def _parse_settings(self, instruction: dict,
symbol_table: SymbolTable) -> list:
try:
settings = []
for index, setting in enumerate(instruction["settings"]):
if "preprocessing" in setting and setting[
"preprocessing"] is not None:
ParameterValidator.assert_type_and_value(
setting["preprocessing"], str,
TrainMLModelParser.__name__, f'settings: {index+1}. '
f'element: preprocessing')
if symbol_table.contains(setting["preprocessing"]):
preprocessing_sequence = symbol_table.get(
setting["preprocessing"])
preproc_name = setting["preprocessing"]
if not all(preproc.keeps_example_count()
for preproc in preprocessing_sequence):
raise ValueError(
f"{TrainMLModelParser.__name__}: preprocessing sequence {preproc_name} includes preprocessing that "
f"change the number of examples at runtime and as such cannot be used with this instruction. See the "
f"documentation for the preprocessing or alternatively use them with other instructions."
)
else:
raise KeyError(
f"{TrainMLModelParser.__name__}: preprocessing was set in the TrainMLModel instruction to value "
f"{setting['preprocessing']}, but no such preprocessing was defined in the specification under "
f"definitions: {PreprocessingParser.keyword}.")
else:
setting["preprocessing"] = None
preprocessing_sequence = []
preproc_name = None
ParameterValidator.assert_keys(
setting.keys(), ["preprocessing", "ml_method", "encoding"],
TrainMLModelParser.__name__,
f"settings, {index + 1}. entry")
encoder = symbol_table.get(setting["encoding"]).build_object(symbol_table.get(instruction["dataset"]),
**symbol_table.get_config(setting["encoding"])["encoder_params"])\
.set_context({"dataset": symbol_table.get(instruction['dataset'])})
ml_method = symbol_table.get(setting["ml_method"])
ml_method.check_encoder_compatibility(encoder)
s = HPSetting(encoder=encoder,
encoder_name=setting["encoding"],
encoder_params=symbol_table.get_config(
setting["encoding"])["encoder_params"],
ml_method=ml_method,
ml_method_name=setting["ml_method"],
ml_params=symbol_table.get_config(
setting["ml_method"]),
preproc_sequence=preprocessing_sequence,
preproc_sequence_name=preproc_name)
settings.append(s)
return settings
except KeyError as key_error:
raise KeyError(
f"{TrainMLModelParser.__name__}: parameter {key_error.args[0]} was not defined under settings in TrainMLModel instruction."
)
def parse(self,
key: str,
instruction: dict,
symbol_table: SymbolTable,
path: Path = None) -> ExploratoryAnalysisInstruction:
exp_analysis_units = {}
ParameterValidator.assert_keys(
instruction, ["analyses", "type", "number_of_processes"],
"ExploratoryAnalysisParser", "ExploratoryAnalysis")
ParameterValidator.assert_type_and_value(
instruction["number_of_processes"], int,
ExploratoryAnalysisParser.__name__, "number_of_processes")
for analysis_key, analysis in instruction["analyses"].items():
params = self._prepare_params(analysis, symbol_table,
f"{key}/{analysis_key}")
params["number_of_processes"] = instruction["number_of_processes"]
exp_analysis_units[analysis_key] = ExploratoryAnalysisUnit(
**params)
process = ExploratoryAnalysisInstruction(
exploratory_analysis_units=exp_analysis_units, name=key)
return process
def parse(self, key: str, instruction: dict, symbol_table: SymbolTable,
path: Path) -> MLApplicationInstruction:
location = MLApplicationParser.__name__
ParameterValidator.assert_keys(instruction.keys(), [
'type', 'dataset', 'number_of_processes', 'config_path',
'store_encoded_data'
], location, key)
ParameterValidator.assert_in_valid_list(
instruction['dataset'],
symbol_table.get_keys_by_type(SymbolType.DATASET), location,
f"{key}: dataset")
ParameterValidator.assert_type_and_value(
instruction['number_of_processes'],
int,
location,
f"{key}: number_of_processes",
min_inclusive=1)
ParameterValidator.assert_type_and_value(instruction['config_path'],
str, location,
f'{key}: config_path')
ParameterValidator.assert_type_and_value(
instruction['store_encoded_data'], bool, location,
f'{key}: store_encoded_data')
hp_setting, label = self._parse_hp_setting(instruction, path, key)
instruction = MLApplicationInstruction(
dataset=symbol_table.get(instruction['dataset']),
name=key,
number_of_processes=instruction['number_of_processes'],
label_configuration=LabelConfiguration([label]),
hp_setting=hp_setting,
store_encoded_data=instruction['store_encoded_data'])
return instruction
def prepare_reference(reference_params: dict, location: str, paired: bool):
ParameterValidator.assert_keys(list(reference_params.keys()), ["format", "params"], location,
"reference")
seq_import_params = reference_params["params"] if "params" in reference_params else {}
assert os.path.isfile(seq_import_params["path"]), f"{location}: the file {seq_import_params['path']} does not exist. " \
f"Specify the correct path under reference."
