/// <summary>
/// Auto-detect purpose for the data view columns.
/// </summary>
public static PurposeInference.Column[] InferPurposes(MLContext context, IDataView data, string label,
PurposeInference.Column[] columnOverrides = null)
{
var labelColumn = data.GetColumn(label);
// select columns to include in inferencing
var columnIndices = CalcIncludedIndices(data.Schema.Count, labelColumn.Index, columnOverrides);
// do purpose inferencing
var intermediateCols = InferPurposes(context, data, columnIndices);
// result to return to caller
var result = new PurposeInference.Column[data.Schema.Count];
// add label column to result
result[labelColumn.Index] = (new IntermediateColumn(data, labelColumn.Index, ColumnPurpose.Label)).GetColumn();
// add inferred columns to result
foreach (var intermediateCol in intermediateCols)
{
result[intermediateCol.ColumnIndex] = intermediateCol.GetColumn();
}
// add overrides to result
if (columnOverrides != null)
{
foreach (var columnOverride in columnOverrides)
{
result[columnOverride.ColumnIndex] = columnOverride;
}
}
return(result);
}
internal PurposeInference.Column[] ToInternalColumnPurposes()
{
var columnIndexList = AutoMlUtils.GetColumnIndexList(Source);
var result = new PurposeInference.Column[columnIndexList.Count];
for (var i = 0; i < columnIndexList.Count; i++)
{
var internalColumn = new PurposeInference.Column(columnIndexList[i], ColumnPurpose, Type);
result[i] = internalColumn;
}
return(result);
}
public IntermediateColumn(IDataView data, PurposeInference.Column column)
{
_data = data;
_columnId = column.ColumnIndex;
_purpose = column.Purpose;
_type = new Lazy <ColumnType>(() => _data.Schema[_columnId].Type);
_columnName = new Lazy <string>(() => _data.Schema[_columnId].Name);
_hasMissing = new Lazy <bool>(() =>
{
if (Type.ItemType() != NumberType.R4)
{
return(false);
}
return(Type.IsVector() ? HasMissingVector() : HasMissingOne());
});
}