private protected SingleFeaturePredictionTransformerBase(IHost host, ModelLoadContext ctx)
: base(host, ctx)
{
FeatureColumnName = ctx.LoadStringOrNull();
if (FeatureColumnName == null)
{
FeatureColumnType = null;
}
else if (!TrainSchema.TryGetColumnIndex(FeatureColumnName, out int col))
{
throw Host.ExceptSchemaMismatch(nameof(FeatureColumnName), "feature", FeatureColumnName);
}
else
{
FeatureColumnType = TrainSchema[col].Type;
}
BindableMapper = ScoreUtils.GetSchemaBindableMapper(Host, ModelAsPredictor);
}
internal SingleFeaturePredictionTransformerBase(IHost host, ModelLoadContext ctx)
: base(host, ctx)
{
FeatureColumn = ctx.LoadStringOrNull();
if (FeatureColumn == null)
{
FeatureColumnType = null;
}
else if (!TrainSchema.TryGetColumnIndex(FeatureColumn, out int col))
{
throw Host.ExceptSchemaMismatch(nameof(FeatureColumn), RoleMappedSchema.ColumnRole.Feature.Value, FeatureColumn);
}
else
{
FeatureColumnType = TrainSchema[col].Type;
}
BindableMapper = ScoreUtils.GetSchemaBindableMapper(Host, Model);
}
/// <summary>
/// Creates a data scorer from the 'LoadName{settings}' string.
/// </summary>
/// <param name="env">The host environment to use.</param>
/// <param name="settings">The settings string.</param>
/// <param name="data">The data to score.</param>
/// <param name="predictor">The predictor to score.</param>
/// <param name="trainSchema">The training data schema from which the scorer can optionally extract
/// additional information, for example, label names. If this is <c>null</c>, no information will be
/// extracted.</param>
/// <returns>The scored data.</returns>
internal static IDataScorerTransform CreateScorer(this IHostEnvironment env, string settings,
RoleMappedData data, IPredictor predictor, RoleMappedSchema trainSchema = null)
{
Contracts.CheckValue(env, nameof(env));
env.CheckValue(data, nameof(data));
env.CheckValue(predictor, nameof(predictor));
env.CheckValueOrNull(trainSchema);
Type factoryType = typeof(IComponentFactory <IDataView, ISchemaBoundMapper, RoleMappedSchema, IDataScorerTransform>);
Type signatureType = typeof(SignatureDataScorer);
ICommandLineComponentFactory scorerFactorySettings = CmdParser.CreateComponentFactory(
factoryType,
signatureType,
settings);
var bindable = ScoreUtils.GetSchemaBindableMapper(env, predictor, scorerFactorySettings: scorerFactorySettings);
var mapper = bindable.Bind(env, data.Schema);
return(CreateCore <IDataScorerTransform>(env, factoryType, signatureType, settings, data.Data, mapper, trainSchema));
}
/// <summary>
/// Initializes a new reference of <see cref="SingleFeaturePredictionTransformerBase{TModel, TScorer}"/>.
