/// <summary>
/// Create a list of <see cref="SweepableEstimator"/> for featurizing catalog columns.
/// </summary>
/// <param name="outputColumnNames">output column names.</param>
/// <param name="inputColumnNames">input column names.</param>
internal SweepableEstimator[] CatalogFeaturizer(string[] outputColumnNames, string[] inputColumnNames)
{
Contracts.Check(outputColumnNames.Count() == inputColumnNames.Count() && outputColumnNames.Count() > 0, "outputColumnNames and inputColumnNames must have the same length and greater than 0");
var option = new OneHotOption
{
InputColumnNames = inputColumnNames,
OutputColumnNames = outputColumnNames,
};
return(new SweepableEstimator[] { SweepableEstimatorFactory.CreateOneHotEncoding(option), SweepableEstimatorFactory.CreateOneHotHashEncoding(option) });
}
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);
}