Changeset 16308 for branches/2845_EnhancedProgress/HeuristicLab.Algorithms.DataAnalysis/3.4/TSNE/TSNEAlgorithm.cs

Timestamp:

11/20/18 13:52:40 (5 years ago)

Author:

pfleck

Message:

#2845 reverted the last merge (r16307) because some revisions were missing

Location:

branches/2845_EnhancedProgress

Files:

• . (modified) (1 prop)
• HeuristicLab.Algorithms.DataAnalysis (modified) (1 prop)
• HeuristicLab.Algorithms.DataAnalysis/3.4 (modified) (1 prop)
• HeuristicLab.Algorithms.DataAnalysis/3.4/TSNE/TSNEAlgorithm.cs (modified) (20 diffs)

branches/2845_EnhancedProgress/HeuristicLab.Algorithms.DataAnalysis/3.4/TSNE/TSNEAlgorithm.cs

@@ -1 +1 @@
 #region License Information
 /* HeuristicLab
- * Copyright (C) 2002-2018 Heuristic and Evolutionary Algorithms Laboratory (HEAL)
+ * Copyright (C) 2002-2016 Heuristic and Evolutionary Algorithms Laboratory (HEAL)
  *
  * This file is part of HeuristicLab.
@@ -38 +38 @@
 namespace HeuristicLab.Algorithms.DataAnalysis {
   /// <summary>
-  /// t-Distributed Stochastic Neighbor Embedding (tSNE) projects the data in a low dimensional 
+  /// t-distributed stochastic neighbourhood embedding (tSNE) projects the data in a low dimensional 
   /// space to allow visual cluster identification.
   /// </summary>
-  [Item("t-Distributed Stochastic Neighbor Embedding (tSNE)", "t-Distributed Stochastic Neighbor Embedding projects the data in a low " +
-                                                              "dimensional space to allow visual cluster identification. Implemented similar to: https://lvdmaaten.github.io/tsne/#implementations (Barnes-Hut t-SNE). Described in : https://lvdmaaten.github.io/publications/papers/JMLR_2014.pdf")]
+  [Item("tSNE", "t-distributed stochastic neighbourhood embedding projects the data in a low " +
+                "dimensional space to allow visual cluster identification. Implemented similar to: https://lvdmaaten.github.io/tsne/#implementations (Barnes-Hut t-SNE). Described in : https://lvdmaaten.github.io/publications/papers/JMLR_2014.pdf")]
   [Creatable(CreatableAttribute.Categories.DataAnalysis, Priority = 100)]
   [StorableClass]
@@ -57 +57 @@
     }
 
-    #region Parameter names
+    #region parameter names
     private const string DistanceFunctionParameterName = "DistanceFunction";
     private const string PerplexityParameterName = "Perplexity";
@@ -72 +72 @@
     private const string ClassesNameParameterName = "ClassesName";
     private const string NormalizationParameterName = "Normalization";
-    private const string RandomInitializationParameterName = "RandomInitialization";
     private const string UpdateIntervalParameterName = "UpdateInterval";
     #endregion
 
-    #region Result names
+    #region result names
     private const string IterationResultName = "Iteration";
     private const string ErrorResultName = "Error";
@@ -84 +83 @@
     #endregion
 
