Skip to content

Averaging

Abstract Base Class#

Averaging #

The abstract base class for metric averaging.

Properties should be implemented as class attributes in derived metrics.

The compute_average method needs to be implemented

Attributes#

dependencies abstractmethod instance-attribute property #
sklearn_equivalent abstractmethod instance-attribute property #
aliases abstractmethod instance-attribute property #

Functions#

compute_average abstractmethod #

Metric Instances#

MacroAverage #

Bases: Averaging

Computes the arithmetic mean over all classes, also known as macro-averaging.

aliases = ['macro', 'macro_average', 'mean'] #

dependencies = () #

sklearn_equivalent = 'macro' #

WeightedAverage #

Bases: Averaging

Computes the class prevalence weighted mean over all classes, also known as weighted averaging.

aliases = ['weighted', 'weighted_average', 'micro', 'micro_average'] #

dependencies = ('p_condition',) #

sklearn_equivalent = 'weighted' #

SelectPositiveClass #

Bases: Averaging

Selects only the positive class, also known as binary averaging.

aliases = ['select_positive', 'binary', 'select'] #

dependencies = () #

sklearn_equivalent = 'binary' #

HarmonicMean #

Bases: Averaging

Computes the harmonic mean over all classes.

aliases = ['harmonic', 'harm'] #

dependencies = () #

sklearn_equivalent = None #

GeometricMean #

Bases: Averaging

Computes the geometric mean over all classes.

aliases = ['geometric', 'geom'] #

dependencies = () #

sklearn_equivalent = None #