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

Sentiment analysis #210

Merged
merged 32 commits into from
Aug 7, 2024
Merged

Sentiment analysis #210

merged 32 commits into from
Aug 7, 2024

Conversation

davidpomerenke
Copy link
Collaborator

No description provided.

@davidpomerenke
fix(fulltext_coding.py): suppress errors from gpt parsing
bf5ba04
@davidpomerenke
refactor(sentiment analysis): use fulltexts endpoint within sentiment…
52925b2 
… trend endpoint
@davidpomerenke
refactor(fulltexts): use sampling when many fulltexts
bdb9dec 
this is only a temporary fix to reduce the number of articles
@davidpomerenke
feature(frontend-observable): add sentiments page
a83837f
@davidpomerenke
chore: fix vscode debug reload condition
9e20a35
@davidpomerenke
refactor: upgrade to gpt4o-mini
c4b374b
@davidpomerenke
feat: defensive json parsing
8bdc751
@davidpomerenke
fix(parallel.py): make parallel_tqdm smoother
e31f404
@davidpomerenke
refactor(fulltext scraping): use parallelization rather than async
865662e
@davidpomerenke
refactor(frontend-observable): smooth interpolation of protest plot
ee1206c
@davidpomerenke
refactor: better caching for mediacloud
e7c228e
@davidpomerenke
chore: comment out fulltext retrieval in cron
ea5708e 
very slow and will be refactored anyway
@davidpomerenke
feat: api endpoint to trigger fill_cache()
a865515
@davidpomerenke
feat: async multiprocessing for llms
e4f61c2 
does not work well with rate limit though
@davidpomerenke
refactor(cache.py): do not raise for status
17bb850
@davidpomerenke
refactor(mediacloud): efficient parallel monthly downloading of metad…
3e14540 
…ata, pages, and extracted fulltexts
@davidpomerenke
refactor(fulltexts): small things about parallel fulltext coding
b45e5ee
@davidpomerenke
style(backend): run ruff
a64136e
@davidpomerenke
fix(sentiment trend): fix issues with missing start and end dates
ecd888c
@davidpomerenke
feat(sentiment analysis): more fine-grained coding with topics and pr…
9e42a1d 
…otest sentiment vs policy sentiment
@davidpomerenke
feat(sentiment trend): stable sampling
70312fb
@davidpomerenke
feat: async with rate limiting for ai requests
d6baed1
@davidpomerenke
refactor(trends): make "aggregation" field work for all trend types
dbcfc24
@davidpomerenke
fix(fulltexts): fix date issue
3b50e9e
@davidpomerenke
refactor(fulltexts): adjust sampling and column names
629059e
@vercel Vercel
Copy link

vercel bot commented Aug 4, 2024 •
edited
Loading

The latest updates on your projects. Learn more about Vercel for Git ↗︎

Name Status Preview Updated (UTC)
media-impact-monitor ✅ Ready (Inspect) Visit Preview Aug 7, 2024 5:34pm

@railway-app Railway App
Copy link

railway-app bot commented Aug 4, 2024 •
edited
Loading

🚅 Previously deployed to Railway in the media-impact-monitor project. Environment has been deleted.

@davidpomerenke davidpomerenke merged commit 1213478 into dev Aug 7, 2024
2 of 3 checks passed
@davidpomerenke davidpomerenke deleted the feature-sentiment-analysis branch August 7, 2024 17:43
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.
1 participant
@davidpomerenke