From b8fb9cf3b403ac3d11829285437b7878eb7d5bbb Mon Sep 17 00:00:00 2001 From: Roland Minrui <114476598+RolandMinrui@users.noreply.github.com> Date: Mon, 12 May 2025 17:20:26 +0800 Subject: [PATCH] fix coder bug (#868) Co-authored-by: Xu --- rdagent/components/coder/data_science/pipeline/prompts.yaml | 4 ++-- rdagent/scenarios/data_science/share.yaml | 5 +++-- 2 files changed, 5 insertions(+), 4 deletions(-) diff --git a/rdagent/components/coder/data_science/pipeline/prompts.yaml b/rdagent/components/coder/data_science/pipeline/prompts.yaml index 4331ce0b..0147d197 100644 --- a/rdagent/components/coder/data_science/pipeline/prompts.yaml +++ b/rdagent/components/coder/data_science/pipeline/prompts.yaml @@ -115,9 +115,9 @@ pipeline_eval: {% if is_sub_enabled %} ## Evaluation Scope Your focus is to check whether the workflow code: - Step 1: Executes successfully, correctly generating a final submission. + Step 1: Executes successfully without any errors. Please distinguish between the errors and warnings. - Step 2: Generates predictions in the correct format, ensuring: they align with the submission structure, the index and column names should match the sample, and the content should not be empty or apparently incorrect. + Step 2: Correctly generates a final submission in the correct format, ensuring: they align with the submission structure, the index names and column names should match the sample, and the items should not be empty or apparently incorrect. Step 3: Aligns with the competition requirements. This includes: - CAREFULLY ANALYZE WHETHER THE EXPERIMENTAL SETUP AND CODE MAY CAUSE MISALIGNMENT BETWEEN VALIDATION AND TEST PERFORMANCE. diff --git a/rdagent/scenarios/data_science/share.yaml b/rdagent/scenarios/data_science/share.yaml index 6118f03f..437951ee 100644 --- a/rdagent/scenarios/data_science/share.yaml +++ b/rdagent/scenarios/data_science/share.yaml @@ -258,8 +258,9 @@ component_spec: {% endraw %} Pipeline: |- - 0. Program Running: - - The program will be runned using python main.py **without any parameters**. Ensure no optional parameters are used in main.py. + 0. Program Execution: + - The workflow will be executed by running `python main.py` with no command-line arguments. Ensure that `main.py` does not require or expect any parameters. + - The working directory will only contain `main.py`. Any additional files required for execution must be downloaded or generated by `main.py` itself. 1. File Handling: - Handle file encoding and delimiters appropriately.