if "is_repertoire" in seq_import_params:
assert seq_import_params["is_repertoire"] == False, f"{location}: is_repertoire must be False for SequenceImport"
else:
seq_import_params["is_repertoire"] = False
if "paired" in seq_import_params:
assert seq_import_params["paired"] == paired, f"{location}: paired must be {paired} for SequenceImport"
else:
seq_import_params["paired"] = paired
format_str = reference_params["format"]
import_class = ReflectionHandler.get_class_by_name("{}Import".format(format_str))
default_params = DefaultParamsLoader.load(EnvironmentSettings.default_params_path / "datasets",
DefaultParamsLoader.convert_to_snake_case(format_str))
params = {**default_params, **seq_import_params}
processed_params = DatasetImportParams.build_object(**params)
receptors = ImportHelper.import_items(import_class, reference_params["params"]["path"], processed_params)
return receptors
def _prepare_parameters(reference: dict,
max_edit_distances: dict,
name: str = None):
location = "MatchedReceptorsEncoder"
legal_chains = [
chain
for receptor in (TCABReceptor(), TCGDReceptor(), BCReceptor())
for chain in receptor.get_chains()
]
if type(max_edit_distances) is int:
max_edit_distances = {
chain: max_edit_distances
for chain in legal_chains
}
elif type(max_edit_distances) is dict:
ParameterValidator.assert_keys(max_edit_distances.keys(),
legal_chains,
location,
"max_edit_distances",
exclusive=False)
else:
ParameterValidator.assert_type_and_value(max_edit_distances, dict,
location,
'max_edit_distances')
reference_receptors = MatchedReferenceUtil.prepare_reference(
reference, location=location, paired=True)
return {
"reference_receptors": reference_receptors,
"max_edit_distances": max_edit_distances,
"name": name
}
def parse(self,
key: str,
instruction: dict,
symbol_table: SymbolTable,
path: Path = None) -> SimulationInstruction:
ParameterValidator.assert_keys(
instruction.keys(),
["dataset", "simulation", "type", "export_formats"],
"SimulationParser", key)
signals = [
signal.item
for signal in symbol_table.get_by_type(SymbolType.SIGNAL)
]
simulation = symbol_table.get(instruction["simulation"])
dataset = symbol_table.get(instruction["dataset"])
exporters = self.parse_exporters(instruction)
process = SimulationInstruction(signals=signals,
simulation=simulation,
dataset=dataset,
name=key,
exporters=exporters)
return process
def _parse_dataset(key: str, dataset_specs: dict,
symbol_table: SymbolTable,
result_path: Path) -> SymbolTable:
location = "ImportParser"
ParameterValidator.assert_keys(list(dataset_specs.keys()),
ImportParser.valid_keys, location,
f"datasets:{key}", False)
valid_formats = ReflectionHandler.all_nonabstract_subclass_basic_names(
DataImport, "Import", "IO/dataset_import/")
ParameterValidator.assert_in_valid_list(dataset_specs["format"],
valid_formats, location,
"format")
import_cls = ReflectionHandler.get_class_by_name("{}Import".format(
dataset_specs["format"]))
params = ImportParser._prepare_params(dataset_specs, result_path, key)
if "is_repertoire" in params:
ParameterValidator.assert_type_and_value(params["is_repertoire"],
bool, location,
"is_repertoire")
if params["is_repertoire"] == True:
if import_cls != IReceptorImport:
assert "metadata_file" in params, f"{location}: Missing parameter: metadata_file under {key}/params/"
ParameterValidator.assert_type_and_value(
