/// <summary>
/// Create an<see cref= "SymbolicSgdLogisticRegressionBinaryTrainer" />, which predicts a target using a linear binary classification model trained over boolean label data.
/// Stochastic gradient descent (SGD) is an iterative algorithm that optimizes a differentiable objective function.
/// The <see cref="SymbolicSgdLogisticRegressionBinaryTrainer"/> parallelizes SGD using <a href="https://www.microsoft.com/en-us/research/project/project-parade/#!symbolic-execution">symbolic execution</a>.
/// </summary>
/// <param name="catalog">The <see cref="BinaryClassificationCatalog"/>.</param>
/// <param name="options">Algorithm advanced options. See <see cref="SymbolicSgdLogisticRegressionBinaryTrainer.Options"/>.</param>
/// <example>
/// <format type="text/markdown">
/// <]
/// ]]>
/// </format>
/// </example>
public static SymbolicSgdLogisticRegressionBinaryTrainer SymbolicSgdLogisticRegression(
this BinaryClassificationCatalog.BinaryClassificationTrainers catalog,
SymbolicSgdLogisticRegressionBinaryTrainer.Options options)
{
Contracts.CheckValue(catalog, nameof(catalog));
Contracts.CheckValue(options, nameof(options));
var env = CatalogUtils.GetEnvironment(catalog);
return new SymbolicSgdLogisticRegressionBinaryTrainer(env, options);
}
/// <summary>
/// Create an <see cref="SymbolicSgdLogisticRegressionBinaryTrainer"/> with advanced options, which predicts a target using a linear binary classification model trained over boolean label data.
/// Stochastic gradient descent (SGD) is an iterative algorithm that optimizes a differentiable objective function.
/// The <see cref="SymbolicSgdLogisticRegressionBinaryTrainer"/> parallelizes SGD using <a href="https://www.microsoft.com/en-us/research/project/project-parade/#!symbolic-execution">symbolic execution</a>.
/// </summary>
/// <param name="catalog">The <see cref="BinaryClassificationCatalog"/>.</param>
/// <param name="labelColumnName">The name of the label column. The column data must be <see cref="System.Boolean"/>.</param>
/// <param name="featureColumnName">The name of the feature column. The column data must be a known-sized vector of <see cref="System.Single"/>.</param>
/// <param name="numberOfIterations">Number of training iterations.</param>
/// <example>
/// <format type="text/markdown">
/// <]
/// ]]>
/// </format>
/// </example>
public static SymbolicSgdLogisticRegressionBinaryTrainer SymbolicSgdLogisticRegression(this BinaryClassificationCatalog.BinaryClassificationTrainers catalog,
string labelColumnName = DefaultColumnNames.Label,
string featureColumnName = DefaultColumnNames.Features,
int numberOfIterations = SymbolicSgdLogisticRegressionBinaryTrainer.Defaults.NumberOfIterations)
{
Contracts.CheckValue(catalog, nameof(catalog));
var env = CatalogUtils.GetEnvironment(catalog);
var options = new SymbolicSgdLogisticRegressionBinaryTrainer.Options
{
LabelColumnName = labelColumnName,
FeatureColumnName = featureColumnName,
};
return(new SymbolicSgdLogisticRegressionBinaryTrainer(env, options));
}
// This example requires installation of additional NuGet package
// <a href="https://www.nuget.org/packages/Microsoft.ML.Mkl.Components/">Microsoft.ML.Mkl.Components</a>.
public static void Example()
{
// Create a new context for ML.NET operations. It can be used for exception tracking and logging,
// as a catalog of available operations and as the source of randomness.
// Setting the seed to a fixed number in this example to make outputs deterministic.
var mlContext = new MLContext(seed: 0);
// Create a list of training data points.
var dataPoints = GenerateRandomDataPoints(1000);
// Convert the list of data points to an IDataView object, which is consumable by ML.NET API.
var trainingData = mlContext.Data.LoadFromEnumerable(dataPoints);
// Define trainer options.
var options = new SymbolicSgdLogisticRegressionBinaryTrainer.Options()
{
LearningRate = 0.2f,
NumberOfIterations = 10,
NumberOfThreads = 1,
};
// Define the trainer.
var pipeline = mlContext.BinaryClassification.Trainers.SymbolicSgdLogisticRegression(options);
// Train the model.
var model = pipeline.Fit(trainingData);
// Create testing data. Use different random seed to make it different from training data.
var testData = mlContext.Data.LoadFromEnumerable(GenerateRandomDataPoints(500, seed: 123));
// Run the model on test data set.
var transformedTestData = model.Transform(testData);
// Convert IDataView object to a list.
var predictions = mlContext.Data.CreateEnumerable <Prediction>(transformedTestData, reuseRowObject: false).ToList();
// Print 5 predictions.
foreach (var p in predictions.Take(5))
{
Console.WriteLine($"Label: {p.Label}, Prediction: {p.PredictedLabel}");
}
// Expected output:
// Label: True, Prediction: False
// Label: False, Prediction: False
// Label: True, Prediction: True
// Label: True, Prediction: True
// Label: False, Prediction: False
// Evaluate the overall metrics.
var metrics = mlContext.BinaryClassification.Evaluate(transformedTestData);
PrintMetrics(metrics);
// Expected output:
// Accuracy: 0.72
// AUC: 0.81
// F1 Score: 0.66
// Negative Precision: 0.68
// Negative Recall: 0.87
// Positive Precision: 0.80
// Positive Recall: 0.56
}
