Changeset 15973 for branches/2522_RefactorPluginInfrastructure/HeuristicLab.Algorithms.DataAnalysis/3.4/NearestNeighbour

Timestamp:

06/28/18 11:13:37 (6 years ago)

Author:

gkronber

Message:

#2522: merged trunk changes from r13402:15972 to branch resolving conflicts where necessary

Location:

branches/2522_RefactorPluginInfrastructure

Files:

• . (modified) (2 props)
• HeuristicLab.Algorithms.DataAnalysis (modified) (1 prop)
• HeuristicLab.Algorithms.DataAnalysis/3.4 (modified) (1 prop)
• HeuristicLab.Algorithms.DataAnalysis/3.4/NearestNeighbour/NearestNeighbourClassification.cs (modified) (7 diffs)
• HeuristicLab.Algorithms.DataAnalysis/3.4/NearestNeighbour/NearestNeighbourClassificationSolution.cs (modified) (2 diffs)
• HeuristicLab.Algorithms.DataAnalysis/3.4/NearestNeighbour/NearestNeighbourModel.cs (modified) (12 diffs)
• HeuristicLab.Algorithms.DataAnalysis/3.4/NearestNeighbour/NearestNeighbourRegression.cs (modified) (6 diffs)
• HeuristicLab.Algorithms.DataAnalysis/3.4/NearestNeighbour/NearestNeighbourRegressionSolution.cs (modified) (2 diffs)

branches/2522_RefactorPluginInfrastructure

@@ -24 +24 @@
 protoc.exe
 obj
+.vs

@@ -24 +24 @@
 protoc.exe
 obj
+.vs

branches/2522_RefactorPluginInfrastructure/HeuristicLab.Algorithms.DataAnalysis/3.4/NearestNeighbour/NearestNeighbourClassification.cs

@@ -1 +1 @@
 #region License Information
 /* HeuristicLab
- * Copyright (C) 2002-2015 Heuristic and Evolutionary Algorithms Laboratory (HEAL)
+ * Copyright (C) 2002-2018 Heuristic and Evolutionary Algorithms Laboratory (HEAL)
  *
  * This file is part of HeuristicLab.
@@ -22 +22 @@
 using System;
 using System.Linq;
+using System.Threading;
 using HeuristicLab.Common;
 using HeuristicLab.Core;
@@ -40 +41 @@
     private const string KParameterName = "K";
     private const string NearestNeighbourClassificationModelResultName = "Nearest neighbour classification solution";
+    private const string WeightsParameterName = "Weights";
+
 
     #region parameter properties
     public IFixedValueParameter<IntValue> KParameter {
       get { return (IFixedValueParameter<IntValue>)Parameters[KParameterName]; }
+    }
+    public IValueParameter<DoubleArray> WeightsParameter {
+      get { return (IValueParameter<DoubleArray>)Parameters[WeightsParameterName]; }
     }
     #endregion
@@ -53 +59 @@
         else KParameter.Value.Value = value;
       }
+    }
+    public DoubleArray Weights {
+      get { return WeightsParameter.Value; }
+      set { WeightsParameter.Value = value; }
     }
     #endregion
@@ -64 +74 @@
       : base() {
       Parameters.Add(new FixedValueParameter<IntValue>(KParameterName, "The number of nearest neighbours to consider for regression.", new IntValue(3)));
+      Parameters.Add(new OptionalValueParameter<DoubleArray>(WeightsParameterName, "Optional: use weights to specify individual scaling values for all features. If not set the weights are calculated automatically (each feature is scaled to unit variance)"));
       Problem = new ClassificationProblem();
     }
     [StorableHook(HookType.AfterDeserialization)]
-    private void AfterDeserialization() { }
+    private void AfterDeserialization() {
+      // BackwardsCompatibility3.3
+      #region Backwards compatible code, remove with 3.4
+      if (!Parameters.ContainsKey(WeightsParameterName)) {
+        Parameters.Add(new OptionalValueParameter<DoubleArray>(WeightsParameterName, "Optional: use weights to specify individual scaling values for all features. If not set the weights are calculated automatically (each feature is scaled to unit variance)"));
+      }
+      #endregion
+    }
 
