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

* 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
@@ -74,6 +74,7 @@ class EnsembleMultiProcessEvolvingStrategy(MultiProcessEvolvingStrategy):
queried_former_failed_knowledge=(
queried_former_failed_knowledge[0] if queried_former_failed_knowledge else None
),
all_code=workspace.all_codes,
)
user_prompt = T(".prompts:ensemble_coder.user").r(
ensemble_spec=workspace.file_dict["spec/ensemble.md"],
@@ -1,4 +1,5 @@
import json
import re
from pathlib import Path
from jinja2 import Environment, StrictUndefined
@@ -69,6 +70,7 @@ class EnsembleCoSTEEREvaluator(CoSTEEREvaluator):
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
@@ -35,7 +35,10 @@ ensemble_coder:
{% endfor %}
{% endif %}
You should avoid using logging module to output information in your generated code, and instead use the print() function.
## Guidelines
1. The function's code is associated with several other functions including a data loader, feature engineering, and model training. all codes are as follows:
{{ all_code }}
2. You should avoid using logging module to output information in your generated code, and instead use the print() function.
## Output Format
Please response the code in the following json format. Here is an example structure for the JSON output: