API Reference¶

The unit_averaging package has two principal modules:

unit_averaging.averager that contains averaging strategies.
unit_averaging.focus_function that contains focus function classes.

For convenience, all public classes and functions from both modules are exposed at the package level, and you can import everything directly from the package without referencing individual modules:

from unit_averaging import OptimalUnitAverager

Averager classes:

Class	Description
BaseUnitAverager	Abstract base class. Subclass and implement `_compute_weights()` for custom strategies.
IndividualUnitAverager	Assigns all weight to the target unit (`weights = [0, ..., 1, ..., 0]`).
MeanGroupUnitAverager	Equal weights for all units (`weights = [1/N, ..., 1/N]`).
OptimalUnitAverager	MSE-optimal weights (agnostic and with prior restrictions).
SteinUnitAverager	MSE-optimal shrinkage towards mean group estimator.

Focus function classes:

Class	Description
BaseFocusFunction	Abstract base class. Subclass and implement `focus_function()` and `gradient()`.
InlineFocusFunction	Convenience class for creating focus functions from callables.
IdentityFocusFunction	Convenience class for creating an identity focus function for when the estimates are already the focus parameters.