Forecaster
GreykiteForecaster
Adapter for using Greykite forecasting models within sktime.
This forecaster wraps Greykite forecast_pipeline (configured via a ForecastConfig) and exposes a sktime-compatible API.
WARNING: the greykite package has very restrictive dependencies that typically prevent installation together with other packages. For this reason, this estimator is also not covered by regular tests. We therefore recommend to run check_estimator(GreykiteForecaster) on your system before deploying this estimator.
Schnellstart
python
from sktime.forecasting.greykite import GreykiteForecaster
estimator = GreykiteForecaster(forecast_config: GreykiteForecaster.ForecastConfig | None=None, date_format: str | None=None, model_template: str='SILVERKITE', coverage: float=0.95)Parameter(4)
- forecast_configForecastConfig, optional
- Configuration object for Greykite’s forecasting pipeline. If None, a default configuration is created.
- date_formatstr, optional
- Format of the timestamp in the data. If None, it is inferred.
- model_templatestr, optional
- Name of the model template to use (default: “SILVERKITE”).
- coveragefloat, optional
- Intended coverage of the prediction bands (0.0 to 1.0).
Beispiele
>>> from sktime.datasets import load_airline
>>> from sktime.forecasting.greykite import GreykiteForecaster
>>> from sktime.forecasting.base import ForecastingHorizon
>>> y = load_airline ()
>>> fh = ForecastingHorizon ([1, 2, 3 ])
>>> forecaster = GreykiteForecaster ()
>>> forecaster. fit (y = y, fh = fh)
>>> y_pred = forecaster. predict (fh = fh)