/// <summary>
/// Connects a row classifier
/// </summary>
/// <param name="classifier"></param>
/// <param name="dataTable"></param>
/// <param name="analysis"></param>
/// <param name="name">Optional name to give the node</param>
/// <returns></returns>
public WireBuilder AddClassifier(IRowClassifier classifier, IDataTable dataTable,
IDataTableAnalysis analysis = null, string name = null)
{
var node = _factory.CreateClassifier(classifier, dataTable, analysis, name);
_SetNode(node.RowClassifier);
return(SetNewSize(node.OutputSize));
}
public DataTableVectoriser(IDataTable table, bool useTargetColumnIndex)
{
_column = table.Columns;
_classColumnIndex = useTargetColumnIndex ? table.TargetColumnIndex : -1;
_analysis = table.GetAnalysis();
foreach (var columnInfo in _analysis.ColumnInfo)
{
var column = table.Columns[columnInfo.ColumnIndex];
var isTarget = columnInfo.ColumnIndex == _classColumnIndex;
int size = 0;
var isContinuous = false;
if (columnInfo is IIndexColumnInfo indexColumn)
{
size = Convert.ToInt32(indexColumn.MaxIndex + 1);
}
else
{
isContinuous = column.IsContinuous || !columnInfo.NumDistinct.HasValue;
if (isContinuous)
{
size = 1;
if (!isTarget)
{
_columnName.Add(column.Name);
}
}
else
{
size = columnInfo.NumDistinct.Value;
var categoryIndex = columnInfo.DistinctValues.Select(s => s.ToString()).OrderBy(s => s).Select((s, i) => Tuple.Create(s, i)).ToList();
var columnMap = categoryIndex.ToDictionary(d => d.Item1, d => d.Item2);
var reverseColumnMap = categoryIndex.ToDictionary(d => d.Item2, d => d.Item1);
_columnMap.Add(columnInfo.ColumnIndex, columnMap);
_reverseColumnMap.Add(columnInfo.ColumnIndex, reverseColumnMap);
if (!isTarget)
{
for (var i = 0; i < size; i++)
{
_columnName.Add(column.Name + ":" + reverseColumnMap[i]);
}
}
}
}
if (isTarget)
{
_outputSize = size;
_isTargetContinuous = isContinuous;
_hasTarget = true;
}
else
{
_inputSize += size;
}
}
}
//readonly List<IRow> _data = new List<IRow>();
public RowClassifier(ILinearAlgebraProvider lap, IRowClassifier classifier,
IDataTable dataTable, IDataTableAnalysis analysis, string name = null) : base(name)
{
_lap = lap;
_dataTable = dataTable;
_classifier = classifier;
_targetLabel = analysis.ColumnInfo.First(ci => dataTable.Columns[ci.ColumnIndex].IsTarget).
DistinctValues.Select((v, i) => (v.ToString(), i)).ToDictionary(d => d.Item1, d => d.Item2);
}
public IDataTableAnalysis GetAnalysis()
{
if (_analysis == null)
{
var analysis = new DataTableAnalysis(this);
Process(analysis);
_analysis = analysis;
}
return(_analysis);
}
/// <summary>
/// Create a row classifier node
/// </summary>
/// <param name="classifier">The classifier for each row</param>
/// <param name="dataTable">The data table that contains the rows to classify (linked by mini batch index)</param>
/// <param name="analysis">Optional data table analysis data</param>
/// <param name="name">Optional name to give the node</param>
/// <returns></returns>
public (INode RowClassifier, int OutputSize) CreateClassifier(IRowClassifier classifier, IDataTable dataTable, IDataTableAnalysis analysis = null, string name = null)
{
var ret = new RowClassifier(_lap, classifier, dataTable, analysis ?? dataTable.GetAnalysis(), name);
return(ret, ret.OutputSize);
}
