by megalodon on 6/22/23, 2:05 PM with 23 comments
by hotstickyballs on 6/22/23, 3:21 PM
Prophet, for example uses dates to create Fourier terms and indicators to holidays for example and that just seems like a more sane approach.
by tony_bagnall on 6/22/23, 5:57 PM
my interests primarily lie in classification, clustering and regression, but next year we are going into the forecasting world, plenty of exciting collaborations in the brew.
by Epa095 on 6/22/23, 3:10 PM
by polo333 on 6/22/23, 5:28 PM
by djl0 on 6/22/23, 3:03 PM
by ahif1999 on 6/22/23, 5:45 PM
by thetinymite on 6/22/23, 3:07 PM
https://twitter.com/sktime_toolbox/status/164721412371161907...
by uoaei on 6/22/23, 4:32 PM
There are of course exceptions, something like `TrendPredictor(order=1, interp="polynomial")` as an example can be flexibly adapted up or down the hierarchy of model complexity much easier than commenting out different lines.
by ahif1999 on 6/22/23, 5:48 PM
by ahif1999 on 6/22/23, 5:50 PM