TimeGPT-1: production ready pre-trained Time Series Foundation Model for forecasting and anomaly detection. Generative pretrained transformer for time series trained on over 100B data points. It's capable of accurately predicting various domains such as retail, electricity, finance, and IoT with just a few lines of code 🚀.
This short notebook on handling categorical variables seems to indicate that this needs to be done through the use of SpecialDates. This is a bit misleading and a limited use case.
Description
This short notebook on handling categorical variables seems to indicate that this needs to be done through the use of
SpecialDates
. This is a bit misleading and a limited use case.This detailed notebook explains the usage much better.
I feel that the short notebook needs to be updated to be more representative of the process for categorical variables.
Link
No response