298 lines
8.6 KiB
Plaintext
298 lines
8.6 KiB
Plaintext
{
|
|
"cells": [
|
|
{
|
|
"cell_type": "markdown",
|
|
"metadata": {},
|
|
"source": [
|
|
"# 质量因子策略 — 构建与回测\n",
|
|
"\n",
|
|
"## 策略思路\n",
|
|
"质量投资（Quality Investing）：买入盈利能力强、财务稳健的公司。\n",
|
|
"本策略使用 **ROE、毛利率、资产负债率** 合成质量因子：\n",
|
|
"- ROE（净资产收益率）越高 → 质量越好\n",
|
|
"- 毛利率越高 → 质量越好\n",
|
|
"- 资产负债率越低 → 财务更稳健\n",
|
|
"\n",
|
|
"每月调仓，持有质量因子最高的一批股票。\n",
|
|
"\n",
|
|
"## 研究流程\n",
|
|
"1. 加载数据（价格 + 财务指标）\n",
|
|
"2. 质量因子计算与 IC 分析\n",
|
|
"3. 分层回测验证因子有效性\n",
|
|
"4. 构建策略并回测\n",
|
|
"5. 绩效评估"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": null,
|
|
"metadata": {},
|
|
"outputs": [],
|
|
"source": [
|
|
"import sys\n",
|
|
"sys.path.insert(0, '..')\n",
|
|
"\n",
|
|
"import numpy as np\n",
|
|
"import pandas as pd\n",
|
|
"import matplotlib.pyplot as plt\n",
|
|
"\n",
|
|
"from alpha.config import AlphaConfig\n",
|
|
"from alpha.factors import FactorAnalyzer\n",
|
|
"from alpha.strategy import Strategy, QuantileSignal, EqualWeightAllocator\n",
|
|
"from alpha.backtest import BacktestEngine\n",
|
|
"from alpha.evaluation import PerformanceEvaluator\n",
|
|
"from alpha.data_loader import DataLoader\n",
|
|
"\n",
|
|
"%matplotlib inline\n",
|
|
"plt.rcParams['font.sans-serif'] = ['SimHei']\n",
|
|
"plt.rcParams['axes.unicode_minus'] = False\n",
|
|
"\n",
|
|
"print('模块导入成功')"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "markdown",
|
|
"metadata": {},
|
|
"source": [
|
|
"## 1. 加载数据\n",
|
|
"\n",
|
|
"质量因子需要财务指标（ROE / 毛利率 / 资产负债率），通过 `DataLoader.load_factor` 加载。"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": null,
|
|
"metadata": {},
|
|
"outputs": [],
|
|
"source": [
|
|
"START_DATE = '2020-01-01'\n",
|
|
"END_DATE = '2024-12-31'\n",
|
|
"\n",
|
|
"loader = DataLoader()\n",
|
|
"\n",
|
|
"# 价格数据 + 财务数据\n",
|
|
"price_data = loader.load_prices(START_DATE, END_DATE)\n",
|
|
"roe_data = loader.load_factor('roe', START_DATE, END_DATE) # 净资产收益率\n",
|
|
"gross_margin_data = loader.load_factor('gross_margin', START_DATE, END_DATE) # 毛利率\n",
|
|
"debt_data = loader.load_factor('debt_to_assets', START_DATE, END_DATE) # 资产负债率\n",
|
|
"\n",
|
|
"print(f'价格数据: {price_data.shape}')\n",
|
|
"print(f'ROE数据: {roe_data.shape}')\n",
|
|
"print(f'毛利率数据: {gross_margin_data.shape}')\n",
|
|
"print(f'资产负债率数据: {debt_data.shape}')"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "markdown",
|
|
"metadata": {},
|
|
"source": [
|
|
"## 2. 质量因子计算与 IC 分析\n",
|
|
"\n",
|
|
"质量因子 = Z(ROE) + Z(毛利率) + Z(-资产负债率)\n",
|
|
"\n",
|
|
"财务指标为季度数据，`DataLoader` 已重采样到交易日并做向前填充。"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": null,
|
|
