Changeset 14345 for trunk/sources/HeuristicLab.Algorithms.DataAnalysis/3.4/GradientBoostedTrees

Timestamp:

10/21/16 17:59:36 (8 years ago)

Author:

gkronber

Message:

#2690: implemented methods to generate symbolic expression tree solutions for decision tree models (random forest and gradient boosted) as well as views which make it possible to inspect each of the individual trees in a GBT and RF solution

Location:

trunk/sources/HeuristicLab.Algorithms.DataAnalysis/3.4/GradientBoostedTrees

Files:

• GradientBoostedTreesAlgorithm.cs (modified) (1 diff)
• GradientBoostedTreesSolution.cs (modified) (1 diff)
• RegressionTreeModel.cs (modified) (2 diffs)

trunk/sources/HeuristicLab.Algorithms.DataAnalysis/3.4/GradientBoostedTrees/GradientBoostedTreesAlgorithm.cs

@@ -269 +269 @@
         } else {
           // otherwise we produce a regression solution
-          Results.Add(new Result("Solution", new RegressionSolution(model, problemData)));
+          Results.Add(new Result("Solution", new GradientBoostedTreesSolution(model, problemData)));
         }
       }

trunk/sources/HeuristicLab.Algorithms.DataAnalysis/3.4/GradientBoostedTrees/GradientBoostedTreesSolution.cs

@@ -20 +20 @@
 #endregion
 
-using System.Collections.Generic;
-using System.Linq;
 using HeuristicLab.Common;
 using HeuristicLab.Persistence.Default.CompositeSerializers.Storable;

trunk/sources/HeuristicLab.Algorithms.DataAnalysis/3.4/GradientBoostedTrees/RegressionTreeModel.cs

@@ -28 +28 @@
 using HeuristicLab.Common;
 using HeuristicLab.Core;
+using HeuristicLab.Encodings.SymbolicExpressionTreeEncoding;
 using HeuristicLab.Persistence.Default.CompositeSerializers.Storable;
 using HeuristicLab.Problems.DataAnalysis;
+using HeuristicLab.Problems.DataAnalysis.Symbolic;
+using HeuristicLab.Problems.DataAnalysis.Symbolic.Regression;
 
 namespace HeuristicLab.Algorithms.DataAnalysis {
@@ -210 +213 @@
     }
 
+    /// <summary>
+    /// Transforms the tree model to a symbolic regression solution
+    /// </summary>
+    /// <param name="problemData"></param>
+    /// <returns>A new symbolic regression solution which matches the tree model</returns>
+    public ISymbolicRegressionSolution CreateSymbolicRegressionSolution(IRegressionProblemData problemData) {
+      var rootSy = new ProgramRootSymbol();
+      var startSy = new StartSymbol();
+      var varCondSy = new VariableCondition() { IgnoreSlope = true };
+      var constSy = new Constant();
+
+      var startNode = startSy.CreateTreeNode();
+      startNode.AddSubtree(CreateSymbolicRegressionTreeRecursive(tree, 0, varCondSy, constSy));
+      var rootNode = rootSy.CreateTreeNode();
+      rootNode.AddSubtree(startNode);
+      var model = new SymbolicRegressionModel(TargetVariable, new SymbolicExpressionTree(rootNode), new SymbolicDataAnalysisExpressionTreeLinearInterpreter());
+      return model.CreateRegressionSolution(problemData);
+    }
+
+    private ISymbolicExpressionTreeNode CreateSymbolicRegressionTreeRecursive(TreeNode[] treeNodes, int nodeIdx, VariableCondition varCondSy, Constant constSy) {
+      var curNode = treeNodes[nodeIdx];
+      if (curNode.VarName == TreeNode.NO_VARIABLE) {
+        var node = (ConstantTreeNode)constSy.CreateTreeNode();
+        node.Value = curNode.Val;
+        return node;
+      } else {
+        var node = (VariableConditionTreeNode)varCondSy.CreateTreeNode();
+        node.VariableName = curNode.VarName;
+        node.Threshold = curNode.Val;
+
+        var left = CreateSymbolicRegressionTreeRecursive(treeNodes, curNode.LeftIdx, varCondSy, constSy);
+        var right = CreateSymbolicRegressionTreeRecursive(treeNodes, curNode.RightIdx, varCondSy, constSy);
+        node.AddSubtree(left);
+        node.AddSubtree(right);
+        return node;
+      }
+    }
+
+
     private string TreeToString(int idx, string part) {
       var n = tree[idx];