params["metadata_file"], Path, location,
"metadata_file")
if params["is_repertoire"] == False:
assert "paired" in params, f"{location}: Missing parameter: paired under {key}/params/"
ParameterValidator.assert_type_and_value(
params["paired"], bool, location, "paired")
if params["paired"] == True:
assert "receptor_chains" in params, f"{location}: Missing parameter: receptor_chains under {key}/params/"
ParameterValidator.assert_in_valid_list(
params["receptor_chains"],
["_".join(cp.value) for cp in ChainPair], location,
"receptor_chains")
try:
dataset = import_cls.import_dataset(params, key)
dataset.name = key
symbol_table.add(key, SymbolType.DATASET, dataset)
except KeyError as key_error:
raise KeyError(
f"{key_error}\n\nAn error occurred during parsing of dataset {key}. "
f"The keyword {key_error.args[0]} was missing. This either means this argument was "
f"not defined under definitions/datasets/{key}/params, or this column was missing from "
f"an input data file. ")
except Exception as ex:
raise Exception(
f"{ex}\n\nAn error occurred while parsing the dataset {key}. See the log above for more details."
)
return symbol_table
def _check_specs(self, workflow_specification):
location = 'MultiDatasetBenchmarkTool'
ParameterValidator.assert_keys(
workflow_specification.keys(),
['definitions', 'instructions', 'output'], location,
'YAML specification')
self._check_dataset_specs(workflow_specification, location)
self._check_instruction_specs(workflow_specification, location)
def parse(specs: dict, symbol_table: SymbolTable) -> dict:
if "output" in specs:
ParameterValidator.assert_keys(specs["output"], ["format"], "OutputParser", "output")
ParameterValidator.assert_in_valid_list(specs["output"]["format"], ["HTML"], "OutputParser", "format")
else:
specs["output"] = {"format": "HTML"}
symbol_table.add("output", SymbolType.OUTPUT, specs["output"])
return specs["output"]
def _prepare_params(self, analysis: dict, symbol_table: SymbolTable) -> dict:
valid_keys = ["dataset", "report", "preprocessing_sequence", "labels", "encoding", "number_of_processes"]
ParameterValidator.assert_keys(list(analysis.keys()), valid_keys, "ExploratoryAnalysisParser", "analysis", False)
params = {"dataset": symbol_table.get(analysis["dataset"]), "report": copy.deepcopy(symbol_table.get(analysis["report"]))}
optional_params = self._prepare_optional_params(analysis, symbol_table)
params = {**params, **optional_params}
return params
def parse(self, key: str, instruction: dict, symbol_table: SymbolTable, path: Path = None) -> ExploratoryAnalysisInstruction:
exp_analysis_units = {}
ParameterValidator.assert_keys(instruction, ["analyses", "type"], "ExploratoryAnalysisParser", "ExploratoryAnalysis")
for analysis_key, analysis in instruction["analyses"].items():
params = self._prepare_params(analysis, symbol_table)
exp_analysis_units[analysis_key] = ExploratoryAnalysisUnit(**params)
process = ExploratoryAnalysisInstruction(exploratory_analysis_units=exp_analysis_units, name=key)
return process
def parse_motifs(motifs: dict, symbol_table: SymbolTable):
valid_motif_keys = ["seed", "instantiation", "seed_chain1", "seed_chain2", "name_chain1", "name_chain2"]
for key in motifs.keys():
ParameterValidator.assert_keys(motifs[key].keys(), valid_motif_keys, "MotifParser", key, exclusive=False)