     public override IDeepCloneable Clone(Cloner cloner) {
@@ -74 +92 @@
 
     #region nearest neighbour
-    protected override void Run() {
-      var solution = CreateNearestNeighbourClassificationSolution(Problem.ProblemData, K);
+    protected override void Run(CancellationToken cancellationToken) {
+      double[] weights = null;
+      if (Weights != null) weights = Weights.CloneAsArray();
+      var solution = CreateNearestNeighbourClassificationSolution(Problem.ProblemData, K, weights);
       Results.Add(new Result(NearestNeighbourClassificationModelResultName, "The nearest neighbour classification solution.", solution));
     }
 
-    public static IClassificationSolution CreateNearestNeighbourClassificationSolution(IClassificationProblemData problemData, int k) {
+    public static IClassificationSolution CreateNearestNeighbourClassificationSolution(IClassificationProblemData problemData, int k, double[] weights = null) {
       var problemDataClone = (IClassificationProblemData)problemData.Clone();
-      return new NearestNeighbourClassificationSolution(problemDataClone, Train(problemDataClone, k));
+      return new NearestNeighbourClassificationSolution(Train(problemDataClone, k, weights), problemDataClone);
     }
 
-    public static INearestNeighbourModel Train(IClassificationProblemData problemData, int k) {
+    public static INearestNeighbourModel Train(IClassificationProblemData problemData, int k, double[] weights = null) {
       return new NearestNeighbourModel(problemData.Dataset,
         problemData.TrainingIndices,
@@ -90 +110 @@
         problemData.TargetVariable,
         problemData.AllowedInputVariables,
+        weights,
         problemData.ClassValues.ToArray());
     }

branches/2522_RefactorPluginInfrastructure/HeuristicLab.Algorithms.DataAnalysis/3.4/NearestNeighbour/NearestNeighbourClassificationSolution.cs

@@ -1 +1 @@
 #region License Information
 /* HeuristicLab
- * Copyright (C) 2002-2015 Heuristic and Evolutionary Algorithms Laboratory (HEAL)
+ * Copyright (C) 2002-2018 Heuristic and Evolutionary Algorithms Laboratory (HEAL)
  *
  * This file is part of HeuristicLab.
@@ -43 +43 @@
       : base(original, cloner) {
     }
-    public NearestNeighbourClassificationSolution(IClassificationProblemData problemData, INearestNeighbourModel nnModel)
+    public NearestNeighbourClassificationSolution(INearestNeighbourModel nnModel, IClassificationProblemData problemData)
       : base(nnModel, problemData) {
     }

branches/2522_RefactorPluginInfrastructure/HeuristicLab.Algorithms.DataAnalysis/3.4/NearestNeighbour/NearestNeighbourModel.cs

@@ -1 +1 @@
 #region License Information
 /* HeuristicLab
- * Copyright (C) 2002-2015 Heuristic and Evolutionary Algorithms Laboratory (HEAL)
+ * Copyright (C) 2002-2018 Heuristic and Evolutionary Algorithms Laboratory (HEAL)
  *
  * This file is part of HeuristicLab.
@@ -34 +34 @@
   [StorableClass]
   [Item("NearestNeighbourModel", "Represents a nearest neighbour model for regression and classification.")]
-  public sealed class NearestNeighbourModel : NamedItem, INearestNeighbourModel {
-
+  public sealed class NearestNeighbourModel : ClassificationModel, INearestNeighbourModel {
+
+    private readonly object kdTreeLockObject = new object();
     private alglib.nearestneighbor.kdtree kdTree;
     public alglib.nearestneighbor.kdtree KDTree {
@@ -48 +49 @@
     }
 
-    [Storable]
-    private string targetVariable;
+
+    public override IEnumerable<string> VariablesUsedForPrediction {
+      get { return allowedInputVariables; }
+    }
+
     [Storable]
     private string[] allowedInputVariables;
@@ -56 +60 @@
     [Storable]
     private int k;
+    [Storable(DefaultValue = null)]
+    private double[] weights; // not set for old versions loaded from disk
+    [Storable(DefaultValue = null)]
+    private double[] offsets; // not set for old versions loaded from disk
 
