feat:添加了基本策略。

alpha/多因子选股策略.ipynb

@@ -0,0 +1,320 @@
+{
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "# 多因子选股策略 — 构建与回测\n",
+    "\n",
+    "## 策略思路\n",
+    "多因子模型（Multi-Factor Model）综合多个维度的因子，分散单一因子的风险，提升选股稳健性。\n",
+    "本策略合成 **四大类因子**：\n",
+    "\n",
+    "| 因子类别 | 具体因子 | 代表逻辑 |\n",
+    "|---------|---------|---------|\n",
+    "| 动量 | 20日收益率 | 强者恒强 |\n",
+    "| 低波 | 20日波动率倒数 | 低波动溢价 |\n",
+    "| 价值 | EP (PE倒数) | 低估值 |\n",
+    "| 质量 | ROE | 高盈利能力 |\n",
+    "\n",
+    "每月调仓，综合得分最高的股票入选。\n",
+    "\n",
+    "## 研究流程\n",
+    "1. 加载数据\n",
+    "2. 各因子计算与 IC 分析\n",
+    "3. 等权合成多因子 + 分层回测\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"
+   ]
+  },
+  {
+   "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 + 估值 + 财务\n",
+    "price_data = loader.load_prices(START_DATE, END_DATE)\n",
+    "pe_data = loader.load_factor('pe_ttm', START_DATE, END_DATE)\n",
+    "roe_data = loader.load_factor('roe', START_DATE, END_DATE)\n",
+    "\n",
+    "print(f'价格数据: {price_data.shape}')\n",
+    "print(f'PE(TTM)数据: {pe_data.shape}')\n",
+    "print(f'ROE数据: {roe_data.shape}')"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## 2. 各因子计算与 IC 分析"
+   ]
+  },
+  {
+   "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",
+    "# ---- 1. 动量因子 (20日收益率) ----\n",
+    "momentum = price_data.pct_change(20)\n",
+    "z_mom = zscore_cross_section(momentum)\n",
+    "\n",
+    "# ---- 2. 低波因子 (20日波动率倒数) ----\n",
+    "daily_ret = price_data.pct_change()\n",
+    "volatility = daily_ret.rolling(20).std()\n",
+    "z_lowvol = -zscore_cross_section(volatility)  # 波动越小越好\n",
+    "\n",
+    "# ---- 3. 价值因子 (EP = 1/PE) ----\n",
+    "ep = 1.0 / pe_data.where(pe_data > 0)\n",
+    "z_value = zscore_cross_section(ep)\n",
+    "\n",
+    "# ---- 4. 质量因子 (ROE) ----\n",
+    "z_quality = zscore_cross_section(roe_data)\n",
+    "\n",
+    "# ---- 汇总各因子 ----\n",
+    "factors = {\n",
+    "    '动量': momentum,\n",
+    "    '低波': -volatility,\n",
+    "    '价值': ep,\n",
+    "    '质量': roe_data,\n",
+    "}\n",
+    "\n",
+    "# 未来 10 日收益率\n",
+    "fwd_10d = price_data.pct_change(10).shift(-10)\n",
+    "\n",
+    "# 各因子 IC 对比\n",
+    "print('各因子 IC 汇总 (未来10日):')\n",
+    "ic_results = {}\n",
+    "for name, fac in factors.items():\n",
+    "    a = FactorAnalyzer(fac.stack(), fwd_10d.stack())\n",
+    "    s = a.ic_summary()\n",
+    "    ic_results[name] = s\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%}')"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## 3. 合成多因子与分层回测\n",
+    "\n",
+    "等权合成综合得分：\n",
+    "$$Score = \\frac{1}{4}(Z_{Momentum} + Z_{LowVol} + Z_{Value} + Z_{Quality})$$"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# 等权合成综合得分\n",
+    "multi_factor = (z_mom + z_lowvol + z_value + z_quality) / 4\n",
+    "\n",
+    "# 分层回测\n",
+    "analyzer = FactorAnalyzer(multi_factor.stack(), fwd_10d.stack())\n",
+    "quantile_ret = analyzer.quantile_returns(n_quantiles=5)\n",
+    "print('多因子分层收益 (Q1=综合得分最低, Q5=最高):')\n",
+    "print(quantile_ret)\n",
+    "\n",
+    "quantile_ret['avg_return'].plot(kind='bar', figsize=(8, 4), color='steelblue')\n",
+    "plt.title('多因子合成分层收益 (未来10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",
+    "# 多因子策略：持有综合得分最高的 20% 股票\n",
+    "strategy = Strategy(\n",
+    "    name='多因子选股策略-动量+低波+价值+质量',\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='每月持有动量/低波/价值/质量四因子综合得分最高的20%股票'\n",
+    ")\n",
+    "\n",
+    "engine = BacktestEngine(config)\n",
+    "equity_curve = engine.run(\n",
+    "    strategy=strategy,\n",
+    "    price_data=price_data,\n",
+    "    factor_data={'multi': multi_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='darkred')\n",
+    "axes[0].axhline(y=1.0, color='gray', linestyle='--')\n",
+    "axes[0].set_title('多因子选股策略净值曲线')\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",
+    "## 因子权重敏感性分析\n",
+    "\n",
+    "对比等权合成与单因子策略的 IC 表现："
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# 单因子 vs 多因子 IC 对比\n",
+    "all_factors = {\n",
+    "    '动量': z_mom,\n",
+    "    '低波': z_lowvol,\n",
+    "    '价值': z_value,\n",
+    "    '质量': z_quality,\n",
+    "    '多因子(等权)': multi_factor,\n",
+    "}\n",
+    "\n",
+    "print(f\"{'因子':<12} {'IC均值':>8} {'ICIR':>8} {'IC>0占比':>10}\")\n",
+    "print('-' * 42)\n",
+    "for name, fac in all_factors.items():\n",
+    "    a = FactorAnalyzer(fac.stack(), fwd_10d.stack())\n",
+    "    s = a.ic_summary()\n",
+    "    print(f\"{name:<12} {s['IC_Mean']:>8.4f} {s['IR']:>8.4f} {s['IC>0_Ratio']:>10.2%}\")"
+   ]
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "Python 3",
+   "language": "python",
+   "name": "python3"
+  },
+  "language_info": {
+   "name": "python",
+   "version": "3.10.0"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 4
+}