Changeset 16397 for branches/2904_CalculateImpacts/3.4

Timestamp:

12/18/18 17:38:50 (6 years ago)

Author:

mkommend

Message:

#2904: Updated branch with trunk changes.

Location:

branches/2904_CalculateImpacts/3.4

Files:

• . (modified) (1 prop)
• Dataset.cs (modified) (1 diff)
• Implementation/Classification/ClassificationModel.cs (modified) (1 diff)
• Implementation/Classification/ClassificationProblemData.cs (modified) (1 diff)
• Implementation/Classification/ClassificationSolutionBase.cs (modified) (2 diffs)
• Implementation/ConstantModel.cs (modified) (1 diff)
• Implementation/DataAnalysisModel.cs (modified) (2 diffs)
• Implementation/DataAnalysisProblemData.cs (modified) (1 diff)
• Implementation/DataAnalysisSolution.cs (modified) (1 diff)
• Implementation/Regression/RegressionModel.cs (modified) (1 diff)
• Implementation/Regression/RegressionProblemData.cs (modified) (1 diff)
• Implementation/Regression/RegressionSolutionBase.cs (modified) (1 diff)
• Implementation/TimeSeriesPrognosis/TimeSeriesPrognosisProblemData.cs (modified) (1 diff)
• Interfaces/Classification/IClassificationModel.cs (modified) (1 diff)
• Interfaces/IDataAnalysisModel.cs (modified) (1 diff)
• Interfaces/IDataAnalysisProblemData.cs (modified) (1 diff)
• Interfaces/IDataset.cs (modified) (1 diff)
• Interfaces/Regression/IRegressionModel.cs (modified) (1 diff)
• ModifiableDataset.cs (modified) (1 diff)

branches/2904_CalculateImpacts/3.4/Dataset.cs

@@ -167 +167 @@
       }
     }
+
+    public bool ContainsVariable(string variableName) {
+      return variableValues.ContainsKey(variableName);
+    }
     public IEnumerable<string> DoubleVariables {
       get { return variableValues.Where(p => p.Value is IList<double>).Select(p => p.Key); }

branches/2904_CalculateImpacts/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;

branches/2904_CalculateImpacts/3.4/Implementation/Classification/ClassificationProblemData.cs

@@ -467 +467 @@
     }
     #endregion
-
-    protected override bool IsProblemDataCompatible(IDataAnalysisProblemData problemData, out string errorMessage) {
-      if (problemData == null) throw new ArgumentNullException("problemData", "The provided problemData is null.");
-      IClassificationProblemData classificationProblemData = problemData as IClassificationProblemData;
-      if (classificationProblemData == null)
-        throw new ArgumentException("The problem data is no classification problem data. Instead a " + problemData.GetType().GetPrettyName() + " was provided.", "problemData");
-
-      var returnValue = base.IsProblemDataCompatible(classificationProblemData, out errorMessage);
-      //check targetVariable
-      if (classificationProblemData.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;
-      }
-
-      var newClassValues = classificationProblemData.Dataset.GetDoubleValues(TargetVariable).Distinct().OrderBy(x => x);
-      if (!newClassValues.SequenceEqual(ClassValues)) {
-        errorMessage = errorMessage + string.Format("The class values differ in the provided classification problem data.");
-        returnValue = false;
-      }
-
-      var newPositivieClassName = classificationProblemData.PositiveClass;
-      if (newPositivieClassName != PositiveClass) {
-        errorMessage = errorMessage + string.Format("The positive class differs in the provided classification problem data.");
-        returnValue = false;
-      }
-
-      return returnValue;
-    }
-
-    public override void AdjustProblemDataProperties(IDataAnalysisProblemData problemData) {
-      if (problemData == null) throw new ArgumentNullException("problemData", "The provided problemData is null.");
-      ClassificationProblemData classificationProblemData = problemData as ClassificationProblemData;
-      if (classificationProblemData == null)
-        throw new ArgumentException("The problem data is not a classification problem data. Instead a " + problemData.GetType().GetPrettyName() + " was provided.", "problemData");
-
-      base.AdjustProblemDataProperties(problemData);
-      TargetVariable = classificationProblemData.TargetVariable;
-      for (int i = 0; i < classificationProblemData.ClassNames.Count(); i++)
-        ClassNamesParameter.Value[i, 0] = classificationProblemData.ClassNames.ElementAt(i);
-
-      PositiveClass = classificationProblemData.PositiveClass;
-
-      for (int i = 0; i < Classes; i++) {
-        for (int j = 0; j < Classes; j++) {
-          ClassificationPenaltiesParameter.Value[i, j] = classificationProblemData.GetClassificationPenalty(ClassValuesCache[i], ClassValuesCache[j]);
-        }
-      }
-    }
   }
 }

branches/2904_CalculateImpacts/3.4/Implementation/Classification/ClassificationSolutionBase.cs

