Changeset 12372 for branches/GBT/HeuristicLab.Algorithms.DataAnalysis/3.4/GradientBoostedTrees/RegressionTreeModel.cs

Timestamp:

05/01/15 18:30:56 (9 years ago)

Author:

gkronber

Message:

#2261: implemented prototype view for gradient boosted trees

File:

• branches/GBT/HeuristicLab.Algorithms.DataAnalysis/3.4/GradientBoostedTrees/RegressionTreeModel.cs (modified) (4 diffs)

branches/GBT/HeuristicLab.Algorithms.DataAnalysis/3.4/GradientBoostedTrees/RegressionTreeModel.cs

@@ -1 @@
-using System.Collections.Generic;
+using System;
+using System.Collections.Generic;
 using System.Linq;
 using HeuristicLab.Common;
@@ -12 +13 @@
   public class RegressionTreeModel : NamedItem, IRegressionModel {
 
+    // trees are represented as a flat array
+    // object-graph-travesal has problems if this is defined as a struct. TODO investigate...
     [StorableClass]
     public class TreeNode {
       public readonly static string NO_VARIABLE = string.Empty;
       [Storable]
-      public readonly string varName; // name of the variable for splitting or -1 if terminal node
+      public string varName; // name of the variable for splitting or -1 if terminal node
       [Storable]
-      public readonly double val; // threshold
+      public double val; // threshold
       [Storable]
-      public readonly TreeNode left;
+      public int leftIdx;
       [Storable]
-      public readonly TreeNode right;
+      public int rightIdx;
 
+      public TreeNode() {
+        varName = NO_VARIABLE;
+        leftIdx = -1;
+        rightIdx = -1;
+      }
       [StorableConstructor]
       private TreeNode(bool deserializing) { }
-
-      public TreeNode(string varName, double value, TreeNode left = null, TreeNode right = null) {
-        this.varName = varName;
-        this.val = value;
-        this.left = left;
-        this.right = right;
-      }
     }
 
     [Storable]
-    public readonly TreeNode tree;
+    public readonly TreeNode[] tree;
 
     [StorableConstructor]
@@ -43 +44 @@
     public RegressionTreeModel(RegressionTreeModel original, Cloner cloner)
       : base(original, cloner) {
-      this.tree = original.tree;
+      this.tree = original.tree; // shallow clone, tree must be readonly
     }
 
-    public RegressionTreeModel(TreeNode tree)
-      : base() {
-      this.name = ItemName;
-      this.description = ItemDescription;
-
+    public RegressionTreeModel(TreeNode[] tree)
+      : base("RegressionTreeModel", "Represents a decision tree for regression.") {
       this.tree = tree;
     }
 
-    private static double GetPredictionForRow(TreeNode t, Dataset ds, int row) {
-      if (t.varName == TreeNode.NO_VARIABLE)
-        return t.val;
-      else if (ds.GetDoubleValue(t.varName, row) <= t.val)
-        return GetPredictionForRow(t.left, ds, row);
+    private static double GetPredictionForRow(TreeNode[] t, int nodeIdx, Dataset ds, int row) {
+      var node = t[nodeIdx];
+      if (node.varName == TreeNode.NO_VARIABLE)
+        return node.val;
+      else if (ds.GetDoubleValue(node.varName, row) <= node.val)
+        return GetPredictionForRow(t, node.leftIdx, ds, row);
       else
-        return GetPredictionForRow(t.right, ds, row);
+        return GetPredictionForRow(t, node.rightIdx, ds, row);
     }
 
@@ -68 +67 @@
 
     public IEnumerable<double> GetEstimatedValues(Dataset ds, IEnumerable<int> rows) {
-      return rows.Select(r => GetPredictionForRow(tree, ds, r));
+      return rows.Select(r => GetPredictionForRow(tree, 0, ds, r));
     }