Changeset 17920

Timestamp:

03/29/21 19:29:08 (4 years ago)

Author:

gkronber

Message:

#3115 cache calculations to improve speed when plotting multiple solutions in a partial dependence plot with factor variables.

File:

• trunk/HeuristicLab.Problems.DataAnalysis.Views/3.4/Controls/PartialDependencePlot.cs (modified) (3 diffs)

trunk/HeuristicLab.Problems.DataAnalysis.Views/3.4/Controls/PartialDependencePlot.cs

@@ -530 +530 @@
 
     public async Task AddSolutionAsync(IRegressionSolution solution) {
+      if (solutions.Contains(solution))
+        return;
       if (!SolutionsCompatible(solutions.Concat(new[] { solution })))
         throw new ArgumentException("The solution is not compatible with the problem data.");
-      if (solutions.Contains(solution))
-        return;
 
       solutions.Add(solution);
@@ -568 +568 @@
       var refSolution = solutions.First();
       var refSolVars = refSolution.ProblemData.Dataset.VariableNames;
+      var refFactorVars = refSolVars.Where(refSolution.ProblemData.Dataset.VariableHasType<string>);
+      var distinctVals = refFactorVars.ToDictionary(fv => fv, fv => refSolution.ProblemData.Dataset.GetStringValues(fv).Distinct().ToArray());
       foreach (var solution in solutions.Skip(1)) {
         var variables1 = solution.ProblemData.Dataset.VariableNames;
@@ -574 +576 @@
 
         foreach (var factorVar in variables1.Where(solution.ProblemData.Dataset.VariableHasType<string>)) {
-          var distinctVals = refSolution.ProblemData.Dataset.GetStringValues(factorVar).Distinct();
-          if (solution.ProblemData.Dataset.GetStringValues(factorVar).Any(val => !distinctVals.Contains(val))) return false;
+          var refValues = distinctVals[factorVar];
+          if (solution.ProblemData.Dataset.GetStringValues(factorVar).Distinct().Any(val => !refValues.Contains(val))) return false;
         }
       }