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>
/// Convert an <see cref="IDataView"/> into a strongly-typed <see cref="IEnumerable{TRow}"/>.
/// </summary>
/// <typeparam name="TRow">The user-defined row type.</typeparam>
/// <param name="data">The underlying data view.</param>
/// <param name="env">The environment.</param>
/// <param name="reuseRowObject">Whether to return the same object on every row, or allocate a new one per row.</param>
/// <param name="ignoreMissingColumns">Whether to ignore the case when a requested column is not present in the data view.</param>
/// <param name="schemaDefinition">Optional user-provided schema definition. If it is not present, the schema is inferred from the definition of T.</param>
/// <returns>The <see cref="IEnumerable{TRow}"/> that holds the data in <paramref name="data"/>. It can be enumerated multiple times.</returns>
public static IEnumerable <TRow> AsEnumerable <TRow>(this IDataView data, IHostEnvironment env, bool reuseRowObject,
bool ignoreMissingColumns = false, SchemaDefinition schemaDefinition = null)
where TRow : class, new()
{
Contracts.AssertValue(env);
env.CheckValue(data, nameof(data));
env.CheckValueOrNull(schemaDefinition);
var engine = new PipeEngine <TRow>(env, data, ignoreMissingColumns, schemaDefinition);
return(engine.RunPipe(reuseRowObject));
}
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);
}