#region License Information
/* HeuristicLab
 * Copyright (C) 2002-2016 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 HeuristicLab.Analysis;
using HeuristicLab.Common;
using HeuristicLab.Core;
using HeuristicLab.Operators;
using HeuristicLab.Optimization;
using HeuristicLab.Parameters;
using HeuristicLab.Persistence.Default.CompositeSerializers.Storable;
using HeuristicLab.Problems.DataAnalysis;

namespace HeuristicLab.Algorithms.EGO {
  [Item("ModelQualityAnalyzer", "Collects RealVectors into a modifiablbe dataset")]
  [StorableClass]
  public class ModelQualityAnalyzer : SingleSuccessorOperator, IAnalyzer, IResultsOperator {
    public override bool CanChangeName => true;
    public bool EnabledByDefault => false;

    public ILookupParameter<IRegressionSolution> ModelParameter => (ILookupParameter<IRegressionSolution>)Parameters["Model"];
    public ILookupParameter<ResultCollection> ResultsParameter => (ILookupParameter<ResultCollection>)Parameters["Results"];

    private const string PlotName = "Model Quality Values";
    private const string R2RowName = "Training R²";
    private const string MAERowName = "Training Mean Absolute Error";
    private const string RMSERowName = "Training Root Mean Squared Error";
    private const string ModelResultName = "Model";


    [StorableConstructor]
    protected ModelQualityAnalyzer(bool deserializing) : base(deserializing) { }
    protected ModelQualityAnalyzer(ModelQualityAnalyzer original, Cloner cloner) : base(original, cloner) { }
    public ModelQualityAnalyzer() {
      Parameters.Add(new LookupParameter<IRegressionSolution>("Model", "The model of this iteration"));
      Parameters.Add(new LookupParameter<ResultCollection>("Results", "The collection to store the results in."));
    }

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

    public sealed override IOperation Apply() {
      var model = ModelParameter.ActualValue;
      var results = ResultsParameter.ActualValue;
      if (model == null) return base.Apply();
      var plot = CreateDataTableResult(results);
      plot.Rows[R2RowName].Values.Add(model.TrainingRSquared);
      plot.Rows[MAERowName].Values.Add(model.TrainingMeanAbsoluteError);
      plot.Rows[RMSERowName].Values.Add(model.TrainingRootMeanSquaredError);
      if (!results.ContainsKey(ModelResultName)) results.Add(new Result(ModelResultName, model));
      results[ModelResultName].Value = model;
      return base.Apply();
    }

    private static DataTable CreateDataTableResult(ResultCollection results) {
      DataTable plot;
      if (!results.ContainsKey(PlotName)) {
        plot = new DataTable("Model-Quality-Measures", "The quality measures of the models on the training data") {
          VisualProperties = {
            XAxisTitle = "Generation",
          }
        };
        results.Add(new Result(PlotName, plot));
      } else plot = (DataTable)results[PlotName].Value;
      if (!plot.Rows.ContainsKey(R2RowName)) plot.Rows.Add(new DataRow(R2RowName, R2RowName, new double[0]));
      if (!plot.Rows.ContainsKey(MAERowName)) plot.Rows.Add(new DataRow(MAERowName, MAERowName, new double[0]));
      if (!plot.Rows.ContainsKey(RMSERowName)) plot.Rows.Add(new DataRow(RMSERowName, RMSERowName, new double[0]));

      return plot;
    }

  }
}