diff --git a/rdagent/app/data_science/conf.py b/rdagent/app/data_science/conf.py index 2d8ec626..488f6b85 100644 --- a/rdagent/app/data_science/conf.py +++ b/rdagent/app/data_science/conf.py @@ -201,6 +201,5 @@ class DataScienceBasePropSetting(KaggleBasePropSetting): DS_RD_SETTING = DataScienceBasePropSetting() # enable_cross_trace_diversity and llm_select_hypothesis should not be true at the same time -assert not ( - DS_RD_SETTING.enable_cross_trace_diversity and DS_RD_SETTING.llm_select_hypothesis -), "enable_cross_trace_diversity and llm_select_hypothesis cannot be true at the same time" +if DS_RD_SETTING.enable_cross_trace_diversity and DS_RD_SETTING.llm_select_hypothesis: + raise ValueError("enable_cross_trace_diversity and llm_select_hypothesis cannot be true at the same time") diff --git a/rdagent/app/finetune/llm/loop.py b/rdagent/app/finetune/llm/loop.py index 9f2bea1e..95450937 100644 --- a/rdagent/app/finetune/llm/loop.py +++ b/rdagent/app/finetune/llm/loop.py @@ -58,18 +58,18 @@ def main( if user_target_scenario: FT_RD_SETTING.user_target_scenario = user_target_scenario - assert ( - FT_RD_SETTING.user_target_scenario is None - ), "user_target_scenario is not yet supported, please specify via benchmark and benchmark_description" + if FT_RD_SETTING.user_target_scenario is not None: + raise ValueError("user_target_scenario is not yet supported, please specify via benchmark and benchmark_description") if upper_data_size_limit: FT_RD_SETTING.upper_data_size_limit = upper_data_size_limit logger.info(f"Set upper_data_size_limit to {FT_RD_SETTING.upper_data_size_limit}") if benchmark and benchmark_description: FT_RD_SETTING.target_benchmark = benchmark FT_RD_SETTING.benchmark_description = benchmark_description - assert FT_RD_SETTING.user_target_scenario or ( - FT_RD_SETTING.target_benchmark and FT_RD_SETTING.benchmark_description - ), "Either user_target_scenario or target_benchmark must be specified for LLM fine-tuning." + if not ( + FT_RD_SETTING.user_target_scenario or (FT_RD_SETTING.target_benchmark and FT_RD_SETTING.benchmark_description) + ): + raise ValueError("Either user_target_scenario or target_benchmark must be specified for LLM fine-tuning.") # Update configuration with provided parameters if dataset: @@ -82,9 +82,8 @@ def main( model_target = FT_RD_SETTING.base_model if FT_RD_SETTING.base_model else "auto selected model" # Temporary assertion until auto-selection is implemented - assert ( - FT_RD_SETTING.base_model is not None - ), "Base model auto selection not yet supported, please specify via --base-model" + if FT_RD_SETTING.base_model is None: + raise ValueError("Base model auto selection not yet supported, please specify via --base-model") logger.info(f"Starting LLM fine-tuning on dataset='{data_set_target}' with model='{model_target}'") diff --git a/rdagent/app/qlib_rd_loop/quant.py b/rdagent/app/qlib_rd_loop/quant.py index 6eb1469e..f5e6464e 100644 --- a/rdagent/app/qlib_rd_loop/quant.py +++ b/rdagent/app/qlib_rd_loop/quant.py @@ -78,7 +78,8 @@ class QuantRDLoop(RDLoop): while True: if self.get_unfinished_loop_cnt(self.loop_idx) < RD_AGENT_SETTINGS.get_max_parallel(): hypo = self._propose() - assert hypo.action in ["factor", "model"] + if hypo.action not in ["factor", "model"]: + raise ValueError(f"hypo.action must be 'factor' or 'model', got {hypo.action!r}") if hypo.action == "factor": exp = self.factor_hypothesis2experiment.convert(hypo, self.trace) else: diff --git a/rdagent/components/coder/CoSTEER/__init__.py b/rdagent/components/coder/CoSTEER/__init__.py index 04bbfb48..33935467 100644 --- a/rdagent/components/coder/CoSTEER/__init__.py +++ b/rdagent/components/coder/CoSTEER/__init__.py @@ -75,8 +75,10 @@ class