source: branches/GP.Symbols (TimeLag, Diff, Integral)/HeuristicLab.Problems.DataAnalysis.Regression/3.3/Symbolic/Evaluators/SymbolicRegressionConditionalPearsonsRSquaredEvaluator.cs @ 6315

#region License Information
/* HeuristicLab
 * Copyright (C) 2002-2010 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 HeuristicLab.Common;
using HeuristicLab.Core;
using HeuristicLab.Data;
using HeuristicLab.Encodings.SymbolicExpressionTreeEncoding;
using HeuristicLab.Parameters;
using HeuristicLab.Persistence.Default.CompositeSerializers.Storable;
using HeuristicLab.Problems.DataAnalysis.Evaluators;
using HeuristicLab.Problems.DataAnalysis.Symbolic;

namespace HeuristicLab.Problems.DataAnalysis.Regression.Symbolic.Evaluators {
  [Item("SymbolicRegressionConditionalPearsonsRSquaredEvaluator", "Evaluates a symbolic regression solution.")]
  [StorableClass]
  public class SymbolicRegressionConditionalPearsonsRSquaredEvaluator : SingleObjectiveSymbolicRegressionEvaluator {
    private const string ConditionVariableParameterName = "ConditionVariable";

    public IValueParameter<StringValue> ConditionVariableParameter {
      get { return (IValueParameter<StringValue>)Parameters[ConditionVariableParameterName]; }
    }
    public StringValue ConditionVariable {
      get { return ConditionVariableParameter.Value; }
    }

    public SymbolicRegressionConditionalPearsonsRSquaredEvaluator()
      : base() {
      Parameters.Add(new ValueLookupParameter<StringValue>(ConditionVariableParameterName, "The variable name that states which samples should be skipped for evaluation."));
    }
    [StorableConstructor]
    protected SymbolicRegressionConditionalPearsonsRSquaredEvaluator(bool deserializing) : base(deserializing) { }
    protected SymbolicRegressionConditionalPearsonsRSquaredEvaluator(SymbolicRegressionConditionalPearsonsRSquaredEvaluator original, Cloner cloner)
      : base(original, cloner) {
    }
    public override IDeepCloneable Clone(Cloner cloner) {
      return new SymbolicRegressionConditionalPearsonsRSquaredEvaluator(this, cloner);
    }

    public override double Evaluate(ISymbolicExpressionTreeInterpreter interpreter, SymbolicExpressionTree solution, double lowerEstimationLimit, double upperEstimationLimit, Dataset dataset, string targetVariable, IEnumerable<int> rows) {
      double mse = Calculate(interpreter, solution, lowerEstimationLimit, upperEstimationLimit, dataset, targetVariable, rows, ConditionVariable.Value);
      return mse;
    }

    public static double Calculate(ISymbolicExpressionTreeInterpreter interpreter, SymbolicExpressionTree solution, double lowerEstimationLimit, double upperEstimationLimit, Dataset dataset, string targetVariable, IEnumerable<int> rows, string conditionVariable) {
      IEnumerable<double> estimatedValues = interpreter.GetSymbolicExpressionTreeValues(solution, dataset, rows);
      IEnumerable<double> originalValues = dataset.GetEnumeratedVariableValues(targetVariable, rows);
      IEnumerator<double> originalEnumerator = originalValues.GetEnumerator();
      IEnumerator<double> estimatedEnumerator = estimatedValues.GetEnumerator();
      IEnumerator<int> rowsEnumerator = rows.GetEnumerator();
      OnlinePearsonsRSquaredEvaluator r2Evaluator = new OnlinePearsonsRSquaredEvaluator();

      int minLag = GetMinimumLagFromTree(solution.Root);

      while (originalEnumerator.MoveNext() && estimatedEnumerator.MoveNext() && rowsEnumerator.MoveNext()) {
        double estimated = estimatedEnumerator.Current;
        double original = originalEnumerator.Current;
        int row = rowsEnumerator.Current;

        bool evaluate = true;
        for (int i = minLag; i <= 0 && evaluate; i++) {
          evaluate = evaluate && dataset[conditionVariable, row - i].IsAlmost(0.0);
        }

        if (evaluate) {
          if (double.IsNaN(estimated))
            estimated = upperEstimationLimit;
          else
            estimated = Math.Min(upperEstimationLimit, Math.Max(lowerEstimationLimit, estimated));
          r2Evaluator.Add(original, estimated);
        }
      }

      if (estimatedEnumerator.MoveNext() || originalEnumerator.MoveNext() || rowsEnumerator.MoveNext()) {
        throw new ArgumentException("Number of elements in original and estimated enumeration doesn't match.");
      } else return r2Evaluator.RSquared;
    }

    protected static int GetMinimumLagFromTree(SymbolicExpressionTreeNode node) {
      if (node == null) return 0;
      int lag = 0;

      var laggedTreeNode = node as ILaggedTreeNode;
      if (laggedTreeNode != null) lag += laggedTreeNode.Lag;

      int subtreeLag = 0;
      foreach (var subtree in node.SubTrees) {
        subtreeLag = Math.Min(subtreeLag, GetMinimumLagFromTree(subtree));
      }
      return lag + subtreeLag;
    }


  }
}