LinearRegression.initial_point

LinearRegression.initial_point(random_seed=None)

Computes the initial point of the model.

Parameters:

random_seedSeedSequenceSeed, default None

Seed(s) for generating initial point from the model. Passed into pymc.pytensorf.reseed_rngs()

Returns:

ipdict of {strarray_like}

Maps names of transformed variables to numeric initial values in the transformed space.

Parameters:

random_seed (None | int | Sequence[int] | ndarray | SeedSequence)

Return type:

dict[str, ndarray]