Changeset 14518 for branches/TSNE/HeuristicLab.Algorithms.DataAnalysis/3.4/TSNE/TSNEAnalysis.cs

Timestamp:

12/22/16 10:08:25 (7 years ago)

Author:

bwerth

Message:

#2700 TSNEAnalysis is now a BasicAlg, hid some Parameters, added optional data normalization to make TSNE scaling-invariant

File:

• branches/TSNE/HeuristicLab.Algorithms.DataAnalysis/3.4/TSNE/TSNEAnalysis.cs (modified) (11 diffs)

branches/TSNE/HeuristicLab.Algorithms.DataAnalysis/3.4/TSNE/TSNEAnalysis.cs

@@ -20 +20 @@
 #endregion
 
+using System;
 using System.Collections.Generic;
 using System.Drawing;
 using System.Linq;
+using System.Threading;
 using HeuristicLab.Analysis;
 using HeuristicLab.Common;
@@ -28 +30 @@
 using HeuristicLab.Data;
 using HeuristicLab.Encodings.RealVectorEncoding;
+using HeuristicLab.Optimization;
 using HeuristicLab.Parameters;
 using HeuristicLab.Persistence.Default.CompositeSerializers.Storable;
@@ -40 +43 @@
   [Creatable(CreatableAttribute.Categories.DataAnalysis, Priority = 100)]
   [StorableClass]
-  public sealed class TSNEAnalysis : FixedDataAnalysisAlgorithm<IRegressionProblem> {
-
+  public sealed class TSNEAnalysis : BasicAlgorithm {
+
+    public override Type ProblemType
+    {
+      get { return typeof(IDataAnalysisProblem); }
+    }
+    public new IDataAnalysisProblem Problem
+    {
+      get { return (IDataAnalysisProblem)base.Problem; }
+      set { base.Problem = value; }
+    }
     #region Resultnames
     private const string ScatterPlotResultName = "Scatterplot";
@@ -61 +73 @@
     private const string SeedParameterName = "Seed";
     private const string ClassesParameterName = "ClassNames";
+    private const string NormalizationParameterName = "Normalization";
     #endregion
 
@@ -115 +128 @@
     {
       get { return Parameters[ClassesParameterName] as IFixedValueParameter<StringValue>; }
+    }
+    public IFixedValueParameter<BoolValue> NormalizationParameter
+    {
+      get { return Parameters[NormalizationParameterName] as IFixedValueParameter<BoolValue>; }
     }
     #endregion
@@ -174 +191 @@
       get { return ClassesParameter.Value.Value; }
     }
-
+    public bool Normalization
+    {
+      get { return NormalizationParameter.Value.Value; }
+    }
     [Storable]
     public TSNE<RealVector> tsne;
@@ -191 +211 @@
       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)));
-      Parameters.Add(new FixedValueParameter<IntValue>(StopLyingIterationParameterName, "Number of iterations after which p is no longer approximated", new IntValue(250)));
-      Parameters.Add(new FixedValueParameter<IntValue>(MomentumSwitchIterationParameterName, "Number of iterations after which the momentum in the gradient descent is switched", new IntValue(250)));
+      Parameters.Add(new FixedValueParameter<IntValue>(StopLyingIterationParameterName, "Number of iterations after which p is no longer approximated", new IntValue(0)));
+      Parameters.Add(new FixedValueParameter<IntValue>(MomentumSwitchIterationParameterName, "Number of iterations after which the momentum in the gradient descent is switched", new IntValue(0)));
       Parameters.Add(new FixedValueParameter<DoubleValue>(InitialMomentumParameterName, "The initial momentum in the gradient descent", new DoubleValue(0.5)));
       Parameters.Add(new FixedValueParameter<DoubleValue>(FinalMomentumParameterName, "The final momentum", new DoubleValue(0.8)));
@@ -199 +219 @@
       Parameters.Add(new FixedValueParameter<IntValue>(SeedParameterName, "The seed used if it should not be random", new IntValue(0)));
       Parameters.Add(new FixedValueParameter<StringValue>(ClassesParameterName, "name of the column specifying the class lables of each data point. \n if the lable column can not be found Training/Test is used as labels", new StringValue("none")));
-    }
-    #endregion
-
-    protected override void Run() {
-      var data = CalculateProjectedData(Problem.ProblemData);
-      var lowDimData = new DoubleMatrix(data);
-    }
+      Parameters.Add(new FixedValueParameter<BoolValue>(NormalizationParameterName, "Wether the data should be zero centered and have variance of 1 for each variable, so different scalings are ignored", new BoolValue(true)));
+
+      MomentumSwitchIterationParameter.Hidden = true;
+      InitialMomentumParameter.Hidden = true;
+      FinalMomentumParameter.Hidden = true;
+      StopLyingIterationParameter.Hidden = true;
+      EtaParameter.Hidden = true;
+    }
+    #endregion
 
