Changeset 15416 for branches/MCTS-SymbReg-2796/Tests

Timestamp:

10/11/17 08:15:19 (7 years ago)

Author:

gkronber

Message:

#2796 worked on MCTS for symbreg

Location:

branches/MCTS-SymbReg-2796/Tests

Files:

• HeuristicLab.Algorithms.DataAnalysis-3.4/MctsSymbolicRegressionTest.cs (modified) (4 diffs)
• Test.csproj (modified) (1 diff)

branches/MCTS-SymbReg-2796/Tests/HeuristicLab.Algorithms.DataAnalysis-3.4/MctsSymbolicRegressionTest.cs

@@ -7 +7 @@
 using HeuristicLab.Problems.DataAnalysis;
 using HeuristicLab.Problems.Instances.DataAnalysis;
+using HeuristicLab.Random;
 using Microsoft.VisualStudio.TestTools.UnitTesting;
 
@@ -550 +551 @@
       var provider = new HeuristicLab.Problems.Instances.DataAnalysis.NguyenInstanceProvider(seed: 1234);
       var regProblem = provider.LoadData(provider.GetDataDescriptors().Single(x => x.Name.Contains("F7 ")));
-      TestMctsWithoutConstants(regProblem, nVarRefs: 10, iterations: 1000000, allowExp: false, allowLog: true, allowInv: false);
-    }
+      TestMctsWithoutConstants(regProblem, nVarRefs: 10, iterations: 100000, allowExp: false, allowLog: true, allowInv: false);
+    }
+
+    [TestMethod]
+    [TestCategory("Algorithms.DataAnalysis")]
+    [TestProperty("Time", "short")]
+    public void MctsSymbReg_NoConstants_Poly10_Part1() {
+      var provider = new HeuristicLab.Problems.Instances.DataAnalysis.VariousInstanceProvider(seed: 1234);
+      var regProblem = provider.LoadData(provider.GetDataDescriptors().Single(x => x.Name.Contains("Poly-10")));
+
+      //  Y = X1*X2 + X3*X4 + X5*X6 + X1*X7*X9 + X3*X6*X10
+      //  Y' = X1*X2 + X3*X4 + X5*X6
+      // simplify problem by changing target
+      var ds = ((Dataset)regProblem.Dataset).ToModifiable();
+      var ys = ds.GetDoubleValues("Y").ToArray();
+      var x1 = ds.GetDoubleValues("X1").ToArray();
+      var x2 = ds.GetDoubleValues("X2").ToArray();
+      var x3 = ds.GetDoubleValues("X3").ToArray();
+      var x4 = ds.GetDoubleValues("X4").ToArray();
+      var x5 = ds.GetDoubleValues("X5").ToArray();
+      var x6 = ds.GetDoubleValues("X6").ToArray();
+      var x7 = ds.GetDoubleValues("X7").ToArray();
+      var x8 = ds.GetDoubleValues("X8").ToArray();
+      var x9 = ds.GetDoubleValues("X9").ToArray();
+      var x10 = ds.GetDoubleValues("X10").ToArray();
+      for (int i = 0; i < ys.Length; i++) {
+        ys[i] -= x1[i] * x7[i] * x9[i];
+        ys[i] -= x3[i] * x6[i] * x10[i];
+      }
+      ds.ReplaceVariable("Y", ys.ToList());
+
+      var modifiedProblemData = new RegressionProblemData(ds, regProblem.AllowedInputVariables, regProblem.TargetVariable);
+
+
+      TestMctsWithoutConstants(modifiedProblemData, nVarRefs: 15, iterations: 100000, allowExp: false, allowLog: false, allowInv: false);
+    }
+
+    [TestMethod]
+    [TestCategory("Algorithms.DataAnalysis")]
+    [TestProperty("Time", "short")]
+    public void MctsSymbReg_NoConstants_Poly10_Part2() {
+      var provider = new HeuristicLab.Problems.Instances.DataAnalysis.VariousInstanceProvider(seed: 1234);
+      var regProblem = provider.LoadData(provider.GetDataDescriptors().Single(x => x.Name.Contains("Poly-10")));
+
+      //  Y = X1*X2 + X3*X4 + X5*X6 + X1*X7*X9 + X3*X6*X10
+      //  Y' = X1*X7*X9 + X3*X6*X10
+      // simplify problem by changing target
+      var ds = ((Dataset)regProblem.Dataset).ToModifiable();
+      var ys = ds.GetDoubleValues("Y").ToArray();
+      var x1 = ds.GetDoubleValues("X1").ToArray();
+      var x2 = ds.GetDoubleValues("X2").ToArray();
+      var x3 = ds.GetDoubleValues("X3").ToArray();
+      var x4 = ds.GetDoubleValues("X4").ToArray();
