feat(quant): QlibEngine v1 — 本地行情落盘 QlibDataset → D.features 读取 → 因子回测
- qlib_adapter/provider.py:SQLite 行情按 qlib 0.9.8 二进制格式落盘(起始索引头 + 逐日 float32、instruments 3 列、小写 instrument、晚上市 offset)
- qlib_adapter/dataset.py:qlib.init 幂等({'day': uri})+ D.features 读取 close 面板
- qlib_adapter/engine.py:QlibEngine(QuantEngine)v1 —— Qlib 数据管线回测与 LocalEngine 同记账规则(无未来函数/成本/涨跌停标注),factor_test 复用共享实现;Alpha158+LightGBM 为 TODO
- 真实 20 股验证:qlib 落盘 142 文件→读取→回测(-12.81%,Local 对照 -12.97%,差异为 qlib float32 存储)
- tests/test_qlib_engine.py 5 项(格式/roundtrip/晚上市 offset/回测/因子测试)→ pytest 86 passed / ruff clean
This commit is contained in:
@@ -1,38 +1,80 @@
|
||||
"""Qlib 后端引擎(桥接占位)。
|
||||
"""QlibEngine —— 基于 Qlib 数据管线的研究引擎(QuantEngine 实现)。
|
||||
|
||||
本模块是 Qlib 引擎的桥接边界(AGENT.md §14 / §15:Qlib 只允许在
|
||||
quant/qlib_adapter/ 内被引用)。Qlib(pyqlib)已通过「源码 git 安装」成功
|
||||
部署到本机(Linux aarch64 + CPython 3.12,backend/.venv,uv 管理;
|
||||
backend/pyproject.toml 固定 commit,细节见 docs/ROADMAP.md §2 备注)。
|
||||
v1 能力(本阶段已打通并测试):
|
||||
1. provider.build_qlib_dataset:把本地行情按 qlib 二进制格式落盘(data/qlib)
|
||||
2. dataset.ensure_qlib_init + D.features:从 QlibDataset 读取行情(真实 qlib 通路)
|
||||
3. 在 Qlib 读取的行情面板上执行 TopK 因子回测 → 标准 BacktestResult
|
||||
(与 LocalEngine 记账规则一致:无未来函数、成本/涨跌停/停牌近似 + unimplemented 标注)
|
||||
|
||||
基于 Qlib 的因子 / 回测工作流(Parquet/本地行情 → QlibDataset → Alpha158 →
|
||||
LightGBM 训练/预测 → 回测,并归一化为 domain.entities.research 输出)属
|
||||
Phase 2 后续实现;当前默认研究引擎仍为 LocalEngine(纯 pandas,见
|
||||
app/quant/engine.py),业务层经 QuantEngine Protocol 注入,切换无需改业务代码。
|
||||
说明:
|
||||
- 因子分(score)在源行情上按 app.quant.factors 计算(注册表口径一致);
|
||||
qlib 侧负责数据读取供给(未来可由 Qlib Dataset 直接产出特征)。
|
||||
- Alpha158 特征集 + LightGBM 预测信号的模型增强(walk-forward 训练/预测)为下一步
|
||||
TODO,详见 docs/ROADMAP.md §2 与 docs/QLIB_VERIFICATION.md。
|
||||
- 默认研究引擎仍是 LocalEngine(app/quant/engine.py);切换只需注入本类。
|
||||
"""
|
||||
|
||||
from __future__ import annotations
|
||||
|
||||
from pathlib import Path
|
||||
|
||||
import pandas as pd
|
||||
|
||||
from app.domain.entities.research import BacktestResult, FactorTestReport, ResearchSpec
|
||||
from app.quant.engine import QuantEngine
|
||||
|
||||
_MSG = (
|
||||
"Qlib 引擎工作流尚未实现:pyqlib 现已可在本机安装使用(见 docs/ROADMAP.md §2),"
|
||||
"但 QlibDataset → LightGBM 的实现待 Phase 2 补齐。当前请使用默认 LocalEngine。"
|
||||
from app.quant.local_engine import (
|
||||
TopKBacktestRunner,
|
||||
build_factor_panels,
|
||||
composite_score,
|
||||
run_spec_factor_test,
|
||||
)
|
||||
from app.quant.qlib_adapter.dataset import ensure_qlib_init, load_close_panel
|
||||
from app.quant.qlib_adapter.provider import build_qlib_dataset
|
||||
|
||||
_ENGINE_NOTE = "QlibEngine v1:本地行情→QlibDataset(bin)→D.features 读取→TopK 因子回测"
|
||||
|
||||
|
||||
class QlibEngine(QuantEngine):
|
||||
"""pyqlib 后端占位:抛 NotImplementedError 并给出启用指引。"""
|
||||
"""基于 Qlib 数据管线的引擎;因子评估复用共享实现,回测从 QlibDataset 读取行情。"""
|
||||
|
||||
name = "qlib"
|
||||
|
||||
def __init__(self, qlib_dir: Path | None = None) -> None:
|
||||
# 默认落盘到 data/qlib(与 storage.qlib_dir 一致);可注入临时目录便于测试
|
||||
self.qlib_dir = qlib_dir or _default_qlib_dir()
|
||||
|
||||
def run_factor_test(
|
||||
self, daily: pd.DataFrame, spec: ResearchSpec, horizon_days: int = 21
|
||||
) -> FactorTestReport:
|
||||
raise NotImplementedError(_MSG)
|
||||
# 因子评估与数据无关,直接复用共享实现(与 LocalEngine 同口径)
|
||||
report, _panels = run_spec_factor_test(daily, spec, horizon_days)
|
||||
return report
|
||||
|
||||
def run_backtest(self, daily: pd.DataFrame, spec: ResearchSpec) -> BacktestResult:
|
||||
raise NotImplementedError(_MSG)
|
||||
panels = build_factor_panels(daily, spec.factors)
|
||||
score = composite_score(panels)
|
||||
|
||||
self.qlib_dir.mkdir(parents=True, exist_ok=True)
|
||||
uri = build_qlib_dataset(daily, self.qlib_dir)
|
||||
ensure_qlib_init(uri)
|
||||
|
||||
symbols = [str(s) for s in daily["symbol"].unique()]
|
||||
start, end = spec.period
|
||||
close = load_close_panel(uri, symbols, start, end)
|
||||
if close.empty:
|
||||
raise RuntimeError(
|
||||
"QlibDataset 读取为空:请检查 build_qlib_dataset 落盘与 provider_uri"
|
||||
)
|
||||
close = close.sort_index()
|
||||
|
||||
result = TopKBacktestRunner(spec, score, close).run()
|
||||
result.config_snapshot = spec.model_dump(mode="json")
|
||||
note = _ENGINE_NOTE
|
||||
result.unimplemented = [note, *result.unimplemented]
|
||||
return result
|
||||
|
||||
|
||||
def _default_qlib_dir() -> Path:
|
||||
from app.core.config import PROJECT_ROOT
|
||||
|
||||
return PROJECT_ROOT / "data" / "qlib"
|
||||
|
||||
Reference in New Issue
Block a user