-    #region Parameter properties
+    #region parameter properties
     public IFixedValueParameter<DoubleValue> PerplexityParameter {
-      get { return (IFixedValueParameter<DoubleValue>)Parameters[PerplexityParameterName]; }
+      get { return Parameters[PerplexityParameterName] as IFixedValueParameter<DoubleValue>; }
     }
     public IFixedValueParameter<PercentValue> ThetaParameter {
-      get { return (IFixedValueParameter<PercentValue>)Parameters[ThetaParameterName]; }
+      get { return Parameters[ThetaParameterName] as IFixedValueParameter<PercentValue>; }
     }
     public IFixedValueParameter<IntValue> NewDimensionsParameter {
-      get { return (IFixedValueParameter<IntValue>)Parameters[NewDimensionsParameterName]; }
+      get { return Parameters[NewDimensionsParameterName] as IFixedValueParameter<IntValue>; }
     }
     public IConstrainedValueParameter<IDistance<double[]>> DistanceFunctionParameter {
-      get { return (IConstrainedValueParameter<IDistance<double[]>>)Parameters[DistanceFunctionParameterName]; }
+      get { return Parameters[DistanceFunctionParameterName] as IConstrainedValueParameter<IDistance<double[]>>; }
     }
     public IFixedValueParameter<IntValue> MaxIterationsParameter {
-      get { return (IFixedValueParameter<IntValue>)Parameters[MaxIterationsParameterName]; }
+      get { return Parameters[MaxIterationsParameterName] as IFixedValueParameter<IntValue>; }
     }
     public IFixedValueParameter<IntValue> StopLyingIterationParameter {
-      get { return (IFixedValueParameter<IntValue>)Parameters[StopLyingIterationParameterName]; }
+      get { return Parameters[StopLyingIterationParameterName] as IFixedValueParameter<IntValue>; }
     }
     public IFixedValueParameter<IntValue> MomentumSwitchIterationParameter {
-      get { return (IFixedValueParameter<IntValue>)Parameters[MomentumSwitchIterationParameterName]; }
+      get { return Parameters[MomentumSwitchIterationParameterName] as IFixedValueParameter<IntValue>; }
     }
     public IFixedValueParameter<DoubleValue> InitialMomentumParameter {
-      get { return (IFixedValueParameter<DoubleValue>)Parameters[InitialMomentumParameterName]; }
+      get { return Parameters[InitialMomentumParameterName] as IFixedValueParameter<DoubleValue>; }
     }
     public IFixedValueParameter<DoubleValue> FinalMomentumParameter {
-      get { return (IFixedValueParameter<DoubleValue>)Parameters[FinalMomentumParameterName]; }
+      get { return Parameters[FinalMomentumParameterName] as IFixedValueParameter<DoubleValue>; }
     }
     public IFixedValueParameter<DoubleValue> EtaParameter {
-      get { return (IFixedValueParameter<DoubleValue>)Parameters[EtaParameterName]; }
+      get { return Parameters[EtaParameterName] as IFixedValueParameter<DoubleValue>; }
     }
     public IFixedValueParameter<BoolValue> SetSeedRandomlyParameter {
-      get { return (IFixedValueParameter<BoolValue>)Parameters[SetSeedRandomlyParameterName]; }
+      get { return Parameters[SetSeedRandomlyParameterName] as IFixedValueParameter<BoolValue>; }
     }
     public IFixedValueParameter<IntValue> SeedParameter {
-      get { return (IFixedValueParameter<IntValue>)Parameters[SeedParameterName]; }
+      get { return Parameters[SeedParameterName] as IFixedValueParameter<IntValue>; }
     }
     public IConstrainedValueParameter<StringValue> ClassesNameParameter {
-      get { return (IConstrainedValueParameter<StringValue>)Parameters[ClassesNameParameterName]; }
+      get { return Parameters[ClassesNameParameterName] as IConstrainedValueParameter<StringValue>; }
     }
     public IFixedValueParameter<BoolValue> NormalizationParameter {
-      get { return (IFixedValueParameter<BoolValue>)Parameters[NormalizationParameterName]; }
-    }
-    public IFixedValueParameter<BoolValue> RandomInitializationParameter {
-      get { return (IFixedValueParameter<BoolValue>)Parameters[RandomInitializationParameterName]; }
+      get { return Parameters[NormalizationParameterName] as IFixedValueParameter<BoolValue>; }
     }
     public IFixedValueParameter<IntValue> UpdateIntervalParameter {
-      get { return (IFixedValueParameter<IntValue>)Parameters[UpdateIntervalParameterName]; }
+      get { return Parameters[UpdateIntervalParameterName] as IFixedValueParameter<IntValue>; }
     }
     #endregion
@@ -191 +187 @@
       set { NormalizationParameter.Value.Value = value; }
     }
-    public bool RandomInitialization {
-      get { return RandomInitializationParameter.Value.Value; }
-      set { RandomInitializationParameter.Value.Value = value; }
-    }
+
     public int UpdateInterval {
       get { return UpdateIntervalParameter.Value.Value; }
@@ -201 +194 @@
     #endregion
 
-    #region Storable poperties
-    [Storable]
-    private Dictionary<string, IList<int>> dataRowIndices;
-    [Storable]
-    private TSNEStatic<double[]>.TSNEState state;
-    #endregion
-
     #region Constructors & Cloning
     [StorableConstructor]
     private TSNEAlgorithm(bool deserializing) : base(deserializing) { }
 
