Changeset 13921 for trunk/sources/HeuristicLab.Algorithms.DataAnalysis/3.4

Timestamp:

06/19/16 19:56:11 (8 years ago)

Author:

bburlacu

Message:

#2604: Revert changes to DataAnalysisSolution and IDataAnalysisSolution and implement the desired properties in model classes that implement IDataAnalysisModel, IRegressionModel and IClassificationModel.

Location:

trunk/sources/HeuristicLab.Algorithms.DataAnalysis/3.4

Files:

• BaselineClassifiers/OneRClassificationModel.cs (modified) (1 diff)
• GaussianProcess/GaussianProcessModel.cs (modified) (2 diffs)
• GaussianProcess/StudentTProcessModel.cs (modified) (1 diff)
• GradientBoostedTrees/GradientBoostedTreesModel.cs (modified) (2 diffs)
• GradientBoostedTrees/GradientBoostedTreesModelSurrogate.cs (modified) (5 diffs)
• GradientBoostedTrees/RegressionTreeModel.cs (modified) (1 diff)
• Linear/MultinomialLogitModel.cs (modified) (3 diffs)
• Nca/NcaModel.cs (modified) (1 diff)
• NearestNeighbour/NearestNeighbourModel.cs (modified) (1 diff)
• NeuralNetwork/NeuralNetworkEnsembleModel.cs (modified) (1 diff)
• NeuralNetwork/NeuralNetworkModel.cs (modified) (1 diff)
• RandomForest/RandomForestModel.cs (modified) (1 diff)
• SupportVectorMachine/SupportVectorMachineModel.cs (modified) (1 diff)
• kMeans/KMeansClusteringModel.cs (modified) (1 diff)

trunk/sources/HeuristicLab.Algorithms.DataAnalysis/3.4/BaselineClassifiers/OneRClassificationModel.cs

@@ -32 +32 @@
   [Item("OneR Classification Model", "A model that uses intervals for one variable to determine the class.")]
   public class OneRClassificationModel : NamedItem, IClassificationModel {
+    public IEnumerable<string> VariablesUsedForPrediction {
+      get { return Enumerable.Empty<string>(); }
+    }
+
+    public string TargetVariable {
+      get { return variable; }
+    }
+
     [Storable]
     protected string variable;

trunk/sources/HeuristicLab.Algorithms.DataAnalysis/3.4/GaussianProcess/GaussianProcessModel.cs

@@ -35 +35 @@
   [Item("GaussianProcessModel", "Represents a Gaussian process posterior.")]
   public sealed class GaussianProcessModel : NamedItem, IGaussianProcessModel {
+    public IEnumerable<string> VariablesUsedForPrediction { get; }
+
     [Storable]
     private double negativeLogLikelihood;
@@ -392 +394 @@
       }
     }
+
   }
 }

trunk/sources/HeuristicLab.Algorithms.DataAnalysis/3.4/GaussianProcess/StudentTProcessModel.cs

@@ -35 +35 @@
   [Item("StudentTProcessModel", "Represents a Student-t process posterior.")]
   public sealed class StudentTProcessModel : NamedItem, IGaussianProcessModel {
+    public IEnumerable<string> VariablesUsedForPrediction {
+      get { return allowedInputVariables; }
+    }
+
     [Storable]
     private double negativeLogLikelihood;

trunk/sources/HeuristicLab.Algorithms.DataAnalysis/3.4/GradientBoostedTrees/GradientBoostedTreesModel.cs

@@ -58 +58 @@
     #endregion
 
+    public string TargetVariable {
+      get { return models.First().TargetVariable; }
+    }
+
+    public IEnumerable<string> VariablesUsedForPrediction {
+      get { return models.SelectMany(x => x.VariablesUsedForPrediction).Distinct().OrderBy(x => x); }
+    }
+
     private readonly IList<IRegressionModel> models;
     public IEnumerable<IRegressionModel> Models { get { return models; } }
@@ -108 +116 @@
       return new RegressionSolution(this, (IRegressionProblemData)problemData.Clone());
     }
+
   }
 }

trunk/sources/HeuristicLab.Algorithms.DataAnalysis/3.4/GradientBoostedTrees/GradientBoostedTreesModelSurrogate.cs

@@ -22 +22 @@
 
 using System.Collections.Generic;
+using System.Linq;
 using HeuristicLab.Common;
 using HeuristicLab.Core;
@@ -54 +55 @@
     private int maxSize;
 
+    public string TargetVariable {
+      get { return trainingProblemData.TargetVariable; }
+    }
+
+    public IEnumerable<string> VariablesUsedForPrediction {
+      get { return actualModel.Models.SelectMany(x => x.VariablesUsedForPrediction).Distinct().OrderBy(x => x); }
+    }
 
     [StorableConstructor]
@@ -73 +81 @@
 
     // create only the surrogate model without an actual model
-    public GradientBoostedTreesModelSurrogate(IRegressionProblemData trainingProblemData, uint seed, ILossFunction lossFunction, int iterations, int maxSize, double r, double m, double nu)
+    public GradientBoostedTreesModelSurrogate(IRegressionProblemData trainingProblemData, uint seed,
+      ILossFunction lossFunction, int iterations, int maxSize, double r, double m, double nu)
       : base("Gradient boosted tree model", string.Empty) {
       this.trainingProblemData = trainingProblemData;
@@ -86 +95 @@
 
