ControlEffect

class pymc_marketing.mmm.additive_effect.ControlEffect(**data)

Additive effect for control variables in the MMM.

Encapsulates the control column logic so that control variables are handled through the MuEffect protocol rather than as inline code inside build_model.

Parameters:

priorPrior, optional

The prior distribution for the gamma_control coefficients. If "control" is absent from the prior’s dims it is automatically added so each control column receives its own independent coefficient. Defaults to Normal(mu=0, sigma=2, dims="control").

date_dim_namestr, optional

The name of the date dimension in the model. Default is "date".

Examples

Standalone usage (the MMM wires this automatically when control_columns is provided, but you can also construct it explicitly):

from pymc_extras.prior import Prior
from pymc_marketing.mmm.additive_effect import ControlEffect

effect = ControlEffect(
    prior=Prior("Normal", mu=0, sigma=1, dims="control"),
)

Methods

ControlEffect.__init__(**data)	Create a new model by parsing and validating input data from keyword arguments.
ControlEffect.construct([_fields_set])
ControlEffect.copy(*[, include, exclude, ...])	Returns a copy of the model.
ControlEffect.create_data(mmm[, X])	Register control data in the PyMC model.
ControlEffect.create_effect(mmm)	Create the control contribution deterministic in the model.
ControlEffect.dict(*[, include, exclude, ...])
ControlEffect.from_dict(data)	Reconstruct from a dict.
ControlEffect.from_orm(obj)
ControlEffect.json(*[, include, exclude, ...])
ControlEffect.model_construct([_fields_set])	Creates a new instance of the Model class with validated data.
ControlEffect.model_copy(*[, update, deep])	!!! abstract "Usage Documentation"
ControlEffect.model_dump(*[, mode, include, ...])	!!! abstract "Usage Documentation"
ControlEffect.model_dump_json(*[, indent, ...])	!!! abstract "Usage Documentation"
ControlEffect.model_json_schema([by_alias, ...])	Generates a JSON schema for a model class.
ControlEffect.model_parametrized_name(params)	Compute the class name for parametrizations of generic classes.
ControlEffect.model_post_init(context, /)	Override this method to perform additional initialization after __init__ and model_construct.
ControlEffect.model_rebuild(*[, force, ...])	Try to rebuild the pydantic-core schema for the model.
ControlEffect.model_validate(obj, *[, ...])	Validate a pydantic model instance.
ControlEffect.model_validate_json(json_data, *)	!!! abstract "Usage Documentation"
ControlEffect.model_validate_strings(obj, *)	Validate the given object with string data against the Pydantic model.
ControlEffect.parse_file(path, *[, ...])
ControlEffect.parse_obj(obj)
ControlEffect.parse_raw(b, *[, ...])
ControlEffect.schema([by_alias, ref_template])
ControlEffect.schema_json(*[, by_alias, ...])
ControlEffect.set_data(mmm, model, X)	Update control data for new predictions.
ControlEffect.to_dict([_orig])	Serialize to a dict via Pydantic model_dump.
ControlEffect.update_forward_refs(**localns)
ControlEffect.validate(value)

Attributes

model_computed_fields
model_config	Configuration for the model, should be a dictionary conforming to [ConfigDict][pydantic.config.ConfigDict].
model_extra	Get extra fields set during validation.
model_fields
model_fields_set	Returns the set of fields that have been explicitly set on this model instance.
prior
date_dim_name