/// </summary>
/// <param name="host">The local instance of <see cref="IHost"/>.</param>
/// <param name="model">The model used for scoring.</param>
/// <param name="trainSchema">The schema of the training data.</param>
/// <param name="featureColumn">The feature column name.</param>
public SingleFeaturePredictionTransformerBase(IHost host, TModel model, Schema trainSchema, string featureColumn)
: base(host, model, trainSchema)
{
FeatureColumn = featureColumn;
FeatureColumn = featureColumn;
if (featureColumn == null)
{
FeatureColumnType = null;
}
else if (!trainSchema.TryGetColumnIndex(featureColumn, out int col))
{
throw Host.ExceptSchemaMismatch(nameof(featureColumn), RoleMappedSchema.ColumnRole.Feature.Value, featureColumn);
}
else
{
FeatureColumnType = trainSchema[col].Type;
}
BindableMapper = ScoreUtils.GetSchemaBindableMapper(Host, model);
}
public BindableMapper(IHostEnvironment env, IFeatureContributionMapper predictor, int topContributionsCount, int bottomContributionsCount, bool normalize, bool stringify)
{
Contracts.CheckValue(env, nameof(env));
_env = env;
_env.CheckValue(predictor, nameof(predictor));
if (topContributionsCount < 0)
{
throw env.Except($"Number of top contribution must be non negative");
}
if (bottomContributionsCount < 0)
{
throw env.Except($"Number of bottom contribution must be non negative");
}
_topContributionsCount = topContributionsCount;
_bottomContributionsCount = bottomContributionsCount;
_normalize = normalize;
Stringify = stringify;
Predictor = predictor;
GenericMapper = ScoreUtils.GetSchemaBindableMapper(_env, Predictor, null);
}
// Factory method for SignatureDataScorer.
private 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)
{
throw env.Except($"Number of top contribution must be non negative");
}
if (args.Bottom < 0)
{
throw env.Except($"Number of bottom contribution must be non negative");
}
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);
}
public BindableMapper(IHostEnvironment env, ModelLoadContext ctx)
{
Contracts.CheckValue(env, nameof(env));
_env = env;
_env.CheckValue(ctx, nameof(ctx));
ctx.CheckAtModel(GetVersionInfo());
// *** Binary format ***
// IFeatureContributionMapper: Predictor
// int: topContributionsCount
// int: bottomContributionsCount
// bool: normalize
// bool: stringify
ctx.LoadModel <IFeatureContributionMapper, SignatureLoadModel>(env, out Predictor, ModelFileUtils.DirPredictor);
GenericMapper = ScoreUtils.GetSchemaBindableMapper(_env, Predictor, null);
_topContributionsCount = ctx.Reader.ReadInt32();
Contracts.CheckDecode(0 <= _topContributionsCount);
_bottomContributionsCount = ctx.Reader.ReadInt32();
Contracts.CheckDecode(0 <= _bottomContributionsCount);
_normalize = ctx.Reader.ReadBoolByte();
Stringify = ctx.Reader.ReadBoolByte();
}
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 = ImplOptions.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(ImplOptions.FeatureColumn), ImplOptions.FeatureColumn, DefaultColumnNames.Features);
string group = TrainUtils.MatchNameOrDefaultOrNull(ch, loader.Schema,
nameof(ImplOptions.GroupColumn), ImplOptions.GroupColumn, DefaultColumnNames.GroupId);
var customCols = TrainUtils.CheckAndGenerateCustomColumns(ch, ImplOptions.CustomColumns);
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 = LegacyCompositeDataLoader.ApplyTransform(Host, loader, "Scorer", scorer.ToString(),
(env, view) => scorer.CreateComponent(env, view, mapper, trainSchema));
loader = LegacyCompositeDataLoader.Create(Host, loader, ImplOptions.PostTransform);
if (!string.IsNullOrWhiteSpace(ImplOptions.OutputModelFile))
{
ch.Trace("Saving the data pipe");
SaveLoader(loader, ImplOptions.OutputModelFile);
}
ch.Trace("Creating saver");
IDataSaver writer;
if (ImplOptions.Saver == null)
{
var ext = Path.GetExtension(ImplOptions.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 = ImplOptions.Saver.CreateComponent(Host);
}
ch.Assert(writer != null);
var outputIsBinary = writer is BinaryWriter;
bool outputAllColumns =
