Changeset 18114 for branches/3140_NumberSymbol/HeuristicLab.Algorithms.DataAnalysis

Timestamp:

12/13/21 10:25:35 (3 years ago)

Author:

gkronber

Message:

#3140: made several more changes while reviewing the branch.

Location:

branches/3140_NumberSymbol/HeuristicLab.Algorithms.DataAnalysis/3.4

Files:

• GradientBoostedTrees/RegressionTreeModel.cs (modified) (2 diffs)
• NonlinearRegression/NonlinearRegression.cs (modified) (3 diffs)
• RandomForest/RandomForestModelAlglib_3_7.cs (modified) (3 diffs)
• RandomForest/RandomForestModelFull.cs (modified) (3 diffs)
• TimeSeries/AutoregressiveModeling.cs (modified) (1 diff)

branches/3140_NumberSymbol/HeuristicLab.Algorithms.DataAnalysis/3.4/GradientBoostedTrees/RegressionTreeModel.cs

@@ -239 +239 @@
     }
 
-    private ISymbolicExpressionTreeNode CreateSymbolicRegressionTreeRecursive(TreeNode[] treeNodes, int nodeIdx, VariableCondition varCondSy, Number constSy) {
+    private ISymbolicExpressionTreeNode CreateSymbolicRegressionTreeRecursive(TreeNode[] treeNodes, int nodeIdx, VariableCondition varCondSy, Number numSy) {
       var curNode = treeNodes[nodeIdx];
       if (curNode.VarName == TreeNode.NO_VARIABLE) {
-        var node = (NumberTreeNode)constSy.CreateTreeNode();
+        var node = (NumberTreeNode)numSy.CreateTreeNode();
         node.Value = curNode.Val;
         return node;
@@ -250 +250 @@
         node.Threshold = curNode.Val;
 
-        var left = CreateSymbolicRegressionTreeRecursive(treeNodes, curNode.LeftIdx, varCondSy, constSy);
-        var right = CreateSymbolicRegressionTreeRecursive(treeNodes, curNode.RightIdx, varCondSy, constSy);
+        var left = CreateSymbolicRegressionTreeRecursive(treeNodes, curNode.LeftIdx, varCondSy, numSy);
+        var right = CreateSymbolicRegressionTreeRecursive(treeNodes, curNode.RightIdx, varCondSy, numSy);
         node.AddSubtree(left);
         node.AddSubtree(right);

branches/3140_NumberSymbol/HeuristicLab.Algorithms.DataAnalysis/3.4/NonlinearRegression/NonlinearRegression.cs

@@ -123 +123 @@
       : base() {
       Problem = new RegressionProblem();
-      Parameters.Add(new FixedValueParameter<StringValue>(ModelStructureParameterName, "The function for which the parameters must be fit (only numeric constants are tuned).", new StringValue("<num> * x*x + 0.0")));
-      Parameters.Add(new FixedValueParameter<IntValue>(IterationsParameterName, "The maximum number of iterations for constants optimization.", new IntValue(200)));
+      Parameters.Add(new FixedValueParameter<StringValue>(ModelStructureParameterName, "The expression for which the <num> parameters should be fit.", new StringValue("<num> * x*x + 0.0")));
+      Parameters.Add(new FixedValueParameter<IntValue>(IterationsParameterName, "The maximum number of iterations for parameter optimization.", new IntValue(200)));
       Parameters.Add(new FixedValueParameter<IntValue>(RestartsParameterName, "The number of independent random restarts (>0)", new IntValue(10)));
       Parameters.Add(new FixedValueParameter<IntValue>(SeedParameterName, "The PRNG seed value.", new IntValue()));
@@ -210 +210 @@
 
     /// <summary>
-    /// Fits a model to the data by optimizing the numeric constants.
+    /// Fits a model to the data by optimizing parameters.
     /// Model is specified as infix expression containing variable names and numbers. 
-    /// The starting point for the numeric constants is initialized randomly if a random number generator is specified (~N(0,1)). Otherwise the user specified constants are
+    /// The starting values for the parameters are initialized randomly if a random number generator is specified (~N(0,1)). Otherwise the user specified values are
     /// used as a starting point. 
     /// </summary>-
     /// <param name="problemData">Training and test data</param>
     /// <param name="modelStructure">The function as infix expression</param>
-    /// <param name="maxIterations">Number of constant optimization iterations (using Levenberg-Marquardt algorithm)</param>
-    /// <param name="random">Optional random number generator for random initialization of numeric constants.</param>
+    /// <param name="maxIterations">Number of Levenberg-Marquardt iterations</param>
+    /// <param name="random">Optional random number generator for random initialization of parameters.</param>
     /// <returns></returns>
     public static ISymbolicRegressionSolution CreateRegressionSolution(IRegressionProblemData problemData, string modelStructure, int maxIterations, bool applyLinearScaling, IRandom rand = null) {
@@ -265 +265 @@
       if (!SymbolicRegressionParameterOptimizationEvaluator.CanOptimizeParameters(tree)) throw new ArgumentException("The optimizer does not support the specified model structure.");
 
