def test_custom_tf(self):
"""Test using a custom triples factories with HPO.
.. seealso:: https://github.com/pykeen/pykeen/issues/230
"""
tf = TriplesFactory.from_path(path=NATIONS_TRAIN_PATH)
training, testing, validation = tf.split([.8, .1, .1], random_state=0)
hpo_pipeline_result = hpo_pipeline(
training=training,
testing=testing,
validation=validation,
model='TransE',
n_trials=2,
training_kwargs=dict(num_epochs=2),
)
with tempfile.TemporaryDirectory() as directory:
hpo_pipeline_result.save_to_directory(directory)
def test_custom_tf_object(self):
"""Test using a custom triples factories with HPO.
.. seealso:: https://github.com/pykeen/pykeen/issues/230
"""
tf = TriplesFactory.from_path(path=NATIONS_TRAIN_PATH)
training, testing, validation = tf.split([.8, .1, .1], random_state=0)
hpo_pipeline_result = self._help_test_hpo(
study_name='HPO with custom triples factories',
training=training,
testing=testing,
validation=validation,
)
self.assertNotIn('dataset', hpo_pipeline_result.study.user_attrs)
# Since there's no source path information, these shouldn't be
# added, even if it might be possible to infer path information
# from the triples factories
self.assertNotIn('training', hpo_pipeline_result.study.user_attrs)
self.assertNotIn('testing', hpo_pipeline_result.study.user_attrs)
self.assertNotIn('validation', hpo_pipeline_result.study.user_attrs)
from pykeen.triples import TriplesFactory
from pykeen.evaluation import RankBasedEvaluator
from pykeen.pipeline import pipeline
import json
n_tokeep = 300
minimum = 500
tf = TriplesFactory.from_path(f'data/rare/rare_{minimum}_{n_tokeep}.csv')
training, testing = tf.split([.8, .2])
result_pipeline = pipeline(
training=training,
testing=testing,
model='RESCAL',
model_kwargs=dict(embedding_dim=300),
training_kwargs=dict( #sampler="schlichtkrull",
# checkpoint_name='RGCN_checkpointt.pt',
# checkpoint_frequency=5,
num_epochs=200 #,
#batch_size=128
),
evaluator=RankBasedEvaluator,
evaluator_kwargs=dict(ks=[50]))
result_pipeline.plot_losses()
result_pipeline.plot()