CoSTEER(Developer[Experiment]): def _get_last_fb(self) -> CoSTEERMultiFeedback: fb = self.evolve_agent.evolving_trace[-1].feedback - assert fb is not None, "feedback is None" - assert isinstance(fb, CoSTEERMultiFeedback), "feedback must be of type CoSTEERMultiFeedback" + if fb is None: + raise AssertionError("feedback is None") + if not isinstance(fb, CoSTEERMultiFeedback): + raise TypeError("feedback must be of type CoSTEERMultiFeedback") return fb def should_use_new_evo(self, base_fb: CoSTEERMultiFeedback | None, new_fb: CoSTEERMultiFeedback) -> bool: @@ -121,7 +123,8 @@ class CoSTEER(Developer[Experiment]): for evo_exp in self.evolve_agent.multistep_evolve(evo_exp, self.evaluator): iteration_count += 1 - assert isinstance(evo_exp, Experiment) # multiple inheritance + if not isinstance(evo_exp, Experiment): + raise TypeError("evo_exp must be an instance of Experiment") evo_fb = self._get_last_fb() update_fallback = self.should_use_new_evo( base_fb=fallback_evo_fb, @@ -154,7 +157,8 @@ class CoSTEER(Developer[Experiment]): evo_exp = fallback_evo_exp evo_exp.recover_ws_ckp() evo_fb = fallback_evo_fb - assert evo_fb is not None # multistep_evolve should run at least once + if evo_fb is None: + raise AssertionError("multistep_evolve should run at least once") evo_exp = self._exp_postprocess_by_feedback(evo_exp, evo_fb) except CoderError as e: e.caused_by_timeout = reached_max_seconds @@ -264,9 +268,12 @@ class CoSTEER(Developer[Experiment]): - Raise Error if it failed to handle the develop task - """ - assert isinstance(evo, Experiment) - assert isinstance(feedback, CoSTEERMultiFeedback) - assert len(evo.sub_workspace_list) == len(feedback) + if not isinstance(evo, Experiment): + raise TypeError("evo must be an instance of Experiment") + if not isinstance(feedback, CoSTEERMultiFeedback): + raise TypeError("feedback must be an instance of CoSTEERMultiFeedback") + if len(evo.sub_workspace_list) != len(feedback): + raise ValueError("Length of sub_workspace_list must match length of feedback") # FIXME: when whould the feedback be None? failed_feedbacks = [ diff --git a/rdagent/components/coder/CoSTEER/evolving_strategy.py b/rdagent/components/coder/CoSTEER/evolving_strategy.py index fbbf3861..11c89296 100644 --- a/rdagent/components/coder/CoSTEER/evolving_strategy.py +++ b/rdagent/components/coder/CoSTEER/evolving_strategy.py @@ -122,7 +122,8 @@ class MultiProcessEvolvingStrategy(EvolvingStrategy): last_feedback = None if len(evolving_trace) > 0: last_feedback = evolving_trace[-1].feedback - assert isinstance(last_feedback, CoSTEERMultiFeedback) + if not isinstance(last_feedback, CoSTEERMultiFeedback): + raise TypeError("last_feedback must be of type CoSTEERMultiFeedback") # 1.找出需要evolve的task to_be_finished_task_index: list[int] = [] diff --git a/rdagent/components/coder/CoSTEER/knowledge_management.py b/rdagent/components/coder/CoSTEER/knowledge_management.py index d45e90f2..9edd39b0 100644 --- a/rdagent/components/coder/CoSTEER/knowledge_management.py +++ b/rdagent/components/coder/CoSTEER/knowledge_management.py @@ -1028,7 +1028,8 @@ class CoSTEERKnowledgeBaseV2(EvolvingKnowledgeBase): """ node_count = len(nodes) - assert node_count >= 2, "nodes length must >=2" + if node_count < 2: + raise ValueError("nodes length must >=2") intersection_node_list = [] if output_intersection_origin: origin_list = [] diff --git a/rdagent/components/coder/model_coder/eva_utils.py b/rdagent/components/coder/model_coder/eva_utils.py index 784e9909..f56fd98c 100644 --- a/rdagent/components/coder/model_coder/eva_utils.py +++ b/rdagent/components/coder/model_coder/eva_utils.py @@ -58,10 +58,12 @@ class ModelCodeEvaluator(CoSTEEREvaluator): model_execution_feedback: