ksalama/data2cooc2emb2ann

Learning embeddings from item co-occurrence statistics, and building an approx. nearest neighbour index

28
/ 100
Experimental

This project helps you understand relationships between items by analyzing how often they appear together in your data. It takes your tabular data, identifies co-occurring items, and generates numerical representations (embeddings) that capture their relatedness. These embeddings are then used to quickly find items similar to a given item, making it useful for data scientists and analysts exploring item relationships.

No commits in the last 6 months.

Use this if you have tabular data and need to discover and quantify how items relate to each other, and then efficiently search for similar items.

Not ideal if you're looking for a simple keyword search or don't have existing co-occurrence data.

item-similarity co-occurrence-analysis recommendation-systems data-exploration embedding-generation
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 4 / 25
Maturity 16 / 25
Community 8 / 25

How are scores calculated?

Stars

8

Forks

1

Language

Jupyter Notebook

License

GPL-3.0

Last pushed

Mar 24, 2023

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/embeddings/ksalama/data2cooc2emb2ann"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.