public void FastForestRegressorEstimator()
{
var dataView = GetRegressionPipeline();
var trainer = new FastForestRegression(Env, "Label", "Features", advancedSettings: s =>
{
s.BaggingSize = 2;
s.NumTrees = 10;
});
TestEstimatorCore(trainer, dataView);
var model = trainer.Train(dataView, dataView);
Done();
}
private FastForestRegressionPredictor FitModel(IEnumerable <IRunResult> previousRuns)
{
Single[] targets = new Single[previousRuns.Count()];
Single[][] features = new Single[previousRuns.Count()][];
int i = 0;
foreach (RunResult r in previousRuns)
{
features[i] = SweeperProbabilityUtils.ParameterSetAsFloatArray(_host, _sweepParameters, r.ParameterSet, true);
targets[i] = (Float)r.MetricValue;
i++;
}
ArrayDataViewBuilder dvBuilder = new ArrayDataViewBuilder(_host);
dvBuilder.AddColumn("Label", NumberType.Float, targets);
dvBuilder.AddColumn("Features", NumberType.Float, features);
IDataView view = dvBuilder.GetDataView();
_host.Assert(view.GetRowCount() == targets.Length, "This data view will have as many rows as there have been evaluations");
RoleMappedData data = TrainUtils.CreateExamples(view, "Label", "Features");
using (IChannel ch = _host.Start("Single training"))
{
// Set relevant random forest arguments.
FastForestRegression.Arguments args = new FastForestRegression.Arguments();
args.FeatureFraction = _args.SplitRatio;
args.NumTrees = _args.NumOfTrees;
args.MinDocumentsInLeafs = _args.NMinForSplit;
// Train random forest.
FastForestRegression trainer = new FastForestRegression(_host, args);
trainer.Train(data);
FastForestRegressionPredictor predictor = trainer.CreatePredictor();
// Return random forest predictor.
ch.Done();
return(predictor);
}
}
private FastForestRegressionModelParameters FitModel(IEnumerable <IRunResult> previousRuns)
{
Single[] targets = new Single[previousRuns.Count()];
Single[][] features = new Single[previousRuns.Count()][];
int i = 0;
foreach (RunResult r in previousRuns)
{
features[i] = SweeperProbabilityUtils.ParameterSetAsFloatArray(_host, _sweepParameters, r.ParameterSet, true);
targets[i] = (Float)r.MetricValue;
i++;
}
ArrayDataViewBuilder dvBuilder = new ArrayDataViewBuilder(_host);
dvBuilder.AddColumn(DefaultColumnNames.Label, NumberType.Float, targets);
dvBuilder.AddColumn(DefaultColumnNames.Features, NumberType.Float, features);
IDataView view = dvBuilder.GetDataView();
_host.Assert(view.GetRowCount() == targets.Length, "This data view will have as many rows as there have been evaluations");
using (IChannel ch = _host.Start("Single training"))
{
// Set relevant random forest arguments.
// Train random forest.
var trainer = new FastForestRegression(_host,
new FastForestRegression.Options
{
FeatureFraction = _args.SplitRatio,
NumTrees = _args.NumOfTrees,
MinDocumentsInLeafs = _args.NMinForSplit,
LabelColumn = DefaultColumnNames.Label,
FeatureColumn = DefaultColumnNames.Features,
});
var predictor = trainer.Train(view);
// Return random forest predictor.
return(predictor.Model);
}
}
private FastForestRegressionModelParameters FitModel(IEnumerable <IRunResult> previousRuns)
{
Single[] targets = new Single[previousRuns.Count()];
Single[][] features = new Single[previousRuns.Count()][];
int i = 0;
foreach (RunResult r in previousRuns)
{
features[i] = SweeperProbabilityUtils.ParameterSetAsFloatArray(_sweepParameters, r.ParameterSet, true);
targets[i] = (Float)r.MetricValue;
i++;
}
ArrayDataViewBuilder dvBuilder = new ArrayDataViewBuilder(_context);
dvBuilder.AddColumn(DefaultColumnNames.Label, NumberType.Float, targets);
dvBuilder.AddColumn(DefaultColumnNames.Features, NumberType.Float, features);
IDataView data = dvBuilder.GetDataView();
AutoMlUtils.Assert(data.GetRowCount() == targets.Length, "This data view will have as many rows as there have been evaluations");
// Set relevant random forest arguments.
// Train random forest.
var trainer = new FastForestRegression(_context, DefaultColumnNames.Label, DefaultColumnNames.Features, advancedSettings: s =>
{
s.FeatureFraction = _args.SplitRatio;
s.NumTrees = _args.NumOfTrees;
s.MinDocumentsInLeafs = _args.NMinForSplit;
});
var predictor = trainer.Train(data).Model;
// Return random forest predictor.
return(predictor);
}