-
Notifications
You must be signed in to change notification settings - Fork 788
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
example: add time-series models with statsmodels #4979
Conversation
For more information, see https://pre-commit.ci
For more information, see https://pre-commit.ci
Hi @xianml, as per your suggestion I have created the same arima model example using bentoml >=1.2, please help to review. Regards! |
saved_model = bentoml.picklable_model.save_model( | ||
"arima_forecast_model", | ||
model, | ||
signatures={"predict": {"batchable": True}}, | ||
) |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
The recommended API here is using bentoml.models.create
with our latest API. https://docs.bentoml.org/en/latest/guides/model-store.html
Hi @jsamantaucd We are preparing to restructure the examples and do not accept new framework-specific examples. You can make it in a standalone repository and we can link it in our README, thanks. |
Feature request
I have implemented and tested a feature that trains a time series model - ARIMA and serves it using BentoML's custom runner to make predictions.
Motivation
I believe it would be a nice guide to someone exploring time series models with custom runner implementation for models like ARIMA.
Others:
This feature was tested on Bentoml v1.2.16