Nicolas Hug
Nicolas Hug
Thanks for the PR! It looks pretty good even though I haven't checked it in details yet. For the tests, take a look at how to use pytest and take...
This looks good and I'd like to merge it but could you please write a few tests in the `test_similarities` module? You'll also need to update the `AlgoBase.compute_similarities` method.
No worries there's absolutely no rush! I just wanted to make sure you knew I need some tests before I can merge this ;)
Yes it's still open so you're welcome to try if you want to. Don't forget to check the contributing guidelines :)
There's no PR related to adjusted cosine so you can go for it. One of the open PRs is related #164, but even then, it's only partially addressed. Just to...
> this would be similar to the actual implementation of cosine similiraty Yes, but adjusted cosine is even closer to pearson similarity. >with common_ratings_only=True There is no `common_ratings_only` option for...
@ghazalaak please don't highjack unrelated issues. Open a new one if you need to (you'll have to be a lot more specific though).
I'm not aware of any, sorry
> With the current implementation, one item can get a higher prediction than another, and we might recommend it, while its prediction might have been derived from some remote neighbours,...
A major issue with your approach is that as it's fairly unlikely the k-nearest neighbors of a user have rated the target item, the prediction is most of the time...