Thanks for this article!
Few questions:
- Does it really make sense to compute similarity between movies looking at their ratings only (what you do in compute_movie_similarity_count if I'm not mistaking)?
- Can you explain the reshape here np.zeros(61700).reshape(617,100) (in function compute_user_similarity)
More importantly:
- It is not clear to me what you do means exactly by "Featuring the Data"... Can you please explain a bit more?
Thanks in advance :)