Changeset 15142 for stable/HeuristicLab.Algorithms.DataAnalysis/3.4/Linear

Timestamp:

07/06/17 11:12:18 (7 years ago)

Author:

gkronber

Message:

#2697: merged r14843 (resolving conflicts in csproj file for HL.Algorithms.DataAnalysis because MCTS has been removed)

Location:

stable/HeuristicLab.Algorithms.DataAnalysis/3.4/Linear

Files:

• AlglibUtil.cs (deleted)
• LinearDiscriminantAnalysis.cs (modified) (2 diffs)
• LinearRegression.cs (modified) (2 diffs)
• MultinomialLogitClassification.cs (modified) (1 diff)
• MultinomialLogitModel.cs (modified) (1 diff)
• Scaling.cs (modified) (1 diff)

stable/HeuristicLab.Algorithms.DataAnalysis/3.4/Linear/LinearDiscriminantAnalysis.cs

@@ -73 +73 @@
       var doubleVariableNames = allowedInputVariables.Where(dataset.VariableHasType<double>).ToArray();
       var factorVariableNames = allowedInputVariables.Where(dataset.VariableHasType<string>).ToArray();
-      double[,] inputMatrix = AlglibUtil.PrepareInputMatrix(dataset, doubleVariableNames.Concat(new string[] { targetVariable }), rows);
+      double[,] inputMatrix = dataset.ToArray(doubleVariableNames.Concat(new string[] { targetVariable }), rows);
 
-      var factorVariables = AlglibUtil.GetFactorVariableValues(dataset, factorVariableNames, rows);
-      double[,] factorMatrix = AlglibUtil.PrepareInputMatrix(dataset, factorVariables, rows);
+      var factorVariables = dataset.GetFactorVariableValues(factorVariableNames, rows);
+      var factorMatrix = dataset.ToArray(factorVariables, rows);
 
       inputMatrix = factorMatrix.HorzCat(inputMatrix);
@@ -94 +94 @@
       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);
-
-      int col = 0;
-      foreach (var kvp in factorVariables) {
-        var varName = kvp.Key;
-        foreach (var cat in kvp.Value) {
-          BinaryFactorVariableTreeNode vNode =
-            (BinaryFactorVariableTreeNode)new HeuristicLab.Problems.DataAnalysis.Symbolic.BinaryFactorVariable().CreateTreeNode();
-          vNode.VariableName = varName;
-          vNode.VariableValue = cat;
-          vNode.Weight = w[col];
-          addition.AddSubtree(vNode);
-          col++;
-        }
-      }
-      foreach (string column in doubleVariableNames) {
-        VariableTreeNode vNode = (VariableTreeNode)new HeuristicLab.Problems.DataAnalysis.Symbolic.Variable().CreateTreeNode();
-        vNode.VariableName = column;
-        vNode.Weight = w[col];
-        addition.AddSubtree(vNode);
-        col++;
-      }
+      var nFactorCoeff = factorMatrix.GetLength(1);
+      var tree = LinearModelToTreeConverter.CreateTree(factorVariables, w.Take(nFactorCoeff).ToArray(),
+        doubleVariableNames, w.Skip(nFactorCoeff).Take(doubleVariableNames.Length).ToArray());
 
       var model = CreateDiscriminantFunctionModel(tree, new SymbolicDataAnalysisExpressionTreeLinearInterpreter(), problemData, rows);

stable/HeuristicLab.Algorithms.DataAnalysis/3.4/Linear/LinearRegression.cs

@@ -76 +76 @@
       var doubleVariables = allowedInputVariables.Where(dataset.VariableHasType<double>);
       var factorVariableNames = allowedInputVariables.Where(dataset.VariableHasType<string>);
-      var factorVariables = AlglibUtil.GetFactorVariableValues(dataset, factorVariableNames, rows);
-      double[,] binaryMatrix = AlglibUtil.PrepareInputMatrix(dataset, factorVariables, rows);
-      double[,] doubleVarMatrix = AlglibUtil.PrepareInputMatrix(dataset, doubleVariables.Concat(new string[] { targetVariable }), rows);
+      var factorVariables = dataset.GetFactorVariableValues(factorVariableNames, rows);
+      double[,] binaryMatrix = dataset.ToArray(factorVariables, rows);
+      double[,] doubleVarMatrix = dataset.ToArray(doubleVariables.Concat(new string[] { targetVariable }), rows);
       var inputMatrix = binaryMatrix.HorzCat(doubleVarMatrix);
 
@@ -98 +98 @@
       alglib.lrunpack(lm, out coefficients, out nFeatures);
 
