Changeset 15485 for branches/Weighted TSNE

Timestamp:

11/22/17 11:06:08 (7 years ago)

Author:

bwerth

Message:

#2850 fixed comment in TSNEAlgorithm; private methods in TSNE less dependent on array type

Location:

branches/Weighted TSNE/3.4/TSNE

Files:

• TSNEAlgorithm.cs (modified) (2 diffs)
• TSNEStatic.cs (modified) (9 diffs)

branches/Weighted TSNE/3.4/TSNE/TSNEAlgorithm.cs

@@ -285 +285 @@
         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;
@@ -296 +298 @@
         }
 
-        //data = allindices.Select(row => allowedInputVariables.Select(col => dataset.GetDoubleValue(col, row)).ToArray()).ToArray();
         if (Normalization) data = NormalizeInputData(data);
         state = TSNEStatic<double[]>.CreateState(data, DistanceFunction, random, NewDimensions, Perplexity, Theta, StopLyingIteration, MomentumSwitchIteration, InitialMomentum, FinalMomentum, Eta, RandomInitialization);

branches/Weighted TSNE/3.4/TSNE/TSNEStatic.cs

@@ -170 +170 @@
       public TSNEState(bool deserializing) { }
 
-      public TSNEState(T[] data, IDistance<T> distance, IRandom random, int newDimensions, double perplexity,
+      public TSNEState(IReadOnlyList<T> data, IDistance<T> distance, IRandom random, int newDimensions, double perplexity,
         double theta, int stopLyingIter, int momSwitchIter, double momentum, double finalMomentum, double eta, bool randomInit) {
         this.distance = distance;
@@ -184 +184 @@
 
         // initialize
-        noDatapoints = data.Length;
+        noDatapoints = data.Count;
         if (noDatapoints - 1 < 3 * perplexity)
           throw new ArgumentException("Perplexity too large for the number of data points!");
@@ -230 +230 @@
 
       #region Helpers
-      private static void CalculateApproximateSimilarities(T[] data, IDistance<T> distance, double perplexity, out int[] rowP, out int[] colP, out double[] valP) {
+      private static void CalculateApproximateSimilarities(IReadOnlyList<T> data, IDistance<T> distance, double perplexity, out int[] rowP, out int[] colP, out double[] valP) {
         // Compute asymmetric pairwise input similarities
         ComputeGaussianPerplexity(data, distance, out rowP, out colP, out valP, perplexity, (int) (3 * perplexity));
@@ -241 +241 @@
         valP = sValP;
         var sumP = .0;
-        for (var i = 0; i < rowP[data.Length]; i++) sumP += valP[i];
-        for (var i = 0; i < rowP[data.Length]; i++) valP[i] /= sumP;
-      }
-
-      private static double[,] CalculateExactSimilarites(T[] data, IDistance<T> distance, double perplexity) {
+        for (var i = 0; i < rowP[data.Count]; i++) sumP += valP[i];
+        for (var i = 0; i < rowP[data.Count]; i++) valP[i] /= sumP;
+      }
+      private static double[,] CalculateExactSimilarites(IReadOnlyList<T> data, IDistance<T> distance, double perplexity) {
         // Compute similarities
-        var p = new double[data.Length, data.Length];
+        var p = new double[data.Count, data.Count];
         ComputeGaussianPerplexity(data, distance, p, perplexity);
         // Symmetrize input similarities
-        for (var n = 0; n < data.Length; n++) {
-          for (var m = n + 1; m < data.Length; m++) {
+        for (var n = 0; n < data.Count; n++) {
+          for (var m = n + 1; m < data.Count; m++) {
             p[n, m] += p[m, n];
             p[m, n] = p[n, m];
@@ -257 +256 @@
         }
         var sumP = .0;
-        for (var i = 0; i < data.Length; i++) {
-          for (var j = 0; j < data.Length; j++) {
+        for (var i = 0; i < data.Count; i++) {
+          for (var j = 0; j < data.Count; j++) {
             sumP += p[i, j];
           }
         }
-        for (var i = 0; i < data.Length; i++) {
-          for (var j = 0; j < data.Length; j++) {
+        for (var i = 0; i < data.Count; i++) {
+          for (var j = 0; j < data.Count; j++) {
             p[i, j] /= sumP;
           }
@@ -269 +268 @@
         return p;
       }
-
       private static void ComputeGaussianPerplexity(IReadOnlyList<T> x, IDistance<T> distance, out int[] rowP, out int[] colP, out double[] valP, double perplexity, int k) {
         if (perplexity > k) throw new ArgumentException("Perplexity should be lower than k!");
@@ -351 +349 @@
         }
       }
-      private static void ComputeGaussianPerplexity(T[] x, IDistance<T> distance, double[,] p, double perplexity) {
+      private static void ComputeGaussianPerplexity(IReadOnlyList<T> x, IDistance<T> distance, double[,] p, double perplexity) {
         // Compute the distance matrix
         var dd = ComputeDistances(x, distance);
 
-        var n = x.Length;
+        var n = x.Count;
         // Compute the Gaussian kernel row by row
         for (var i = 0; i < n; i++) {
@@ -411 +409 @@
         }
       }
-      private static double[][] ComputeDistances(T[] x, IDistance<T> distance) {
-        var res = new double[x.Length][];
-        for (var r = 0; r < x.Length; r++) {
-          var rowV = new double[x.Length];
+      private static double[][] ComputeDistances(IReadOnlyList<T> x, IDistance<T> distance) {
+        var res = new double[x.Count][];
+        for (var r = 0; r < x.Count; r++) {
+          var rowV = new double[x.Count];
           // all distances must be symmetric 
           for (var c = 0; c < r; c++) {
@@ -420 +418 @@
           }
           rowV[r] = 0.0; // distance to self is zero for all distances
-          for (var c = r + 1; c < x.Length; c++) {
+          for (var c = r + 1; c < x.Count; c++) {
             rowV[c] = distance.Get(x[r], x[c]);
           }