feat: make spec optional (#719)

* feat: Add spec_enabled configuration for data science settings

* make spec alternative

* change spec logic in exp_gen

* remove some general texts

* align

---------

Co-authored-by: Young <afe.young@gmail.com>
Co-authored-by: yuanteli <1957922024@qq.com>

rdagent/components/coder/data_science/feature/__init__.py

@@ -1,6 +1,8 @@
 import json
+from pathlib import Path
 from typing import Dict
 
+from rdagent.app.data_science.conf import DS_RD_SETTING
 from rdagent.components.coder.CoSTEER import CoSTEER
 from rdagent.components.coder.CoSTEER.evaluators import (
     CoSTEERMultiEvaluator,
@@ -22,6 +24,8 @@ from rdagent.oai.llm_utils import APIBackend
 from rdagent.utils.agent.ret import PythonAgentOut
 from rdagent.utils.agent.tpl import T
 
+DIRNAME = Path(__file__).absolute().resolve().parent
+
 
 class FeatureMultiProcessEvolvingStrategy(MultiProcessEvolvingStrategy):
     def implement_one_task(
@@ -64,8 +68,16 @@ class FeatureMultiProcessEvolvingStrategy(MultiProcessEvolvingStrategy):
             queried_former_failed_knowledge=queried_former_failed_knowledge[0],
             out_spec=PythonAgentOut.get_spec(),
         )
+        code_spec = (
+            workspace.file_dict["spec/feature.md"]
+            if DS_RD_SETTING.spec_enabled
+            else T("scenarios.data_science.share:component_spec.general").r(
+                spec=T("scenarios.data_science.share:component_spec.FeatureEng").r(),
+                test_code=(DIRNAME / "eval_tests" / "feature_test.txt").read_text(),
+            )
+        )
         user_prompt = T(".prompts:feature_coder.user").r(
-            feature_spec=workspace.file_dict["spec/feature.md"],
+            code_spec=code_spec,
             latest_code=workspace.file_dict.get("feature.py"),
             latest_code_feedback=prev_task_feedback,
         )

rdagent/components/coder/data_science/feature/eval_tests/feature_test.txt

@@ -1,10 +1,5 @@
 """
-A qualified data loader should support following features
-- successfully run
-- len(test) == len(test_ids) == submission length
-- len(train) == len(y)
-
-Please make sure the stdout is rich enough to support informative feedback
+Tests for `feat_eng` in feature.py
 """
 
 import pickle

rdagent/components/coder/data_science/feature/prompts.yaml

@@ -55,8 +55,8 @@ feature_coder:
     {% endif %}
   
   user: |-
-    --------- Feature Processing Specification ---------
-    {{ feature_spec }}
+    --------- Code Specification ---------
+    {{ code_spec }}
 
     {% if latest_code %}
     --------- Former code ---------