Changeset 8786 for trunk/sources/HeuristicLab.Algorithms.DataAnalysis/3.4/RandomForest/RandomForestClassification.cs

Timestamp:

10/11/12 10:44:57 (12 years ago)

Author:

mkommend

Message:

#1968: Added seed and m parameter to random forest modeling.

File:

• trunk/sources/HeuristicLab.Algorithms.DataAnalysis/3.4/RandomForest/RandomForestClassification.cs (modified) (9 diffs)

trunk/sources/HeuristicLab.Algorithms.DataAnalysis/3.4/RandomForest/RandomForestClassification.cs

@@ -26 +26 @@
 using HeuristicLab.Core;
 using HeuristicLab.Data;
-using HeuristicLab.Encodings.SymbolicExpressionTreeEncoding;
 using HeuristicLab.Optimization;
+using HeuristicLab.Parameters;
 using HeuristicLab.Persistence.Default.CompositeSerializers.Storable;
 using HeuristicLab.Problems.DataAnalysis;
-using HeuristicLab.Problems.DataAnalysis.Symbolic;
-using HeuristicLab.Problems.DataAnalysis.Symbolic.Regression;
-using HeuristicLab.Parameters;
 
 namespace HeuristicLab.Algorithms.DataAnalysis {
@@ -45 +42 @@
     private const string NumberOfTreesParameterName = "Number of trees";
     private const string RParameterName = "R";
+    private const string MParameterName = "M";
+    private const string SeedParameterName = "Seed";
+    private const string SetSeedRandomlyParameterName = "SetSeedRandomly";
+
     #region parameter properties
-    public IValueParameter<IntValue> NumberOfTreesParameter {
-      get { return (IValueParameter<IntValue>)Parameters[NumberOfTreesParameterName]; }
+    public IFixedValueParameter<IntValue> NumberOfTreesParameter {
+      get { return (IFixedValueParameter<IntValue>)Parameters[NumberOfTreesParameterName]; }
     }
-    public IValueParameter<DoubleValue> RParameter {
-      get { return (IValueParameter<DoubleValue>)Parameters[RParameterName]; }
+    public IFixedValueParameter<DoubleValue> RParameter {
+      get { return (IFixedValueParameter<DoubleValue>)Parameters[RParameterName]; }
+    }
+    public IFixedValueParameter<DoubleValue> MParameter {
+      get { return (IFixedValueParameter<DoubleValue>)Parameters[MParameterName]; }
+    }
+    public IFixedValueParameter<IntValue> SeedParameter {
+      get { return (IFixedValueParameter<IntValue>)Parameters[SeedParameterName]; }
+    }
+    public IFixedValueParameter<BoolValue> SetSeedRandomlyParameter {
+      get { return (IFixedValueParameter<BoolValue>)Parameters[SetSeedRandomlyParameterName]; }
     }
     #endregion
@@ -62 +72 @@
       set { RParameter.Value.Value = value; }
     }
+    public double M {
+      get { return MParameter.Value.Value; }
+      set { MParameter.Value.Value = value; }
+    }
+    public int Seed {
+      get { return SeedParameter.Value.Value; }
+      set { SeedParameter.Value.Value = value; }
+    }
+    public bool SetSeedRandomly {
+      get { return SetSeedRandomlyParameter.Value.Value; }
+      set { SetSeedRandomlyParameter.Value.Value = value; }
+    }
     #endregion
+
     [StorableConstructor]
     private RandomForestClassification(bool deserializing) : base(deserializing) { }
@@ -68 +91 @@
       : base(original, cloner) {
     }
+
     public RandomForestClassification()
       : base() {
       Parameters.Add(new FixedValueParameter<IntValue>(NumberOfTreesParameterName, "The number of trees in the forest. Should be between 50 and 100", new IntValue(50)));
       Parameters.Add(new FixedValueParameter<DoubleValue>(RParameterName, "The ratio of the training set that will be used in the construction of individual trees (0<r<=1). Should be adjusted depending on the noise level in the dataset in the range from 0.66 (low noise) to 0.05 (high noise). This parameter should be adjusted to achieve good generalization error.", new DoubleValue(0.3)));
+      Parameters.Add(new FixedValueParameter<DoubleValue>(MParameterName, "The ratio of features that will be used in the construction of individual trees (0<m<=1)", new DoubleValue(0.5)));
+      Parameters.Add(new FixedValueParameter<IntValue>(SeedParameterName, "The random seed used to initialize the new pseudo random number generator.", new IntValue(0)));
+      Parameters.Add(new FixedValueParameter<BoolValue>(SetSeedRandomlyParameterName, "True if the random seed should be set to a random value, otherwise false.", new BoolValue(true)));
       Problem = new ClassificationProblem();
     }
+
     [StorableHook(HookType.AfterDeserialization)]
-    private void AfterDeserialization() { }
+    private void AfterDeserialization() {
+      if (!Parameters.ContainsKey(MParameterName))
+        Parameters.Add(new FixedValueParameter<DoubleValue>(MParameterName, "The ratio of features that will be used in the construction of individual trees (0<m<=1)", new DoubleValue(0.5)));
+      if (!Parameters.ContainsKey(SeedParameterName))
+        Parameters.Add(new FixedValueParameter<IntValue>(SeedParameterName, "The random seed used to initialize the new pseudo random number generator.", new IntValue(0)));
+      if (!Parameters.ContainsKey((SetSeedRandomlyParameterName)))
+        Parameters.Add(new FixedValueParameter<BoolValue>(SetSeedRandomlyParameterName, "True if the random seed should be set to a random value, otherwise false.", new BoolValue(true)));
+    }
 
