Changeset 17120 for branches/2994-AutoDiffForIntervals/HeuristicLab.Algorithms.DataAnalysis/3.4/GradientBoostedTrees

Timestamp:

07/10/19 17:39:38 (5 years ago)

Author:

gkronber

Message:

#2994: merged r17007:17118 from trunk to branch

Location:

branches/2994-AutoDiffForIntervals

Files:

• . (modified) (1 prop)
• HeuristicLab.Algorithms.DataAnalysis (modified) (1 prop)
• HeuristicLab.Algorithms.DataAnalysis/3.4 (modified) (1 prop)
• HeuristicLab.Algorithms.DataAnalysis/3.4/GradientBoostedTrees/GradientBoostedTreesAlgorithm.cs (modified) (10 diffs)
• HeuristicLab.Algorithms.DataAnalysis/3.4/GradientBoostedTrees/GradientBoostedTreesAlgorithmStatic.cs (modified) (1 diff)
• HeuristicLab.Algorithms.DataAnalysis/3.4/GradientBoostedTrees/GradientBoostedTreesModel.cs (modified) (2 diffs)
• HeuristicLab.Algorithms.DataAnalysis/3.4/GradientBoostedTrees/GradientBoostedTreesModelSurrogate.cs (modified) (2 diffs)
• HeuristicLab.Algorithms.DataAnalysis/3.4/GradientBoostedTrees/ModelCreation.cs (copied) (copied from trunk/HeuristicLab.Algorithms.DataAnalysis/3.4/GradientBoostedTrees/ModelCreation.cs)

branches/2994-AutoDiffForIntervals/HeuristicLab.Algorithms.DataAnalysis/3.4/GradientBoostedTrees/GradientBoostedTreesAlgorithm.cs

@@ -21 +21 @@
 #endregion
 
+using System;
 using System.Linq;
 using System.Threading;
+using HeuristicLab.Algorithms.DataAnalysis.GradientBoostedTrees;
 using HeuristicLab.Analysis;
 using HeuristicLab.Common;
@@ -48 +50 @@
     private const string LossFunctionParameterName = "LossFunction";
     private const string UpdateIntervalParameterName = "UpdateInterval";
-    private const string CreateSolutionParameterName = "CreateSolution";
+    private const string ModelCreationParameterName = "ModelCreation";
     #endregion
 
@@ -79 +81 @@
       get { return (IFixedValueParameter<IntValue>)Parameters[UpdateIntervalParameterName]; }
     }
-    public IFixedValueParameter<BoolValue> CreateSolutionParameter {
-      get { return (IFixedValueParameter<BoolValue>)Parameters[CreateSolutionParameterName]; }
+    private IFixedValueParameter<EnumValue<ModelCreation>> ModelCreationParameter {
+      get { return (IFixedValueParameter<EnumValue<ModelCreation>>)Parameters[ModelCreationParameterName]; }
     }
     #endregion
@@ -113 +115 @@
       set { MParameter.Value.Value = value; }
     }
-    public bool CreateSolution {
-      get { return CreateSolutionParameter.Value.Value; }
-      set { CreateSolutionParameter.Value.Value = value; }
+    public ModelCreation ModelCreation {
+      get { return ModelCreationParameter.Value.Value; }
+      set { ModelCreationParameter.Value.Value = value; }
     }
     #endregion
@@ -146 +148 @@
       Parameters.Add(new FixedValueParameter<IntValue>(SeedParameterName, "The random seed used to initialize the new pseudo random number generator.", new IntValue(0)));
       Parameters.Add(new FixedValueParameter<BoolValue>(SetSeedRandomlyParameterName, "True if the random seed should be set to a random value, otherwise false.", new BoolValue(true)));
-      Parameters.Add(new FixedValueParameter<IntValue>(MaxSizeParameterName, "Maximal size of the tree learned in each step (prefer smaller sizes if possible)", new IntValue(10)));
+      Parameters.Add(new FixedValueParameter<IntValue>(MaxSizeParameterName, "Maximal size of the tree learned in each step (prefer smaller sizes (3 to 10) if possible)", new IntValue(10)));
       Parameters.Add(new FixedValueParameter<DoubleValue>(RParameterName, "Ratio of training rows selected randomly in each step (0 < R <= 1)", new DoubleValue(0.5)));
       Parameters.Add(new FixedValueParameter<DoubleValue>(MParameterName, "Ratio of variables selected randomly in each step (0 < M <= 1)", new DoubleValue(0.5)));
@@ -152 +154 @@
       Parameters.Add(new FixedValueParameter<IntValue>(UpdateIntervalParameterName, "", new IntValue(100)));
       Parameters[UpdateIntervalParameterName].Hidden = true;
-      Parameters.Add(new FixedValueParameter<BoolValue>(CreateSolutionParameterName, "Flag that indicates if a solution should be produced at the end of the run", new BoolValue(true)));
-      Parameters[CreateSolutionParameterName].Hidden = true;
+      Parameters.Add(new FixedValueParameter<EnumValue<ModelCreation>>(ModelCreationParameterName, "Defines the results produced at the end of the run (Surrogate => Less disk space, lazy recalculation of model)", new EnumValue<ModelCreation>(ModelCreation.Model)));
+      Parameters[ModelCreationParameterName].Hidden = true;
 
