Changeset 15866 for branches/2719_HeuristicLab.DatastreamAnalysis/HeuristicLab.Problems.DataAnalysis/3.4/Implementation/Regression

Timestamp:

03/27/18 17:23:42 (7 years ago)

Author:

mkommend

Message:

#2719: Updated HL.Problems.DataAnalysis from trunk.

Location:

branches/2719_HeuristicLab.DatastreamAnalysis/HeuristicLab.Problems.DataAnalysis

Files:

• . (modified) (1 prop)
• 3.4/Implementation/Regression/ConfidenceBoundRegressionSolution.cs (modified) (1 diff)
• 3.4/Implementation/Regression/ConstantRegressionModel.cs (modified) (1 diff)
• 3.4/Implementation/Regression/ConstantRegressionSolution.cs (modified) (1 diff)
• 3.4/Implementation/Regression/RegressionEnsembleModel.cs (modified) (1 diff)
• 3.4/Implementation/Regression/RegressionEnsembleProblemData.cs (modified) (1 diff)
• 3.4/Implementation/Regression/RegressionEnsembleSolution.cs (modified) (1 diff)
• 3.4/Implementation/Regression/RegressionModel.cs (modified) (1 diff)
• 3.4/Implementation/Regression/RegressionProblem.cs (modified) (1 diff)
• 3.4/Implementation/Regression/RegressionProblemData.cs (modified) (4 diffs)
• 3.4/Implementation/Regression/RegressionSolution.cs (modified) (1 diff)
• 3.4/Implementation/Regression/RegressionSolutionBase.cs (modified) (1 diff)
• 3.4/Implementation/Regression/RegressionSolutionVariableImpactsCalculator.cs (modified) (4 diffs)

branches/2719_HeuristicLab.DatastreamAnalysis/HeuristicLab.Problems.DataAnalysis/3.4/Implementation/Regression/ConfidenceBoundRegressionSolution.cs

@@ -1 +1 @@
 #region License Information
 /* HeuristicLab
- * Copyright (C) 2002-2016 Heuristic and Evolutionary Algorithms Laboratory (HEAL)
+ * Copyright (C) 2002-2018 Heuristic and Evolutionary Algorithms Laboratory (HEAL)
  *
  * This file is part of HeuristicLab.

branches/2719_HeuristicLab.DatastreamAnalysis/HeuristicLab.Problems.DataAnalysis/3.4/Implementation/Regression/ConstantRegressionModel.cs

@@ -1 +1 @@
 #region License Information
 /* HeuristicLab
- * Copyright (C) 2002-2016 Heuristic and Evolutionary Algorithms Laboratory (HEAL)
+ * Copyright (C) 2002-2018 Heuristic and Evolutionary Algorithms Laboratory (HEAL)
  *
  * This file is part of HeuristicLab.

branches/2719_HeuristicLab.DatastreamAnalysis/HeuristicLab.Problems.DataAnalysis/3.4/Implementation/Regression/ConstantRegressionSolution.cs

@@ -1 +1 @@
 #region License Information
 /* HeuristicLab
- * Copyright (C) 2002-2016 Heuristic and Evolutionary Algorithms Laboratory (HEAL)
+ * Copyright (C) 2002-2018 Heuristic and Evolutionary Algorithms Laboratory (HEAL)
  *
  * This file is part of HeuristicLab.

branches/2719_HeuristicLab.DatastreamAnalysis/HeuristicLab.Problems.DataAnalysis/3.4/Implementation/Regression/RegressionEnsembleModel.cs

@@ -1 +1 @@
 #region License Information
 /* HeuristicLab
- * Copyright (C) 2002-2016 Heuristic and Evolutionary Algorithms Laboratory (HEAL)
+ * Copyright (C) 2002-2018 Heuristic and Evolutionary Algorithms Laboratory (HEAL)
  *
  * This file is part of HeuristicLab.

branches/2719_HeuristicLab.DatastreamAnalysis/HeuristicLab.Problems.DataAnalysis/3.4/Implementation/Regression/RegressionEnsembleProblemData.cs

@@ -1 +1 @@
 #region License Information
 /* HeuristicLab
- * Copyright (C) 2002-2016 Heuristic and Evolutionary Algorithms Laboratory (HEAL)
+ * Copyright (C) 2002-2018 Heuristic and Evolutionary Algorithms Laboratory (HEAL)
  *
  * This file is part of HeuristicLab.