     [StorableConstructor]
@@ -91 +99 @@
 
       k = original.k;
-      targetVariable = original.targetVariable;
+      isCompatibilityLoaded = original.IsCompatibilityLoaded;
+      if (!IsCompatibilityLoaded) {
+        weights = new double[original.weights.Length];
+        Array.Copy(original.weights, weights, weights.Length);
+        offsets = new double[original.offsets.Length];
+        Array.Copy(original.offsets, this.offsets, this.offsets.Length);
+      }
       allowedInputVariables = (string[])original.allowedInputVariables.Clone();
       if (original.classValues != null)
         this.classValues = (double[])original.classValues.Clone();
     }
-    public NearestNeighbourModel(IDataset dataset, IEnumerable<int> rows, int k, string targetVariable, IEnumerable<string> allowedInputVariables, double[] classValues = null) {
+    public NearestNeighbourModel(IDataset dataset, IEnumerable<int> rows, int k, string targetVariable, IEnumerable<string> allowedInputVariables, IEnumerable<double> weights = null, double[] classValues = null)
+      : base(targetVariable) {
       Name = ItemName;
       Description = ItemDescription;
       this.k = k;
-      this.targetVariable = targetVariable;
       this.allowedInputVariables = allowedInputVariables.ToArray();
-
-      var inputMatrix = AlglibUtil.PrepareInputMatrix(dataset,
-                                   allowedInputVariables.Concat(new string[] { targetVariable }),
-                                   rows);
-
-      if (inputMatrix.Cast<double>().Any(x => double.IsNaN(x) || double.IsInfinity(x)))
+      double[,] inputMatrix;
+      if (IsCompatibilityLoaded) {
+        // no scaling
+        inputMatrix = dataset.ToArray(
+          this.allowedInputVariables.Concat(new string[] { targetVariable }),
+          rows);
+      } else {
+        this.offsets = this.allowedInputVariables
+          .Select(name => dataset.GetDoubleValues(name, rows).Average() * -1)
+          .Concat(new double[] { 0 }) // no offset for target variable
+          .ToArray();
+        if (weights == null) {
+          // automatic determination of weights (all features should have variance = 1)
+          this.weights = this.allowedInputVariables
+            .Select(name => 1.0 / dataset.GetDoubleValues(name, rows).StandardDeviationPop())
+            .Concat(new double[] { 1.0 }) // no scaling for target variable
+            .ToArray();
+        } else {
+          // user specified weights (+ 1 for target)
+          this.weights = weights.Concat(new double[] { 1.0 }).ToArray();
+          if (this.weights.Length - 1 != this.allowedInputVariables.Length)
+            throw new ArgumentException("The number of elements in the weight vector must match the number of input variables");
+        }
+        inputMatrix = CreateScaledData(dataset, this.allowedInputVariables.Concat(new string[] { targetVariable }), rows, this.offsets, this.weights);
+      }
+
+      if (inputMatrix.ContainsNanOrInfinity())
         throw new NotSupportedException(
-          "Nearest neighbour classification does not support NaN or infinity values in the input dataset.");
+          "Nearest neighbour model does not support NaN or infinity values in the input dataset.");
 
       this.kdTree = new alglib.nearestneighbor.kdtree();
@@ -131 +166 @@
     }
 
+    private static double[,] CreateScaledData(IDataset dataset, IEnumerable<string> variables, IEnumerable<int> rows, double[] offsets, double[] factors) {
+      var transforms =
+        variables.Select(
+          (_, colIdx) =>
+            new LinearTransformation(variables) { Addend = offsets[colIdx] * factors[colIdx], Multiplier = factors[colIdx] });
+      return dataset.ToArray(variables, transforms, rows);
+    }
+
     public override IDeepCloneable Clone(Cloner cloner) {
       return new NearestNeighbourModel(this, cloner);
@@ -136 +179 @@
 
     public IEnumerable<double> GetEstimatedValues(IDataset dataset, IEnumerable<int> rows) {
-      double[,] inputData = AlglibUtil.PrepareInputMatrix(dataset, allowedInputVariables, rows);
+      double[,] inputData;
+      if (IsCompatibilityLoaded) {
+        inputData = dataset.ToArray(allowedInputVariables, rows);
+      } else {
+        inputData = CreateScaledData(dataset, allowedInputVariables, rows, offsets, weights);
+      }
 
       int n = inputData.GetLength(0);
       int columns = inputData.GetLength(1);
       double[] x = new double[columns];
-      double[] y = new double[1];
       double[] dists = new double[k];
       double[,] neighbours = new double[k, columns + 1];
@@ -149 +196 @@
           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);
+        }
 
