From a dataset of over 23,000 songs, enter any song and get a recommendation for a similar song based on metrics such as its name, artist, and genre.
No followers yet
Once you ship this you can't edit the description of the project, but you'll be able to add more devlogs and re-ship it as you add new features!
Added front-end to the project using streamlit, and added spotify web player for each similar song.
Transfered code from chromebook to windows. Added exploratory data analysis step, displaying data with matplotlib. Added breakpoint results after each line with imaginary input for learning. Construcuted and debugged interpreting results for cosine_similarity matrix.
Cosine similarity, attempting to interpret the results, learning structure etc of pandas data structures, exploring np argmax