# 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 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,
def test_load_plot(self):
# only run data download tests 20% of the time to speed up frequent testing
random.seed(time.time())
if random.random() > 0.8:
plots, ids = movielens.load_plot()
self.assertEqual(len(ids), 10076)