Changeset 12607 for branches/GBT-trunkintegration/HeuristicLab.Algorithms.DataAnalysis/3.4/GradientBoostedTrees/GradientBoostedTreesAlgorithmStatic.cs

Timestamp:

07/06/15 15:20:28 (9 years ago)

Author:

gkronber

Message:

#2261: also use line search function for the initial estimation f0, changed logistic regression loss function to match description in GBM paper, comments and code improvements

File:

• branches/GBT-trunkintegration/HeuristicLab.Algorithms.DataAnalysis/3.4/GradientBoostedTrees/GradientBoostedTreesAlgorithmStatic.cs (modified) (1 diff)

branches/GBT-trunkintegration/HeuristicLab.Algorithms.DataAnalysis/3.4/GradientBoostedTrees/GradientBoostedTreesAlgorithmStatic.cs

@@ -84 +84 @@
         activeIdx = Enumerable.Range(0, nRows).ToArray();
 
-        // prepare arrays (allocate only once)
-        double f0 = y.Average(); // default prediction (constant)
+        var zeros = Enumerable.Repeat(0.0, nRows);
+        var ones = Enumerable.Repeat(1.0, nRows);
+        double f0 = lossFunction.GetLineSearchFunc(y, zeros, ones)(activeIdx, 0, nRows - 1); // initial constant value (mean for squared errors)
         pred = Enumerable.Repeat(f0, nRows).ToArray();
         predTest = Enumerable.Repeat(f0, problemData.TestIndices.Count()).ToArray();