recommenders-team/recommenders
Ver no GitHub[ASK] [DISCUSSION] What kind of news is recommended
Open
#1.251 aberto em 26 de nov. de 2020
help wanted
Métricas do repositório
- Stars
- (17.706 stars)
- Métricas de merge de PR
- (Mesclagem média 6d 16h) (10 fundiu PRs em 30d)
Description
Scorer and recommendation items
if you look in the function run_fast_eval what exactly we recommend and add the following changes:
for (
impr_index,
news_index,
user_index,
label,
) in tqdm(self.test_iterator.load_impression_from_file(behaviors_file)):
pred = np.dot(
**np.stack(news_vecs.values(), axis=0),**
user_vecs[impr_index],
)
**pred = np.argsort(pred)[::-1]**
it will become clear that at the beginning of the list of recommendations there will ALWAYS be those articles, the number of which on the train as 1 was greater. which means, in fact, not quite relevant items are recommended. and not even the most popular, since this is only the number in the target, and not in all sessions
similarly, if you shoot a metric in a slice not an impression but in a user slice, that is, for 1 user and several 1 targets, then the metric will immediately drop by more than 2 times