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: add async to direct_exp_gen avoid infinite loop (#992)

Browse Source 
* refactor: convert direct_exp_gen to async and enforce parallel limit

* fix bug

* change coroutine function position

* fix fin_quant's direct_exp_gen

* format with isort

---------

Co-authored-by: Bowen Xian <xianbowen@outlook.com>
Co-authored-by: SunsetWolf <Lv.Linlang@hotmail.com>
This commit is contained in:
you-n-g
2025-06-26 22:10:52 +08:00
committed by GitHub
parent a439d9ef2e
commit defefd37f5
4 changed files with 39 additions and 30 deletions
Download Patch File Download Diff File Expand all files Collapse all files
rdagent/app/qlib_rd_loop/factor_from_report.py
+17 -14
View File
@@ -11,6 +11,7 @@ from rdagent.components.document_reader.document_reader import (
extract_first_page_screenshot_from_pdf,
load_and_process_pdfs_by_langchain,
)
from rdagent.core.conf import RD_AGENT_SETTINGS
from rdagent.core.proposal import Hypothesis
from rdagent.log import rdagent_logger as logger
from rdagent.oai.llm_utils import APIBackend
@@ -105,21 +106,23 @@ class FactorReportLoop(FactorRDLoop, metaclass=LoopMeta):
self.loop_n = min(len(self.judge_pdf_data_items), FACTOR_FROM_REPORT_PROP_SETTING.report_limit)
def direct_exp_gen(self, prev_out: dict[str, Any]):
async def direct_exp_gen(self, prev_out: dict[str, Any]):
while True:
report_file_path = self.judge_pdf_data_items[self.loop_idx]
logger.info(f"Processing number {self.loop_idx} report: {report_file_path}")
exp = extract_hypothesis_and_exp_from_reports(str(report_file_path))
if exp is None:
continue
exp.based_experiments = [QlibFactorExperiment(sub_tasks=[], hypothesis=exp.hypothesis)] + [
t[0] for t in self.trace.hist if t[1]
]
exp.sub_workspace_list = exp.sub_workspace_list[: FACTOR_FROM_REPORT_PROP_SETTING.max_factors_per_exp]
exp.sub_tasks = exp.sub_tasks[: FACTOR_FROM_REPORT_PROP_SETTING.max_factors_per_exp]
logger.log_object(exp.hypothesis, tag="hypothesis generation")
logger.log_object(exp.sub_tasks, tag="experiment generation")
return exp
if self.get_unfinished_loop_cnt(self.loop_idx) < RD_AGENT_SETTINGS.get_max_parallel():
report_file_path = self.judge_pdf_data_items[self.loop_idx]
logger.info(f"Processing number {self.loop_idx} report: {report_file_path}")
exp = extract_hypothesis_and_exp_from_reports(str(report_file_path))
if exp is None:
continue
exp.based_experiments = [QlibFactorExperiment(sub_tasks=[], hypothesis=exp.hypothesis)] + [
t[0] for t in self.trace.hist if t[1]
]
exp.sub_workspace_list = exp.sub_workspace_list[: FACTOR_FROM_REPORT_PROP_SETTING.max_factors_per_exp]
exp.sub_tasks = exp.sub_tasks[: FACTOR_FROM_REPORT_PROP_SETTING.max_factors_per_exp]
logger.log_object(exp.hypothesis, tag="hypothesis generation")
logger.log_object(exp.sub_tasks, tag="experiment generation")
return exp
await asyncio.sleep(1)
def coding(self, prev_out: dict[str, Any]):
exp = self.coder.develop(prev_out["direct_exp_gen"])
rdagent/app/qlib_rd_loop/quant.py
+13 -9
View File
@@ -10,6 +10,7 @@ import fire
from rdagent.app.qlib_rd_loop.conf import QUANT_PROP_SETTING
from rdagent.components.workflow.conf import BasePropSetting
from rdagent.components.workflow.rd_loop import RDLoop
from rdagent.core.conf import RD_AGENT_SETTINGS
from rdagent.core.developer import Developer
from rdagent.core.exception import FactorEmptyError, ModelEmptyError
from rdagent.core.proposal import (
@@ -64,15 +65,18 @@ class QuantRDLoop(RDLoop):
self.trace = QuantTrace(scen=scen)
super(RDLoop, self).__init__()
def direct_exp_gen(self, prev_out: dict[str, Any]):
hypo = self._propose()
assert hypo.action in ["factor", "model"]
if hypo.action == "factor":
exp = self.factor_hypothesis2experiment.convert(hypo, self.trace)
else:
exp = self.model_hypothesis2experiment.convert(hypo, self.trace)
logger.log_object(exp.sub_tasks, tag="experiment generation")
return {"propose": hypo, "exp_gen": exp}
async def direct_exp_gen(self, prev_out: dict[str, Any]):
while True:
if self.get_unfinished_loop_cnt(self.loop_idx) < RD_AGENT_SETTINGS.get_max_parallel():
hypo = self._propose()
assert hypo.action in ["factor", "model"]
if hypo.action == "factor":
exp = self.factor_hypothesis2experiment.convert(hypo, self.trace)
else:
exp = self.model_hypothesis2experiment.convert(hypo, self.trace)
logger.log_object(exp.sub_tasks, tag="experiment generation")
return {"propose": hypo, "exp_gen": exp}
await asyncio.sleep(1)
def coding(self, prev_out: dict[str, Any]):
if prev_out["direct_exp_gen"]["propose"].action == "factor":
rdagent/components/workflow/rd_loop.py
+9 -4
View File
@@ -3,9 +3,11 @@ Model workflow with session control
It is from `rdagent/app/qlib_rd_loop/model.py` and try to replace `rdagent/app/qlib_rd_loop/RDAgent.py`
"""
import asyncio
from typing import Any
from rdagent.components.workflow.conf import BasePropSetting
from rdagent.core.conf import RD_AGENT_SETTINGS
from rdagent.core.developer import Developer
from rdagent.core.proposal import (
Experiment2Feedback,
@@ -55,10 +57,13 @@ class RDLoop(LoopBase, metaclass=LoopMeta):
return exp
# included steps
def direct_exp_gen(self, prev_out: dict[str, Any]):
hypo = self._propose()
exp = self._exp_gen(hypo)
return {"propose": hypo, "exp_gen": exp}
async def direct_exp_gen(self, prev_out: dict[str, Any]):
while True:
if self.get_unfinished_loop_cnt(self.loop_idx) < RD_AGENT_SETTINGS.get_max_parallel():
hypo = self._propose()
exp = self._exp_gen(hypo)
return {"propose": hypo, "exp_gen": exp}
await asyncio.sleep(1)
def coding(self, prev_out: dict[str, Any]):
exp = self.coder.develop(prev_out["direct_exp_gen"]["exp_gen"])
rdagent/scenarios/data_science/loop.py
-3
View File
@@ -156,9 +156,6 @@ class DataScienceRDLoop(RDLoop):
exp = await self.exp_gen.async_gen(self.trace, self)
logger.log_object(exp)
# FIXME: this is for LLM debug webapp, remove this when the debugging is done.
logger.log_object(exp, tag="debug_exp_gen")
return exp
def coding(self, prev_out: dict[str, Any]):