Nixtla / nixtla

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 🚀.
https://docs.nixtla.io
Other
1.91k stars 151 forks source link

Does Nixtla support time format "YYYY-MM-DD hh:mm:ss“ ? #220

Closed hvacking closed 1 month ago

hvacking commented 5 months ago

hi , In many timeserial prediction scenarios , we need use time "YYYY-MM-DD hh:mm:ss“ as timestamp.Now it seems timeGPT only support format "YYYY-MM-DD". Will timeGPT support this in the future?

MMenchero commented 4 months ago

Hi @hvacking the format "YYY-MM-DD hh:mm:ss" is currently supported as evidenced in this tutorial that uses hourly data. If you're having trouble with the format, please share with us a reproducible example.

elephaint commented 1 month ago

I think this issue is solved, @hvacking let us know if you have issues with the explanation offered in the tutorial.