Changeset 8465 for trunk/sources/HeuristicLab.Algorithms.DataAnalysis/3.4/NearestNeighbour

Timestamp:

08/10/12 14:57:21 (12 years ago)

Author:

abeham

Message:

#1913: Changed k-NN to move model representation (kdTree) into the model object

Location:

trunk/sources/HeuristicLab.Algorithms.DataAnalysis/3.4/NearestNeighbour

Files:

• NearestNeighbourClassification.cs (modified) (2 diffs)
• NearestNeighbourModel.cs (modified) (4 diffs)
• NearestNeighbourRegression.cs (modified) (2 diffs)

trunk/sources/HeuristicLab.Algorithms.DataAnalysis/3.4/NearestNeighbour/NearestNeighbourClassification.cs

@@ -21 +21 @@
 
 using System;
-using System.Collections.Generic;
 using System.Linq;
 using HeuristicLab.Common;
 using HeuristicLab.Core;
 using HeuristicLab.Data;
-using HeuristicLab.Encodings.SymbolicExpressionTreeEncoding;
 using HeuristicLab.Optimization;
+using HeuristicLab.Parameters;
 using HeuristicLab.Persistence.Default.CompositeSerializers.Storable;
 using HeuristicLab.Problems.DataAnalysis;
-using HeuristicLab.Problems.DataAnalysis.Symbolic;
-using HeuristicLab.Problems.DataAnalysis.Symbolic.Regression;
-using HeuristicLab.Parameters;
 
 namespace HeuristicLab.Algorithms.DataAnalysis {
@@ -84 +80 @@
 
     public static IClassificationSolution CreateNearestNeighbourClassificationSolution(IClassificationProblemData problemData, int k) {
-      Dataset dataset = problemData.Dataset;
-      string targetVariable = problemData.TargetVariable;
-      IEnumerable<string> allowedInputVariables = problemData.AllowedInputVariables;
-      IEnumerable<int> rows = problemData.TrainingIndices;
-      double[,] inputMatrix = AlglibUtil.PrepareInputMatrix(dataset, allowedInputVariables.Concat(new string[] { targetVariable }), rows);
-      if (inputMatrix.Cast<double>().Any(x => double.IsNaN(x) || double.IsInfinity(x)))
-        throw new NotSupportedException("Nearest neighbour classification does not support NaN or infinity values in the input dataset.");
+      var problemDataClone = (IClassificationProblemData)problemData.Clone();
+      return new NearestNeighbourClassificationSolution(problemDataClone, Train(problemDataClone, k));
+    }
 
-      alglib.nearestneighbor.kdtree kdtree = new alglib.nearestneighbor.kdtree();
-
-      int nRows = inputMatrix.GetLength(0);
-      int nFeatures = inputMatrix.GetLength(1) - 1;
-      double[] classValues = dataset.GetDoubleValues(targetVariable).Distinct().OrderBy(x => x).ToArray();
-      int nClasses = classValues.Count();
-      // map original class values to values [0..nClasses-1]
-      Dictionary<double, double> classIndices = new Dictionary<double, double>();
-      for (int i = 0; i < nClasses; i++) {
-        classIndices[classValues[i]] = i;
-      }
-      for (int row = 0; row < nRows; row++) {
-        inputMatrix[row, nFeatures] = classIndices[inputMatrix[row, nFeatures]];
-      }
-      alglib.nearestneighbor.kdtreebuild(inputMatrix, nRows, inputMatrix.GetLength(1) - 1, 1, 2, kdtree);
-      var problemDataClone = (IClassificationProblemData) problemData.Clone();
-      return new NearestNeighbourClassificationSolution(problemDataClone, new NearestNeighbourModel(kdtree, k, targetVariable, allowedInputVariables, problemDataClone.ClassValues.ToArray()));
+    public static INearestNeighbourModel Train(IClassificationProblemData problemData, int k) {
+      return new NearestNeighbourModel(problemData.Dataset,
+        problemData.TrainingIndices,
+        k,
+        problemData.TargetVariable,
+        problemData.AllowedInputVariables,
+        problemData.ClassValues.ToArray());
     }
     #endregion

trunk/sources/HeuristicLab.Algorithms.DataAnalysis/3.4/NearestNeighbour/NearestNeighbourModel.cs

@@ -33 +33 @@
   /// </summary>
   [StorableClass]
-  [Item("NearestNeighbourModel", "Represents a neural network for regression and classification.")]
+  [Item("NearestNeighbourModel", "Represents a nearest neighbour model for regression and classification.")]
   public sealed class NearestNeighbourModel : NamedItem, INearestNeighbourModel {
 