"metadata": {},
|
|
"outputs": [],
|
|
"source": [
|
|
"# 截面标准化函数\n",
|
|
"def zscore_cross_section(df):\n",
|
|
" return (df - df.mean(axis=1)) / (df.std(axis=1) + 1e-12)\n",
|
|
"\n",
|
|
"z_roe = zscore_cross_section(roe_data)\n",
|
|
"z_gm = zscore_cross_section(gross_margin_data)\n",
|
|
"z_debt = -zscore_cross_section(debt_data) # 负债率越低越好\n",
|
|
"\n",
|
|
"quality_factor = z_roe + z_gm + z_debt\n",
|
|
"\n",
|
|
"# 未来 20 日收益率（质量因子预测周期较长）\n",
|
|
"fwd_20d = price_data.pct_change(20).shift(-20)\n",
|
|
"\n",
|
|
"factor_stacked = quality_factor.stack()\n",
|
|
"fwd_stacked = fwd_20d.stack()\n",
|
|
"\n",
|
|
"analyzer = FactorAnalyzer(factor_stacked, fwd_stacked)\n",
|
|
"ic = analyzer.compute_ic(method='rank')\n",
|
|
"\n",
|
|
"print('质量因子 IC 汇总:')\n",
|
|
"for k, v in analyzer.ic_summary().items():\n",
|
|
" print(f' {k}: {v:.4f}')\n",
|
|
"\n",
|
|
"ic.plot(figsize=(12, 3), title='质量因子 Rank IC 时间序列')\n",
|
|
"plt.axhline(y=0, color='r', linestyle='--')\n",
|
|
"plt.show()"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "markdown",
|
|
"metadata": {},
|
|
"source": [
|
|
"## 3. 分层回测"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": null,
|
|
"metadata": {},
|
|
"outputs": [],
|
|
"source": [
|
|
"quantile_ret = analyzer.quantile_returns(n_quantiles=5)\n",
|
|
"print('各分位组平均收益 (Q1=质量最差, Q5=质量最好):')\n",
|
|
"print(quantile_ret)\n",
|
|
"\n",
|
|
"quantile_ret['avg_return'].plot(kind='bar', figsize=(8, 4), color='steelblue')\n",
|
|
"plt.title('质量因子分层收益 (未来20日)')\n",
|
|
"plt.ylabel('平均收益率')\n",
|
|
"plt.grid(True, alpha=0.3)\n",
|
|
"plt.show()"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "markdown",
|
|
"metadata": {},
|
|
"source": [
|
|
"## 4. 构建策略并回测"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": null,
|
|
"metadata": {},
|
|
"outputs": [],
|
|
"source": [
|
|
"# 回测配置\n",
|
|
"config = AlphaConfig(\n",
|
|
" initial_cash=1_000_000,\n",
|
|
" commission_rate=0.0003,\n",
|
|
" slippage=0.001,\n",
|
|
" stamp_tax=0.001,\n",
|
|
")\n",
|
|
"\n",
|
|
"# 质量策略：持有质量因子最高的 20% 股票\n",
|
|
"strategy = Strategy(\n",
|
|
" name='质量因子策略-ROE+毛利率+低负债',\n",
|
|
" factors=[],\n",
|
|
" signal_generator=QuantileSignal(\n",
|
|
" n_quantiles=5, long_quantile=5, short_quantile=0,\n",
|
|
" ),\n",
|
|
" weight_allocator=EqualWeightAllocator(max_positions=10),\n",
|
|
" description='每月持有ROE高、毛利率高、负债率低的优质公司'\n",
|
|
")\n",
|
|
"\n",
|
|
"engine = BacktestEngine(config)\n",
|
|
"equity_curve = engine.run(\n",
|
|
" strategy=strategy,\n",
|
|
" price_data=price_data,\n",
|
|
" factor_data={'quality': quality_factor},\n",
|
|
" rebalance_freq='M',\n",
|
|
")\n",
|
|
"\n",
