private BinaryClassificationMetrics EvaluateBinary(IHostEnvironment env, IDataView scoredData)
{
var dataEval = TrainUtils.CreateExamplesOpt(scoredData, label: "Label", feature: "Features");
// Evaluate.
// It does not work. It throws error "Failed to find 'Score' column" when Evaluate is called
//var evaluator = new BinaryClassifierEvaluator(env, new BinaryClassifierEvaluator.Arguments());
var evaluator = new BinaryClassifierMamlEvaluator(env, new BinaryClassifierMamlEvaluator.Arguments());
var metricsDic = evaluator.Evaluate(dataEval);
return(BinaryClassificationMetrics.FromMetrics(env, metricsDic["OverallMetrics"], metricsDic["ConfusionMatrix"])[0]);
}
private void Run(IChannel ch)
{
IDataLoader loader = null;
IPredictor rawPred = null;
IDataView view;
RoleMappedSchema trainSchema = null;
if (_model == null)
{
if (string.IsNullOrEmpty(Args.InputModelFile))
{
loader = CreateLoader();
rawPred = null;
trainSchema = null;
Host.CheckUserArg(Args.LoadPredictor != true, nameof(Args.LoadPredictor),
"Cannot be set to true unless " + nameof(Args.InputModelFile) + " is also specifified.");
}
else
{
LoadModelObjects(ch, _loadPredictor, out rawPred, true, out trainSchema, out loader);
}
view = loader;
}
else
{
view = _model.Apply(Host, new EmptyDataView(Host, _model.InputSchema));
}
// Get the transform chain.
IDataView source;
IDataView end;
LinkedList <ITransformCanSaveOnnx> transforms;
GetPipe(ch, view, out source, out end, out transforms);
Host.Assert(transforms.Count == 0 || transforms.Last.Value == end);
var assembly = System.Reflection.Assembly.GetExecutingAssembly();
var versionInfo = System.Diagnostics.FileVersionInfo.GetVersionInfo(assembly.Location);
var ctx = new OnnxContextImpl(Host, _name, ProducerName, versionInfo.FileVersion,
ModelVersion, _domain);
// If we have a predictor, try to get the scorer for it.
if (rawPred != null)
{
RoleMappedData data;
if (trainSchema != null)
{
data = RoleMappedData.Create(end, trainSchema.GetColumnRoleNames());
}
else
{
// We had a predictor, but no roles stored in the model. Just suppose
// default column names are OK, if present.
data = TrainUtils.CreateExamplesOpt(end, DefaultColumnNames.Label,
DefaultColumnNames.Features, DefaultColumnNames.GroupId, DefaultColumnNames.Weight, DefaultColumnNames.Name);
}
var scorePipe = ScoreUtils.GetScorer(rawPred, data, Host, trainSchema);
var scoreOnnx = scorePipe as ITransformCanSaveOnnx;
if (scoreOnnx?.CanSaveOnnx == true)
{
Host.Assert(scorePipe.Source == end);
end = scorePipe;
transforms.AddLast(scoreOnnx);
}
else
{
Contracts.CheckUserArg(_loadPredictor != true,
nameof(Arguments.LoadPredictor), "We were explicitly told to load the predictor but we do not know how to save it as ONNX.");
ch.Warning("We do not know how to save the predictor as ONNX. Ignoring.");
}
}
else
{
Contracts.CheckUserArg(_loadPredictor != true,
nameof(Arguments.LoadPredictor), "We were explicitly told to load the predictor but one was not present.");
}
HashSet <string> inputColumns = new HashSet <string>();
//Create graph inputs.
for (int i = 0; i < source.Schema.ColumnCount; i++)
{
string colName = source.Schema.GetColumnName(i);
if (_inputsToDrop.Contains(colName))
{
continue;
}
ctx.AddInputVariable(source.Schema.GetColumnType(i), colName);
inputColumns.Add(colName);
}
//Create graph nodes, outputs and intermediate values.
foreach (var trans in transforms)
{
Host.Assert(trans.CanSaveOnnx);
trans.SaveAsOnnx(ctx);
}
//Add graph outputs.
