public static IDataScorerTransform Create(IHostEnvironment env, Arguments args, IDataView data, ISchemaBoundMapper mapper, RoleMappedSchema trainSchema) { Contracts.CheckValue(env, nameof(env)); env.CheckValue(data, nameof(data)); env.CheckValue(mapper, nameof(mapper)); if (args.Top <= 0 || args.Top > MaxTopBottom) { throw env.Except($"Number of top contribution must be in range (0,{MaxTopBottom}]"); } if (args.Bottom <= 0 || args.Bottom > MaxTopBottom) { throw env.Except($"Number of bottom contribution must be in range (0,{MaxTopBottom}]"); } var contributionMapper = mapper as RowMapper; env.CheckParam(mapper != null, nameof(mapper), "Unexpected mapper"); var scorer = ScoreUtils.GetScorerComponent(env, contributionMapper); var scoredPipe = scorer.CreateComponent(env, data, contributionMapper, trainSchema); return(scoredPipe); }
private void RunCore(IChannel ch) { Host.AssertValue(ch); ch.Trace("Creating loader"); LoadModelObjects(ch, true, out var predictor, true, out var trainSchema, out var loader); ch.AssertValue(predictor); ch.AssertValueOrNull(trainSchema); ch.AssertValue(loader); ch.Trace("Creating pipeline"); var scorer = Args.Scorer; ch.Assert(scorer == null || scorer is ICommandLineComponentFactory, "ScoreCommand should only be used from the command line."); var bindable = ScoreUtils.GetSchemaBindableMapper(Host, predictor, scorerFactorySettings: scorer as ICommandLineComponentFactory); ch.AssertValue(bindable); // REVIEW: We probably ought to prefer role mappings from the training schema. string feat = TrainUtils.MatchNameOrDefaultOrNull(ch, loader.Schema, nameof(Args.FeatureColumn), Args.FeatureColumn, DefaultColumnNames.Features); string group = TrainUtils.MatchNameOrDefaultOrNull(ch, loader.Schema, nameof(Args.GroupColumn), Args.GroupColumn, DefaultColumnNames.GroupId); var customCols = TrainUtils.CheckAndGenerateCustomColumns(ch, Args.CustomColumn); var schema = new RoleMappedSchema(loader.Schema, label: null, feature: feat, group: group, custom: customCols, opt: true); var mapper = bindable.Bind(Host, schema); if (scorer == null) { scorer = ScoreUtils.GetScorerComponent(Host, mapper); } loader = CompositeDataLoader.ApplyTransform(Host, loader, "Scorer", scorer.ToString(), (env, view) => scorer.CreateComponent(env, view, mapper, trainSchema)); loader = CompositeDataLoader.Create(Host, loader, Args.PostTransform); if (!string.IsNullOrWhiteSpace(Args.OutputModelFile)) { ch.Trace("Saving the data pipe"); SaveLoader(loader, Args.OutputModelFile); } ch.Trace("Creating saver"); IDataSaver writer; if (Args.Saver == null) { var ext = Path.GetExtension(Args.OutputDataFile); var isText = ext == ".txt" || ext == ".tlc"; if (isText) { writer = new TextSaver(Host, new TextSaver.Arguments()); } else { writer = new BinarySaver(Host, new BinarySaver.Arguments()); } } else { writer = Args.Saver.CreateComponent(Host); } ch.Assert(writer != null); var outputIsBinary = writer is BinaryWriter; bool outputAllColumns = Args.OutputAllColumns == true || (Args.OutputAllColumns == null && Utils.Size(Args.OutputColumn) == 0 && outputIsBinary); bool outputNamesAndLabels = Args.OutputAllColumns == true || Utils.Size(Args.OutputColumn) == 0; if (Args.OutputAllColumns == true && Utils.Size(Args.OutputColumn) != 0) { ch.Warning(nameof(Args.OutputAllColumns) + "=+ always writes all columns irrespective of " + nameof(Args.OutputColumn) + " specified."); } if (!outputAllColumns && Utils.Size(Args.OutputColumn) != 0) { foreach (var outCol in Args.OutputColumn) { if (!loader.Schema.TryGetColumnIndex(outCol, out int dummyColIndex)) { throw ch.ExceptUserArg(nameof(Arguments.OutputColumn), "Column '{0}' not found.", outCol); } } } uint maxScoreId = 0; if (!outputAllColumns) { maxScoreId = loader.Schema.GetMaxMetadataKind(out int colMax, MetadataUtils.Kinds.ScoreColumnSetId); } ch.Assert(outputAllColumns || maxScoreId > 0); // score set IDs are one-based var cols = new List <int>(); for (int i = 0; i < loader.Schema.Count; i++) { if (!Args.KeepHidden && loader.Schema.IsHidden(i)) { continue; } if (!(outputAllColumns || ShouldAddColumn(loader.Schema, i, maxScoreId, outputNamesAndLabels))) { continue; } var type = loader.Schema.GetColumnType(i); if (writer.IsColumnSavable(type)) { cols.Add(i); } else { ch.Warning("The column '{0}' will not be written as it has unsavable column type.", loader.Schema.GetColumnName(i)); } } ch.Check(cols.Count > 0, "No valid columns to save"); ch.Trace("Scoring and saving data"); using (var file = Host.CreateOutputFile(Args.OutputDataFile)) using (var stream = file.CreateWriteStream()) writer.SaveData(stream, loader, cols.ToArray()); }
