def test_from_splits(self):
data = Reader().read("./tests/data.txt")
try:
BaseMethod.from_splits(train_data=None, test_data=None)
except ValueError:
assert True
try:
BaseMethod.from_splits(train_data=data, test_data=None)
except ValueError:
assert True
try:
BaseMethod.from_splits(train_data=data,
test_data=[],
exclude_unknowns=True)
except ValueError:
assert True
bm = BaseMethod.from_splits(train_data=data[:-1], test_data=data[-1:])
self.assertEqual(bm.total_users, 10)
self.assertEqual(bm.total_items, 10)
bm = BaseMethod.from_splits(
train_data=data[:-1],
test_data=data[-1:],
val_data=[(data[0][0], data[1][1], 5.0)],
verbose=True,
)
self.assertEqual(bm.total_users, 10)
self.assertEqual(bm.total_items, 10)
def test_with_modalities(self):
data = Reader().read("./tests/data.txt")
sentiment_data = Reader().read("./tests/sentiment_data.txt",
fmt="UITup",
sep=",",
tup_sep=":")
bm = BaseMethod.from_splits(train_data=data[:-1], test_data=data[-1:])
self.assertIsNone(bm.user_text)
self.assertIsNone(bm.item_text)
self.assertIsNone(bm.user_image)
self.assertIsNone(bm.item_image)
self.assertIsNone(bm.user_graph)
self.assertIsNone(bm.item_graph)
self.assertIsNone(bm.sentiment)
bm.user_text = TextModality()
bm.item_image = ImageModality()
bm.sentiment = SentimentModality(data=sentiment_data)
bm._build_modalities()
try:
bm.user_text = ImageModality()
except ValueError:
assert True
try:
bm.item_text = ImageModality()
except ValueError:
assert True
try:
bm.user_image = TextModality()
except ValueError:
assert True
try:
bm.item_image = TextModality()
except ValueError:
assert True
try:
bm.user_graph = TextModality()
except ValueError:
assert True
try:
bm.item_graph = ImageModality()
except ValueError:
assert True
try:
bm.sentiment = TextModality()
except ValueError:
assert True
try:
bm.sentiment = ImageModality()
except ValueError:
assert True
def test_from_splits(self):
data = Reader().read('./tests/data.txt')
try:
BaseMethod.from_splits(train_data=None, test_data=None)
except ValueError:
assert True
try:
BaseMethod.from_splits(train_data=data, test_data=None)
except ValueError:
assert True
bm = BaseMethod.from_splits(train_data=data, test_data=data)
self.assertEqual(bm.total_users, 10)
self.assertEqual(bm.total_items, 10)
bm = BaseMethod.from_splits(train_data=data, test_data=data,
val_data=data, verbose=True)
self.assertEqual(bm.total_users, 10)
self.assertEqual(bm.total_items, 10)
def test_from_splits():
data = reader.read_uir('./tests/data.txt')
try:
BaseMethod.from_splits(train_data=None, test_data=None)
except ValueError:
assert True
try:
BaseMethod.from_splits(train_data=data, test_data=None)
except ValueError:
assert True
bm = BaseMethod.from_splits(train_data=data, test_data=data)
assert bm.total_users == 10
assert bm.total_items == 10
bm = BaseMethod.from_splits(train_data=data,
test_data=data,
val_data=data,
verbose=True)
assert bm.total_users == 10
assert bm.total_items == 10
def test_evaluate(self):
data = Reader().read('./tests/data.txt')
bm = BaseMethod.from_splits(train_data=data, test_data=data)
model = MF(k=1, max_iter=0)
result = bm.evaluate(model, metrics=[MAE()], user_based=False)
result.__str__()
args = parse_arguments()
os.makedirs(args.out, exist_ok=True)
reader = Reader()
train_data = reader.read(os.path.join(args.indir, "train.txt"), sep=",")
test_data = reader.read(os.path.join(args.indir, "test.txt"), sep=",")
sentiment = reader.read(os.path.join(args.indir, "sentiment.txt"),
fmt="UITup",
sep=",",
tup_sep=":")
md = SentimentModality(data=sentiment)
eval_method = BaseMethod.from_splits(
train_data=train_data,
test_data=test_data,
sentiment=md,
exclude_unknowns=True,
verbose=args.verbose,
)
mter = cornac.models.MTER(
n_user_factors=args.user_factors,
n_item_factors=args.item_factors,
n_aspect_factors=args.aspect_factors,
n_opinion_factors=args.opinion_factors,
n_bpr_samples=args.bpr_samples,
n_element_samples=args.element_samples,
lambda_reg=args.lambda_reg,
lambda_bpr=args.lambda_bpr,
max_iter=args.epoch,
lr=args.learning_rate,
from cornac.data import Reader
from cornac.eval_methods import BaseMethod
from cornac.models import MF
from cornac.metrics import MAE, RMSE
from cornac.utils import cache
# Download MovieLens 100K provided training and test splits
reader = Reader()
train_data = reader.read(
cache(url='http://files.grouplens.org/datasets/movielens/ml-100k/u1.base'))
test_data = reader.read(
cache(url='http://files.grouplens.org/datasets/movielens/ml-100k/u1.test'))
eval_method = BaseMethod.from_splits(train_data=train_data,
test_data=test_data,
exclude_unknowns=False,
verbose=True)
mf = MF(k=10,
max_iter=25,
learning_rate=0.01,
lambda_reg=0.02,
use_bias=True,
early_stop=True,
verbose=True)
# Evaluation
result = eval_method.evaluate(model=mf,
metrics=[MAE(), RMSE()],
user_based=True)
print(result)
random.shuffle(data)
train = data[math.ceil(0.2 * len(data)):]
test = data[:math.ceil(0.2 * len(data))]
holdout = cornac.data.Reader(bin_threshold=1.0).read(
fpath='./cs608_ip_probe_v2.csv', sep=",", fmt='UIR', skip_lines=1)
ratio_split = cornac.eval_methods.RatioSplit(data=train,
test_size=0.2,
rating_threshold=0.5,
seed=123)
eval_method = BaseMethod.from_splits(train_data=train,
test_data=test,
val_data=holdout,
exclude_unknowns=True,
verbose=True,
seed=123)
cv = cornac.eval_methods.cross_validation.CrossValidation(
data,
n_folds=3,
rating_threshold=1.0,
seed=123,
exclude_unknowns=True,
verbose=True)
# In[24]:
mae = cornac.metrics.MAE()
rmse = cornac.metrics.RMSE()
