source: branches/DataPreprocessing/HeuristicLab.DataPreprocessing/3.3/Implementations/TransformationLogic.cs @ 10611

#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;

namespace HeuristicLab.DataPreprocessing {

  public class TransformationLogic : ITransformationLogic {

    private readonly ITransactionalPreprocessingData preprocessingData;
    private readonly ISearchLogic searchLogic;
    private readonly IStatisticsLogic statisticsLogic;

    public TransformationLogic(ITransactionalPreprocessingData thePreprocessingData, ISearchLogic theSearchLogic, IStatisticsLogic theStatisticsLogic) {
      preprocessingData = thePreprocessingData;
      searchLogic = theSearchLogic;
      statisticsLogic = theStatisticsLogic;
    }

    public void DeleteRowsWithMissingValuesGreater(double percent) {
      for (int i = 0; i < preprocessingData.Rows; ++i) {
        int missingCount = statisticsLogic.GetRowMissingValueCount(i);
        if (100f / preprocessingData.Columns * missingCount >= percent) {
          preprocessingData.DeleteRow(i);
          --i;
        }
      }
    }

    public void DeleteColumnsWithMissingValuesGreater(float percent) {
      for (int i = 0; i < preprocessingData.Columns; ++i) {
        int missingCount = statisticsLogic.GetMissingValueCount(i);
        if (100f / preprocessingData.Columns * missingCount >= percent) {
          preprocessingData.DeleteColumn(i);
          --i;
        }
      }
    }

    public void DeleteColumnsWithVarianceSmaller(double variance) {
      for (int i = 0; i < preprocessingData.Columns; ++i) {
        if (preprocessingData.IsType<double>(i) || preprocessingData.IsType<DateTime>(i)) {
          double columnVariance = statisticsLogic.GetVariance(i);
          if (columnVariance < variance) {
            preprocessingData.DeleteColumn(i);
            --i;
          }
        }
      }
    }

  }
}