Changeset 16243

Timestamp:

10/19/18 13:27:06 (6 years ago)

Author:

mkommend

Message:

#2955: Added IsProblemDataCompatible and IsDatasetCompatible to all DataAnalysisModels.

Location:

trunk

Files:

• HeuristicLab.Algorithms.DataAnalysis/3.4/NearestNeighbour/NearestNeighbourModel.cs (modified) (1 diff)
• HeuristicLab.Algorithms.DataAnalysis/3.4/NeuralNetwork/NeuralNetworkEnsembleModel.cs (modified) (1 diff)
• HeuristicLab.Algorithms.DataAnalysis/3.4/NeuralNetwork/NeuralNetworkModel.cs (modified) (1 diff)
• HeuristicLab.Algorithms.DataAnalysis/3.4/RandomForest/RandomForestModel.cs (modified) (1 diff)
• HeuristicLab.Algorithms.DataAnalysis/3.4/SupportVectorMachine/SupportVectorMachineModel.cs (modified) (2 diffs)
• HeuristicLab.Algorithms.DataAnalysis/3.4/kMeans/KMeansClusteringModel.cs (modified) (3 diffs)
• HeuristicLab.Problems.DataAnalysis.Symbolic.Classification/3.4/SymbolicClassificationModel.cs (modified) (1 diff)
• HeuristicLab.Problems.DataAnalysis.Symbolic.Regression/3.4/SymbolicRegressionModel.cs (modified) (1 diff)
• HeuristicLab.Problems.DataAnalysis.Symbolic/3.4/SymbolicDataAnalysisModel.cs (modified) (2 diffs)
• HeuristicLab.Problems.DataAnalysis.Trading/3.4/Symbolic/Model.cs (modified) (2 diffs)
• HeuristicLab.Problems.DataAnalysis/3.4/Implementation/Classification/ClassificationModel.cs (modified) (1 diff)
• HeuristicLab.Problems.DataAnalysis/3.4/Implementation/ConstantModel.cs (modified) (1 diff)
• HeuristicLab.Problems.DataAnalysis/3.4/Implementation/DataAnalysisModel.cs (modified) (2 diffs)
• HeuristicLab.Problems.DataAnalysis/3.4/Implementation/Regression/RegressionModel.cs (modified) (1 diff)
• HeuristicLab.Problems.DataAnalysis/3.4/Interfaces/Classification/IClassificationModel.cs (modified) (1 diff)
• HeuristicLab.Problems.DataAnalysis/3.4/Interfaces/IDataAnalysisModel.cs (modified) (1 diff)
• HeuristicLab.Problems.DataAnalysis/3.4/Interfaces/Regression/IRegressionModel.cs (modified) (1 diff)

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

@@ -262 +262 @@
 
 
+    public bool IsProblemDataCompatible(IRegressionProblemData problemData, out string errorMessage) {
+      return RegressionModel.IsProblemDataCompatible(this, problemData, out errorMessage);
+    }
+
+    public override bool IsProblemDataCompatible(IDataAnalysisProblemData problemData, out string errorMessage) {
+      if (problemData == null) throw new ArgumentNullException("problemData", "The provided problemData is null.");
+
+      var regressionProblemData = problemData as IRegressionProblemData;
+      if (regressionProblemData != null)
+        return IsProblemDataCompatible(regressionProblemData, out errorMessage);
+
+      var classificationProblemData = problemData as IClassificationProblemData;
+      if (classificationProblemData != null)
+        return IsProblemDataCompatible(classificationProblemData, out errorMessage);
+
+      throw new ArgumentException("The problem data is not a regression nor a classification problem data. Instead a " + problemData.GetType().GetPrettyName() + " was provided.", "problemData");
+    }
+
     IRegressionSolution IRegressionModel.CreateRegressionSolution(IRegressionProblemData problemData) {
       return new NearestNeighbourRegressionSolution(this, new RegressionProblemData(problemData));