         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];
@@ -163 +213 @@
     }
 
-    public IEnumerable<double> GetEstimatedClassValues(IDataset dataset, IEnumerable<int> rows) {
+    public override IEnumerable<double> GetEstimatedClassValues(IDataset dataset, IEnumerable<int> rows) {
       if (classValues == null) throw new InvalidOperationException("No class values are defined.");
-      double[,] inputData = AlglibUtil.PrepareInputMatrix(dataset, allowedInputVariables, rows);
-
+      double[,] inputData;
+      if (IsCompatibilityLoaded) {
+        inputData = dataset.ToArray(allowedInputVariables, rows);
+      } else {
+        inputData = CreateScaledData(dataset, allowedInputVariables, rows, offsets, weights);
+      }
       int n = inputData.GetLength(0);
       int columns = inputData.GetLength(1);
@@ -178 +232 @@
           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]++;
@@ -201 +258 @@
     }
 
-    public INearestNeighbourRegressionSolution CreateRegressionSolution(IRegressionProblemData problemData) {
-      return new NearestNeighbourRegressionSolution(new RegressionProblemData(problemData), this);
-    }
+
     IRegressionSolution IRegressionModel.CreateRegressionSolution(IRegressionProblemData problemData) {
-      return CreateRegressionSolution(problemData);
-    }
-    public INearestNeighbourClassificationSolution CreateClassificationSolution(IClassificationProblemData problemData) {
-      return new NearestNeighbourClassificationSolution(new ClassificationProblemData(problemData), this);
-    }
-    IClassificationSolution IClassificationModel.CreateClassificationSolution(IClassificationProblemData problemData) {
-      return CreateClassificationSolution(problemData);
+      return new NearestNeighbourRegressionSolution(this, new RegressionProblemData(problemData));
+    }
+    public override IClassificationSolution CreateClassificationSolution(IClassificationProblemData problemData) {
+      return new NearestNeighbourClassificationSolution(this, new ClassificationProblemData(problemData));
     }
 
@@ -223 +275 @@
     #endregion
 
+
+    // BackwardsCompatibility3.3
+    #region Backwards compatible code, remove with 3.4
+
+    private bool isCompatibilityLoaded = false; // new kNN models have the value false, kNN models loaded from disc have the value true
+    [Storable(DefaultValue = true)]
+    public bool IsCompatibilityLoaded {
+      get { return isCompatibilityLoaded; }
+      set { isCompatibilityLoaded = value; }
+    }
+    #endregion
     #region persistence
     [Storable]

branches/2522_RefactorPluginInfrastructure/HeuristicLab.Algorithms.DataAnalysis/3.4/NearestNeighbour/NearestNeighbourRegression.cs

@@ -1 +1 @@
 #region License Information
 /* HeuristicLab
- * Copyright (C) 2002-2015 Heuristic and Evolutionary Algorithms Laboratory (HEAL)
+ * Copyright (C) 2002-2018 Heuristic and Evolutionary Algorithms Laboratory (HEAL)
  *
  * This file is part of HeuristicLab.
@@ -21 +21 @@
 
 using System;
+using System.Threading;
 using HeuristicLab.Common;
 using HeuristicLab.Core;
@@ -39 +40 @@
     private const string KParameterName = "K";
     private const string NearestNeighbourRegressionModelResultName = "Nearest neighbour regression solution";
+    private const string WeightsParameterName = "Weights";
 
