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);
}
static void Main(string[] args)
{
var df = DataFrame.ReadCSV("iris.csv", ',', true);
var X = df.GetDoubleRange(0, 4);
var y = df.GetRange(4, 5, x => x).Select(x => x[0]).ToArray();
var Y = DataFrame.GetDummies(y);
var testSplit = new TrainTestSplit(X, Y);
var t = testSplit.Split(0, testSize: 0.30);
var network = new MLPClassifier(new int[] { 4, 5, 5, 5, 3 },
activation: "sigmoid",
randomSeed: 0,
verbose: true,
learningRate: 0.5);
network.Fit(t.XTrain, t.YTrain, numberOfEpochs: 200);
var predictions = network.Predict(t.XTest);
var report = new ClasificationReport(t.YTest, predictions);
System.Console.WriteLine($"Good predictions: {report.CorrectPredictions}/{report.SampleLength}. Presicion: {report.CorrectPredictions / (double)report.SampleLength}");
System.Console.ReadLine();
}
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);
}