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

@@ -130 +130 @@
     }
 
+
+    public bool IsProblemDataCompatible(IRegressionProblemData problemData, out string errorMessage) {
+      return RegressionModel.IsProblemDataCompatible(this, problemData, out errorMessage);
+    }
+
+    public override bool IsProblemDataCompatible(IDataAnalysisProblemData problemData, out string errorMessage) {
+      if (problemData == null) throw new ArgumentNullException("problemData", "The provided problemData is null.");
+
+      var regressionProblemData = problemData as IRegressionProblemData;
+      if (regressionProblemData != null)
+        return IsProblemDataCompatible(regressionProblemData, out errorMessage);
+
+      var classificationProblemData = problemData as IClassificationProblemData;
+      if (classificationProblemData != null)
+        return IsProblemDataCompatible(classificationProblemData, out errorMessage);
+
+      throw new ArgumentException("The problem data is not a regression nor a classification problem data. Instead a " + problemData.GetType().GetPrettyName() + " was provided.", "problemData");
+    }
+
     public IRegressionSolution CreateRegressionSolution(IRegressionProblemData problemData) {
       return new NeuralNetworkEnsembleRegressionSolution(this, new RegressionEnsembleProblemData(problemData));

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

@@ -134 +134 @@
     }
 
+    public bool IsProblemDataCompatible(IRegressionProblemData problemData, out string errorMessage) {
+      return RegressionModel.IsProblemDataCompatible(this, problemData, out errorMessage);
+    }
+
+    public override bool IsProblemDataCompatible(IDataAnalysisProblemData problemData, out string errorMessage) {
+      if (problemData == null) throw new ArgumentNullException("problemData", "The provided problemData is null.");
+
+      var regressionProblemData = problemData as IRegressionProblemData;
+      if (regressionProblemData != null)
+        return IsProblemDataCompatible(regressionProblemData, out errorMessage);
+
+      var classificationProblemData = problemData as IClassificationProblemData;
+      if (classificationProblemData != null)
+        return IsProblemDataCompatible(classificationProblemData, out errorMessage);
+
+      throw new ArgumentException("The problem data is not a regression nor a classification problem data. Instead a " + problemData.GetType().GetPrettyName() + " was provided.", "problemData");
+    }
+
     public IRegressionSolution CreateRegressionSolution(IRegressionProblemData problemData) {
       return new NeuralNetworkRegressionSolution(this, new RegressionProblemData(problemData));

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

@@ -286 +286 @@
     }
 
+    public bool IsProblemDataCompatible(IRegressionProblemData problemData, out string errorMessage) {
+      return RegressionModel.IsProblemDataCompatible(this, problemData, out errorMessage);
+    }
+
+    public override bool IsProblemDataCompatible(IDataAnalysisProblemData problemData, out string errorMessage) {
+      if (problemData == null) throw new ArgumentNullException("problemData", "The provided problemData is null.");
+
+      var regressionProblemData = problemData as IRegressionProblemData;
+      if (regressionProblemData != null)
+        return IsProblemDataCompatible(regressionProblemData, out errorMessage);
+
+      var classificationProblemData = problemData as IClassificationProblemData;
+      if (classificationProblemData != null)
+        return IsProblemDataCompatible(classificationProblemData, out errorMessage);
+
+      throw new ArgumentException("The problem data is not a regression nor a classification problem data. Instead a " + problemData.GetType().GetPrettyName() + " was provided.", "problemData");
+    }
+
     public static RandomForestModel CreateRegressionModel(IRegressionProblemData problemData, int nTrees, double r, double m, int seed,
       out double rmsError, out double outOfBagRmsError, out double avgRelError, out double outOfBagAvgRelError) {

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

@@ -126 +126 @@
       return new SupportVectorRegressionSolution(this, new RegressionProblemData(problemData));
     }
-    #endregion
+
+    public bool IsProblemDataCompatible(IRegressionProblemData problemData, out string errorMessage) {
+      return RegressionModel.IsProblemDataCompatible(this, problemData, out errorMessage);
+    }
+    #endregion
+
+    public override bool IsProblemDataCompatible(IDataAnalysisProblemData problemData, out string errorMessage) {
+      if (problemData == null) throw new ArgumentNullException("problemData", "The provided problemData is null.");
+
+      var regressionProblemData = problemData as IRegressionProblemData;
+      if (regressionProblemData != null)
+        return IsProblemDataCompatible(regressionProblemData, out errorMessage);
+
+      var classificationProblemData = problemData as IClassificationProblemData;
+      if (classificationProblemData != null)
+        return IsProblemDataCompatible(classificationProblemData, out errorMessage);
+
+      throw new ArgumentException("The problem data is not a regression nor a classification problem data. Instead a " + problemData.GetType().GetPrettyName() + " was provided.", "problemData");
+    }
 
