Changeset 17456 for branches/3040_VectorBasedGP/HeuristicLab.Problems.DataAnalysis

Timestamp:

02/28/20 10:43:50 (5 years ago)

Author:

pfleck

Message:

#3040 Merged trunk to branch

Location:

branches/3040_VectorBasedGP

Files:

• . (modified) (1 prop)
• HeuristicLab.Problems.DataAnalysis (modified) (1 prop)
• HeuristicLab.Problems.DataAnalysis/3.4 (modified) (1 prop)
• HeuristicLab.Problems.DataAnalysis/3.4/Implementation/Classification/ClassificationSolutionVariableImpactsCalculator.cs (modified) (8 diffs)
• HeuristicLab.Problems.DataAnalysis/3.4/Implementation/Classification/DiscriminantFunctionClassificationModel.cs (modified) (1 diff)

branches/3040_VectorBasedGP/HeuristicLab.Problems.DataAnalysis/3.4/Implementation/Classification/ClassificationSolutionVariableImpactsCalculator.cs

@@ -26 +26 @@
 using System.Collections.Generic;
 using System.Linq;
+using HEAL.Attic;
 using HeuristicLab.Common;
 using HeuristicLab.Core;
 using HeuristicLab.Data;
 using HeuristicLab.Parameters;
-using HEAL.Attic;
 using HeuristicLab.Random;
 
@@ -173 +173 @@
 
       IList originalValues = null;
-      IList replacementValues = GetReplacementValues(modifiableDataset, variableName, model, rows, targetValues, out originalValues, replacementMethod, factorReplacementMethod);
-
-      double newValue = CalculateQualityForReplacement(model, modifiableDataset, variableName, originalValues, rows, replacementValues, targetValues);
+      IList replacementValues = GetReplacementValues(modifiableDataset, variableName, model, problemData.AllowedInputVariables, rows, targetValues, out originalValues, replacementMethod, factorReplacementMethod);
+
+      double newValue = CalculateQualityForReplacement(model, modifiableDataset, problemData.AllowedInputVariables, variableName, originalValues, rows, replacementValues, targetValues);
       double impact = quality - newValue;
 
@@ -184 +184 @@
       string variableName,
       IClassificationModel model,
+      IEnumerable<string> allowedInputVariables,
       IEnumerable<int> rows,
       IEnumerable<double> targetValues,
@@ -196 +197 @@
       } else if (modifiableDataset.VariableHasType<string>(variableName)) {
         originalValues = modifiableDataset.GetReadOnlyStringValues(variableName).ToList();
-        replacementValues = GetReplacementValuesForString(model, modifiableDataset, variableName, rows, (List<string>)originalValues, targetValues, factorReplacementMethod);
+        replacementValues = GetReplacementValuesForString(model, modifiableDataset, allowedInputVariables, variableName, rows, (List<string>)originalValues, targetValues, factorReplacementMethod);
       } else {
         throw new NotSupportedException("Variable not supported");
@@ -254 +255 @@
     private static IList GetReplacementValuesForString(IClassificationModel model,
       ModifiableDataset modifiableDataset,
+      IEnumerable<string> allowedInputVariables,
       string variableName,
       IEnumerable<int> rows,
@@ -270 +272 @@
             List<string> curReplacementValues = Enumerable.Repeat(repl, modifiableDataset.Rows).ToList();
             //fholzing: this result could be used later on (theoretically), but is neglected for better readability/method consistency 
-            var newValue = CalculateQualityForReplacement(model, modifiableDataset, variableName, originalValues, rows, curReplacementValues, targetValues);
+            var newValue = CalculateQualityForReplacement(model, modifiableDataset, allowedInputVariables, variableName, originalValues, rows, curReplacementValues, targetValues);
             var curQuality = newValue;
 
@@ -308 +310 @@
       IClassificationModel model,
       ModifiableDataset modifiableDataset,
+      IEnumerable<string> allowedInputVariables,
       string variableName,
       IList originalValues,
@@ -317 +320 @@
       var discModel = model as IDiscriminantFunctionClassificationModel;
       if (discModel != null) {
-        var problemData = new ClassificationProblemData(modifiableDataset, modifiableDataset.VariableNames, model.TargetVariable);
+        var problemData = new ClassificationProblemData(modifiableDataset, allowedInputVariables, model.TargetVariable);
         discModel.RecalculateModelParameters(problemData, rows);
       }

branches/3040_VectorBasedGP/HeuristicLab.Problems.DataAnalysis/3.4/Implementation/Classification/DiscriminantFunctionClassificationModel.cs

@@ -74 +74 @@
       classValues = (double[])original.classValues.Clone();
       thresholds = (double[])original.thresholds.Clone();
+      thresholdCalculator = (IDiscriminantFunctionThresholdCalculator)original.thresholdCalculator.Clone();
     }