def run_algorithm(data, parameters):
if MODE == "SUBMIT":
recommender = GDannunzioEnsemble(data["URM_complete"], data["URM_test"], icm=data["ICM"], parameters=parameters)
else:
recommender = GDannunzioEnsemble(data["URM_train"], data["URM_test"], icm=data["ICM"], parameters=parameters)
recommender.fit()
target = pd.read_csv('../data/target_playlists.csv', index_col=False)
target = target['playlist_id']
recommended = recommender.recommend_batch(user_list=target, combiner=linearCombiner())
playlists = recommended[:, 0]
recommended = np.delete(recommended, 0, 1)
i = 0
res_fin = []
for j in recommended:
res = ''
for k in range(0, len(j)):
res = res + '{0} '.format(j[k])
res_fin.append(res)
i = i + 1
d = {'playlist_id': playlists, 'track_ids': res_fin}
df = pd.DataFrame(data=d, index=None)
distrib_data = recommender.get_component_data()
del recommender
gc.collect()
return [recommended, df, distrib_data]
def recommend(self, user_id, combiner, at=10):
user_profile = self.train[user_id, :]
bm_list = self.bm_recommender.recommend(user_id, linearCombiner(), at=40)
item_bpr_r = preprocessing.normalize(user_profile.dot(self.item_bpr_w).toarray(), norm='l2').ravel()
bpr_scores = [
[item_bpr_r, self.ensemble_weights["ITEM_BPR"], "ITEM_BPR"]
]
for r in bpr_scores:
self.filter_seen(user_id, r[0])
bpr_list = (linearCombiner()).combine(bpr_scores, at=40)
lists = [
[bm_list],
[bpr_list]
]
return (ProbabilisticCombiner()).combine(scores=lists, alpha=self.ensemble_weights["ALPHA"], at=at)