     #region parameter properties
     public IFixedValueParameter<IntValue> KParameter {
       get { return (IFixedValueParameter<IntValue>)Parameters[KParameterName]; }
+    }
+
+    public IValueParameter<DoubleArray> WeightsParameter {
+      get { return (IValueParameter<DoubleArray>)Parameters[WeightsParameterName]; }
     }
     #endregion
@@ -52 +58 @@
         else KParameter.Value.Value = value;
       }
+    }
+
+    public DoubleArray Weights {
+      get { return WeightsParameter.Value; }
+      set { WeightsParameter.Value = value; }
     }
     #endregion
@@ -63 +74 @@
       : base() {
       Parameters.Add(new FixedValueParameter<IntValue>(KParameterName, "The number of nearest neighbours to consider for regression.", new IntValue(3)));
+      Parameters.Add(new OptionalValueParameter<DoubleArray>(WeightsParameterName, "Optional: use weights to specify individual scaling values for all features. If not set the weights are calculated automatically (each feature is scaled to unit variance)"));
       Problem = new RegressionProblem();
     }
+
     [StorableHook(HookType.AfterDeserialization)]
-    private void AfterDeserialization() { }
+    private void AfterDeserialization() {
+      // BackwardsCompatibility3.3
+      #region Backwards compatible code, remove with 3.4
+      if (!Parameters.ContainsKey(WeightsParameterName)) {
+        Parameters.Add(new OptionalValueParameter<DoubleArray>(WeightsParameterName, "Optional: use weights to specify individual scaling values for all features. If not set the weights are calculated automatically (each feature is scaled to unit variance)"));
+      }
+      #endregion
+    }
 
     public override IDeepCloneable Clone(Cloner cloner) {
@@ -73 +93 @@
 
     #region nearest neighbour
-    protected override void Run() {
-      var solution = CreateNearestNeighbourRegressionSolution(Problem.ProblemData, K);
+    protected override void Run(CancellationToken cancellationToken) {
+      double[] weights = null;
+      if (Weights != null) weights = Weights.CloneAsArray();
+      var solution = CreateNearestNeighbourRegressionSolution(Problem.ProblemData, K, weights);
       Results.Add(new Result(NearestNeighbourRegressionModelResultName, "The nearest neighbour regression solution.", solution));
     }
 
-    public static IRegressionSolution CreateNearestNeighbourRegressionSolution(IRegressionProblemData problemData, int k) {
+    public static IRegressionSolution CreateNearestNeighbourRegressionSolution(IRegressionProblemData problemData, int k, double[] weights = null) {
       var clonedProblemData = (IRegressionProblemData)problemData.Clone();
-      return new NearestNeighbourRegressionSolution(clonedProblemData, Train(problemData, k));
+      return new NearestNeighbourRegressionSolution(Train(problemData, k, weights), clonedProblemData);
     }
 
-    public static INearestNeighbourModel Train(IRegressionProblemData problemData, int k) {
+    public static INearestNeighbourModel Train(IRegressionProblemData problemData, int k, double[] weights = null) {
       return new NearestNeighbourModel(problemData.Dataset,
         problemData.TrainingIndices,
         k,
         problemData.TargetVariable,
-        problemData.AllowedInputVariables);
+        problemData.AllowedInputVariables,
+        weights);
     }
     #endregion

branches/2522_RefactorPluginInfrastructure/HeuristicLab.Algorithms.DataAnalysis/3.4/NearestNeighbour/NearestNeighbourRegressionSolution.cs

@@ -1 +1 @@
 #region License Information
 /* HeuristicLab
- * Copyright (C) 2002-2015 Heuristic and Evolutionary Algorithms Laboratory (HEAL)
+ * Copyright (C) 2002-2018 Heuristic and Evolutionary Algorithms Laboratory (HEAL)
  *
  * This file is part of HeuristicLab.
@@ -43 +43 @@
       : base(original, cloner) {
     }
-    public NearestNeighbourRegressionSolution(IRegressionProblemData problemData, INearestNeighbourModel nnModel)
+    public NearestNeighbourRegressionSolution(INearestNeighbourModel nnModel, IRegressionProblemData problemData)
       : base(nnModel, problemData) {
     }

@@ -24 +24 @@
 protoc.exe
 obj
+.vs