public void TestPipelineNodeCloning()
{
var env = new MLContext().AddStandardComponents(); // AutoInference uses ComponentCatalog to find all learners
var lr1 = RecipeInference
.AllowedLearners(env, MacroUtils.TrainerKinds.SignatureBinaryClassifierTrainer)
.First(learner => learner.PipelineNode != null && learner.LearnerName.Contains("LogisticRegression"));
var sdca1 = RecipeInference
.AllowedLearners(env, MacroUtils.TrainerKinds.SignatureBinaryClassifierTrainer)
.First(learner => learner.PipelineNode != null && learner.LearnerName.Contains("StochasticDualCoordinateAscent"));
// Clone and change hyperparam values
var lr2 = lr1.Clone();
lr1.PipelineNode.SweepParams[0].RawValue = 1.2f;
lr2.PipelineNode.SweepParams[0].RawValue = 3.5f;
var sdca2 = sdca1.Clone();
sdca1.PipelineNode.SweepParams[0].RawValue = 3;
sdca2.PipelineNode.SweepParams[0].RawValue = 0;
// Make sure the changes are propagated to entry point objects
env.Check(lr1.PipelineNode.UpdateProperties());
env.Check(lr2.PipelineNode.UpdateProperties());
env.Check(sdca1.PipelineNode.UpdateProperties());
env.Check(sdca2.PipelineNode.UpdateProperties());
env.Check(lr1.PipelineNode.CheckEntryPointStateMatchesParamValues());
env.Check(lr2.PipelineNode.CheckEntryPointStateMatchesParamValues());
env.Check(sdca1.PipelineNode.CheckEntryPointStateMatchesParamValues());
env.Check(sdca2.PipelineNode.CheckEntryPointStateMatchesParamValues());
// Make sure second object's set of changes didn't overwrite first object's
env.Check(!lr1.PipelineNode.SweepParams[0].RawValue.Equals(lr2.PipelineNode.SweepParams[0].RawValue));
env.Check(!sdca2.PipelineNode.SweepParams[0].RawValue.Equals(sdca1.PipelineNode.SweepParams[0].RawValue));
}
public void TestLearn()
{
var env = new MLContext().AddStandardComponents(); // AutoInference uses ComponentCatalog to find all learners
string pathData = GetDataPath("adult.train");
string pathDataTest = GetDataPath("adult.test");
int numOfSampleRows = 1000;
int batchSize = 5;
int numIterations = 10;
int numTransformLevels = 3;
SupportedMetric metric = PipelineSweeperSupportedMetrics.GetSupportedMetric(PipelineSweeperSupportedMetrics.Metrics.Auc);
// Using the simple, uniform random sampling (with replacement) engine
PipelineOptimizerBase autoMlEngine = new UniformRandomEngine(env);
// Test initial learning
var amls = AutoInference.InferPipelines(env, autoMlEngine, pathData, "", out var schema, numTransformLevels, batchSize,
metric, out var bestPipeline, numOfSampleRows, new IterationTerminator(numIterations / 2), MacroUtils.TrainerKinds.SignatureBinaryClassifierTrainer);
env.Check(amls.GetAllEvaluatedPipelines().Length == numIterations / 2);
// Resume learning
amls.UpdateTerminator(new IterationTerminator(numIterations));
bestPipeline = amls.InferPipelines(numTransformLevels, batchSize, numOfSampleRows);
env.Check(amls.GetAllEvaluatedPipelines().Length == numIterations);
// Use best pipeline for another task
var inputFileTrain = new SimpleFileHandle(env, pathData, false, false);
#pragma warning disable 0618
var datasetTrain = ImportTextData.ImportText(env,
new ImportTextData.Input {
InputFile = inputFileTrain, CustomSchema = schema
}).Data;
var inputFileTest = new SimpleFileHandle(env, pathDataTest, false, false);
var datasetTest = ImportTextData.ImportText(env,
new ImportTextData.Input {
InputFile = inputFileTest, CustomSchema = schema
}).Data;
#pragma warning restore 0618
// REVIEW: Theoretically, it could be the case that a new, very bad learner is introduced and
// we get unlucky and only select it every time, such that this test fails. Not
// likely at all, but a non-zero probability. Should be ok, since all current learners are returning d > .80.
bestPipeline.RunTrainTestExperiment(datasetTrain, datasetTest, metric, MacroUtils.TrainerKinds.SignatureBinaryClassifierTrainer,
out var testMetricValue, out var trainMtericValue);
env.Check(testMetricValue > 0.2);
Done();
}
public void TestTextDatasetLearn()
{
var env = new MLContext().AddStandardComponents(); // AutoInference uses ComponentCatalog to find all learners
string pathData = GetDataPath(@"../UnitTest/tweets_labeled_10k_test_validation.tsv");
int batchSize = 5;
int numIterations = 35;
int numTransformLevels = 1;
int numSampleRows = 100;
SupportedMetric metric = PipelineSweeperSupportedMetrics.GetSupportedMetric(PipelineSweeperSupportedMetrics.Metrics.AccuracyMicro);
// Using the simple, uniform random sampling (with replacement) engine
PipelineOptimizerBase autoMlEngine = new UniformRandomEngine(env);
// Test initial learning
var amls = AutoInference.InferPipelines(env, autoMlEngine, pathData, "", out var _, numTransformLevels, batchSize,
metric, out var _, numSampleRows, new IterationTerminator(numIterations),
MacroUtils.TrainerKinds.SignatureMultiClassClassifierTrainer);
env.Check(amls.GetAllEvaluatedPipelines().Length == numIterations);
Done();
}