def _prepare_specs(self):
with self.yaml_path.open("r") as file:
specs = yaml.safe_load(file)
ParameterValidator.assert_keys_present(specs.keys(), ["definitions", "instructions"], GalaxyTrainMLModel.__name__, "YAML specification")
ParameterValidator.assert_all_in_valid_list(specs.keys(), ["definitions", "instructions", "output"], GalaxyTrainMLModel.__name__,
"YAML specification")
ParameterValidator.assert_type_and_value(specs["instructions"], dict, GalaxyTrainMLModel.__name__, "instructions")
assert len(list(specs["instructions"].keys())) == 1, f"{GalaxyTrainMLModel.__name__}: one instruction has to be specified under " \
f"`instructions`, got the following instead: {list(specs['instructions'].keys())}."
self.instruction_name = list(specs["instructions"].keys())[0]
ParameterValidator.assert_type_and_value(specs['instructions'][self.instruction_name], dict, GalaxyTrainMLModel.__name__,
self.instruction_name)
ParameterValidator.assert_keys_present(specs['instructions'][self.instruction_name].keys(), ['type'], GalaxyTrainMLModel.__name__,
self.instruction_name)
assert specs['instructions'][self.instruction_name]['type'] == TrainMLModelInstruction.__name__[:-11], \
f"{GalaxyTrainMLModel.__name__}: instruction `type` under {self.instruction_name} has to be {TrainMLModelInstruction.__name__[:-11]} " \
f"for this tool."
assert len(
specs['instructions'][self.instruction_name]['labels']) == 1, f"{GalaxyTrainMLModel.__name__}: one label has to be specified under " \
f"`labels`, got the following instead: {specs['instructions'][self.instruction_name]['labels']}."
Util.check_paths(specs, GalaxyTrainMLModel.__name__)
Util.update_result_paths(specs, self.result_path, self.yaml_path)
def __init__(self, specification_path: Path, result_path: Path, **kwargs):
Util.check_parameters(specification_path, result_path, kwargs,
DataSimulationTool.__name__)
super().__init__(specification_path, result_path, **kwargs)
self.expected_instruction = DatasetExportInstruction.__name__[:-11]
self.instruction_name = None
self.dataset_name = None
self.export_format = None
def _run(self):
self.prepare_specs()
Util.run_tool(self.yaml_path, self.result_path)
dataset_location = self.result_path / f"{self.instruction_name}/{self.dataset_name}/{self.export_format}/"
shutil.copytree(dataset_location, self.result_path / 'result/')
logging.info(
f"{DataSimulationTool.__name__}: immuneML has finished and the dataset was created."
)
def _run(self):
self.prepare_specs()
Util.run_tool(self.yaml_path, self.result_path)
dataset_location = list(
self.result_path.glob("*/exported_dataset/*/"))[0]
shutil.copytree(dataset_location, self.result_path / 'result/')
logging.info(
f"{GalaxySimulationTool.__name__}: immuneML has finished and the signals were implanted in the dataset."
)
def prepare_specs(self):
with self.yaml_path.open("r") as file:
specs = yaml.safe_load(file)
instruction_name = Util.check_instruction_type(
specs, GalaxySimulationTool.__name__,
SimulationInstruction.__name__[:-11])
Util.check_export_format(specs, GalaxySimulationTool.__name__,
instruction_name)
Util.update_dataset_key(specs, GalaxySimulationTool.__name__)
Util.check_paths(specs, "GalaxySimulationTool")
Util.update_result_paths(specs, self.result_path, self.yaml_path)
def _update_specs(self):
with self.yaml_path.open('r') as file:
specs = yaml.safe_load(file)
ParameterValidator.assert_keys_present(specs.keys(),
["definitions", "instructions"],
DatasetGenerationTool.__name__,
"YAML specification")
ParameterValidator.assert_all_in_valid_list(
specs.keys(), ["definitions", "instructions", "output"],
DatasetGenerationTool.__name__, "YAML specification")
self._check_dataset(specs)
self._check_instruction(specs)
Util.check_paths(specs, DatasetGenerationTool.__name__)
Util.update_result_paths(specs, self.result_path, self.yaml_path)
def prepare_specs(self):
with self.yaml_path.open("r") as file:
specs = yaml.safe_load(file)
self.instruction_name = Util.check_instruction_type(
specs, DataSimulationTool.__name__, self.expected_instruction)
self.export_format = Util.check_export_format(
specs, DataSimulationTool.__name__, self.instruction_name)
ParameterValidator.assert_keys_present(specs["definitions"],
["datasets"],
DataSimulationTool.__name__,
"definitions/datasets")
ParameterValidator.assert_type_and_value(
specs['definitions']['datasets'], dict,
DataSimulationTool.__name__, "definitions/datasets")
dataset_names = list(specs['definitions']['datasets'].keys())
assert len(dataset_names) == 1, f"{DataSimulationTool.__name__}: one dataset has to be defined under definitions/datasets, got " \
f"{dataset_names} instead."
