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

81 level of information evalutation #90

Merged

Conversation

i-be-snek
Copy link
Collaborator

@i-be-snek i-be-snek commented Aug 30, 2024

See #81

Definition of done:

  • Commands to evaluate:
    • l1
    • l2 monetary
    • l3 monetary
    • l2 numerical
    • l3 numerical
  • Commands to append the database
    • l1
    • l2
    • l3
  • Bash script to parse, evaluate, and insert data from llm output (full working example)

an additional requirement:

  • The database size is reduced and GeoJson objects are not duplicated, but rather represented by a nid (uid)

@i-be-snek i-be-snek linked an issue Aug 30, 2024 that may be closed by this pull request
13 tasks
@i-be-snek i-be-snek changed the base branch from main to 81-level-of-information-dev September 5, 2024 06:30
@i-be-snek i-be-snek force-pushed the 81-level-of-information-evalutation branch from a774ab5 to 87486b1 Compare September 8, 2024 13:13
@i-be-snek i-be-snek force-pushed the 81-level-of-information-dev branch from 91e533f to 9f9bcd7 Compare September 8, 2024 13:13
@i-be-snek i-be-snek self-assigned this Sep 8, 2024
@i-be-snek i-be-snek closed this Sep 8, 2024
@i-be-snek i-be-snek reopened this Sep 8, 2024
@i-be-snek
Copy link
Collaborator Author

i-be-snek commented Sep 8, 2024

TODO:

  • adapt db insertion scripts of l2+l3
  • make sure db insertion scripts work for l1
  • float("nan") instead of using numpy
  • test l1 evaluation script
  • bash command to evaluate l2
  • bash command to evaluate l3
  • double check all column names
  • LEFTOVER: evaluate based on available currency
  • get fresh data pull for the dev set
  • README: add bash script for dummies
  • README: bash script for parsing + evaluating + inserting the dev set
  • README: one last sweep of all READMEs in the repo to make sure they are up to date
  • request reviews when the PR is ready
  • update weights
  • "Event_Names" or "Event_Name"? Not evaluated anyway
  • De-duplicate GeoJson blobs in db
  • open new PR for leftovers
  • Admin Area evaluation gives a score of 1: data type mismatch?

PROBLEMS: All commented out categories in weights.py are not properly working.

  • Monetary impact types do not yet have evaluation by the correct currency implemented
  • Lists of areas have problems with data type mismatches -- could be the code or the llm output

@i-be-snek i-be-snek force-pushed the 81-level-of-information-evalutation branch from 977e255 to d5cae0e Compare September 16, 2024 12:45
@i-be-snek i-be-snek force-pushed the 81-level-of-information-dev branch 2 times, most recently from 6e562df to ab1f732 Compare September 16, 2024 12:47
@i-be-snek i-be-snek force-pushed the 81-level-of-information-evalutation branch from d5cae0e to ed1f7f1 Compare September 16, 2024 12:49
@i-be-snek i-be-snek force-pushed the 81-level-of-information-evalutation branch from ed1f7f1 to 48e7f63 Compare September 16, 2024 12:52
@i-be-snek i-be-snek changed the title WIP: 81 level of information evalutation 81 level of information evalutation Sep 18, 2024
@i-be-snek i-be-snek merged commit ac0b764 into 81-level-of-information-dev Sep 18, 2024
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.

Level of information: introducing L1-L3 (3 PRs)
1 participant