public static AutoMlMlState InferPipelines(IHostEnvironment env, PipelineOptimizerBase autoMlEngine, string trainDataPath,
string schemaDefinitionFile, out string schemaDefinition, int numTransformLevels, int batchSize, SupportedMetric metric,
out PipelinePattern bestPipeline, int numOfSampleRows, ITerminator terminator, MacroUtils.TrainerKinds trainerKind)
{
Contracts.CheckValue(env, nameof(env));
// REVIEW: Should be able to infer schema by itself, without having to
// infer recipes. Look into this.
// Set loader settings through inference
RecipeInference.InferRecipesFromData(env, trainDataPath, schemaDefinitionFile,
out var _, out schemaDefinition, out var _, true);
#pragma warning disable 0618
var data = ImportTextData.ImportText(env, new ImportTextData.Input
{
InputFile = new SimpleFileHandle(env, trainDataPath, false, false),
CustomSchema = schemaDefinition
}).Data;
#pragma warning restore 0618
var splitOutput = TrainTestSplit.Split(env, new TrainTestSplit.Input {
Data = data, Fraction = 0.8f
});
AutoMlMlState amls = new AutoMlMlState(env, metric, autoMlEngine, terminator, trainerKind,
splitOutput.TrainData.Take(numOfSampleRows), splitOutput.TestData.Take(numOfSampleRows));
bestPipeline = amls.InferPipelines(numTransformLevels, batchSize, numOfSampleRows);
return(amls);
}
/// <summary>
/// Given a predictor type returns a set of all permissible learners (with their sweeper params, if defined).
/// </summary>
/// <returns>Array of viable learners.</returns>
public static SuggestedRecipe.SuggestedLearner[] AllowedLearners(IHostEnvironment env, MacroUtils.TrainerKinds trainerKind)
{
//not all learners advertised in the API are available in CORE.
var catalog = env.ComponentCatalog;
var availableLearnersList = catalog.AllEntryPoints().Where(
x => x.InputKinds?.FirstOrDefault(i => i == typeof(CommonInputs.ITrainerInput)) != null);
var learners = new List <SuggestedRecipe.SuggestedLearner>();
var type = typeof(CommonInputs.ITrainerInput);
var trainerTypes = typeof(Experiment).Assembly.GetTypes()
.Where(p => type.IsAssignableFrom(p) &&
MacroUtils.IsTrainerOfKind(p, trainerKind));
foreach (var tt in trainerTypes)
{
var sweepParams = AutoMlUtils.GetSweepRanges(tt);
var epInputObj = (CommonInputs.ITrainerInput)tt.GetConstructor(Type.EmptyTypes)?.Invoke(new object[] { });
var sl = new SuggestedRecipe.SuggestedLearner
{
PipelineNode = new TrainerPipelineNode(epInputObj, sweepParams),
LearnerName = tt.Name
};
if (sl.PipelineNode != null && availableLearnersList.FirstOrDefault(l => l.Name.Equals(sl.PipelineNode.GetEpName())) != null)
{
learners.Add(sl);
}
}
return(learners.ToArray());
}
/// <summary>
/// The InferPipelines methods are just public portals to the internal function that handle different
/// types of data being passed in: training IDataView, path to training file, or train and test files.
/// </summary>
public static AutoMlMlState InferPipelines(IHostEnvironment env, PipelineOptimizerBase autoMlEngine,
IDataView trainData, IDataView testData, int numTransformLevels, int batchSize, SupportedMetric metric,
out PipelinePattern bestPipeline, ITerminator terminator, MacroUtils.TrainerKinds trainerKind)
{
Contracts.CheckValue(env, nameof(env));
env.CheckValue(trainData, nameof(trainData));
env.CheckValue(testData, nameof(testData));
int numOfRows = (int)(trainData.GetRowCount(false) ?? 1000);
AutoMlMlState amls = new AutoMlMlState(env, metric, autoMlEngine, terminator, trainerKind, trainData, testData);
bestPipeline = amls.InferPipelines(numTransformLevels, batchSize, numOfRows);
return(amls);
}
