/// <summary>
/// Predict a target using logistic regression trained with the <see cref="SgdBinaryTrainer"/> trainer.
/// </summary>
/// <param name="catalog">The binary classification catalog trainer object.</param>
/// <param name="label">The name of the label column.</param>
/// <param name="features">The name of the feature column.</param>
/// <param name="weights">The name for the example weight column.</param>
/// <param name="options">Advanced arguments to the algorithm.</param>
/// <param name="onFit">A delegate that is called every time the
/// <see cref="Estimator{TTupleInShape, TTupleOutShape, TTransformer}.Fit(DataView{TTupleInShape})"/> method is called on the
/// <see cref="Estimator{TTupleInShape, TTupleOutShape, TTransformer}"/> instance created out of this. This delegate will receive
/// the linear model that was trained. Note that this action cannot change the result in any way; it is only a way for the caller to
/// be informed about what was learnt.</param>
/// <returns>The predicted output.</returns>
public static (Scalar <float> score, Scalar <float> probability, Scalar <bool> predictedLabel) StochasticGradientDescentClassificationTrainer(
this BinaryClassificationCatalog.BinaryClassificationTrainers catalog,
Scalar <bool> label,
Vector <float> features,
Scalar <float> weights,
SgdBinaryTrainer.Options options,
Action <CalibratedModelParametersBase <LinearBinaryModelParameters, PlattCalibrator> > onFit = null)
{
var rec = new TrainerEstimatorReconciler.BinaryClassifier(
(env, labelName, featuresName, weightsName) =>
{
options.FeatureColumnName = featuresName;
options.LabelColumnName = labelName;
options.ExampleWeightColumnName = weightsName;
var trainer = new SgdBinaryTrainer(env, options);
if (onFit != null)
{
return(trainer.WithOnFitDelegate(trans => onFit(trans.Model)));
}
return(trainer);
}, label, features, weights);
return(rec.Output);
}
/// <summary>
/// Predict a target using logistic regression trained with the <see cref="SgdBinaryTrainer"/> trainer.
/// </summary>
/// <param name="catalog">The binary classificaiton catalog trainer object.</param>
/// <param name="options">Advanced arguments to the algorithm.</param>
public static SgdBinaryTrainer StochasticGradientDescent(this BinaryClassificationCatalog.BinaryClassificationTrainers catalog,
SgdBinaryTrainer.Options options)
{
Contracts.CheckValue(catalog, nameof(catalog));
Contracts.CheckValue(options, nameof(options));
var env = CatalogUtils.GetEnvironment(catalog);
return(new SgdBinaryTrainer(env, options));
}
// In this examples we will use the adult income dataset. The goal is to predict
// if a person's income is above $50K or not, based on demographic information about that person.
// For more details about this dataset, please see https://archive.ics.uci.edu/ml/datasets/adult.
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);
// Download and featurize the dataset.
var data = SamplesUtils.DatasetUtils.LoadFeaturizedAdultDataset(mlContext);
// Leave out 10% of data for testing.
var trainTestData = mlContext.BinaryClassification.TrainTestSplit(data, testFraction: 0.1);
// Define the trainer options.
var options = new SgdBinaryTrainer.Options()
{
// Make the convergence tolerance tighter.
ConvergenceTolerance = 5e-5,
// Increase the maximum number of passes over training data.
NumberOfIterations = 30,
// Give the instances of the positive class slightly more weight.
PositiveInstanceWeight = 1.2f,
};
// Create data training pipeline.
var pipeline = mlContext.BinaryClassification.Trainers.StochasticGradientDescent(options);
// Fit this pipeline to the training data.
var model = pipeline.Fit(trainTestData.TrainSet);
// Evaluate how the model is doing on the test data.
var dataWithPredictions = model.Transform(trainTestData.TestSet);
var metrics = mlContext.BinaryClassification.Evaluate(dataWithPredictions);
SamplesUtils.ConsoleUtils.PrintMetrics(metrics);
// Expected output:
// Accuracy: 0.85
// AUC: 0.90
// F1 Score: 0.67
// Negative Precision: 0.91
// Negative Recall: 0.89
// Positive Precision: 0.65
// Positive Recall: 0.70
// LogLoss: 0.48
// LogLossReduction: 37.52
// Entropy: 0.78
}
