source: branches/DataPreprocessing Enhancements/HeuristicLab.DataPreprocessing/3.4/Content/HistogramContent.cs @ 14725

#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 System;
using System.Drawing;
using System.Linq;
using HeuristicLab.Analysis;
using HeuristicLab.Common;
using HeuristicLab.Core;

namespace HeuristicLab.DataPreprocessing {
  [Item("Histogram", "Represents the histogram grid.")]
  public class HistogramContent : PreprocessingChartContent {
    public static new Image StaticItemImage {
      get { return HeuristicLab.Common.Resources.VSImageLibrary.Statistics; }
    }

    public string GroupingVariableName { get; set; }

    public int Bins { get; set; }
    public bool ExactBins { get; set; }

    public HistogramContent(IFilteredPreprocessingData preprocessingData)
      : base(preprocessingData) {
      Bins = 10;
      ExactBins = false;
    }

    public HistogramContent(HistogramContent content, Cloner cloner)
      : base(content, cloner) {
    }
    public override IDeepCloneable Clone(Cloner cloner) {
      return new HistogramContent(this, cloner);
    }

    public static DataTable CreateHistogram(IFilteredPreprocessingData preprocessingData, string variableName, string groupingVariableName, DataRowVisualProperties.DataRowHistogramAggregation aggregation) {
      {
        var dataTable = new DataTable();

        if (string.IsNullOrEmpty(groupingVariableName)) {
          var row = PreprocessingChartContent.CreateDataRow(preprocessingData, variableName, DataRowVisualProperties.DataRowChartType.Histogram);
          dataTable.Rows.Add(row);
          return dataTable;
        }

        dataTable.VisualProperties.Title = variableName;

        int variableIndex = preprocessingData.GetColumnIndex(variableName);
        var variableValues = preprocessingData.GetValues<double>(variableIndex);
        int groupVariableIndex = preprocessingData.GetColumnIndex(groupingVariableName);
        var groupingValues = Enumerable.Empty<string>();

        if (preprocessingData.VariableHasType<double>(groupVariableIndex)) {
          groupingValues = preprocessingData.GetValues<double>(groupVariableIndex).Select(x => x.ToString());
        } else if (preprocessingData.VariableHasType<string>(groupVariableIndex)) {
          groupingValues = preprocessingData.GetValues<string>(groupVariableIndex);
        } else if (preprocessingData.VariableHasType<DateTime>(groupVariableIndex)) {
          groupingValues = preprocessingData.GetValues<DateTime>(groupVariableIndex).Select(x => x.ToString());
        }

        var groups = groupingValues.Zip(variableValues, Tuple.Create).GroupBy(t => t.Item1, t => t.Item2);

        foreach (var group in groups) {
          var classRow = new DataRow();
          classRow.Name = group.Key;
          classRow.VisualProperties.ChartType = DataRowVisualProperties.DataRowChartType.Histogram;
          classRow.VisualProperties.Aggregation = aggregation;
          classRow.Values.AddRange(group);
          dataTable.Rows.Add(classRow);
        }
        return dataTable;
      }
    }


  }
}