Changeset 196 for trunk/sources/HeuristicLab.DataAnalysis

Timestamp:

04/25/08 16:09:38 (17 years ago)

Author:

gkronber

Message:

fixed caching of mean and range in dataset for another nice speed improvement in GP evaluation.

File:

• trunk/sources/HeuristicLab.DataAnalysis/Dataset.cs (modified) (5 diffs)

trunk/sources/HeuristicLab.DataAnalysis/Dataset.cs

@@ -39 +39 @@
     private double[] samples;
     private int rows;
+    Dictionary<int, Dictionary<int, double>>[] cachedMeans;
+    Dictionary<int, Dictionary<int, double>>[] cachedRanges;
 
     public int Rows {
@@ -50 +52 @@
       set { columns = value; }
     }
-    private Dictionary<int, double[]>[] ranges;
-    private Dictionary<int, double[]>[] means;
 
     public double GetValue(int i, int j) {
@@ -94 +94 @@
       // keep a means and ranges dictionary for each column (possible target variable) of the dataset.
 
-      means = new Dictionary<int, double[]>[columns];
-      ranges = new Dictionary<int, double[]>[columns];
+      cachedMeans = new Dictionary<int, Dictionary<int, double>>[columns];
+      cachedRanges = new Dictionary<int, Dictionary<int, double>>[columns];
 
       for(int i = 0; i < columns; i++) {
-        means[i] = new Dictionary<int, double[]>();
-        ranges[i] = new Dictionary<int, double[]>();
+        cachedMeans[i] = new Dictionary<int, Dictionary<int, double>>();
+        cachedRanges[i] = new Dictionary<int, Dictionary<int, double>>();
       }
     }
@@ -201 +201 @@
 
     public double GetMean(int column, int from, int to) {
-      double[] values = new double[to - from + 1];
-      for(int sample = from; sample <= to; sample++) {
-        values[sample - from] = GetValue(sample, column);
-      }
-
-      return Statistics.Mean(values);
+      if(!cachedMeans[column].ContainsKey(from) || !cachedMeans[column][from].ContainsKey(to)) {
+        double[] values = new double[to - from + 1];
+        for(int sample = from; sample <= to; sample++) {
+          values[sample - from] = GetValue(sample, column);
+        }
+        double mean = Statistics.Mean(values);
+        if(!cachedMeans[column].ContainsKey(from)) cachedMeans[column][from] = new Dictionary<int, double>();
+        cachedMeans[column][from][to] = mean;
+        return mean;
+      } else {
+        return cachedMeans[column][from][to];
+      }
     }
 
@@ -214 +220 @@
 
     public double GetRange(int column, int from, int to) {
-      double[] values = new double[to - from + 1];
-      for(int sample = from; sample <= to; sample++) {
-        values[sample - from] = GetValue(sample, column);
-      }
-
-      return Statistics.Range(values);
+      if(!cachedRanges[column].ContainsKey(from) || !cachedRanges[column][from].ContainsKey(to)) {
+        double[] values = new double[to - from + 1];
+        for(int sample = from; sample <= to; sample++) {
+          values[sample - from] = GetValue(sample, column);
+        }
+        double range = Statistics.Range(values);
+        if(!cachedRanges[column].ContainsKey(from)) cachedRanges[column][from] = new Dictionary<int, double>();
+        cachedRanges[column][from][to] = range;
+        return range;
+      } else {
+        return cachedRanges[column][from][to];
+      }
     }
   }