       var lossFunctions = ApplicationManager.Manager.GetInstances<ILossFunction>();
@@ -164 +166 @@
       // BackwardsCompatibility3.4
       #region Backwards compatible code, remove with 3.5
+
+      #region LossFunction
       // parameter type has been changed
       var lossFunctionParam = Parameters[LossFunctionParameterName] as ConstrainedValueParameter<StringValue>;
@@ -182 +186 @@
       }
       #endregion
+
+      #region CreateSolution
+      // parameter type has been changed
+      if (Parameters.ContainsKey("CreateSolution")) {
+        var createSolutionParam = Parameters["CreateSolution"] as FixedValueParameter<BoolValue>;
+        Parameters.Remove(createSolutionParam);
+
+        ModelCreation value = createSolutionParam.Value.Value ? ModelCreation.Model : ModelCreation.QualityOnly;
+        Parameters.Add(new FixedValueParameter<EnumValue<ModelCreation>>(ModelCreationParameterName, "Defines the results produced at the end of the run (Surrogate => Less disk space, lazy recalculation of model)", new EnumValue<ModelCreation>(value)));
+        Parameters[ModelCreationParameterName].Hidden = true;
+      }
+      #endregion
+      #endregion
     }
 
@@ -248 +265 @@
 
       // produce solution 
-      if (CreateSolution) {
-        var model = state.GetModel();
+      if (ModelCreation == ModelCreation.SurrogateModel || ModelCreation == ModelCreation.Model) {
+        IRegressionModel model = state.GetModel();
+
+        if (ModelCreation == ModelCreation.SurrogateModel) {
+          model = new GradientBoostedTreesModelSurrogate((GradientBoostedTreesModel)model, problemData, (uint)Seed, lossFunction, Iterations, MaxSize, R, M, Nu);
+        }
 
         // for logistic regression we produce a classification solution
@@ -271 +292 @@
           Results.Add(new Result("Solution", new GradientBoostedTreesSolution(model, problemData)));
         }
+      } else if (ModelCreation == ModelCreation.QualityOnly) {
+        //Do nothing
+      } else {
+        throw new NotImplementedException("Selected parameter for CreateSolution isn't implemented yet");
       }
     }

branches/2994-AutoDiffForIntervals/HeuristicLab.Algorithms.DataAnalysis/3.4/GradientBoostedTrees/GradientBoostedTreesAlgorithmStatic.cs

