Changeset 15127 for stable/HeuristicLab.Algorithms.DataAnalysis

Timestamp:

07/06/17 09:22:48 (7 years ago)

Author:

gkronber

Message:

#2690: merged r14345, r14346, r14368 from trunk to stable

Location:

stable/HeuristicLab.Algorithms.DataAnalysis/3.4

Files:

• GradientBoostedTrees/GradientBoostedTreesAlgorithm.cs (modified) (1 diff)
• GradientBoostedTrees/GradientBoostedTreesSolution.cs (modified) (1 diff)
• GradientBoostedTrees/RegressionTreeModel.cs (modified) (2 diffs)
• Interfaces/IRandomForestClassificationSolution.cs (modified) (1 diff)
• Interfaces/IRandomForestModel.cs (modified) (2 diffs)
• Interfaces/IRandomForestRegressionSolution.cs (modified) (2 diffs)
• RandomForest/RandomForestClassificationSolution.cs (modified) (1 diff)
• RandomForest/RandomForestModel.cs (modified) (4 diffs)
• RandomForest/RandomForestRegressionSolution.cs (modified) (2 diffs)

stable/HeuristicLab.Algorithms.DataAnalysis/3.4/GradientBoostedTrees/GradientBoostedTreesAlgorithm.cs

@@ -270 +270 @@
         } 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)));
         }
       }

stable/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;

stable/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];

stable/HeuristicLab.Algorithms.DataAnalysis/3.4/Interfaces/IRandomForestClassificationSolution.cs

@@ -30 +30 @@
   public interface IRandomForestClassificationSolution : IClassificationSolution {
     new IRandomForestModel Model { get; }
+    int NumberOfTrees { get; }
   }
 }

stable/HeuristicLab.Algorithms.DataAnalysis/3.4/Interfaces/IRandomForestModel.cs

@@ -20 +20 @@
 #endregion
 
-using HeuristicLab.Optimization;
+using HeuristicLab.Encodings.SymbolicExpressionTreeEncoding;
 using HeuristicLab.Problems.DataAnalysis;
-using HeuristicLab.Core;
-using System.Collections.Generic;
+
 
 namespace HeuristicLab.Algorithms.DataAnalysis {
@@ -30 +29 @@
   /// </summary>
   public interface IRandomForestModel : IConfidenceRegressionModel, IClassificationModel {
+    int NumberOfTrees { get; }
+    ISymbolicExpressionTree ExtractTree(int treeIdx); // returns a specific tree from the random forest as a ISymbolicRegressionModel
   }
 }

stable/HeuristicLab.Algorithms.DataAnalysis/3.4/Interfaces/IRandomForestRegressionSolution.cs

@@ -20 +20 @@
 #endregion
 
-using HeuristicLab.Optimization;
 using HeuristicLab.Problems.DataAnalysis;
-using HeuristicLab.Core;
+using HeuristicLab.Problems.DataAnalysis.Symbolic.Regression;
 
 namespace HeuristicLab.Algorithms.DataAnalysis {
@@ -30 +29 @@
   public interface IRandomForestRegressionSolution : IConfidenceRegressionSolution {
     new IRandomForestModel Model { get; }
+    int NumberOfTrees { get; }
   }
 }

stable/HeuristicLab.Algorithms.DataAnalysis/3.4/RandomForest/RandomForestClassificationSolution.cs

@@ -38 +38 @@
     }
 
+    public int NumberOfTrees {
+      get { return Model.NumberOfTrees; }
+    }
+
     [StorableConstructor]
     private RandomForestClassificationSolution(bool deserializing) : base(deserializing) { }

stable/HeuristicLab.Algorithms.DataAnalysis/3.4/RandomForest/RandomForestModel.cs

@@ -25 +25 @@
 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;
 
 namespace HeuristicLab.Algorithms.DataAnalysis {
@@ -49 +51 @@
     }
 
+    public int NumberOfTrees {
+      get { return nTrees; }
+    }
 
     // instead of storing the data of the model itself
@@ -64 +69 @@
     [Storable]
     private double m;
-
 