@@ -20 +20 @@
 #endregion
 
+using System;
 using System.Collections.Generic;
 using System.Linq;
@@ -44 +45 @@
     public new IClassificationProblemData ProblemData {
       get { return (IClassificationProblemData)base.ProblemData; }
-      set { base.ProblemData = value; }
+      set {
+        if (value == null) throw new ArgumentNullException("The problemData must not be null.");
+        string errorMessage = string.Empty;
+        if (!Model.IsProblemDataCompatible(value, out errorMessage)) throw new ArgumentException(errorMessage);
+
+        base.ProblemData = value;
+      }
     }
 

branches/2904_CalculateImpacts/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; }

branches/2904_CalculateImpacts/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);
+    }
   }
 }

branches/2904_CalculateImpacts/3.4/Implementation/DataAnalysisProblemData.cs

@@ -207 +207 @@
       if (listeners != null) listeners(this, EventArgs.Empty);
     }
-
-    protected virtual bool IsProblemDataCompatible(IDataAnalysisProblemData problemData, out string errorMessage) {
-      errorMessage = string.Empty;
-      if (problemData == null) throw new ArgumentNullException("problemData", "The provided problemData is null.");
-
-      //check allowed input variables
-      StringBuilder message = new StringBuilder();
-      var variables = new HashSet<string>(problemData.InputVariables.Select(x => x.Value));
-      foreach (var item in AllowedInputVariables) {
-        if (!variables.Contains(item))
-          message.AppendLine("Input variable '" + item + "' is not present in the new problem data.");
-      }
-
-      if (message.Length != 0) {
-        errorMessage = message.ToString();
-        return false;
-      }
-      return true;
-
-    }
-
-    public virtual void AdjustProblemDataProperties(IDataAnalysisProblemData problemData) {
-      DataAnalysisProblemData data = problemData as DataAnalysisProblemData;
-      if (data == null) throw new ArgumentException("The problem data is not a data analysis problem data. Instead a " + problemData.GetType().GetPrettyName() + " was provided.", "problemData");
-
-      string errorMessage;
-      if (!data.IsProblemDataCompatible(this, out errorMessage)) {
-        throw new InvalidOperationException(errorMessage);
-      }
-
-      foreach (var inputVariable in InputVariables) {
-        var variable = data.InputVariables.FirstOrDefault(i => i.Value == inputVariable.Value);
-        InputVariables.SetItemCheckedState(inputVariable, variable != null && data.InputVariables.ItemChecked(variable));
-      }
-    }
   }
 }

branches/2904_CalculateImpacts/3.4/Implementation/DataAnalysisSolution.cs

@@ -58 +58 @@
       get { return (IDataAnalysisProblemData)this[ProblemDataResultName].Value; }
       set {
-        if (this[ProblemDataResultName].Value != value) {
-          if (value != null) {
-            ProblemData.Changed -= new EventHandler(ProblemData_Changed);
-            this[ProblemDataResultName].Value = value;
-            ProblemData.Changed += new EventHandler(ProblemData_Changed);
-            OnProblemDataChanged();
-          }
-        }
+        if (value == null) throw new ArgumentNullException("The problemData must not be null.");
+        if (this[ProblemDataResultName].Value == value) return;
+        string errorMessage = string.Empty;
+        if (!Model.IsProblemDataCompatible(value, out errorMessage)) throw new ArgumentException(errorMessage);
+
+        ProblemData.Changed -= new EventHandler(ProblemData_Changed);
+        this[ProblemDataResultName].Value = value;
+        ProblemData.Changed += new EventHandler(ProblemData_Changed);
+        OnProblemDataChanged();
       }
     }

branches/2904_CalculateImpacts/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;

branches/2904_CalculateImpacts/3.4/Implementation/Regression/RegressionProblemData.cs