+      var x5 = ds.GetDoubleValues("X5").ToArray();
+      var x6 = ds.GetDoubleValues("X6").ToArray();
+      var x7 = ds.GetDoubleValues("X7").ToArray();
+      var x8 = ds.GetDoubleValues("X8").ToArray();
+      var x9 = ds.GetDoubleValues("X9").ToArray();
+      var x10 = ds.GetDoubleValues("X10").ToArray();
+      for (int i = 0; i < ys.Length; i++) {
+        ys[i] -= x1[i] * x2[i];
+        ys[i] -= x3[i] * x4[i];
+        ys[i] -= x5[i] * x6[i];
+      }
+      ds.ReplaceVariable("Y", ys.ToList());
+
+      var modifiedProblemData = new RegressionProblemData(ds, regProblem.AllowedInputVariables, regProblem.TargetVariable);
+
+
+      TestMctsWithoutConstants(modifiedProblemData, nVarRefs: 15, iterations: 100000, allowExp: false, allowLog: false, allowInv: false);
+    }
+
+    [TestMethod]
+    [TestCategory("Algorithms.DataAnalysis")]
+    [TestProperty("Time", "short")]
+    public void MctsSymbReg_NoConstants_Poly10_Part3() {
+      var provider = new HeuristicLab.Problems.Instances.DataAnalysis.VariousInstanceProvider(seed: 1234);
+      var regProblem = provider.LoadData(provider.GetDataDescriptors().Single(x => x.Name.Contains("Poly-10")));
+
+      //  Y = X1*X2 + X3*X4 + X5*X6 + X1*X7*X9 + X3*X6*X10
+      //  Y' = X1*X2 + X1*X7*X9
+      // simplify problem by changing target
+      var ds = ((Dataset)regProblem.Dataset).ToModifiable();
+      var ys = ds.GetDoubleValues("Y").ToArray();
+      var x1 = ds.GetDoubleValues("X1").ToArray();
+      var x2 = ds.GetDoubleValues("X2").ToArray();
+      var x3 = ds.GetDoubleValues("X3").ToArray();
+      var x4 = ds.GetDoubleValues("X4").ToArray();
+      var x5 = ds.GetDoubleValues("X5").ToArray();
+      var x6 = ds.GetDoubleValues("X6").ToArray();
+      var x7 = ds.GetDoubleValues("X7").ToArray();
+      var x8 = ds.GetDoubleValues("X8").ToArray();
+      var x9 = ds.GetDoubleValues("X9").ToArray();
+      var x10 = ds.GetDoubleValues("X10").ToArray();
+      for (int i = 0; i < ys.Length; i++) {
+        ys[i] -= x3[i] * x4[i];
+        ys[i] -= x5[i] * x6[i];
+        ys[i] -= x3[i] * x6[i] * x10[i];
+      }
+      ds.ReplaceVariable("Y", ys.ToList());
+
+      var modifiedProblemData = new RegressionProblemData(ds, regProblem.AllowedInputVariables, regProblem.TargetVariable);
+
+
+      TestMctsWithoutConstants(modifiedProblemData, nVarRefs: 15, iterations: 100000, allowExp: false, allowLog: false, allowInv: false);
+    }
+
+    [TestMethod]
+    [TestCategory("Algorithms.DataAnalysis")]
+    [TestProperty("Time", "short")]
+    public void MctsSymbReg_NoConstants_Poly10_Part4() {
+      var provider = new HeuristicLab.Problems.Instances.DataAnalysis.VariousInstanceProvider(seed: 1234);
+      var regProblem = provider.LoadData(provider.GetDataDescriptors().Single(x => x.Name.Contains("Poly-10")));
+
+      //  Y = X1*X2 + X3*X4 + X5*X6 + X1*X7*X9 + X3*X6*X10
+      //  Y' = X3*X4 + X5*X6 + X3*X6*X10
+      // simplify problem by changing target
+      var ds = ((Dataset)regProblem.Dataset).ToModifiable();
+      var ys = ds.GetDoubleValues("Y").ToArray();
+      var x1 = ds.GetDoubleValues("X1").ToArray();
+      var x2 = ds.GetDoubleValues("X2").ToArray();
+      var x3 = ds.GetDoubleValues("X3").ToArray();
+      var x4 = ds.GetDoubleValues("X4").ToArray();
+      var x5 = ds.GetDoubleValues("X5").ToArray();
+      var x6 = ds.GetDoubleValues("X6").ToArray();
+      var x7 = ds.GetDoubleValues("X7").ToArray();
+      var x8 = ds.GetDoubleValues("X8").ToArray();
+      var x9 = ds.GetDoubleValues("X9").ToArray();
+      var x10 = ds.GetDoubleValues("X10").ToArray();
