I scraped HN's 1000 most mentioned books and visualised them.
This month I used a new embedding model (Nomic), switch out UMAP for PaCMAP, and added automatic cluster labelling.
The clustering and dimensionality reduction aren't quite as stable as I'd like, but most seeds give decent results now.
I scraped HN's 1000 most mentioned books and visualised them. This month I used a new embedding model (Nomic), switch out UMAP for PaCMAP, and added automatic cluster labelling.
The clustering and dimensionality reduction aren't quite as stable as I'd like, but most seeds give decent results now.