ImplOptions.OutputAllColumns == true ||
(ImplOptions.OutputAllColumns == null && Utils.Size(ImplOptions.OutputColumns) == 0 && outputIsBinary);
bool outputNamesAndLabels =
ImplOptions.OutputAllColumns == true || Utils.Size(ImplOptions.OutputColumns) == 0;
if (ImplOptions.OutputAllColumns == true && Utils.Size(ImplOptions.OutputColumns) != 0)
{
ch.Warning(nameof(ImplOptions.OutputAllColumns) + "=+ always writes all columns irrespective of " + nameof(ImplOptions.OutputColumns) + " specified.");
}
if (!outputAllColumns && Utils.Size(ImplOptions.OutputColumns) != 0)
{
foreach (var outCol in ImplOptions.OutputColumns)
{
if (!loader.Schema.TryGetColumnIndex(outCol, out int dummyColIndex))
{
throw ch.ExceptUserArg(nameof(Arguments.OutputColumns), "Column '{0}' not found.", outCol);
}
}
}
uint maxScoreId = 0;
if (!outputAllColumns)
{
maxScoreId = loader.Schema.GetMaxAnnotationKind(out int colMax, AnnotationUtils.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 (!ImplOptions.KeepHidden && loader.Schema[i].IsHidden)
{
continue;
}
if (!(outputAllColumns || ShouldAddColumn(loader.Schema, i, maxScoreId, outputNamesAndLabels)))
{
continue;
}
var type = loader.Schema[i].Type;
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[i].Name);
}
}
ch.Check(cols.Count > 0, "No valid columns to save");
ch.Trace("Scoring and saving data");
using (var file = Host.CreateOutputFile(ImplOptions.OutputDataFile))
using (var stream = file.CreateWriteStream())
writer.SaveData(stream, loader, cols.ToArray());
}
private void RunCore(IChannel ch, string cmd)
{
Host.AssertValue(ch);
Host.AssertNonEmpty(cmd);
ch.Trace("Constructing trainer");
ITrainer trainer = ImplOptions.Trainer.CreateComponent(Host);
IPredictor inputPredictor = null;
if (ImplOptions.ContinueTrain && !TrainUtils.TryLoadPredictor(ch, Host, ImplOptions.InputModelFile, out inputPredictor))
{
ch.Warning("No input model file specified or model file did not contain a predictor. The model state cannot be initialized.");
}
ch.Trace("Constructing the training pipeline");
IDataView trainPipe = CreateLoader();
var schema = trainPipe.Schema;
string label = TrainUtils.MatchNameOrDefaultOrNull(ch, schema, nameof(Arguments.LabelColumn),
ImplOptions.LabelColumn, DefaultColumnNames.Label);
string features = TrainUtils.MatchNameOrDefaultOrNull(ch, schema, nameof(Arguments.FeatureColumn),
ImplOptions.FeatureColumn, DefaultColumnNames.Features);
string group = TrainUtils.MatchNameOrDefaultOrNull(ch, schema, nameof(Arguments.GroupColumn),
ImplOptions.GroupColumn, DefaultColumnNames.GroupId);
string weight = TrainUtils.MatchNameOrDefaultOrNull(ch, schema, nameof(Arguments.WeightColumn),
ImplOptions.WeightColumn, DefaultColumnNames.Weight);
string name = TrainUtils.MatchNameOrDefaultOrNull(ch, schema, nameof(Arguments.NameColumn),
ImplOptions.NameColumn, DefaultColumnNames.Name);
TrainUtils.AddNormalizerIfNeeded(Host, ch, trainer, ref trainPipe, features, ImplOptions.NormalizeFeatures);
ch.Trace("Binding columns");
var customCols = TrainUtils.CheckAndGenerateCustomColumns(ch, ImplOptions.CustomColumns);
var data = new RoleMappedData(trainPipe, label, features, group, weight, name, customCols);
RoleMappedData validData = null;
if (!string.IsNullOrWhiteSpace(ImplOptions.ValidationFile))
{
if (!trainer.Info.SupportsValidation)
{
ch.Warning("Ignoring validationFile: Trainer does not accept validation dataset.");
}
else
{
ch.Trace("Constructing the validation pipeline");
IDataView validPipe = CreateRawLoader(dataFile: ImplOptions.ValidationFile);
validPipe = ApplyTransformUtils.ApplyAllTransformsToData(Host, trainPipe, validPipe);
validData = new RoleMappedData(validPipe, data.Schema.GetColumnRoleNames());
}
}
// In addition to the training set, some trainers can accept two data sets, validation set and test set,
// in training phase. The major difference between validation set and test set is that training process may
// indirectly use validation set to improve the model but the learned model should totally independent of test set.
