def test_local_folder(self, _, compute_job_raises):
channel_name = 'dummy_channel'
compute_plan_tag = 'cp1'
compute_plan_key = str(uuid.uuid4())
file = 'model.txt'
initial_value = 'initial value'
updated_value = 'updated value'
subtuple = {
'key': str(uuid.uuid4()),
'compute_plan_key': compute_plan_key,
'rank': 1,
'algo': {
'key': 'some key'
}
}
# Write an initial value into the compute plan local folder
cp_local_folder = get_cp_local_folder(compute_plan_key)
os.makedirs(cp_local_folder, exist_ok=True)
with open(os.path.join(cp_local_folder, file), 'w') as x:
x.write(initial_value)
# Call `do_task`, which will:
# 1. write a new value to the subtuple local folder
# 2. and then:
# - complete successfully (compute_job_raises == False)
# - or raise an exception (compute_job_raises == True)
with mock.patch('substrapp.ledger.api.query_ledger') as mquery_ledger,\
mock.patch('substrapp.tasks.tasks.generate_command'),\
mock.patch('substrapp.tasks.tasks.save_models'),\
mock.patch('substrapp.tasks.tasks.compute_job') as mcompute_job:
def compute_job(*args, **kwargs):
for vol in kwargs['volumes']:
if vol.endswith('/local'):
with open(os.path.join(vol, file), 'w') as x:
x.write(updated_value)
if compute_job_raises:
raise Exception('Boom!')
mquery_ledger.return_value = {'tag': compute_plan_tag}
mcompute_job.side_effect = compute_job
try:
build_subtuple_folders(subtuple)
do_task(channel_name, subtuple, TRAINTUPLE_TYPE)
except Exception:
if compute_job_raises:
# exception expected
pass
# Check the compute plan local folder value is correct:
# - If do_task did raise an exception then the local value should be unchanged
# - If do_task did not raise an exception then the local value should be updated
with open(os.path.join(cp_local_folder, file), 'r') as x:
content = x.read()
self.assertEqual(
content, initial_value if compute_job_raises else updated_value)
def test_prepare_data_sample_zip_fail(self):
data_sample = DataSample(key=uuid.uuid4(),
path=self.data_sample_filename)
data_sample.save()
subtuple = {'key': 'bar', 'dataset': {'data_sample_keys': ['fake_pk']}}
subtuple2 = {
'key': 'bar',
'dataset': {
'data_sample_keys': [data_sample.key]
}
}
with mock.patch('substrapp.models.DataSample.objects.get') as mget:
mget.return_value = data_sample
subtuple_directory = build_subtuple_folders(subtuple)
with self.assertRaises(Exception):
prepare_data_sample(subtuple_directory, subtuple)
with self.assertRaises(Exception):
prepare_data_sample('/fake/directory/failure', subtuple2)
def test_put_data_tar(self):
checksum, datasamples_path_from_file = store_datasamples_archive(
self.data_sample_tar)
key = str(uuid.uuid4())
data_sample = DataSample(key=key,
path=datasamples_path_from_file,
checksum=checksum)
data_sample.save()
subtuple = {
'key': 'bar',
'dataset': {
'data_sample_keys': [str(data_sample.key)]
}
}
with mock.patch('substrapp.models.DataSample.objects.get') as mget:
mget.return_value = data_sample
subtuple_directory = build_subtuple_folders(subtuple)
prepare_data_sample(subtuple_directory, subtuple)
# check folder has been correctly renamed with key of directory containing uncompressed data_sample
self.assertFalse(
os.path.exists(os.path.join(MEDIA_ROOT, 'datasamples', 'foo')))
self.assertTrue(
os.path.exists(os.path.join(MEDIA_ROOT, 'datasamples', key)))
# check subtuple folder has been created and sym links exists
self.assertTrue(
os.path.exists(
os.path.join(MEDIA_ROOT, 'subtuple/bar/data',
data_sample.key)))
self.assertTrue(
os.path.islink(
os.path.join(MEDIA_ROOT, 'subtuple/bar/data',
data_sample.key)))
self.assertTrue(
os.path.exists(
os.path.join(MEDIA_ROOT, 'subtuple/bar/data',
data_sample.key, 'LABEL_0024900.csv')))
self.assertTrue(
os.path.exists(
os.path.join(MEDIA_ROOT, 'subtuple/bar/data',
data_sample.key, 'IMG_0024900.jpg')))
def test_compute_task(self):
subtuple_key = 'test_owkin'
subtuple = {'key': subtuple_key, 'inModels': None}
subtuple_directory = build_subtuple_folders(subtuple)
with mock.patch(
'substrapp.tasks.tasks.log_start_tuple') as mlog_start_tuple:
mlog_start_tuple.return_value = 'data', 200
for name in ['opener', 'metrics']:
with open(
os.path.join(subtuple_directory, f'{name}/{name}.py'),
'w') as f:
f.write('Hello World')
perf = 0.3141592
with open(os.path.join(subtuple_directory, 'pred/perf.json'),
'w') as f:
f.write(f'{{"all": {perf}}}')
with open(os.path.join(subtuple_directory, 'model/model'),
'w') as f:
f.write("MODEL")
with mock.patch('substrapp.tasks.tasks.compute_docker') as mcompute_docker, \
mock.patch('substrapp.tasks.tasks.do_task') as mdo_task,\
