private static ITransformer BuildTrainEvaluateAndSaveModel(MLContext mlContext)
{
// STEP 1: Load data
IDataView trainingDataView = mlContext.Data.LoadFromTextFile <SentimentIssue>(TrainDataPath, hasHeader: true);
IDataView testDataView = mlContext.Data.LoadFromTextFile <SentimentIssue>(TestDataPath, hasHeader: true);
// STEP 2: Display first few rows of training data
ConsoleHelper.ShowDataViewInConsole(mlContext, trainingDataView);
// STEP 3: Initialize our user-defined progress handler that AutoML will
// invoke after each model it produces and evaluates.
var progressHandler = new BinaryExperimentProgressHandler();
// STEP 4: Run AutoML binary classification experiment
ConsoleHelper.ConsoleWriteHeader("=============== Running AutoML experiment ===============");
Console.WriteLine($"Running AutoML binary classification experiment for {ExperimentTime} seconds...");
ExperimentResult <BinaryClassificationMetrics> experimentResult = mlContext.Auto()
.CreateBinaryClassificationExperiment(ExperimentTime)
.Execute(trainingDataView, progressHandler: progressHandler);
// Print top models found by AutoML
Console.WriteLine();
PrintTopModels(experimentResult);
// STEP 5: Evaluate the model and print metrics
ConsoleHelper.ConsoleWriteHeader("=============== Evaluating model's accuracy with test data ===============");
RunDetail <BinaryClassificationMetrics> bestRun = experimentResult.BestRun;
ITransformer trainedModel = bestRun.Model;
var predictions = trainedModel.Transform(testDataView);
var metrics = mlContext.BinaryClassification.EvaluateNonCalibrated(data: predictions, scoreColumnName: "Score");
ConsoleHelper.PrintBinaryClassificationMetrics(bestRun.TrainerName, metrics);
// STEP 6: Save/persist the trained model to a .ZIP file
mlContext.Model.Save(trainedModel, trainingDataView.Schema, ModelPath);
Console.WriteLine("The model is saved to {0}", ModelPath);
return(trainedModel);
}
private static ExperimentResult <BinaryClassificationMetrics> RunAutoMLExperiment(MLContext mlContext,
ColumnInferenceResults columnInference)
{
// STEP 1: Display first few rows of the training data.
// ConsoleHelper.ShowDataViewInConsole(mlContext, TrainDataView);
// STEP 2: Build a pre-featurizer for use in the AutoML experiment.
// (Internally, AutoML uses one or more train/validation data splits to
// evaluate the models it produces. The pre-featurizer is fit only on the
// training data split to produce a trained transform. Then, the trained transform
// is applied to both the train and validation data splits.)
//IEstimator<ITransformer> preFeaturizer = mlContext.Transforms.Conversion.MapValue("is_cash",
// new[] { new KeyValuePair<string, bool>("CSH", true) }, "payment_type");
//IEstimator<ITransformer> preFeaturizer = mlContext.Transforms.Conversion.MapValue("fstrClassCategory",
// new[] { new KeyValuePair<float, String>(1, "First"), new KeyValuePair<float, String>(2, "Second"), new KeyValuePair<float, String>(3, "Third") }, "fstrClass").Append(mlContext.Transforms.Categorical.OneHotEncoding("fstrClassCategory", "fstrClassCategory")).Append(mlContext.Transforms.DropColumns("fstrClass"));
// STEP 3: Customize column information returned by InferColumns API.
ColumnInformation columnInformation = columnInference.ColumnInformation;
columnInformation = CorrectColumnTypes(columnInformation);
// columnInformation.NumericColumnNames.Remove("fstrClass");
// columnInformation.CategoricalColumnNames.Add("fstrClass");
// columnInformation.IgnoredColumnNames.Add("fstrClass");
// columnInformation.IgnoredColumnNames.
// STEP 4: Initialize a cancellation token source to stop the experiment.
var cts = new CancellationTokenSource();
// STEP 5: Initialize our user-defined progress handler that AutoML will
// invoke after each model it produces and evaluates.
var progressHandler = new BinaryExperimentProgressHandler(); // RegressionExperimentProgressHandler();
// STEP 6: Create experiment settings
var experimentSettings = CreateExperimentSettings(mlContext, cts);
// STEP 7: Run AutoML Binary Classification experiment.
var experiment = mlContext.Auto().CreateBinaryClassificationExperiment(experimentSettings);
ConsoleHelper.ConsoleWriteHeader("=============== Running AutoML experiment ===============");
Console.WriteLine($"Running AutoML regression experiment...");
var stopwatch = Stopwatch.StartNew();
// Cancel experiment after the user presses any key.