self.dataset_name = dataset_names[0]
Util.check_paths(specs, DataSimulationTool.__name__)
Util.update_result_paths(specs, self.result_path, self.yaml_path)
def _check_instruction(self, specs):
instruction_name = Util.check_instruction_type(
specs, DatasetGenerationTool.__name__,
DatasetExportInstruction.__name__[:-11])
for key in ['datasets', 'export_formats']:
ParameterValidator.assert_keys_present(
list(specs['instructions'][instruction_name].keys()), [key],
DatasetGenerationTool.__name__, instruction_name)
ParameterValidator.assert_type_and_value(
specs["instructions"][instruction_name][key], list,
DatasetGenerationTool.__name__, f"{instruction_name}/{key}")
assert len(specs['instructions'][instruction_name][key]) == 1, \
f"{DatasetGenerationTool.__name__}: this tool accepts only one item under {key}, got {specs['instructions'][instruction_name][key]} " \
f"instead."
def _check_specs(self):
with open(self.yaml_path, "r") as file:
specs = yaml.load(file)
instruction_name = Util.check_instruction_type(
specs, GalaxyMLApplicationTool.__name__,
MLApplicationInstruction.__name__[:-11])
ParameterValidator.assert_keys_present(
list(specs['instructions'][instruction_name].keys()),
["dataset", "config_path"], GalaxyMLApplicationTool.__name__,
instruction_name)
assert os.path.isfile(specs['instructions'][instruction_name]['config_path']), \
f"{GalaxyMLApplicationTool.__name__}: file specified under 'config_path' parameter " \
f"({specs['instructions'][instruction_name]['config_path']}) is not available. Please check if it was correctly uploaded or if the file" \
f" name is correct."
def prepare_specs(self):
with self.yaml_path.open("r") as file:
specs = yaml.safe_load(file)
self.instruction_name = Util.check_instruction_type(
specs, DataSimulationTool.__name__, self.expected_instruction)
self.export_format = Util.check_export_format(
specs, DataSimulationTool.__name__, self.instruction_name)
ParameterValidator.assert_keys_present(specs["definitions"],
["datasets"],
DataSimulationTool.__name__,
"definitions/datasets")
ParameterValidator.assert_type_and_value(
specs['definitions']['datasets'], dict,
DataSimulationTool.__name__, "definitions/datasets")
self.dataset_name = "dataset"
Util.update_dataset_key(specs, DataSimulationTool.__name__,
self.dataset_name)
Util.check_paths(specs, DataSimulationTool.__name__)
Util.update_result_paths(specs, self.result_path, self.yaml_path)
def __init__(self, specification_path: Path, result_path: Path, **kwargs):
Util.check_parameters(specification_path, result_path, kwargs,
"Dataset generation tool")
super().__init__(specification_path, result_path, **kwargs)
def __init__(self, specification_path: Path, result_path: Path, **kwargs):
Util.check_parameters(specification_path, result_path, kwargs,
GalaxySimulationTool.__name__)
super().__init__(specification_path, result_path, **kwargs)
def __init__(self, specification_path: Path, result_path: Path, **kwargs):
Util.check_parameters(specification_path, result_path, kwargs, GalaxyTrainMLModel.__name__)
super().__init__(specification_path, result_path, **kwargs)
self.instruction_name = None
def update_specs(self):
with self.yaml_path.open("r") as file:
specs_dict = yaml.safe_load(file)
Util.check_paths(specs_dict, 'GalaxyYamlTool')
Util.update_result_paths(specs_dict, self.result_path, self.yaml_path)
def __init__(self, specification_path: Path, result_path: Path, **kwargs):
Util.check_parameters(specification_path, result_path, kwargs, "GalaxyYamlTool")
super().__init__(specification_path, result_path, **kwargs)