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>
/// 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);
}
public static AutoMlMlState InferPipelines(IHostEnvironment env, PipelineOptimizerBase autoMlEngine, IDataView data, int numTransformLevels,
int batchSize, SupportedMetric metric, out PipelinePattern bestPipeline, int numOfSampleRows,
ITerminator terminator, MacroUtils.TrainerKinds trainerKind)
{
Contracts.CheckValue(env, nameof(env));
env.CheckValue(data, nameof(data));
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);
}