     public override void Stop() {
@@ -212 +234 @@
     }
 
+    protected override void Run(CancellationToken cancellationToken) {
+      var data = CalculateProjectedData(Problem.ProblemData);
+      var lowDimData = new DoubleMatrix(data);
+    }
+
     private double[,] CalculateProjectedData(IDataAnalysisProblemData problemData) {
-      var DataRowNames = new Dictionary<string, List<int>>();
+      var dataRowNames = new Dictionary<string, List<int>>();
       var rows = new Dictionary<string, ScatterPlotDataRow>();
 
@@ -220 +247 @@
           var classes = problemData.Dataset.GetStringValues(Classes).ToArray();
           for (int i = 0; i < classes.Length; i++) {
-            if (!DataRowNames.ContainsKey(classes[i])) DataRowNames.Add(classes[i], new List<int>());
-            DataRowNames[classes[i]].Add(i); //always succeeds
+            if (!dataRowNames.ContainsKey(classes[i])) dataRowNames.Add(classes[i], new List<int>());
+            dataRowNames[classes[i]].Add(i); //always succeeds
           }
         } else if ((problemData.Dataset as Dataset).VariableHasType<double>(Classes)) {
@@ -228 +255 @@
           var min = classValues.Min() - 0.1;
           var contours = 8;
-          for (int i = 0; i < contours; i++) {
+          for (var i = 0; i < contours; i++) {
             var name = GetContourName(i, min, max, contours);
-            DataRowNames.Add(name, new List<int>());
+            dataRowNames.Add(name, new List<int>());
             rows.Add(name, new ScatterPlotDataRow(name, "", new List<Point2D<double>>()));
             rows[name].VisualProperties.Color = GetHeatMapColor(i, contours);
-            rows[name].VisualProperties.PointSize = i+3;
+            rows[name].VisualProperties.PointSize = i + 3;
           }
           for (int i = 0; i < classValues.Length; i++) {
-            DataRowNames[GetContourName(classValues[i], min, max, contours)].Add(i); //always succeeds
+            dataRowNames[GetContourName(classValues[i], min, max, contours)].Add(i); //always succeeds
           }
 
         }
 
-
       } else {
-        DataRowNames.Add("Training", problemData.TrainingIndices.ToList());
-        DataRowNames.Add("Test", problemData.TestIndices.ToList());
+        dataRowNames.Add("Training", problemData.TrainingIndices.ToList());
+        dataRowNames.Add("Test", problemData.TestIndices.ToList());
       }
 
       var random = SetSeedRandomly ? new MersenneTwister() : new MersenneTwister(Seed);
-      tsne = new TSNE<RealVector>(Distance, random, Results, MaxIterations, StopLyingIteration, MomentumSwitchIteration, InitialMomentum, FinalMomentum, Eta, DataRowNames, rows);
+      tsne = new TSNE<RealVector>(Distance, random, Results, MaxIterations, StopLyingIteration, MomentumSwitchIteration, InitialMomentum, FinalMomentum, Eta, dataRowNames, rows);
       var dataset = problemData.Dataset;
       var allowedInputVariables = problemData.AllowedInputVariables.ToArray();
       var data = new RealVector[dataset.Rows];
       for (var row = 0; row < dataset.Rows; row++) data[row] = new RealVector(allowedInputVariables.Select(col => dataset.GetDoubleValue(col, row)).ToArray());
+
+      if (Normalization) {
+        data = NormalizeData(data);
+      }
+
       return tsne.Run(data, NewDimensions, Perplexity, Theta);
+    }
+
+    private RealVector[] NormalizeData(RealVector[] data) {
+      var n = data[0].Length;
+      var mean = new double[n];
+      var sd = new double[n];
+      var nData = new RealVector[data.Length];
+      for (var i = 0; i < n; i++) {
+        var i1 = i;
+        sd[i] = Enumerable.Range(0, data.Length).Select(x => data[x][i1]).StandardDeviation();
+        mean[i] = Enumerable.Range(0, data.Length).Select(x => data[x][i1]).Average();
+      }
+      for (int i = 0; i < data.Length; i++) {
+        nData[i] = new RealVector(n);
+        for (int j = 0; j < n; j++) {
+          nData[i][j] = (data[i][j] - mean[j]) / sd[j];
+        }
+      }
+      return nData;
+
+
     }