str = "", model_value_feedback: str = "", ): - assert isinstance(target_task, ModelTask) - assert isinstance(implementation, ModelFBWorkspace) - if gt_implementation is not None: - assert isinstance(gt_implementation, ModelFBWorkspace) + if not isinstance(target_task, ModelTask): + raise TypeError("target_task must be of type ModelTask") + if not isinstance(implementation, ModelFBWorkspace): + raise TypeError("implementation must be of type ModelFBWorkspace") + if gt_implementation is not None and not isinstance(gt_implementation, ModelFBWorkspace): + raise TypeError("gt_implementation must be of type ModelFBWorkspace") model_task_information = target_task.get_task_information() code = implementation.all_codes @@ -113,10 +115,12 @@ class ModelFinalEvaluator(CoSTEEREvaluator): model_value_feedback: str, model_code_feedback: str, ): - assert isinstance(target_task, ModelTask) - assert isinstance(implementation, ModelFBWorkspace) - if gt_implementation is not None: - assert isinstance(gt_implementation, ModelFBWorkspace) + if not isinstance(target_task, ModelTask): + raise TypeError("target_task must be of type ModelTask") + if not isinstance(implementation, ModelFBWorkspace): + raise TypeError("implementation must be of type ModelFBWorkspace") + if gt_implementation is not None and not isinstance(gt_implementation, ModelFBWorkspace): + raise TypeError("gt_implementation must be of type ModelFBWorkspace") system_prompt = T(".prompts:evaluator_final_feedback.system").r( scenario=( diff --git a/rdagent/components/document_reader/document_reader.py b/rdagent/components/document_reader/document_reader.py index 46e57d6b..e63c06a6 100644 --- a/rdagent/components/document_reader/document_reader.py +++ b/rdagent/components/document_reader/document_reader.py @@ -85,13 +85,16 @@ def load_and_process_one_pdf_by_azure_document_intelligence( def load_and_process_pdfs_by_azure_document_intelligence(path: Path) -> dict[str, str]: - assert RD_AGENT_SETTINGS.azure_document_intelligence_key is not None - assert RD_AGENT_SETTINGS.azure_document_intelligence_endpoint is not None + if RD_AGENT_SETTINGS.azure_document_intelligence_key is None: + raise AssertionError("azure_document_intelligence_key must be set") + if RD_AGENT_SETTINGS.azure_document_intelligence_endpoint is None: + raise AssertionError("azure_document_intelligence_endpoint must be set") content_dict = {} ab_path = path.resolve() if ab_path.is_file(): - assert ".pdf" in ab_path.suffixes, "The file must be a PDF file." + if ".pdf" not in ab_path.suffixes: + raise ValueError("The file must be a PDF file.") proc = load_and_process_one_pdf_by_azure_document_intelligence content_dict[str(ab_path)] = proc( ab_path, diff --git a/rdagent/components/loader/task_loader.py b/rdagent/components/loader/task_loader.py index 9fbb0ec6..86657331 100644 --- a/rdagent/components/loader/task_loader.py +++ b/rdagent/components/loader/task_loader.py @@ -87,7 +87,8 @@ class ModelWsLoader(WsLoader[ModelTask, ModelFBWorkspace]): self.path = Path(path) def load(self, task: ModelTask) -> ModelFBWorkspace: - assert task.name is not None + if task.name is None: + raise AssertionError("task.name should not be None") mti = ModelFBWorkspace(task) mti.prepare() with open(self.path / f"{task.name}.py", "r") as f: diff --git a/rdagent/oai/backend/base.py b/rdagent/oai/backend/base.py index 20853cad..69d71702 100644 --- a/rdagent/oai/backend/base.py +++ b/rdagent/oai/backend/base.py @@ -541,7 +541,8 @@ class APIBackend(ABC): **kwargs, ) -> str | list[list[float]]: """This function to share operation between embedding and chat completion""" - assert not (chat_completion and embedding), "chat_completion and embedding cannot be True at the