Changeset 16692 for branches/2521_ProblemRefactoring/HeuristicLab.Algorithms.DataAnalysis/3.4/Linear/LinearDiscriminantAnalysis.cs

Timestamp:

03/18/19 17:24:30 (6 years ago)

Author:

abeham

Message:

#2521: merged trunk changes up to r15681 into branch (removal of trunk/sources)

Location:

branches/2521_ProblemRefactoring

Files:

• . (modified) (2 props)
• HeuristicLab.Algorithms.DataAnalysis (modified) (1 prop)
• HeuristicLab.Algorithms.DataAnalysis/3.4 (modified) (1 prop)
• HeuristicLab.Algorithms.DataAnalysis/3.4/Linear/LinearDiscriminantAnalysis.cs (modified) (7 diffs)

branches/2521_ProblemRefactoring

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

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

branches/2521_ProblemRefactoring/HeuristicLab.Algorithms.DataAnalysis/3.4/Linear/LinearDiscriminantAnalysis.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.
@@ -23 +23 @@
 using System.Collections.Generic;
 using System.Linq;
+using System.Threading;
 using HeuristicLab.Common;
 using HeuristicLab.Core;
@@ -36 +37 @@
   /// Linear discriminant analysis classification algorithm.
   /// </summary>
-  [Item("Linear Discriminant Analysis", "Linear discriminant analysis classification algorithm (wrapper for ALGLIB).")]
+  [Item("Linear Discriminant Analysis (LDA)", "Linear discriminant analysis classification algorithm (wrapper for ALGLIB).")]
   [Creatable(CreatableAttribute.Categories.DataAnalysisClassification, Priority = 100)]
   [StorableClass]
@@ -59 +60 @@
 
     #region Fisher LDA
-    protected override void Run() {
+    protected override void Run(CancellationToken cancellationToken) {
       var solution = CreateLinearDiscriminantAnalysisSolution(Problem.ProblemData);
       Results.Add(new Result(LinearDiscriminantAnalysisSolutionResultName, "The linear discriminant analysis.", solution));
@@ -70 +71 @@
       IEnumerable<int> rows = problemData.TrainingIndices;
       int nClasses = problemData.ClassNames.Count();
-      double[,] inputMatrix = AlglibUtil.PrepareInputMatrix(dataset, allowedInputVariables.Concat(new string[] { targetVariable }), rows);
+      var doubleVariableNames = allowedInputVariables.Where(dataset.VariableHasType<double>).ToArray();
+      var factorVariableNames = allowedInputVariables.Where(dataset.VariableHasType<string>).ToArray();
+      double[,] inputMatrix = dataset.ToArray(doubleVariableNames.Concat(new string[] { targetVariable }), rows);
+
+      var factorVariables = dataset.GetFactorVariableValues(factorVariableNames, rows);
+      var factorMatrix = dataset.ToArray(factorVariables, rows);
+
+      inputMatrix = factorMatrix.HorzCat(inputMatrix);
+
       if (inputMatrix.Cast<double>().Any(x => double.IsNaN(x) || double.IsInfinity(x)))
         throw new NotSupportedException("Linear discriminant analysis does not support NaN or infinity values in the input dataset.");
@@ -82 +91 @@
       int info;
       double[] w;
-      alglib.fisherlda(inputMatrix, inputMatrix.GetLength(0), allowedInputVariables.Count(), nClasses, out info, out w);
+      alglib.fisherlda(inputMatrix, inputMatrix.GetLength(0), inputMatrix.GetLength(1) - 1, nClasses, out info, out w);
       if (info < 1) throw new ArgumentException("Error in calculation of linear discriminant analysis solution");
 
-      ISymbolicExpressionTree tree = new SymbolicExpressionTree(new ProgramRootSymbol().CreateTreeNode());
-      ISymbolicExpressionTreeNode startNode = new StartSymbol().CreateTreeNode();
-      tree.Root.AddSubtree(startNode);
-      ISymbolicExpressionTreeNode addition = new Addition().CreateTreeNode();
-      startNode.AddSubtree(addition);
+      var nFactorCoeff = factorMatrix.GetLength(1);
+      var tree = LinearModelToTreeConverter.CreateTree(factorVariables, w.Take(nFactorCoeff).ToArray(),
+        doubleVariableNames, w.Skip(nFactorCoeff).Take(doubleVariableNames.Length).ToArray());
 
-      int col = 0;
-      foreach (string column in allowedInputVariables) {
-        VariableTreeNode vNode = (VariableTreeNode)new HeuristicLab.Problems.DataAnalysis.Symbolic.Variable().CreateTreeNode();
-        vNode.VariableName = column;
-        vNode.Weight = w[col];
-        addition.AddSubtree(vNode);
-        col++;
-      }
-
-      var model = LinearDiscriminantAnalysis.CreateDiscriminantFunctionModel(tree, new SymbolicDataAnalysisExpressionTreeInterpreter(), problemData, rows);
+      var model = CreateDiscriminantFunctionModel(tree, new SymbolicDataAnalysisExpressionTreeLinearInterpreter(), problemData, rows);
       SymbolicDiscriminantFunctionClassificationSolution solution = new SymbolicDiscriminantFunctionClassificationSolution(model, (IClassificationProblemData)problemData.Clone());
 
@@ -111 +109 @@
       IClassificationProblemData problemData,
       IEnumerable<int> rows) {
-      var model = new SymbolicDiscriminantFunctionClassificationModel(tree, interpreter, new AccuracyMaximizationThresholdCalculator());
+      var model = new SymbolicDiscriminantFunctionClassificationModel(problemData.TargetVariable, tree, interpreter, new AccuracyMaximizationThresholdCalculator());
       model.RecalculateModelParameters(problemData, rows);
       return model;

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