motif = MotifParser._parse_motif(key, motifs[key])
symbol_table.add(key, SymbolType.MOTIF, motif)
return symbol_table, motifs
def build_object(cls, **kwargs):
location = cls.__name__
ParameterValidator.assert_keys(kwargs.keys(), ["filter_sequence_type", "batch_size", "count_agg"], location,
"DuplicateSequenceFilter")
ParameterValidator.assert_in_valid_list(kwargs["filter_sequence_type"].upper(), [item.name for item in SequenceType],
location, "filter_sequence_type")
ParameterValidator.assert_in_valid_list(kwargs["count_agg"].upper(), [item.name for item in CountAggregationFunction], location,
"count_agg")
ParameterValidator.assert_type_and_value(kwargs["batch_size"], int, location, "batch_size", 1)
return DuplicateSequenceFilter(filter_sequence_type=SequenceType[kwargs["filter_sequence_type"].upper()],
batch_size=kwargs["batch_size"], count_agg=CountAggregationFunction[kwargs["count_agg"].upper()])
def _parse_settings(self, instruction: dict,
symbol_table: SymbolTable) -> list:
try:
settings = []
for index, setting in enumerate(instruction["settings"]):
if "preprocessing" in setting:
ParameterValidator.assert_type_and_value(
setting["preprocessing"], str,
TrainMLModelParser.__name__, f'settings: {index+1}. '
f'element: preprocessing')
if symbol_table.contains(setting["preprocessing"]):
preprocessing_sequence = symbol_table.get(
setting["preprocessing"])
preproc_name = setting["preprocessing"]
else:
raise KeyError(
f"{TrainMLModelParser.__name__}: preprocessing was set in the TrainMLModel instruction to value "
f"{setting['preprocessing']}, but no such preprocessing was defined in the specification under "
f"definitions: {PreprocessingParser.keyword}.")
else:
setting["preprocessing"] = None
preprocessing_sequence = []
preproc_name = None
ParameterValidator.assert_keys(
setting.keys(), ["preprocessing", "ml_method", "encoding"],
TrainMLModelParser.__name__,
f"settings, {index + 1}. entry")
encoder = symbol_table.get(setting["encoding"]).build_object(symbol_table.get(instruction["dataset"]),
**symbol_table.get_config(setting["encoding"])["encoder_params"])\
.set_context({"dataset": symbol_table.get(instruction['dataset'])})
s = HPSetting(encoder=encoder,
encoder_name=setting["encoding"],
encoder_params=symbol_table.get_config(
setting["encoding"])["encoder_params"],
ml_method=symbol_table.get(setting["ml_method"]),
ml_method_name=setting["ml_method"],
ml_params=symbol_table.get_config(
setting["ml_method"]),
preproc_sequence=preprocessing_sequence,
preproc_sequence_name=preproc_name)
settings.append(s)
return settings
except KeyError as key_error:
raise KeyError(
f"{TrainMLModelParser.__name__}: parameter {key_error.args[0]} was not defined under settings in TrainMLModel instruction."
)
def parse(self,
key: str,
instruction: dict,
symbol_table: SymbolTable,
path: Path = None) -> SubsamplingInstruction:
valid_keys = [
"type", "dataset", "subsampled_dataset_sizes",
"dataset_export_formats"
]
ParameterValidator.assert_keys(instruction.keys(), valid_keys,
SubsamplingParser.__name__, key)
dataset_keys = symbol_table.get_keys_by_type(SymbolType.DATASET)
ParameterValidator.assert_in_valid_list(instruction['dataset'],
dataset_keys,
SubsamplingParser.__name__,
f'{key}/dataset')
dataset = symbol_table.get(instruction['dataset'])
ParameterValidator.assert_type_and_value(
instruction['subsampled_dataset_sizes'], list,
