Use timely-beliefs tooling to create forecast model specs #154
Conversation
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Flix6x
changed the title
nhoening
requested changes
Jul 21, 2021
|
Does this deserve a changelog entry? I think it might. It would also force you to formulate the benefit of this PR from a higher perspective. I believe that with the level of timely beliefs integration we already have, this PR is necessary to achieve forecasting, or some part of that functionality. But I think you know this more precisely. |
|
One more thought: can you check if the tutorial on creating forecasts would require adaptations after this PR? |
# Conflicts: # documentation/changelog.rst
nhoening
approved these changes
Aug 2, 2021
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
This PR introduces
TBSeriesSpecs(subclassed fromSeriesSpecs) that makes use of thecollectfunctionality introduced earlier in FlexMeasures. We need such timely-beliefs tooling to ensure our beliefs data is properly mapped to a time series data structure that ML models can work with (i.e. feature frames). Currently, thecollectfunctionality makes sure that the regressor data is deterministic and single-sourced.Also introduces the possibility to set the desired resolution of forecasts, plus some minor refactoring.