#region License Information
/* HeuristicLab
 * Copyright (C) 2002-2013 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.Problems.DataAnalysis;

namespace HeuristicLab.DataPreprocessing {
  internal class ProblemDataCreator {

    private readonly IPreprocessingContext context;

    public ProblemDataCreator(IPreprocessingContext context) {
      this.context = context;
    }

    public IDataAnalysisProblemData CreateProblemData() {
      var oldProblemData = context.Problem.ProblemData;

      IDataAnalysisProblemData problemData = null;

      var dataSet = context.Data.ExportToDataset();
      var inputVariables = context.Data.VariableNames;

      if (oldProblemData is RegressionProblemData) {
        problemData = CreateRegressionData((RegressionProblemData)oldProblemData, dataSet, inputVariables);
      } else if (oldProblemData is ClassificationProblemData) {
        problemData = CreateClassificationData((ClassificationProblemData)oldProblemData, dataSet, inputVariables);
      } else if (oldProblemData is ClusteringProblemData) {
        problemData = CreateClusteringData((ClusteringProblemData)oldProblemData, dataSet, inputVariables);
      } else {
        throw new NotImplementedException("The type of the DataAnalysisProblemData is not supported.");
      }

      SetTrainingAndTestPartition(problemData);

      return problemData;
    }

    private IDataAnalysisProblemData CreateRegressionData(RegressionProblemData oldProblemData, Dataset dataSet, IEnumerable<string> inputVariables) {
      var targetVariable = oldProblemData.TargetVariable;
      // target variable must be double and must exist in the new dataset
      return new RegressionProblemData(dataSet, inputVariables, targetVariable);
    }

    private IDataAnalysisProblemData CreateClassificationData(ClassificationProblemData oldProblemData, Dataset dataSet, IEnumerable<string> inputVariables) {
      var targetVariable = oldProblemData.TargetVariable;
      // target variable must be double and must exist in the new dataset
      return new ClassificationProblemData(dataSet, inputVariables, targetVariable);
    }

    private IDataAnalysisProblemData CreateClusteringData(ClusteringProblemData oldProblemData, Dataset dataSet, IEnumerable<string> inputVariables) {
      return new ClusteringProblemData(dataSet, inputVariables);
    }

    private void SetTrainingAndTestPartition(IDataAnalysisProblemData problemData) {
      var ppData = context.Data;

      problemData.TrainingPartition.Start = ppData.TrainingPartition.Start;
      problemData.TrainingPartition.End = ppData.TrainingPartition.End;
      problemData.TestPartition.Start = ppData.TestPartition.Start;
      problemData.TestPartition.End = ppData.TestPartition.End;
    }
  }
}