def test_create_output_loc(self):
print('Creating output location')
dir_to_be_created = os.path.join(get_project_root_dir(),
'.another_test_output')
self.input_checker.check_output_loc(dir_to_be_created)
self.assertTrue(
'.another_test_output' in os.listdir(get_project_root_dir()))
def setUpClass(cls):
print('Setting up.')
cls.input_loc = os.path.join(get_project_root_dir(), 'CAPICE_example')
root_dir = get_project_root_dir()
cls.output_directory = os.path.join(root_dir, '.test_output')
if not os.path.exists(cls.output_directory):
os.makedirs(cls.output_directory)
cls.input_checker = InputChecker()
def test_log_checker_both(self):
print('Log checker with both output and log_loc given')
log_output = os.path.join(get_project_root_dir(), '.test_log_output')
logchecker = LogChecker(log_loc=log_output,
output_loc=self.output_directory)
logchecker.check_log_loc()
self.assertTrue(
'.test_log_output' in os.listdir(get_project_root_dir()))
def test_log_checker_output(self):
print('Log checker with only output given')
logchecker = LogChecker(log_loc=None,
output_loc=os.path.join(
get_project_root_dir(),
'.another_test_log_output'))
logchecker.check_log_loc()
self.assertTrue(
'.another_test_log_output' in os.listdir(get_project_root_dir()))
def _load_preprocessors(self):
"""
Function to dynamically load in the preprocessors modules,
but must have the following properties:
name,
supported_vep_version and
supported_genomebuild_version.
"""
self.log.info('Identifying preprocessing files.')
directory = os.path.join(get_project_root_dir(),
'src',
'main',
'python',
'resources',
'models')
usable_modules = load_modules(directory)
if len(usable_modules) < 1:
self._raise_no_module_found_error()
imported_modules = importer(
usable_modules=usable_modules,
path=directory
)
for module in imported_modules:
if "name" in dir(module) and "supported_vep_version" in dir(
module) and "supported_grch_build" in dir(module):
self.preprocessors.append(module)
if len(self.preprocessors) < 1:
self._raise_no_module_found_error()
self.log.info(
'Succesfully loaded {} preprocessors.'.format(
len(self.preprocessors)
)
)
def setUpClass(cls):
print('Setting up.')
cls.manager, output_loc = set_up_manager_and_loc()
input_file = os.path.join(get_project_root_dir(), 'CAPICE_example',
'CAPICE_input.tsv.gz')
cls.main = set_up_main()
cls.main.infile = input_file
def _load_modules(self):
"""
Method to dynamically load in all python files containing a class that
contains the properties
name and
_json_name.
If at the end of this function, the list of impute files is empty,
will throw the module not found error.
"""
self.log.info('Identifying imputing files.')
directory = os.path.join(get_project_root_dir(), 'src', 'main',
'python', 'resources', 'data_files',
'imputing')
usable_modules = load_modules(directory)
if len(usable_modules) < 1:
self._raise_no_module_found_error()
loaded_modules = importer(usable_modules=usable_modules,
path=directory)
for module in loaded_modules:
if "name" in dir(module) and "_json_name" in dir(module):
self.modules.append(module)
if len(self.modules) < 1:
self._raise_no_module_found_error()
self.log.info(
'Identified {} files available for usage in imputing.'.format(
len(self.modules)))
def test_unit_load_specified_defaults(self):
"""
Unit test to see if specified default hyper parameters can be loaded.