+      for (int i = 0; i < ys.Length; i++) {
+        ys[i] -= x1[i] * x2[i];
+        ys[i] -= x1[i] * x7[i] * x9[i];
+      }
+      ds.ReplaceVariable("Y", ys.ToList());
+      var modifiedProblemData = new RegressionProblemData(ds, regProblem.AllowedInputVariables, regProblem.TargetVariable);
+
+
+      TestMctsWithoutConstants(modifiedProblemData, nVarRefs: 15, iterations: 100000, allowExp: false, allowLog: false, allowInv: false);
+    }
+
+    [TestMethod]
+    [TestCategory("Algorithms.DataAnalysis")]
+    [TestProperty("Time", "short")]
+    public void MctsSymbReg_NoConstants_Poly10_Part5() {
+      var provider = new HeuristicLab.Problems.Instances.DataAnalysis.VariousInstanceProvider(seed: 1234);
+      var regProblem = provider.LoadData(provider.GetDataDescriptors().Single(x => x.Name.Contains("Poly-10")));
+
+      //  Y = X1*X2 + X3*X4 + X5*X6 + X1*X7*X9 + X3*X6*X10
+      //  Y' = X1*X2 + X3*X4 + X5*X6 + X1*X7*X9
+      // simplify problem by changing target
+      var ds = ((Dataset)regProblem.Dataset).ToModifiable();
+      var ys = ds.GetDoubleValues("Y").ToArray();
+      var x1 = ds.GetDoubleValues("X1").ToArray();
+      var x2 = ds.GetDoubleValues("X2").ToArray();
+      var x3 = ds.GetDoubleValues("X3").ToArray();
+      var x4 = ds.GetDoubleValues("X4").ToArray();
+      var x5 = ds.GetDoubleValues("X5").ToArray();
+      var x6 = ds.GetDoubleValues("X6").ToArray();
+      var x7 = ds.GetDoubleValues("X7").ToArray();
+      var x8 = ds.GetDoubleValues("X8").ToArray();
+      var x9 = ds.GetDoubleValues("X9").ToArray();
+      var x10 = ds.GetDoubleValues("X10").ToArray();
+      for (int i = 0; i < ys.Length; i++) {
+        ys[i] -= x3[i] * x6[i] * x10[i];
+      }
+      ds.ReplaceVariable("Y", ys.ToList());
+      var modifiedProblemData = new RegressionProblemData(ds, regProblem.AllowedInputVariables, regProblem.TargetVariable);
+
+
+      TestMctsWithoutConstants(modifiedProblemData, nVarRefs: 15, iterations: 100000, allowExp: false, allowLog: false, allowInv: false);
+    }
+
+    [TestMethod]
+    [TestCategory("Algorithms.DataAnalysis")]
+    [TestProperty("Time", "short")]
+    public void MctsSymbReg_NoConstants_Poly10_Part6() {
+      var provider = new HeuristicLab.Problems.Instances.DataAnalysis.VariousInstanceProvider(seed: 1234);
+      var regProblem = provider.LoadData(provider.GetDataDescriptors().Single(x => x.Name.Contains("Poly-10")));
+
+      //  Y = X1*X2 + X3*X4 + X5*X6 + X1*X7*X9 + X3*X6*X10
+      //  Y' = X1*X2 + X3*X4 + X5*X6 + X3*X6*X10
+      // simplify problem by changing target
+      var ds = ((Dataset)regProblem.Dataset).ToModifiable();
+      var ys = ds.GetDoubleValues("Y").ToArray();
+      var x1 = ds.GetDoubleValues("X1").ToArray();
+      var x2 = ds.GetDoubleValues("X2").ToArray();
+      var x3 = ds.GetDoubleValues("X3").ToArray();
+      var x4 = ds.GetDoubleValues("X4").ToArray();
+      var x5 = ds.GetDoubleValues("X5").ToArray();
+      var x6 = ds.GetDoubleValues("X6").ToArray();
+      var x7 = ds.GetDoubleValues("X7").ToArray();
+      var x8 = ds.GetDoubleValues("X8").ToArray();
+      var x9 = ds.GetDoubleValues("X9").ToArray();
+      var x10 = ds.GetDoubleValues("X10").ToArray();
+      for (int i = 0; i < ys.Length; i++) {
+        ys[i] -= x1[i] * x7[i] * x9[i];
+      }
+      ds.ReplaceVariable("Y", ys.ToList());
+      var modifiedProblemData = new RegressionProblemData(ds, regProblem.AllowedInputVariables, regProblem.TargetVariable);
+
+
+      TestMctsWithoutConstants(modifiedProblemData, nVarRefs: 9, iterations: 100000, allowExp: false, allowLog: false, allowInv: false);
+    }
+
 
