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.

Sign up for GitHub

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

Jump to bottom

[WIP] First version of curebot bertopic refactor #24

Open
wants to merge 27 commits into
base: main
Choose a base branch
from
Open

[WIP] First version of curebot bertopic refactor #24

wants to merge 27 commits into from

Conversation

grosjeang
Copy link
Collaborator

@grosjeang grosjeang commented Feb 7, 2025 •
edited
Loading

A first version of BERTopic demonstrator for Curebot.

TODO:

  • better demo configuration management using a config.file
  • add newsletter tab
  • currently uses tags for zeroshot by default, add possibility to disable

picaultj and others added 24 commits January 21, 2025 16:51
@picaultj
Simplified typing
04a2a39
@picaultj
Refactor BERTrend (moved functions inside the class)
a11cd28
@picaultj
Refactor generate_topic_description (JSON output)
5676c32
@picaultj
Simplification of parameters of analyze_signal
8d6b632
@picaultj
Updated train topics function for incremental topic learning
7009d59 
Updated notebook
@picaultj
Improvements notebook, bug fix in merge_all_models
e463cf5
🎨 Format Python code with psf/black
56d1a2e
@picaultj
Bugix: In some cases, there are no word description for the topic whi…
fb5d043 
…ch prevents from generating the LLM description. Added sanity check
@picaultj
WIP: Management of data feeds
c52f7a5
@picaultj
WIP: first version of script for partial training
c39e88d
@picaultj
WIP
69e89f9
@picaultj
Simplification / improvement to BERTrend serialization
2ffd01e
@picaultj
WIP: dashboard
311b844
@picaultj
Various bug fixes
ec016cf
@picaultj
Updated config for model analysis
88b1f67
@picaultj
Bug fixes
09c224b
@picaultj
Bug fix: problem of indices between the html analysis and the title/d…
c13ee2b 
…escription of the topic (NB. do not use the indices from bertrend.topic_models[x])
@picaultj
Bug fix: language was not correctly taken into account
829f71c
@picaultj
Updated BERTrend default path: .../bertrend/data|config|logs etc.
0beff96
@grosjeang
[WIP] First version of curebot bertopic refactor
1efd89d
@grosjeang
Tags usage is now an option
c0da490
@grosjeang
Add newsletter tab to curebot demonstrator
73ed11b
@grosjeang
Remove useless code
330df9c
@grosjeang
Remove useless code
cb98592
@grosjeang grosjeang force-pushed the refactor-bertopic-demo branch from c8bb15f to cb98592 Compare February 11, 2025 15:13
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Reviewers
No reviews
Assignees
No one assigned
Labels
None yet
Projects
None yet
Milestone
No milestone
Development

Successfully merging this pull request may close these issues.
2 participants
@grosjeang @picaultj