CancelExperimentAfterAnyKeyPress(cts);
ExperimentResult <BinaryClassificationMetrics> experimentResult = experiment.Execute(trainData: TrainDataView, columnInformation: columnInformation, progressHandler: progressHandler);
Console.WriteLine($"{experimentResult.RunDetails.Count()} models were returned after {stopwatch.Elapsed.TotalSeconds:0.00} seconds{Environment.NewLine}");
// Print top models found by AutoML.
PrintTopModels(experimentResult);
// var featureNames = columnInformation.CategoricalColumnNames.Concat(columnInformation.ImagePathColumnNames).Concat(columnInformation.NumericColumnNames).Concat(columnInformation.TextColumnNames).ToList();
// var permutationMetrics = mlContext.BinaryClassification.PermutationFeatureImportance(predictionTransformer: )
// PrintContributions(featureNames, TrainDataView, experimentResult.RunDetails);
// DatasetDimensionsUtil.GetTextColumnCardinality();
return(experimentResult);
}
private static ITransformer BuildTrainEvaluateAndSaveModel(MLContext mlContext)
{
// STEP 1: Common data loading configuration
string connectionString = @"Data Source=(LocalDB)\MSSQLLocalDB;Database=Northwind;Integrated Security=True;Connect Timeout=30";
string sqlCommand = @"SELECT OrderID,
CAST([ProductID] as varchar) as ProductID,
CAST([UnitPrice] as REAL) as UnitPrice,
CAST([Quantity] as REAL) as Quantity,
CAST([Discount] as varchar) as Discount
FROM [dbo].[Order Details]";
DatabaseSource dbSource = new DatabaseSource(SqlClientFactory.Instance, connectionString, sqlCommand);
DatabaseLoader loader = mlContext.Data.CreateDatabaseLoader <OrderDetails>();
IDataView dataview = loader.Load(dbSource);
//IDataView dataview = mlContext.Data.LoadFromTextFile<OrderDetails>(DataPath, hasHeader: true, separatorChar: ',');
var pipeline = mlContext.Transforms.Conversion.MapValue("PayFullPrice",
new[] { new KeyValuePair <string, bool>("0", true) }, "Discount")
.Append(mlContext.Transforms.DropColumns("Discount"));
var transformedDataView = pipeline.Fit(dataview).Transform(dataview);
using (var stream = File.Create("transformedData.tsv"))
{
mlContext.Data.SaveAsText(transformedDataView, stream);
}
ConsoleHelper.ShowDataViewInConsole(mlContext, transformedDataView);
//// STEP 2: Initialize our user-defined progress handler that AutoML will
// invoke after each model it produces and evaluates.
var progressHandler = new BinaryExperimentProgressHandler();
//// STEP 3: Run AutoML regression experiment
ConsoleHelper.ConsoleWriteHeader("=============== Training the model ===============");
Console.WriteLine($"Running AutoML regression experiment for {ExperimentTime} seconds...");
ExperimentResult <BinaryClassificationMetrics> experimentResult = mlContext.Auto()
.CreateBinaryClassificationExperiment(ExperimentTime)
.Execute(transformedDataView, LabelColumnName, progressHandler: progressHandler);
// Print top models found by AutoML
Console.WriteLine();
PrintTopModels(experimentResult);
//// STEP 4: Evaluate the model and print metrics
ConsoleHelper.ConsoleWriteHeader("===== Evaluating model's accuracy with test data =====");
RunDetail <BinaryClassificationMetrics> best = experimentResult.BestRun;
ITransformer trainedModel = best.Model;
//// STEP 5: Save/persist the trained model - convonnx
using (var stream = File.Create(MODEL_NAME))
{
mlContext.Model.ConvertToOnnx(trainedModel, dataview, stream);
}
Console.WriteLine("The model is saved to {0}", MODEL_NAME);
return(trainedModel);
}
