gavindiaz/NexQuant
1
0
Fork 0
mirror of https://github.com/NicolasBohn/NexQuant.git synced 2026-07-27 23:47:46 +00:00
Code Issues Packages Projects Releases Wiki Activity

fix: fix a minor bug in DS eval (#1012)

Browse Source
This commit is contained in:
Yuante Li
2025-07-02 23:31:29 +08:00
committed by GitHub
parent d589b859d0
commit fb8f2b561e
8 changed files with 12 additions and 12 deletions
Download Patch File Download Diff File Expand all files Collapse all files
rdagent/components/coder/data_science/ensemble/eval.py
+1 -1
View File
@@ -65,7 +65,7 @@ class EnsembleCoSTEEREvaluator(CoSTEEREvaluator):
implementation.inject_files(**{fname: test_code})
result = implementation.run(env=env, entry=f"python {fname}")
stdout = result.stdout
ret_code = result.ret_code
ret_code = result.exit_code
stdout += f"\nNOTE: the above scripts run with return code {ret_code}"
rdagent/components/coder/data_science/feature/eval.py
+2 -2
View File
@@ -52,7 +52,7 @@ class FeatureCoSTEEREvaluator(CoSTEEREvaluator):
result = implementation.run(env=env, entry=f"python {fname}")
if "main.py" in implementation.file_dict and result.ret_code == 0:
if "main.py" in implementation.file_dict and result.exit_code == 0:
workflow_stdout = implementation.execute(env=env, entry="python main.py")
workflow_stdout = remove_eda_part(workflow_stdout)
else:
@@ -76,6 +76,6 @@ class FeatureCoSTEEREvaluator(CoSTEEREvaluator):
user_prompt=user_prompt,
init_kwargs_update_func=FeatureEvalFeedback.val_and_update_init_dict,
)
fb.final_decision = fb.final_decision and result.ret_code == 0
fb.final_decision = fb.final_decision and result.exit_code == 0
return fb
rdagent/components/coder/data_science/model/eval.py
+2 -2
View File
@@ -69,7 +69,7 @@ class ModelGeneralCaseSpecEvaluator(CoSTEEREvaluator):
implementation.inject_files(**{fname: test_code})
result = implementation.run(env=env, entry=f"python {fname}")
stdout = result.stdout
ret_code = result.ret_code
ret_code = result.exit_code
if stdout is None:
raise CoderError(
@@ -115,6 +115,6 @@ class ModelGeneralCaseSpecEvaluator(CoSTEEREvaluator):
user_prompt=user_prompt,
init_kwargs_update_func=ModelSingleFeedback.val_and_update_init_dict,
)
fb.final_decision = fb.final_decision and result.ret_code == 0
fb.final_decision = fb.final_decision and result.exit_code == 0
return fb
rdagent/components/coder/data_science/pipeline/eval.py
+2 -2
View File
@@ -59,7 +59,7 @@ class PipelineCoSTEEREvaluator(CoSTEEREvaluator):
implementation.execute(env=env, entry=get_clear_ws_cmd())
result = implementation.run(env=env, entry=f"python -m coverage run main.py")
implementation.running_info.running_time = result.running_time
execute_ret_code = result.ret_code
execute_ret_code = result.exit_code
stdout = remove_eda_part(result.stdout)
stdout += f"The code executed {'successfully' if execute_ret_code == 0 else 'failed'}."
@@ -109,7 +109,7 @@ class PipelineCoSTEEREvaluator(CoSTEEREvaluator):
# stdout += "----Submission Check 1-----\n"
submission_result = implementation.run(env=env, entry="python test/submission_format_test.py")
submission_check_out = submission_result.stdout
submission_ret_code = submission_result.ret_code
submission_ret_code = submission_result.exit_code
if DS_RD_SETTING.rule_base_eval:
if execute_ret_code == 0 and score_ret_code == 0 and submission_ret_code == 0:
return PipelineSingleFeedback(
rdagent/components/coder/data_science/raw_data_loader/eval.py
+1 -1
View File
@@ -54,7 +54,7 @@ class DataLoaderCoSTEEREvaluator(CoSTEEREvaluator):
implementation.inject_files(**{fname: test_code})
result = implementation.run(env=env, entry=f"python {fname}")
stdout = result.stdout
ret_code = result.ret_code
ret_code = result.exit_code
match = re.search(r"(.*?)=== Start of EDA part ===(.*)=== End of EDA part ===(.*)", stdout, re.DOTALL)
stdout_part_1, eda_output, stdout_part_2 = match.groups() if match else (stdout, None, "")
stdout = stdout_part_1 + stdout_part_2
rdagent/components/coder/data_science/workflow/eval.py
+1 -1
View File
@@ -123,7 +123,7 @@ class WorkflowGeneralCaseSpecEvaluator(CoSTEEREvaluator):
# stdout += "----Submission Check 1-----\n"
submission_result = implementation.run(env=env, entry="python test/submission_format_test.py")
submission_check_out = submission_result.stdout
submission_ret_code = submission_result.ret_code
submission_ret_code = submission_result.exit_code
stdout += "\n" + submission_check_out
system_prompt = T(".prompts:workflow_eval.system").r(
rdagent/scenarios/data_science/dev/runner/eval.py
+1 -1
View File
@@ -55,7 +55,7 @@ class DSCoSTEERCoSTEEREvaluator(CoSTEEREvaluator):
# execute workflow
result = implementation.run(env=env, entry="python -m coverage run main.py")
stdout = result.stdout
execute_ret_code = result.ret_code
execute_ret_code = result.exit_code
implementation.running_info.running_time = result.running_time
match = re.search(r"(.*?)=== Start of EDA part ===(.*)=== End of EDA part ===", stdout, re.DOTALL)
rdagent/scenarios/data_science/test_eval.py
+2 -2
View File
@@ -82,7 +82,7 @@ class TestEval(TestEvalBase):
**{file: workspace.DEL_KEY for file in ["submission_format_valid.py", "submission_test.csv"]}
)
workspace.inject_files(**{"test/mle_submission_format_test.output": submission_result.stdout})
return submission_result.stdout, submission_result.ret_code
return submission_result.stdout, submission_result.exit_code
def enabled(self, competition) -> bool:
return Path(
@@ -119,7 +119,7 @@ class MLETestEval(TestEvalBase):
submission_result = workspace.run(env=self.env, entry="python test/mle_submission_format_test.py")
workspace.inject_files(**{"test/mle_submission_format_test.output": submission_result.stdout})
return submission_result.stdout, submission_result.ret_code
return submission_result.stdout, submission_result.exit_code
def enabled(self, competition) -> bool:
return True