mirror of
https://github.com/NicolasBohn/NexQuant.git
synced 2026-07-28 16:07:46 +00:00
Xu Yang
be2c19307e
* Implemented model.py - Need to run within the RDAgent folder (relevant path) - Each time copy a template & insert code & run qlib & store result back to experiment * Create model.py * Create conf.yaml This is the sample conf.yaml to be copied each time. This has gone several times of iteration and is now working for both tabular and Time-Series data. * Create read_exp.py This is to read the results within Qlib * Create ReadMe.md * Update model.py * Create test_model.py A testing file that separates model code generation and running&feedback section. * move the template folder * help xisen finish the model runner * help xisen fix improve model feedback generation * delete debug file * rename readme.md --------- Co-authored-by: Xisen Wang <118058822+Xisen-Wang@users.noreply.github.com>
65 lines
2.1 KiB
Python
65 lines
2.1 KiB
Python
from abc import ABC, abstractmethod
|
|
from typing import Any
|
|
|
|
from tqdm import tqdm
|
|
|
|
from rdagent.core.evaluation import Evaluator
|
|
from rdagent.core.evolving_framework import EvolvableSubjects, EvoStep, Feedback
|
|
|
|
|
|
class EvoAgent(ABC):
|
|
def __init__(self, max_loop, evolving_strategy) -> None:
|
|
self.max_loop = max_loop
|
|
self.evolving_strategy = evolving_strategy
|
|
|
|
@abstractmethod
|
|
def multistep_evolve(self, evo: EvolvableSubjects, eva: Evaluator | Feedback, **kwargs: Any) -> EvolvableSubjects:
|
|
pass
|
|
|
|
|
|
class RAGEvoAgent(EvoAgent):
|
|
def __init__(self, max_loop, evolving_strategy, rag) -> None:
|
|
super().__init__(max_loop, evolving_strategy)
|
|
self.rag = rag
|
|
self.evolving_trace = []
|
|
|
|
def multistep_evolve(
|
|
self,
|
|
evo: EvolvableSubjects,
|
|
eva: Evaluator | Feedback,
|
|
*,
|
|
with_knowledge: bool = False,
|
|
with_feedback: bool = True,
|
|
knowledge_self_gen: bool = False,
|
|
) -> EvolvableSubjects:
|
|
for _ in tqdm(range(self.max_loop), "Implementing"):
|
|
# 1. knowledge self-evolving
|
|
if knowledge_self_gen and self.rag is not None:
|
|
self.rag.generate_knowledge(self.evolving_trace)
|
|
# 2. RAG
|
|
queried_knowledge = None
|
|
if with_knowledge and self.rag is not None:
|
|
# TODO: Putting the evolving trace in here doesn't actually work
|
|
queried_knowledge = self.rag.query(evo, self.evolving_trace)
|
|
|
|
# 3. evolve
|
|
evo = self.evolving_strategy.evolve(
|
|
evo=evo,
|
|
evolving_trace=self.evolving_trace,
|
|
queried_knowledge=queried_knowledge,
|
|
)
|
|
|
|
# 4. Pack evolve results
|
|
es = EvoStep(evo, queried_knowledge)
|
|
|
|
# 5. Evaluation
|
|
if with_feedback:
|
|
es.feedback = (
|
|
eva if isinstance(eva, Feedback) else eva.evaluate(evo, queried_knowledge=queried_knowledge)
|
|
)
|
|
|
|
# 6. update trace
|
|
self.evolving_trace.append(es)
|
|
|
|
return evo
|