same time" + if chat_completion and embedding: + raise ValueError("chat_completion and embedding cannot be True at the same time") max_retry = LLM_SETTINGS.max_retry if LLM_SETTINGS.max_retry is not None else max_retry timeout_count = 0 violation_count = 0 diff --git a/rdagent/scenarios/data_science/debug/data.py b/rdagent/scenarios/data_science/debug/data.py index b2c06ffa..346306b4 100644 --- a/rdagent/scenarios/data_science/debug/data.py +++ b/rdagent/scenarios/data_science/debug/data.py @@ -268,7 +268,8 @@ class JsonReducer(DataReducer): parent[key] = sampled # type: ignore # parent 是 list，key 是 index, list.__setitem__(key, sampled) self.sampled_files.extend([self.extract_filename(i) for i in sampled]) break - assert len(self.sampled_files) > 0 + if len(self.sampled_files) <= 0: + raise AssertionError("sampled_files must contain at least one file") return data def _find_all_lists( diff --git a/rdagent/scenarios/data_science/example/source_data/arf-12-hours-prediction-task/prepare.py b/rdagent/scenarios/data_science/example/source_data/arf-12-hours-prediction-task/prepare.py index d10f7e13..92bab740 100644 --- a/rdagent/scenarios/data_science/example/source_data/arf-12-hours-prediction-task/prepare.py +++ b/rdagent/scenarios/data_science/example/source_data/arf-12-hours-prediction-task/prepare.py @@ -56,14 +56,17 @@ sparse.save_npz(public / "test" / "X.npz", X_test) sparse.save_npz(public / "train" / "X.npz", X_train) df_train.to_csv(public / "train" / "ARF_12h.csv", index=False) -assert ( - X_train.shape[0] == df_train.shape[0] -), f"Mismatch: X_train rows ({X_train.shape[0]}) != df_train rows ({df_train.shape[0]})" -assert ( - X_test.shape[0] == df_test.shape[0] -), f"Mismatch: X_test rows ({X_test.shape[0]}) != df_test rows ({df_test.shape[0]})" -assert df_test.shape[1] == 2, "Public test set should have 2 columns" -assert df_train.shape[1] == 3, "Public train set should have 3 columns" -assert len(df_train) + len(df_test) == len( - df_label -), "Length of new_train and new_test should equal length of old_train" +if X_train.shape[0] != df_train.shape[0]: + raise ValueError( + f"Mismatch: X_train rows ({X_train.shape[0]}) != df_train rows ({df_train.shape[0]})" + ) +if X_test.shape[0] != df_test.shape[0]: + raise ValueError( + f"Mismatch: X_test rows ({X_test.shape[0]}) != df_test rows ({df_test.shape[0]})" + ) +if df_test.shape[1] != 2: + raise ValueError("Public test set should have 2 columns") +if df_train.shape[1] != 3: + raise ValueError("Public train set should have 3 columns") +if len(df_train) + len(df_test) != len(df_label): + raise ValueError("Length of new_train and new_test should equal length of old_train") diff --git a/rdagent/scenarios/data_science/loop.py b/rdagent/scenarios/data_science/loop.py index bdf02831..f6fce402 100644 --- a/rdagent/scenarios/data_science/loop.py +++ b/rdagent/scenarios/data_science/loop.py @@ -320,7 +320,8 @@ class DataScienceRDLoop(RDLoop): # only clean current workspace without affecting other loops. for k in "direct_exp_gen", "coding", "running": if k in prev_out and prev_out[k] is not None: - assert isinstance(prev_out[k], DSExperiment) + if not isinstance(prev_out[k], DSExperiment): + raise TypeError(f"prev_out[{k!r}] must be an instance of DSExperiment") clean_workspace(prev_out[k].experiment_workspace.workspace_path) # Backup the workspace (only necessary files are included) diff --git a/rdagent/scenarios/data_science/proposal/exp_gen/base.py b/rdagent/scenarios/data_science/proposal/exp_gen/base.py index d94a054a..f7f2e69c 100644 --- a/rdagent/scenarios/data_science/proposal/exp_gen/base.py +++ b/rdagent/scenarios/data_science/proposal/exp_gen/base.py @@ -213,7 +213,8 @@ class