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

Pipeline preprocessor behavior #139

Merged
merged 10 commits into from
Sep 19, 2024
Merged

Pipeline preprocessor behavior #139

merged 10 commits into from
Sep 19, 2024

Conversation

wgifford
Copy link
Collaborator

@wgifford wgifford commented Sep 18, 2024

This PR adopts new behavior for the time series forecasting pipeline.

In the case where a preprocessor (feature_extractor) is available and passed to the pipeline, it will be used to both scale the inputs and inverse scale the outputs. Previously, only inverse scaling was done -- making it the responsibility of the caller to pre-scale the data if needed.

If no preprocessor is passed to the pipeline, behavior remains unchanged.

Miscellaneous fixes:

  • Address inference of time series frequency
  • Edge cases in plotting functions

@wgifford wgifford merged commit f124336 into main Sep 19, 2024
9 checks passed
@wgifford wgifford deleted the pipeline_preprocess branch September 19, 2024 01:00
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

Successfully merging this pull request may close these issues.

1 participant