     public override IDeepCloneable Clone(Cloner cloner) {
@@ -84 +119 @@
     protected override void Run() {
       double rmsError, relClassificationError, outOfBagRmsError, outOfBagRelClassificationError;
-      var solution = CreateRandomForestClassificationSolution(Problem.ProblemData, NumberOfTrees, R, out rmsError, out relClassificationError, out outOfBagRmsError, out outOfBagRelClassificationError);
+      if (SetSeedRandomly) Seed = new System.Random().Next();
+
+      var solution = CreateRandomForestClassificationSolution(Problem.ProblemData, NumberOfTrees, R, M, Seed, out rmsError, out relClassificationError, out outOfBagRmsError, out outOfBagRelClassificationError);
       Results.Add(new Result(RandomForestClassificationModelResultName, "The random forest classification solution.", solution));
       Results.Add(new Result("Root mean square error", "The root of the mean of squared errors of the random forest regression solution on the training set.", new DoubleValue(rmsError)));
@@ -92 +129 @@
     }
 
-    public static IClassificationSolution CreateRandomForestClassificationSolution(IClassificationProblemData problemData, int nTrees, double r,
+    public static IClassificationSolution CreateRandomForestClassificationSolution(IClassificationProblemData problemData, int nTrees, double r, double m, int seed,
       out double rmsError, out double relClassificationError, out double outOfBagRmsError, out double outOfBagRelClassificationError) {
+      if (r <= 0 || r > 1) throw new ArgumentException("The R parameter in the random forest regression must be between 0 and 1.");
+      if (m <= 0 || m > 1) throw new ArgumentException("The M parameter in the random forest regression must be between 0 and 1.");
+
+      lock (alglib.math.rndobject) {
+        alglib.math.rndobject = new System.Random(seed);
+      }
+
       Dataset dataset = problemData.Dataset;
       string targetVariable = problemData.TargetVariable;
@@ -102 +146 @@
         throw new NotSupportedException("Random forest classification does not support NaN or infinity values in the input dataset.");
 
+      int info = 0;
+      alglib.decisionforest dForest = new alglib.decisionforest();
+      alglib.dfreport rep = new alglib.dfreport(); ;
+      int nRows = inputMatrix.GetLength(0);
+      int nColumns = inputMatrix.GetLength(1);
+      int sampleSize = Math.Max((int)Math.Round(r * nRows), 1);
+      int nFeatures = Math.Max((int)Math.Round(m * (nColumns - 1)), 1);
 
-      alglib.decisionforest dforest;
-      alglib.dfreport rep;
-      int nRows = inputMatrix.GetLength(0);
-      int nCols = inputMatrix.GetLength(1);
-      int info;
-      double[] classValues = dataset.GetDoubleValues(targetVariable).Distinct().OrderBy(x => x).ToArray();
-      int nClasses = classValues.Count();
+
+      double[] classValues = problemData.ClassValues.ToArray();
+      int nClasses = problemData.Classes;
       // map original class values to values [0..nClasses-1]
       Dictionary<double, double> classIndices = new Dictionary<double, double>();
@@ -116 +163 @@
       }
       for (int row = 0; row < nRows; row++) {
-        inputMatrix[row, nCols - 1] = classIndices[inputMatrix[row, nCols - 1]];
+        inputMatrix[row, nColumns - 1] = classIndices[inputMatrix[row, nColumns - 1]];
       }
-      // execute random forest algorithm
-      alglib.dfbuildrandomdecisionforest(inputMatrix, nRows, nCols - 1, nClasses, nTrees, r, out info, out dforest, out rep);
+      // execute random forest algorithm      
+      alglib.dforest.dfbuildinternal(inputMatrix, nRows, nColumns - 1, nClasses, nTrees, sampleSize, nFeatures, alglib.dforest.dfusestrongsplits + alglib.dforest.dfuseevs, ref info, dForest.innerobj, rep.innerobj);
       if (info != 1) throw new ArgumentException("Error in calculation of random forest classification solution");
 
@@ -126 +173 @@
       relClassificationError = rep.relclserror;
       outOfBagRelClassificationError = rep.oobrelclserror;
-      return new RandomForestClassificationSolution((IClassificationProblemData)problemData.Clone(), new RandomForestModel(dforest, targetVariable, allowedInputVariables, classValues));
+      return new RandomForestClassificationSolution((IClassificationProblemData)problemData.Clone(), new RandomForestModel(dForest, targetVariable, allowedInputVariables, classValues));
     }
     #endregion