#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.Collections.Generic;
using System.Linq;
using HeuristicLab.Analysis;
using HeuristicLab.Common;
using HeuristicLab.Core;
using HeuristicLab.Data;
using HeuristicLab.Encodings.SymbolicExpressionTreeEncoding;
using HeuristicLab.Operators;
using HeuristicLab.Optimization;
using HeuristicLab.Parameters;
using HeuristicLab.Persistence.Default.CompositeSerializers.Storable;
using HeuristicLab.Problems.DataAnalysis.Symbolic;

namespace HeuristicLab.Problems.DataAnalysis.Regression.Symbolic.Analyzers {
  /// <summary>
  /// A base class for operators that analyze the validation fitness of symbolic regression models.
  /// </summary>
  [Item("SymbolicRegressionValidationAnalyzer", "A base class for operators that analyze the validation fitness of symbolic regression models.")]
  [StorableClass]
  public abstract class SymbolicRegressionValidationAnalyzer : SingleSuccessorOperator {
    private const string RandomParameterName = "Random";
    private const string SymbolicExpressionTreeParameterName = "SymbolicExpressionTree";
    private const string SymbolicExpressionTreeInterpreterParameterName = "SymbolicExpressionTreeInterpreter";
    private const string ProblemDataParameterName = "ProblemData";
    private const string ValidationSamplesStartParameterName = "SamplesStart";
    private const string ValidationSamplesEndParameterName = "SamplesEnd";
    private const string UpperEstimationLimitParameterName = "UpperEstimationLimit";
    private const string LowerEstimationLimitParameterName = "LowerEstimationLimit";
    private const string EvaluatorParameterName = "Evaluator";
    private const string RelativeNumberOfEvaluatedSamplesParameterName = "RelativeNumberOfEvaluatedSamples";

    #region parameter properties
    public ILookupParameter<IRandom> RandomParameter {
      get { return (ILookupParameter<IRandom>)Parameters[RandomParameterName]; }
    }
    public ScopeTreeLookupParameter<SymbolicExpressionTree> SymbolicExpressionTreeParameter {
      get { return (ScopeTreeLookupParameter<SymbolicExpressionTree>)Parameters[SymbolicExpressionTreeParameterName]; }
    }
    public IValueLookupParameter<ISymbolicExpressionTreeInterpreter> SymbolicExpressionTreeInterpreterParameter {
      get { return (IValueLookupParameter<ISymbolicExpressionTreeInterpreter>)Parameters[SymbolicExpressionTreeInterpreterParameterName]; }
    }
    public ILookupParameter<ISymbolicRegressionEvaluator> EvaluatorParameter {
      get { return (ILookupParameter<ISymbolicRegressionEvaluator>)Parameters[EvaluatorParameterName]; }
    }
    public IValueLookupParameter<DataAnalysisProblemData> ProblemDataParameter {
      get { return (IValueLookupParameter<DataAnalysisProblemData>)Parameters[ProblemDataParameterName]; }
    }
    public IValueLookupParameter<IntValue> ValidationSamplesStartParameter {
      get { return (IValueLookupParameter<IntValue>)Parameters[ValidationSamplesStartParameterName]; }
    }
    public IValueLookupParameter<IntValue> ValidationSamplesEndParameter {
      get { return (IValueLookupParameter<IntValue>)Parameters[ValidationSamplesEndParameterName]; }
    }
    public IValueParameter<PercentValue> RelativeNumberOfEvaluatedSamplesParameter {
      get { return (IValueParameter<PercentValue>)Parameters[RelativeNumberOfEvaluatedSamplesParameterName]; }
    }

    public IValueLookupParameter<DoubleValue> UpperEstimationLimitParameter {
      get { return (IValueLookupParameter<DoubleValue>)Parameters[UpperEstimationLimitParameterName]; }
    }
    public IValueLookupParameter<DoubleValue> LowerEstimationLimitParameter {
      get { return (IValueLookupParameter<DoubleValue>)Parameters[LowerEstimationLimitParameterName]; }
    }
    #endregion
    #region properties
    public IRandom Random {
      get { return RandomParameter.ActualValue; }
    }
    public ItemArray<SymbolicExpressionTree> SymbolicExpressionTree {
      get { return SymbolicExpressionTreeParameter.ActualValue; }
    }
    public ISymbolicExpressionTreeInterpreter SymbolicExpressionTreeInterpreter {
      get { return SymbolicExpressionTreeInterpreterParameter.ActualValue; }
    }
    public ISymbolicRegressionEvaluator Evaluator {
      get { return EvaluatorParameter.ActualValue; }
    }
    public DataAnalysisProblemData ProblemData {
      get { return ProblemDataParameter.ActualValue; }
    }
    public IntValue ValidiationSamplesStart {
      get { return ValidationSamplesStartParameter.ActualValue; }
    }
    public IntValue ValidationSamplesEnd {
      get { return ValidationSamplesEndParameter.ActualValue; }
    }
    public PercentValue RelativeNumberOfEvaluatedSamples {
      get { return RelativeNumberOfEvaluatedSamplesParameter.Value; }
    }