private FoldResult RunFold(int fold) { var host = GetHost(); host.Assert(0 <= fold && fold <= _numFolds); // REVIEW: Make channels buffered in multi-threaded environments. using (var ch = host.Start($"Fold {fold}")) { ch.Trace("Constructing trainer"); ITrainer trainer = _trainer.CreateInstance(host); // Train pipe. var trainFilter = new RangeFilter.Arguments(); trainFilter.Column = _splitColumn; trainFilter.Min = (Double)fold / _numFolds; trainFilter.Max = (Double)(fold + 1) / _numFolds; trainFilter.Complement = true; IDataView trainPipe = new RangeFilter(host, trainFilter, _inputDataView); trainPipe = new OpaqueDataView(trainPipe); var trainData = _createExamples(host, ch, trainPipe, trainer); // Test pipe. var testFilter = new RangeFilter.Arguments(); testFilter.Column = trainFilter.Column; testFilter.Min = trainFilter.Min; testFilter.Max = trainFilter.Max; ch.Assert(!testFilter.Complement); IDataView testPipe = new RangeFilter(host, testFilter, _inputDataView); testPipe = new OpaqueDataView(testPipe); var testData = _applyTransformsToTestData(host, ch, testPipe, trainData, trainPipe); // Validation pipe and examples. RoleMappedData validData = null; if (_getValidationDataView != null) { ch.Assert(_applyTransformsToValidationData != null); if (!trainer.Info.SupportsValidation) { ch.Warning("Trainer does not accept validation dataset."); } else { ch.Trace("Constructing the validation pipeline"); IDataView validLoader = _getValidationDataView(); var validPipe = ApplyTransformUtils.ApplyAllTransformsToData(host, _inputDataView, validLoader); validPipe = new OpaqueDataView(validPipe); validData = _applyTransformsToValidationData(host, ch, validPipe, trainData, trainPipe); } } // Train. var predictor = TrainUtils.Train(host, ch, trainData, trainer, _trainer.Kind, validData, _calibrator, _maxCalibrationExamples, _cacheData, _inputPredictor); // Score. ch.Trace("Scoring and evaluating"); var bindable = ScoreUtils.GetSchemaBindableMapper(host, predictor, _scorer); ch.AssertValue(bindable); var mapper = bindable.Bind(host, testData.Schema); var scorerComp = _scorer.IsGood() ? _scorer : ScoreUtils.GetScorerComponent(mapper); IDataScorerTransform scorePipe = scorerComp.CreateInstance(host, testData.Data, mapper, trainData.Schema); // Save per-fold model. string modelFileName = ConstructPerFoldName(_outputModelFile, fold); if (modelFileName != null && _loader != null) { using (var file = host.CreateOutputFile(modelFileName)) { var rmd = new RoleMappedData( CompositeDataLoader.ApplyTransform(host, _loader, null, null, (e, newSource) => ApplyTransformUtils.ApplyAllTransformsToData(e, trainData.Data, newSource)), trainData.Schema.GetColumnRoleNames()); TrainUtils.SaveModel(host, ch, file, predictor, rmd, _cmd); } } // Evaluate. var evalComp = _evaluator; if (!evalComp.IsGood()) { evalComp = EvaluateUtils.GetEvaluatorType(ch, scorePipe.Schema); } var eval = evalComp.CreateInstance(host); // Note that this doesn't require the provided columns to exist (because of the "opt" parameter). // We don't normally expect the scorer to drop columns, but if it does, we should not require // all the columns in the test pipeline to still be present. var dataEval = new RoleMappedData(scorePipe, testData.Schema.GetColumnRoleNames(), opt: true); var dict = eval.Evaluate(dataEval); RoleMappedData perInstance = null; if (_savePerInstance) { var perInst = eval.GetPerInstanceMetrics(dataEval); perInstance = new RoleMappedData(perInst, dataEval.Schema.GetColumnRoleNames(), opt: true); } ch.Done(); return(new FoldResult(dict, dataEval.Schema.Schema, perInstance, trainData.Schema)); } }