def set_up_manager_and_out():
"""
Function to set up the CapiceManager and testing output location
:return: manager instance, output_directory
"""
manager = CapiceManager()
manager.critical_logging_only = True
root_dir = _project_root_directory
output_directory = os.path.join(root_dir, '.test_output')
if not os.path.exists(output_directory):
os.makedirs(output_directory)
return manager, output_directory
def __init__(self):
self.version = __version__
self.parser = argparse.ArgumentParser(
description=
"CAPICE, a machine-learning-based method for prioritizing pathogenic"
" variants https://doi.org/10.1186/s13073-020-00775-w")
self.manager = CapiceManager()
def setUpClass(cls):
print('Setting up.')
cls.manager = CapiceManager()
cls.manager.loglevel = 10
with open(
os.path.join(_project_root_directory, 'tests', 'resources',
'xgb_booster_poc.pickle.dat'),
'rb') as model_file:
cls.model = pickle.load(model_file)
def _handle_module_specific_args(self, input_path, output_path,
output_filename, output_given, args):
model_path = input_path
with open(model_path, 'rb') as model_file:
model = pickle.load(model_file)
validator = ModelValidator()
validator.validate_is_xgb_classifier(model)
validator.validate_has_required_attributes(model)
CapiceManager().output_filename = output_filename
CapiceExplain(model, output_path, output_given).run()
def __init__(self):
self.global_settings = CapiceManager()
self.stdout = False
self.stdout_filter = []
self.stderr_loglevel = 50
self.min_loglevel = 50
self.set_stderr_loglevel()
self.logger = None
if self.logger is None:
self.load_logger()
def __init__(self, file_path, output_given):
self.log = Logger().logger
self.capice_filename = CapiceManager().output_filename
self.file_path = file_path
self.output_given = output_given
self.export_cols = [
Column.chr.value, Column.pos.value, Column.ref.value,
Column.alt.value, Column.gene_name.value, Column.gene_id.value,
Column.id_source.value, Column.feature.value,
Column.feature_type.value, Column.score.value,
Column.suggested_class.value
]
def setUpClass(cls) -> None:
with open(
os.path.join(
_project_root_directory,
'tests',
'resources',
'xgb_booster_poc.pickle.dat'
), 'rb'
) as model_file:
cls.model = pickle.load(model_file)
if not os.path.isdir(cls.output_path):
os.makedirs(cls.output_path)
CapiceManager().output_filename = cls.output_filename
def _handle_module_specific_args(self, input_path, output_path,
output_filename, output_given, args):
impute = self.validate_length_one(args.impute, '-m/--impute')
self.validate_input_json(impute)
test_split = self.validate_length_one(args.split, '-s/--split')
if test_split is None:
test_split = self.split_default
# Since argparse doesn't cooperate well with default values and always
# returns them as a list, this has to be done.
if isinstance(test_split, list):
test_split = test_split[0]
self.validate_test_split(test_split)
n_threads = args.threads
self.validate_n_threads(n_threads)
CapiceManager().output_filename = output_filename
CapiceTrain(input_path, impute, test_split, output_path, output_given,
n_threads).run()
def __init__(self, exclude_features: list, model_features: list = None):
"""
:param exclude_features: list,
all the features that the preprocessor should not process.
Features that are already excluded include:
chr_pos_ref_alt, chr and pos.
:param model_features: list (default None), a list containing all
the features present within a model file.
"""
self.log = Logger().logger
self.manager = CapiceManager()
self.log.info('Preprocessor started.')
self.train = False
self.exclude_features = [
Column.chr_pos_ref_alt.value,
Column.chr.value,
Column.pos.value
]
self.exclude_features += exclude_features
self.model_features = model_features
self.objects = []
def __init__(self, input_path, output_path, output_given):
# Assumes CapiceManager has been initialized & filled.
self.manager = CapiceManager()
self.log = Logger().logger
self.log.info('Initiating selected mode.')
# Input file.
self.infile = input_path
self.log.debug('Input argument -i / --input confirmed: %s', self.infile)
# Output file.
self.output = output_path
self.log.debug('Output directory -o / --output confirmed: %s', self.output)
self.output_given = output_given
# Preprocessor global exclusion features
# Overwrite in specific module if features are incorrect
self.exclude_features = [Column.gene_name.value,
Column.gene_id.value,
Column.id_source.value,
Column.feature.value,
Column.feature_type.value]
def _export(self, dataset, output):
output_path = os.path.join(output, CapiceManager().output_filename)
dataset.to_csv(output_path, compression='gzip', index=False, sep='\t')
if not self.output_given:
print(f'Successfully exported explain to: {output_path}')
def _handle_module_specific_args(self, input_path, output_path,
output_filename, output_given, args):
model_path = self.validate_length_one(args.model, '-m/--model')
model = self.validate_model(model_path)
CapiceManager().output_filename = output_filename
CapicePredict(input_path, model, output_path, output_given).run()
def setUpClass(cls):
print('Setting up.')
cls.manager = CapiceManager()
cls.manager.critical_logging_only = False
cls.not_present_string = 'Not present string'