branches/2719_HeuristicLab.DatastreamAnalysis/HeuristicLab.Problems.DataAnalysis/3.4/Implementation/Regression/RegressionEnsembleSolution.cs

@@ -1 +1 @@
 #region License Information
 /* HeuristicLab
- * Copyright (C) 2002-2016 Heuristic and Evolutionary Algorithms Laboratory (HEAL)
+ * Copyright (C) 2002-2018 Heuristic and Evolutionary Algorithms Laboratory (HEAL)
  *
  * This file is part of HeuristicLab.

branches/2719_HeuristicLab.DatastreamAnalysis/HeuristicLab.Problems.DataAnalysis/3.4/Implementation/Regression/RegressionModel.cs

@@ -1 +1 @@
 #region License Information
 /* HeuristicLab
- * Copyright (C) 2002-2016 Heuristic and Evolutionary Algorithms Laboratory (HEAL)
+ * Copyright (C) 2002-2018 Heuristic and Evolutionary Algorithms Laboratory (HEAL)
  *
  * This file is part of HeuristicLab.

branches/2719_HeuristicLab.DatastreamAnalysis/HeuristicLab.Problems.DataAnalysis/3.4/Implementation/Regression/RegressionProblem.cs

@@ -1 +1 @@
 #region License Information
 /* HeuristicLab
- * Copyright (C) 2002-2016 Heuristic and Evolutionary Algorithms Laboratory (HEAL)
+ * Copyright (C) 2002-2018 Heuristic and Evolutionary Algorithms Laboratory (HEAL)
  *
  * This file is part of HeuristicLab.

branches/2719_HeuristicLab.DatastreamAnalysis/HeuristicLab.Problems.DataAnalysis/3.4/Implementation/Regression/RegressionProblemData.cs

@@ -1 +1 @@
 #region License Information
 /* HeuristicLab
- * Copyright (C) 2002-2016 Heuristic and Evolutionary Algorithms Laboratory (HEAL)
+ * Copyright (C) 2002-2018 Heuristic and Evolutionary Algorithms Laboratory (HEAL)
  *
  * This file is part of HeuristicLab.
@@ -38 +38 @@
     #region default data
     private static double[,] kozaF1 = new double[,] {
-          {2.017885919, -1.449165046},
-          {1.30060506,  -1.344523885},
-          {1.147134798, -1.317989331},
-          {0.877182504, -1.266142284},
-          {0.852562452, -1.261020794},
-          {0.431095788, -1.158793317},
-          {0.112586002, -1.050908405},
-          {0.04594507,  -1.021989402},
-          {0.042572879, -1.020438113},
-          {-0.074027291,  -0.959859562},
-          {-0.109178553,  -0.938094706},
-          {-0.259721109,  -0.803635355},
-          {-0.272991057,  -0.387519561},
-          {-0.161978191,  -0.193611001},
-          {-0.102489983,  -0.114215349},
-          {-0.01469968, -0.014918985},
-          {-0.008863365,  -0.008942626},
-          {0.026751057, 0.026054094},
-          {0.166922436, 0.14309643},
-          {0.176953808, 0.1504144},
-          {0.190233418, 0.159916534},
-          {0.199800708, 0.166635331},
-          {0.261502822, 0.207600348},
-          {0.30182879,  0.232370249},
-          {0.83763905,  0.468046718}
+          {2.017885919, -1.449165046},
+          {1.30060506,  -1.344523885},
+          {1.147134798, -1.317989331},
+          {0.877182504, -1.266142284},
+          {0.852562452, -1.261020794},
+          {0.431095788, -1.158793317},
+          {0.112586002, -1.050908405},
+          {0.04594507,  -1.021989402},
+          {0.042572879, -1.020438113},
+          {-0.074027291,  -0.959859562},
+          {-0.109178553,  -0.938094706},
+          {-0.259721109,  -0.803635355},
+          {-0.272991057,  -0.387519561},
+          {-0.161978191,  -0.193611001},
+          {-0.102489983,  -0.114215349},
+          {-0.01469968, -0.014918985},
+          {-0.008863365,  -0.008942626},
+          {0.026751057, 0.026054094},
+          {0.166922436, 0.14309643},
+          {0.176953808, 0.1504144},
+          {0.190233418, 0.159916534},
+          {0.199800708, 0.166635331},
+          {0.261502822, 0.207600348},
+          {0.30182879,  0.232370249},
+          {0.83763905,  0.468046718}
     };
     private static readonly Dataset defaultDataset;
@@ -169 +169 @@
 
