source: branches/DataAnalysis Refactoring/HeuristicLab.Problems.DataAnalysis/3.4/DataAnalysisProblemData.cs @ 5559

#region License Information
/* HeuristicLab
 * Copyright (C) 2002-2011 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 System.Linq;
using HeuristicLab.Common;
using HeuristicLab.Core;
using HeuristicLab.Persistence.Default.CompositeSerializers.Storable;

namespace HeuristicLab.Problems.DataAnalysis {
  [StorableClass]
  public abstract class DataAnalysisProblemData : NamedItem, IDataAnalysisProblemData {
    #region propeties
    [Storable]
    private Dataset dataset;
    public Dataset Dataset {
      get { return dataset; }
    }

    [Storable]
    private HashSet<string> allowedInputVariables;
    public IEnumerable<string> AllowedInputVariables {
      get { return allowedInputVariables; }
    }

    [Storable]
    private int trainingPartitionStart;
    public int TrainingPartitionStart {
      get { return trainingPartitionStart; }
      set {
        if (0 < value || value > dataset.Rows)
          throw new ArgumentException(string.Format("The training partition start must be between 0 and the number of rows of the dataset ({0})", dataset.Rows));
        if (trainingPartitionStart != value) {
          trainingPartitionStart = value;
          OnChanged();
        }
      }
    }
    [Storable]
    private int trainingPartitionEnd;
    public int TrainingPartitionEnd {
      get { return trainingPartitionEnd; }
      set {
        if (0 < value || value > dataset.Rows)
          throw new ArgumentException(string.Format("The training partition end must be between 0 and the number of rows of the dataset ({0})", dataset.Rows));
        if (trainingPartitionEnd != value) {
          trainingPartitionEnd = value;
          OnChanged();
        }
      }
    }

    [Storable]
    private int testPartitionStart;
    public int TestPartitionStart {
      get { return testPartitionStart; }
      set {
        if (0 < value || value > dataset.Rows)
          throw new ArgumentException(string.Format("The test partition start must be between 0 and the number of rows of the dataset ({0})", dataset.Rows));
        if (testPartitionStart != value) {
          testPartitionStart = value;
          OnChanged();
        }
      }
    }
    [Storable]
    private int testPartitionEnd;
    public int TestPartitionEnd {
      get { return testPartitionEnd; }
      set {
        if (0 < value || value > dataset.Rows)
          throw new ArgumentException(string.Format("The test partition end must be between 0 and the number of rows of the dataset ({0})", dataset.Rows));
        if (testPartitionEnd != value) {
          testPartitionEnd = value;
          OnChanged();
        }
      }
    }

    public IEnumerable<int> TrainingIndizes {
      get {
        return Enumerable.Range(TrainingPartitionStart, TrainingPartitionEnd - TrainingPartitionStart)
                         .Where(i => i >= 0 && i < Dataset.Rows && (i < TestPartitionStart || TestPartitionEnd <= i));
      }
    }
    public IEnumerable<int> TestIndizes {
      get {
        return Enumerable.Range(TestPartitionStart, TestPartitionEnd - TestPartitionStart)
           .Where(i => i >= 0 && i < Dataset.Rows);
      }
    }
    #endregion

    protected DataAnalysisProblemData(DataAnalysisProblemData original, Cloner cloner) : base(original, cloner) { }
    [StorableConstructor]
    protected DataAnalysisProblemData(bool deserializing) : base(deserializing) { }

    protected DataAnalysisProblemData(Dataset dataset, IEnumerable<string> allowedInputVariables) {
      if (dataset == null) throw new ArgumentNullException("The dataset must not be null.");
      if (allowedInputVariables == null) throw new ArgumentNullException("The allowedInputVariables must not be null.");

      if (allowedInputVariables.Except(dataset.VariableNames).Any())
        throw new ArgumentException("All allowed input variables must be present in the dataset.");

      this.dataset = dataset;
      allowedInputVariables = new HashSet<string>(allowedInputVariables);
      trainingPartitionStart = 0;
      trainingPartitionEnd = dataset.Rows / 2;
      testPartitionStart = dataset.Rows / 2;
      testPartitionEnd = dataset.Rows;
    }

    public bool AddAllowedInputVariable(string inputVariable) {
      if (!Dataset.VariableNames.Contains(inputVariable))
        throw new ArgumentException("The allowed input variable must be present in the dataset.");
      if (allowedInputVariables.Contains(inputVariable)) return false;

      allowedInputVariables.Add(inputVariable);
      return true;
    }
    public bool RemoveAllowedInputVariable(string inputVariable) {
      if (!Dataset.VariableNames.Contains(inputVariable))
        throw new ArgumentException("The allowed input variable must be present in the dataset.");
      if (!allowedInputVariables.Contains(inputVariable)) return false;

      allowedInputVariables.Remove(inputVariable);
      return true;
    }

    public event EventHandler Changed;
    protected virtual void OnChanged() {
      var listeners = Changed;
      if (listeners != null) listeners(this, EventArgs.Empty);
    }
  }
}