-    [StorableHook(HookType.AfterDeserialization)]
-    private void AfterDeserialization() {
-      if (!Parameters.ContainsKey(RandomInitializationParameterName))
-        Parameters.Add(new FixedValueParameter<BoolValue>(RandomInitializationParameterName, "Wether data points should be randomly initialized or according to the first 2 dimensions", new BoolValue(true)));
-      RegisterParameterEvents();
-    }
     private TSNEAlgorithm(TSNEAlgorithm original, Cloner cloner) : base(original, cloner) {
-      if (original.dataRowIndices != null)
-        dataRowIndices = new Dictionary<string, IList<int>>(original.dataRowIndices);
+      if (original.dataRowNames != null)
+        this.dataRowNames = new Dictionary<string, List<int>>(original.dataRowNames);
+      if (original.dataRows != null)
+        this.dataRows = original.dataRows.ToDictionary(kvp => kvp.Key, kvp => cloner.Clone(kvp.Value));
       if (original.state != null)
-        state = cloner.Clone(original.state);
-      RegisterParameterEvents();
-    }
-    public override IDeepCloneable Clone(Cloner cloner) {
-      return new TSNEAlgorithm(this, cloner);
-    }
+        this.state = cloner.Clone(original.state);
+      this.iter = original.iter;
+    }
+    public override IDeepCloneable Clone(Cloner cloner) { return new TSNEAlgorithm(this, cloner); }
     public TSNEAlgorithm() {
       var distances = new ItemSet<IDistance<double[]>>(ApplicationManager.Manager.GetInstances<IDistance<double[]>>());
@@ -233 +213 @@
       Parameters.Add(new FixedValueParameter<DoubleValue>(PerplexityParameterName, "Perplexity-parameter of tSNE. Comparable to k in a k-nearest neighbour algorithm. Recommended value is floor(number of points /3) or lower", new DoubleValue(25)));
       Parameters.Add(new FixedValueParameter<PercentValue>(ThetaParameterName, "Value describing how much appoximated " +
-                                                                               "gradients my differ from exact gradients. Set to 0 for exact calculation and in [0,1] otherwise. " +
-                                                                               "Appropriate values for theta are between 0.1 and 0.7 (default = 0.5). CAUTION: exact calculation of " +
-                                                                               "forces requires building a non-sparse N*N matrix where N is the number of data points. This may " +
-                                                                               "exceed memory limitations. The function is designed to run on large (N > 5000) data sets. It may give" +
-                                                                               " poor performance on very small data sets(it is better to use a standard t - SNE implementation on such data).", new PercentValue(0)));
+                                                                              "gradients my differ from exact gradients. Set to 0 for exact calculation and in [0,1] otherwise. " +
+                                                                              "Appropriate values for theta are between 0.1 and 0.7 (default = 0.5). CAUTION: exact calculation of " +
+                                                                              "forces requires building a non-sparse N*N matrix where N is the number of data points. This may " +
+                                                                              "exceed memory limitations. The function is designed to run on large (N > 5000) data sets. It may give" +
+                                                                              " poor performance on very small data sets(it is better to use a standard t - SNE implementation on such data).", new PercentValue(0)));
       Parameters.Add(new FixedValueParameter<IntValue>(NewDimensionsParameterName, "Dimensionality of projected space (usually 2 for easy visual analysis)", new IntValue(2)));
       Parameters.Add(new FixedValueParameter<IntValue>(MaxIterationsParameterName, "Maximum number of iterations for gradient descent.", new IntValue(1000)));
@@ -250 +230 @@
       Parameters.Add(new FixedValueParameter<BoolValue>(NormalizationParameterName, "Whether the data should be zero centered and have variance of 1 for each variable, so different scalings are ignored.", new BoolValue(true)));
       Parameters.Add(new FixedValueParameter<IntValue>(UpdateIntervalParameterName, "The interval after which the results will be updated.", new IntValue(50)));
-      Parameters.Add(new FixedValueParameter<BoolValue>(RandomInitializationParameterName, "Wether data points should be randomly initialized or according to the first 2 dimensions", new BoolValue(true)));
-
-      UpdateIntervalParameter.Hidden = true;
+      Parameters[UpdateIntervalParameterName].Hidden = true;
+
       MomentumSwitchIterationParameter.Hidden = true;
       InitialMomentumParameter.Hidden = true;
@@ -259 +238 @@
       EtaParameter.Hidden = false;
       Problem = new RegressionProblem();
-      RegisterParameterEvents();
-    }
-    #endregion
+    }
+    #endregion
+
+    [Storable]
+    private Dictionary<string, List<int>> dataRowNames;
+    [Storable]
+    private Dictionary<string, ScatterPlotDataRow> dataRows;
+    [Storable]
+    private TSNEStatic<double[]>.TSNEState state;
+    [Storable]
+    private int iter;
 
