Remove 4 26#15
Open
dalyw wants to merge 9 commits into
Open
Conversation
In unitprocess_json file: Adding Denitrification Filter to UP list Moving anaerobic filter out of fixed film category Moving biosolids lagoon out of disposal category and adding Lagoon as secondary category Cleaning up some alt_names Deleting old llm output files (using facility name rather than place ID)
Modified LLM prompt to further encourage structured output and adherence to ontology categories Expanding San Jose example to include solids, disinfection Renaming "truth" to "manual reading" throughout after figure_2
Renaming cwns_processes_by_facility to cwns_unit_processes_by_facility for consistency with LLM file Updating README
fletchapin
reviewed
May 30, 2026
Contributor
fletchapin
left a comment
There was a problem hiding this comment.
Overall it looks great! I just had a minor comment about the date folder
| sys.path.insert(0, os.path.dirname(os.path.abspath(__file__))) | ||
|
|
||
| DATE_FOLDER = "2026-5-15" | ||
| DATE_FOLDER = "2026-5-25" |
Contributor
There was a problem hiding this comment.
Is the date important for publication? I guess I'm wondering if we can just remove a level of nesting and publish this data directly in the output folder
Collaborator
Author
There was a problem hiding this comment.
The date only matters if we re-run every ~6-12 months as permits are updated to keep separate versions of the results.
But we could keep these analysis scripts “flat” and then save any date-specific versions in the Stanford Digital Repository output file - how does that sound?
| from helpers.plotting import make_grouped_legend, save_and_close, set_thick_spines | ||
|
|
||
| DATE_FOLDER = "2026-5-15" | ||
| DATE_FOLDER = "2026-5-25" |
Contributor
There was a problem hiding this comment.
Same question about the date
Adding final unit_processes_by_facility.csv file with both datasets Fixing bug in step4 where "offsite" laction wasn't being used Re-running model comparison with final ontology and Place ID suffix on filenames Updating step5_llm_extraction with higher token limits for gpt-5 and to save manifest/token csv rows after every facility
This file contains hidden or 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
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
2 participants
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.
No description provided.