Changeset 14029 for branches/crossvalidation-2434/HeuristicLab.Algorithms.DataAnalysis/3.4/GradientBoostedTrees/GradientBoostedTreesModelSurrogate.cs

Timestamp:

07/08/16 14:40:02 (8 years ago)

Author:

gkronber

Message:

#2434: merged trunk changes r12934:14026 from trunk to branch

Location:

branches/crossvalidation-2434

Files:

• . (modified) (1 prop)
• HeuristicLab.Algorithms.DataAnalysis (modified) (1 prop)
• HeuristicLab.Algorithms.DataAnalysis/3.4/GradientBoostedTrees/GradientBoostedTreesModelSurrogate.cs (modified) (7 diffs)

branches/crossvalidation-2434/HeuristicLab.Algorithms.DataAnalysis/3.4/GradientBoostedTrees/GradientBoostedTreesModelSurrogate.cs

@@ -21 +21 @@
 #endregion
 
-using System;
 using System.Collections.Generic;
 using System.Linq;
@@ -27 +26 @@
 using HeuristicLab.Core;
 using HeuristicLab.Persistence.Default.CompositeSerializers.Storable;
-using HeuristicLab.PluginInfrastructure;
 using HeuristicLab.Problems.DataAnalysis;
 
@@ -36 +34 @@
   // recalculate the actual GBT model on demand
   [Item("Gradient boosted tree model", "")]
-  public sealed class GradientBoostedTreesModelSurrogate : NamedItem, IRegressionModel {
+  public sealed class GradientBoostedTreesModelSurrogate : RegressionModel, IGradientBoostedTreesModel {
     // don't store the actual model!
-    private IRegressionModel actualModel; // the actual model is only recalculated when necessary
+    private IGradientBoostedTreesModel actualModel; // the actual model is only recalculated when necessary
 
     [Storable]
@@ -58 +56 @@
 
 
+    public override IEnumerable<string> VariablesUsedForPrediction {
+      get { return actualModel.Models.SelectMany(x => x.VariablesUsedForPrediction).Distinct().OrderBy(x => x); }
+    }
+
     [StorableConstructor]
     private GradientBoostedTreesModelSurrogate(bool deserializing) : base(deserializing) { }
@@ -76 +78 @@
 
     // create only the surrogate model without an actual model
-    public GradientBoostedTreesModelSurrogate(IRegressionProblemData trainingProblemData, uint seed, ILossFunction lossFunction, int iterations, int maxSize, double r, double m, double nu)
-      : base("Gradient boosted tree model", string.Empty) {
+    public GradientBoostedTreesModelSurrogate(IRegressionProblemData trainingProblemData, uint seed,
+      ILossFunction lossFunction, int iterations, int maxSize, double r, double m, double nu)
+      : base(trainingProblemData.TargetVariable, "Gradient boosted tree model", string.Empty) {
       this.trainingProblemData = trainingProblemData;
       this.seed = seed;
@@ -89 +92 @@
 
     // wrap an actual model in a surrograte
-    public GradientBoostedTreesModelSurrogate(IRegressionProblemData trainingProblemData, uint seed, ILossFunction lossFunction, int iterations, int maxSize, double r, double m, double nu, IRegressionModel model)
+    public GradientBoostedTreesModelSurrogate(IRegressionProblemData trainingProblemData, uint seed,
+      ILossFunction lossFunction, int iterations, int maxSize, double r, double m, double nu,
+      IGradientBoostedTreesModel model)
       : this(trainingProblemData, seed, lossFunction, iterations, maxSize, r, m, nu) {
       this.actualModel = model;
@@ -99 +104 @@
 
     // forward message to actual model (recalculate model first if necessary)
-    public IEnumerable<double> GetEstimatedValues(IDataset dataset, IEnumerable<int> rows) {
+    public override IEnumerable<double> GetEstimatedValues(IDataset dataset, IEnumerable<int> rows) {
       if (actualModel == null) actualModel = RecalculateModel();
       return actualModel.GetEstimatedValues(dataset, rows);
     }
 
-    public IRegressionSolution CreateRegressionSolution(IRegressionProblemData problemData) {
+    public override IRegressionSolution CreateRegressionSolution(IRegressionProblemData problemData) {
       return new RegressionSolution(this, (IRegressionProblemData)problemData.Clone());
     }
 
+    private IGradientBoostedTreesModel RecalculateModel() {
+      return GradientBoostedTreesAlgorithmStatic.TrainGbm(trainingProblemData, lossFunction, maxSize, nu, r, m, iterations, seed).Model;
+    }
 
-    private IRegressionModel RecalculateModel() {
-      return GradientBoostedTreesAlgorithmStatic.TrainGbm(trainingProblemData, lossFunction, maxSize, nu, r, m, iterations, seed).Model;
+    public IEnumerable<IRegressionModel> Models {
+      get {
+        if (actualModel == null) actualModel = RecalculateModel();
+        return actualModel.Models;
+      }
+    }
+
+    public IEnumerable<double> Weights {
+      get {
+        if (actualModel == null) actualModel = RecalculateModel();
+        return actualModel.Weights;
+      }
     }
   }