-      ISymbolicExpressionTree tree = new SymbolicExpressionTree(new ProgramRootSymbol().CreateTreeNode());
-      ISymbolicExpressionTreeNode startNode = new StartSymbol().CreateTreeNode();
-      tree.Root.AddSubtree(startNode);
-      ISymbolicExpressionTreeNode addition = new Addition().CreateTreeNode();
-      startNode.AddSubtree(addition);
-
-      int col = 0;
-      foreach (var kvp in factorVariables) {
-        var varName = kvp.Key;
-        foreach (var cat in kvp.Value) {
-          BinaryFactorVariableTreeNode vNode =
-            (BinaryFactorVariableTreeNode)new HeuristicLab.Problems.DataAnalysis.Symbolic.BinaryFactorVariable().CreateTreeNode();
-          vNode.VariableName = varName;
-          vNode.VariableValue = cat;
-          vNode.Weight = coefficients[col];
-          addition.AddSubtree(vNode);
-          col++;
-        }
-      }
-      foreach (string column in doubleVariables) {
-        VariableTreeNode vNode = (VariableTreeNode)new HeuristicLab.Problems.DataAnalysis.Symbolic.Variable().CreateTreeNode();
-        vNode.VariableName = column;
-        vNode.Weight = coefficients[col];
-        addition.AddSubtree(vNode);
-        col++;
-      }
-
-      ConstantTreeNode cNode = (ConstantTreeNode)new Constant().CreateTreeNode();
-      cNode.Value = coefficients[coefficients.Length - 1];
-      addition.AddSubtree(cNode);
-
+      int nFactorCoeff = binaryMatrix.GetLength(1);
+      int nVarCoeff = doubleVariables.Count();
+      var tree = LinearModelToTreeConverter.CreateTree(factorVariables, coefficients.Take(nFactorCoeff).ToArray(),
+        doubleVariables.ToArray(), coefficients.Skip(nFactorCoeff).Take(nVarCoeff).ToArray(), 
+        @const: coefficients[nFeatures]);
+      
       SymbolicRegressionSolution solution = new SymbolicRegressionSolution(new SymbolicRegressionModel(problemData.TargetVariable, tree, new SymbolicDataAnalysisExpressionTreeLinearInterpreter()), (IRegressionProblemData)problemData.Clone());
       solution.Model.Name = "Linear Regression Model";

stable/HeuristicLab.Algorithms.DataAnalysis/3.4/Linear/MultinomialLogitClassification.cs

@@ -72 +72 @@
       var factorVariableNames = problemData.AllowedInputVariables.Where(dataset.VariableHasType<string>);
       IEnumerable<int> rows = problemData.TrainingIndices;
-      double[,] inputMatrix = AlglibUtil.PrepareInputMatrix(dataset, doubleVariableNames.Concat(new string[] { targetVariable }), rows);
+      double[,] inputMatrix = dataset.ToArray(doubleVariableNames.Concat(new string[] { targetVariable }), rows);
 
-      var factorVariableValues = AlglibUtil.GetFactorVariableValues(dataset, factorVariableNames, rows);
-      var factorMatrix = AlglibUtil.PrepareInputMatrix(dataset, factorVariableValues, rows);
+      var factorVariableValues = dataset.GetFactorVariableValues(factorVariableNames, rows);
+      var factorMatrix = dataset.ToArray(factorVariableValues, rows);
       inputMatrix = factorMatrix.HorzCat(inputMatrix);
 

stable/HeuristicLab.Algorithms.DataAnalysis/3.4/Linear/MultinomialLogitModel.cs

@@ -97 +97 @@
     public override IEnumerable<double> GetEstimatedClassValues(IDataset dataset, IEnumerable<int> rows) {
 
-      double[,] inputData = AlglibUtil.PrepareInputMatrix(dataset, allowedInputVariables, rows);
-      double[,] factorData = AlglibUtil.PrepareInputMatrix(dataset, factorVariables, rows);
+      double[,] inputData = dataset.ToArray(allowedInputVariables, rows);
+      double[,] factorData = dataset.ToArray(factorVariables, rows);
 
       inputData = factorData.HorzCat(inputData);

stable/HeuristicLab.Algorithms.DataAnalysis/3.4/Linear/Scaling.cs

@@ -29 +29 @@
 
 namespace HeuristicLab.Algorithms.DataAnalysis {
+  [Obsolete("Use transformation classes in Problems.DataAnalysis instead")]
   [StorableClass]
   [Item(Name = "Scaling", Description = "Contains information about scaling of variables for data-analysis algorithms.")]