     [TestMethod]
@@ -559 +762 @@
       var provider = new HeuristicLab.Problems.Instances.DataAnalysis.VariousInstanceProvider(seed: 1234);
       var regProblem = provider.LoadData(provider.GetDataDescriptors().Single(x => x.Name.Contains("Poly-10")));
-      TestMctsWithoutConstants(regProblem, nVarRefs: 15, iterations: 1000000, allowExp: false, allowLog: false, allowInv: false);
+      TestMctsWithoutConstants(regProblem, nVarRefs: 15, iterations: 200000, allowExp: false, allowLog: false, allowInv: false);
+    }
+
+    [TestMethod]
+    [TestCategory("Algorithms.DataAnalysis")]
+    [TestProperty("Time", "short")]
+    public void MctsSymbReg_NoConstants_TwoVars() {
+
+      // y = x1 + x2 + x1*x2 + x1*x2*x2 + x1*x1*x2
+      var rand = new FastRandom(1234);
+      var x1 = Enumerable.Range(0, 100).Select(_ => rand.NextDouble()).ToList();
+      var x2 = Enumerable.Range(0, 100).Select(_ => rand.NextDouble()).ToList();
+      var ys = x1.Zip(x2, (x1i, x2i) => x1i + x2i + x1i * x2i + x1i * x2i * x2i + x1i * x1i * x2i).ToList();
+
+      var ds = new Dataset(new string[] { "a", "b", "y" }, new[] { x1, x2, ys });
+
+      var problemData = new RegressionProblemData(ds, new string[] { "a", "b" }, "y");
+
+
+      TestMctsWithoutConstants(problemData, nVarRefs: 10, iterations: 10000, allowExp: false, allowLog: false, allowInv: false);
+    }
+
+    [TestMethod]
+    [TestCategory("Algorithms.DataAnalysis")]
+    [TestProperty("Time", "short")]
+    public void MctsSymbReg_NoConstants_Misleading() {
+
+      // y = a + baaaaa (the effect of the second term should be very small)
+      // the alg will quickly find that a has big effect and will search below a
+      // since we prevent a + a... the algorithm must find the correct expression via a + b...
+      // however b has a small effect so the branch might not be identified as relevant
+
+      var rand = new FastRandom(1234);
+      var @as = Enumerable.Range(0, 100).Select(_ => rand.NextDouble()).ToList();
+      var bs = Enumerable.Range(0, 100).Select(_ => rand.NextDouble()).ToList();
+      var cs = Enumerable.Range(0, 100).Select(_ => rand.NextDouble() *1.0e-3).ToList();
+      var ds = Enumerable.Range(0, 100).Select(_ => rand.NextDouble() ).ToList();
+      var es = Enumerable.Range(0, 100).Select(_ => rand.NextDouble() ).ToList();
+      var ys = new double[@as.Count];
+      for(int i=0;i<ys.Length;i++)
+        ys[i] = @as[i] + bs[i] + @as[i]*bs[i]*cs[i];
+
+      var dataset = new Dataset(new string[] { "a", "b", "c", "d", "e", "y" }, new[] { @as, bs, cs, ds, es, ys.ToList() });
+
+      var problemData = new RegressionProblemData(dataset, new string[] { "a", "b","c","d","e" }, "y");
+
+
+      TestMctsWithoutConstants(problemData, nVarRefs: 10, iterations: 10000, allowExp: false, allowLog: false, allowInv: false);
     }
     #endregion
@@ -822 +1072 @@
       mctsSymbReg.ConstantOptimizationIterations = -1;
 
+      // random policy
+      // var epsPolicy = new EpsilonGreedy();
+      // epsPolicy.Eps = 1.0;
+      // mctsSymbReg.Policy = epsPolicy;
+
+      // UCB tuned
+      // var ucbTuned = new UcbTuned();
+      // ucbTuned.C = 1.5; 
+      // mctsSymbReg.Policy = ucbTuned;
+
+
       #endregion
       RunAlgorithm(mctsSymbReg);

branches/MCTS-SymbReg-2796/Tests/Test.csproj

@@ -63 +63 @@
       <HintPath>..\..\..\trunk\sources\bin\HeuristicLab.Problems.Instances.DataAnalysis-3.3.dll</HintPath>
     </Reference>
+    <Reference Include="HeuristicLab.Random-3.3, Version=3.3.0.0, Culture=neutral, PublicKeyToken=ba48961d6f65dcec, processorArchitecture=MSIL">
+      <SpecificVersion>False</SpecificVersion>
+      <HintPath>..\..\..\trunk\sources\bin\HeuristicLab.Random-3.3.dll</HintPath>
+    </Reference>
     <Reference Include="System" />
   </ItemGroup>