// Similar to validation set, the trainer can report the scores computed using test set.
RoleMappedData testDataUsedInTrainer = null;
if (!string.IsNullOrWhiteSpace(ImplOptions.TestFile))
{
// In contrast to the if-else block for validation above, we do not throw a warning if test file is provided
// because this is TrainTest command.
if (trainer.Info.SupportsTest)
{
ch.Trace("Constructing the test pipeline");
IDataView testPipeUsedInTrainer = CreateRawLoader(dataFile: ImplOptions.TestFile);
testPipeUsedInTrainer = ApplyTransformUtils.ApplyAllTransformsToData(Host, trainPipe, testPipeUsedInTrainer);
testDataUsedInTrainer = new RoleMappedData(testPipeUsedInTrainer, data.Schema.GetColumnRoleNames());
}
}
var predictor = TrainUtils.Train(Host, ch, data, trainer, validData,
ImplOptions.Calibrator, ImplOptions.MaxCalibrationExamples, ImplOptions.CacheData, inputPredictor, testDataUsedInTrainer);
ILegacyDataLoader testPipe;
bool hasOutfile = !string.IsNullOrEmpty(ImplOptions.OutputModelFile);
var tempFilePath = hasOutfile ? null : Path.GetTempFileName();
using (var file = new SimpleFileHandle(ch, hasOutfile ? ImplOptions.OutputModelFile : tempFilePath, true, !hasOutfile))
{
TrainUtils.SaveModel(Host, ch, file, predictor, data, cmd);
ch.Trace("Constructing the testing pipeline");
using (var stream = file.OpenReadStream())
using (var rep = RepositoryReader.Open(stream, ch))
testPipe = LoadLoader(rep, ImplOptions.TestFile, true);
}
// Score.
ch.Trace("Scoring and evaluating");
ch.Assert(ImplOptions.Scorer == null || ImplOptions.Scorer is ICommandLineComponentFactory, "TrainTestCommand should only be used from the command line.");
IDataScorerTransform scorePipe = ScoreUtils.GetScorer(ImplOptions.Scorer, predictor, testPipe, features, group, customCols, Host, data.Schema);
// Evaluate.
var evaluator = ImplOptions.Evaluator?.CreateComponent(Host) ??
EvaluateUtils.GetEvaluator(Host, scorePipe.Schema);
var dataEval = new RoleMappedData(scorePipe, label, features,
group, weight, name, customCols, opt: true);
var metrics = evaluator.Evaluate(dataEval);
MetricWriter.PrintWarnings(ch, metrics);
evaluator.PrintFoldResults(ch, metrics);
if (!metrics.TryGetValue(MetricKinds.OverallMetrics, out var overall))
{
throw ch.Except("No overall metrics found");
}
overall = evaluator.GetOverallResults(overall);
MetricWriter.PrintOverallMetrics(Host, ch, ImplOptions.SummaryFilename, overall, 1);
evaluator.PrintAdditionalMetrics(ch, metrics);
Dictionary <string, IDataView>[] metricValues = { metrics };
SendTelemetryMetric(metricValues);
if (!string.IsNullOrWhiteSpace(ImplOptions.OutputDataFile))
{
var perInst = evaluator.GetPerInstanceMetrics(dataEval);
var perInstData = new RoleMappedData(perInst, label, null, group, weight, name, customCols);
var idv = evaluator.GetPerInstanceDataViewToSave(perInstData);
MetricWriter.SavePerInstance(Host, ch, ImplOptions.OutputDataFile, idv);
}
}
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));
}
}
