def test_from_feature(self):
# build a toy feature matrix
import numpy as np
F = np.zeros((4, 3))
F[0] = np.asarray([1, 0, 0])
F[1] = np.asarray([1, 1, 0])
F[2] = np.asarray([0, 0, 1])
F[3] = np.asarray([1, 1, 1])
# the expected output graph
s = set()
s.update([(0, 1, 1.0), \
(0, 3, 1.0), \
(1, 0, 1.0), \
(1, 2, 1.0), \
(1, 3, 1.0), \
(2, 1, 1.0), \
(2, 3, 1.0), \
(3, 0, 1.0), \
(3, 1, 1.0), \
(3, 2, 1.0)])
# build graph modality from features
gm = GraphModality.from_feature(features=F, k=2, verbose=False)
self.assertTrue(isinstance(gm, GraphModality))
self.assertTrue(not bool(gm.raw_data.difference(s)))
def test_build(self):
data = Reader().read('./tests/graph_data.txt', sep=' ')
gmd = GraphModality(data=data)
global_iid_map = OrderedDict()
for raw_iid, raw_jid, val in data:
global_iid_map.setdefault(raw_iid, len(global_iid_map))
gmd.build(id_map=global_iid_map)
self.assertEqual(len(gmd.map_rid), 7)
self.assertEqual(len(gmd.map_cid), 7)
self.assertEqual(len(gmd.val), 7)
self.assertEqual(gmd.matrix.shape, (7, 7))
try:
GraphModality().build()
except ValueError:
assert True
def test_get_node_degree(self):
data = Reader().read('./tests/graph_data.txt', sep=' ')
gmd = GraphModality(data=data)
global_iid_map = OrderedDict()
for raw_iid, raw_jid, val in data:
global_iid_map.setdefault(raw_iid, len(global_iid_map))
gmd.build(id_map=global_iid_map)
degree = gmd.get_node_degree()
self.assertEqual(degree.get(0)[0], 4)
self.assertEqual(degree.get(0)[1], 1)
self.assertEqual(degree.get(1)[0], 2)
self.assertEqual(degree.get(1)[1], 1)
self.assertEqual(degree.get(5)[0], 0)
self.assertEqual(degree.get(5)[1], 1)
degree = gmd.get_node_degree([0, 1], [0, 1])
self.assertEqual(degree.get(0)[0], 1)
self.assertEqual(degree.get(0)[1], 0)
self.assertEqual(degree.get(1)[0], 0)
self.assertEqual(degree.get(1)[1], 1)
def test_get_train_triplet(self):
data = Reader().read('./tests/graph_data.txt', sep=' ')
gmd = GraphModality(data=data)
global_iid_map = OrderedDict()
for raw_iid, raw_jid, val in data:
global_iid_map.setdefault(raw_iid, len(global_iid_map))
gmd.build(id_map=global_iid_map)
rid, cid, val = gmd.get_train_triplet([0, 1, 2], [0, 1, 2])
self.assertEqual(len(rid), 3)
self.assertEqual(len(cid), 3)
self.assertEqual(len(val), 3)
rid, cid, val = gmd.get_train_triplet([0, 2], [0, 1])
self.assertEqual(len(rid), 1)
self.assertEqual(len(cid), 1)
self.assertEqual(len(val), 1)
# limitations under the License.
# ============================================================================
"""Fit to and evaluate MCF on the Office Amazon dataset"""
from cornac.data import GraphModality
from cornac.eval_methods import RatioSplit
from cornac.experiment import Experiment
from cornac import metrics
from cornac.models import MCF
from cornac.datasets import amazon_office as office
# Load office ratings and item contexts, see C2PF paper for details
ratings = office.load_rating()
contexts = office.load_context()
item_graph_modality = GraphModality(data=contexts)
ratio_split = RatioSplit(data=ratings,
test_size=0.2,
rating_threshold=3.5,
exclude_unknowns=True,
verbose=True,
item_graph=item_graph_modality)
mcf = MCF(k=10, max_iter=40, learning_rate=0.001, verbose=True)
# Evaluation metrics
ndcg = metrics.NDCG(k=-1)
rmse = metrics.RMSE()
rec = metrics.Recall(k=20)
pre = metrics.Precision(k=20)
from cornac.data import GraphModality
from cornac.eval_methods import RatioSplit
from cornac.experiment import Experiment
from cornac import metrics
from cornac.models import CVAECF
from cornac.datasets import filmtrust
# In addition to learning from preference data, CVAECF further leverages users' auxiliary data (social network in this example).
# The necessary data can be loaded as follows
ratings = filmtrust.load_feedback()
trust = filmtrust.load_trust()
# Instantiate a GraphModality, it makes it convenient to work with graph (network) auxiliary information
# For more details, please refer to the tutorial on how to work with auxiliary data
user_graph_modality = GraphModality(data=trust)
# Define an evaluation method to split feedback into train and test sets
ratio_split = RatioSplit(
data=ratings,
test_size=0.2,
rating_threshold=2.5,
exclude_unknowns=True,
verbose=True,
user_graph=user_graph_modality,
seed=123,
)
# Instantiate CVAECF model
cvaecf = CVAECF(z_dim=20,
h_dim=20,
# distributed under the License is distributed on an "AS IS" BASIS,
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
# See the License for the specific language governing permissions and
# limitations under the License.
# ============================================================================
"""Example for Social Bayesian Personalized Ranking with Epinions dataset"""
import cornac
from cornac.data import Reader, GraphModality
from cornac.datasets import epinions
from cornac.eval_methods import RatioSplit
ratio_split = RatioSplit(data=epinions.load_data(Reader(bin_threshold=4.0)),
test_size=0.1,
rating_threshold=0.5,
exclude_unknowns=True,
verbose=True,
user_graph=GraphModality(data=epinions.load_trust()))
sbpr = cornac.models.SBPR(k=10,
max_iter=50,
learning_rate=0.001,
lambda_u=0.015,
lambda_v=0.025,
lambda_b=0.01,
verbose=True)
rec_10 = cornac.metrics.Recall(k=10)
cornac.Experiment(eval_method=ratio_split, models=[sbpr],
metrics=[rec_10]).run()
from cornac.data import GraphModality
from cornac.eval_methods import RatioSplit
from cornac.experiment import Experiment
from cornac import metrics
from cornac.models import MCF
from cornac.datasets import amazon_office as office
# MCF leverages relationships among items, it jointly factorizes the user-item and item-item matrices
# The necessary data can be loaded as follows
ratings = office.load_feedback()
item_net = office.load_graph()
# Instantiate a GraphModality, it make it convenient to work with graph (network) auxiliary information
# For more details, please refer to the tutorial on how to work with auxiliary data
item_graph_modality = GraphModality(data=item_net)
# Define an evaluation method to split feedback into train and test sets
ratio_split = RatioSplit(data=ratings,
test_size=0.2, rating_threshold=3.5,
exclude_unknowns=True, verbose=True,
item_graph=item_graph_modality)
# Instantiate MCF
mcf = MCF(k=10, max_iter=40, learning_rate=0.001, verbose=True)
# Evaluation metrics
ndcg = metrics.NDCG(k=-1)
rmse = metrics.RMSE()
rec = metrics.Recall(k=20)
pre = metrics.Precision(k=20)
def test_init(self):
data = Reader().read('./tests/graph_data.txt', sep=' ')
gmd = GraphModality(data=data)
self.assertEqual(len(gmd.raw_data), 7)