private static ITransformer BuildTrainEvaluateAndSaveModel(MLContext mlContext)
{
// STEP 1: Common data loading configuration
DataLoader dataLoader = new DataLoader(mlContext);
var trainingDataView = dataLoader.GetDataView(TrainDataPath);
var testDataView = dataLoader.GetDataView(TestDataPath);
// STEP 2: Common data process configuration with pipeline data transformations
var dataProcessor = new DataProcessor(mlContext);
var dataProcessPipeline = dataProcessor.DataProcessPipeline;
// (OPTIONAL) Peek data (such as 5 records) in training DataView after applying the ProcessPipeline's transformations into "Features"
Common.ConsoleHelper.PeekDataViewInConsole <TaxiTrip>(mlContext, trainingDataView, dataProcessPipeline, 5);
Common.ConsoleHelper.PeekVectorColumnDataInConsole(mlContext, "Features", trainingDataView, dataProcessPipeline, 5);
// STEP 3: Set the training algorithm, then create and config the modelBuilder
var modelBuilder = new Common.ModelBuilder <TaxiTrip, TaxiTripFarePrediction>(mlContext, dataProcessPipeline);
// We apply our selected Trainer (SDCA Regression algorithm)
var trainer = mlContext.Regression.Trainers.StochasticDualCoordinateAscent(label: "Label", features: "Features");
modelBuilder.AddTrainer(trainer);
// STEP 4: Train the model fitting to the DataSet
//The pipeline is trained on the dataset that has been loaded and transformed.
Console.WriteLine("=============== Training the model ===============");
modelBuilder.Train(trainingDataView);
// STEP 5: Evaluate the model and show accuracy stats
Console.WriteLine("===== Evaluating Model's accuracy with Test data =====");
var metrics = modelBuilder.EvaluateRegressionModel(testDataView, "Label", "Score");
Common.ConsoleHelper.PrintRegressionMetrics("StochasticDualCoordinateAscent", metrics);
// STEP 6: Save/persist the trained model to a .ZIP file
Console.WriteLine("=============== Saving the model to a file ===============");
modelBuilder.SaveModelAsFile(ModelPath);
return(modelBuilder.TrainedModel);
}
