source: trunk/sources/HeuristicLab.DataPreprocessing/3.4/Data/IPreprocessingData.cs @ 15518

Last change on this file since 15518 was 15518, checked in by pfleck, 21 months ago

#2809: merged branch to trunk

File size: 4.5 KB
Line 
1#region License Information
2/* HeuristicLab
3 * Copyright (C) 2002-2016 Heuristic and Evolutionary Algorithms Laboratory (HEAL)
4 *
5 * This file is part of HeuristicLab.
6 *
7 * HeuristicLab is free software: you can redistribute it and/or modify
8 * it under the terms of the GNU General Public License as published by
9 * the Free Software Foundation, either version 3 of the License, or
10 * (at your option) any later version.
11 *
12 * HeuristicLab is distributed in the hope that it will be useful,
13 * but WITHOUT ANY WARRANTY; without even the implied warranty of
14 * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
15 * GNU General Public License for more details.
16 *
17 * You should have received a copy of the GNU General Public License
18 * along with HeuristicLab. If not, see <http://www.gnu.org/licenses/>.
19 */
20#endregion
21
22using System;
23using System.Collections.Generic;
24using HeuristicLab.Core;
25using HeuristicLab.Data;
26using HeuristicLab.Problems.DataAnalysis;
27
28namespace HeuristicLab.DataPreprocessing {
29  public interface IPreprocessingData : INamedItem {
30    #region Cells
31    bool IsCellEmpty(int columnIndex, int rowIndex);
32    T GetCell<T>(int columnIndex, int rowIndex);
33
34    void SetCell<T>(int columnIndex, int rowIndex, T value);
35
36    string GetCellAsString(int columnIndex, int rowIndex);
37
38    IList<T> GetValues<T>(int columnIndex, bool considerSelection = false);
39
40    void SetValues<T>(int columnIndex, IList<T> values);
41    bool SetValue(string value, int columnIndex, int rowIndex);
42
43    int Columns { get; }
44    int Rows { get; }
45    #endregion
46
47    #region Rows
48    void InsertRow(int rowIndex);
49    void DeleteRow(int rowIndex);
50    void DeleteRowsWithIndices(IEnumerable<int> rows);
51    void InsertColumn<T>(string variableName, int columnIndex);
52
53    void DeleteColumn(int columnIndex);
54
55    void RenameColumn(int columnIndex, string name);
56    void RenameColumns(IList<string> names);
57
58    bool AreAllStringColumns(IEnumerable<int> columnIndices);
59    #endregion
60
61    #region Variables
62    IEnumerable<string> VariableNames { get; }
63    IEnumerable<string> GetDoubleVariableNames();
64    string GetVariableName(int columnIndex);
65    int GetColumnIndex(string variableName);
66
67    bool VariableHasType<T>(int columnIndex);
68    Type GetVariableType(int columnIndex);
69
70    IList<string> InputVariables { get; }
71    string TargetVariable { get; } // optional
72    #endregion
73
74    #region Partitions
75    IntRange TrainingPartition { get; }
76    IntRange TestPartition { get; }
77    #endregion
78
79    #region Transformations
80    IList<ITransformation> Transformations { get; }
81    #endregion
82
83    #region Validation
84    bool Validate(string value, out string errorMessage, int columnIndex);
85    #endregion
86
87    #region Import & Export
88    void Import(IDataAnalysisProblemData problemData);
89    Dataset ExportToDataset();
90    #endregion
91
92    #region Selection
93    IDictionary<int, IList<int>> Selection { get; set; }
94    void ClearSelection();
95
96    event EventHandler SelectionChanged;
97    #endregion
98
99    #region Transactions
100    event DataPreprocessingChangedEventHandler Changed;
101
102    bool IsUndoAvailable { get; }
103    void Undo();
104    void InTransaction(Action action, DataPreprocessingChangedEventType type = DataPreprocessingChangedEventType.Any);
105    void BeginTransaction(DataPreprocessingChangedEventType type);
106    void EndTransaction();
107    #endregion
108
109    #region Statistics
110    T GetMin<T>(int columnIndex, bool considerSelection = false, T emptyValue = default(T));
111    T GetMax<T>(int columnIndex, bool considerSelection = false, T emptyValue = default(T));
112    T GetMean<T>(int columnIndex, bool considerSelection = false, T emptyValue = default(T));
113    T GetMedian<T>(int columnIndex, bool considerSelection = false, T emptyValue = default(T)) where T : IComparable<T>;
114    T GetMode<T>(int columnIndex, bool considerSelection = false, T emptyValue = default(T)) where T : IEquatable<T>;
115    T GetStandardDeviation<T>(int columnIndex, bool considerSelection = false, T emptyValue = default(T));
116    T GetVariance<T>(int columnIndex, bool considerSelection = false, T emptyValue = default(T));
117    T GetQuantile<T>(double alpha, int columnIndex, bool considerSelection = false, T emptyValue = default(T)) where T : IComparable<T>;
118    int GetDistinctValues<T>(int columnIndex, bool considerSelection = false);
119
120    int GetMissingValueCount();
121    int GetMissingValueCount(int columnIndex);
122    int GetRowMissingValueCount(int rowIndex);
123    #endregion
124  }
125}
Note: See TracBrowser for help on using the repository browser.