for u in s2u_tr[s]:
s_set.add(u2i[u])
s2u_tr[s]=s_set
del u2i
print ('user to songs on %s'%f_triplets_tev)
u2s_v=MSD_util.user_to_songs(f_triplets_tev) #creates dict (user,songs which he has listened to) based on the evaluation set
print ('Creating predictor..')
_A = 0.15
_Q = 3
### calibrated
### pr=MSD_rec.PredSIc(s2u_tr, _A, _Q, "songs_scores.txt")
### uncalibrated song-based predictor
pr=MSD_rec.PredSI(s2u_tr, _A, _Q)
print ('Creating recommender..')
cp = MSD_rec.SReco(songs_ordered) # the input songs to the recommender is from the train_triplets.
cp.Add(pr)
cp.Gamma=[1.0] # the prob. on how to choose different predictors, here we only have one predictor so it's just [1.0]
r=cp.RecommendToUsers(users_v[user_min:user_max],u2s_v)
MSD_util.save_recommendations(r,"kaggle_songs.txt",osfile) #saves the output in terms of 500 song indices for each user seperated by space and then each user by \n
_Q = 3
### calibrated
### pr=MSD_rec.PredSIc(s2u_tr, _A, _Q, "songs_scores.txt")
### uncalibrated
pr = MSD_rec_shefali.PredSI(s2u_tr, _A, _Q)
pr2 = MSD_rec_shefali.PredSU(
s2u_tr, 0.3,
5) #with only this, 0.0 for 10 users in contrast to 0.33 in SI
print 'Creating recommender..'
cp = MSD_rec_shefali.SReco(songs_ordered)
cp.Add(pr)
cp.Add(pr2)
cp.Gamma = [1.0]
r = cp.RecommendToUsers(users_v[user_min:user_max], u2s_v)
#cp.Valid(uu, u2s_v, u2s_h, n_batch=10)
c = 0
for i, user in enumerate(users_v[user_min:user_max]):
c = c + metrics.apk(u2s_h[user], r[user])
pass
print i
t = c / (i + 1)
print t
MSD_util.save_recommendations(r, "kaggle_songs.txt", osfile)
print 'creating predictor...' _A = 0.15 _Q = 3 pr = MSD_rec.PredSI(s2u_tr,_A,_Q) print 'creating recommender..' cp = MSD_rec.SReco(songs_ordered) cp.Add(pr) cp.Gamma = [1.0] r = cp.RecommendToUsers(users_v[user_min:user_max],u2s_v) MSD_util.save_recommendations(r,"kaggle_songs.txt",osfile)
def main(argv):
if len(argv) < 3:
print(
"Nee more arguments, Example:MSD_subm_rec.py user_min user_max resultFile.txt"
)
user_min = 1
user_max = 110000
osfile = "resultfull.txt"
#exit()
else:
user_min = argv[0]
user_max = argv[1]
osfile = argv[2]
user_min = int(user_min)
user_max = int(user_max)
print("user_min: %d , user_max: %d" % (user_min, user_max))
sys.stdout.flush()
# TRIPLETS
f_triplets_tr = "train_triplets.txt"
f_triplets_tev = "kaggle_visible_evaluation_triplets.txt"
print('loading users in %s' % "kaggle_users.txt")
sys.stdout.flush()
users_v = list(MSD_util.load_users("kaggle_users.txt"))
print('default ordering by popularity')
sys.stdout.flush()
songs_ordered = MSD_util.sort_dict_dec(
MSD_util.song_to_count(f_triplets_tr))
print("loading unique users indexes")
uu = MSD_util.unique_users(f_triplets_tr)
u2i = {}
for i, u in enumerate(uu):
u2i[u] = i
print('song to users on %s' % f_triplets_tr)
s2u_tr = MSD_util.song_to_users(f_triplets_tr)
print("converting users to indexes")
for s in s2u_tr:
s_set = set()
for u in s2u_tr[s]:
s_set.add(u2i[u])
s2u_tr[s] = s_set
del u2i
print('user to songs on %s' % f_triplets_tev)
u2s_v = MSD_util.user_to_songs(f_triplets_tev)
print('Creating predictor..')
_A = 0.15
_Q = 3
### calibrated
### pr=MSD_rec.PredSIc(s2u_tr, _A, _Q, "songs_scores.txt")
### uncalibrated
pr = MSD_rec.PredSI(s2u_tr, _A, _Q)
print('Creating recommender..')
cp = MSD_rec.SReco(songs_ordered)
cp.Add(pr)
cp.Gamma = [1.0]
r = cp.RecommendToUsers(users_v[user_min:user_max], u2s_v)
MSD_util.save_recommendations(r, "kaggle_songs.txt", osfile)
