public static MultiModelPipeline Append(this SweepableEstimator estimator, params SweepableEstimator[] estimators)
{
var multiModelPipeline = new MultiModelPipeline();
multiModelPipeline = multiModelPipeline.Append(estimator);
return(multiModelPipeline.Append(estimators));
}
public override ExperimentResult <BinaryClassificationMetrics> Execute(IDataView trainData, ColumnInformation columnInformation, IEstimator <ITransformer> preFeaturizer = null, IProgress <RunDetail <BinaryClassificationMetrics> > progressHandler = null)
{
var label = columnInformation.LabelColumnName;
_experiment.SetEvaluateMetric(Settings.OptimizingMetric, label);
_experiment.SetTrainingTimeInSeconds(Settings.MaxExperimentTimeInSeconds);
// Cross val threshold for # of dataset rows --
// If dataset has < threshold # of rows, use cross val.
// Else, run experiment using train-validate split.
const int crossValRowCountThreshold = 15000;
var rowCount = DatasetDimensionsUtil.CountRows(trainData, crossValRowCountThreshold);
// TODO
// split cross validation result according to sample key as well.
if (rowCount < crossValRowCountThreshold)
{
const int numCrossValFolds = 10;
_experiment.SetDataset(trainData, numCrossValFolds);
}
else
{
var splitData = Context.Data.TrainTestSplit(trainData);
_experiment.SetDataset(splitData.TrainSet, splitData.TestSet);
}
MultiModelPipeline pipeline = new MultiModelPipeline();
if (preFeaturizer != null)
{
pipeline = pipeline.Append(preFeaturizer);
}
pipeline = pipeline.Append(Context.Auto().Featurizer(trainData, columnInformation, Features))
.Append(Context.Auto().BinaryClassification(label, Features));
_experiment.SetPipeline(pipeline);
var monitor = new BinaryClassificationTrialResultMonitor();
monitor.OnTrialCompleted += (o, e) =>
{
var detail = ToRunDetail(e);
progressHandler?.Report(detail);
};
_experiment.SetMonitor(monitor);
_experiment.Run();
var runDetails = monitor.RunDetails.Select(e => ToRunDetail(e));
var bestRun = ToRunDetail(monitor.BestRun);
var result = new ExperimentResult <BinaryClassificationMetrics>(runDetails, bestRun);
return(result);
}
public static MultiModelPipeline Append(this SweepableEstimatorPipeline pipeline, params SweepableEstimator[] estimators)
{
var multiModelPipeline = new MultiModelPipeline();
foreach (var estimator in pipeline.Estimators)
{
multiModelPipeline = multiModelPipeline.Append(estimator);
}
return(multiModelPipeline.Append(estimators));
}
/// <summary>
/// Create a single featurize pipeline according to <paramref name="columnInformation"/>. This function will collect all columns in <paramref name="columnInformation"/>,
/// featurizing them using <see cref="CatalogFeaturizer(string[], string[])"/>, <see cref="NumericFeaturizer(string[], string[])"/> or <see cref="TextFeaturizer(string, string)"/>. And combine
/// them into a single feature column as output.
/// </summary>
/// <param name="data">input data.</param>
/// <param name="columnInformation">column information.</param>
/// <param name="outputColumnName">output feature column.</param>
/// <returns>A <see cref="MultiModelPipeline"/> for featurization.</returns>
public MultiModelPipeline Featurizer(IDataView data, ColumnInformation columnInformation, string outputColumnName = "Features")
{
Contracts.CheckValue(data, nameof(data));
Contracts.CheckValue(columnInformation, nameof(columnInformation));
var columnPurposes = PurposeInference.InferPurposes(this._context, data, columnInformation);
var textFeatures = columnPurposes.Where(c => c.Purpose == ColumnPurpose.TextFeature);
var numericFeatures = columnPurposes.Where(c => c.Purpose == ColumnPurpose.NumericFeature);
var catalogFeatures = columnPurposes.Where(c => c.Purpose == ColumnPurpose.CategoricalFeature);
var textFeatureColumnNames = textFeatures.Select(c => data.Schema[c.ColumnIndex].Name).ToArray();
var numericFeatureColumnNames = numericFeatures.Select(c => data.Schema[c.ColumnIndex].Name).ToArray();
var catalogFeatureColumnNames = catalogFeatures.Select(c => data.Schema[c.ColumnIndex].Name).ToArray();
var pipeline = new MultiModelPipeline();
if (numericFeatureColumnNames.Length > 0)
{
pipeline = pipeline.Append(this.NumericFeaturizer(numericFeatureColumnNames, numericFeatureColumnNames));
}
if (catalogFeatureColumnNames.Length > 0)
{
pipeline = pipeline.Append(this.CatalogFeaturizer(catalogFeatureColumnNames, catalogFeatureColumnNames));
}
foreach (var textColumn in textFeatureColumnNames)
{
pipeline = pipeline.Append(this.TextFeaturizer(textColumn, textColumn));
}
var option = new ConcatOption
{
InputColumnNames = textFeatureColumnNames.Concat(numericFeatureColumnNames).Concat(catalogFeatureColumnNames).ToArray(),
OutputColumnName = outputColumnName,
};
if (option.InputColumnNames.Length > 0)
{
pipeline = pipeline.Append(SweepableEstimatorFactory.CreateConcatenate(option));
}
return(pipeline);
}
public AutoMLExperiment SetPipeline(SweepableEstimatorPipeline pipeline)
{
var res = new MultiModelPipeline();
foreach (var e in pipeline.Estimators)
{
res = res.Append(e);
}
SetPipeline(res);
return(this);
}
public override CrossValidationExperimentResult <BinaryClassificationMetrics> Execute(IDataView trainData, uint numberOfCVFolds, ColumnInformation columnInformation = null, IEstimator <ITransformer> preFeaturizer = null, IProgress <CrossValidationRunDetail <BinaryClassificationMetrics> > progressHandler = null)
{
var label = columnInformation.LabelColumnName;
_experiment.SetEvaluateMetric(Settings.OptimizingMetric, label);
_experiment.SetTrainingTimeInSeconds(Settings.MaxExperimentTimeInSeconds);
_experiment.SetDataset(trainData, (int)numberOfCVFolds);
MultiModelPipeline pipeline = new MultiModelPipeline();
if (preFeaturizer != null)
{
pipeline = pipeline.Append(preFeaturizer);
}
pipeline = pipeline.Append(Context.Auto().Featurizer(trainData, columnInformation, "__Features__"))
.Append(Context.Auto().BinaryClassification(label, featureColumnName: Features));
_experiment.SetPipeline(pipeline);
var monitor = new BinaryClassificationTrialResultMonitor();
monitor.OnTrialCompleted += (o, e) =>
{
var runDetails = ToCrossValidationRunDetail(e);
progressHandler?.Report(runDetails);
};
_experiment.SetMonitor(monitor);
_experiment.Run();
var runDetails = monitor.RunDetails.Select(e => ToCrossValidationRunDetail(e));
var bestResult = ToCrossValidationRunDetail(monitor.BestRun);
var result = new CrossValidationExperimentResult <BinaryClassificationMetrics>(runDetails, bestResult);
return(result);
}