mlrl.common.cython.probability_calibration module

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

class mlrl.common.cython.probability_calibration.IsotonicJointProbabilityCalibrationModel

Bases: JointProbabilityCalibrationModel, IsotonicProbabilityCalibrationModel

A model for the calibration of joint probabilities via isotonic regression.

visit(visitor: IsotonicProbabilityCalibrationModelVisitor)

Invokes a given visitor for each bin that is stored by the calibration model.

Parameters:

visitor – The visitor to be invoked

class mlrl.common.cython.probability_calibration.IsotonicMarginalProbabilityCalibrationModel

Bases: MarginalProbabilityCalibrationModel, IsotonicProbabilityCalibrationModel

A model for the calibration of marginal probabilities via isotonic regression.

visit(visitor: IsotonicProbabilityCalibrationModelVisitor)

Invokes a given visitor for each bin that is stored by the calibration model.

Parameters:

visitor – The visitor to be invoked

class mlrl.common.cython.probability_calibration.IsotonicProbabilityCalibrationModel

Bases: ABC

Defines an interface for all models for the calibration of probabilities via isotonic regression.

abstract visit(visitor: IsotonicProbabilityCalibrationModelVisitor)

Invokes a given visitor for each bin that is stored by the calibration model.

Parameters:

visitor – The visitor to be invoked

class mlrl.common.cython.probability_calibration.IsotonicProbabilityCalibrationModelVisitor

Bases: ABC

Defines an interface for all visitors that allow to handle the bins stores by a model for the calibration of probabilities via isotonic regression.

abstract visit_bin(list_index: int, threshold: float, probability: float)

Must be implemented by subclasses in order to handle a bin.

Parameters:

• list_index – The index of the list, the bin corresponds to

• threshold – The threshold of the bin

• probability – The probability of the bin

class mlrl.common.cython.probability_calibration.JointProbabilityCalibrationModel

Bases: object

A model that may be used for the calibration of joint probabilities.

class mlrl.common.cython.probability_calibration.MarginalProbabilityCalibrationModel

Bases: object

A model that may be used for the calibration of marginal probabilities.

class mlrl.common.cython.probability_calibration.NoJointProbabilityCalibrationModel

Bases: JointProbabilityCalibrationModel, NoProbabilityCalibrationModel

A model for the calibration of joint probabilities that does not make any adjustments.

class mlrl.common.cython.probability_calibration.NoMarginalProbabilityCalibrationModel

Bases: MarginalProbabilityCalibrationModel, NoProbabilityCalibrationModel

A model for the calibration of marginal probabilities that does not make any adjustments.

class mlrl.common.cython.probability_calibration.NoProbabilityCalibrationModel

Bases: ABC

Defines an inteface for all models for the calibration of probabilities that do not make any adjustments.