def get_reco_algo(request, algo_name='knn', category='all'):
chrono = Chrono(is_enabled=CHRONO_ENABLED)
already_rated_works = list(current_user_ratings(request))
if request.user.is_anonymous:
assert request.user.id is None
# We only support KNN for anonymous users, since the offline models did
# not learn anything about them.
# FIXME: We should also force KNN for new users for which we have no
# offline trained model available.
algo_name = 'knn'
chrono.save('get rated works')
try:
algo = get_algo_backup(algo_name)
dataset = get_dataset_backup(algo_name)
except FileNotFoundError:
triplets = list(
Rating.objects.values_list('user_id', 'work_id', 'choice'))
chrono.save('get all %d interesting ratings' % len(triplets))
dataset, algo = fit_algo(algo_name, triplets)
if algo_name == 'knn':
framed_rated_works = pd.DataFrame(list(current_user_ratings(request).items()), columns=['work_id', 'choice'])
framed_rated_works['work_id'] = dataset.encode_works(framed_rated_works['work_id'])
framed_rated_works['rating'] = framed_rated_works['choice'].map(rating_values)
nb_rated_works = len(framed_rated_works['work_id'])
ratings_from_user = coo_matrix((framed_rated_works['rating'],([0.] * nb_rated_works, framed_rated_works['work_id'])), shape=(1, algo.nb_works))
ratings_from_user = ratings_from_user.tocsr()
#Expands knn.M with current user ratings (vstack is too slow)
algo.M.data = np.hstack((algo.M.data, ratings_from_user.data))
algo.M.indices = np.hstack((algo.M.indices, ratings_from_user.indices))
algo.M.indptr = np.hstack((algo.M.indptr, (ratings_from_user.indptr + algo.M.nnz)[1:]))
algo.M._shape = (algo.M.shape[0] + ratings_from_user.shape[0], ratings_from_user.shape[1])
chrono.save('loading knn and expanding with current user ratings')
chrono.save('fit %s' % algo.get_shortname())
if category != 'all':
category_filter = set(Work.objects.filter(category__slug=category).values_list('id', flat=True))
else:
category_filter = dataset.interesting_works
filtered_works = list((dataset.interesting_works & category_filter) - set(already_rated_works))
chrono.save('remove already rated')
pos_of_best = get_pos_of_best_works_for_user_via_algo(algo, dataset, request.user.id, filtered_works, limit=NB_RECO)
best_work_ids = [filtered_works[pos] for pos in pos_of_best]
chrono.save('compute every prediction')
works = Work.objects.in_bulk(best_work_ids)
# Some of the works may have been deleted since the algo backup was created.
ranked_work_ids = [work_id for work_id in best_work_ids if work_id in works]
chrono.save('get bulk')
return {'work_ids': ranked_work_ids, 'works': works}
def build_profile_compare_function(algo_name: Optional[str],
ratings: List[Rating], user: User):
ordering = ['favorite', 'willsee', 'like', 'neutral', 'dislike', 'wontsee']
# By default, sort by rating then name
def default_compare_function(item):
return ordering.index(item.choice), item.work.title.lower()
if algo_name is not None:
try:
work_ids = [rating.work_id for rating in ratings]
algo = get_algo_backup(algo_name)
dataset = get_dataset_backup(algo_name)
best_pos = get_pos_of_best_works_for_user_via_algo(
algo, dataset, user.id, work_ids)
ranking = defaultdict(lambda: len(ratings))
for rank, pos in enumerate(best_pos):
ranking[ratings[pos].id] = rank
def special_compare_function(item):
return ordering.index(item.choice), ranking[item.id]
return special_compare_function
except: # Two possible reasons: no backup or user not in backup
pass
return default_compare_function
def load_from_algo(self, algo_name):
algo = get_algo_backup(algo_name)
dataset = get_dataset_backup(algo_name)
available_work_ids = list(
set(self.work_ids) & set(dataset.encode_work.keys()))
self.work_ids = np.array(available_work_ids)
self.vectors = algo.VT.T[dataset.encode_works(available_work_ids)]
self.preprocess()
def user_exists_in_backup(user, algo_name):
try:
dataset = get_dataset_backup(algo_name)
return user.id in dataset.encode_user
except FileNotFoundError:
return False