Forecaster

UpdateEvery

Categorical in XInsamplePred int insampleExogenous

Update only periodically when update is called.

If update is called, behaves like update_params=False, unless update_interval time has elapsed since the last “true” update, i.e., call to forecaster.update with update_params=False.

update_interval controls the minimum time that needs to elapse.

Caution: default value of update_interval means no updates after fit.

Schnellstart

python

from sktime.forecasting.stream import UpdateEvery

estimator = UpdateEvery(forecaster, update_interval=None)

Parameter(1)

update_intervaldifference of sktime time indices (int or timedelta), optional: interval that needs to elapse until inner update call with update_params=True default = None = infinity, i.e., never updates
if index of y seen in fit is integer or y is index-free container type, refit_interval must be int, and is interpreted as difference of int location
if index of y seen in fit is timestamp, must be int or pd.Timedelta
if pd.Timedelta, will be interpreted as time since last refit elapsed
if int, will be interpreted as number of time stamps seen since last refit

Beispiele

>>> from sktime.forecasting.trend import TrendForecaster
>>> from sktime.forecasting.stream import UpdateEvery
>>> from sktime.datasets import load_airline
>>> y = load_airline ()
>>> y0 = y. iloc [: - 20 ]
>>> y1 = y. iloc [- 20: - 10 ]
>>> y2 = y. iloc [- 10:]
>>> inner_forecaster = TrendForecaster ()
>>> forecaster = UpdateEvery (inner_forecaster, update_interval = 12)
>>> forecaster. fit (y0, fh = [1, 2, 3 ]) UpdateEvery(
... )
>>> # predict etc could be called here
>>> # e.g., forecaster.predict()
>>> 
>>> # first update, 10 < update_interval = 12, so calls update with
>>> # update_params=False
>>> forecaster. update (y1) UpdateEvery(
... )
>>> # second update, 20 >= update_interval = 12, so calls update with
>>> # update_params=True
>>> forecaster. update (y2) UpdateEvery(
... )