@@ -56 +56 @@
     [Storable]
     private int k;
+
     [StorableConstructor]
     private NearestNeighbourModel(bool deserializing)
@@ -95 +96 @@
         this.classValues = (double[])original.classValues.Clone();
     }
-    public NearestNeighbourModel(alglib.nearestneighbor.kdtree kdTree, int k, string targetVariable, IEnumerable<string> allowedInputVariables, double[] classValues = null)
-      : base() {
-      this.name = ItemName;
-      this.description = ItemDescription;
-      this.kdTree = kdTree;
+    public NearestNeighbourModel(Dataset dataset, IEnumerable<int> rows, int k, string targetVariable, IEnumerable<string> allowedInputVariables, double[] classValues = null) {
       this.k = k;
       this.targetVariable = targetVariable;
       this.allowedInputVariables = allowedInputVariables.ToArray();
-      if (classValues != null)
+
+      var inputMatrix = AlglibUtil.PrepareInputMatrix(dataset,
+                                   allowedInputVariables.Concat(new string[] { targetVariable }),
+                                   rows);
+
+      if (inputMatrix.Cast<double>().Any(x => double.IsNaN(x) || double.IsInfinity(x)))
+        throw new NotSupportedException(
+          "Nearest neighbour classification does not support NaN or infinity values in the input dataset.");
+
+      this.kdTree = new alglib.nearestneighbor.kdtree();
+
+      var nRows = inputMatrix.GetLength(0);
+      var nFeatures = inputMatrix.GetLength(1) - 1;
+
+      if (classValues != null) {
         this.classValues = (double[])classValues.Clone();
+        int nClasses = classValues.Length;
+        // map original class values to values [0..nClasses-1]
+        var classIndices = new Dictionary<double, double>();
+        for (int i = 0; i < nClasses; i++)
+          classIndices[classValues[i]] = i;
+
+        for (int row = 0; row < nRows; row++) {
+          inputMatrix[row, nFeatures] = classIndices[inputMatrix[row, nFeatures]];
+        }
+      }
+      alglib.nearestneighbor.kdtreebuild(inputMatrix, nRows, inputMatrix.GetLength(1) - 1, 1, 2, kdTree);
     }
 
@@ -140 +162 @@
 
     public IEnumerable<double> GetEstimatedClassValues(Dataset dataset, IEnumerable<int> rows) {
+      if (classValues == null) throw new InvalidOperationException("No class values are defined.");
       double[,] inputData = AlglibUtil.PrepareInputMatrix(dataset, allowedInputVariables, rows);
 

trunk/sources/HeuristicLab.Algorithms.DataAnalysis/3.4/NearestNeighbour/NearestNeighbourRegression.cs

@@ -21 +21 @@
 
 using System;
-using System.Collections.Generic;
-using System.Linq;
 using HeuristicLab.Common;
 using HeuristicLab.Core;
 using HeuristicLab.Data;
-using HeuristicLab.Encodings.SymbolicExpressionTreeEncoding;
 using HeuristicLab.Optimization;
+using HeuristicLab.Parameters;
 using HeuristicLab.Persistence.Default.CompositeSerializers.Storable;
 using HeuristicLab.Problems.DataAnalysis;
-using HeuristicLab.Problems.DataAnalysis.Symbolic;
-using HeuristicLab.Problems.DataAnalysis.Symbolic.Regression;
-using HeuristicLab.Parameters;
 
 namespace HeuristicLab.Algorithms.DataAnalysis {
@@ -84 +79 @@
 
     public static IRegressionSolution CreateNearestNeighbourRegressionSolution(IRegressionProblemData problemData, int k) {
-      Dataset dataset = problemData.Dataset;
-      string targetVariable = problemData.TargetVariable;
-      IEnumerable<string> allowedInputVariables = problemData.AllowedInputVariables;
-      IEnumerable<int> rows = problemData.TrainingIndices;
-      double[,] inputMatrix = AlglibUtil.PrepareInputMatrix(dataset, allowedInputVariables.Concat(new string[] { targetVariable }), rows);
-      if (inputMatrix.Cast<double>().Any(x => double.IsNaN(x) || double.IsInfinity(x)))
-        throw new NotSupportedException("Nearest neighbour regression does not support NaN or infinity values in the input dataset.");
+      var clonedProblemData = (IRegressionProblemData)problemData.Clone();
+      return new NearestNeighbourRegressionSolution(clonedProblemData, Train(problemData, k));
+    }
 
-      alglib.nearestneighbor.kdtree kdtree = new alglib.nearestneighbor.kdtree();
-
-      int nRows = inputMatrix.GetLength(0);
-
-      alglib.nearestneighbor.kdtreebuild(inputMatrix, nRows, inputMatrix.GetLength(1) - 1, 1, 2, kdtree);
-
-      return new NearestNeighbourRegressionSolution((IRegressionProblemData)problemData.Clone(), new NearestNeighbourModel(kdtree, k, targetVariable, allowedInputVariables));
+    public static INearestNeighbourModel Train(IRegressionProblemData problemData, int k) {
+      return new NearestNeighbourModel(problemData.Dataset,
+        problemData.TrainingIndices,
+        k,
+        problemData.TargetVariable,
+        problemData.AllowedInputVariables);
     }
     #endregion