public SchemaShape GetOutputSchema(SchemaShape inputSchema)
{
_host.CheckValue(inputSchema, nameof(inputSchema));
var result = inputSchema.Columns.ToDictionary(x => x.Name);
foreach (var colInfo in _columns)
{
var col = inputSchema.FindColumn(colInfo.Input);
if (col == null)
{
throw _host.ExceptSchemaMismatch(nameof(inputSchema), "input", colInfo.Input);
}
if ((col.ItemType.ItemType.RawKind == default) || !(col.ItemType.IsVector || col.ItemType.IsPrimitive))
{
throw _host.ExceptSchemaMismatch(nameof(inputSchema), "input", colInfo.Input);
}
string[] metadata;
if (col.MetadataKinds.Contains(MetadataUtils.Kinds.SlotNames))
{
metadata = new[] { MetadataUtils.Kinds.SlotNames, MetadataUtils.Kinds.KeyValues }
}
;
else
{
metadata = new[] { MetadataUtils.Kinds.KeyValues }
};
result[colInfo.Output] = new SchemaShape.Column(colInfo.Output, col.Kind, NumberType.U4, true, metadata);
}
return(new SchemaShape(result.Values));
}
}
private void CheckInputSchema(SchemaShape inputSchema)
{
// Verify that all required input columns are present, and are of the same type.
var featureCol = inputSchema.FindColumn(FeatureColumn.Name);
if (featureCol == null)
{
throw Host.Except($"Feature column '{FeatureColumn.Name}' is not found");
}
if (!FeatureColumn.IsCompatibleWith(featureCol))
{
throw Host.Except($"Feature column '{FeatureColumn.Name}' is not compatible");
}
if (WeightColumn != null)
{
var weightCol = inputSchema.FindColumn(WeightColumn.Name);
if (weightCol == null)
{
throw Host.Except($"Weight column '{WeightColumn.Name}' is not found");
}
if (!WeightColumn.IsCompatibleWith(weightCol))
{
throw Host.Except($"Weight column '{WeightColumn.Name}' is not compatible");
}
}
// Special treatment for label column: we allow different types of labels, so the trainers
// may define their own requirements on the label column.
if (LabelColumn != null)
{
var labelCol = inputSchema.FindColumn(LabelColumn.Name);
if (labelCol == null)
{
throw Host.Except($"Label column '{LabelColumn.Name}' is not found");
}
CheckLabelCompatible(labelCol);
}
}
/// <summary>
/// Checks whether this object is consistent with an actual schema shape from a dynamic object,
/// throwing exceptions if not.
/// </summary>
/// <param name="ectx">The context on which to throw exceptions</param>
/// <param name="shape">The schema shape to check</param>
public void Check(IExceptionContext ectx, SchemaShape shape)
{
Contracts.AssertValue(ectx);
ectx.AssertValue(shape);
foreach (var pair in Pairs)
{
var col = shape.FindColumn(pair.Key);
if (col == null)
{
throw ectx.ExceptParam(nameof(shape), $"Column named '{pair.Key}' was not found");
}
var type = GetTypeOrNull(col);
if ((type != null && !pair.Value.IsAssignableFromStaticPipeline(type)) || (type == null && IsStandard(ectx, pair.Value)))
{
// When not null, we can use IsAssignableFrom to indicate we could assign to this, so as to allow
// for example Key<uint, string> to be considered to be compatible with Key<uint>.
// In the null case, while we cannot directly verify an unrecognized type, we can at least verify
// that the statically declared type should not have corresponded to a recognized type.
if (!pair.Value.IsAssignableFromStaticPipeline(type))
{
// This is generally an error, unless it's the situation where the asserted type is Key<,> but we could
// only resolve it so far as Key<>, since for the moment the SchemaShape cannot determine the type of key
// value metadata. In which case, we can check if the declared type is a subtype of the key that was determined
// from the analysis.
if (pair.Value.IsGenericType && pair.Value.GetGenericTypeDefinition() == typeof(Key <,>) &&
type.IsAssignableFromStaticPipeline(pair.Value))
{
continue;
}
throw ectx.ExceptParam(nameof(shape),
$"Column '{pair.Key}' of type '{col.GetTypeString()}' cannot be expressed statically as type '{pair.Value}'.");
}
}
}
}
