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;
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");
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);
}
}
private void RunCore(IChannel ch)
{
Host.AssertValue(ch);
ch.Trace("Creating loader");
IPredictor predictor;
IDataLoader loader;
RoleMappedSchema trainSchema;
LoadModelObjects(ch, true, out predictor, true, out trainSchema, out loader);
ch.AssertValue(predictor);
ch.AssertValueOrNull(trainSchema);
ch.AssertValue(loader);
ch.Trace("Creating pipeline");
var scorer = Args.Scorer;
var bindable = ScoreUtils.GetSchemaBindableMapper(Host, predictor, scorer);
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 = TrainUtils.CreateRoleMappedSchemaOpt(loader.Schema, feat, group, customCols);
var mapper = bindable.Bind(Host, schema);
if (!scorer.IsGood())
{
scorer = ScoreUtils.GetScorerComponent(mapper);
}
loader = CompositeDataLoader.ApplyTransform(Host, loader, "Scorer", scorer.ToString(),
(env, view) => scorer.CreateInstance(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");
var saver = Args.Saver;
if (!saver.IsGood())
{
var ext = Path.GetExtension(Args.OutputDataFile);
var isText = ext == ".txt" || ext == ".tlc";
saver = new SubComponent <IDataSaver, SignatureDataSaver>(isText ? "TextSaver" : "BinarySaver");
}
var writer = saver.CreateInstance(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("outputAllColumns=+ always writes all columns irrespective of outputColumn specified.");
}
if (!outputAllColumns && Utils.Size(Args.OutputColumn) != 0)
{
foreach (var outCol in Args.OutputColumn)
{
int dummyColIndex;
if (!loader.Schema.TryGetColumnIndex(outCol, out dummyColIndex))
{
throw ch.ExceptUserArg(nameof(Arguments.OutputColumn), "Column '{0}' not found.", outCol);
}
}
}
int colMax;
uint maxScoreId = 0;
if (!outputAllColumns)
{
maxScoreId = loader.Schema.GetMaxMetadataKind(out 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.ColumnCount; 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.CreateComponent(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, 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));
}
}
private string GetSplitColumn(IChannel ch, IDataView input, ref IDataView output)
{
// The stratification column and/or group column, if they exist at all, must be present at this point.
var schema = input.Schema;
output = input;
// If no stratification column was specified, but we have a group column of type Single, Double or
// Key (contiguous) use it.
string stratificationColumn = null;
if (!string.IsNullOrWhiteSpace(Args.StratificationColumn))
{
stratificationColumn = Args.StratificationColumn;
}
else
{
string group = TrainUtils.MatchNameOrDefaultOrNull(ch, schema, nameof(Args.GroupColumn), Args.GroupColumn, DefaultColumnNames.GroupId);
int index;
if (group != null && schema.TryGetColumnIndex(group, out index))
{
// Check if group column key type with known cardinality.
var type = schema.GetColumnType(index);
if (type.KeyCount > 0)
{
stratificationColumn = group;
}
}
}
if (string.IsNullOrEmpty(stratificationColumn))
{
stratificationColumn = "StratificationColumn";
int tmp;
int inc = 0;
while (input.Schema.TryGetColumnIndex(stratificationColumn, out tmp))
{
stratificationColumn = string.Format("StratificationColumn_{0:000}", ++inc);
}
var keyGenArgs = new GenerateNumberTransform.Arguments();
var col = new GenerateNumberTransform.Column();
col.Name = stratificationColumn;
keyGenArgs.Column = new[] { col };
output = new GenerateNumberTransform(Host, keyGenArgs, input);
}
else
{
int col;
if (!input.Schema.TryGetColumnIndex(stratificationColumn, out col))
{
throw ch.ExceptUserArg(nameof(Arguments.StratificationColumn), "Column '{0}' does not exist", stratificationColumn);
}
var type = input.Schema.GetColumnType(col);
if (!RangeFilter.IsValidRangeFilterColumnType(ch, type))
{
ch.Info("Hashing the stratification column");
var origStratCol = stratificationColumn;
int tmp;
int inc = 0;
while (input.Schema.TryGetColumnIndex(stratificationColumn, out tmp))
{
stratificationColumn = string.Format("{0}_{1:000}", origStratCol, ++inc);
}
output = new HashingEstimator(Host, origStratCol, stratificationColumn, 30).Fit(input).Transform(input);
}
}
return(stratificationColumn);
}
private void RunCore(IChannel ch, string cmd)
{
Host.AssertValue(ch);
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");
IDataLoader loader = CreateRawLoader();
// If the per-instance results are requested and there is no name column, add a GenerateNumberTransform.
