public SaveDataCommand(IHostEnvironment env, Arguments args)
: base(env, args, nameof(SaveDataCommand))
{
Contracts.CheckNonEmpty(args.OutputDataFile, nameof(args.OutputDataFile));
Utils.CheckOptionalUserDirectory(args.OutputDataFile, nameof(args.OutputDataFile));
}
public RouteInfo(string routeId)
{
Contracts.CheckNonEmpty(routeId, nameof(routeId));
RouteId = routeId;
}
public ColumnType GetMetadataTypeOrNull(string kind, int col)
{
Contracts.CheckNonEmpty(kind, nameof(kind));
Contracts.CheckParam(0 <= col && col < ColumnCount, nameof(col));
return(Input.GetMetadataTypeOrNull(kind, Infos[col].Source));
}
public void GetMetadata <TValue>(string kind, int col, ref TValue value)
{
Contracts.CheckNonEmpty(kind, nameof(kind));
Contracts.CheckParam(0 <= col && col < ColumnCount, nameof(col));
Input.GetMetadata(kind, Infos[col].Source, ref value);
}
/// <summary>
/// Extract all values of one column of the data view in a form of an <see cref="IEnumerable{T}"/>.
/// </summary>
/// <typeparam name="T">The type of the values. This must match the actual column type.</typeparam>
/// <param name="data">The data view to get the column from.</param>
/// <param name="column">The column to be extracted.</param>
public static IEnumerable <T> GetColumn <T>(this IDataView data, DataViewSchema.Column column)
{
Contracts.CheckValue(data, nameof(data));
Contracts.CheckNonEmpty(column.Name, nameof(column));
var colIndex = column.Index;
var colType = column.Type;
var colName = column.Name;
// Use column index as the principle address of the specified input column and check if that address in data contains
// the column indicated.
if (data.Schema[colIndex].Name != colName || data.Schema[colIndex].Type != colType)
{
throw Contracts.ExceptParam(nameof(column), string.Format("column with name {0}, type {1}, and index {2} cannot be found in {3}",
colName, colType, colIndex, nameof(data)));
}
// There are two decisions that we make here:
// - Is the T an array type?
// - If yes, we need to map VBuffer to array and densify.
// - If no, this is not needed.
// - Does T (or item type of T if it's an array) equal to the data view type?
// - If this is the same type, we can map directly.
// - Otherwise, we need a conversion delegate.
if (colType.RawType == typeof(T))
{
// Direct mapping is possible.
return(GetColumnDirect <T>(data, colIndex));
}
else if (typeof(T) == typeof(string) && colType is TextDataViewType)
{
// Special case of ROM<char> to string conversion.
Delegate convert = (Func <ReadOnlyMemory <char>, string>)((ReadOnlyMemory <char> txt) => txt.ToString());
Func <IDataView, int, Func <int, T>, IEnumerable <T> > del = GetColumnConvert;
var meth = del.Method.GetGenericMethodDefinition().MakeGenericMethod(typeof(T), colType.RawType);
return((IEnumerable <T>)(meth.Invoke(null, new object[] { data, colIndex, convert })));
}
else if (typeof(T).IsArray)
{
// Output is an array type.
if (!(colType is VectorType colVectorType))
{
throw Contracts.ExceptParam(nameof(column), string.Format("Cannot load vector type, {0}, specified in {1} to the user-defined type, {2}.", column.Type, nameof(column), typeof(T)));
}
var elementType = typeof(T).GetElementType();
if (elementType == colVectorType.ItemType.RawType)
{
// Direct mapping of items.
Func <IDataView, int, IEnumerable <int[]> > del = GetColumnArrayDirect <int>;
var meth = del.Method.GetGenericMethodDefinition().MakeGenericMethod(elementType);
return((IEnumerable <T>)meth.Invoke(null, new object[] { data, colIndex }));
}
else if (elementType == typeof(string) && colVectorType.ItemType is TextDataViewType)
{
// Conversion of DvText items to string items.
Delegate convert = (Func <ReadOnlyMemory <char>, string>)((ReadOnlyMemory <char> txt) => txt.ToString());
Func <IDataView, int, Func <int, long>, IEnumerable <long[]> > del = GetColumnArrayConvert;
var meth = del.Method.GetGenericMethodDefinition().MakeGenericMethod(elementType, colVectorType.ItemType.RawType);
return((IEnumerable <T>)meth.Invoke(null, new object[] { data, colIndex, convert }));
}
// Fall through to the failure.
}
throw Contracts.ExceptParam(nameof(column), string.Format("Cannot map column (name: {0}, type: {1}) in {2} to the user-defined type, {3}.",
column.Name, column.Type, nameof(data), typeof(T)));
}