     #region IClassificationModel Members
@@ -153 +171 @@
     }
     #endregion
+
     private IEnumerable<double> GetEstimatedValuesHelper(IDataset dataset, IEnumerable<int> rows) {
       // calculate predictions for the currently requested rows

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

@@ -20 +20 @@
 #endregion
 
+using System;
 using System.Collections.Generic;
 using System.Drawing;
@@ -34 +35 @@
   [StorableClass]
   [Item("KMeansClusteringModel", "Represents a k-Means clustering model.")]
-  public sealed class KMeansClusteringModel : NamedItem, IClusteringModel {
+  public sealed class KMeansClusteringModel : DataAnalysisModel, IClusteringModel {
     public static new Image StaticItemImage {
       get { return HeuristicLab.Common.Resources.VSImageLibrary.Function; }
     }
 
-    public IEnumerable<string> VariablesUsedForPrediction {
+    public override IEnumerable<string> VariablesUsedForPrediction {
       get { return allowedInputVariables; }
     }
@@ -84 +85 @@
     }
 
+    public override bool IsProblemDataCompatible(IDataAnalysisProblemData problemData, out string errorMessage) {
+      if (problemData == null) throw new ArgumentNullException("problemData", "The provided problemData is null.");
+      return IsDatasetCompatible(problemData.Dataset, out errorMessage);
+    }
+
 
     public IEnumerable<int> GetClusterValues(IDataset dataset, IEnumerable<int> rows) {

trunk/HeuristicLab.Problems.DataAnalysis.Symbolic.Classification/3.4/SymbolicClassificationModel.cs

@@ -74 +74 @@
     }
 
+    public virtual bool IsProblemDataCompatible(IClassificationProblemData problemData, out string errorMessage) {
+      return ClassificationModel.IsProblemDataCompatible(this, problemData, out errorMessage);
+    }
+
+    public override bool IsProblemDataCompatible(IDataAnalysisProblemData problemData, out string errorMessage) {
+      if (problemData == null) throw new ArgumentNullException("problemData", "The provided problemData is null.");
+      var classificationProblemData = problemData as IClassificationProblemData;
+      if (classificationProblemData == null)
+        throw new ArgumentException("The problem data is not a regression problem data. Instead a " + problemData.GetType().GetPrettyName() + " was provided.", "problemData");
+      return IsProblemDataCompatible(classificationProblemData, out errorMessage);
+    }
+
     #region events
     public event EventHandler TargetVariableChanged;

trunk/HeuristicLab.Problems.DataAnalysis.Symbolic.Regression/3.4/SymbolicRegressionModel.cs

@@ -83 +83 @@
     }
 
+    public virtual bool IsProblemDataCompatible(IRegressionProblemData problemData, out string errorMessage) {
+      return RegressionModel.IsProblemDataCompatible(this, problemData, out errorMessage);
+    }
+
+    public override bool IsProblemDataCompatible(IDataAnalysisProblemData problemData, out string errorMessage) {
+      if (problemData == null) throw new ArgumentNullException("problemData", "The provided problemData is null.");
+      var regressionProblemData = problemData as IRegressionProblemData;
+      if (regressionProblemData == null)
+        throw new ArgumentException("The problem data is not a regression problem data. Instead a " + problemData.GetType().GetPrettyName() + " was provided.", "problemData");
+      return IsProblemDataCompatible(regressionProblemData, out errorMessage);
+    }
+
     #region events
     public event EventHandler TargetVariableChanged;

trunk/HeuristicLab.Problems.DataAnalysis.Symbolic/3.4/SymbolicDataAnalysisModel.cs

@@ -34 +34 @@
   /// </summary>
   [StorableClass]
-  public abstract class SymbolicDataAnalysisModel : NamedItem, ISymbolicDataAnalysisModel {
+  public abstract class SymbolicDataAnalysisModel : DataAnalysisModel, ISymbolicDataAnalysisModel {
     public static new Image StaticItemImage {
       get { return HeuristicLab.Common.Resources.VSImageLibrary.Function; }
@@ -59 +59 @@
     }
 
-    public IEnumerable<string> VariablesUsedForPrediction {
+    public override IEnumerable<string> VariablesUsedForPrediction {
       get {
         var variables =

trunk/HeuristicLab.Problems.DataAnalysis.Trading/3.4/Symbolic/Model.cs

@@ -20 +20 @@
 #endregion
 
+using System;
 using System.Collections.Generic;
 using System.Linq;
@@ -53 +54 @@
     }
 