       var returnValue = base.IsProblemDataCompatible(problemData, out errorMessage);
-      //check targetVariable
-      if (problemData.InputVariables.All(var => var.Value != TargetVariable)) {
-        errorMessage = string.Format("The target variable {0} is not present in the new problem data.", TargetVariable)
-                       + Environment.NewLine + errorMessage;
-        return false;
-      }
       return returnValue;
     }
@@ -185 +179 @@
 
       base.AdjustProblemDataProperties(problemData);
-      TargetVariable = regressionProblemData.TargetVariable;
     }
   }

branches/2719_HeuristicLab.DatastreamAnalysis/HeuristicLab.Problems.DataAnalysis/3.4/Implementation/Regression/RegressionSolution.cs

@@ -1 +1 @@
 #region License Information
 /* HeuristicLab
- * Copyright (C) 2002-2016 Heuristic and Evolutionary Algorithms Laboratory (HEAL)
+ * Copyright (C) 2002-2018 Heuristic and Evolutionary Algorithms Laboratory (HEAL)
  *
  * This file is part of HeuristicLab.

branches/2719_HeuristicLab.DatastreamAnalysis/HeuristicLab.Problems.DataAnalysis/3.4/Implementation/Regression/RegressionSolutionBase.cs

@@ -1 +1 @@
 #region License Information
 /* HeuristicLab
- * Copyright (C) 2002-2016 Heuristic and Evolutionary Algorithms Laboratory (HEAL)
+ * Copyright (C) 2002-2018 Heuristic and Evolutionary Algorithms Laboratory (HEAL)
  *
  * This file is part of HeuristicLab.

branches/2719_HeuristicLab.DatastreamAnalysis/HeuristicLab.Problems.DataAnalysis/3.4/Implementation/Regression/RegressionSolutionVariableImpactsCalculator.cs

@@ -2 +2 @@
 
 /* HeuristicLab
- * Copyright (C) 2002-2016 Heuristic and Evolutionary Algorithms Laboratory (HEAL)
+ * Copyright (C) 2002-2018 Heuristic and Evolutionary Algorithms Laboratory (HEAL)
  *
  * This file is part of HeuristicLab.
@@ -96 +96 @@
       DataPartitionEnum data = DataPartitionEnum.Training,
       ReplacementMethodEnum replacementMethod = ReplacementMethodEnum.Median,
-      FactorReplacementMethodEnum factorReplacementMethod = FactorReplacementMethodEnum.Best) {
+      FactorReplacementMethodEnum factorReplacementMethod = FactorReplacementMethodEnum.Best,
+      Func<double, string, bool> progressCallback = null) {
 
       var problemData = solution.ProblemData;
@@ -134 +135 @@
       var allowedInputVariables = dataset.VariableNames.Where(v => inputvariables.Contains(v)).ToList();
 
+      int curIdx = 0;
+      int count = allowedInputVariables.Where(problemData.Dataset.VariableHasType<double>).Count();
       // calculate impacts for double variables
       foreach (var inputVariable in allowedInputVariables.Where(problemData.Dataset.VariableHasType<double>)) {
+        //Report the current progress in percent. If the callback returns true, it means the execution shall be stopped
+        if (progressCallback != null) {
+          curIdx++;
+          if (progressCallback((double)curIdx / count, string.Format("Calculating impact for variable {0} ({1} of {2})", inputVariable, curIdx, count))) { return null; }
+        }
         var newEstimates = EvaluateModelWithReplacedVariable(solution.Model, inputVariable, modifiableDataset, rows, replacementMethod);
         var newR2 = OnlinePearsonsRCalculator.Calculate(targetValues, newEstimates, out error);
@@ -180 +188 @@
     }
 
+
     private static IEnumerable<double> EvaluateModelWithReplacedVariable(IRegressionModel model, string variable, ModifiableDataset dataset, IEnumerable<int> rows, ReplacementMethodEnum replacement = ReplacementMethodEnum.Median) {
       var originalValues = dataset.GetReadOnlyDoubleValues(variable).ToList();