     public override void Prepare() {
       base.Prepare();
-      dataRowIndices = null;
+      dataRowNames = null;
+      dataRows = null;
       state = null;
     }
@@ -271 +259 @@
     protected override void Run(CancellationToken cancellationToken) {
       var problemData = Problem.ProblemData;
-      // set up and initialize everything if necessary
-      var wdist = DistanceFunction as WeightedEuclideanDistance;
-      if (wdist != null) wdist.Initialize(problemData);
+      // set up and initialized everything if necessary
       if (state == null) {
         if (SetSeedRandomly) Seed = new System.Random().Next();
@@ -279 +265 @@
         var dataset = problemData.Dataset;
         var allowedInputVariables = problemData.AllowedInputVariables.ToArray();
-        var allindices = Problem.ProblemData.AllIndices.ToArray();
-
-        // jagged array is required to meet the static method declarations of TSNEStatic<T> 
-        var data = Enumerable.Range(0, dataset.Rows).Select(x => new double[allowedInputVariables.Length]).ToArray();
-        var col = 0;
-        foreach (var s in allowedInputVariables) {
-          var row = 0;
-          foreach (var d in dataset.GetDoubleValues(s)) {
-            data[row][col] = d;
-            row++;
-          }
-          col++;
-        }
-        if (Normalization) data = NormalizeInputData(data);
-        state = TSNEStatic<double[]>.CreateState(data, DistanceFunction, random, NewDimensions, Perplexity, Theta, StopLyingIteration, MomentumSwitchIteration, InitialMomentum, FinalMomentum, Eta, RandomInitialization);
-        SetUpResults(allindices);
-      }
-      while (state.iter < MaxIterations && !cancellationToken.IsCancellationRequested) {
-        if (state.iter % UpdateInterval == 0) Analyze(state);
+        var data = new double[dataset.Rows][];
+        for (var row = 0; row < dataset.Rows; row++)
+          data[row] = allowedInputVariables.Select(col => dataset.GetDoubleValue(col, row)).ToArray();
+
+        if (Normalization) data = NormalizeData(data);
+
+        state = TSNEStatic<double[]>.CreateState(data, DistanceFunction, random, NewDimensions, Perplexity, Theta,
+          StopLyingIteration, MomentumSwitchIteration, InitialMomentum, FinalMomentum, Eta);
+
+        SetUpResults(data);
+        iter = 0;
+      }
+      for (; iter < MaxIterations && !cancellationToken.IsCancellationRequested; iter++) {
+        if (iter % UpdateInterval == 0)
+          Analyze(state);
         TSNEStatic<double[]>.Iterate(state);
       }
@@ -312 +294 @@
     protected override void RegisterProblemEvents() {
       base.RegisterProblemEvents();
-      if (Problem == null) return;
       Problem.ProblemDataChanged += OnProblemDataChanged;
-      if (Problem.ProblemData == null) return;
-      Problem.ProblemData.Changed += OnPerplexityChanged;
-      Problem.ProblemData.Changed += OnColumnsChanged;
-      if (Problem.ProblemData.Dataset == null) return;
-      Problem.ProblemData.Dataset.RowsChanged += OnPerplexityChanged;
-      Problem.ProblemData.Dataset.ColumnsChanged += OnColumnsChanged;
-    }
-
+    }
     protected override void DeregisterProblemEvents() {
       base.DeregisterProblemEvents();
-      if (Problem == null) return;
       Problem.ProblemDataChanged -= OnProblemDataChanged;
-      if (Problem.ProblemData == null) return;
-      Problem.ProblemData.Changed -= OnPerplexityChanged;
-      Problem.ProblemData.Changed -= OnColumnsChanged;
-      if (Problem.ProblemData.Dataset == null) return;
-      Problem.ProblemData.Dataset.RowsChanged -= OnPerplexityChanged;
-      Problem.ProblemData.Dataset.ColumnsChanged -= OnColumnsChanged;
-    }
-
-    protected override void OnStopped() {
-      base.OnStopped();
-      //bwerth: state objects can be very large; avoid state serialization 
-      state = null;
-      dataRowIndices = null;
     }
 
