/// <summary>
/// Callback from the CV method to apply the transforms to the train data.
/// </summary>
private RoleMappedData CreateRoleMappedData(IHostEnvironment env, IChannel ch, IDataView data, ITrainer trainer)
{
foreach (var kvp in Args.Transform)
{
data = kvp.Value.CreateComponent(env, data);
}
var schema = data.Schema;
string label = TrainUtils.MatchNameOrDefaultOrNull(ch, schema, nameof(Args.LabelColumn), Args.LabelColumn, DefaultColumnNames.Label);
string features = TrainUtils.MatchNameOrDefaultOrNull(ch, schema, nameof(Args.FeatureColumn), Args.FeatureColumn, DefaultColumnNames.Features);
string weight = TrainUtils.MatchNameOrDefaultOrNull(ch, schema, nameof(Args.WeightColumn), Args.WeightColumn, DefaultColumnNames.Weight);
string name = TrainUtils.MatchNameOrDefaultOrNull(ch, schema, nameof(Args.NameColumn), Args.NameColumn, DefaultColumnNames.Name);
string group = TrainUtils.MatchNameOrDefaultOrNull(ch, schema, nameof(Args.GroupColumn), Args.GroupColumn, DefaultColumnNames.GroupId);
TrainUtils.AddNormalizerIfNeeded(env, ch, trainer, ref data, features, Args.NormalizeFeatures);
// Training pipe and examples.
var customCols = TrainUtils.CheckAndGenerateCustomColumns(ch, Args.CustomColumn);
return(new RoleMappedData(data, label, features, group, weight, name, customCols));
}
private static void TrainCore(IHost host, IDataView input, Arguments args, ref VBuffer <Single> scores)
{
Contracts.AssertValue(host);
host.AssertValue(args);
host.AssertValue(input);
host.Assert(args.Threshold.HasValue != args.NumSlotsToKeep.HasValue);
using (var ch = host.Start("Train"))
{
ch.Trace("Constructing trainer");
ITrainer trainer = args.Filter.CreateComponent(host);
IDataView view = input;
ISchema schema = view.Schema;
var label = TrainUtils.MatchNameOrDefaultOrNull(ch, schema, nameof(args.LabelColumn), args.LabelColumn, DefaultColumnNames.Label);
var feature = TrainUtils.MatchNameOrDefaultOrNull(ch, schema, nameof(args.FeatureColumn), args.FeatureColumn, DefaultColumnNames.Features);
var group = TrainUtils.MatchNameOrDefaultOrNull(ch, schema, nameof(args.GroupColumn), args.GroupColumn, DefaultColumnNames.GroupId);
var weight = TrainUtils.MatchNameOrDefaultOrNull(ch, schema, nameof(args.WeightColumn), args.WeightColumn, DefaultColumnNames.Weight);
var name = TrainUtils.MatchNameOrDefaultOrNull(ch, schema, nameof(args.NameColumn), args.NameColumn, DefaultColumnNames.Name);
TrainUtils.AddNormalizerIfNeeded(host, ch, trainer, ref view, feature, args.NormalizeFeatures);
ch.Trace("Binding columns");
var customCols = TrainUtils.CheckAndGenerateCustomColumns(ch, args.CustomColumn);
var data = new RoleMappedData(view, label, feature, group, weight, name, customCols);
var predictor = TrainUtils.Train(host, ch, data, trainer, null,
null, 0, args.CacheData);
var rfs = predictor as IPredictorWithFeatureWeights <Single>;
Contracts.AssertValue(rfs);
rfs.GetFeatureWeights(ref scores);
ch.Done();
}
}
private void RunCore(IChannel ch, string cmd)
{
Host.AssertValue(ch);
Host.AssertNonEmpty(cmd);
ch.Trace("Constructing trainer");
ITrainer trainer = _trainer.CreateComponent(Host);
IPredictor inputPredictor = null;
if (Args.ContinueTrain && !TrainUtils.TryLoadPredictor(ch, Host, Args.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 data pipeline");
IDataView view = CreateLoader();
ISchema schema = view.Schema;
var label = TrainUtils.MatchNameOrDefaultOrNull(ch, schema, nameof(Arguments.LabelColumn), _labelColumn, DefaultColumnNames.Label);
var feature = TrainUtils.MatchNameOrDefaultOrNull(ch, schema, nameof(Arguments.FeatureColumn), _featureColumn, DefaultColumnNames.Features);
var group = TrainUtils.MatchNameOrDefaultOrNull(ch, schema, nameof(Arguments.GroupColumn), _groupColumn, DefaultColumnNames.GroupId);
var weight = TrainUtils.MatchNameOrDefaultOrNull(ch, schema, nameof(Arguments.WeightColumn), _weightColumn, DefaultColumnNames.Weight);
var name = TrainUtils.MatchNameOrDefaultOrNull(ch, schema, nameof(Arguments.NameColumn), _nameColumn, DefaultColumnNames.Name);
TrainUtils.AddNormalizerIfNeeded(Host, ch, trainer, ref view, feature, Args.NormalizeFeatures);
ch.Trace("Binding columns");
var customCols = TrainUtils.CheckAndGenerateCustomColumns(ch, Args.CustomColumn);
var data = new RoleMappedData(view, label, feature, group, weight, name, customCols);
// REVIEW: Unify the code that creates validation examples in Train, TrainTest and CV commands.
