def test_parse_reports(self): reports = {"r1": {"SequenceLengthDistribution": {}}} symbol_table = SymbolTable() symbol_table, specs = ReportParser.parse_reports(reports, symbol_table) self.assertTrue(symbol_table.contains("r1")) self.assertTrue( isinstance(symbol_table.get("r1"), SequenceLengthDistribution))
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_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 test_parse_simulation(self): simulation = { "sim1": { "var1": { "signals": ["signal1"], "dataset_implanting_rate": 0.5, "repertoire_implanting_rate": 0.1 } } } symbol_table = SymbolTable() symbol_table.add("motif1", SymbolType.MOTIF, Motif("motif1", GappedKmerInstantiation(position_weights={0: 1}), seed="CAS")) symbol_table.add("signal1", SymbolType.SIGNAL, Signal("signal1", [symbol_table.get("motif1")], HealthySequenceImplanting(GappedMotifImplanting(), implanting_computation=ImplantingComputation.ROUND))) symbol_table, specs = SimulationParser.parse_simulations(simulation, symbol_table) self.assertTrue(symbol_table.contains("sim1")) sim1 = symbol_table.get("sim1") self.assertEqual(1, len(sim1.implantings))