     private void OnProblemDataChanged(object sender, EventArgs args) {
       if (Problem == null || Problem.ProblemData == null) return;
-      OnPerplexityChanged(this, null);
-      OnColumnsChanged(this, null);
-      Problem.ProblemData.Changed += OnPerplexityChanged;
-      Problem.ProblemData.Changed += OnColumnsChanged;
-      if (Problem.ProblemData.Dataset == null) return;
-      Problem.ProblemData.Dataset.RowsChanged += OnPerplexityChanged;
-      Problem.ProblemData.Dataset.ColumnsChanged += OnColumnsChanged;
       if (!Parameters.ContainsKey(ClassesNameParameterName)) return;
       ClassesNameParameter.ValidValues.Clear();
@@ -355 +308 @@
     }
 
-    private void OnColumnsChanged(object sender, EventArgs e) {
-      if (Problem == null || Problem.ProblemData == null || Problem.ProblemData.Dataset == null || !Parameters.ContainsKey(DistanceFunctionParameterName)) return;
-      DistanceFunctionParameter.ValidValues.OfType<WeightedEuclideanDistance>().Single().AdaptToProblemData(Problem.ProblemData);
-    }
-
-    private void RegisterParameterEvents() {
-      PerplexityParameter.Value.ValueChanged += OnPerplexityChanged;
-    }
-
-    private void OnPerplexityChanged(object sender, EventArgs e) {
-      if (Problem == null || Problem.ProblemData == null || Problem.ProblemData.Dataset == null || !Parameters.ContainsKey(PerplexityParameterName)) return;
-      PerplexityParameter.Value.Value = Math.Max(1, Math.Min((Problem.ProblemData.Dataset.Rows - 1) / 3.0, Perplexity));
-    }
     #endregion
 
     #region Helpers
-    private void SetUpResults(IReadOnlyList<int> allIndices) {
+    private void SetUpResults(IReadOnlyCollection<double[]> data) {
       if (Results == null) return;
       var results = Results;
-      dataRowIndices = new Dictionary<string, IList<int>>();
+      dataRowNames = new Dictionary<string, List<int>>();
+      dataRows = new Dictionary<string, ScatterPlotDataRow>();
       var problemData = Problem.ProblemData;
 