@@ -101 +101 @@
 
       public IRegressionModel GetModel() {
-#pragma warning disable 618
-        var model = new GradientBoostedTreesModel(models, weights);
-#pragma warning restore 618
-        // we don't know the number of iterations here but the number of weights is equal 
-        // to the number of iterations + 1 (for the constant model)
-        // wrap the actual model in a surrogate that enables persistence and lazy recalculation of the model if necessary
-        return new GradientBoostedTreesModelSurrogate(problemData, randSeed, lossFunction, weights.Count - 1, maxSize, r, m, nu, model);
+        return new GradientBoostedTreesModel(models, weights);
       }
       public IEnumerable<KeyValuePair<string, double>> GetVariableRelevance() {

branches/2994-AutoDiffForIntervals/HeuristicLab.Algorithms.DataAnalysis/3.4/GradientBoostedTrees/GradientBoostedTreesModel.cs

@@ -34 +34 @@
   // this is essentially a collection of weighted regression models
   public sealed class GradientBoostedTreesModel : RegressionModel, IGradientBoostedTreesModel {
-    // BackwardsCompatibility3.4 for allowing deserialization & serialization of old models
-    #region Backwards compatible code, remove with 3.5
-    private bool isCompatibilityLoaded = false; // only set to true if the model is deserialized from the old format, needed to make sure that information is serialized again if it was loaded from the old format
-
     [Storable(Name = "models")]
     private IList<IRegressionModel> __persistedModels {
       set {
-        this.isCompatibilityLoaded = true;
         this.models.Clear();
         foreach (var m in value) this.models.Add(m);
       }
-      get { if (this.isCompatibilityLoaded) return models; else return null; }
+      get { return models; }
     }
     [Storable(Name = "weights")]
     private IList<double> __persistedWeights {
       set {
-        this.isCompatibilityLoaded = true;
         this.weights.Clear();
         foreach (var w in value) this.weights.Add(w);
       }
-      get { if (this.isCompatibilityLoaded) return weights; else return null; }
+      get { return weights; }
     }
-    #endregion
 
     public override IEnumerable<string> VariablesUsedForPrediction {
@@ -77 +70 @@
       this.weights = new List<double>(original.weights);
       this.models = new List<IRegressionModel>(original.models.Select(m => cloner.Clone(m)));
-      this.isCompatibilityLoaded = original.isCompatibilityLoaded;
     }
-    [Obsolete("The constructor of GBTModel should not be used directly anymore (use GBTModelSurrogate instead)")]
+
     internal GradientBoostedTreesModel(IEnumerable<IRegressionModel> models, IEnumerable<double> weights)
       : base(string.Empty, "Gradient boosted tree model", string.Empty) {

branches/2994-AutoDiffForIntervals/HeuristicLab.Algorithms.DataAnalysis/3.4/GradientBoostedTrees/GradientBoostedTreesModelSurrogate.cs

@@ -90 +90 @@
     private Func<IGradientBoostedTreesModel> CreateLazyInitFunc(IGradientBoostedTreesModel clonedModel) {
       return () => {
-        return clonedModel == null ? RecalculateModel() : clonedModel;
+        return clonedModel ?? RecalculateModel();
       };
     }
 
     // create only the surrogate model without an actual model
-    public GradientBoostedTreesModelSurrogate(IRegressionProblemData trainingProblemData, uint seed,
+    private 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) {
@@ -106 +106 @@
       this.m = m;
       this.nu = nu;
+
+      actualModel = new Lazy<IGradientBoostedTreesModel>(() => RecalculateModel());
     }
 
     // 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,
-      IGradientBoostedTreesModel model)
+    public GradientBoostedTreesModelSurrogate(IGradientBoostedTreesModel model, IRegressionProblemData trainingProblemData, uint seed,
+      ILossFunction lossFunction, int iterations, int maxSize, double r, double m, double nu)
       : this(trainingProblemData, seed, lossFunction, iterations, maxSize, r, m, nu) {
       actualModel = new Lazy<IGradientBoostedTreesModel>(() => model);