source: branches/HeuristicLab.DataImporter/HeuristicLab.DataImporter.Command/MissingValues/DeleteRowsWithMissingValuesThresholdCommand.cs @ 14349

#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 System.Linq;
using HeuristicLab.DataImporter.Command.View;
using HeuristicLab.DataImporter.Data;
using HeuristicLab.DataImporter.Data.CommandBase;
using HeuristicLab.DataImporter.Data.Model;
using HeuristicLab.Persistence.Default.CompositeSerializers.Storable;

namespace HeuristicLab.DataImporter.Command {
  [StorableClass]
  [ViewableCommandInfoAttribute("Delete Rows beneath Threshold", 1, ColumnGroupState.Active,
    "Handle Missing Values", Position = 5, OptionsView = typeof(DeleteWithThresholdView))]
  public class DeleteRowsWithMissingValuesThresholdCommand : ColumnGroupCommandBase, IThresholdCommand {
    private Dictionary<int, IComparable[]> deletedRows;

    [Storable]
    private double threshold = 0.8;
    public double Threshold { get { return threshold; } set { threshold = value; } }

    [StorableConstructor]
    protected DeleteRowsWithMissingValuesThresholdCommand(bool deserializing)
      : base(deserializing) {
      deletedRows = new Dictionary<int, IComparable[]>();
    }

    public DeleteRowsWithMissingValuesThresholdCommand(DataSet dataSet, string columnGroupName)
      : base(dataSet, columnGroupName) {
      deletedRows = new Dictionary<int, IComparable[]>();
    }

    public override void Execute() {
      base.Execute();
      IComparable[] row;

      double columnsCount = ColumnGroup.Columns.Count();
      for (int rowInd = 0; rowInd < ColumnGroup.RowCount; rowInd++) {
        row = ColumnGroup.GetRow(rowInd);
        double setValues = ColumnGroup.GetRow(rowInd).Where(x => x != null).Count();
        if (setValues / columnsCount < Threshold) {
          deletedRows[rowInd] = row;
        }
      }

      foreach (int rowInd in deletedRows.Select(x => x.Key).Reverse()) {
        ColumnGroup.DeleteRow(rowInd);
      }

      ColumnGroup.FireChanged();
      ColumnGroup = null;
    }

    public override void UndoExecute() {
      base.UndoExecute();
      foreach (KeyValuePair<int, IComparable[]> pair in deletedRows) {
        ColumnGroup.InsertRow(pair.Key, pair.Value);
      }
      deletedRows.Clear();
      ColumnGroup.FireChanged();
      ColumnGroup = null;
    }

    public override string Description {
      get { return "Delete rows with a missing value percentage beneath a certain threshold"; }
    }
  }
}