search

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 153 forks source link

When the y data is missing, how to deal with? Thank you! #353

Open zhao0415 opened 1 month ago

zhao0415 commented 1 month ago

How does TimeGPT deal with the missing y data? Could you please give a way to deal with it? Thank you so much!

elephaint commented 1 month ago

There is a tutorial for dealing with missing values. In short, you should make sure that there are no missing values before using TimeGPT to forecast. Thus, the missing values need to be imputed somehow.

Hope this helps.