/// <summary>
/// Initializes a new instance of <see cref="SdcaRegressionTrainer"/>
/// </summary>
/// <param name="env">The environment to use.</param>
/// <param name="labelColumn">The label, or dependent variable.</param>
/// <param name="featureColumn">The features, or independent variables.</param>
/// <param name="weights">The optional example weights.</param>
/// <param name="loss">The custom loss.</param>
/// <param name="l2Const">The L2 regularization hyperparameter.</param>
/// <param name="l1Threshold">The L1 regularization hyperparameter. Higher values will tend to lead to more sparse model.</param>
/// <param name="maxIterations">The maximum number of passes to perform over the data.</param>
internal SdcaRegressionTrainer(IHostEnvironment env,
string labelColumn = DefaultColumnNames.Label,
string featureColumn = DefaultColumnNames.Features,
string weights = null,
ISupportSdcaRegressionLoss loss = null,
float?l2Const = null,
float?l1Threshold = null,
int?maxIterations = null)
: base(env, featureColumn, TrainerUtils.MakeR4ScalarColumn(labelColumn), TrainerUtils.MakeR4ScalarWeightColumn(weights),
l2Const, l1Threshold, maxIterations)
{
Host.CheckNonEmpty(featureColumn, nameof(featureColumn));
Host.CheckNonEmpty(labelColumn, nameof(labelColumn));
_loss = loss ?? SdcaTrainerOptions.LossFunction.CreateComponent(env);
Loss = _loss;
}
/// <summary>
/// Initializes a new instance of <see cref="SdcaRegressionTrainer"/>
/// </summary>
/// <param name="env">The environment to use.</param>
/// <param name="featureColumn">The features, or independent variables.</param>
/// <param name="labelColumn">The label, or dependent variable.</param>
/// <param name="loss">The custom loss.</param>
/// <param name="weightColumn">The optional example weights.</param>
/// <param name="l2Const">The L2 regularization hyperparameter.</param>
/// <param name="l1Threshold">The L1 regularization hyperparameter. Higher values will tend to lead to more sparse model.</param>
/// <param name="maxIterations">The maximum number of passes to perform over the data.</param>
/// <param name="advancedSettings">A delegate to set more settings.
/// The settings here will override the ones provided in the direct method signature,
/// if both are present and have different values.
/// The columns names, however need to be provided directly, not through the <paramref name="advancedSettings"/>.</param>
public SdcaRegressionTrainer(IHostEnvironment env,
string featureColumn,
string labelColumn,
string weightColumn = null,
ISupportSdcaRegressionLoss loss = null,
float?l2Const = null,
float?l1Threshold = null,
int?maxIterations = null,
Action <Arguments> advancedSettings = null)
: base(env, featureColumn, TrainerUtils.MakeR4ScalarLabel(labelColumn), TrainerUtils.MakeR4ScalarWeightColumn(weightColumn), advancedSettings,
l2Const, l1Threshold, maxIterations)
{
Host.CheckNonEmpty(featureColumn, nameof(featureColumn));
Host.CheckNonEmpty(labelColumn, nameof(labelColumn));
_loss = loss ?? Args.LossFunction.CreateComponent(env);
Loss = _loss;
}
/// <summary>
/// Predict a target using a linear regression model trained with the SDCA trainer.
/// </summary>
/// <param name="ctx">The regression context 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="l2Const">The L2 regularization hyperparameter.</param>
/// <param name="l1Threshold">The L1 regularization hyperparameter. Higher values will tend to lead to more sparse model.</param>
/// <param name="maxIterations">The maximum number of passes to perform over the data.</param>
/// <param name="loss">The custom loss, if unspecified will be <see cref="SquaredLossSDCARegressionLossFunction"/>.</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> Sdca(this RegressionContext.RegressionTrainers ctx,
Scalar <float> label, Vector <float> features, Scalar <float> weights = null,
float?l2Const = null,
float?l1Threshold = null,
int?maxIterations = null,
ISupportSdcaRegressionLoss loss = null,
Action <LinearRegressionPredictor> onFit = null)
{
Contracts.CheckValue(label, nameof(label));
Contracts.CheckValue(features, nameof(features));
Contracts.CheckValueOrNull(weights);
Contracts.CheckParam(!(l2Const < 0), nameof(l2Const), "Must not be negative, if specified.");
Contracts.CheckParam(!(l1Threshold < 0), nameof(l1Threshold), "Must not be negative, if specified.");
Contracts.CheckParam(!(maxIterations < 1), nameof(maxIterations), "Must be positive if specified");
Contracts.CheckValueOrNull(loss);
Contracts.CheckValueOrNull(onFit);
var args = new SdcaRegressionTrainer.Arguments()
{
L2Const = l2Const,
L1Threshold = l1Threshold,
MaxIterations = maxIterations
};
if (loss != null)
{
args.LossFunction = new TrivialRegressionLossFactory(loss);
}
var rec = new TrainerEstimatorReconciler.Regression(
(env, labelName, featuresName, weightsName) =>
{
var trainer = new SdcaRegressionTrainer(env, args, featuresName, labelName, weightsName);
if (onFit != null)
{
return(trainer.WithOnFitDelegate(trans => onFit(trans.Model)));
}
return(trainer);
}, label, features, weights);
return(rec.Score);
}
public TrivialRegressionLossFactory(ISupportSdcaRegressionLoss loss)
{
_loss = loss;
}
