public override SchemaShape GetOutputSchema(SchemaShape inputSchema)
{
var addedCols = DataViewConstructionUtils.GetSchemaColumns(Transformer.AddedSchema);
var addedSchemaShape = SchemaShape.Create(SchemaBuilder.MakeSchema(addedCols));
var result = inputSchema.Columns.ToDictionary(x => x.Name);
var inputDef = InternalSchemaDefinition.Create(typeof(TSrc), Transformer.InputSchemaDefinition);
foreach (var col in inputDef.Columns)
{
if (!result.TryGetValue(col.ColumnName, out var column))
{
throw Contracts.ExceptSchemaMismatch(nameof(inputSchema), "input", col.ColumnName);
}
SchemaShape.GetColumnTypeShape(col.ColumnType, out var vecKind, out var itemType, out var isKey);
// Special treatment for vectors: if we expect variable vector, we also allow fixed-size vector.
if (itemType != column.ItemType || isKey != column.IsKey ||
vecKind == SchemaShape.Column.VectorKind.Scalar && column.Kind != SchemaShape.Column.VectorKind.Scalar ||
vecKind == SchemaShape.Column.VectorKind.Vector && column.Kind != SchemaShape.Column.VectorKind.Vector ||
vecKind == SchemaShape.Column.VectorKind.VariableVector && column.Kind == SchemaShape.Column.VectorKind.Scalar)
{
throw Contracts.ExceptSchemaMismatch(nameof(inputSchema), "input", col.ColumnName, col.ColumnType.ToString(), column.GetTypeString());
}
}
foreach (var addedCol in addedSchemaShape.Columns)
{
result[addedCol.Name] = addedCol;
}
return(new SchemaShape(result.Values));
}
/// <summary>
/// The 'reapply' constructor.
/// </summary>
private StatefulFilterTransform(IHostEnvironment env, StatefulFilterTransform <TSrc, TDst, TState> transform, IDataView newSource)
{
_host.AssertValue(transform);
_host.AssertValue(newSource);
_source = newSource;
_filterFunc = transform._filterFunc;
_typedSource = TypedCursorable <TSrc> .Create(_host, newSource, false, transform._inputSchemaDefinition);
_addedSchema = transform._addedSchema;
_bindings = new ColumnBindings(newSource.Schema, DataViewConstructionUtils.GetSchemaColumns(_addedSchema));
}
public override SchemaShape GetOutputSchema(SchemaShape inputSchema)
{
var addedCols = DataViewConstructionUtils.GetSchemaColumns(Transformer.AddedSchema);
var addedSchemaShape = SchemaShape.Create(new Schema(addedCols));
var result = inputSchema.Columns.ToDictionary(x => x.Name);
foreach (var addedCol in addedSchemaShape.Columns)
{
result[addedCol.Name] = addedCol;
}
return(new SchemaShape(result.Values));
}
/// <summary>
/// Create a filter transform
/// </summary>
/// <param name="env">The host environment</param>
/// <param name="source">The dataview upon which we construct the transform</param>
/// <param name="filterFunc">The function by which we transform source to destination columns and decide whether
/// to keep the row.</param>
/// <param name="initStateAction">The function that is called once per cursor to initialize state. Can be null.</param>
/// <param name="inputSchemaDefinition">The schema definition overrides for <typeparamref name="TSrc"/></param>
/// <param name="outputSchemaDefinition">The schema definition overrides for <typeparamref name="TDst"/></param>
public StatefulFilterTransform(IHostEnvironment env, IDataView source, Func <TSrc, TDst, TState, bool> filterFunc,
Action <TState> initStateAction,
SchemaDefinition inputSchemaDefinition = null, SchemaDefinition outputSchemaDefinition = null)
{
_host = env.Register(RegistrationName);
_host.AssertValue(source, "source");
_host.AssertValue(filterFunc, "filterFunc");
_host.AssertValueOrNull(initStateAction);
_host.AssertValueOrNull(inputSchemaDefinition);
_host.AssertValueOrNull(outputSchemaDefinition);
_source = source;
_filterFunc = filterFunc;
_initStateAction = initStateAction;
_inputSchemaDefinition = inputSchemaDefinition;
_typedSource = TypedCursorable <TSrc> .Create(_host, Source, false, inputSchemaDefinition);
var outSchema = InternalSchemaDefinition.Create(typeof(TDst), outputSchemaDefinition);
_addedSchema = outSchema;
_bindings = new ColumnBindings(Source.Schema, DataViewConstructionUtils.GetSchemaColumns(outSchema));
}
/// <summary>
/// Create a filter transform that is savable iff <paramref name="saveAction"/> and <paramref name="loadFunc"/> are
/// not null.
/// </summary>
/// <param name="env">The host environment</param>
/// <param name="source">The dataview upon which we construct the transform</param>
/// <param name="filterFunc">The function by which we transform source to destination columns and decide whether
/// to keep the row.</param>
/// <param name="initStateAction">The function that is called once per cursor to initialize state. Can be null.</param>
/// <param name="saveAction">An action that allows us to save state to the serialization stream. May be
/// null simultaneously with <paramref name="loadFunc"/>.</param>
/// <param name="loadFunc">A function that given the serialization stream and a data view, returns
/// an <see cref="ITransformTemplate"/>. The intent is, this returned object should itself be a
/// <see cref="CustomMappingTransformer{TSrc,TDst}"/>, but this is not strictly necessary. This delegate should be
/// a static non-lambda method that this assembly can legally call. May be null simultaneously with
/// <paramref name="saveAction"/>.</param>
/// <param name="inputSchemaDefinition">The schema definition overrides for <typeparamref name="TSrc"/></param>
/// <param name="outputSchemaDefinition">The schema definition overrides for <typeparamref name="TDst"/></param>
public StatefulFilterTransform(IHostEnvironment env, IDataView source, Func <TSrc, TDst, TState, bool> filterFunc,
Action <TState> initStateAction,
Action <BinaryWriter> saveAction, LambdaTransform.LoadDelegate loadFunc,
SchemaDefinition inputSchemaDefinition = null, SchemaDefinition outputSchemaDefinition = null)
: base(env, RegistrationName, saveAction, loadFunc)
{
Host.AssertValue(source, "source");
Host.AssertValue(filterFunc, "filterFunc");
Host.AssertValueOrNull(initStateAction);
Host.AssertValueOrNull(inputSchemaDefinition);
Host.AssertValueOrNull(outputSchemaDefinition);
_source = source;
_filterFunc = filterFunc;
_initStateAction = initStateAction;
_inputSchemaDefinition = inputSchemaDefinition;
_typedSource = TypedCursorable <TSrc> .Create(Host, Source, false, inputSchemaDefinition);
var outSchema = InternalSchemaDefinition.Create(typeof(TDst), outputSchemaDefinition);
_addedSchema = outSchema;
_bindings = new ColumnBindings(Schema.Create(Source.Schema), DataViewConstructionUtils.GetSchemaColumns(outSchema));
}