GeometricAdstock.apply#

GeometricAdstock.apply(x, *, dims=None, core_dim=None, idx=None)[source]#

Call within a model context.

Used internally of the MMM to apply the transformation to the data.

Parameters:

xXTensorLike: The data to be transformed.
dimsstr, sequence[str], optional: The dims of the parameters. Defaults to None. Not the dims of the data!
core_dim: str: The dimension of X along which to apply the transformation.

Returns:

XTensorVariable: The transformed data.

Examples

Call the function for custom use-case

import pymc as pm

transformation = ...

coords = {
    "channel": ["TV", "Radio", "Digital"],
    "date": range(10),
}
with pm.Model(coords=coords):
    transformed_data = transformation.apply(
        data, dims="channel", core_dim="date"
    )