You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
I have two questions related to holidays, which have an important impact on the quantity to forecast for some use cases.
First, passing an instance of sktime.transformations.series.holiday.CountryHolidaysTransformer in the list of fe_target_rr passed to setup results in an error: fe_target_rr = [ CountryHolidaysTransformer("FR")] exp = TSForecastingExperiment() exp.setup(data = df_train, fh=28, fe_target_rr=fe_target_rr)
The error occurs when a model with exogeneous variable is instantiated.
The message in the log isn't precise. The errors disapears when I remove the CountryHolidaysTransformer.
Is it possible to solve it?
Second, if a feature related to holidays is provided, and forecast is performed for more than one step ahead, will a model supporting exogeneous variable receives as input this feature (which is available for the future) to forecast for the next steps? Is it possible to do so?
reacted with thumbs up emoji reacted with thumbs down emoji reacted with laugh emoji reacted with hooray emoji reacted with confused emoji reacted with heart emoji reacted with rocket emoji reacted with eyes emoji
-
Hi,
I have two questions related to holidays, which have an important impact on the quantity to forecast for some use cases.
First, passing an instance of sktime.transformations.series.holiday.CountryHolidaysTransformer in the list of fe_target_rr passed to setup results in an error:
fe_target_rr = [ CountryHolidaysTransformer("FR")]
exp = TSForecastingExperiment()
exp.setup(data = df_train, fh=28, fe_target_rr=fe_target_rr)
The error occurs when a model with exogeneous variable is instantiated.
The message in the log isn't precise. The errors disapears when I remove the CountryHolidaysTransformer.
Is it possible to solve it?
Second, if a feature related to holidays is provided, and forecast is performed for more than one step ahead, will a model supporting exogeneous variable receives as input this feature (which is available for the future) to forecast for the next steps? Is it possible to do so?
Kind regards
Beta Was this translation helpful? Give feedback.
All reactions