mlrl.boosting.config module

Author: Michael Rapp (michael.rapp.ml@gmail.com)

Provides utility function for configuring boosting algorithms.

class mlrl.boosting.config.BinaryPredictorParameter

Bases: NominalParameter

A parameter that allows to configure the strategy to be used for predicting binary labels.

BINARY_PREDICTOR_EXAMPLE_WISE = 'example-wise'

BINARY_PREDICTOR_GFM = 'gfm'

BINARY_PREDICTOR_LABEL_WISE = 'label-wise'

class mlrl.boosting.config.DefaultRuleParameter

Bases: NominalParameter

A parameter that allows to configure whether a default rule should be induced or not.

class mlrl.boosting.config.ExtendedFeatureBinningParameter

Bases: FeatureBinningParameter

Extends the FeatureBinningParameter by a value for automatic configuration.

class mlrl.boosting.config.ExtendedParallelRuleRefinementParameter

Bases: ParallelRuleRefinementParameter

Extends the ParallelRuleRefinementParameter by a value for automatic configuration.

class mlrl.boosting.config.ExtendedParallelStatisticUpdateParameter

Bases: ParallelStatisticUpdateParameter

Extends the ParallelStatisticUpdateParameter by a value for automatic configuration.

class mlrl.boosting.config.ExtendedPartitionSamplingParameter

Bases: PartitionSamplingParameter

Extends the PartitionSamplingParameter by a value for automatic configuration.

class mlrl.boosting.config.HeadTypeParameter

Bases: NominalParameter

A parameter that allows to configure the type of the rule heads that should be used.

HEAD_TYPE_COMPLETE = 'complete'

HEAD_TYPE_PARTIAL_DYNAMIC = 'partial-dynamic'

HEAD_TYPE_PARTIAL_FIXED = 'partial-fixed'

HEAD_TYPE_SINGLE = 'single-label'

OPTION_EXPONENT = 'exponent'

OPTION_LABEL_RATIO = 'label_ratio'

OPTION_MAX_LABELS = 'max_labels'

OPTION_MIN_LABELS = 'min_labels'

OPTION_THRESHOLD = 'threshold'

class mlrl.boosting.config.JointProbabilityCalibrationParameter

Bases: NominalParameter

A parameter that allows to configure the method to be used for the calibration of joint probabilities.

class mlrl.boosting.config.L1RegularizationParameter

Bases: FloatParameter

A parameter that allows to configure the weight of the L1 regularization.

class mlrl.boosting.config.L2RegularizationParameter

Bases: FloatParameter

A parameter that allows to configure the weight of the L2 regularization.

class mlrl.boosting.config.LabelBinningParameter

Bases: NominalParameter

A parameter that allows to configure the strategy to be used for gradient-based label binning (GBLB).

class mlrl.boosting.config.LossParameter

Bases: NominalParameter

A parameter that allows to configure the loss function to be minimized during training.

LOSS_LOGISTIC_EXAMPLE_WISE = 'logistic-example-wise'

LOSS_LOGISTIC_LABEL_WISE = 'logistic-label-wise'

LOSS_SQUARED_ERROR_EXAMPLE_WISE = 'squared-error-example-wise'

LOSS_SQUARED_ERROR_LABEL_WISE = 'squared-error-label-wise'

LOSS_SQUARED_HINGE_EXAMPLE_WISE = 'squared-hinge-example-wise'

LOSS_SQUARED_HINGE_LABEL_WISE = 'squared-hinge-label-wise'

class mlrl.boosting.config.MarginalProbabilityCalibrationParameter

Bases: NominalParameter

A parameter that allows to configure the method to be used for the calibration of marginal probabilities.

class mlrl.boosting.config.ProbabilityPredictorParameter

Bases: NominalParameter

A parameter that allows to configure the strategy to be used for predicting probabilities.

PROBABILITY_PREDICTOR_LABEL_WISE = 'label-wise'

PROBABILITY_PREDICTOR_MARGINALIZED = 'marginalized'

class mlrl.boosting.config.ShrinkageParameter

Bases: FloatParameter

A parameter that allows to configure the shrinkage parameter, a.k.a. the learning rate, to be used.

class mlrl.boosting.config.StatisticFormatParameter

Bases: NominalParameter

A parameter that allows to configure the format to be used for the representation of gradients and Hessians.

STATISTIC_FORMAT_DENSE = 'dense'

STATISTIC_FORMAT_SPARSE = 'sparse'