source: branches/HeuristicLab.EvolutionTracking/HeuristicLab.Problems.DataAnalysis.Symbolic/3.4/Tracking/SchemaDiversification/UpdateEstimatedValuesOperator.cs @ 12979

#region License Information
/* HeuristicLab
 * Copyright (C) 2002-2015 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.Linq;
using HeuristicLab.Common;
using HeuristicLab.Core;
using HeuristicLab.Data;
using HeuristicLab.Encodings.SymbolicExpressionTreeEncoding;
using HeuristicLab.EvolutionTracking;
using HeuristicLab.Parameters;
using HeuristicLab.Persistence.Default.CompositeSerializers.Storable;

namespace HeuristicLab.Problems.DataAnalysis.Symbolic {
  [Item("UpdateEstimatedValuesOperator", "Put the estimated values of the tree in the scope to be used by the phenotypic similarity calculator")]
  [StorableClass]
  public class UpdateEstimatedValuesOperator : EvolutionTrackingOperator<ISymbolicExpressionTree> {
    private const string ProblemDataParameterName = "ProblemData";
    private const string InterpreterParameterName = "SymbolicExpressionTreeInterpreter";
    private const string EstimationLimitsParameterName = "EstimationLimits";
    private const string SymbolicExpressionTreeParameterName = "SymbolicExpressionTree";

    public ILookupParameter<IRegressionProblemData> ProblemDataParameter {
      get { return (ILookupParameter<IRegressionProblemData>)Parameters[ProblemDataParameterName]; }
    }
    public ILookupParameter<ISymbolicDataAnalysisExpressionTreeInterpreter> InterpreterParameter {
      get { return (ILookupParameter<ISymbolicDataAnalysisExpressionTreeInterpreter>)Parameters[InterpreterParameterName]; }
    }
    public ILookupParameter<DoubleLimit> EstimationLimitsParameter {
      get { return (ILookupParameter<DoubleLimit>)Parameters[EstimationLimitsParameterName]; }
    }
    public ILookupParameter<ISymbolicExpressionTree> SymbolicExpressionTreeParameter {
      get { return (ILookupParameter<ISymbolicExpressionTree>)Parameters[SymbolicExpressionTreeParameterName]; }
    }


    public UpdateEstimatedValuesOperator() {
      Parameters.Add(new LookupParameter<IRegressionProblemData>(ProblemDataParameterName));
      Parameters.Add(new LookupParameter<ISymbolicDataAnalysisExpressionTreeInterpreter>(InterpreterParameterName));
      Parameters.Add(new LookupParameter<DoubleLimit>(EstimationLimitsParameterName));
      Parameters.Add(new LookupParameter<ISymbolicExpressionTree>(SymbolicExpressionTreeParameterName));
    }

    [StorableConstructor]
    protected UpdateEstimatedValuesOperator(bool deserializing) : base(deserializing) { }

    protected UpdateEstimatedValuesOperator(UpdateEstimatedValuesOperator original, Cloner cloner) : base(original, cloner) {
    }

    public override IDeepCloneable Clone(Cloner cloner) {
      return new UpdateEstimatedValuesOperator(this, cloner);
    }

    public override IOperation Apply() {
      var tree = SymbolicExpressionTreeParameter.ActualValue;
      var problemData = ProblemDataParameter.ActualValue;
      var estimationLimits = EstimationLimitsParameter.ActualValue;
      var interpreter = InterpreterParameter.ActualValue;

      var estimatedValues = interpreter.GetSymbolicExpressionTreeValues(tree, problemData.Dataset, problemData.TrainingIndices).ToArray();
      var targetValues = problemData.Dataset.GetDoubleValues(problemData.TargetVariable, problemData.TrainingIndices).ToArray();

      if (estimatedValues.Length != targetValues.Length)
        throw new ArgumentException("Number of elements in target and estimated values enumeration do not match.");

      var linearScalingCalculator = new OnlineLinearScalingParameterCalculator();

      for (int i = 0; i < estimatedValues.Length; ++i) {
        var estimated = estimatedValues[i];
        var target = targetValues[i];
        if (!double.IsNaN(estimated) && !double.IsInfinity(estimated))
          linearScalingCalculator.Add(estimated, target);
      }
      double alpha = linearScalingCalculator.Alpha;
      double beta = linearScalingCalculator.Beta;
      if (linearScalingCalculator.ErrorState != OnlineCalculatorError.None) {
        alpha = 0.0;
        beta = 1.0;
      }

      var scaled = estimatedValues.Select(x => x * beta + alpha).LimitToRange(estimationLimits.Lower, estimationLimits.Upper).ToArray();
      OnlineCalculatorError error;
      var r = OnlinePearsonsRCalculator.Calculate(targetValues, scaled, out error);
      if (error != OnlineCalculatorError.None) r = 0;

      var r2 = r * r;
      if (r2 > 1.0) r2 = 1.0;

      var variables = ExecutionContext.Scope.Variables;
      ((DoubleValue)variables["Quality"].Value).Value = r2;

      if (variables.ContainsKey("EstimatedValues")) {
        variables["EstimatedValues"].Value = new DoubleArray(scaled);
      } else {
        variables.Add(new Core.Variable("EstimatedValues", new DoubleArray(scaled)));
      }
      return base.Apply();
    }
  }
}