+    public override bool IsProblemDataCompatible(IDataAnalysisProblemData problemData, out string errorMessage) {
+      if (problemData == null) throw new ArgumentNullException("problemData", "The provided problemData is null.");
+      return IsDatasetCompatible(problemData.Dataset, out errorMessage);
+    }
+
+
     // Transforms an enumerable of real values to an enumerable of trading signals (buy(1) / hold(0) / sell(-1))
     public static IEnumerable<double> GetSignals(IEnumerable<double> xs) {

trunk/HeuristicLab.Problems.DataAnalysis/3.4/Implementation/Classification/ClassificationModel.cs

@@ -66 +66 @@
     public abstract IClassificationSolution CreateClassificationSolution(IClassificationProblemData problemData);
 
+    public virtual bool IsProblemDataCompatible(IClassificationProblemData problemData, out string errorMessage) {
+      return IsProblemDataCompatible(this, problemData, out errorMessage);
+    }
+
+    public override bool IsProblemDataCompatible(IDataAnalysisProblemData problemData, out string errorMessage) {
+      if (problemData == null) throw new ArgumentNullException("problemData", "The provided problemData is null.");
+      var classificationProblemData = problemData as IClassificationProblemData;
+      if (classificationProblemData == null)
+        throw new ArgumentException("The problem data is not a regression problem data. Instead a " + problemData.GetType().GetPrettyName() + " was provided.", "problemData");
+      return IsProblemDataCompatible(classificationProblemData, out errorMessage);
+    }
+
+    public static bool IsProblemDataCompatible(IClassificationModel model, IClassificationProblemData problemData, out string errorMessage) {
+      if (model == null) throw new ArgumentNullException("model", "The provided model is null.");
+      if (problemData == null) throw new ArgumentNullException("problemData", "The provided problemData is null.");
+      errorMessage = string.Empty;
+
+      if (model.TargetVariable != problemData.TargetVariable)
+        errorMessage = string.Format("The target variable of the model {0} does not match the target variable of the problemData {1}.", model.TargetVariable, problemData.TargetVariable);
+
+      var evaluationErrorMessage = string.Empty;
+      var datasetCompatible = model.IsDatasetCompatible(problemData.Dataset, out evaluationErrorMessage);
+      if (!datasetCompatible)
+        errorMessage += evaluationErrorMessage;
+
+      return string.IsNullOrEmpty(errorMessage);
+    }
+
     #region events
     public event EventHandler TargetVariableChanged;

trunk/HeuristicLab.Problems.DataAnalysis/3.4/Implementation/ConstantModel.cs

@@ -83 +83 @@
     }
 
+    public virtual bool IsProblemDataCompatible(IClassificationProblemData problemData, out string errorMessage) {
+      return ClassificationModel.IsProblemDataCompatible(this, problemData, out errorMessage);
+    }
+
+    public override bool IsProblemDataCompatible(IDataAnalysisProblemData problemData, out string errorMessage) {
+      if (problemData == null) throw new ArgumentNullException("problemData", "The provided problemData is null.");
+
+      var regressionProblemData = problemData as IRegressionProblemData;
+      if (regressionProblemData != null)
+        return IsProblemDataCompatible(regressionProblemData, out errorMessage);
+
+      var classificationProblemData = problemData as IClassificationProblemData;
+      if (classificationProblemData != null)
+        return IsProblemDataCompatible(classificationProblemData, out errorMessage);
+
+      throw new ArgumentException("The problem data is not a regression nor a classification problem data. Instead a " + problemData.GetType().GetPrettyName() + " was provided.", "problemData");
+    }
+
     #region IStringConvertibleValue
     public bool ReadOnly { get; private set; }

trunk/HeuristicLab.Problems.DataAnalysis/3.4/Implementation/DataAnalysisModel.cs

@@ -20 +20 @@
 #endregion
 
+using System;
 using System.Collections.Generic;
 using HeuristicLab.Common;
@@ -38 +39 @@
 
