Changeset 13930

Timestamp:

06/21/16 09:00:35 (8 years ago)

Author:

gkronber

Message:

#745: added parameter lambda to support calculation of a solution for a specific lambda value (instead of the full path)

Location:

branches/HeuristicLab.Algorithms.DataAnalysis.Glmnet/3.4

Files:

• ElasticNetLinearRegression.cs (modified) (9 diffs)
• HeuristicLab.Algorithms.DataAnalysis.Glmnet.csproj (modified) (2 diffs)
• Plugin.cs.frame (modified) (1 diff)

branches/HeuristicLab.Algorithms.DataAnalysis.Glmnet/3.4/ElasticNetLinearRegression.cs

@@ -7 +7 @@
 using HeuristicLab.Core;
 using HeuristicLab.Data;
+using HeuristicLab.Encodings.SymbolicExpressionTreeEncoding;
 using HeuristicLab.Optimization;
 using HeuristicLab.Parameters;
 using HeuristicLab.Persistence.Default.CompositeSerializers.Storable;
 using HeuristicLab.Problems.DataAnalysis;
+using HeuristicLab.Problems.DataAnalysis.Symbolic;
+using HeuristicLab.Problems.DataAnalysis.Symbolic.Regression;
 
 namespace HeuristicLab.LibGlmNet {
@@ -18 +21 @@
   public sealed class ElasticNetLinearRegression : FixedDataAnalysisAlgorithm<IRegressionProblem> {
     private const string PenalityParameterName = "Penality";
+    private const string LambdaParameterName = "Lambda";
     #region parameters
     public IFixedValueParameter<DoubleValue> PenalityParameter {
       get { return (IFixedValueParameter<DoubleValue>)Parameters[PenalityParameterName]; }
+    }
+    public IValueParameter<DoubleValue> LambdaParameter {
+      get { return (IValueParameter<DoubleValue>)Parameters[LambdaParameterName]; }
     }
     #endregion
@@ -28 +35 @@
       set { PenalityParameter.Value.Value = value; }
     }
+    public DoubleValue Lambda {
+      get { return LambdaParameter.Value; }
+      set { LambdaParameter.Value = value; }
+    }
     #endregion
 
@@ -38 +49 @@
       Problem = new RegressionProblem();
       Parameters.Add(new FixedValueParameter<DoubleValue>(PenalityParameterName, "Penalty factor for balancing between ridge (0.0) and lasso (1.0) regression", new DoubleValue(0.5)));
+      Parameters.Add(new OptionalValueParameter<DoubleValue>(LambdaParameterName, "Optional: the value of lambda for which to calculate an elastic-net solution. lambda == null => calculate the whole path of all lambdas"));
     }
 
@@ -48 +60 @@
 
     protected override void Run() {
+      if (Lambda == null) {
+        CreateSolutionPath();
+      } else {
+        CreateSolution(Lambda.Value);
+      }
+    }
+
+    private void CreateSolution(double lambda) {
+      double trainRsq;
+      double testRsq;
+      var coeff = CreateElasticNetLinearRegressionSolution(Problem.ProblemData, Penality, lambda, out trainRsq, out testRsq);
+      Results.Add(new Result("R² (train)", new DoubleValue(trainRsq)));
+      Results.Add(new Result("R² (test)", new DoubleValue(testRsq)));
+
+      // copied from LR => TODO: reuse code (but skip coefficients = 0.0)
+      ISymbolicExpressionTree tree = new SymbolicExpressionTree(new ProgramRootSymbol().CreateTreeNode());
+      ISymbolicExpressionTreeNode startNode = new StartSymbol().CreateTreeNode();
+      tree.Root.AddSubtree(startNode);
+      ISymbolicExpressionTreeNode addition = new Addition().CreateTreeNode();
+      startNode.AddSubtree(addition);
+
+      int col = 0;
+      foreach (string column in Problem.ProblemData.AllowedInputVariables) {
+        if (!coeff[col].IsAlmost(0.0)) {
+          VariableTreeNode vNode = (VariableTreeNode)new HeuristicLab.Problems.DataAnalysis.Symbolic.Variable().CreateTreeNode();
+          vNode.VariableName = column;
+          vNode.Weight = coeff[col];
+          addition.AddSubtree(vNode);
+        }
+        col++;
+      }
+
+      if (!coeff[coeff.Length - 1].IsAlmost(0.0)) {
+        ConstantTreeNode cNode = (ConstantTreeNode)new Constant().CreateTreeNode();
+        cNode.Value = coeff[coeff.Length - 1];
+        addition.AddSubtree(cNode);
+      }
+
+      SymbolicRegressionSolution solution = new SymbolicRegressionSolution(new SymbolicRegressionModel(tree, new SymbolicDataAnalysisExpressionTreeInterpreter()), (IRegressionProblemData)Problem.ProblemData.Clone());
+      solution.Model.Name = "Elastic-net Linear Regression Model";
+      solution.Name = "Elastic-net Linear Regression Solution";
+
+      Results.Add(new Result(solution.Name, solution.Description, solution));
+    }
+
+    private void CreateSolutionPath() {
       double[] lambda;
       double[] trainRsq;
@@ -72 +130 @@
       rsqTable.Rows.Add(new DataRow("R² (train)", "Path of R² values over different lambda values", trainRsq));
       rsqTable.Rows.Add(new DataRow("R² (test)", "Path of R² values over different lambda values", testRsq));
+      rsqTable.Rows.Add(new DataRow("Lambda", "The lambda values along the path", lambda));
+      rsqTable.Rows["Lambda"].VisualProperties.ChartType = DataRowVisualProperties.DataRowChartType.Points;
+      rsqTable.Rows["Lambda"].VisualProperties.SecondYAxis = true;
+      rsqTable.VisualProperties.SecondYAxisMinimumFixedValue = 1E-7;
+      rsqTable.VisualProperties.SecondYAxisLogScale = true;
       Results.Add(new Result(rsqTable.Name, rsqTable.Description, rsqTable));
     }
 
