#region License Information
/* HeuristicLab
* Copyright (C) 2002-2011 Heuristic and Evolutionary Algorithms Laboratory (HEAL)
*
* This file is part of HeuristicLab.
*
* HeuristicLab is free software: you can redistribute it and/or modify
* it under the terms of the GNU General Public License as published by
* the Free Software Foundation, either version 3 of the License, or
* (at your option) any later version.
*
* HeuristicLab is distributed in the hope that it will be useful,
* but WITHOUT ANY WARRANTY; without even the implied warranty of
* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
* GNU General Public License for more details.
*
* You should have received a copy of the GNU General Public License
* along with HeuristicLab. If not, see .
*/
#endregion
using System;
using System.Collections.Generic;
using System.Linq;
using HeuristicLab.Common;
using HeuristicLab.Core;
using HeuristicLab.Data;
using HeuristicLab.Encodings.SymbolicExpressionTreeEncoding;
using HeuristicLab.Optimization;
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 {
///
/// Random forest regression data analysis algorithm.
///
[Item("Random Forest Regression", "Random forest regression data analysis algorithm (wrapper for ALGLIB).")]
[Creatable("Data Analysis")]
[StorableClass]
public sealed class RandomForestRegression : FixedDataAnalysisAlgorithm {
private const string RandomForestRegressionModelResultName = "Random forest regression solution";
private const string NumberOfTreesParameterName = "Number of trees";
private const string RParameterName = "R";
#region parameter properties
public IValueParameter NumberOfTreesParameter {
get { return (IValueParameter)Parameters[NumberOfTreesParameterName]; }
}
public IValueParameter RParameter {
get { return (IValueParameter)Parameters[RParameterName]; }
}
#endregion
#region properties
public int NumberOfTrees {
get { return NumberOfTreesParameter.Value.Value; }
set { NumberOfTreesParameter.Value.Value = value; }
}
public double R {
get { return RParameter.Value.Value; }
set { RParameter.Value.Value = value; }
}
#endregion
[StorableConstructor]
private RandomForestRegression(bool deserializing) : base(deserializing) { }
private RandomForestRegression(RandomForestRegression original, Cloner cloner)
: base(original, cloner) {
}
public RandomForestRegression()
: base() {
Parameters.Add(new FixedValueParameter(NumberOfTreesParameterName, "The number of trees in the forest. Should be between 50 and 100", new IntValue(50)));
Parameters.Add(new FixedValueParameter(RParameterName, "The ratio of the training set that will be used in the construction of individual trees (0 allowedInputVariables = problemData.AllowedInputVariables;
IEnumerable rows = problemData.TrainingIndizes;
double[,] inputMatrix = AlglibUtil.PrepareInputMatrix(dataset, allowedInputVariables.Concat(new string[] { targetVariable }), rows);
if (inputMatrix.Cast().Any(x => double.IsNaN(x) || double.IsInfinity(x)))
throw new NotSupportedException("Random forest regression does not support NaN or infinity values in the input dataset.");
alglib.decisionforest dforest;
alglib.dfreport rep;
int nRows = inputMatrix.GetLength(0);
int info;
alglib.dfbuildrandomdecisionforest(inputMatrix, nRows, allowedInputVariables.Count(), 1, nTrees, r, out info, out dforest, out rep);
if (info != 1) throw new ArgumentException("Error in calculation of random forest regression solution");
rmsError = rep.rmserror;
avgRelError = rep.avgrelerror;
outOfBagAvgRelError = rep.oobavgrelerror;
outOfBagRmsError = rep.oobrmserror;
return new RandomForestRegressionSolution((IRegressionProblemData)problemData.Clone(), new RandomForestModel(dforest, targetVariable, allowedInputVariables));
}
#endregion
}
}