mock.patch('substrapp.tasks.tasks.prepare_materials') as mprepare_materials, \
mock.patch('substrapp.tasks.tasks.log_success_tuple') as mlog_success_tuple:
mcompute_docker.return_value = 'DONE'
mprepare_materials.return_value = 'DONE'
mdo_task.return_value = 'DONE'
mlog_success_tuple.return_value = 'data', 201
compute_task('traintuple', subtuple, None)
mlog_success_tuple.return_value = 'data', 404
compute_task('traintuple', subtuple, None)
with mock.patch('substrapp.tasks.tasks.log_fail_tuple'
) as mlog_fail_tuple:
mdo_task.side_effect = Exception("Test")
mlog_fail_tuple.return_value = 'data', 404
with self.assertRaises(Exception) as exc:
compute_task('traintuple', subtuple, None)
self.assertEqual(str(exc.exception), "Test")
def test_build_subtuple_folders(self):
with mock.patch('substrapp.tasks.tasks.getattr') as getattr:
getattr.return_value = self.subtuple_path
subtuple_key = 'test1234'
subtuple = {'key': subtuple_key}
subtuple_directory = build_subtuple_folders(subtuple)
self.assertTrue(os.path.exists(subtuple_directory))
self.assertEqual(
os.path.join(self.subtuple_path,
f'subtuple/{subtuple["key"]}'),
subtuple_directory)
for root, dirs, files in os.walk(subtuple_directory):
nb_subfolders = len(dirs)
self.assertTrue(5, nb_subfolders)
def test_do_task(self):
class FakeSettings(object):
def __init__(self):
self.MEDIA_ROOT = MEDIA_ROOT
subtuple_key = 'test_owkin'
subtuple = {
'key': subtuple_key,
'in_models': None,
'algo': {
'key': 'mykey',
'checksum': 'myhash'
},
'dataset': {
'data_sample_keys': []
},
}
subtuple_directory = build_subtuple_folders(subtuple)
with mock.patch('substrapp.tasks.tasks.settings') as msettings, \
mock.patch('substrapp.tasks.tasks.getattr') as mgetattr:
msettings.return_value = FakeSettings()
mgetattr.return_value = self.subtuple_path
for name in ['opener', 'metrics']:
with open(
os.path.join(subtuple_directory, f'{name}/{name}.py'),
'w') as f:
f.write('Hello World')
perf = 0.3141592
with open(os.path.join(subtuple_directory, 'pred/perf.json'),
'w') as f:
f.write(f'{{"all": {perf}}}')
with open(os.path.join(subtuple_directory, 'output_model/model'),
'w') as f:
f.write("MODEL")
with mock.patch(
'substrapp.tasks.tasks.compute_job') as mcompute_job:
mcompute_job.return_value = 'DONE'
do_task(CHANNEL, subtuple, 'traintuple')
def test_prepare_data_sample_zip(self):
dir_pkhash, datasamples_path_from_file = store_datasamples_archive(
self.data_sample)
data_sample = DataSample(pkhash=dir_pkhash,
path=datasamples_path_from_file)
data_sample.save()
subtuple = {'key': 'bar', 'dataset': {'keys': [data_sample.pk]}}
with mock.patch('substrapp.models.DataSample.objects.get') as mget:
mget.return_value = data_sample
subtuple_directory = build_subtuple_folders(subtuple)
prepare_data_sample(subtuple_directory, subtuple)
# check folder has been correctly renamed with pk of directory containing uncompressed data sample
self.assertFalse(
os.path.exists(os.path.join(MEDIA_ROOT, 'datasamples', 'foo')))
self.assertTrue(
os.path.exists(
os.path.join(MEDIA_ROOT, 'datasamples', dir_pkhash)))
# check subtuple folder has been created and sym links exists
self.assertTrue(
os.path.exists(
os.path.join(MEDIA_ROOT, 'subtuple/bar/data',
data_sample.pk)))
self.assertTrue(
os.path.islink(
os.path.join(MEDIA_ROOT, 'subtuple/bar/data',
data_sample.pk)))
self.assertTrue(
os.path.exists(
os.path.join(MEDIA_ROOT, 'subtuple/bar/data',
data_sample.pk, 'LABEL_0024900.csv')))
self.assertTrue(
os.path.exists(
os.path.join(MEDIA_ROOT, 'subtuple/bar/data',
data_sample.pk, 'IMG_0024900.jpg')))
def test_do_task(self):
class FakeSettings(object):
def __init__(self):
self.LEDGER = {
'signcert': 'signcert',
'org': 'owkin',
'peer': 'peer'
}
self.MEDIA_ROOT = MEDIA_ROOT
subtuple_key = 'test_owkin'
subtuple = {'key': subtuple_key, 'inModels': None}
subtuple_directory = build_subtuple_folders(subtuple)
with mock.patch('substrapp.tasks.tasks.settings') as msettings, \
mock.patch('substrapp.tasks.tasks.getattr') as mgetattr:
msettings.return_value = FakeSettings()
mgetattr.return_value = self.subtuple_path
for name in ['opener', 'metrics']:
with open(
os.path.join(subtuple_directory, f'{name}/{name}.py'),
'w') as f:
f.write('Hello World')
perf = 0.3141592
with open(os.path.join(subtuple_directory, 'pred/perf.json'),
'w') as f:
f.write(f'{{"all": {perf}}}')
with open(os.path.join(subtuple_directory, 'model/model'),
'w') as f:
f.write("MODEL")
with mock.patch(
'substrapp.tasks.tasks.compute_docker') as mcompute_docker:
mcompute_docker.return_value = 'DONE'
do_task(subtuple, 'traintuple')
