Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Question: PatchTSMixer - Support for exogenous variables #229

Open
gabriel301 opened this issue Jan 2, 2025 · 1 comment
Open

Question: PatchTSMixer - Support for exogenous variables #229

gabriel301 opened this issue Jan 2, 2025 · 1 comment

Comments

@gabriel301
Copy link

Some time ago I asked this question about some type of inputs that were available in the ForecastDFDataset class constructor:
#43

At that time, there were no models that supported those kind of inputs. Are they available now for PatchTSMixer? If so, is there any usage example?

Thanks!

@wgifford
Copy link
Collaborator

wgifford commented Jan 2, 2025

Hi @gabriel301

There is an example of using control_columns with the TinyTimeMixer model here: https://github.com/ibm-granite-community/granite-timeseries-cookbook/blob/main/recipes/Time_Series/Bike_Sharing_Finetuning_with_Exogenous.ipynb

conditional_columns and observed_columns would work in a similar way (expect for conditional_columns the underlying assumption is that future values are not observed).

Let me know if that example helps.

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

No branches or pull requests

2 participants