lift_test

Adding lift tests as observations of saturation function.

This provides the inner workings of MMM.add_lift_test_measurements method. Other methods can be MMM.add_cost_per_target_calibration. Use any of these methods directly while working with the MMM class.

Functions

add_cost_per_target_potentials(calibration_df, *)	Add pm.Potential penalties to calibrate cost-per-target.
add_lift_measurements_to_likelihood_from_saturation(...)	Add lift measurements to the likelihood from a saturation transformation.
add_saturation_observations(df_lift_test, ...)	Add saturation observations to the likelihood of the model.
assert_is_subset(required, available)	Check if the available set is a subset of the required set.
assert_monotonic(delta_x, delta_y)	Check if the lift test results satisfy the increasing assumption.
create_time_varying_saturation(saturation, ...)	Return function and variable mapping that use a time-varying variable.
create_variable_indexer(model, indices)	Create a function to index variables in the model.
exact_row_indices(df, model)	Get indices in the model for each row in the DataFrame.
scale_channel_lift_measurements(...[, dim_cols])	Scale the lift measurements for a specific channel.
scale_lift_measurements(df_lift_test, ...[, ...])	Scale the DataFrame with lift test results to be used in the model.
scale_target_for_lift_measurements(target, ...)	Scale the target for the lift measurements.

Exceptions

MissingValueError(missing_values, ...)	Error when values are missing from a required set.
NonMonotonicError	Data is not monotonic.
UnalignedValuesError(unaligned_values)	Raised when some values are not aligned.