DSTrace(Trace[DataScienceScen, KnowledgeBase]): self, component: COMPONENT, search_list: list[tuple[DSExperiment, ExperimentFeedback]] = [] ) -> bool: for exp, fb in search_list: - assert isinstance(exp.hypothesis, DSHypothesis), "Hypothesis should be DSHypothesis (and not None)" + if not isinstance(exp.hypothesis, DSHypothesis): + raise TypeError("Hypothesis should be DSHypothesis (and not None)") if exp.hypothesis.component == component and fb: return True return False diff --git a/rdagent/scenarios/data_science/proposal/exp_gen/merge.py b/rdagent/scenarios/data_science/proposal/exp_gen/merge.py index 6f943441..75b5bb38 100644 --- a/rdagent/scenarios/data_science/proposal/exp_gen/merge.py +++ b/rdagent/scenarios/data_science/proposal/exp_gen/merge.py @@ -377,7 +377,8 @@ class ExpGen2TraceAndMergeV2(ExpGen): if DS_RD_SETTING.enable_multi_version_exp_gen: exp_gen_version_list = DS_RD_SETTING.exp_gen_version_list.split(",") for version in exp_gen_version_list: - assert version in ["v3", "v2", "v1"] + if version not in ["v3", "v2", "v1"]: + raise ValueError(f"version must be 'v1', 'v2', or 'v3', got {version!r}") if len(trace.hist) == 0: # set the proposal version for the first sub-trace diff --git a/rdagent/scenarios/data_science/proposal/exp_gen/proposal.py b/rdagent/scenarios/data_science/proposal/exp_gen/proposal.py index 1696387e..4869a8cf 100644 --- a/rdagent/scenarios/data_science/proposal/exp_gen/proposal.py +++ b/rdagent/scenarios/data_science/proposal/exp_gen/proposal.py @@ -339,7 +339,8 @@ class DSProposalV1ExpGen(ExpGen): eda_output = sota_exp.experiment_workspace.file_dict.get("EDA.md", None) scenario_desc = trace.scen.get_scenario_all_desc(eda_output=eda_output) - assert sota_exp is not None, "SOTA experiment is not provided." + if sota_exp is None: + raise ValueError("SOTA experiment is not provided.") last_exp = trace.last_exp() # exp_and_feedback = trace.hist[-1] # last_exp = exp_and_feedback[0] @@ -445,8 +446,10 @@ class DSProposalV1ExpGen(ExpGen): json_target_type=dict[str, dict[str, str | dict] | str], ) ) - assert "hypothesis_proposal" in resp_dict, "Hypothesis proposal not provided." - assert "task_design" in resp_dict, "Task design not provided." + if "hypothesis_proposal" not in resp_dict: + raise ValueError("Hypothesis proposal not provided.") + if "task_design" not in resp_dict: + raise ValueError("Task design not provided.") task_class = component_info["task_class"] hypothesis_proposal = resp_dict.get("hypothesis_proposal", {}) hypothesis = DSHypothesis( @@ -1149,8 +1152,10 @@ You help users retrieve relevant knowledge from community discussions and public ) response_dict = json.loads(response) - assert response_dict.get("component") in HypothesisComponent.__members__, f"Invalid component" - assert response_dict.get("hypothesis") is not None, f"Invalid hypothesis" + if response_dict.get("component") not in HypothesisComponent.__members__: + raise ValueError(f"Invalid component: {response_dict.get('component')}") + if response_dict.get("hypothesis") is None: + raise ValueError("Invalid hypothesis") return response_dict # END: for support llm-based hypothesis selection ----- @@ -1253,7 +1258,8 @@ You help users retrieve relevant knowledge from community discussions and public description=task_desc, ) - assert isinstance(task, PipelineTask), f"Task {task_name} is not a PipelineTask, got {type(task)}" + if not isinstance(task, PipelineTask): + raise TypeError(f"Task {task_name} is not a PipelineTask, got {type(task)}") # only for llm with response schema.