gavindiaz/NexQuant
1
0
Fork 0
mirror of https://github.com/NicolasBohn/NexQuant.git synced 2026-07-29 08:27:43 +00:00
Code Issues Packages Projects Releases Wiki Activity

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

Browse Source 
* 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
Download Patch File Download Diff File Expand all files Collapse all files
rdagent/components/coder/data_science/raw_data_loader/eval.py
+8
View File
@@ -1,6 +1,7 @@
# tess successfully running.
# (GPT) if it aligns with the spec & rationality of the spec.
import json
import re
from pathlib import Path
from rdagent.app.data_science.conf import DS_RD_SETTING
@@ -58,9 +59,15 @@ class DataLoaderCoSTEEREvaluator(CoSTEEREvaluator):
test_code = (DIRNAME / "eval_tests" / "data_loader_test.txt").read_text()
implementation.inject_files(**{fname: test_code})
stdout = implementation.execute(env=de, entry=f"python {fname}")
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
if eda_output is not None and len(eda_output.split(" ")) > 10000:
eda_output += "Length of EDA output is too long, truncated. Please reject this implementation and motivate it to reduce the length of EDA output."
if "main.py" in implementation.file_dict:
workflow_stdout = implementation.execute(env=de, entry="python main.py")
workflow_stdout = re.sub(r"=== Start of EDA part ===(.*)=== End of EDA part ===", "", workflow_stdout)
else:
workflow_stdout = None
@@ -73,6 +80,7 @@ class DataLoaderCoSTEEREvaluator(CoSTEEREvaluator):
)
user_prompt = T(".prompts:data_loader_eval.user").r(
stdout=stdout,
eda_output=eda_output,
workflow_stdout=workflow_stdout,
)