search

Joseph-233 / music-recommendation

This project recommends music to users based on their heart beat (bpm)
3 stars 1 forks source link

Predicting Fetures Based on Heart Rate Using LightGBM Multi-Regression Model. Fetching Songs from Spotify instead of Our Dataset #21

Closed juan-yu closed 6 months ago

juan-yu commented 6 months ago

IMPORTANT: Run this in console "streamlit run streamlit\app.py"

  1. Train the multiregression model with light gbm to find the relationship between tempo and other features, then store this model into spotify_reco/models/saved_models
  2. When a user inputs heart rate, I load the saved model to predict the other features, then use https://developer.spotify.com/documentation/web-api/reference/get-recommendations to fetch 10 songs by the predicted features and the user profile
  3. Showing fetched songs in embed
  4. Let user like or dislike songs like Tinder, then save their preference

image

juan-yu commented 6 months ago

Seems like the test programs are not found?