+      //color datapoints acording to classes variable (be it double or string)
+      if (problemData.Dataset.VariableNames.Contains(ClassesName)) {
+        if ((problemData.Dataset as Dataset).VariableHasType<string>(ClassesName)) {
+          var classes = problemData.Dataset.GetStringValues(ClassesName).ToArray();
+          for (var i = 0; i < classes.Length; i++) {
+            if (!dataRowNames.ContainsKey(classes[i])) dataRowNames.Add(classes[i], new List<int>());
+            dataRowNames[classes[i]].Add(i);
+          }
+        } else if ((problemData.Dataset as Dataset).VariableHasType<double>(ClassesName)) {
+          var classValues = problemData.Dataset.GetDoubleValues(ClassesName).ToArray();
+          var max = classValues.Max() + 0.1;
+          var min = classValues.Min() - 0.1;
+          const int contours = 8;
+          for (var i = 0; i < contours; i++) {
+            var contourname = GetContourName(i, min, max, contours);
+            dataRowNames.Add(contourname, new List<int>());
+            dataRows.Add(contourname, new ScatterPlotDataRow(contourname, "", new List<Point2D<double>>()));
+            dataRows[contourname].VisualProperties.Color = GetHeatMapColor(i, contours);
+            dataRows[contourname].VisualProperties.PointSize = i + 3;
+          }
+          for (var i = 0; i < classValues.Length; i++) {
+            dataRowNames[GetContourName(classValues[i], min, max, contours)].Add(i);
+          }
+        }
+      } else {
+        dataRowNames.Add("Training", problemData.TrainingIndices.ToList());
+        dataRowNames.Add("Test", problemData.TestIndices.ToList());
+      }
+
       if (!results.ContainsKey(IterationResultName)) results.Add(new Result(IterationResultName, new IntValue(0)));
+      else ((IntValue)results[IterationResultName].Value).Value = 0;
+
       if (!results.ContainsKey(ErrorResultName)) results.Add(new Result(ErrorResultName, new DoubleValue(0)));
-      if (!results.ContainsKey(ScatterPlotResultName)) results.Add(new Result(ScatterPlotResultName, "Plot of the projected data", new ScatterPlot(DataResultName, "")));
-      if (!results.ContainsKey(DataResultName)) results.Add(new Result(DataResultName, "Projected Data", new DoubleMatrix()));
-      if (!results.ContainsKey(ErrorPlotResultName)) {
-        var errortable = new DataTable(ErrorPlotResultName, "Development of errors during gradient descent") {
-          VisualProperties = {
-            XAxisTitle = "UpdateIntervall",
-            YAxisTitle = "Error",
-            YAxisLogScale = true
-          }
-        };
-        errortable.Rows.Add(new DataRow("Errors"));
-        errortable.Rows["Errors"].VisualProperties.StartIndexZero = true;
-        results.Add(new Result(ErrorPlotResultName, errortable));
-      }
-
-      //color datapoints acording to classes variable (be it double, datetime or string)
-      if (!problemData.Dataset.VariableNames.Contains(ClassesName)) {
-        dataRowIndices.Add("Training", problemData.TrainingIndices.ToList());
-        dataRowIndices.Add("Test", problemData.TestIndices.ToList());
-        return;
-      }
-
-      var classificationData = problemData as ClassificationProblemData;
-      if (classificationData != null && classificationData.TargetVariable.Equals(ClassesName)) {
-        var classNames = classificationData.ClassValues.Zip(classificationData.ClassNames, (v, n) => new {v, n}).ToDictionary(x => x.v, x => x.n);
-        var classes = classificationData.Dataset.GetDoubleValues(classificationData.TargetVariable, allIndices).Select(v => classNames[v]).ToArray();
-        for (var i = 0; i < classes.Length; i++) {
-          if (!dataRowIndices.ContainsKey(classes[i])) dataRowIndices.Add(classes[i], new List<int>());
-          dataRowIndices[classes[i]].Add(i);
-        }
-      } else if (((Dataset)problemData.Dataset).VariableHasType<string>(ClassesName)) {
-        var classes = problemData.Dataset.GetStringValues(ClassesName, allIndices).ToArray();
-        for (var i = 0; i < classes.Length; i++) {
-          if (!dataRowIndices.ContainsKey(classes[i])) dataRowIndices.Add(classes[i], new List<int>());
-          dataRowIndices[classes[i]].Add(i);
-        }
-      } else if (((Dataset)problemData.Dataset).VariableHasType<double>(ClassesName)) {
-        var clusterdata = new Dataset(problemData.Dataset.DoubleVariables, problemData.Dataset.DoubleVariables.Select(v => problemData.Dataset.GetDoubleValues(v, allIndices).ToList()));
-        const int contours = 8;
-        Dictionary<int, string> contourMap;
-        IClusteringModel clusterModel;
-        double[][] borders;
-        CreateClusters(clusterdata, ClassesName, contours, out clusterModel, out contourMap, out borders);
-        var contourorder = borders.Select((x, i) => new {x, i}).OrderBy(x => x.x[0]).Select(x => x.i).ToArray();
-        for (var i = 0; i < contours; i++) {
-          var c = contourorder[i];
-          var contourname = contourMap[c];
-          dataRowIndices.Add(contourname, new List<int>());
-          var row = new ScatterPlotDataRow(contourname, "", new List<Point2D<double>>()) {VisualProperties = {Color = GetHeatMapColor(i, contours), PointSize = 8}};
-          ((ScatterPlot)results[ScatterPlotResultName].Value).Rows.Add(row);
-        }
-        var allClusters = clusterModel.GetClusterValues(clusterdata, Enumerable.Range(0, clusterdata.Rows)).ToArray();
-        for (var i = 0; i < clusterdata.Rows; i++) dataRowIndices[contourMap[allClusters[i] - 1]].Add(i);
-      } else if (((Dataset)problemData.Dataset).VariableHasType<DateTime>(ClassesName)) {
-        var clusterdata = new Dataset(problemData.Dataset.DateTimeVariables, problemData.Dataset.DateTimeVariables.Select(v => problemData.Dataset.GetDoubleValues(v, allIndices).ToList()));
-        const int contours = 8;
-        Dictionary<int, string> contourMap;
-        IClusteringModel clusterModel;
-        double[][] borders;
-        CreateClusters(clusterdata, ClassesName, contours, out clusterModel, out contourMap, out borders);
-        var contourorder = borders.Select((x, i) => new {x, i}).OrderBy(x => x.x[0]).Select(x => x.i).ToArray();
-        for (var i = 0; i < contours; i++) {
-          var c = contourorder[i];
-          var contourname = contourMap[c];
-          dataRowIndices.Add(contourname, new List<int>());
-          var row = new ScatterPlotDataRow(contourname, "", new List<Point2D<double>>()) {VisualProperties = {Color = GetHeatMapColor(i, contours), PointSize = 8}};
-          row.VisualProperties.PointSize = 8;
-          ((ScatterPlot)results[ScatterPlotResultName].Value).Rows.Add(row);
-        }
-        var allClusters = clusterModel.GetClusterValues(clusterdata, Enumerable.Range(0, clusterdata.Rows)).ToArray();
-        for (var i = 0; i < clusterdata.Rows; i++) dataRowIndices[contourMap[allClusters[i] - 1]].Add(i);
-      } else {
-        dataRowIndices.Add("Training", problemData.TrainingIndices.ToList());
-        dataRowIndices.Add("Test", problemData.TestIndices.ToList());
-      }
+      else ((DoubleValue)results[ErrorResultName].Value).Value = 0;
+
+      if (!results.ContainsKey(ErrorPlotResultName)) results.Add(new Result(ErrorPlotResultName, new DataTable(ErrorPlotResultName, "Development of errors during gradient descent")));
+      else results[ErrorPlotResultName].Value = new DataTable(ErrorPlotResultName, "Development of errors during gradient descent");
+
+      var plot = results[ErrorPlotResultName].Value as DataTable;
+      if (plot == null) throw new ArgumentException("could not create/access error data table in results collection");
+
+      if (!plot.Rows.ContainsKey("errors")) plot.Rows.Add(new DataRow("errors"));
+      plot.Rows["errors"].Values.Clear();
+      plot.Rows["errors"].VisualProperties.StartIndexZero = true;
+
+      results.Add(new Result(ScatterPlotResultName, "Plot of the projected data", new ScatterPlot(DataResultName, "")));
+      results.Add(new Result(DataResultName, "Projected Data", new DoubleMatrix()));
     }
 