-      // initialize constants randomly
+      // initialize parameters randomly
       if (rand != null) {
         foreach (var node in tree.IterateNodesPrefix().OfType<NumberTreeNode>()) {

branches/3140_NumberSymbol/HeuristicLab.Algorithms.DataAnalysis/3.4/RandomForest/RandomForestModelAlglib_3_7.cs

@@ -232 +232 @@
     }
 
-    private ISymbolicExpressionTreeNode CreateRegressionTreeRec(double[] trees, int offset, int k, Number constSy, VariableCondition varCondSy) {
+    private ISymbolicExpressionTreeNode CreateRegressionTreeRec(double[] trees, int offset, int k, Number numSy, VariableCondition varCondSy) {
 
       // alglib source for evaluation of one tree (dfprocessinternal)
@@ -261 +261 @@
       // }
 
-      if ((double)(trees[k]) == (double)(-1)) {
-        var numNode = (NumberTreeNode)constSy.CreateTreeNode();
+      if (trees[k] == -1) {
+        var numNode = (NumberTreeNode)numSy.CreateTreeNode();
         numNode.Value = trees[k + 1];
         return numNode;
@@ -271 +271 @@
         condNode.Slope = double.PositiveInfinity;
 
-        var left = CreateRegressionTreeRec(trees, offset, k + 3, constSy, varCondSy);
-        var right = CreateRegressionTreeRec(trees, offset, offset + (int)Math.Round(trees[k + 2]), constSy, varCondSy);
+        var left = CreateRegressionTreeRec(trees, offset, k + 3, numSy, varCondSy);
+        var right = CreateRegressionTreeRec(trees, offset, offset + (int)Math.Round(trees[k + 2]), numSy, varCondSy);
 
         condNode.AddSubtree(left); // not 100% correct because interpreter uses: if(x <= thres) left() else right() and RF uses if(x < thres) left() else right() (see above)

branches/3140_NumberSymbol/HeuristicLab.Algorithms.DataAnalysis/3.4/RandomForest/RandomForestModelFull.cs

@@ -211 +211 @@
     }
 
-    private ISymbolicExpressionTreeNode CreateRegressionTreeRec(double[] trees, int offset, int k, Number constSy, VariableCondition varCondSy) {
+    private ISymbolicExpressionTreeNode CreateRegressionTreeRec(double[] trees, int offset, int k, Number numSy, VariableCondition varCondSy) {
 
       // alglib source for evaluation of one tree (dfprocessinternal)
@@ -240 +240 @@
       // }
 
-      if ((double)(trees[k]) == (double)(-1)) {
-        var numNode = (NumberTreeNode)constSy.CreateTreeNode();
+      if (trees[k] == -1) {
+        var numNode = (NumberTreeNode)numSy.CreateTreeNode();
         numNode.Value = trees[k + 1];
         return numNode;
@@ -250 +250 @@
         condNode.Slope = double.PositiveInfinity;
 
-        var left = CreateRegressionTreeRec(trees, offset, k + 3, constSy, varCondSy);
-        var right = CreateRegressionTreeRec(trees, offset, offset + (int)Math.Round(trees[k + 2]), constSy, varCondSy);
+        var left = CreateRegressionTreeRec(trees, offset, k + 3, numSy, varCondSy);
+        var right = CreateRegressionTreeRec(trees, offset, offset + (int)Math.Round(trees[k + 2]), numSy, varCondSy);
 
         condNode.AddSubtree(left); // not 100% correct because interpreter uses: if(x <= thres) left() else right() and RF uses if(x < thres) left() else right() (see above)

branches/3140_NumberSymbol/HeuristicLab.Algorithms.DataAnalysis/3.4/TimeSeries/AutoregressiveModeling.cs

@@ -104 +104 @@
       int nRows = inputMatrix.GetLength(0);
       int nFeatures = inputMatrix.GetLength(1) - 1;
-      double[] coefficients = new double[nFeatures + 1]; // last coefficient is for the constant
+      double[] coefficients = new double[nFeatures + 1]; // last coefficient is for the offset
 
       int retVal = 1;