source: branches/DataAnalysis Refactoring/HeuristicLab.Problems.DataAnalysis.Symbolic/3.4/Evaluators/SymbolicDataAnalysisEvaluator.cs @ 5507

#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 <http://www.gnu.org/licenses/>.
 */
#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.Operators;
using HeuristicLab.Parameters;
using HeuristicLab.Persistence.Default.CompositeSerializers.Storable;
using HeuristicLab.Random;

namespace HeuristicLab.Problems.DataAnalysis.Symbolic {
  public abstract class SymbolicDataAnalysisEvaluator : SingleSuccessorOperator,
    ISymbolicDataAnalysisEvaluator, ISymbolicDataAnalysisBoundedEvaluator, ISymbolicDataAnalysisInterpreterOperator {
    private const string RandomParameterName = "Random";
    private const string SymbolicExpressionTreeParameterName = "SymbolicExpressionTree";
    private const string SymbolicExpressionTreeInterpreterParameterName = "SymbolicExpressionTreeInterpreter";
    private const string ProblemDataParameterName = "ProblemData";
    private const string UpperEstimationLimitParameterName = "UpperEstimationLimit";
    private const string LowerEstimationLimitParameterName = "LowerEstimationLimit";
    private const string SamplesStartParameterName = "SamplesStart";
    private const string SamplesEndParameterName = "SamplesEnd";
    private const string RelativeNumberOfEvaluatedSamplesParameterName = "RelativeNumberOfEvaluatedSamples";

    #region parameter properties
    public ILookupParameter<IRandom> RandomParameter {
      get { return (ILookupParameter<IRandom>)Parameters[RandomParameterName]; }
    }
    public ILookupParameter<ISymbolicExpressionTree> SymbolicExpressionTreeParameter {
      get { return (ILookupParameter<ISymbolicExpressionTree>)Parameters[SymbolicExpressionTreeParameterName]; }
    }
    public ILookupParameter<ISymbolicDataAnalysisTreeInterpreter> SymbolicExpressionTreeInterpreterParameter {
      get { return (ILookupParameter<ISymbolicDataAnalysisTreeInterpreter>)Parameters[SymbolicExpressionTreeInterpreterParameterName]; }
    }
    public ILookupParameter<IDataAnalysisProblemData> ProblemDataParameter {
      get { return (ILookupParameter<IDataAnalysisProblemData>)Parameters[ProblemDataParameterName]; }
    }

    public IValueLookupParameter<IntValue> SamplesStartParameter {
      get { return (IValueLookupParameter<IntValue>)Parameters[SamplesStartParameterName]; }
    }
    public IValueLookupParameter<IntValue> SamplesEndParameter {
      get { return (IValueLookupParameter<IntValue>)Parameters[SamplesEndParameterName]; }
    }

    public IValueLookupParameter<DoubleValue> UpperEstimationLimitParameter {
      get { return (IValueLookupParameter<DoubleValue>)Parameters[UpperEstimationLimitParameterName]; }
    }
    public IValueLookupParameter<DoubleValue> LowerEstimationLimitParameter {
      get { return (IValueLookupParameter<DoubleValue>)Parameters[LowerEstimationLimitParameterName]; }
    }

    public IValueParameter<PercentValue> RelativeNumberOfEvaluatedSamplesParameter {
      get { return (IValueParameter<PercentValue>)Parameters[RelativeNumberOfEvaluatedSamplesParameterName]; }
    }
    #endregion

    #region properties
    public IDataAnalysisProblemData ProblemData {
      get { return ProblemDataParameter.ActualValue; }
    }

    public IntValue SamplesStart {
      get { return SamplesStartParameter.ActualValue; }
    }
    public IntValue SamplesEnd {
      get { return SamplesEndParameter.ActualValue; }
    }
    public DoubleValue UpperEstimationLimit {
      get { return UpperEstimationLimitParameter.ActualValue; }
    }
    public DoubleValue LowerEstimationLimit {
      get { return LowerEstimationLimitParameter.ActualValue; }
    }
    public PercentValue RelativeNumberOfEvaluatedSamples {
      get { return RelativeNumberOfEvaluatedSamplesParameter.Value; }
    }
    #endregion

    [StorableConstructor]
    protected SymbolicDataAnalysisEvaluator(bool deserializing) : base(deserializing) { }
    protected SymbolicDataAnalysisEvaluator(SymbolicDataAnalysisEvaluator original, Cloner cloner)
      : base(original, cloner) {
    }
    public SymbolicDataAnalysisEvaluator()
      : base() {
      Parameters.Add(new LookupParameter<IRandom>(RandomParameterName, "The random generator to use."));
      Parameters.Add(new LookupParameter<ISymbolicDataAnalysisTreeInterpreter>(SymbolicExpressionTreeInterpreterParameterName, "The interpreter that should be used to calculate the output values of the symbolic expression tree."));
      Parameters.Add(new LookupParameter<SymbolicExpressionTree>(SymbolicExpressionTreeInterpreterParameterName, "The symbolic regression solution encoded as a symbolic expression tree."));
      Parameters.Add(new LookupParameter<IDataAnalysisProblemData>(ProblemDataParameterName, "The problem data on which the symbolic regression solution should be evaluated."));
      Parameters.Add(new ValueLookupParameter<IntValue>(SamplesStartParameterName, "The start index of the dataset partition on which the symbolic regression solution should be evaluated."));
      Parameters.Add(new ValueLookupParameter<IntValue>(SamplesEndParameterName, "The end index of the dataset partition on which the symbolic regression solution should be evaluated."));
      Parameters.Add(new ValueLookupParameter<DoubleValue>(UpperEstimationLimitParameterName, "The upper limit that should be used as cut off value for the output values of symbolic expression trees."));
      Parameters.Add(new ValueLookupParameter<DoubleValue>(LowerEstimationLimitParameterName, "The lower limit that should be used as cut off value for the output values of symbolic expression trees."));
      Parameters.Add(new ValueParameter<PercentValue>(RelativeNumberOfEvaluatedSamplesParameterName, "The relative number of samples of the dataset partition, which should be randomly chosen for evaluation between the start and end index.", new PercentValue(1)));
    }

    protected IEnumerable<int> GenerateRowsToEvaluate() {
      int seed = RandomParameter.ActualValue.Next();
      if (SamplesEnd.Value < SamplesStart.Value) throw new ArgumentException("Start value is larger than end value.");
      int count = (int)((SamplesEnd.Value - SamplesStart.Value) * RelativeNumberOfEvaluatedSamples.Value);
      if (count == 0) count = 1;
      return RandomEnumerable.SampleRandomNumbers(seed, SamplesEnd.Value, SamplesStart.Value, count)
        .Where(i => i < ProblemDataParameter.ActualValue.TestSamplesStart || ProblemDataParameter.ActualValue.TestSamplesEnd <= i);
    }

    public static IEnumerable<double> BoundEstimatedValues(IEnumerable<double> estimatedValues, double lowerEstimationLimit, double upperEstimationLimit) {
      return estimatedValues.Select(v => {
        if (double.IsNaN(v)) return v;
        else if (v < lowerEstimationLimit) return lowerEstimationLimit;
        else if (v > upperEstimationLimit) return upperEstimationLimit;
        return v;
      });
    }
  }
}