@@ -461 +372 @@
       var plot = results[ErrorPlotResultName].Value as DataTable;
       if (plot == null) throw new ArgumentException("Could not create/access error data table in results collection.");
-      var errors = plot.Rows["Errors"].Values;
+      var errors = plot.Rows["errors"].Values;
       var c = tsneState.EvaluateError();
       errors.Add(c);
@@ -467 +378 @@
       ((DoubleValue)results[ErrorResultName].Value).Value = errors.Last();
 
-      var ndata = NormalizeProjectedData(tsneState.newData);
+      var ndata = Normalize(tsneState.newData);
       results[DataResultName].Value = new DoubleMatrix(ndata);
       var splot = results[ScatterPlotResultName].Value as ScatterPlot;
-      FillScatterPlot(ndata, splot, dataRowIndices);
-    }
-
-    private static void FillScatterPlot(double[,] lowDimData, ScatterPlot plot, Dictionary<string, IList<int>> dataRowIndices) {
-      foreach (var rowName in dataRowIndices.Keys) {
-        if (!plot.Rows.ContainsKey(rowName)) {
-          plot.Rows.Add(new ScatterPlotDataRow(rowName, "", new List<Point2D<double>>()));
-          plot.Rows[rowName].VisualProperties.PointSize = 8;
-        }
-        plot.Rows[rowName].Points.Replace(dataRowIndices[rowName].Select(i => new Point2D<double>(lowDimData[i, 0], lowDimData[i, 1])));
-      }
-    }
-
-    private static double[,] NormalizeProjectedData(double[,] data) {
+      FillScatterPlot(ndata, splot);
+    }
+
+    private void FillScatterPlot(double[,] lowDimData, ScatterPlot plot) {
+      foreach (var rowName in dataRowNames.Keys) {
+        if (!plot.Rows.ContainsKey(rowName))
+          plot.Rows.Add(dataRows.ContainsKey(rowName) ? dataRows[rowName] : new ScatterPlotDataRow(rowName, "", new List<Point2D<double>>()));
+        plot.Rows[rowName].Points.Replace(dataRowNames[rowName].Select(i => new Point2D<double>(lowDimData[i, 0], lowDimData[i, 1])));
+      }
+    }
+
+    private static double[,] Normalize(double[,] data) {
       var max = new double[data.GetLength(1)];
       var min = new double[data.GetLength(1)];
@@ -489 +398 @@
       for (var i = 0; i < max.Length; i++) max[i] = min[i] = data[0, i];
       for (var i = 0; i < data.GetLength(0); i++)
-      for (var j = 0; j < data.GetLength(1); j++) {
-        var v = data[i, j];
-        max[j] = Math.Max(max[j], v);
-        min[j] = Math.Min(min[j], v);
-      }
+        for (var j = 0; j < data.GetLength(1); j++) {
+          var v = data[i, j];
+          max[j] = Math.Max(max[j], v);
+          min[j] = Math.Min(min[j], v);
+        }
       for (var i = 0; i < data.GetLength(0); i++) {
         for (var j = 0; j < data.GetLength(1); j++) {
           var d = max[j] - min[j];
-          var s = data[i, j] - (max[j] + min[j]) / 2; //shift data
-          if (d.IsAlmost(0)) res[i, j] = data[i, j]; //no scaling possible
-          else res[i, j] = s / d; //scale data
+          var s = data[i, j] - (max[j] + min[j]) / 2;  //shift data
+          if (d.IsAlmost(0)) res[i, j] = data[i, j];   //no scaling possible
+          else res[i, j] = s / d;  //scale data
         }
       }
@@ -505 +414 @@
     }
 