var preXf = Args.PreTransform;
if (!string.IsNullOrEmpty(Args.OutputDataFile))
{
string name = TrainUtils.MatchNameOrDefaultOrNull(ch, loader.Schema, nameof(Args.NameColumn), Args.NameColumn, DefaultColumnNames.Name);
if (name == null)
{
preXf = preXf.Concat(
new[]
{
new KeyValuePair <string, IComponentFactory <IDataView, IDataTransform> >(
"", ComponentFactoryUtils.CreateFromFunction <IDataView, IDataTransform>(
(env, input) =>
{
var args = new GenerateNumberTransform.Arguments();
args.Column = new[] { new GenerateNumberTransform.Column()
{
Name = DefaultColumnNames.Name
}, };
args.UseCounter = true;
return(new GenerateNumberTransform(env, args, input));
}))
}).ToArray();
}
}
loader = CompositeDataLoader.Create(Host, loader, preXf);
ch.Trace("Binding label and features columns");
IDataView pipe = loader;
var stratificationColumn = GetSplitColumn(ch, loader, ref pipe);
var scorer = Args.Scorer;
var evaluator = Args.Evaluator;
Func <IDataView> validDataCreator = null;
if (Args.ValidationFile != null)
{
validDataCreator =
() =>
{
// Fork the command.
var impl = new CrossValidationCommand(this);
return(impl.CreateRawLoader(dataFile: Args.ValidationFile));
};
}
FoldHelper fold = new FoldHelper(Host, RegistrationName, pipe, stratificationColumn,
Args, CreateRoleMappedData, ApplyAllTransformsToData, scorer, evaluator,
validDataCreator, ApplyAllTransformsToData, inputPredictor, cmd, loader, !string.IsNullOrEmpty(Args.OutputDataFile));
var tasks = fold.GetCrossValidationTasks();
var eval = evaluator?.CreateComponent(Host) ??
EvaluateUtils.GetEvaluator(Host, tasks[0].Result.ScoreSchema);
// Print confusion matrix and fold results for each fold.
for (int i = 0; i < tasks.Length; i++)
{
var dict = tasks[i].Result.Metrics;
MetricWriter.PrintWarnings(ch, dict);
eval.PrintFoldResults(ch, dict);
}
// Print the overall results.
if (!TryGetOverallMetrics(tasks.Select(t => t.Result.Metrics).ToArray(), out var overallList))
{
throw ch.Except("No overall metrics found");
}
var overall = eval.GetOverallResults(overallList.ToArray());
MetricWriter.PrintOverallMetrics(Host, ch, Args.SummaryFilename, overall, Args.NumFolds);
eval.PrintAdditionalMetrics(ch, tasks.Select(t => t.Result.Metrics).ToArray());
Dictionary <string, IDataView>[] metricValues = tasks.Select(t => t.Result.Metrics).ToArray();
SendTelemetryMetric(metricValues);
// Save the per-instance results.
if (!string.IsNullOrWhiteSpace(Args.OutputDataFile))
{
var perInstance = EvaluateUtils.ConcatenatePerInstanceDataViews(Host, eval, Args.CollateMetrics,
Args.OutputExampleFoldIndex, tasks.Select(t => t.Result.PerInstanceResults).ToArray(), out var variableSizeVectorColumnNames);
if (variableSizeVectorColumnNames.Length > 0)
{
ch.Warning("Detected columns of variable length: {0}. Consider setting collateMetrics- for meaningful per-Folds results.",
string.Join(", ", variableSizeVectorColumnNames));
}
if (Args.CollateMetrics)
{
ch.Assert(perInstance.Length == 1);
MetricWriter.SavePerInstance(Host, ch, Args.OutputDataFile, perInstance[0]);
}
else
{
int i = 0;
foreach (var idv in perInstance)
{
MetricWriter.SavePerInstance(Host, ch, ConstructPerFoldName(Args.OutputDataFile, i), idv);
i++;
}
}
}
}
private void RunCore(IChannel ch)
{
ch.Trace("Constructing data pipeline");
IDataLoader loader;
IPredictor predictor;
RoleMappedSchema trainSchema;
LoadModelObjects(ch, true, out predictor, true, out trainSchema, out loader);
ch.AssertValue(predictor);
ch.AssertValueOrNull(trainSchema);
ch.AssertValue(loader);
ch.Trace("Binding columns");
ISchema schema = loader.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 group = TrainUtils.MatchNameOrDefaultOrNull(ch, schema, nameof(Args.GroupColumn),
Args.GroupColumn, DefaultColumnNames.GroupId);
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);
var customCols = TrainUtils.CheckAndGenerateCustomColumns(ch, Args.CustomColumn);
// Score.
ch.Trace("Scoring and evaluating");
ch.Assert(Args.Scorer == null || Args.Scorer is ICommandLineComponentFactory, "TestCommand should only be used from the command line.");
IDataScorerTransform scorePipe = ScoreUtils.GetScorer(Args.Scorer, predictor, loader, features, group, customCols, Host, trainSchema);
// Evaluate.
var evalComp = Args.Evaluator;
if (!evalComp.IsGood())
{
evalComp = EvaluateUtils.GetEvaluatorType(ch, scorePipe.Schema);
}
var evaluator = evalComp.CreateInstance(Host);
var data = new RoleMappedData(scorePipe, label, null, group, weight, name, customCols);
var metrics = evaluator.Evaluate(data);
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(data);
var perInstData = new RoleMappedData(perInst, label, null, group, weight, name, customCols);
var idv = evaluator.GetPerInstanceDataViewToSave(perInstData);
MetricWriter.SavePerInstance(Host, ch, Args.OutputDataFile, idv);
}
}