RoleMappedData validData = null;
if (!string.IsNullOrWhiteSpace(Args.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: Args.ValidationFile);
validPipe = ApplyTransformUtils.ApplyAllTransformsToData(Host, view, validPipe);
validData = new RoleMappedData(validPipe, data.Schema.GetColumnRoleNames());
}
}
// In addition to the training set, some trainers can accept two extra 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(Args.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: Args.TestFile);
testPipeUsedInTrainer = ApplyTransformUtils.ApplyAllTransformsToData(Host, view, testPipeUsedInTrainer);
testDataUsedInTrainer = new RoleMappedData(testPipeUsedInTrainer, data.Schema.GetColumnRoleNames());
}
}
var predictor = TrainUtils.Train(Host, ch, data, trainer, validData,
Args.Calibrator, Args.MaxCalibrationExamples, Args.CacheData, inputPredictor, testDataUsedInTrainer);
using (var file = Host.CreateOutputFile(Args.OutputModelFile))
TrainUtils.SaveModel(Host, ch, file, predictor, data, cmd);
}
private void RunCore(IChannel ch, string cmd)
{
Host.AssertValue(ch);
Host.AssertNonEmpty(cmd);
ch.Trace("Constructing trainer");
ITrainer trainer = Args.Trainer.CreateInstance(Host);
IPredictor inputPredictor = null;
if (Args.ContinueTrain && !TrainUtils.TryLoadPredictor(ch, Host, Args.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();
ISchema schema = trainPipe.Schema;
string label = TrainUtils.MatchNameOrDefaultOrNull(ch, schema, nameof(Arguments.LabelColumn),
Args.LabelColumn, DefaultColumnNames.Label);
string features = TrainUtils.MatchNameOrDefaultOrNull(ch, schema, nameof(Arguments.FeatureColumn),
Args.FeatureColumn, DefaultColumnNames.Features);
string group = TrainUtils.MatchNameOrDefaultOrNull(ch, schema, nameof(Arguments.GroupColumn),
Args.GroupColumn, DefaultColumnNames.GroupId);
string weight = TrainUtils.MatchNameOrDefaultOrNull(ch, schema, nameof(Arguments.WeightColumn),
Args.WeightColumn, DefaultColumnNames.Weight);
string name = TrainUtils.MatchNameOrDefaultOrNull(ch, schema, nameof(Arguments.NameColumn),
Args.NameColumn, DefaultColumnNames.Name);
TrainUtils.AddNormalizerIfNeeded(Host, ch, trainer, ref trainPipe, features, Args.NormalizeFeatures);
ch.Trace("Binding columns");
var customCols = TrainUtils.CheckAndGenerateCustomColumns(ch, Args.CustomColumn);
var data = new RoleMappedData(trainPipe, label, features, group, weight, name, customCols);
RoleMappedData validData = null;
if (!string.IsNullOrWhiteSpace(Args.ValidationFile))
{
if (!TrainUtils.CanUseValidationData(trainer))
{
ch.Warning("Ignoring validationFile: Trainer does not accept validation dataset.");
}
else
{
ch.Trace("Constructing the validation pipeline");
IDataView validPipe = CreateRawLoader(dataFile: Args.ValidationFile);
validPipe = ApplyTransformUtils.ApplyAllTransformsToData(Host, trainPipe, validPipe);
validData = new RoleMappedData(validPipe, data.Schema.GetColumnRoleNames());
}
}
var predictor = TrainUtils.Train(Host, ch, data, trainer, _info.LoadNames[0], validData,
Args.Calibrator, Args.MaxCalibrationExamples, Args.CacheData, inputPredictor);
IDataLoader testPipe;
using (var file = !string.IsNullOrEmpty(Args.OutputModelFile) ?
