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, 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());
}
}
var predictor = TrainUtils.Train(Host, ch, data, trainer, 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");
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, 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.Combine(((IHostEnvironmentInternal)Host).TempFilePath, Path.GetRandomFileName());
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);
}
}
protected override void PrintFoldResultsCore(IChannel ch, Dictionary <string, IDataView> metrics)
{
IDataView top;
if (!metrics.TryGetValue(AnomalyDetectionEvaluator.TopKResults, out top))
{
throw Host.Except("Did not find the top-k results data view");
}
var sb = new StringBuilder();
using (var cursor = top.GetRowCursor(col => true))
{
int index;
if (!top.Schema.TryGetColumnIndex(AnomalyDetectionEvaluator.TopKResultsColumns.Instance, out index))
{
throw Host.Except("Data view does not contain the 'Instance' column");
}
var instanceGetter = cursor.GetGetter <DvText>(index);
if (!top.Schema.TryGetColumnIndex(AnomalyDetectionEvaluator.TopKResultsColumns.AnomalyScore, out index))
{
throw Host.Except("Data view does not contain the 'Anomaly Score' column");
}
var scoreGetter = cursor.GetGetter <Single>(index);
if (!top.Schema.TryGetColumnIndex(AnomalyDetectionEvaluator.TopKResultsColumns.Label, out index))
{
throw Host.Except("Data view does not contain the 'Label' column");
}
var labelGetter = cursor.GetGetter <Single>(index);
bool hasRows = false;
while (cursor.MoveNext())
{
if (!hasRows)
{
sb.AppendFormat("{0} Top-scored Results", _topScored);
sb.AppendLine();
sb.AppendLine("=================================================");
sb.AppendLine("Instance Anomaly Score Labeled");
hasRows = true;
}
var name = default(DvText);
Single score = 0;
Single label = 0;
instanceGetter(ref name);
scoreGetter(ref score);
labelGetter(ref label);
sb.AppendFormat("{0,-10}{1,12:G4}{2,12}", name, score, label);
sb.AppendLine();
}
}
if (sb.Length > 0)
{
ch.Info(MessageSensitivity.UserData, sb.ToString());
}
IDataView overall;
if (!metrics.TryGetValue(MetricKinds.OverallMetrics, out overall))
{
throw Host.Except("No overall metrics found");
}
// Find the number of anomalies, and the thresholds.
int numAnomIndex;
if (!overall.Schema.TryGetColumnIndex(AnomalyDetectionEvaluator.OverallMetrics.NumAnomalies, out numAnomIndex))
{
throw Host.Except("Could not find the 'NumAnomalies' column");
}
int stratCol;
var hasStrat = overall.Schema.TryGetColumnIndex(MetricKinds.ColumnNames.StratCol, out stratCol);
int stratVal;
bool hasStratVals = overall.Schema.TryGetColumnIndex(MetricKinds.ColumnNames.StratVal, out stratVal);
Contracts.Assert(hasStrat == hasStratVals);
DvInt8 numAnomalies = 0;
using (var cursor = overall.GetRowCursor(col => col == numAnomIndex ||
(hasStrat && col == stratCol)))
{
var numAnomGetter = cursor.GetGetter <DvInt8>(numAnomIndex);
ValueGetter <uint> stratGetter = null;
if (hasStrat)
{
var type = cursor.Schema.GetColumnType(stratCol);
stratGetter = RowCursorUtils.GetGetterAs <uint>(type, cursor, stratCol);
}
bool foundRow = false;
while (cursor.MoveNext())
{
uint strat = 0;
if (stratGetter != null)
{
stratGetter(ref strat);
}
if (strat > 0)
{
continue;
}
if (foundRow)
{
throw Host.Except("Found multiple non-stratified rows in overall results data view");
}
foundRow = true;
numAnomGetter(ref numAnomalies);
}
}
var args = new ChooseColumnsTransform.Arguments();
var cols = new List <ChooseColumnsTransform.Column>()
{
new ChooseColumnsTransform.Column()
{
Name = string.Format(FoldDrAtKFormat, _k),
Source = AnomalyDetectionEvaluator.OverallMetrics.DrAtK
},
new ChooseColumnsTransform.Column()
{
Name = string.Format(FoldDrAtPFormat, _p),
Source = AnomalyDetectionEvaluator.OverallMetrics.DrAtPFpr
},
new ChooseColumnsTransform.Column()
{
Name = string.Format(FoldDrAtNumAnomaliesFormat, numAnomalies),
Source = AnomalyDetectionEvaluator.OverallMetrics.DrAtNumPos
},
new ChooseColumnsTransform.Column()
{
Name = AnomalyDetectionEvaluator.OverallMetrics.ThreshAtK
},
new ChooseColumnsTransform.Column()
{
Name = AnomalyDetectionEvaluator.OverallMetrics.ThreshAtP
},
new ChooseColumnsTransform.Column()
{
Name = AnomalyDetectionEvaluator.OverallMetrics.ThreshAtNumPos
},
new ChooseColumnsTransform.Column()
{
Name = BinaryClassifierEvaluator.Auc
}
};
args.Column = cols.ToArray();
IDataView fold = new ChooseColumnsTransform(Host, args, overall);
string weightedFold;
ch.Info(MetricWriter.GetPerFoldResults(Host, fold, out weightedFold));
}
protected override void Serialize(MetricWriter writer, DateTime now)
{
WriteValue(writer, Value, now);
}
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);
}
}
