# http://www.apache.org/licenses/LICENSE-2.0
#
# Unless required by applicable law or agreed to in writing, software
# 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 Variational Autoencoder for Collaborative Filtering, using the CiteULike dataset"""
import cornac
from cornac.datasets import citeulike
from cornac.eval_methods import RatioSplit
# Load user-item feedback
data = citeulike.load_feedback()
# Instantiate an evaluation method to split data into train and test sets.
ratio_split = RatioSplit(
data=data,
test_size=0.2,
exclude_unknowns=True,
verbose=True,
seed=123,
rating_threshold=0.5,
)
# Instantiate the VAECF model
vaecf = cornac.models.VAECF(
k=10,
autoencoder_structure=[20],
# See the License for the specific language governing permissions and
# limitations under the License.
# ============================================================================
"""Example for Collaborative Deep Ranking (CDR)"""
import cornac
from cornac.data import Reader
from cornac.datasets import citeulike
from cornac.eval_methods import RatioSplit
from cornac.data import TextModality
from cornac.data.text import BaseTokenizer
# CDR composes an autoencoder with a ranking collaborative model to represent item texts and user-item interactions
# The necessary data can be loaded as follows
docs, item_ids = citeulike.load_text()
feedback = citeulike.load_feedback(reader=Reader(item_set=item_ids))
# Instantiate a TextModality, it makes it convenient to work with text auxiliary information
# For more details, please refer to the tutorial on how to work with auxiliary data
item_text_modality = TextModality(
corpus=docs,
ids=item_ids,
tokenizer=BaseTokenizer(stop_words="english"),
max_vocab=8000,
max_doc_freq=0.5,
)
# Define an evaluation method to split feedback into train and test sets
ratio_split = RatioSplit(
data=feedback,
test_size=0.2,