#region License Information /* HeuristicLab * Copyright (C) 2002-2015 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 . */ #endregion using System; using System.Collections; using System.Collections.Generic; namespace HeuristicLab.DataPreprocessing { public class SearchLogic { private readonly ITransactionalPreprocessingData preprocessingData; private readonly FilterLogic filterLogic; private Dictionary> MissingValueIndicies { get; set; } private Dictionary ValuesWithoutNaN { get; set; } public IEnumerable VariableNames { get { return preprocessingData.VariableNames; } } public int Columns { get { return preprocessingData.Columns; } } public int Rows { get { return preprocessingData.Rows; } } public SearchLogic(ITransactionalPreprocessingData thePreprocessingData, FilterLogic theFilterLogic) { preprocessingData = thePreprocessingData; filterLogic = theFilterLogic; MissingValueIndicies = new Dictionary>(); ValuesWithoutNaN = new Dictionary(); preprocessingData.Changed += PreprocessingData_Changed; filterLogic.FilterChanged += FilterLogic_FilterChanged; } void FilterLogic_FilterChanged(object sender, EventArgs e) { //recalculate for (int i = 0; i < Columns; i++) { MissingValueIndicies.Remove(i); ValuesWithoutNaN.Remove(i); } } void PreprocessingData_Changed(object sender, DataPreprocessingChangedEventArgs e) { switch (e.Type) { case DataPreprocessingChangedEventType.DeleteColumn: case DataPreprocessingChangedEventType.ChangeColumn: MissingValueIndicies.Remove(e.Column); ValuesWithoutNaN.Remove(e.Column); break; case DataPreprocessingChangedEventType.AddColumn: //cache does not need to be updated, will be calculated the first time it is requested break; case DataPreprocessingChangedEventType.DeleteRow: case DataPreprocessingChangedEventType.AddRow: case DataPreprocessingChangedEventType.ChangeItem: case DataPreprocessingChangedEventType.Any: case DataPreprocessingChangedEventType.Transformation: default: MissingValueIndicies = new Dictionary>(); ValuesWithoutNaN = new Dictionary(); break; } } public IDictionary> GetMissingValueIndices() { var dic = new Dictionary>(); for (int i = 0; i < preprocessingData.Columns; ++i) { dic.Add(i, GetMissingValueIndices(i)); } return dic; } public IList GetMissingValueIndices(int columnIndex) { int index = 0; var indices = new List(); if (MissingValueIndicies.ContainsKey(columnIndex)) { return MissingValueIndicies[columnIndex]; } if (preprocessingData.VariableHasType(columnIndex)) { foreach (var v in preprocessingData.GetValues(columnIndex)) { if (double.IsNaN(v)) indices.Add(index); index++; } } else if (preprocessingData.VariableHasType(columnIndex)) { foreach (var v in preprocessingData.GetValues(columnIndex)) { if (string.IsNullOrEmpty(v)) indices.Add(index); index++; } } else if (preprocessingData.VariableHasType(columnIndex)) { foreach (var v in preprocessingData.GetValues(columnIndex)) { if (DateTime.MinValue.Equals(v)) indices.Add(index); index++; } } else { throw new ArgumentException("column " + columnIndex + " contains a non supported type."); } MissingValueIndicies[columnIndex] = indices; return MissingValueIndicies[columnIndex]; } public bool IsMissingValue(int columnIndex, int rowIndex) { if (preprocessingData.VariableHasType(columnIndex)) { return double.IsNaN(preprocessingData.GetCell(columnIndex, rowIndex)); } else if (preprocessingData.VariableHasType(columnIndex)) { return string.IsNullOrEmpty(preprocessingData.GetCell(columnIndex, rowIndex)); } else if (preprocessingData.VariableHasType(columnIndex)) { return preprocessingData.GetCell(columnIndex, rowIndex).Equals(DateTime.MinValue); } else { throw new ArgumentException("cell in column " + columnIndex + " and row index " + rowIndex + " contains a non supported type."); } } public IEnumerable GetValuesWithoutNaN(int columnIndex, bool considerSelection) { if (considerSelection) { var selectedRows = preprocessingData.Selection[columnIndex]; List values = new List(); foreach (var rowIdx in selectedRows) { if (!IsMissingValue(columnIndex, rowIdx)) { values.Add(preprocessingData.GetCell(columnIndex, rowIdx)); } } return values; } else { if (!ValuesWithoutNaN.ContainsKey(columnIndex)) { List values = new List(); for (int row = 0; row < preprocessingData.Rows; ++row) { if (!IsMissingValue(columnIndex, row)) { values.Add(preprocessingData.GetCell(columnIndex, row)); } } ValuesWithoutNaN[columnIndex] = values; } return (IEnumerable)ValuesWithoutNaN[columnIndex]; } } } }