def test_populate_cache(self, run_mock, flow_mock, dataset_mock,
task_mock):
openml.populate_cache(task_ids=[1, 2],
dataset_ids=[3, 4],
flow_ids=[5, 6],
run_ids=[7, 8])
self.assertEqual(run_mock.call_count, 2)
for argument, fixture in six.moves.zip(run_mock.call_args_list,
[(7, ), (8, )]):
self.assertEqual(argument[0], fixture)
self.assertEqual(flow_mock.call_count, 2)
for argument, fixture in six.moves.zip(flow_mock.call_args_list,
[(5, ), (6, )]):
self.assertEqual(argument[0], fixture)
self.assertEqual(dataset_mock.call_count, 2)
for argument, fixture in six.moves.zip(dataset_mock.call_args_list,
[(3, ), (4, )]):
self.assertEqual(argument[0], fixture)
self.assertEqual(task_mock.call_count, 2)
for argument, fixture in six.moves.zip(task_mock.call_args_list,
[(1, ), (2, )]):
self.assertEqual(argument[0], fixture)
def callattr_ahead_of_alltests(request):
"""
This procedure will run at the start of the pytest session.
It will prefetch several task that are going to be used by
the testing face, and it does so in a robust way, until the openml
API provides the desired resources
"""
tasks_used = [
146818, # Australian
2295, # cholesterol
2075, # abalone
2071, # adult
3, # kr-vs-kp
9981, # cnae-9
146821, # car
146822, # Segment
2, # anneal
53, # vehicle
5136, # tecator
4871, # sensory
4857, # boston
3916, # kc1
]
# Populate the cache
# This will make the test fail immediately rather than
# Waiting for a openml fetch timeout
openml.populate_cache(task_ids=tasks_used)
# Also the bunch
for task in tasks_used:
fetch_openml(data_id=openml.tasks.get_task(task).dataset_id,
return_X_y=True)
return
def test_populate_cache(self, run_mock, flow_mock, dataset_mock, task_mock):
openml.populate_cache(task_ids=[1, 2], dataset_ids=[3, 4],
flow_ids=[5, 6], run_ids=[7, 8])
self.assertEqual(run_mock.call_count, 2)
for argument, fixture in six.moves.zip(run_mock.call_args_list, [(7,), (8,)]):
self.assertEqual(argument[0], fixture)
self.assertEqual(flow_mock.call_count, 2)
for argument, fixture in six.moves.zip(flow_mock.call_args_list, [(5,), (6,)]):
self.assertEqual(argument[0], fixture)
self.assertEqual(dataset_mock.call_count, 2)
for argument, fixture in six.moves.zip(dataset_mock.call_args_list, [(3,), (4,)]):
self.assertEqual(argument[0], fixture)
self.assertEqual(task_mock.call_count, 2)
for argument, fixture in six.moves.zip(task_mock.call_args_list, [(1,), (2,)]):
self.assertEqual(argument[0], fixture)
import openml
tasks = list(openml.tasks.list_tasks(tag='study_14').keys())
openml.populate_cache(task_ids=tasks)
print('Using %d tasks', len(tasks))
