def __init__(self, sm_config, analysis_version, database):
reports_path = Path(proj_root()) / 'tests/reports'
timestamp = datetime.now().replace(microsecond=0).isoformat().replace(
':', '-')
suffix = f'{database}-v{analysis_version}'
self.sm_config = sm_config
self.db = DB()
self.ds_id = '2000-01-01_00h00m01s'
self.ref_results_path = reports_path / f'spheroid-{suffix}.csv'
self.output_results_path = reports_path / f'test-{suffix}-{timestamp}.csv'
self.ds_name = 'sci_test_spheroid_untreated'
self.ds_data_path = join(self.sm_config['fs']['spark_data_path'],
self.ds_name)
self.moldb = MOL_DBS[database]
self.analysis_version = analysis_version
self.input_path = join(proj_root(), 'tests/data/untreated')
self.ds_config_path = join(self.input_path, 'config.json')
self.metrics = [
'chaos', 'spatial', 'spectral', 'mz_err_abs', 'mz_err_rel', 'msm',
'fdr'
]
self.comparison_df = None
def test_lcms_geometry_factory():
lcms_file_path = join(
proj_root(),
'tests/data/lcms_acq_geometry_example/apple_surface_swab.mzML')
geometry = make_acq_geometry('lcms', lcms_file_path, {}, (0, 0))
assert geometry['length_unit'] == 's'
assert not geometry['acquisition_grid']['regular_grid']
assert len(geometry['acquisition_grid']['coord_list']) == 285
assert geometry['pixel_size'] == {
'regular_size': True,
'size_x': 1,
'size_y': 1
}
def sm_config():
SMConfig.set_path(Path(proj_root()) / TEST_CONFIG_PATH)
SMConfig.get_conf(
update=True) # Force reload in case previous tests modified it
worker_id = os.environ.get('PYTEST_XDIST_WORKER', 'gw0')
test_id = f'sm_test_{worker_id}'
# Update the internal cached copy of the config, so independent calls to SMConfig.get_conf()
# also get the updated config
SMConfig._config_dict['db']['database'] = test_id
SMConfig._config_dict['elasticsearch']['index'] = test_id
SMConfig._config_dict['rabbitmq']['prefix'] = f'test_{worker_id}__'
for path in SMConfig._config_dict['lithops']['sm_storage'].values():
# prefix keys with test ID so they can be cleaned up later
path[1] = f'{test_id}/{path[1]}'
# __LITHOPS_SESSION_ID determines the prefix to use for anonymous cloudobjects
os.environ['__LITHOPS_SESSION_ID'] = f'{test_id}/cloudobjects'
return SMConfig.get_conf()
def ensure_db_populated(sm_config, analysis_version, database):
db = DB()
# Install DB schema if needed
query = "SELECT COUNT(*) FROM pg_tables WHERE schemaname = 'public' AND tablename = 'dataset'"
tables_exist = db.select_one(query)[0] >= 1
if not tables_exist:
print('Installing DB schema')
db.alter(DB_SQL_SCHEMA)
# Import HMDB if needed
moldb = MOL_DBS[database]
try:
molecular_db.find_by_name_version(moldb['name'], moldb['version'])
except SMError:
print(f'Importing {database}')
with TemporaryDirectory() as tmp:
urlretrieve(moldb['url'], f'{tmp}/moldb.tsv')
molecular_db.create(moldb['name'], moldb['version'],
f'{tmp}/moldb.tsv')
if analysis_version > 1:
if len(
db.select(
"SELECT name FROM scoring_model WHERE name = 'v3_default'")
) == 0:
print("Importing v3_default scoring model")
params = upload_catboost_scoring_model(
model=Path(proj_root()) /
'../scoring-models/v3_default/model-2022-01-05T13-45-26.947188-416b1311.cbm',
bucket=sm_config['lithops']['lithops']['storage_bucket'],
prefix=f'test_scoring_models/v3_default',
is_public=False,
)
save_scoring_model_to_db(name='v3_default',
type_='catboost',
params=params)
if __name__ == '__main__':
parser = argparse.ArgumentParser(
description='Scientific tests runner\n'
'Example: python tests/sci_test/spheroid.py'
'or: python tests/sci_test/spheroid.py --lithops --analysis-version 3')
parser.add_argument('--save',
action='store_true',
help='save comparison report even on success')
parser.add_argument('--save-ref',
action='store_true',
help='update reference results')
parser.add_argument(
'--config',
dest='sm_config_path',
default=join(proj_root(), 'conf/scitest_config.json'),
help='path to sm config file',
)
parser.add_argument(
'--store-images',
action='store_true',
help='whether to store ion images. (Default: don\'t store)',
)
parser.add_argument(
'--lithops',
action='store_true',
help=
'whether to use the Lithops executor. (Default: use Spark executor)',
)
parser.add_argument('--analysis-version',
type=int,