AsymmetricGaussianBasis

class pymc_marketing.mmm.events.AsymmetricGaussianBasis(event_in='after', **kwargs)

Asymmetric Gaussian bump basis transformation.

Allows different widths (sigma_before, sigma_after) and amplitudes (a_after) after the event.

(Source code, png, hires.png, pdf)

Parameters:

event_inLiteral[“before”, “after”, “exclude”]

Whether to include the event in the before or after part of the basis, or leave it out entirely. Default is “after”.

priorsdict[str, Prior]

Prior for the sigma_before, sigma_after, a_before, and a_after parameters.

prefixstr

Prefix for the parameters.

Methods

AsymmetricGaussianBasis.__init__([event_in])
AsymmetricGaussianBasis.apply(x, *[, ...])	Call within a model context.
AsymmetricGaussianBasis.from_dict(data)	Reconstruct a basis from a dict.
AsymmetricGaussianBasis.function(x, ...[, dim])	Asymmetric Gaussian bump function.
AsymmetricGaussianBasis.plot_curve(curve[, ...])	Plot curve HDI and samples.
AsymmetricGaussianBasis.plot_curve_hdi(curve)	Plot the HDI of the curve.
AsymmetricGaussianBasis.plot_curve_samples(curve)	Plot samples from the curve.
AsymmetricGaussianBasis.sample_curve([...])	Sample the curve of the saturation transformation given parameters.
AsymmetricGaussianBasis.sample_prior([coords])	Sample the priors for the transformation.
AsymmetricGaussianBasis.set_dims_for_all_priors(dims)	Set the dims for all priors.
AsymmetricGaussianBasis.to_dict([_orig])	Convert the transformation to a dictionary.
AsymmetricGaussianBasis.update_priors(priors)	Update the priors for a function after initialization.
AsymmetricGaussianBasis.with_default_prior_dims(dims)	Return a copy with default prior dims (dims=None) set to dims instead.
AsymmetricGaussianBasis.with_updated_priors(priors)	Return a copy with updated priors.

Attributes

AsymmetricGaussianBasis.combined_dims	Get the combined dims for all the parameters.
AsymmetricGaussianBasis.default_priors
AsymmetricGaussianBasis.function_priors	Get the priors for the function.
AsymmetricGaussianBasis.model_config	Mapping from variable name to prior for the model.
AsymmetricGaussianBasis.prefix
AsymmetricGaussianBasis.priors	Get the priors for the function.
AsymmetricGaussianBasis.variable_mapping	Mapping from parameter name to variable name in the model.