public static CommonOutputs.TransformOutput FilterByRange(IHostEnvironment env, RangeFilter.Options input) { Contracts.CheckValue(env, nameof(env)); var host = env.Register(RangeFilter.LoaderSignature); host.CheckValue(input, nameof(input)); EntryPointUtils.CheckInputArgs(host, input); var xf = new RangeFilter(host, input, input.Data); return(new CommonOutputs.TransformOutput { Model = new TransformModelImpl(env, xf, input.Data), OutputData = xf }); }
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.CreateComponent(host); // Train pipe. var trainFilter = new RangeFilter.Options(); 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.Options(); 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, validData, _calibrator, _maxCalibrationExamples, _cacheData, _inputPredictor); // Score. ch.Trace("Scoring and evaluating"); ch.Assert(_scorer == null || _scorer is ICommandLineComponentFactory, "CrossValidationCommand should only be used from the command line."); var bindable = ScoreUtils.GetSchemaBindableMapper(host, predictor, scorerFactorySettings: _scorer as ICommandLineComponentFactory); ch.AssertValue(bindable); var mapper = bindable.Bind(host, testData.Schema); var scorerComp = _scorer ?? ScoreUtils.GetScorerComponent(host, mapper); IDataScorerTransform scorePipe = scorerComp.CreateComponent(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 eval = _evaluator?.CreateComponent(host) ?? EvaluateUtils.GetEvaluator(host, scorePipe.Schema); // 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); } return(new FoldResult(dict, dataEval.Schema.Schema, perInstance, trainData.Schema)); } }
IDataTransform AppendToPipeline(IDataView input) { IDataView current = input; if (_shuffleInput) { var args1 = new RowShufflingTransformer.Options() { ForceShuffle = false, ForceShuffleSeed = _seedShuffle, PoolRows = _poolRows, PoolOnly = false, }; current = new RowShufflingTransformer(Host, args1, current); } // We generate a random number. var columnName = current.Schema.GetTempColumnName(); var args2 = new GenerateNumberTransform.Options() { Columns = new GenerateNumberTransform.Column[] { new GenerateNumberTransform.Column() { Name = columnName } }, Seed = _seed ?? 42 }; IDataTransform currentTr = new GenerateNumberTransform(Host, args2, current); // We convert this random number into a part. var cRatios = new float[_ratios.Length]; cRatios[0] = 0; for (int i = 1; i < _ratios.Length; ++i) { cRatios[i] = cRatios[i - 1] + _ratios[i - 1]; } ValueMapper <float, int> mapper = (in float src, ref int dst) => { for (int i = cRatios.Length - 1; i > 0; --i) { if (src >= cRatios[i]) { dst = i; return; } } dst = 0; }; // Get location of columnName int index = SchemaHelper.GetColumnIndex(currentTr.Schema, columnName); var ct = currentTr.Schema[index].Type; var view = LambdaColumnMapper.Create(Host, "Key to part mapper", currentTr, columnName, _newColumn, ct, NumberDataViewType.Int32, mapper); // We cache the result to avoid the pipeline to change the random number. var args3 = new ExtendedCacheTransform.Arguments() { inDataFrame = string.IsNullOrEmpty(_cacheFile), numTheads = _numThreads, cacheFile = _cacheFile, reuse = _reuse, }; currentTr = new ExtendedCacheTransform(Host, args3, view); // Removing the temporary column. var objtr = ColumnSelectingTransformer.CreateDrop(Host, currentTr, new string[] { columnName }); var finalTr = objtr as IDataTransform; if (finalTr == null) { throw Contracts.ExceptNotSupp("Desgin change."); } var taggedViews = new List <Tuple <string, ITaggedDataView> >(); // filenames if (_filenames != null || _tags != null) { int nbf = _filenames == null ? 0 : _filenames.Length; if (nbf > 0 && nbf != _ratios.Length) { throw Host.Except("Differen number of filenames and ratios."); } int nbt = _tags == null ? 0 : _tags.Length; if (nbt > 0 && nbt != _ratios.Length) { throw Host.Except("Differen number of filenames and ratios."); } int nb = Math.Max(nbf, nbt); using (var ch = Host.Start("Split the datasets and stores each part.")) { for (int i = 0; i < nb; ++i) { if (_filenames == null || !_filenames.Any()) { ch.Info("Create part {0}: {1} (tag: {2})", i + 1, _ratios[i], _tags[i]); } else { ch.Info("Create part {0}: {1} (file: {2})", i + 1, _ratios[i], _filenames[i]); } var ar1 = new RangeFilter.Options() { Column = _newColumn, Min = i, Max = i, IncludeMax = true }; int pardId = i; var filtView = LambdaFilter.Create <int>(Host, string.Format("Select part {0}", i), currentTr, _newColumn, NumberDataViewType.Int32, (in int part) => { return(part.Equals(pardId)); });