for (int i = 0; i < end.Schema.ColumnCount; ++i)
{
if (end.Schema.IsHidden(i))
{
continue;
}
var idataviewColumnName = end.Schema.GetColumnName(i);;
if (_outputsToDrop.Contains(idataviewColumnName) || _inputsToDrop.Contains(idataviewColumnName))
{
continue;
}
var variableName = ctx.TryGetVariableName(idataviewColumnName);
if (variableName != null)
{
ctx.AddOutputVariable(end.Schema.GetColumnType(i), variableName);
}
}
var model = ctx.MakeModel();
if (_outputModelPath != null)
{
using (var file = Host.CreateOutputFile(_outputModelPath))
using (var stream = file.CreateWriteStream())
model.WriteTo(stream);
}
if (_outputJsonModelPath != null)
{
using (var file = Host.CreateOutputFile(_outputJsonModelPath))
using (var stream = file.CreateWriteStream())
using (var writer = new StreamWriter(stream))
{
var parsedJson = JsonConvert.DeserializeObject(model.ToString());
writer.Write(JsonConvert.SerializeObject(parsedJson, Formatting.Indented));
}
}
if (!string.IsNullOrWhiteSpace(Args.OutputModelFile))
{
Contracts.Assert(loader != null);
ch.Trace("Saving the data pipe");
// Should probably include "end"?
SaveLoader(loader, Args.OutputModelFile);
}
}
private void Run(IChannel ch)
{
IDataLoader loader;
IPredictor rawPred;
RoleMappedSchema trainSchema;
if (string.IsNullOrEmpty(Args.InputModelFile))
{
loader = CreateLoader();
rawPred = null;
trainSchema = null;
Host.CheckUserArg(Args.LoadPredictor != true, nameof(Args.LoadPredictor),
"Cannot be set to true unless " + nameof(Args.InputModelFile) + " is also specifified.");
}
else
{
LoadModelObjects(ch, _loadPredictor, out rawPred, true, out trainSchema, out loader);
}
// Get the transform chain.
IDataView source;
IDataView end;
LinkedList <ITransformCanSavePfa> transforms;
GetPipe(ch, loader, out source, out end, out transforms);
Host.Assert(transforms.Count == 0 || transforms.Last.Value == end);
// If we have a predictor, try to get the scorer for it.
if (rawPred != null)
{
RoleMappedData data;
if (trainSchema != null)
{
data = RoleMappedData.Create(end, trainSchema.GetColumnRoleNames());
}
else
{
// We had a predictor, but no roles stored in the model. Just suppose
// default column names are OK, if present.
data = TrainUtils.CreateExamplesOpt(end, DefaultColumnNames.Label,
DefaultColumnNames.Features, DefaultColumnNames.GroupId, DefaultColumnNames.Weight, DefaultColumnNames.Name);
}
var scorePipe = ScoreUtils.GetScorer(rawPred, data, Host, trainSchema);
var scorePfa = scorePipe as ITransformCanSavePfa;
if (scorePfa?.CanSavePfa == true)
{
Host.Assert(scorePipe.Source == end);
end = scorePipe;
transforms.AddLast(scorePfa);
}
else
{
Contracts.CheckUserArg(_loadPredictor != true,
nameof(Arguments.LoadPredictor), "We were explicitly told to load the predictor but we do not know how to save it as PFA.");
ch.Warning("We do not know how to save the predictor as PFA. Ignoring.");
}
}
else
{
Contracts.CheckUserArg(_loadPredictor != true,
nameof(Arguments.LoadPredictor), "We were explicitly told to load the predictor but one was not present.");
}
var ctx = new BoundPfaContext(Host, source.Schema, _inputsToDrop, allowSet: _allowSet);
foreach (var trans in transforms)
{
Host.Assert(trans.CanSavePfa);
trans.SaveAsPfa(ctx);
}
var toExport = new List <string>();
for (int i = 0; i < end.Schema.ColumnCount; ++i)
{
if (end.Schema.IsHidden(i))
{
continue;
}
var name = end.Schema.GetColumnName(i);
if (_outputsToDrop.Contains(name))
{
continue;
}
if (!ctx.IsInput(name) || _keepInput)
{
toExport.Add(name);
}
}
JObject pfaDoc = ctx.Finalize(end.Schema, toExport.ToArray());
if (_name != null)
{
pfaDoc["name"] = _name;
}
if (_outputModelPath == null)
{
ch.Info(MessageSensitivity.Schema, pfaDoc.ToString(_formatting));
}
else
{
using (var file = Host.CreateOutputFile(_outputModelPath))
using (var stream = file.CreateWriteStream())
using (var writer = new StreamWriter(stream))
writer.Write(pfaDoc.ToString(_formatting));
}
if (!string.IsNullOrWhiteSpace(Args.OutputModelFile))
{
ch.Trace("Saving the data pipe");
// Should probably include "end"?
SaveLoader(loader, Args.OutputModelFile);
}
}