I think this is an error, the function is supposed to view 5 samples of user_train data but they show the same user id
Hello @tinted,
Each row represents one rating from one user for one movie. This table is showing the user part for 5 ratings, and if those ratings are from the same user, then it will be like that.
Cheers,
Raymond
I should have included this as well but the above image is the description/analysis of the data displayed. The way I understand is that it is not Users x Movies but User x User Features
Edit: Actually, you are right, That last line “The user vector is the same for all the movies rated by a user” explains it that it is indeed Users x Movies and that the rows will be same for all the movies rated by a single user
I still have hard time imagining how the data is stored in that “user_train” . I will edit the code and check more samples after the assignment for more clarity
Sure. We can discuss about your findings if needed.
Good luck!
Ok, I printed 100 samples and there are other user IDs as well. So basically it is
( User x Movies ) flattened vs User Features
But the movies from the same users have the same row vector since the values are from Users x User Features