Unusual changepoints plot
- Dominant language
- Python
- Stars
- 20.4k
- Forks
- 4.6k
- Avg merge
- 19h 52m
- Merged PRs (30d)
- 1
Description
Hi,
usually changepoints plot look like this:
I would like your opinion on a model with such changepoints (on the same series):
Parameters for this model:
changepoint_prior_scale = 0.46, changepoint_range = 0.94, fourier_order_weekly_seasonality = 10, fourier_order_yearly_seasonality = 9, seasonality_mode = 'multiplicative', growth = 'linear', weekly_seasonality_prior_scale = 6.119445545860264, yearly_seasonality_prior_scale = 7.131054290549793
(I used hyperopt for tuning.)
Is such a model ok, or is there something wrong?
Contributor guide
Assessment
This issue has not been assessed yet.