# 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_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)
# Instantiate and then run an experiment.
exp = cornac.Experiment(eval_method=ratio_split,
models=[ibpr],
# 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 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
plots, movie_ids = movielens.load_plot()
ml_1m = movielens.load_1m(reader=Reader(item_set=movie_ids))
# build text module
item_text_modality = TextModality(corpus=plots,
ids=movie_ids,
tokenizer=BaseTokenizer(
sep='\t', stop_words='english'),
max_vocab=5000,
max_doc_freq=0.5)
ratio_split = RatioSplit(data=ml_1m,
test_size=0.2,
exclude_unknowns=True,
item_text=item_text_modality,
verbose=True,
seed=123)
# -*- coding: utf-8 -*-
"""
Example for Matrix Factorization with biases
@author: Quoc-Tuan Truong <*****@*****.**>
"""
import cornac
from cornac.datasets import movielens
from cornac.eval_methods import RatioSplit
ratio_split = RatioSplit(data=movielens.load_1m(),
test_size=0.2,
exclude_unknowns=False,
verbose=True)
mf = cornac.models.MF(k=10, max_iter=25, learning_rate=0.01, lambda_reg=0.02,
use_bias=True, early_stop=True, verbose=True)
mae = cornac.metrics.MAE()
rmse = cornac.metrics.RMSE()
exp = cornac.Experiment(eval_method=ratio_split,
models=[mf],
metrics=[mae, rmse],
user_based=True)
exp.run()
def test_movielens_1m():
# only run data download tests 20% of the time to speed up frequent testing
random.seed(time.time())
if random.random() > 0.8:
ml_1m = movielens.load_1m()
assert len(ml_1m) == 1000209
def test_load_1m(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_1m = movielens.load_1m()
self.assertEqual(len(ml_1m), 1000209)