Files
NexQuant/rdagent/components/coder/data_science/raw_data_loader
you-n-g 918b0b0d43 feat: condaenv & full docker env (#668)
* use conda to run kaggle and mlebench code

* refactor: Simplify environment configuration and execution logic

* add setting to use local env in ds

* refine dockerfile

* fix: Move MLEBDockerEnv initialization inside conditionals &  fix condaenv

* refactor: reformat code for better readability and consistency

* feat: add conda env to all envs.

* fix: fix bugs when run loop

* refactor: Simplify DockerEnv configuration in mle_summary.py

* fix image bug

* style: reformat code for better readability and consistency

* change commit

* feat: Add entrypoint script for sing_docker scenario in rdagent

* refactor: add Any type hints and comments for clarity in env.py

* feat: Create log directory if it doesn't exist in entrypoint script

* feat: Add debug mode and list root directory in entrypoint script

* fix: Remove specific branch checkout in Dockerfile for RD-Agent

* fix: Add competition argument to loop.py script execution

* fix: Correct directory navigation and dependency installation in entrypoint.sh

* fix: Correct user ownership assignment in entrypoint script

* refactor: Comment out redundant log copying to RD_OUTPUT_DIR

* fix: Unset LOG_TRACE_PATH to prevent log contamination in entrypoint.sh

---------

Co-authored-by: Xu Yang <peteryang@vip.qq.com>
2025-03-12 11:36:28 +08:00
..
2025-03-12 11:36:28 +08:00

CoSTEER

  • subworkspace使用主experiment_workspace RD-Agent/rdagent/scenarios/data_science/experiment/experiment.py

evolving_strategy ( implement_one_task() )

  1. xxxTask (in exp.py)
    • spec
    • description

evaluator

  1. queried_knowledge部分 共用
  2. eval_test脚本