     // wrap an actual model in a surrograte
-    public GradientBoostedTreesModelSurrogate(IRegressionProblemData trainingProblemData, uint seed, ILossFunction lossFunction, int iterations, int maxSize, double r, double m, double nu, IGradientBoostedTreesModel model)
+    public GradientBoostedTreesModelSurrogate(IRegressionProblemData trainingProblemData, uint seed,
+      ILossFunction lossFunction, int iterations, int maxSize, double r, double m, double nu,
+      IGradientBoostedTreesModel model)
       : this(trainingProblemData, seed, lossFunction, iterations, maxSize, r, m, nu) {
       this.actualModel = model;
@@ -104 +115 @@
       return new RegressionSolution(this, (IRegressionProblemData)problemData.Clone());
     }
-
 
     private IGradientBoostedTreesModel RecalculateModel() {

trunk/sources/HeuristicLab.Algorithms.DataAnalysis/3.4/GradientBoostedTrees/RegressionTreeModel.cs

@@ -35 +35 @@
   [Item("RegressionTreeModel", "Represents a decision tree for regression.")]
   public sealed class RegressionTreeModel : NamedItem, IRegressionModel {
+    public IEnumerable<string> VariablesUsedForPrediction {
+      get { return Enumerable.Empty<string>(); }
+    }
+
+    public string TargetVariable {
+      get { return string.Empty; }
+    }
 
     // trees are represented as a flat array    

trunk/sources/HeuristicLab.Algorithms.DataAnalysis/3.4/Linear/MultinomialLogitModel.cs

@@ -46 +46 @@
         }
       }
+    }
+
+    public IEnumerable<string> VariablesUsedForPrediction {
+      get { return allowedInputVariables; }
+    }
+
+    public string TargetVariable {
+      get { return targetVariable; }
     }
 
@@ -111 +119 @@
       return new MultinomialLogitClassificationSolution(new ClassificationProblemData(problemData), this);
     }
+
+
+
     IClassificationSolution IClassificationModel.CreateClassificationSolution(IClassificationProblemData problemData) {
       return CreateClassificationSolution(problemData);
@@ -135 +146 @@
     }
     #endregion
+
   }
 }

trunk/sources/HeuristicLab.Algorithms.DataAnalysis/3.4/Nca/NcaModel.cs

@@ -31 +31 @@
   [StorableClass]
   public class NcaModel : NamedItem, INcaModel {
+    public IEnumerable<string> VariablesUsedForPrediction {
+      get { return allowedInputVariables; }
+    }
+
+    public string TargetVariable {
+      get { return targetVariable; }
+    }
 
     [Storable]

trunk/sources/HeuristicLab.Algorithms.DataAnalysis/3.4/NearestNeighbour/NearestNeighbourModel.cs

@@ -46 +46 @@
         }
       }
+    }
+
+    public IEnumerable<string> VariablesUsedForPrediction {
+      get { return allowedInputVariables; }
+    }
+
+    public string TargetVariable {
+      get { return targetVariable; }
     }
 

trunk/sources/HeuristicLab.Algorithms.DataAnalysis/3.4/NeuralNetwork/NeuralNetworkEnsembleModel.cs

@@ -46 +46 @@
         }
       }
+    }
+
+    public string TargetVariable {
+      get { return targetVariable; }
+    }
+
+    public IEnumerable<string> VariablesUsedForPrediction {
+      get { return allowedInputVariables; }
     }
 

trunk/sources/HeuristicLab.Algorithms.DataAnalysis/3.4/NeuralNetwork/NeuralNetworkModel.cs

@@ -46 +46 @@
         }
       }
+    }
+
+    public IEnumerable<string> VariablesUsedForPrediction {
+      get { return allowedInputVariables; }
+    }
+
+    public string TargetVariable {
+      get { return targetVariable; }
     }
 

trunk/sources/HeuristicLab.Algorithms.DataAnalysis/3.4/RandomForest/RandomForestModel.cs

@@ -45 +45 @@
     }
 
+    public IEnumerable<string> VariablesUsedForPrediction {
+      get { return originalTrainingData.AllowedInputVariables; }
+    }
+
+    public string TargetVariable {
+      get {
+        var regressionProblemData = originalTrainingData as IRegressionProblemData;
+        var classificationProblemData = originalTrainingData as IClassificationProblemData;
+        if (classificationProblemData != null)
+          return classificationProblemData.TargetVariable;
+        if (regressionProblemData != null)
+          return regressionProblemData.TargetVariable;
+        throw new InvalidOperationException("Getting the target variable requires either a regression or a classification problem data.");
+      }
+    }
+
     // instead of storing the data of the model itself
     // we instead only store data necessary to recalculate the same model lazily on demand

trunk/sources/HeuristicLab.Algorithms.DataAnalysis/3.4/SupportVectorMachine/SupportVectorMachineModel.cs

@@ -38 +38 @@
   [Item("SupportVectorMachineModel", "Represents a support vector machine model.")]
   public sealed class SupportVectorMachineModel : NamedItem, ISupportVectorMachineModel {
+    public IEnumerable<string> VariablesUsedForPrediction {
+      get { return allowedInputVariables; }
+    }
+
+    public string TargetVariable {
+      get { return targetVariable; }
+    }
 
     private svm_model model;

trunk/sources/HeuristicLab.Algorithms.DataAnalysis/3.4/kMeans/KMeansClusteringModel.cs

@@ -37 +37 @@
     public static new Image StaticItemImage {
       get { return HeuristicLab.Common.Resources.VSImageLibrary.Function; }
+    }
+
+    public IEnumerable<string> VariablesUsedForPrediction {
+      get { return allowedInputVariables; }
     }