def _loadRatings(self, sc, data_file):
data = sc.textFile(data_file)
data_dict, data_triplet = format_triplets(data)
data_triplet = by_max_count(data_triplet)
num_ratings = data_triplet.count()
num_users = data_triplet.map(lambda r: r[0]).distinct().count()
num_songs = data_triplet.map(lambda r: r[1]).distinct().count()
print(100 * '//')
print("Got {} ratings, with {} distinct songs and {} distinct users".format(num_ratings,
num_users,
num_songs))
print(100 * '//')
train_ratings = data_triplet.map(lambda l: Rating(l[0], l[1], l[2]))
return train_ratings
def get_ratings(sc, data_file):
data = sc.textFile(data_file)
# # Normalize start # #
print('Training normalization started')
data_dict, data_triplet = format_triplets(data)
data_triplet = by_max_count(data_triplet)
print(' Training normalization ended')
# # Normalize end # #
num_ratings = data_triplet.count()
num_users = data_triplet.map(lambda r: r[0]).distinct().count()
num_songs = data_triplet.map(lambda r: r[1]).distinct().count()
print(100 * '//')
print("Got {} ratings, with {} distinct songs and {} distinct users".format(num_ratings,
num_users,
num_songs))
print(100 * '//')
train_ratings = data_triplet.map(lambda l: Rating(l[0], l[1], l[2]))
return train_ratings
def get_ratings(sc, data_file):
data = sc.textFile(data_file)
# # Normalize start # #
print('Training normalization started')
data_dict, data_triplet = format_triplets(data)
data_triplet = by_max_count(data_triplet)
print(' Training normalization ended')
# # Normalize end # #
num_ratings = data_triplet.count()
num_users = data_triplet.map(lambda r: r[0]).distinct().count()
num_songs = data_triplet.map(lambda r: r[1]).distinct().count()
print(100 * '//')
print(
"Got {} ratings, with {} distinct songs and {} distinct users".format(
num_ratings, num_users, num_songs))
print(100 * '//')
train_ratings = data_triplet.map(lambda l: Rating(l[0], l[1], l[2]))
return train_ratings