Changeset 14015 for trunk

Timestamp:

07/07/16 12:51:31 (8 years ago)

Author:

gkronber

Message:

#2612: added NaN handling for the evaluation of regression tree models (GBT)

Location:

trunk/sources/HeuristicLab.Algorithms.DataAnalysis/3.4

Files:

• GradientBoostedTrees/RegressionTreeModel.cs (modified) (1 diff)
• MctsSymbolicRegression/ExpressionEvaluator.cs (modified) (3 diffs)

trunk/sources/HeuristicLab.Algorithms.DataAnalysis/3.4/GradientBoostedTrees/RegressionTreeModel.cs

@@ -170 +170 @@
         if (node.VarName == TreeNode.NO_VARIABLE)
           return node.Val;
-        if (columnCache[nodeIdx] == null) {
+        if (columnCache[nodeIdx] == null || double.IsNaN(columnCache[nodeIdx][row])) {
           if (node.WeightLeft.IsAlmost(-1.0)) throw new InvalidOperationException("Cannot calculate partial dependence for trees loaded from older versions of HeuristicLab.");
           // weighted average for partial dependence plot (recursive here because we need to calculate both sub-trees)

trunk/sources/HeuristicLab.Algorithms.DataAnalysis/3.4/MctsSymbolicRegression/ExpressionEvaluator.cs

@@ -89 +89 @@
 
     // pred must be allocated by the caller
-    // if adjustOffsetForLogAndExp is set to true we determine c in log(c + f(x)) to make sure that c + f(x) is positive
-    public void Exec(byte[] code, double[][] vars, double[] consts, double[] pred, bool adjustOffsetForLogAndExp = false) {
+    // if adjustParameters is set to true we determine parameters in function to make sure that the function output is valid
+    // e.g. in log(c + f(x)) to make sure that c + f(x) is positive
+    public void Exec(byte[] code, double[][] vars, double[] consts, double[] pred, bool adjustParameters = false) {
       Contract.Assert(pred != null && pred.Length >= vLen);
       int topOfStack = -1;
@@ -153 +154 @@
             }
           case (byte)OpCodes.Log: {
-              if (adjustOffsetForLogAndExp) {
+              if (adjustParameters) {
                 // here we assume that the last used parameter is c in log(f(x) + c)
                 // this must match actions for producing code in the automaton!
@@ -174 +175 @@
             }
           case (byte)OpCodes.Exp: {
-              if (adjustOffsetForLogAndExp) {
+              if (adjustParameters) {
                 // here we assume that the last used parameter is c in exp(f(x) * c)
                 // this must match actions for producing code in the automaton!