEE
+        D -> EE
+        V -> <variables>
+        ";
 
     // when we use constants optimization we can completely ignore all constants by a simple strategy:
@@ -51 +66 @@
     private readonly int d;
     private readonly double[] erc;
-
-
-    public SymbolicRegressionProblem(Random random, string partOfName) {
+    private readonly bool useConstantOpt;
+
+
+    public SymbolicRegressionProblem(Random random, string partOfName, bool useConstantOpt = true) {
       var instanceProvider = new RegressionRealWorldInstanceProvider();
       var dds = instanceProvider.GetDataDescriptors().OfType<RegressionDataDescriptor>();
+      this.useConstantOpt = useConstantOpt;
 
       var problemData = instanceProvider.LoadData(dds.Single(ds => ds.Name.Contains(partOfName)));
@@ -78 +95 @@
       char firstVar = 'a';
       char lastVar = Convert.ToChar(Convert.ToByte('a') + d - 1);
-      this.grammar = new Grammar(grammarString.Replace("<variables>", firstVar + " .. " + lastVar));
-      this.TreeBasedGPGrammar = new Grammar(treeGrammarString.Replace("<variables>", firstVar + " .. " + lastVar));
+      if (!useConstantOpt) {
+        this.grammar = new Grammar(grammarString.Replace("<variables>", firstVar + " .. " + lastVar));
+        this.TreeBasedGPGrammar = new Grammar(treeGrammarString.Replace("<variables>", firstVar + " .. " + lastVar));
+      } else {
+        this.grammar = new Grammar(grammarConstOptString.Replace("<variables>", firstVar + " .. " + lastVar));
+        this.TreeBasedGPGrammar = new Grammar(treeGrammarConstOptString.Replace("<variables>", firstVar + " .. " + lastVar));
+      }
     }
 
@@ -93 +115 @@
 
     public double Evaluate(string sentence) {
-      return OptimizeConstantsAndEvaluate(sentence);
+      if (useConstantOpt)
+        return OptimizeConstantsAndEvaluate(sentence);
+      else {
+        return SimpleEvaluate(sentence);
+      }
     }
 
@@ -107 +133 @@
 
     public string CanonicalRepresentation(string phrase) {
-      return phrase;
-      //var terms = phrase.Split('+');
-      //return string.Join("+", terms.Select(term => string.Join("", term.Replace("*", "").OrderBy(ch => ch)))
-      //  .OrderBy(term => term));
+      throw new NotImplementedException();
     }
 
     public IEnumerable<Feature> GetFeatures(string phrase) {
+      // first generate canonical expression (which must not contain ())
+      // recursively split into expressions
+      // for each expression split into terms
+      // for each term order factors to canonical // ../E = * 1/E
+      var canonical = CanonicalRepresentation(phrase);
       throw new NotImplementedException();
     }
@@ -212 +240 @@
         }
         // nonterminal
-        if (op == "+" || op == "-") sb.Append("(");
+        if (treeNode.SubtreeCount > 1) sb.Append("(");
         TreeToSentence(treeNode.Subtrees.First(), sb);
         foreach (var subTree in treeNode.Subtrees.Skip(1)) {
@@ -218 +246 @@
           TreeToSentence(subTree, sb);
         }
-        if (op == "+" || op == "-") sb.Append(")");
+        if (treeNode.SubtreeCount > 1) sb.Append(")");
       }
     }

branches/HeuristicLab.Problems.GrammaticalOptimization/Test/Test.csproj

@@ -69 +69 @@
   </Choose>
   <ItemGroup>
+    <Compile Include="TestCanonicalExpressions.cs" />
     <Compile Include="TestSymbRegInstances.cs" />
     <Compile Include="TestSequence.cs" />
@@ -88 +89 @@
       <Project>{eea07488-1a51-412a-a52c-53b754a628b3}</Project>
       <Name>HeuristicLab.Algorithms.GrammaticalOptimization</Name>
+    </ProjectReference>
+    <ProjectReference Include="..\HeuristicLab.Common\HeuristicLab.Common.csproj">
+      <Project>{3A2FBBCB-F9DF-4970-87F3-F13337D941AD}</Project>
+      <Name>HeuristicLab.Common</Name>
     </ProjectReference>
     <ProjectReference Include="..\HeuristicLab.Distributions\HeuristicLab.Distributions.csproj">