Abstract Base Classes¶
Metric
¶
The abstract base class for metrics.
Properties should be implemented as class attributes in derived metrics
The compute_metric method needs to be implemented
Attributes¶
full_name
abstractmethod
instance-attribute
property
¶
A human-readable name for this metric.
is_multiclass
abstractmethod
instance-attribute
property
¶
Whether or not this metric computes a value for each class individually, or for all classes at once.
bounds
abstractmethod
instance-attribute
property
¶
A tuple of the minimum and maximum possible value for this metric to take.
Can be infinite.
dependencies
abstractmethod
instance-attribute
property
¶
All metrics upon which this metric depends.
Used to generate a computation schedule, such that no metric is calculated before its
dependencies. The dependencies must match the compute_metric signature.
This is checked during class definition.
sklearn_equivalent
abstractmethod
instance-attribute
property
¶
The sklearn equivalent function, if applicable.
aliases
abstractmethod
instance-attribute
property
¶
A list of all valid aliases for this metric.
Can be used when creating metric syntax strings.
name
property
¶
The name of this metric.
Will try to use the name used by the user.
Otherwise, takes the first element in the aliases list.
Functions¶
compute_metric
abstractmethod
¶
Computes the metric values from its dependencies.
__call__
¶
Computes the metric values from its dependencies.
AveragedMetric
¶
The composition of any instance of Metric with any instance of Averaging.
Parameters:
Attributes¶
aliases
property
¶
A list of all valid aliases for this metric.
Constructed from the product of the all aliases of the Metric and Averaging methods.
Can be used when creating metric syntax strings.
full_name
property
¶
The full, human-readable name for this composed metric.
is_multiclass
property
¶
Whether this metric computes a value for each class, or for all classes at once.
An AveragedMetric is always multiclass.
bounds
property
¶
A tuple of the minimum and maximum possible value for this metric to take.
Can be non-finite.
dependencies
property
¶
All metrics upon which this AveragedMetric depends.
Constructed from the union of all Metric and AveragingMethod dependencies.
Used to generate a computation schedule.
The dependencies must match the compute_metric signature.
This is checked during class definition.
sklearn_equivalent
property
¶
The sklearn equivalent function, if applicable.
name
property
¶
The name of this composed metric.
Combines the names of the base metric and averaging method instances.
Functions¶
compute_metric
¶
Computes the metric values from its dependencies.
compute_average
¶
Computes the average across experiment classes.
__call__
¶
Computes the metric and averages it, in succession.