/// <summary>
/// Predict a target using a linear regression model trained with the <see cref="Microsoft.ML.Trainers.LbfgsLogisticRegressionBinaryTrainer"/> trainer.
/// </summary>
/// <param name="catalog">The regression catalog trainer object.</param>
/// <param name="label">The label, or dependent variable.</param>
/// <param name="features">The features, or independent variables.</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. 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> LbfgsPoissonRegression(this RegressionCatalog.RegressionTrainers catalog,
Scalar <float> label,
Vector <float> features,
Scalar <float> weights,
LbfgsPoissonRegressionTrainer.Options options,
Action <PoissonRegressionModelParameters> onFit = null)
{
Contracts.CheckValue(label, nameof(label));
Contracts.CheckValue(features, nameof(features));
Contracts.CheckValue(options, nameof(options));
Contracts.CheckValueOrNull(onFit);
var rec = new TrainerEstimatorReconciler.Regression(
(env, labelName, featuresName, weightsName) =>
{
options.LabelColumnName = labelName;
options.FeatureColumnName = featuresName;
options.ExampleWeightColumnName = weightsName;
var trainer = new LbfgsPoissonRegressionTrainer(env, options);
if (onFit != null)
{
return(trainer.WithOnFitDelegate(trans => onFit(trans.Model)));
}
return(trainer);
}, label, features, weights);
return(rec.Score);
}
LbfgsPoissonRegression(
this SweepableRegressionTrainers trainers,
string labelColumnName = "Label",
string featureColumnName = "Features",
SweepableOption <LbfgsPoissonRegressionTrainer.Options> optionSweeper = null,
LbfgsPoissonRegressionTrainer.Options defaultOption = null)
{
var context = trainers.Context;
if (optionSweeper == null)
{
optionSweeper = LbfgsPoissonRegressionTrainerSweepableOptions.Default;
}
optionSweeper.SetDefaultOption(defaultOption);
return(context.AutoML().CreateSweepableEstimator(
(context, option) =>
{
option.LabelColumnName = labelColumnName;
option.FeatureColumnName = featureColumnName;
return context.Regression.Trainers.LbfgsPoissonRegression(option);
},
optionSweeper,
new string[] { labelColumnName, featureColumnName },
new string[] { Score },
nameof(LbfgsPoissonRegressionTrainer)));
}
public override IEstimator <ITransformer> BuildFromOption(MLContext context, LbfgsOption param)
{
var option = new LbfgsPoissonRegressionTrainer.Options()
{
L1Regularization = param.L1Regularization,
L2Regularization = param.L2Regularization,
LabelColumnName = param.LabelColumnName,
FeatureColumnName = param.FeatureColumnName,
ExampleWeightColumnName = param.ExampleWeightColumnName,
NumberOfThreads = AutoMlUtils.GetNumberOfThreadFromEnvrionment(),
};
return(context.Regression.Trainers.LbfgsPoissonRegression(option));
}
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 LbfgsPoissonRegressionTrainer.Options
{
LabelColumnName = nameof(DataPoint.Label),
FeatureColumnName = nameof(DataPoint.Features),
// Reduce optimization tolerance to speed up training at the cost of accuracy.
OptimizationTolerance = 1e-4f,
// Decrease history size to speed up training at the cost of accuracy.
HistorySize = 30,
// Specify scale for initial weights.
InitialWeightsDiameter = 0.2f
};
// Define the trainer.
var pipeline = mlContext.Regression.Trainers.LbfgsPoissonRegression(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(5, 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();
// Look at 5 predictions for the Label, side by side with the actual Label for comparison.
foreach (var p in predictions)
{
Console.WriteLine($"Label: {p.Label:F3}, Prediction: {p.Score:F3}");
}
// Expected output:
// Label: 0.985, Prediction: 1.110
// Label: 0.155, Prediction: 0.169
// Label: 0.515, Prediction: 0.400
// Label: 0.566, Prediction: 0.415
// Label: 0.096, Prediction: 0.169
// Evaluate the overall metrics
var metrics = mlContext.Regression.Evaluate(transformedTestData);
PrintMetrics(metrics);
// Expected output:
// Mean Absolute Error: 0.10
// Mean Squared Error: 0.01
// Root Mean Squared Error: 0.11
// RSquared: 0.89 (closer to 1 is better. The worest case is 0)
}