@@ -161 +161 @@
       OnChanged();
     }
-
-    protected override bool IsProblemDataCompatible(IDataAnalysisProblemData problemData, out string errorMessage) {
-      if (problemData == null) throw new ArgumentNullException("problemData", "The provided problemData is null.");
-      IRegressionProblemData 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");
-
-      var returnValue = base.IsProblemDataCompatible(problemData, out errorMessage);
-      return returnValue;
-    }
-
-    public override void AdjustProblemDataProperties(IDataAnalysisProblemData problemData) {
-      if (problemData == null) throw new ArgumentNullException("problemData", "The provided problemData is null.");
-      RegressionProblemData regressionProblemData = problemData as RegressionProblemData;
-      if (regressionProblemData == null)
-        throw new ArgumentException("The problem data is not a regression problem data. Instead a " + problemData.GetType().GetPrettyName() + " was provided.", "problemData");
-
-      base.AdjustProblemDataProperties(problemData);
-    }
   }
 }

branches/2904_CalculateImpacts/3.4/Implementation/Regression/RegressionSolutionBase.cs

@@ -70 +70 @@
     public new IRegressionProblemData ProblemData {
       get { return (IRegressionProblemData)base.ProblemData; }
-      set { base.ProblemData = value; }
+      set {
+        if (value == null) throw new ArgumentNullException("The problemData must not be null.");
+        string errorMessage = string.Empty;
+        if (!Model.IsProblemDataCompatible(value, out errorMessage)) throw new ArgumentException(errorMessage);
+
+        base.ProblemData = value;
+      }
     }
 

branches/2904_CalculateImpacts/3.4/Implementation/TimeSeriesPrognosis/TimeSeriesPrognosisProblemData.cs

@@ -1620 +1620 @@
       OnChanged();
     }
-
-    protected override bool IsProblemDataCompatible(IDataAnalysisProblemData problemData, out string errorMessage) {
-      if (problemData == null) throw new ArgumentNullException("problemData", "The provided problemData is null.");
-      ITimeSeriesPrognosisProblemData timeseriesProblemData = problemData as ITimeSeriesPrognosisProblemData;
-      if (timeseriesProblemData == null)
-        throw new ArgumentException("The problem data is not a time-series problem data. Instead a " + problemData.GetType().GetPrettyName() + " was provided.", "problemData");
-
-      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;
-    }
-
-    public override void AdjustProblemDataProperties(IDataAnalysisProblemData problemData) {
-      TimeSeriesPrognosisProblemData timeSeriesProblemData = problemData as TimeSeriesPrognosisProblemData;
-      if (timeSeriesProblemData == null)
-        throw new ArgumentException("The problem data is not a timeseries problem data. Instead a " + problemData.GetType().GetPrettyName() + " was provided.", "problemData");
-
-      var trainingDataStart = TrainingIndices.First();
-
-      base.AdjustProblemDataProperties(problemData);
-
-      TestPartition.Start = trainingDataStart;
-
-      TrainingHorizon = timeSeriesProblemData.TrainingHorizon;
-      TestHorizon = timeSeriesProblemData.TestHorizon;
-    }
-
   }
 }

branches/2904_CalculateImpacts/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;

branches/2904_CalculateImpacts/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);
   }
 }

branches/2904_CalculateImpacts/3.4/Interfaces/IDataAnalysisProblemData.cs

@@ -49 +49 @@
 
     event EventHandler Changed;
-
-    void AdjustProblemDataProperties(IDataAnalysisProblemData problemData);
   }
 }

branches/2904_CalculateImpacts/3.4/Interfaces/IDataset.cs

@@ -33 +33 @@
     IEnumerable<string> DateTimeVariables { get; }
 
+    bool ContainsVariable(string variablename);
     bool VariableHasType<T>(string variableName);
 

branches/2904_CalculateImpacts/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;

branches/2904_CalculateImpacts/3.4/ModifiableDataset.cs

@@ -56 +56 @@
 
     public IEnumerable<object> GetRow(int row) {
+      if (row < 0 || row >= Rows)
+        throw new ArgumentException(string.Format("Invalid row {0} specified. The dataset contains {1} row(s).", row, Rows));
+
       return variableValues.Select(x => x.Value[row]);
     }