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 a time-series DataFrame with hourly frequency. The data is financial and the trading occurs only during business hours 9am-5pm.
In order to train a DeepVAR model (or any other from GluonTS), one needs to have a uniformly spaced (in my case its hourly frequency) DataFrame which means all 24 hours in the day.
What is the best practice in this case - should I have all non-business hours as NaN, or forward fill the last available value for all non-business hours? Is there a way to set frequency to be 'business hours' rather than 'hourly'?
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
-
I have a time-series DataFrame with hourly frequency. The data is financial and the trading occurs only during business hours 9am-5pm.
In order to train a DeepVAR model (or any other from GluonTS), one needs to have a uniformly spaced (in my case its hourly frequency) DataFrame which means all 24 hours in the day.
What is the best practice in this case - should I have all non-business hours as NaN, or forward fill the last available value for all non-business hours? Is there a way to set frequency to be 'business hours' rather than 'hourly'?
Beta Was this translation helpful? Give feedback.
All reactions