SdcaNonCalibrated(
this SweepableBinaryClassificationTrainers trainer,
string labelColumnName = "Label",
string featureColumnName = "Features",
SweepableOption <SdcaNonCalibratedBinaryTrainer.Options> optionBuilder = null,
SdcaNonCalibratedBinaryTrainer.Options defaultOption = null)
{
var context = trainer.Context;
if (optionBuilder == null)
{
optionBuilder = SdcaNonCalibratedBinaryTrainerSweepableOptions.Default;
}
optionBuilder.SetDefaultOption(defaultOption);
return(context.AutoML().CreateSweepableEstimator(
(context, option) =>
{
option.LabelColumnName = labelColumnName;
option.FeatureColumnName = featureColumnName;
return context.BinaryClassification.Trainers.SdcaNonCalibrated(option);
},
optionBuilder,
new string[] { labelColumnName, featureColumnName },
new string[] { PredictedLabel },
nameof(SdcaNonCalibratedBinaryTrainer)));
}
/// <summary>
/// Predict a target using a linear binary classification model trained with the SDCA trainer, and a custom loss.
/// Note that because we cannot be sure that all loss functions will produce naturally calibrated outputs, setting
/// a custom loss function will not produce a calibrated probability column.
/// </summary>
/// <param name="catalog">The binary classification catalog trainer object.</param>
/// <param name="label">The label, or dependent variable.</param>
/// <param name="features">The features, or independent variables.</param>
/// <param name="lossFunction">The custom loss.</param>
/// <param name="weights">The optional example weights.</param>
/// <param name="options">Advanced arguments to the algorithm.</param>
/// <param name="onFit">A delegate that is called every time the
/// <see cref="Estimator{TInShape, TOutShape, TTransformer}.Fit(DataView{TInShape})"/> method is called on the
/// <see cref="Estimator{TInShape, TOutShape, TTransformer}"/> instance created out of this. This delegate will receive
/// the linear model that was trained, as well as the calibrator on top of that model. 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 set of output columns including in order the predicted binary classification score (which will range
/// from negative to positive infinity), and the predicted label.</returns>
public static (Scalar <float> score, Scalar <bool> predictedLabel) SdcaNonCalibrated(
this BinaryClassificationCatalog.BinaryClassificationTrainers catalog,
Scalar <bool> label, Vector <float> features, Scalar <float> weights,
ISupportSdcaClassificationLoss lossFunction,
SdcaNonCalibratedBinaryTrainer.Options options,
Action <LinearBinaryModelParameters> onFit = null)
{
Contracts.CheckValue(label, nameof(label));
Contracts.CheckValue(features, nameof(features));
Contracts.CheckValueOrNull(weights);
Contracts.CheckValueOrNull(options);
Contracts.CheckValueOrNull(onFit);
var rec = new TrainerEstimatorReconciler.BinaryClassifierNoCalibration(
(env, labelName, featuresName, weightsName) =>
{
options.FeatureColumnName = featuresName;
options.LabelColumnName = labelName;
var trainer = new SdcaNonCalibratedBinaryTrainer(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 a linear binary classification model trained with the SDCA trainer.
/// </summary>
/// <param name="catalog">The binary classification catalog trainer object.</param>
/// <param name="options">Advanced arguments to the algorithm.</param>
public static SdcaNonCalibratedBinaryTrainer StochasticDualCoordinateAscentNonCalibrated(
this BinaryClassificationCatalog.BinaryClassificationTrainers catalog,
SdcaNonCalibratedBinaryTrainer.Options options)
{
Contracts.CheckValue(catalog, nameof(catalog));
Contracts.CheckValue(options, nameof(options));
var env = CatalogUtils.GetEnvironment(catalog);
return(new SdcaNonCalibratedBinaryTrainer(env, options));
}
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);
// ML.NET doesn't cache data set by default. Therefore, if one reads a data set from a file and accesses it many times,
// it can be slow due to expensive featurization and disk operations. When the considered data can fit into memory,
// a solution is to cache the data in memory. Caching is especially helpful when working with iterative algorithms
// which needs many data passes.
trainingData = mlContext.Data.Cache(trainingData);
// Define trainer options.
var options = new SdcaNonCalibratedBinaryTrainer.Options()
{
// Specify loss function.
LossFunction = new HingeLoss(),
// Make the convergence tolerance tighter.
ConvergenceTolerance = 0.05f,
// Increase the maximum number of passes over training data.
MaximumNumberOfIterations = 30,
// Give the instances of the positive class slightly more weight.
PositiveInstanceWeight = 1.2f,
};
// Define the trainer.
var pipeline = mlContext.BinaryClassification.Trainers.SdcaNonCalibrated(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: True
// Evaluate the overall metrics.
var metrics = mlContext.BinaryClassification.EvaluateNonCalibrated(transformedTestData);
PrintMetrics(metrics);
// Expected output:
// Accuracy: 0.61
// AUC: 0.67
// F1 Score: 0.65
// Negative Precision: 0.69
// Negative Recall: 0.45
// Positive Precision: 0.56
// Positive Recall: 0.77
//
// TEST POSITIVE RATIO: 0.4760 (238.0/(238.0+262.0))
// Confusion table
// ||======================
// PREDICTED || positive | negative | Recall
// TRUTH ||======================
// positive || 178 | 60 | 0.7479
// negative || 134 | 128 | 0.4885
// ||======================
// Precision || 0.5705 | 0.6809 |
}
