Martin Spišák
Martin Spišák
I agree with #5230. 64-bit indices are often unnecessary and cause large memory overhead.
added Usage section to readme: https://github.com/glami/sansa/commit/3d690141dbb7a65ab94a0eb3b0b1b47626e0b070
created new issue https://github.com/glami/sansa/issues/11 for tasks related to demo notebooks
> It’s working for me again. It might have been an issue on YouTube’s side. > Issue had resolved but it has come back again > sometimes I'm lucky and...
> 50k per axis (i.e. 50k x 50k) and **_symmetric_** I'm very late to reply but we have an industry ML use case for large-scale (10^6+) dimensional linear regression, and...
@tqtg I'd be happy to contribute the implementation of [SANSA](https://github.com/glami/sansa) to your library :). Since it's basically EASE, it more or less suffices to copy its interface and replace the...
@filippo-orru > My data is quite skewed. Few users, each with lots of ratings: > `'users': 73, 'items': 445049, 'interactions': 634437, 'interaction density': '1.95%'` The problem here is caused by...
Yes, I think splitting the users can work well. It really depends on your data and domain, but if you collected this data over a longer period of time, it...