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));
}
/// <summary>
/// Create a list of <see cref="SweepableEstimator"/> for binary classification.
/// </summary>
/// <param name="labelColumnName">label column name.</param>
/// <param name="featureColumnName">feature column name.</param>
/// <param name="exampleWeightColumnName">example weight column name.</param>
/// <param name="useFastForest">true if use fast forest as available trainer.</param>
/// <param name="useLgbm">true if use lgbm as available trainer.</param>
/// <param name="useFastTree">true if use fast tree as available trainer.</param>
/// <param name="useLbfgs">true if use lbfgs as available trainer.</param>
/// <param name="useSdca">true if use sdca as available trainer.</param>
/// <param name="fastTreeOption">if provided, use it as initial option for fast tree, otherwise the default option will be used.</param>
/// <param name="lgbmOption">if provided, use it as initial option for lgbm, otherwise the default option will be used.</param>
/// <param name="fastForestOption">if provided, use it as initial option for fast forest, otherwise the default option will be used.</param>
/// <param name="lbfgsOption">if provided, use it as initial option for lbfgs, otherwise the default option will be used.</param>
/// <param name="sdcaOption">if provided, use it as initial option for sdca, otherwise the default option will be used.</param>
/// <param name="fastTreeSearchSpace">if provided, use it as search space for fast tree, otherwise the default search space will be used.</param>
/// <param name="lgbmSearchSpace">if provided, use it as search space for lgbm, otherwise the default search space will be used.</param>
/// <param name="fastForestSearchSpace">if provided, use it as search space for fast forest, otherwise the default search space will be used.</param>
/// <param name="lbfgsSearchSpace">if provided, use it as search space for lbfgs, otherwise the default search space will be used.</param>
/// <param name="sdcaSearchSpace">if provided, use it as search space for sdca, otherwise the default search space will be used.</param>
/// <returns></returns>
public SweepableEstimator[] BinaryClassification(string labelColumnName = DefaultColumnNames.Label, string featureColumnName = DefaultColumnNames.Features, string exampleWeightColumnName = null, bool useFastForest = true, bool useLgbm = true, bool useFastTree = true, bool useLbfgs = true, bool useSdca = true,
FastTreeOption fastTreeOption = null, LgbmOption lgbmOption = null, FastForestOption fastForestOption = null, LbfgsOption lbfgsOption = null, SdcaOption sdcaOption = null,
SearchSpace <FastTreeOption> fastTreeSearchSpace = null, SearchSpace <LgbmOption> lgbmSearchSpace = null, SearchSpace <FastForestOption> fastForestSearchSpace = null, SearchSpace <LbfgsOption> lbfgsSearchSpace = null, SearchSpace <SdcaOption> sdcaSearchSpace = null)
{
var res = new List <SweepableEstimator>();
if (useFastTree)
{
fastTreeOption = fastTreeOption ?? new FastTreeOption();
fastTreeOption.LabelColumnName = labelColumnName;
fastTreeOption.FeatureColumnName = featureColumnName;
fastTreeOption.ExampleWeightColumnName = exampleWeightColumnName;
res.Add(SweepableEstimatorFactory.CreateFastTreeBinary(fastTreeOption, fastTreeSearchSpace ?? new SearchSpace <FastTreeOption>(fastTreeOption)));
}
if (useFastForest)
{
fastForestOption = fastForestOption ?? new FastForestOption();
fastForestOption.LabelColumnName = labelColumnName;
fastForestOption.FeatureColumnName = featureColumnName;
fastForestOption.ExampleWeightColumnName = exampleWeightColumnName;
res.Add(SweepableEstimatorFactory.CreateFastForestBinary(fastForestOption, fastForestSearchSpace ?? new SearchSpace <FastForestOption>(fastForestOption)));
}
if (useLgbm)
{
lgbmOption = lgbmOption ?? new LgbmOption();
lgbmOption.LabelColumnName = labelColumnName;
lgbmOption.FeatureColumnName = featureColumnName;
lgbmOption.ExampleWeightColumnName = exampleWeightColumnName;
res.Add(SweepableEstimatorFactory.CreateLightGbmBinary(lgbmOption, lgbmSearchSpace ?? new SearchSpace <LgbmOption>(lgbmOption)));
}
if (useLbfgs)
{
lbfgsOption = lbfgsOption ?? new LbfgsOption();
lbfgsOption.LabelColumnName = labelColumnName;
lbfgsOption.FeatureColumnName = featureColumnName;
lbfgsOption.ExampleWeightColumnName = exampleWeightColumnName;
res.Add(SweepableEstimatorFactory.CreateLbfgsLogisticRegressionBinary(lbfgsOption, lbfgsSearchSpace ?? new SearchSpace <LbfgsOption>(lbfgsOption)));
}
if (useSdca)
{
sdcaOption = sdcaOption ?? new SdcaOption();
sdcaOption.LabelColumnName = labelColumnName;
sdcaOption.FeatureColumnName = featureColumnName;
sdcaOption.ExampleWeightColumnName = exampleWeightColumnName;
res.Add(SweepableEstimatorFactory.CreateSdcaLogisticRegressionBinary(sdcaOption, sdcaSearchSpace ?? new SearchSpace <SdcaOption>(sdcaOption)));
}
return(res.ToArray());
}
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);
}
