sknifedatar is a package that serves primarily as an extension to the modeltime 📦 ecosystem. In addition to some functionalities of spatial data and visualization.
Hey @ichsan2895 ,
Thanks for this comment! This function currently expects the data in ascending order.
However, data order validation could be implemented in future developments.
Hello, I have tried this tutorial
https://github.com/rafzamb/sknifedatar
I found some bug (or restriction maybe?). Sknifedatar will give wrong test dataset if the column date is not ordered by ascending.
Lets try this ORIGINAL
nested_serie = emae_series %>% filter(date < '2020-02-01') %>% nest(nested_column=-sector)
EXPERIMENT
nested_serie = emae_series %>% filter(date < '2020-02-01') %>% arrange(desc(date)) %>% nest(nested_column=-sector)
The result is like this:
and this
I aware this problem since I tried with another dataset which have random order of date column.