feat: add eda to data science scenario (#639)

* add eda to data science scenario

* fix CI
This commit is contained in:
Xu Yang
2025-02-26 22:35:44 +08:00
committed by GitHub
parent d7da15c826
commit a57e625b17
17 changed files with 107 additions and 10 deletions
@@ -31,7 +31,6 @@ class WorkflowMultiProcessEvolvingStrategy(MultiProcessEvolvingStrategy):
workspace: FBWorkspace | None = None,
prev_task_feedback: CoSTEERSingleFeedback | None = None,
) -> dict[str, str]:
# competition_info = self.scen.competition_descriptions
workflow_information_str = target_task.get_task_information()
# 1. query
@@ -57,7 +56,7 @@ class WorkflowMultiProcessEvolvingStrategy(MultiProcessEvolvingStrategy):
# 2. code
system_prompt = T(".prompts:workflow_coder.system").r(
task_desc=workflow_information_str,
competition_info=self.scen.get_competition_full_desc(),
competition_info=self.scen.get_scenario_all_desc(),
queried_similar_successful_knowledge=queried_similar_successful_knowledge,
queried_former_failed_knowledge=queried_former_failed_knowledge[0],
)
@@ -70,10 +70,10 @@ class WorkflowGeneralCaseSpecEvaluator(CoSTEEREvaluator):
# mde.prepare()
# Clean the scores.csv & submission.csv.
stdout = implementation.execute(env=de, entry=f"rm submission.csv scores.csv")
implementation.execute(env=de, entry=f"rm submission.csv scores.csv")
fname = "main.py"
stdout = implementation.execute(env=de, entry=f"python {fname}")
stdout = implementation.execute(env=de, entry=f"python main.py")
stdout = re.sub(r"=== Start of EDA part ===(.*)=== End of EDA part ===", "", stdout)
# Check score file
score_fp = implementation.workspace_path / "scores.csv"