Interfaces
This section lists the most important interfaces used in the package.
bmi.interface.IMutualInformationPointEstimator
Bases: Protocol
Interface for the mutual information estimator returning point estimates. All estimators should be implementations of this interface.
estimate(x, y)
abstractmethod
A point estimate of MI(X; Y) from an i.i.d. sample from the \(P(X, Y)\) distribution.
Parameters:
| Name | Type | Description | Default |
|---|---|---|---|
x |
ArrayLike
|
shape |
required |
y |
ArrayLike
|
shape |
required |
Returns:
| Type | Description |
|---|---|
float
|
mutual information estimate |
estimate_with_info(x, y)
Allows for reporting additional information about the run.
parameters()
abstractmethod
Returns the parameters of the estimator.
bmi.interface.ISampler
Bases: Protocol
Interface for a distribution \(P(X, Y)\).
dim_total: int
property
Dimension of the space in which the (X, Y) variable is valued.
Should be equal to the sum of dim_x and dim_y.
dim_x: int
abstractmethod
property
Dimension of the space in which the X variable is valued.
dim_y: int
abstractmethod
property
Dimension of the space in which the Y variable is valued.
mutual_information()
abstractmethod
Mutual information MI(X; Y).
sample(n_points, rng)
abstractmethod
Returns a sample from the joint distribution P(X, Y).
Parameters:
| Name | Type | Description | Default |
|---|---|---|---|
n_points |
int
|
sample size |
required |
rng |
Union[int, KeyArray]
|
pseudorandom number generator |
required |
Returns:
| Type | Description |
|---|---|
ndarray
|
X samples, shape (n_points, dim_x) |
ndarray
|
Y samples, shape (n_points, dim_y). Note that these samples are paired with X samples. |