public void SweepablePipeline_Append_SweepableEstimator_Test()
{
var pipeline = new SweepablePipeline();
var concatOption = new ConcatOption()
{
InputColumnNames = new List <string> {
"a", "b", "c"
}.ToArray(),
OutputColumnName = "a",
};
var lgbmOption = new LgbmOption()
{
FeatureColumnName = "Feature",
LabelColumnName = "Label",
};
// pipeline can append a single sweepable estimator
pipeline = pipeline.Append(SweepableEstimatorFactory.CreateConcatenate(concatOption));
// pipeline can append muliple sweepable estimators.
pipeline = pipeline.Append(SweepableEstimatorFactory.CreateLightGbmBinary(lgbmOption), SweepableEstimatorFactory.CreateConcatenate(concatOption));
// pipeline can append sweepable pipelines mixed with sweepble estimators
pipeline = pipeline.Append(SweepableEstimatorFactory.CreateConcatenate(concatOption), pipeline);
// pipeline can append sweepable pipelines.
pipeline = pipeline.Append(pipeline, pipeline);
Approvals.Verify(JsonSerializer.Serialize(pipeline, _jsonSerializerOptions));
}
private SweepableEstimatorPipeline CreateSweepbaleEstimatorPipeline()
{
var concat = SweepableEstimatorFactory.CreateConcatenate(new ConcatOption());
var replaceMissingValue = SweepableEstimatorFactory.CreateReplaceMissingValues(new ReplaceMissingValueOption());
var oneHot = SweepableEstimatorFactory.CreateOneHotEncoding(new OneHotOption());
var lightGbm = SweepableEstimatorFactory.CreateLightGbmBinary(new LgbmOption());
var fastTree = SweepableEstimatorFactory.CreateFastTreeBinary(new FastTreeOption());
var pipeline = new SweepableEstimatorPipeline(new SweepableEstimator[] { concat, replaceMissingValue, oneHot, lightGbm, fastTree });
return(pipeline);
}
private MultiModelPipeline CreateMultiModelPipeline()
{
var concat = SweepableEstimatorFactory.CreateConcatenate(new ConcatOption());
var replaceMissingValue = SweepableEstimatorFactory.CreateReplaceMissingValues(new ReplaceMissingValueOption());
var oneHot = SweepableEstimatorFactory.CreateOneHotEncoding(new OneHotOption());
var lightGbm = SweepableEstimatorFactory.CreateLightGbmBinary(new LgbmOption());
var fastTree = SweepableEstimatorFactory.CreateFastTreeBinary(new FastTreeOption());
var pipeline = new MultiModelPipeline();
pipeline = pipeline.AppendOrSkip(replaceMissingValue + replaceMissingValue * oneHot);
pipeline = pipeline.AppendOrSkip(concat);
pipeline = pipeline.Append(lightGbm + fastTree);
return(pipeline);
}
/// <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);
}