     [StorableConstructor]
@@ -197 +201 @@
     }
 
+    public ISymbolicExpressionTree ExtractTree(int treeIdx) {
+      var rf = RandomForest;
+      // hoping that the internal representation of alglib is stable
+
+      // TREE FORMAT
+      // W[Offs]      -   size of sub-array (for the tree)
+      //     node info:
+      // W[K+0]       -   variable number        (-1 for leaf mode)
+      // W[K+1]       -   threshold              (class/value for leaf node)
+      // W[K+2]       -   ">=" branch index      (absent for leaf node)
+
+      // skip irrelevant trees
+      int offset = 0;
+      for (int i = 0; i < treeIdx - 1; i++) {
+        offset = offset + (int)Math.Round(rf.innerobj.trees[offset]);
+      }
+
+      var constSy = new Constant();
+      var varCondSy = new VariableCondition() { IgnoreSlope = true };
+
+      var node = CreateRegressionTreeRec(rf.innerobj.trees, offset, offset + 1, constSy, varCondSy);
+
+      var startNode = new StartSymbol().CreateTreeNode();
+      startNode.AddSubtree(node);
+      var root = new ProgramRootSymbol().CreateTreeNode();
+      root.AddSubtree(startNode);
+      return new SymbolicExpressionTree(root);
+    }
+
+    private ISymbolicExpressionTreeNode CreateRegressionTreeRec(double[] trees, int offset, int k, Constant constSy, VariableCondition varCondSy) {
+
+      // alglib source for evaluation of one tree (dfprocessinternal)
+      // offs = 0
+      //
+      // Set pointer to the root
+      //
+      // k = offs + 1;
+      // 
+      // //
+      // // Navigate through the tree
+      // //
+      // while (true) {
+      //   if ((double)(df.trees[k]) == (double)(-1)) {
+      //     if (df.nclasses == 1) {
+      //       y[0] = y[0] + df.trees[k + 1];
+      //     } else {
+      //       idx = (int)Math.Round(df.trees[k + 1]);
+      //       y[idx] = y[idx] + 1;
+      //     }
+      //     break;
+      //   }
+      //   if ((double)(x[(int)Math.Round(df.trees[k])]) < (double)(df.trees[k + 1])) {
+      //     k = k + innernodewidth;
+      //   } else {
+      //     k = offs + (int)Math.Round(df.trees[k + 2]);
+      //   }
+      // }
+
+      if ((double)(trees[k]) == (double)(-1)) {
+        var constNode = (ConstantTreeNode)constSy.CreateTreeNode();
+        constNode.Value = trees[k + 1];
+        return constNode;
+      } else {
+        var condNode = (VariableConditionTreeNode)varCondSy.CreateTreeNode();
+        condNode.VariableName = AllowedInputVariables[(int)Math.Round(trees[k])];
+        condNode.Threshold = trees[k + 1];
+        condNode.Slope = double.PositiveInfinity;
+
+        var left = CreateRegressionTreeRec(trees, offset, k + 3, constSy, varCondSy);
+        var right = CreateRegressionTreeRec(trees, offset, offset + (int)Math.Round(trees[k + 2]), constSy, varCondSy);
+
+        condNode.AddSubtree(left); // not 100% correct because interpreter uses: if(x <= thres) left() else right() and RF uses if(x < thres) left() else right() (see above)
+        condNode.AddSubtree(right);
+        return condNode;
+      }
+    }
+
 
     public IRegressionSolution CreateRegressionSolution(IRegressionProblemData problemData) {

stable/HeuristicLab.Algorithms.DataAnalysis/3.4/RandomForest/RandomForestRegressionSolution.cs

@@ -20 +20 @@
 #endregion
 
+using System;
 using HeuristicLab.Common;
 using HeuristicLab.Core;
 using HeuristicLab.Persistence.Default.CompositeSerializers.Storable;
 using HeuristicLab.Problems.DataAnalysis;
+using HeuristicLab.Problems.DataAnalysis.Symbolic.Regression;
 
 namespace HeuristicLab.Algorithms.DataAnalysis {
@@ -36 +38 @@
       get { return (IRandomForestModel)base.Model; }
       set { base.Model = value; }
+    }
+
+    public int NumberOfTrees {
+      get { return Model.NumberOfTrees; }
     }