mirror of
https://github.com/NicolasBohn/NexQuant.git
synced 2026-07-28 16:07:46 +00:00
Tim
6f9843a7df
* custom data * fix: simplify competition check and log local description file * no sample data * feat: add test evaluation module with error handling support * fix: update eval path to use eval_sub_dir and add valid_check TODO * refactor: add MLETestEval check to conditionally run grading steps * avoid blank stdout * valid in testeval * rename test.csv to avoid conflict * Support Disabling sample submission * refactoring * fix: remove DS_KAGGLE_DATA and update prompt instructions * add try for grade * ignore submission * fix: remove tee from eval command and warn about pipeline exit code detection * optional to use raw description * support old data * add execution result to stdout * add metric to raw description * custom data explain * add debug_path * rst update --------- Co-authored-by: Young <afe.young@gmail.com>
72 lines
2.2 KiB
Python
72 lines
2.2 KiB
Python
from typing import Literal
|
|
|
|
from rdagent.app.data_science.conf import DS_RD_SETTING
|
|
from rdagent.components.coder.CoSTEER.config import CoSTEERSettings
|
|
from rdagent.utils.env import (
|
|
CondaConf,
|
|
DockerEnv,
|
|
DSDockerConf,
|
|
Env,
|
|
LocalEnv,
|
|
MLEBDockerConf,
|
|
MLECondaConf,
|
|
)
|
|
|
|
|
|
class DSCoderCoSTEERSettings(CoSTEERSettings):
|
|
"""Data Science CoSTEER settings"""
|
|
|
|
class Config:
|
|
env_prefix = "DS_Coder_CoSTEER_"
|
|
|
|
max_seconds: int = 2400
|
|
env_type: str = "docker"
|
|
# TODO: extract a function for env and conf.
|
|
|
|
|
|
def get_ds_env(
|
|
conf_type: Literal["kaggle", "mlebench"] = "kaggle",
|
|
extra_volumes: dict = {},
|
|
running_timeout_period: int = (
|
|
DS_RD_SETTING.debug_timeout if DS_RD_SETTING.sample_data else DS_RD_SETTING.full_timeout
|
|
),
|
|
) -> Env:
|
|
"""
|
|
Retrieve the appropriate environment configuration based on the env_type setting.
|
|
|
|
Returns:
|
|
Env: An instance of the environment configured either as DockerEnv or LocalEnv.
|
|
|
|
Raises:
|
|
ValueError: If the env_type is not recognized.
|
|
"""
|
|
conf = DSCoderCoSTEERSettings()
|
|
assert conf_type in ["kaggle", "mlebench"], f"Unknown conf_type: {conf_type}"
|
|
|
|
if conf.env_type == "docker":
|
|
env_conf = DSDockerConf() if conf_type == "kaggle" else MLEBDockerConf()
|
|
env = DockerEnv(conf=env_conf)
|
|
elif conf.env_type == "conda":
|
|
env = LocalEnv(
|
|
conf=(
|
|
CondaConf(conda_env_name=conf_type) if conf_type == "kaggle" else MLECondaConf(conda_env_name=conf_type)
|
|
)
|
|
)
|
|
else:
|
|
raise ValueError(f"Unknown env type: {conf.env_type}")
|
|
env.conf.extra_volumes = extra_volumes
|
|
env.conf.running_timeout_period = running_timeout_period
|
|
return env
|
|
|
|
|
|
def get_clear_ws_cmd(stage: Literal["before_training", "before_inference"] = "before_training") -> str:
|
|
"""
|
|
Clean the files in workspace to a specific stage
|
|
"""
|
|
assert stage in ["before_training", "before_inference"], f"Unknown stage: {stage}"
|
|
if DS_RD_SETTING.enable_model_dump and stage == "before_training":
|
|
cmd = "rm -r submission.csv scores.csv models"
|
|
else:
|
|
cmd = "rm submission.csv scores.csv"
|
|
return cmd
|