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));
}
public static SweepablePipelineDataContract ToDataContract(this SweepablePipeline pipeline)
{
var estimatorContracts = new List <List <SweepableEstimatorDataContract> >();
var nodes = pipeline.EstimatorGenerators;
foreach (var node in nodes)
{
var estimators = new List <SweepableEstimatorDataContract>();
for (int i = 0; i != node.Count; ++i)
{
var estimator = node[i].RawValue as SweepableEstimatorBase;
var estimatorContract = new SweepableEstimatorDataContract()
{
EstimatorName = estimator.EstimatorName,
InputColumns = estimator.InputColumns,
OutputColumns = estimator.OutputColumns,
Scope = estimator.Scope,
};
estimators.Add(estimatorContract);
}
estimatorContracts.Add(estimators);
}
return(new SweepablePipelineDataContract()
{
Estimators = estimatorContracts,
});
}
public void SweepablePipeline_summary_should_work()
{
var sweepablePipeline = new SweepablePipeline()
.Append(new MockTransformer())
.Append(new MockEstimatorBuilder("mockEstimator"));
sweepablePipeline.ToString().Should().Be("SweepablePipeline([MockTransformer]=>[mockEstimator])");
}
public static SweepablePipeline ToPipeline(this SweepablePipelineDataContract pipelineContract, MLContext context)
{
var sweepablePipeline = new SweepablePipeline();
foreach (var node in pipelineContract.Estimators)
{
sweepablePipeline.Append(node.Select(n => context.AutoML().Serializable().Factory.CreateSweepableEstimator(n)).ToArray());
}
return(sweepablePipeline);
}
public SweepablePipeline BuildPipeline(MLContext context, IEnumerable <Column> columns)
{
var sweepablePipeline = new SweepablePipeline();
foreach (var column in columns)
{
switch (column.ColumnPurpose)
{
case ColumnPurpose.NumericFeature:
sweepablePipeline.Append(this.GetSuggestedNumericColumnTransformers(context, column).ToArray());
break;
case ColumnPurpose.CategoricalFeature:
sweepablePipeline.Append(this.GetSuggestedCatagoricalColumnTransformers(context, column).ToArray());
break;
case ColumnPurpose.TextFeature:
sweepablePipeline.Append(this.GetSuggestedTextColumnTransformers(context, column).ToArray());
break;
case ColumnPurpose.Label:
sweepablePipeline.Append(this.GetSuggestedLabelColumnTransformers(context, column).ToArray());
break;
default:
break;
}
}
var featureColumns = columns.Where(c => c.ColumnPurpose == ColumnPurpose.CategoricalFeature ||
c.ColumnPurpose == ColumnPurpose.NumericFeature ||
c.ColumnPurpose == ColumnPurpose.TextFeature)
.Select(c => c.Name)
.ToArray();
if (this.PipelineBuilderOption.IsUsingSingleFeatureTrainer)
{
sweepablePipeline.Append(context.AutoML().Serializable().Transformer.Concatnate(featureColumns, "_FEATURE"));
var labelColumn = columns.Where(c => c.ColumnPurpose == ColumnPurpose.Label).First();
sweepablePipeline.Append(this.GetSuggestedSingleFeatureTrainers(context, labelColumn, "_FEATURE").ToArray());
}
return(sweepablePipeline);
}
public void SweepablePipeline_should_create_SingleEstimatorSweepablePipeline()
{
var sweepablePipeline = new SweepablePipeline()
.Append(new MockEstimatorBuilder("estimator1_1"))
.Append(new MockEstimatorBuilder("estimator2_1"), new MockEstimatorBuilder("estimator2_2"))
.Append(new MockEstimatorBuilder("estimator3_1"), new MockEstimatorBuilder("estimator3_2"), new MockEstimatorBuilder("estimator3_3"));
var res = new StringBuilder();
res.AppendLine(sweepablePipeline.ToString());
var sweeper = new GridSearchSweeper();
foreach (var param in sweeper.ProposeSweeps(sweepablePipeline, 100))
{
var singleEstimatorPipeline = sweepablePipeline.BuildFromParameters(param);
res.AppendLine(singleEstimatorPipeline.ToString());
}
Approvals.Verify(res.ToString());
}