|
|
"print(f'回测完成, 共 {len(equity_curve)} 个交易日')\n",
|
|
"print(f'累计收益率: {(equity_curve[\"nav\"].iloc[-1] - 1) * 100:.2f}%')"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "markdown",
|
|
"metadata": {},
|
|
"source": [
|
|
"## 5. 净值曲线与回撤"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": null,
|
|
"metadata": {},
|
|
"outputs": [],
|
|
"source": [
|
|
"fig, axes = plt.subplots(2, 1, figsize=(14, 8))\n",
|
|
"\n",
|
|
"# 净值曲线\n",
|
|
"axes[0].plot(equity_curve.index, equity_curve['nav'], label='策略净值', color='brown')\n",
|
|
"axes[0].axhline(y=1.0, color='gray', linestyle='--')\n",
|
|
"axes[0].set_title('质量因子策略净值曲线')\n",
|
|
"axes[0].legend()\n",
|
|
"axes[0].grid(True, alpha=0.3)\n",
|
|
"\n",
|
|
"# 回撤曲线\n",
|
|
"nav = equity_curve['nav']\n",
|
|
"running_max = nav.cummax()\n",
|
|
"drawdown = (nav - running_max) / running_max\n",
|
|
"axes[1].fill_between(equity_curve.index, 0, drawdown.values, color='red', alpha=0.3)\n",
|
|
"axes[1].set_title('回撤曲线')\n",
|
|
"axes[1].grid(True, alpha=0.3)\n",
|
|
"\n",
|
|
"plt.tight_layout()\n",
|
|
"plt.show()"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "markdown",
|
|
"metadata": {},
|
|
"source": [
|
|
"## 6. 绩效评估"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": null,
|
|
"metadata": {},
|
|
"outputs": [],
|
|
"source": [
|
|
"# 基准：股票池等权组合\n",
|
|
"bench_ret = price_data.pct_change().mean(axis=1)\n",
|
|
"\n",
|
|
"evaluator = PerformanceEvaluator(equity_curve, benchmark_returns=bench_ret, risk_free_rate=0.03)\n",
|
|
"print(evaluator.summary())\n",
|
|
"\n",
|
|
"report_df = evaluator.full_report()\n",
|
|
"pd.DataFrame(list(report_df.items()), columns=['指标', '数值']).set_index('指标')"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "markdown",
|
|
"metadata": {},
|
|
"source": [
|
|
"---\n",
|
|
"## 质量分项指标对比\n",
|
|
"\n",
|
|
"对比各质量指标单独用于选股的效果："
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": null,
|
|
"metadata": {},
|
|
"outputs": [],
|
|
"source": [
|
|
"# 各分项因子 IC 对比\n",
|
|
"for name, fac in [\n",
|
|
" ('ROE', z_roe),\n",
|
|
" ('毛利率', z_gm),\n",
|
|
" ('低负债率', z_debt),\n",
|
|
" ('质量合成', quality_factor),\n",
|
|
"]:\n",
|
|
" a = FactorAnalyzer(fac.stack(), fwd_stacked)\n",
|
|
" s = a.ic_summary()\n",
|
|
" print(f'{name}: IC均值={s[\"IC_Mean\"]:.4f}, ICIR={s[\"IR\"]:.4f}, '\n",
|
|
" f'IC>0占比={s[\"IC>0_Ratio\"]:.2%}')"
|
|
]
|
|
}
|
|
],
|
|
"metadata": {
|
|
"kernelspec": {
|
|
"display_name": "Python 3",
|
|
"language": "python",
|
|
"name": "python3"
|
|
},
|
|
"language_info": {
|
|
"name": "python",
|
|
"version": "3.10.0"
|
|
}
|
|
},
|
|
"nbformat": 4,
|
|
"nbformat_minor": 4
|
|
} |