     public abstract IEnumerable<string> VariablesUsedForPrediction { get; }
+
+    public virtual bool IsDatasetCompatible(IDataset dataset, out string errorMessage) {
+      if (dataset == null) throw new ArgumentNullException("dataset", "The provided dataset is null.");
+      return IsDatasetCompatible(this, dataset, out errorMessage);
+    }
+
+    public abstract bool IsProblemDataCompatible(IDataAnalysisProblemData problemData, out string errorMessage);
+
+    public static bool IsDatasetCompatible(IDataAnalysisModel model, IDataset dataset, out string errorMessage) {
+      if(model == null) throw new ArgumentNullException("model", "The provided model is null.");
+      if (dataset == null) throw new ArgumentNullException("dataset", "The provided dataset is null.");
+      errorMessage = string.Empty;
+
+      foreach (var variable in model.VariablesUsedForPrediction) {
+        if (!dataset.ContainsVariable(variable)) {
+          if (string.IsNullOrEmpty(errorMessage)) {
+            errorMessage = "The following variables must be present in the dataset for model evaluation:";
+          }
+          errorMessage += System.Environment.NewLine + " " + variable;
+        }
+      }
+
+      return string.IsNullOrEmpty(errorMessage);
+    }
   }
 }

trunk/HeuristicLab.Problems.DataAnalysis/3.4/Implementation/Regression/RegressionModel.cs

@@ -67 +67 @@
     public abstract IRegressionSolution CreateRegressionSolution(IRegressionProblemData problemData);
 
+    public virtual bool IsProblemDataCompatible(IRegressionProblemData problemData, out string errorMessage) {
+      return IsProblemDataCompatible(this, problemData, out errorMessage);
+    }
+
+    public override bool IsProblemDataCompatible(IDataAnalysisProblemData problemData, out string errorMessage) {
+      if (problemData == null) throw new ArgumentNullException("problemData", "The provided problemData is null.");
+      var regressionProblemData = problemData as IRegressionProblemData;
+      if (regressionProblemData == null)
+        throw new ArgumentException("The problem data is not a regression problem data. Instead a " + problemData.GetType().GetPrettyName() + " was provided.", "problemData");
+      return IsProblemDataCompatible(regressionProblemData, out errorMessage);
+    }
+
+    public static bool IsProblemDataCompatible(IRegressionModel model, IRegressionProblemData problemData, out string errorMessage) {
+      if (model == null) throw new ArgumentNullException("model", "The provided model is null.");
+      if (problemData == null) throw new ArgumentNullException("problemData", "The provided problemData is null.");
+      errorMessage = string.Empty;
+
+      if (model.TargetVariable != problemData.TargetVariable)
+        errorMessage = string.Format("The target variable of the model {0} does not match the target variable of the problemData {1}.", model.TargetVariable, problemData.TargetVariable);
+
+      var evaluationErrorMessage = string.Empty;
+      var datasetCompatible = model.IsDatasetCompatible(problemData.Dataset, out evaluationErrorMessage);
+      if (!datasetCompatible)
+        errorMessage += evaluationErrorMessage;
+
+      return string.IsNullOrEmpty(errorMessage);
+    }
+
     #region events
     public event EventHandler TargetVariableChanged;

trunk/HeuristicLab.Problems.DataAnalysis/3.4/Interfaces/Classification/IClassificationModel.cs

@@ -31 +31 @@
     IEnumerable<double> GetEstimatedClassValues(IDataset dataset, IEnumerable<int> rows);
     IClassificationSolution CreateClassificationSolution(IClassificationProblemData problemData);
+    bool IsProblemDataCompatible(IClassificationProblemData problemData, out string errorMessage);
     string TargetVariable { get; set; }
     event EventHandler TargetVariableChanged;

trunk/HeuristicLab.Problems.DataAnalysis/3.4/Interfaces/IDataAnalysisModel.cs

@@ -30 +30 @@
   public interface IDataAnalysisModel : INamedItem {
     IEnumerable<string> VariablesUsedForPrediction { get; }
+    bool IsDatasetCompatible(IDataset dataset, out string errorMessage);
+    bool IsProblemDataCompatible(IDataAnalysisProblemData problemData, out string errorMessage);
   }
 }

trunk/HeuristicLab.Problems.DataAnalysis/3.4/Interfaces/Regression/IRegressionModel.cs

@@ -31 +31 @@
     IEnumerable<double> GetEstimatedValues(IDataset dataset, IEnumerable<int> rows);
     IRegressionSolution CreateRegressionSolution(IRegressionProblemData problemData);
+    bool IsProblemDataCompatible(IRegressionProblemData problemData, out string errorMessage);
     string TargetVariable { get; set; }
     event EventHandler TargetVariableChanged;