Host.CreateOutputFile(Args.OutputModelFile) : Host.CreateTempFile(".zip"))
{
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, Args.TestFile, true);
}
// Score.
ch.Trace("Scoring and evaluating");
IDataScorerTransform scorePipe = ScoreUtils.GetScorer(Args.Scorer, predictor, testPipe, features, group, customCols, Host, data.Schema);
// Evaluate.
var evalComp = Args.Evaluator;
if (!evalComp.IsGood())
{
evalComp = EvaluateUtils.GetEvaluatorType(ch, scorePipe.Schema);
}
var evaluator = evalComp.CreateInstance(Host);
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, Args.SummaryFilename, overall, 1);
evaluator.PrintAdditionalMetrics(ch, metrics);
Dictionary <string, IDataView>[] metricValues = { metrics };
SendTelemetryMetric(metricValues);
if (!string.IsNullOrWhiteSpace(Args.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, Args.OutputDataFile, idv);
}
}
private void RunCore(IChannel ch, string cmd)
{
Host.AssertValue(ch);
Host.AssertNonEmpty(cmd);
ch.Trace("Constructing trainer");
ITrainer trainer = Args.Trainer.CreateComponent(Host);
IPredictor inputPredictor = null;
if (Args.ContinueTrain && !TrainUtils.TryLoadPredictor(ch, Host, Args.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();
ISchema schema = trainPipe.Schema;
string label = TrainUtils.MatchNameOrDefaultOrNull(ch, schema, nameof(Arguments.LabelColumn),
Args.LabelColumn, DefaultColumnNames.Label);
string features = TrainUtils.MatchNameOrDefaultOrNull(ch, schema, nameof(Arguments.FeatureColumn),
Args.FeatureColumn, DefaultColumnNames.Features);
string group = TrainUtils.MatchNameOrDefaultOrNull(ch, schema, nameof(Arguments.GroupColumn),
Args.GroupColumn, DefaultColumnNames.GroupId);
string weight = TrainUtils.MatchNameOrDefaultOrNull(ch, schema, nameof(Arguments.WeightColumn),
Args.WeightColumn, DefaultColumnNames.Weight);
string name = TrainUtils.MatchNameOrDefaultOrNull(ch, schema, nameof(Arguments.NameColumn),
Args.NameColumn, DefaultColumnNames.Name);
TrainUtils.AddNormalizerIfNeeded(Host, ch, trainer, ref trainPipe, features, Args.NormalizeFeatures);
ch.Trace("Binding columns");
var customCols = TrainUtils.CheckAndGenerateCustomColumns(ch, Args.CustomColumn);
var data = new RoleMappedData(trainPipe, label, features, group, weight, name, customCols);
RoleMappedData validData = null;
if (!string.IsNullOrWhiteSpace(Args.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: Args.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(Args.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: Args.TestFile);
testPipeUsedInTrainer = ApplyTransformUtils.ApplyAllTransformsToData(Host, trainPipe, testPipeUsedInTrainer);
testDataUsedInTrainer = new RoleMappedData(testPipeUsedInTrainer, data.Schema.GetColumnRoleNames());
}
}
var predictor = TrainUtils.Train(Host, ch, data, trainer, validData,
Args.Calibrator, Args.MaxCalibrationExamples, Args.CacheData, inputPredictor, testDataUsedInTrainer);
IDataLoader testPipe;
bool hasOutfile = !string.IsNullOrEmpty(Args.OutputModelFile);
var tempFilePath = hasOutfile ? null : Path.GetTempFileName();
using (var file = new SimpleFileHandle(ch, hasOutfile ? Args.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, Args.TestFile, true);
}
// Score.
ch.Trace("Scoring and evaluating");
ch.Assert(Args.Scorer == null || Args.Scorer is ICommandLineComponentFactory, "TrainTestCommand should only be used from the command line.");
IDataScorerTransform scorePipe = ScoreUtils.GetScorer(Args.Scorer, predictor, testPipe, features, group, customCols, Host, data.Schema);
// Evaluate.
var evaluator = Args.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, Args.SummaryFilename, overall, 1);
evaluator.PrintAdditionalMetrics(ch, metrics);
Dictionary <string, IDataView>[] metricValues = { metrics };
SendTelemetryMetric(metricValues);
if (!string.IsNullOrWhiteSpace(Args.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, Args.OutputDataFile, idv);
}
}
