View source on GitHub
|
Central registry for managing calibration.
meridian.model.calibration.base.CalibrationRegistry()
This registry stores channel-level incrementality experiment results and information for calibration and delegates calibration calls to the appropriate calibration strategy.
Methods
add_input
add_input(
data: CalibrationInput
) -> None
Registers calibration input for a channel.
| Args | |
|---|---|
data
|
The CalibrationInput to register. |
get_roi_distributions_by_channel
get_roi_distributions_by_channel(
last_modeled_date: datetime.date,
*,
max_lag: int,
interval_days: int,
model_duration_days: int
) -> CalibrationRegistryResult
Retrieves calibrated ROI distributions for media and reach & frequency channels.
| Args | |
|---|---|
last_modeled_date
|
The last date of the modeled period in the Meridian model. |
max_lag
|
The maximum lag value in model intervals. |
interval_days
|
The interval size of the Meridian model time coordinates in days. |
model_duration_days
|
The number of days in the modeled period of the Meridian model. |
| Returns | |
|---|---|
A CalibrationRegistryResult containing the mappings of channel names
to ROI distributions and calibration outputs.
|
| Raises | |
|---|---|
ValueError
|
If a baseline prior was provided for a channel, but no experiments were found. |
__eq__
__eq__(
other
)
Return self==value.
View source on GitHub