Skip to content

crypto-sentiment/crypto_sentiment_tfidf_logreg_streamlit

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

7 Commits
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

Cryptonews sentiment classification model

A simple cryptonews sentiment classification app.

The model (simple tf-idf & logreg) is trained with ~4500 news titles manually classiified into positive, neutral or negative.

Launching the app:

  • install requirements from requirements.txt
  • execute streamlit run src/app.py

To run this as a background process, you can do (streamlit run src/app.py > streamlit.log 2>&1 &). This will also write all Stramlit logs including error logs to the file streamlit.log.

Releases

No releases published

Packages

No packages published

Languages