BaseDelayedSaturatedMMM

class pymc_marketing.mmm.delayed_saturated_mmm.BaseDelayedSaturatedMMM(date_column, channel_columns, adstock_max_lag, model_config=None, sampler_config=None, validate_data=True, control_columns=None, yearly_seasonality=None, **kwargs)

Base class for a media mix model with delayed adstock and logistic saturation class (see [1]).

References

[1]

Jin, Yuxue, et al. “Bayesian methods for media mix modeling with carryover and shape effects.” (2017).

Methods

BaseDelayedSaturatedMMM.__init__(...[, ...])	Constructor method.
BaseDelayedSaturatedMMM.build_model(X, y, ...)	Builds a probabilistic model using PyMC for marketing mix modeling.
BaseDelayedSaturatedMMM.channel_contributions_forward_pass(...)	Evaluate the channel contribution for a given channel data and a fitted model, ie.
BaseDelayedSaturatedMMM.compute_channel_contribution_original_scale()	rtype: DataArray
BaseDelayedSaturatedMMM.compute_channel_curve_optimization_parameters_original_scale([...])	Experimental: Estimate the parameters for the saturating function of each channel's contribution.
BaseDelayedSaturatedMMM.compute_mean_contributions_over_time([...])	Get the contributions of each channel over time.
BaseDelayedSaturatedMMM.fit(X[, y, ...])	Fit a model using the data passed as a parameter.
BaseDelayedSaturatedMMM.get_params([deep])	Get all the model parameters needed to instantiate a copy of the model, not including training data.
BaseDelayedSaturatedMMM.get_target_transformer()	rtype: Pipeline
BaseDelayedSaturatedMMM.graphviz(**kwargs)
BaseDelayedSaturatedMMM.load(fname)	Creates a DelayedSaturatedMMM instance from a file, instantiating the model with the saved original input parameters.
BaseDelayedSaturatedMMM.optimize_channel_budget_for_maximum_contribution(...)	Experimental: Optimize the allocation of a given total budget across multiple channels to maximize the expected contribution.
BaseDelayedSaturatedMMM.plot_budget_scenearios(*, ...)	Experimental: Plots the budget and contribution bars side by side for multiple scenarios.
BaseDelayedSaturatedMMM.plot_channel_contribution_share_hdi([...])	rtype: Figure
BaseDelayedSaturatedMMM.plot_channel_parameter(...)	rtype: Figure
BaseDelayedSaturatedMMM.plot_components_contributions(...)	rtype: Figure
BaseDelayedSaturatedMMM.plot_direct_contribution_curves([...])	Plots the direct contribution curves for each marketing channel.
BaseDelayedSaturatedMMM.plot_grouped_contribution_breakdown_over_time([...])	Plot a time series area chart for all channel contributions.
BaseDelayedSaturatedMMM.plot_posterior_predictive([...])	rtype: Figure
BaseDelayedSaturatedMMM.plot_prior_predictive([...])	rtype: Figure
BaseDelayedSaturatedMMM.plot_waterfall_components_decomposition([...])	This function creates a waterfall plot.
BaseDelayedSaturatedMMM.predict(X_pred[, ...])	Uses model to predict on unseen data and return point prediction of all the samples.
BaseDelayedSaturatedMMM.predict_posterior(X_pred)	Generate posterior predictive samples on unseen data.
BaseDelayedSaturatedMMM.predict_proba(X_pred)	Alias for predict_posterior, for consistency with scikit-learn probabilistic estimators.
BaseDelayedSaturatedMMM.preprocess(target, data)	Preprocess the provided data according to the specified target.
BaseDelayedSaturatedMMM.sample_posterior_predictive(X_pred)	Sample from the model's posterior predictive distribution.
BaseDelayedSaturatedMMM.sample_prior_predictive(X_pred)	Sample from the model's prior predictive distribution.
BaseDelayedSaturatedMMM.save(fname)	Save the model's inference data to a file.
BaseDelayedSaturatedMMM.set_idata_attrs([idata])	Set attributes on an InferenceData object.
BaseDelayedSaturatedMMM.set_params(**params)	Set all the model parameters needed to instantiate the model, not including training data.
BaseDelayedSaturatedMMM.validate(target, data)	Validates the input data based on the specified target type.
BaseDelayedSaturatedMMM.validate_channel_columns(data)	rtype: None
BaseDelayedSaturatedMMM.validate_date_col(data)	rtype: None
BaseDelayedSaturatedMMM.validate_target(data)	rtype: None

Attributes

X
default_model_config	Returns a class default config dict for model builder if no model_config is provided on class initialization Useful for understanding structure of required model_config to allow its customization by users .
default_sampler_config	Returns a class default sampler dict for model builder if no sampler_config is provided on class initialization Useful for understanding structure of required sampler_config to allow its customization by users .
fit_result
id	Generate a unique hash value for the model.
methods
output_var	Defines target variable for the model
posterior_predictive
preprocessing_methods	A property that provides preprocessing methods for features ("X") and the target variable ("y").
prior
prior_predictive
validation_methods	A property that provides validation methods for features ("X") and the target variable ("y").
version
y
model
date_column
channel_columns