SubsamplingParser.__name__, f'{key}/subsampled_dataset_sizes')
ParameterValidator.assert_all_type_and_value(
instruction['subsampled_dataset_sizes'], int,
SubsamplingParser.__name__, f'{key}/subsampled_dataset_sizes', 1,
dataset.get_example_count())
valid_export_formats = ReflectionHandler.all_nonabstract_subclass_basic_names(
DataExporter, 'Exporter', "dataset_export/")
ParameterValidator.assert_type_and_value(
instruction['dataset_export_formats'], list,
SubsamplingParser.__name__, f"{key}/dataset_export_formats")
ParameterValidator.assert_all_in_valid_list(
instruction['dataset_export_formats'], valid_export_formats,
SubsamplingParser.__name__, f"{key}/dataset_export_formats")
return SubsamplingInstruction(
dataset=dataset,
subsampled_dataset_sizes=instruction['subsampled_dataset_sizes'],
dataset_export_formats=[
ReflectionHandler.get_class_by_name(export_format + "Exporter",
"dataset_export/")
for export_format in instruction['dataset_export_formats']
],
name=key)
def build_object(cls, **kwargs):
ParameterValidator.assert_keys(kwargs.keys(),
['metadata_labels', 'name'],
ConfounderAnalysis.__name__,
ConfounderAnalysis.__name__)
ParameterValidator.assert_type_and_value(kwargs['metadata_labels'],
list,
ConfounderAnalysis.__name__,
'metadata_labels')
ParameterValidator.assert_all_type_and_value(
kwargs['metadata_labels'], str, ConfounderAnalysis.__name__,
'metadata_labels')
ParameterValidator.assert_type_and_value(kwargs['name'], str,
ConfounderAnalysis.__name__,
'name')
return ConfounderAnalysis(metadata_labels=kwargs['metadata_labels'],
name=kwargs['name'])
def build_object(cls, **kwargs):
ParameterValidator.assert_keys(
kwargs.keys(),
['reference_path', 'comparison_attributes', 'name', 'label'],
ReferenceSequenceOverlap.__name__,
f"reports: {kwargs['name'] if 'name' in kwargs else ''}")
kwargs['reference_path'] = Path(kwargs['reference_path'])
assert kwargs['reference_path'].is_file(), f"{ReferenceSequenceOverlap.__name__}: 'reference_path' for report {kwargs['name']} is not " \
f"a valid file path."
reference_sequences_df = pd.read_csv(kwargs['reference_path'])
attributes = reference_sequences_df.columns.tolist()
ParameterValidator.assert_keys_present(
expected_values=kwargs['comparison_attributes'],
values=attributes,
location=ReferenceSequenceOverlap.__name__,
parameter_name='columns in file under reference_path')
return ReferenceSequenceOverlap(**kwargs)
def _parse_simulation(key: str, simulation: dict, symbol_table: SymbolTable) -> SymbolTable:
location = "SimulationParser"
valid_implanting_keys = ["dataset_implanting_rate", "repertoire_implanting_rate", "signals", "is_noise"]
implantings = []
for impl_key, implanting in simulation.items():
ParameterValidator.assert_keys(implanting.keys(), valid_implanting_keys, location, impl_key, exclusive=False)
ParameterValidator.assert_keys(implanting["signals"], symbol_table.get_keys_by_type(SymbolType.SIGNAL), location, impl_key, False)
implanting_params = copy.deepcopy(implanting)
implanting_params["signals"] = [symbol_table.get(signal) for signal in implanting["signals"]]
implanting_params["name"] = impl_key
implantings.append(Implanting(**implanting_params))
assert sum([settings["dataset_implanting_rate"] for settings in simulation.values()]) <= 1, \
"The total dataset implanting rate can not exceed 1."