     public static double[] CreateElasticNetLinearRegressionSolution(IRegressionProblemData problemData, double penalty, double lambda,
-            out double trainRsq,  out double testRsq,
+            out double trainRsq, out double testRsq,
             double coeffLowerBound = double.NegativeInfinity, double coeffUpperBound = double.PositiveInfinity) {
       double[] trainRsqs;
@@ -192 +255 @@
         modval(intercept[solIdx], selectedCa, ia, selectedNin, numTestObs, testX, out fn);
         OnlineCalculatorError error;
-        var r  = OnlinePearsonsRCalculator.Calculate(testY, fn, out error);
+        var r = OnlinePearsonsRCalculator.Calculate(testY, fn, out error);
         if (error != OnlineCalculatorError.None) r = 0;
         testRsq[solIdx] = r * r;
@@ -204 +267 @@
     }
 
-    private static void PrepareData(IRegressionProblemData problemData, out double[,] trainX, out double[] trainY, out int numTrainObs, 
+    private static void PrepareData(IRegressionProblemData problemData, out double[,] trainX, out double[] trainY, out int numTrainObs,
       out double[,] testX, out double[] testY, out int numTestObs, out int numVars) {
       numVars = problemData.AllowedInputVariables.Count();
@@ -229 +292 @@
       // test
       rIdx = 0;
-      foreach(var row in problemData.TestIndices) {
+      foreach (var row in problemData.TestIndices) {
         int cIdx = 0;
-        foreach(var var in problemData.AllowedInputVariables) {
+        foreach (var var in problemData.AllowedInputVariables) {
           testX[cIdx, rIdx] = ds.GetDoubleValue(var, row);
           cIdx++;

branches/HeuristicLab.Algorithms.DataAnalysis.Glmnet/3.4/HeuristicLab.Algorithms.DataAnalysis.Glmnet.csproj

@@ -75 +75 @@
       <Private>False</Private>
     </Reference>
+    <Reference Include="HeuristicLab.Encodings.SymbolicExpressionTreeEncoding-3.4, Version=3.4.0.0, Culture=neutral, PublicKeyToken=ba48961d6f65dcec, processorArchitecture=MSIL">
+      <SpecificVersion>False</SpecificVersion>
+      <HintPath>..\..\..\trunk\sources\bin\HeuristicLab.Encodings.SymbolicExpressionTreeEncoding-3.4.dll</HintPath>
+    </Reference>
     <Reference Include="HeuristicLab.Optimization-3.3, Version=3.3.0.0, Culture=neutral, PublicKeyToken=ba48961d6f65dcec, processorArchitecture=MSIL">
       <HintPath>..\..\..\trunk\sources\bin\HeuristicLab.Optimization-3.3.dll</HintPath>
@@ -99 +103 @@
       <SpecificVersion>False</SpecificVersion>
       <Private>False</Private>
+    </Reference>
+    <Reference Include="HeuristicLab.Problems.DataAnalysis.Symbolic-3.4, Version=3.4.0.0, Culture=neutral, PublicKeyToken=ba48961d6f65dcec, processorArchitecture=MSIL">
+      <SpecificVersion>False</SpecificVersion>
+      <HintPath>..\..\..\trunk\sources\bin\HeuristicLab.Problems.DataAnalysis.Symbolic-3.4.dll</HintPath>
+    </Reference>
+    <Reference Include="HeuristicLab.Problems.DataAnalysis.Symbolic.Regression-3.4, Version=3.4.0.0, Culture=neutral, PublicKeyToken=ba48961d6f65dcec, processorArchitecture=MSIL">
+      <SpecificVersion>False</SpecificVersion>
+      <HintPath>..\..\..\trunk\sources\bin\HeuristicLab.Problems.DataAnalysis.Symbolic.Regression-3.4.dll</HintPath>
     </Reference>
     <Reference Include="HeuristicLab.Problems.Instances-3.3, Version=3.3.0.0, Culture=neutral, PublicKeyToken=ba48961d6f65dcec, processorArchitecture=MSIL">

branches/HeuristicLab.Algorithms.DataAnalysis.Glmnet/3.4/Plugin.cs.frame

@@ -37 +37 @@
   [PluginDependency("HeuristicLab.Core", "3.3")]
   [PluginDependency("HeuristicLab.Data", "3.3")]
+  [PluginDependency("HeuristicLab.Encodings.SymbolicExpressionTreeEncoding", "3.4")]
   [PluginDependency("HeuristicLab.Optimization", "3.3")]
   [PluginDependency("HeuristicLab.Parameters", "3.3")]
   [PluginDependency("HeuristicLab.Persistence", "3.3")]
   [PluginDependency("HeuristicLab.Problems.DataAnalysis", "3.4")]
+  [PluginDependency("HeuristicLab.Problems.DataAnalysis.Symbolic", "3.4")]
+  [PluginDependency("HeuristicLab.Problems.DataAnalysis.Symbolic.Regression", "3.4")]
   [PluginDependency("HeuristicLab.Problems.Instances", "3.3")]
   public class HeuristicLabAlgorithmsDataAnalysisGlmnetPlugin : PluginBase {