internal BatchPredictionEngine(IHostEnvironment env, Stream modelStream, bool ignoreMissingColumns,
SchemaDefinition inputSchemaDefinition = null, SchemaDefinition outputSchemaDefinition = null)
{
Contracts.AssertValue(env);
Contracts.AssertValue(modelStream);
Contracts.AssertValueOrNull(inputSchemaDefinition);
Contracts.AssertValueOrNull(outputSchemaDefinition);
// Initialize pipe.
_srcDataView = DataViewConstructionUtils.CreateFromEnumerable(env, new TSrc[] { }, inputSchemaDefinition);
// Load transforms.
var pipe = env.LoadTransforms(modelStream, _srcDataView);
// Load predictor (if present) and apply default scorer.
// REVIEW: distinguish the case of predictor / no predictor?
var predictor = env.LoadPredictorOrNull(modelStream);
if (predictor != null)
{
var roles = ModelFileUtils.LoadRoleMappingsOrNull(env, modelStream);
pipe = roles != null
? env.CreateDefaultScorer(RoleMappedData.CreateOpt(pipe, roles), predictor)
: env.CreateDefaultScorer(env.CreateExamples(pipe, "Features"), predictor);
}
_pipeEngine = new PipeEngine <TDst>(env, pipe, ignoreMissingColumns, outputSchemaDefinition);
}
/// <summary>
/// Create a new <see cref="IDataView"/> over an enumerable of the items of user-defined type.
/// The user maintains ownership of the <paramref name="data"/> and the resulting data view will
/// never alter the contents of the <paramref name="data"/>.
/// Since <see cref="IDataView"/> is assumed to be immutable, the user is expected to support
/// multiple enumeration of the <paramref name="data"/> that would return the same results, unless
/// the user knows that the data will only be cursored once.
///
/// One typical usage for streaming data view could be: create the data view that lazily loads data
/// as needed, then apply pre-trained transformations to it and cursor through it for transformation
/// results. This is how <see cref="BatchPredictionEngine{TSrc,TDst}"/> is implemented.
/// </summary>
/// <typeparam name="TRow">The user-defined item type.</typeparam>
/// <param name="env">The host environment to use for data view creation.</param>
/// <param name="data">The data to wrap around.</param>
/// <param name="schemaDefinition">The optional schema definition of the data view to create. If <c>null</c>,
/// the schema definition is inferred from <typeparamref name="TRow"/>.</param>
/// <returns>The constructed <see cref="IDataView"/>.</returns>
public static IDataView CreateStreamingDataView <TRow>(this IHostEnvironment env, IEnumerable <TRow> data, SchemaDefinition schemaDefinition = null)
where TRow : class
{
Contracts.CheckValue(env, nameof(env));
env.CheckValue(data, nameof(data));
env.CheckValueOrNull(schemaDefinition);
return(DataViewConstructionUtils.CreateFromEnumerable(env, data, schemaDefinition));
}
internal BatchPredictionEngine(IHostEnvironment env, IDataView dataPipeline, bool ignoreMissingColumns,
SchemaDefinition inputSchemaDefinition = null, SchemaDefinition outputSchemaDefinition = null)
{
Contracts.AssertValue(env);
Contracts.AssertValue(dataPipeline);
Contracts.AssertValueOrNull(inputSchemaDefinition);
Contracts.AssertValueOrNull(outputSchemaDefinition);
// Initialize pipe.
_srcDataView = DataViewConstructionUtils.CreateFromEnumerable(env, new TSrc[] { }, inputSchemaDefinition);
var pipe = ApplyTransformUtils.ApplyAllTransformsToData(env, dataPipeline, _srcDataView);
_pipeEngine = new PipeEngine <TDst>(env, pipe, ignoreMissingColumns, outputSchemaDefinition);
}
internal BatchPredictionEngine(IHostEnvironment env, Stream modelStream, bool ignoreMissingColumns,
SchemaDefinition inputSchemaDefinition = null, SchemaDefinition outputSchemaDefinition = null)
{
Contracts.AssertValue(env);
Contracts.AssertValue(modelStream);
Contracts.AssertValueOrNull(inputSchemaDefinition);
Contracts.AssertValueOrNull(outputSchemaDefinition);
// Initialize pipe.
_srcDataView = DataViewConstructionUtils.CreateFromEnumerable(env, new TSrc[] { }, inputSchemaDefinition);
var pipe = DataViewConstructionUtils.LoadPipeWithPredictor(env, modelStream, _srcDataView);
_pipeEngine = new PipeEngine <TDst>(env, pipe, ignoreMissingColumns, outputSchemaDefinition);
}