"""
print('Load_specified_defaults (unit)')
self.main.specified_default = os.path.join(get_project_root_dir(), 'CAPICE_example', 'specified_defaults.json')
self.main.load_defaults()
def tearDownClass(cls):
print('Tearing down.')
to_remove = [
'.another_test_log_output', '.test_log_output',
'.another_test_output'
]
for removal in to_remove:
os.rmdir(os.path.join(get_project_root_dir(), removal))
teardown()
def setUpClass(cls):
print('Setting up.')
manager, output_loc = set_up_manager_and_loc()
cls.main = set_up_main()
cls.main.infile = os.path.join(get_project_root_dir(),
'CAPICE_example',
'CAPICE_input.tsv.gz')
manager.overwrite_model = 'CAPICE using XGBoost 0.72.1,' \
' CADD 1.4 and genome build 37.'
def _json_loc(self):
path = os.path.join(get_project_root_dir(), 'src', 'main', 'python',
'resources', 'data_files', 'json_data')
json_name = self._json_name()
if json_name == 'none':
error_message = 'Location of JSON must be specified!'
self.log.critical(error_message)
raise FileNotFoundError(error_message)
return os.path.join(path, json_name)
def setUpClass(cls):
print('Setting up.')
cls.manager, output_loc = set_up_manager_and_loc()
cls.vep_version = 104.0
cls.grch_build = 37
cls.impute_overwrite = 'VEP104'
cls.main = set_up_main()
cls.main.infile = os.path.join(get_project_root_dir(),
'CAPICE_example', 'CAPICE_input.tsv.gz')
def teardown():
"""
Function to remove any and all files from the '.test_output' folder and
remove the folder itself too.
"""
test_folder = os.path.join(get_project_root_dir(), '.test_output')
if len(os.listdir(test_folder)) > 0:
for file in os.listdir(test_folder):
os.remove(os.path.join(test_folder, file))
os.rmdir(test_folder)
Logger.instance = None
def setUpClass(cls):
print('Setting up.')
cls.manager, cls.output_dir = set_up_manager_and_loc()
cls.manager.overwrite_impute = 'CADD 1.4, GRCh build 37'
train_file = os.path.join(get_project_root_dir(), 'CAPICE_example', 'train_dataset.tsv.gz')
ConfigReader().parse()
cls.main = Train(__program__=__program__,
__author__=__author__,
__version__=__version__,
input_loc=train_file,
output_loc=cls.output_dir)
def test_component_load_specified_defaults(self):
"""
Component test to see if specified default hyper parameters are loaded correctly.
"""
print('Load_specified_defaults (component)')
self.main.specified_default = os.path.join(get_project_root_dir(), 'CAPICE_example', 'specified_defaults.json')
self.main.load_defaults()
defaults = self.main.defaults
self.assertEqual(defaults['learning_rate'], 0.5)
self.assertEqual(defaults['max_depth'], 10)
self.assertEqual(defaults['n_estimators'], 10)
def setUpClass(cls):
print('Setting up.')
cls.manager = CapiceManager()
cls.output_loc = os.path.join(get_project_root_dir(), '.test_output')
if not os.path.exists(cls.output_loc):
os.makedirs(cls.output_loc)
cls.manager.now = datetime.now()
cls.manager.log_loc = cls.output_loc
cls.manager.critical_logging_only = False
cls.manager.enable_logfile = True
cls.log = Logger().logger
def __init__(self):
self.log = Logger().logger
self.vep_annotators = []
self.location = os.path.join(get_project_root_dir(),
'src',
'main',
'python',
'resources',
'annotaters',
'vep')
self._load_vep_annotators()
def set_up_manager_and_loc():
"""
Function to set up the CapiceManager and testing output location
:return: manager instance, output_directory
"""
manager = CapiceManager()
manager.now = datetime.now()
manager.enable_logfile = False
manager.critical_logging_only = True
manager.verbose = False
root_dir = get_project_root_dir()
output_directory = os.path.join(root_dir, '.test_output')
if not os.path.exists(output_directory):
os.makedirs(output_directory)
config_reader = ConfigReader()
config_reader.parse()
manager.reference_genome = config_reader.get_datafiles_value('reference')
return manager, output_directory
def _get_model_loc():
model_loc = os.path.join(get_project_root_dir(), 'CAPICE_model',
'GRCh37', 'xgb_booster.pickle.dat')
return model_loc
def _parse(self):
self.config.read(os.path.join(get_project_root_dir(), 'config.cfg'))