-    private static double[][] NormalizeInputData(IReadOnlyList<IReadOnlyList<double>> data) {
+    private static double[][] NormalizeData(IReadOnlyList<double[]> data) {
       // as in tSNE implementation by van der Maaten
-      var n = data[0].Count;
+      var n = data[0].Length;
       var mean = new double[n];
       var max = new double[n];
@@ -517 +426 @@
       for (var i = 0; i < data.Count; i++) {
         nData[i] = new double[n];
-        for (var j = 0; j < n; j++)
-          nData[i][j] = max[j].IsAlmost(0) ? data[i][j] - mean[j] : (data[i][j] - mean[j]) / max[j];
+        for (var j = 0; j < n; j++) nData[i][j] = max[j].IsAlmost(0) ? data[i][j] - mean[j] : (data[i][j] - mean[j]) / max[j];
       }
       return nData;
@@ -524 +432 @@
 
     private static Color GetHeatMapColor(int contourNr, int noContours) {
-      return ConvertTotalToRgb(0, noContours, contourNr);
-    }
-
-    private static void CreateClusters(IDataset data, string target, int contours, out IClusteringModel contourCluster, out Dictionary<int, string> contourNames, out double[][] borders) {
-      var cpd = new ClusteringProblemData((Dataset)data, new[] {target});
-      contourCluster = KMeansClustering.CreateKMeansSolution(cpd, contours, 3).Model;
-
-      borders = Enumerable.Range(0, contours).Select(x => new[] {double.MaxValue, double.MinValue}).ToArray();
-      var clusters = contourCluster.GetClusterValues(cpd.Dataset, cpd.AllIndices).ToArray();
-      var targetvalues = cpd.Dataset.GetDoubleValues(target).ToArray();
-      foreach (var i in cpd.AllIndices) {
-        var cl = clusters[i] - 1;
-        var clv = targetvalues[i];
-        if (borders[cl][0] > clv) borders[cl][0] = clv;
-        if (borders[cl][1] < clv) borders[cl][1] = clv;
-      }
-
-      contourNames = new Dictionary<int, string>();
-      for (var i = 0; i < contours; i++)
-        contourNames.Add(i, "[" + borders[i][0] + ";" + borders[i][1] + "]");
-    }
-
-    private static Color ConvertTotalToRgb(double low, double high, double cell) {
-      var colorGradient = ColorGradient.Colors;
-      var range = high - low;
-      var h = Math.Min(cell / range * colorGradient.Count, colorGradient.Count - 1);
-      return colorGradient[(int)h];
+      var q = (double)contourNr / noContours;  // q in [0,1]
+      var c = q < 0.5 ? Color.FromArgb((int)(q * 2 * 255), 255, 0) : Color.FromArgb(255, (int)((1 - q) * 2 * 255), 0);
+      return c;
+    }
+
+    private static string GetContourName(double value, double min, double max, int noContours) {
+      var size = (max - min) / noContours;
+      var contourNr = (int)((value - min) / size);
+      return GetContourName(contourNr, min, max, noContours);
+    }
+
+    private static string GetContourName(int i, double min, double max, int noContours) {
+      var size = (max - min) / noContours;
+      return "[" + (min + i * size) + ";" + (min + (i + 1) * size) + ")";
     }
     #endregion