symbol_table.add(key, SymbolType.SIMULATION, Simulation(implantings))
return symbol_table
def parse_signals(signals: dict, symbol_table: SymbolTable):
for key, signal_spec in signals.items():
ParameterValidator.assert_keys_present(signal_spec.keys(),
SignalParser.VALID_KEYS,
"SignalParser", key)
implanting_strategy = SignalParser._get_implanting_strategy(
key, signal_spec)
ParameterValidator.assert_keys(
signal_spec["motifs"],
symbol_table.get_keys_by_type(SymbolType.MOTIF),
"SignalParser", f"motifs in signal {key}", False)
signal_motifs = [
symbol_table.get(motif_id)
for motif_id in signal_spec["motifs"]
]
signal = Signal(key, signal_motifs, implanting_strategy)
symbol_table.add(key, SymbolType.SIGNAL, signal)
return symbol_table, signals
def parse(self, key: str, instruction: dict, symbol_table: SymbolTable, path: Path = None) -> TrainMLModelInstruction:
valid_keys = ["assessment", "selection", "dataset", "strategy", "labels", "metrics", "settings", "number_of_processes", "type", "reports",
"optimization_metric", 'refit_optimal_model', 'store_encoded_data']
ParameterValidator.assert_type_and_value(instruction['settings'], list, TrainMLModelParser.__name__, 'settings')
ParameterValidator.assert_keys(list(instruction.keys()), valid_keys, TrainMLModelParser.__name__, "TrainMLModel")
ParameterValidator.assert_type_and_value(instruction['refit_optimal_model'], bool, TrainMLModelParser.__name__, 'refit_optimal_model')
ParameterValidator.assert_type_and_value(instruction['metrics'], list, TrainMLModelParser.__name__, 'metrics')
ParameterValidator.assert_type_and_value(instruction['optimization_metric'], str, TrainMLModelParser.__name__, 'optimization_metric')
ParameterValidator.assert_type_and_value(instruction['number_of_processes'], int, TrainMLModelParser.__name__, 'number_of_processes')
ParameterValidator.assert_type_and_value(instruction['strategy'], str, TrainMLModelParser.__name__, 'strategy')
ParameterValidator.assert_type_and_value(instruction['store_encoded_data'], bool, TrainMLModelParser.__name__, 'store_encoded_data')
if instruction["reports"] is not None:
ParameterValidator.assert_type_and_value(instruction['reports'], list, TrainMLModelParser.__name__, 'reports')
settings = self._parse_settings(instruction, symbol_table)
dataset = symbol_table.get(instruction["dataset"])
assessment = self._parse_split_config(key, instruction, "assessment", symbol_table, len(settings))
selection = self._parse_split_config(key, instruction, "selection", symbol_table, len(settings))
assessment, selection = self._update_split_configs(assessment, selection, dataset)
label_config = self._create_label_config(instruction, dataset, key)
strategy = ReflectionHandler.get_class_by_name(instruction["strategy"], "hyperparameter_optimization/")
metrics = {Metric[metric.upper()] for metric in instruction["metrics"]}
optimization_metric = Metric[instruction["optimization_metric"].upper()]
metric_search_criterion = Metric.get_search_criterion(optimization_metric)
path = self._prepare_path(instruction)
context = self._prepare_context(instruction, symbol_table)
reports = self._prepare_reports(instruction["reports"], symbol_table)
hp_instruction = TrainMLModelInstruction(dataset=dataset, hp_strategy=strategy(settings, metric_search_criterion),
hp_settings=settings, assessment=assessment, selection=selection, metrics=metrics,
optimization_metric=optimization_metric, refit_optimal_model=instruction['refit_optimal_model'],
label_configuration=label_config, path=path, context=context,
store_encoded_data=instruction['store_encoded_data'],
number_of_processes=instruction["number_of_processes"], reports=reports, name=key)
return hp_instruction
def parse(self,
key: str,
instruction: dict,
symbol_table: SymbolTable,
path: Path = None) -> DatasetExportInstruction:
location = "DatasetExportParser"
ParameterValidator.assert_keys(
list(instruction.keys()), DatasetExportParser.REQUIRED_KEYS +
DatasetExportParser.OPTIONAL_KEYS, location, key, False)
ParameterValidator.assert_keys_present(
list(instruction.keys()), DatasetExportParser.REQUIRED_KEYS,
location, key)
valid_formats = ReflectionHandler.all_nonabstract_subclass_basic_names(
DataExporter, "Exporter", 'dataset_export/')
ParameterValidator.assert_all_in_valid_list(
instruction["export_formats"], valid_formats, location,
"export_formats")
ParameterValidator.assert_all_in_valid_list(
instruction["datasets"],
symbol_table.get_keys_by_type(SymbolType.DATASET), location,
"datasets")
return DatasetExportInstruction(
datasets=[
symbol_table.get(dataset_key)
for dataset_key in instruction["datasets"]
],
exporters=[
ReflectionHandler.get_class_by_name(f"{key}Exporter",
"dataset_export/")
for key in instruction["export_formats"]
],
preprocessing_sequence=symbol_table.get(
instruction["preprocessing_sequence"])
if "preprocessing_sequence" in instruction else None,
name=key)
