Changeset 14836 for branches/TSNE/HeuristicLab.Algorithms.DataAnalysis/3.4/Linear/LinearRegression.cs

Timestamp:

04/10/17 15:48:20 (7 years ago)

Author:

gkronber

Message:

#2700 merged changesets from trunk to branch

Location:

branches/TSNE/HeuristicLab.Algorithms.DataAnalysis

Files:

• . (modified) (1 prop)
• 3.4/Linear/LinearRegression.cs (modified) (5 diffs)

branches/TSNE/HeuristicLab.Algorithms.DataAnalysis/3.4/Linear/LinearRegression.cs

@@ -23 +23 @@
 using System.Collections.Generic;
 using System.Linq;
+using System.Threading;
 using HeuristicLab.Common;
 using HeuristicLab.Core;
@@ -60 +61 @@
 
     #region linear regression
-    protected override void Run() {
+    protected override void Run(CancellationToken cancellationToken) {
       double rmsError, cvRmsError;
       var solution = CreateLinearRegressionSolution(Problem.ProblemData, out rmsError, out cvRmsError);
@@ -73 +74 @@
       IEnumerable<string> allowedInputVariables = problemData.AllowedInputVariables;
       IEnumerable<int> rows = problemData.TrainingIndices;
-      double[,] inputMatrix = AlglibUtil.PrepareInputMatrix(dataset, allowedInputVariables.Concat(new string[] { targetVariable }), rows);
+      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 inputMatrix = binaryMatrix.HorzCat(doubleVarMatrix);
+
       if (inputMatrix.Cast<double>().Any(x => double.IsNaN(x) || double.IsInfinity(x)))
         throw new NotSupportedException("Linear regression does not support NaN or infinity values in the input dataset.");
@@ -98 +105 @@
 
       int col = 0;
-      foreach (string column in allowedInputVariables) {
+      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;
@@ -110 +129 @@
       addition.AddSubtree(cNode);
 
-      SymbolicRegressionSolution solution = new SymbolicRegressionSolution(new SymbolicRegressionModel(problemData.TargetVariable, tree, new SymbolicDataAnalysisExpressionTreeInterpreter()), (IRegressionProblemData)problemData.Clone());
+      SymbolicRegressionSolution solution = new SymbolicRegressionSolution(new SymbolicRegressionModel(problemData.TargetVariable, tree, new SymbolicDataAnalysisExpressionTreeLinearInterpreter()), (IRegressionProblemData)problemData.Clone());
       solution.Model.Name = "Linear Regression Model";
       solution.Name = "Linear Regression Solution";