    public DoubleValue UpperEstimationLimit {
      get { return UpperEstimationLimitParameter.ActualValue; }
    }
    public DoubleValue LowerEstimationLimit {
      get { return LowerEstimationLimitParameter.ActualValue; }
    }
    #endregion

    [StorableConstructor]
    protected SymbolicRegressionValidationAnalyzer(bool deserializing) : base(deserializing) { }
    protected SymbolicRegressionValidationAnalyzer(SymbolicRegressionValidationAnalyzer original, Cloner cloner) : base(original, cloner) { }
    public SymbolicRegressionValidationAnalyzer()
      : base() {
      Parameters.Add(new LookupParameter<IRandom>(RandomParameterName, "The random generator to use."));
      Parameters.Add(new LookupParameter<ISymbolicRegressionEvaluator>(EvaluatorParameterName, "The evaluator which should be used to evaluate the solution on the validation set."));
      Parameters.Add(new ScopeTreeLookupParameter<SymbolicExpressionTree>(SymbolicExpressionTreeParameterName, "The symbolic expression trees to analyze."));
      Parameters.Add(new ValueLookupParameter<ISymbolicExpressionTreeInterpreter>(SymbolicExpressionTreeInterpreterParameterName, "The interpreter that should be used for the analysis of symbolic expression trees."));
      Parameters.Add(new ValueLookupParameter<DataAnalysisProblemData>(ProblemDataParameterName, "The problem data for which the symbolic expression tree is a solution."));
      Parameters.Add(new ValueLookupParameter<IntValue>(ValidationSamplesStartParameterName, "The first index of the validation partition of the data set."));
      Parameters.Add(new ValueLookupParameter<IntValue>(ValidationSamplesEndParameterName, "The last index of the validation partition of the data set."));
      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)));
      Parameters.Add(new ValueLookupParameter<DoubleValue>(UpperEstimationLimitParameterName, "The upper estimation limit that was set for the evaluation of the symbolic expression trees."));
      Parameters.Add(new ValueLookupParameter<DoubleValue>(LowerEstimationLimitParameterName, "The lower estimation limit that was set for the evaluation of the symbolic expression trees."));
    }

    [StorableHook(HookType.AfterDeserialization)]
    private void AfterDeserialization() { }

    public override IOperation Apply() {
      var trees = SymbolicExpressionTree.ToArray();

      string targetVariable = ProblemData.TargetVariable.Value;

      // select a random subset of rows in the validation set
      int validationStart = ValidiationSamplesStart.Value;
      int validationEnd = ValidationSamplesEnd.Value;
      int seed = Random.Next();
      int count = (int)((validationEnd - validationStart) * RelativeNumberOfEvaluatedSamples.Value);
      if (count == 0) count = 1;
      IEnumerable<int> rows = RandomEnumerable.SampleRandomNumbers(seed, validationStart, validationEnd, count)
        .Where(row => row < ProblemData.TestSamplesStart.Value || ProblemData.TestSamplesEnd.Value <= row);

      double upperEstimationLimit = UpperEstimationLimit != null ? UpperEstimationLimit.Value : double.PositiveInfinity;
      double lowerEstimationLimit = LowerEstimationLimit != null ? LowerEstimationLimit.Value : double.NegativeInfinity;

      double[] validationQuality = new double[trees.Count()];
      for (int i = 0; i < validationQuality.Length; i++) {
        validationQuality[i] = Evaluator.Evaluate(SymbolicExpressionTreeInterpreter, trees[i],
            lowerEstimationLimit, upperEstimationLimit,
            ProblemData.Dataset, targetVariable,
           rows);
      }

      Analyze(trees, validationQuality);
      return base.Apply();
    }

    protected abstract void Analyze(SymbolicExpressionTree[] trees, double[] validationQuality);
  }
}