def test_load_feedback(self):
# only run data download tests 20% of the time to speed up frequent testing
random.seed(time.time())
if random.random() > 0.8:
ml_100k = movielens.load_feedback()
self.assertEqual(len(ml_100k), 100000)
if random.random() > 0.8:
ml_1m = movielens.load_feedback(variant='1M')
self.assertEqual(len(ml_1m), 1000209)
#
# 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 to run Probabilistic Matrix Factorization (PMF) model with Ratio Split evaluation strategy"""
import cornac
from cornac.datasets import movielens
from cornac.eval_methods import RatioSplit
from cornac.models import PMF
# Load the MovieLens 100K dataset
ml_100k = movielens.load_feedback()
# Instantiate an evaluation method.
ratio_split = RatioSplit(data=ml_100k,
test_size=0.2,
rating_threshold=4.0,
exclude_unknowns=False)
# Instantiate a PMF recommender model.
pmf = PMF(k=10, max_iter=100, learning_rate=0.001, lambda_reg=0.001)
# Instantiate evaluation metrics.
mae = cornac.metrics.MAE()
rmse = cornac.metrics.RMSE()
rec_20 = cornac.metrics.Recall(k=20)
pre_20 = cornac.metrics.Precision(k=20)
#
# 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 Matrix Factorization with biases"""
import cornac
from cornac.datasets import movielens
from cornac.eval_methods import RatioSplit
# Load MovieLens 1M ratings
ml_1m = movielens.load_feedback(variant="1M")
# Define an evaluation method to split feedback into train and test sets
ratio_split = RatioSplit(
data=ml_1m, test_size=0.2, exclude_unknowns=False, verbose=True
)
# Instantiate the global average baseline and MF model
global_avg = cornac.models.GlobalAvg()
mf = cornac.models.MF(
k=10,
max_iter=25,
learning_rate=0.01,
lambda_reg=0.02,
use_bias=True,
early_stop=True,
# 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 SKMeans vs BPR on MovieLens data"""
import cornac
from cornac.datasets import movielens
from cornac.eval_methods import RatioSplit
# Load user-item feedback
data = movielens.load_feedback(variant="100K")
# 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 models
skm = cornac.models.SKMeans(k=5, max_iter=100, tol=1e-10, seed=123)
bpr = cornac.models.BPR(k=5,
# See the License for the specific language governing permissions and
# limitations under the License.
# ============================================================================
"""Example for Hidden Factors as Topics (HFT) with Movilen 1M dataset """
import cornac
from cornac.data import Reader
from cornac.datasets import movielens
from cornac.eval_methods import RatioSplit
from cornac.data import TextModality
from cornac.data.text import BaseTokenizer
# HFT jointly models the user-item preferences and item texts (e.g., product reviews) with shared item factors
# Below we fit HFT to the MovieLens 1M dataset. We need both the ratings and movie plots information
plots, movie_ids = movielens.load_plot()
ml_1m = movielens.load_feedback(variant="1M",
reader=Reader(item_set=movie_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=plots,
ids=movie_ids,
tokenizer=BaseTokenizer(sep="\t", stop_words="english"),
max_vocab=5000,
max_doc_freq=0.5,
)
# Define an evaluation method to split feedback into train and test sets
ratio_split = RatioSplit(
data=ml_1m,
test_size=0.2,
# 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 hyper-parameter searching with Matrix Factorization"""
import numpy as np
import cornac
from cornac.datasets import movielens
from cornac.eval_methods import RatioSplit
from cornac.hyperopt import Discrete, Continuous
from cornac.hyperopt import GridSearch, RandomSearch
# Load MovieLens 100K ratings
ml_100k = movielens.load_feedback(variant="100K")
# Define an evaluation method to split feedback into train, validation and test sets
ratio_split = RatioSplit(data=ml_100k,
test_size=0.1,
val_size=0.1,
verbose=True)
# Instantiate MAE and RMSE for evaluation
mae = cornac.metrics.MAE()
rmse = cornac.metrics.RMSE()
# Define a base MF model with fixed hyper-parameters
mf = cornac.models.MF(max_iter=20,
learning_rate=0.01,
early_stop=True,
# 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.
# ============================================================================
import cornac
from cornac.datasets import movielens
from cornac.eval_methods import RatioSplit
from cornac.models import IBPR
# Load the MovieLens 1M dataset
ml_1m = movielens.load_feedback(variant='1M')
# Instantiate an evaluation method.
ratio_split = RatioSplit(data=ml_1m,
test_size=0.2,
rating_threshold=1.0,
exclude_unknowns=True,
verbose=True)
# Instantiate a IBPR recommender model.
ibpr = IBPR(k=10, init_params={'U': None, 'V': None}, verbose=True)
# Instantiate evaluation metrics.
rec_20 = cornac.metrics.Recall(k=20)
pre_20 = cornac.metrics.Precision(k=20)