Changeset 14327 for stable/HeuristicLab.Algorithms.DataAnalysis/3.4

Timestamp:

10/07/16 11:00:55 (8 years ago)

Author:

gkronber

Message:

#2653: merged r14236,r14314:14315 and r14322 from trunk to stable

Location:

stable

Files:

• . (modified) (1 prop)
• HeuristicLab.Algorithms.DataAnalysis (modified) (1 prop)
• HeuristicLab.Algorithms.DataAnalysis/3.4/GradientBoostedTrees/GradientBoostedTreesModelSurrogate.cs (modified) (8 diffs)
• HeuristicLab.Algorithms.DataAnalysis/3.4/NearestNeighbour/NearestNeighbourModel.cs (modified) (4 diffs)

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

@@ -21 +21 @@
 #endregion
 
+using System;
 using System.Collections.Generic;
+using System.Diagnostics.Eventing.Reader;
 using System.Linq;
 using HeuristicLab.Common;
@@ -36 +38 @@
   public sealed class GradientBoostedTreesModelSurrogate : RegressionModel, IGradientBoostedTreesModel {
     // don't store the actual model!
-    private IGradientBoostedTreesModel actualModel; // the actual model is only recalculated when necessary
+    // the actual model is only recalculated when necessary
+    private readonly Lazy<IGradientBoostedTreesModel> actualModel;
+    private IGradientBoostedTreesModel ActualModel {
+      get { return actualModel.Value; }
+    }
 
     [Storable]
@@ -57 +63 @@
 
     public override IEnumerable<string> VariablesUsedForPrediction {
-      get { return actualModel.Models.SelectMany(x => x.VariablesUsedForPrediction).Distinct().OrderBy(x => x); }
+      get {
+        return ActualModel.Models.SelectMany(x => x.VariablesUsedForPrediction).Distinct().OrderBy(x => x);
+      }
     }
 
     [StorableConstructor]
-    private GradientBoostedTreesModelSurrogate(bool deserializing) : base(deserializing) { }
+    private GradientBoostedTreesModelSurrogate(bool deserializing)
+      : base(deserializing) {
+      actualModel = new Lazy<IGradientBoostedTreesModel>(() => RecalculateModel());
+    }
 
     private GradientBoostedTreesModelSurrogate(GradientBoostedTreesModelSurrogate original, Cloner cloner)
       : base(original, cloner) {
-      if (original.actualModel != null) this.actualModel = cloner.Clone(original.actualModel);
+      IGradientBoostedTreesModel clonedModel = null;
+      if (original.ActualModel != null) clonedModel = cloner.Clone(original.ActualModel);
+      actualModel = new Lazy<IGradientBoostedTreesModel>(CreateLazyInitFunc(clonedModel)); // only capture clonedModel in the closure
 
       this.trainingProblemData = cloner.Clone(original.trainingProblemData);
@@ -75 +88 @@
       this.m = original.m;
       this.nu = original.nu;
+    }
+
+    private Func<IGradientBoostedTreesModel> CreateLazyInitFunc(IGradientBoostedTreesModel clonedModel) {
+      return () => {
+        return clonedModel == null ? RecalculateModel() : clonedModel;
+      };
     }
 
@@ -96 +115 @@
       IGradientBoostedTreesModel model)
       : this(trainingProblemData, seed, lossFunction, iterations, maxSize, r, m, nu) {
-      this.actualModel = model;
+      actualModel = new Lazy<IGradientBoostedTreesModel>(() => model);
     }
 
@@ -105 +124 @@
     // forward message to actual model (recalculate model first if necessary)
     public override IEnumerable<double> GetEstimatedValues(IDataset dataset, IEnumerable<int> rows) {
-      if (actualModel == null) actualModel = RecalculateModel();
-      return actualModel.GetEstimatedValues(dataset, rows);
+      return ActualModel.GetEstimatedValues(dataset, rows);
     }
 
@@ -119 +137 @@
     public IEnumerable<IRegressionModel> Models {
       get {
-        if (actualModel == null) actualModel = RecalculateModel();
-        return actualModel.Models;
+        return ActualModel.Models;
       }
     }
@@ -126 +143 @@
     public IEnumerable<double> Weights {
       get {
-        if (actualModel == null) actualModel = RecalculateModel();
-        return actualModel.Weights;
+        return ActualModel.Weights;
       }
     }

stable/HeuristicLab.Algorithms.DataAnalysis/3.4/NearestNeighbour/NearestNeighbourModel.cs

@@ -36 +36 @@
   public sealed class NearestNeighbourModel : ClassificationModel, INearestNeighbourModel {
 
+    private readonly object kdTreeLockObject = new object();
     private alglib.nearestneighbor.kdtree kdTree;
     public alglib.nearestneighbor.kdtree KDTree {
@@ -47 +48 @@
       }
     }
+
 
     public override IEnumerable<string> VariablesUsedForPrediction {
@@ -200 +202 @@
           x[column] = inputData[row, column];
         }
-        int actNeighbours = alglib.nearestneighbor.kdtreequeryknn(kdTree, x, k, false);
-        alglib.nearestneighbor.kdtreequeryresultsdistances(kdTree, ref dists);
-        alglib.nearestneighbor.kdtreequeryresultsxy(kdTree, ref neighbours); // gkronber: this call changes the kdTree data structure
+        int numNeighbours;
+        lock (kdTreeLockObject) { // gkronber: the following calls change the kdTree data structure
+          numNeighbours = alglib.nearestneighbor.kdtreequeryknn(kdTree, x, k, false);
+          alglib.nearestneighbor.kdtreequeryresultsdistances(kdTree, ref dists);
+          alglib.nearestneighbor.kdtreequeryresultsxy(kdTree, ref neighbours);
+        }
 
         double distanceWeightedValue = 0.0;
         double distsSum = 0.0;
-        for (int i = 0; i < actNeighbours; i++) {
+        for (int i = 0; i < numNeighbours; i++) {
           distanceWeightedValue += neighbours[i, columns] / dists[i];
           distsSum += 1.0 / dists[i];
@@ -233 +238 @@
           x[column] = inputData[row, column];
         }
-        int actNeighbours = alglib.nearestneighbor.kdtreequeryknn(kdTree, x, k, false);
-        alglib.nearestneighbor.kdtreequeryresultsdistances(kdTree, ref dists);
-        alglib.nearestneighbor.kdtreequeryresultsxy(kdTree, ref neighbours);
-
+        int numNeighbours;
+        lock (kdTreeLockObject) {
+          // gkronber: the following calls change the kdTree data structure
+          numNeighbours = alglib.nearestneighbor.kdtreequeryknn(kdTree, x, k, false);
+          alglib.nearestneighbor.kdtreequeryresultsdistances(kdTree, ref dists);
+          alglib.nearestneighbor.kdtreequeryresultsxy(kdTree, ref neighbours);
+        }
         Array.Clear(y, 0, y.Length);
-        for (int i = 0; i < actNeighbours; i++) {
+        for (int i = 0; i < numNeighbours; i++) {
           int classValue = (int)Math.Round(neighbours[i, columns]);
           y[classValue]++;