def main():
topics = int(sys.argv[1])
total_iters = int(sys.argv[2])
burn_in = float(sys.argv[3])
thinning = int(sys.argv[4])
ratings, _ = get_split_review_mats()
bpf = BayesianPoissonFactorization(0.3, 0.3, 1.0, 0.3, 0.3, 1.0, topics, ratings)
bpf.sample(total_iters, burn_in, thinning)
def main():
topics = int(sys.argv[1])
total_iters = int(sys.argv[2])
burn_in = float(sys.argv[3])
thinning = int(sys.argv[4])
ratings, _ = get_split_review_mats()
bpf = BayesianPoissonFactorization(0.3, 0.3, 1.0, 0.3, 0.3, 1.0, topics,
ratings)
bpf.sample(total_iters, burn_in, thinning)
def __init__(self, numTopics, alpha, beta, gamma):
# Setup logger
self.log = logging.getLogger("Gibbs")
self.log.setLevel(logging.DEBUG)
formatter = logging.Formatter("%(asctime)s %(message)s",
datefmt="%m/%d/%Y %I:%M:%S %p")
fh = logging.handlers.TimedRotatingFileHandler("logs/gibbs.log",
when="D",
interval=1,
backupCount=10)
ch = logging.StreamHandler()
fh.setFormatter(formatter)
ch.setFormatter(formatter)
self.log.addHandler(fh)
self.log.addHandler(ch)
self.numTopics = numTopics
self.alpha = alpha
self.beta = beta
self.gamma = gamma
self.info = getMeta()
self.user_movies, _ = get_split_review_mats()
user_indices, movie_indices = self.user_movies.nonzero()
self.user_movie_indices = zip(user_indices, movie_indices)
self.CountMT = np.zeros((self.info["movies"], numTopics), dtype=np.int)
self.CountRUT = np.zeros((6, self.info["users"], numTopics),
dtype=np.int) # ratings 1-5 and 0
self.CountUT = np.zeros((self.info["users"], numTopics), dtype=np.int)
self.topic_assignments = np.zeros(
(self.info["users"], self.info["movies"]), dtype=np.int)
# Normalization factors
self.CountT = np.zeros(numTopics, dtype=np.int)
self.CountU = np.zeros(self.info["users"], dtype=np.int)
self.CountRU = np.zeros((6, self.info["users"]), dtype=np.int)
for userid, movieid in self.user_movie_indices:
topic = randint(0, numTopics - 1)
self.CountMT[movieid, topic] += 1
rating = self.user_movies[userid, movieid]
self.CountRUT[rating, userid, topic] += 1
self.CountUT[userid, topic] += 1
self.topic_assignments[userid, movieid] = topic
self.CountT[topic] += 1
self.CountU[userid] += 1
self.CountRU[rating, userid] += 1
def __init__(self, numTopics, alpha, beta, gamma):
# Setup logger
self.log = logging.getLogger("Gibbs")
self.log.setLevel(logging.DEBUG)
formatter = logging.Formatter("%(asctime)s %(message)s",
datefmt="%m/%d/%Y %I:%M:%S %p")
fh = logging.handlers.TimedRotatingFileHandler("logs/gibbs.log",
when="D",
interval=1,
backupCount=10)
ch = logging.StreamHandler()
fh.setFormatter(formatter)
ch.setFormatter(formatter)
self.log.addHandler(fh)
self.log.addHandler(ch)
self.numTopics = numTopics
self.alpha = alpha
self.beta = beta
self.gamma = gamma
self.info = getMeta()
self.user_movies, _ = get_split_review_mats()
user_indices, movie_indices = self.user_movies.nonzero()
self.user_movie_indices = zip(user_indices, movie_indices)
self.CountMT = np.zeros((self.info["movies"], numTopics), dtype=np.int)
self.CountRUT = np.zeros((6, self.info["users"], numTopics), dtype=np.int) # ratings 1-5 and 0
self.CountUT = np.zeros((self.info["users"], numTopics), dtype=np.int)
self.topic_assignments = np.zeros((self.info["users"], self.info["movies"]), dtype=np.int)
# Normalization factors
self.CountT = np.zeros(numTopics, dtype=np.int)
self.CountU = np.zeros(self.info["users"], dtype=np.int)
self.CountRU = np.zeros((6, self.info["users"]), dtype=np.int)
for userid, movieid in self.user_movie_indices:
topic = randint(0, numTopics - 1)
self.CountMT[movieid, topic] += 1
rating = self.user_movies[userid, movieid]
self.CountRUT[rating, userid, topic] += 1
self.CountUT[userid, topic] += 1
self.topic_assignments[userid, movieid] = topic
self.CountT[topic] += 1
self.CountU[userid] += 1
self.CountRU[rating, userid] += 1
def test_iid_users():
train, test = get_split_review_mats()
avg_ratings = train.sum(axis=0) / (train != 0).sum(axis=0).astype(np.float)
rmse = 0.0
count = 0
for user, movie in izip(*test.nonzero()):
true_rating = test[user, movie]
predicted = avg_ratings[movie]
if np.isnan(predicted):
# The movie wasn't rated by any users in the training data set
continue
rmse += (predicted - true_rating) ** 2
count += 1
return math.sqrt(rmse / count)
def test_iid_users():
train, test = get_split_review_mats()
avg_ratings = train.sum(axis=0) / (train != 0).sum(axis=0).astype(np.float)
rmse = 0.0
count = 0
for user, movie in izip(*test.nonzero()):
true_rating = test[user, movie]
predicted = avg_ratings[movie]
if np.isnan(predicted):
# The movie wasn't rated by any users in the training data set
continue
rmse += (predicted - true_rating)**2
count += 1
return math.sqrt(rmse / count)
def top_recommendations_iid():
info = getMeta()
train, reviews = get_split_review_mats()
avg_ratings = train.sum(axis=0) / (train != 0).sum(axis=0).astype(np.float)
top_movies = sorted(((movie, rating) for movie, rating in enumerate(avg_ratings)),
key=lambda x: x[1])
top_movies = set(movie for movie, rating in top_movies[-1000:])
precision = 0.0
num_users = 0
for user in xrange(info["users"]):
movies = reviews[user, :].nonzero()[0]
user_precision = 0.0
for movie in movies:
if movie in top_movies:
user_precision += 1
if len(movies) > 0:
num_users += 1
precision += (user_precision / len(movies))
return precision / num_users
def top_recommendations_iid():
info = getMeta()
train, reviews = get_split_review_mats()
avg_ratings = train.sum(axis=0) / (train != 0).sum(axis=0).astype(np.float)
top_movies = sorted(
((movie, rating) for movie, rating in enumerate(avg_ratings)),
key=lambda x: x[1])
top_movies = set(movie for movie, rating in top_movies[-1000:])
precision = 0.0
num_users = 0
for user in xrange(info["users"]):
movies = reviews[user, :].nonzero()[0]
user_precision = 0.0
for movie in movies:
if movie in top_movies:
user_precision += 1
if len(movies) > 0:
num_users += 1
precision += (user_precision / len(movies))
return precision / num_users