(TODO: support for non-schema llm?) # If the LLM provides a "packages" field (list[str]), compute runtime environment now and cache it for subsequent prompts in later loops. if isinstance(task_dict, dict) and "packages" in task_dict and isinstance(task_dict["packages"], list): diff --git a/rdagent/scenarios/kaggle/experiment/scenario.py b/rdagent/scenarios/kaggle/experiment/scenario.py index acf0ad8b..480bc4b9 100644 --- a/rdagent/scenarios/kaggle/experiment/scenario.py +++ b/rdagent/scenarios/kaggle/experiment/scenario.py @@ -165,7 +165,8 @@ class KGScenario(Scenario): return data_info def output_format(self, tag=None) -> str: - assert tag in [None, "feature", "model"] + if tag not in [None, "feature", "model"]: + raise ValueError(f"tag must be None, 'feature', or 'model', got {tag!r}") feature_output_format = f"""The feature code should output following the format: {T(".prompts:kg_feature_output_format").r()}""" model_output_format = f"""The model code should output following the format:\n""" + T( @@ -180,7 +181,8 @@ class KGScenario(Scenario): return model_output_format def interface(self, tag=None) -> str: - assert tag in [None, "feature", "XGBoost", "RandomForest", "LightGBM", "NN"] + if tag not in [None, "feature", "XGBoost", "RandomForest", "LightGBM", "NN"]: + raise ValueError(f"tag must be None, 'feature', 'XGBoost', 'RandomForest', 'LightGBM', or 'NN', got {tag!r}") feature_interface = f"""The feature code should follow the interface: {T(".prompts:kg_feature_interface").r()}""" if tag == "feature": @@ -195,7 +197,8 @@ class KGScenario(Scenario): return model_interface def simulator(self, tag=None) -> str: - assert tag in [None, "feature", "model"] + if tag not in [None, "feature", "model"]: + raise ValueError(f"tag must be None, 'feature', or 'model', got {tag!r}") kg_feature_simulator = ( "The feature code will be sent to the simulator:\n" + T(".prompts:kg_feature_simulator").r() diff --git a/rdagent/scenarios/kaggle/kaggle_crawler.py b/rdagent/scenarios/kaggle/kaggle_crawler.py index 3b4c590b..c8d518d6 100644 --- a/rdagent/scenarios/kaggle/kaggle_crawler.py +++ b/rdagent/scenarios/kaggle/kaggle_crawler.py @@ -87,7 +87,12 @@ def crawl_descriptions( content = e.get_attribute("innerHTML") contents.append(content) - assert len(subtitles) == len(contents) + 1 and subtitles[-1] == "Citation" + if not (len(subtitles) == len(contents) + 1 and subtitles[-1] == "Citation"): + raise AssertionError( + f"Expected len(contents)+1 == len(subtitles) and last subtitle == 'Citation', " + f"got len(subtitles)={len(subtitles)}, len(contents)={len(contents)}, " + f"last subtitle={subtitles[-1]!r}" + ) for i in range(len(subtitles) - 1): descriptions[subtitles[i]] = contents[i] diff --git a/rdagent/scenarios/kaggle/proposal/proposal.py b/rdagent/scenarios/kaggle/proposal/proposal.py index 551acfa4..30640ab3 100644 --- a/rdagent/scenarios/kaggle/proposal/proposal.py +++ b/rdagent/scenarios/kaggle/proposal/proposal.py @@ -307,7 +307,8 @@ class KGHypothesisGen(FactorAndModelHypothesisGen): class KGHypothesis2Experiment(FactorAndModelHypothesis2Experiment): def prepare_context(self, hypothesis: Hypothesis, trace: Trace) -> Tuple[dict, bool]: scenario = trace.scen.get_scenario_all_desc(filtered_tag="hypothesis_and_experiment") - assert isinstance(hypothesis, KGHypothesis) + if not isinstance(hypothesis, KGHypothesis): + raise TypeError("hypothesis must be an instance of KGHypothesis") experiment_output_format = ( T("scenarios.kaggle.prompts:feature_experiment_output_format").r() if hypothesis.action in [KG_ACTION_FEATURE_ENGINEERING, KG_ACTION_FEATURE_PROCESSING] diff --git a/rdagent/scenarios/qlib/experiment/quant_experiment.py b/rdagent/scenarios/qlib/experiment/quant_experiment.py index 63e56d33..d18c29c6 100644 --- a/rdagent/scenarios/qlib/experiment/quant_experiment.py +++ b/rdagent/scenarios/qlib/experiment/quant_experiment.py @@ -56,7 +56,8 @@ class QlibQuantScenario(Scenario): ) def background(self, tag=None) -> str: - assert tag in [None, "factor", "model"] + if tag not in [None, "factor", "model"]: + raise ValueError(f"tag must be None, 'factor', or 'model', got {tag!r}") quant_background = "The background of the scenario is as follows:\n" + T(".prompts:qlib_quant_background").r( runtime_environment=self.get_runtime_environment(), ) @@ -83,7 +84,8 @@ class QlibQuantScenario(Scenario): return self._source_data def output_format(self, tag=None) -> str: - assert tag in [None, "factor", "model"] + if tag not in [None, "factor", "model"]: + raise ValueError(f"tag must be None, 'factor', or 'model', got {tag!r}") factor_output_format = ( "The factor code should output the following format:\n" + T(".prompts:qlib_factor_output_format").r() ) @@ -99,7 +101,8 @@ class QlibQuantScenario(Scenario): return model_output_format def interface(self, tag=None) -> str: - assert tag in [None, "factor", "model"] + if tag not in [None, "factor", "model"]: + raise ValueError(f"tag must be None, 'factor', or 'model', got {tag!r}") factor_interface = ( "The factor code should be written in the following interface:\n" + T(".prompts:qlib_factor_interface").r() ) @@ -115,7 +118,8 @@ class QlibQuantScenario(Scenario): return model_interface def simulator(self, tag=None) -> str: - assert tag in [None, "factor", "model"] + if tag not in [None, "factor", "model"]: + raise ValueError(f"tag must be None, 'factor', or 'model', got {tag!r}") factor_simulator = "The factor code will be sent to the simulator:\n" + T(".prompts:qlib_factor_simulator").r() model_simulator = "The model code will be sent to the simulator:\n" + T(".prompts:qlib_model_simulator").r() @@ -185,7 +189,8 @@ class QlibQuantScenario(Scenario): return common_description(action) + interface(action) + output(action) + simulator(action) def get_runtime_environment(self, tag: str = None) -> str: - assert tag in [None, "factor", "model"] + if tag not in [None, "factor", "model"]: + raise ValueError(f"tag must be None, 'factor', or 'model', got {tag!r}") if tag is None or tag == "factor": # Use factor env to get the runtime environment diff --git a/rdagent/utils/env.py b/rdagent/utils/env.py index f3b46521..67c73abf 100644 --- a/rdagent/utils/env.py +++ b/rdagent/utils/env.py @@ -620,7 +620,8 @@ class LocalEnv(Env[ASpecificLocalConf]): for lp, rp in running_extra_volume.items(): volumes[lp] = rp - assert local_path is not None, "local_path should not be None" + if local_path is None: + raise ValueError("local_path should not be None") volumes = normalize_volumes(volumes, local_path) @contextlib.contextmanager @@ -1472,7 +1473,8 @@ class DockerEnv(Env[DockerConf]): cpu_count=self.conf.cpu_count, # Set CPU limit **self._gpu_kwargs(client), ) - assert container is not None # Ensure container was created successfully + if container is None: + raise AssertionError("Docker container was not created successfully") logs = container.logs(stream=True) print(Rule("[bold green]Docker Logs Begin[/bold green]", style="dark_orange")) table = Table(title="Run Info", show_header=False) diff --git a/rdagent/utils/workflow/tracking.py b/rdagent/utils/workflow/tracking.py index 598b16a7..c721b9a8 100644 --- a/rdagent/utils/workflow/tracking.py +++ b/rdagent/utils/workflow/tracking.py @@ -84,7 +84,8 @@ class WorkflowTracker: # Log timer status if timer is started if self.loop_base.timer.started: remain_time = self.loop_base.timer.remain_time() - assert remain_time is not None + if remain_time is None: + raise AssertionError("remain_time should not be None") mlflow.log_metric("remain_time", remain_time.total_seconds()) mlflow.log_metric( "remain_percent",