docs: add quantitative guide, update README + CHANGELOG, bump v1.11.1

Co-Authored-By: Claude <noreply@anthropic.com>
2026-09-12 16:54:20 +08:00 · 2026-06-12 22:12:19 +08:00
parent bfefadf70b
commit a6ed0eac16
11 changed files with 3338 additions and 11 deletions
@@ -0,0 +1,540 @@
+# v1.15.0 归因分析 实施计划
+
+> **For agentic workers:** REQUIRED SUB-SKILL: Use superpowers:subagent-driven-development (recommended) or superpowers:executing-plans to implement this plan task-by-task.
+
+**Goal:** 新增归因分析模块，支持 Brinson 归因（配置 vs 选股）、因子归因、成本归因。
+
+**Architecture:** 新增 `backtest/attribution.py`，纯 pandas/numpy 计算，与现有 `FactorEngine` 无缝衔接。
+
+**Tech Stack:** 纯 numpy/pandas，无新外部依赖。
+
+---
+
+## 文件结构
+
+| 文件 | 操作 | 职责 |
+|------|------|------|
+| `src/easy_tdx/backtest/attribution.py` | 新增 | AttributionReport + AttributionAnalyzer |
+| `tests/unit/test_backtest_attribution.py` | 新增 | 归因分析测试（~20 个） |
+
+---
+
+### Task 1: AttributionReport + cost_attribution + brinson_attribution + factor_attribution
+
+**Files:**
+- Create: `src/easy_tdx/backtest/attribution.py`
+- Create: `tests/unit/test_backtest_attribution.py`
+
+- [ ] **Step 1: Write implementation**
+
+```python
+"""归因分析模块。"""
+from __future__ import annotations
+
+from dataclasses import dataclass, field
+
+import numpy as np
+import pandas as pd
+
+
+@dataclass
+class AttributionReport:
+    """归因分析报告。"""
+
+    total_return: float = 0.0
+    # Brinson 归因
+    allocation_return: float = 0.0
+    selection_return: float = 0.0
+    interaction_return: float = 0.0
+    # 因子归因
+    factor_returns: dict[str, float] = field(default_factory=dict)
+    specific_return: float = 0.0
+    # 成本归因
+    total_trade_cost: float = 0.0
+    slippage_cost: float = 0.0
+    commission_cost: float = 0.0
+    stamp_tax_cost: float = 0.0
+
+
+class AttributionAnalyzer:
+    """收益归因分析器。
+
+    支持三种归因视角：
+    1. 成本归因：分解交易成本的来源（佣金/滑点/印花税）
+    2. Brinson 归因：分解超额收益（配置 vs 选股）
+    3. 因子归因：分解收益为因子贡献 + 特质收益
+    """
+
+    def __init__(
+        self,
+        trades: pd.DataFrame,
+        equity_curve: pd.DataFrame,
+        benchmark: pd.DataFrame | None = None,
+        factor_exposures: pd.DataFrame | None = None,
+        factor_returns: pd.DataFrame | None = None,
+        groups: pd.DataFrame | None = None,
+    ) -> None:
+        self._trades = trades
+        self._equity_curve = equity_curve
+        self._benchmark = benchmark
+        self._factor_exposures = factor_exposures
+        self._factor_returns = factor_returns
+        self._groups = groups
+
+    def cost_attribution(self) -> AttributionReport:
+        """成本归因：分解交易成本。"""
+        if self._trades.empty:
+            return AttributionReport()
+
+        valid = self._trades[~self._trades["rejected"]] if "rejected" in self._trades.columns else self._trades
+
+        slippage_cost = float(valid["slippage"].sum()) if "slippage" in valid.columns else 0.0
+        commission_cost = float(valid["commission"].sum()) if "commission" in valid.columns else 0.0
+
+        # 总成本 = 滑点 + 佣金（佣金内含印花税）
+        total_trade_cost = slippage_cost + commission_cost
+
+        # 估算印花税（卖出交易 0.1%）
+        sell_mask = valid["direction"] == "SELL" if "direction" in valid.columns else pd.Series(dtype=bool)
+        stamp_tax_cost = 0.0
+        if sell_mask.any():
+            sell_trades = valid[sell_mask]
+            if "price" in sell_trades.columns and "size" in sell_trades.columns:
+                stamp_tax_cost = float((sell_trades["price"] * sell_trades["size"] * 0.001).sum())
+
+        total_return = 0.0
+        if not self._equity_curve.empty and "total" in self._equity_curve.columns:
+            total_arr = self._equity_curve["total"].to_numpy()
+            if len(total_arr) >= 2 and total_arr[0] > 0:
+                total_return = float((total_arr[-1] / total_arr[0]) - 1)
+
+        return AttributionReport(
+            total_return=total_return,
+            total_trade_cost=total_trade_cost,
+            slippage_cost=slippage_cost,
+            commission_cost=commission_cost,
+            stamp_tax_cost=stamp_tax_cost,
+        )
+
+    def brinson_attribution(self) -> AttributionReport:
+        """Brinson-Hood-Beebower 归因分解。
+
+        Total = Allocation + Selection + Interaction
+        R_p = Σ(w_pi × R_pi)   组合收益
+        R_b = Σ(w_bi × R_bi)   基准收益
+        Allocation = Σ((w_pi - w_bi) × R_bi)
+        Selection = Σ(w_bi × (R_pi - R_bi))
+        Interaction = Σ((w_pi - w_bi) × (R_pi - R_bi))
+
+        需要提供 benchmark 参数。
+        如果没有 benchmark，只返回 total_return。
+        """
+        cost_report = self.cost_attribution()
+
+        if self._benchmark is None:
+            return cost_report
+
+        # 简化 Brinson：使用 equity_curve 估算
+        if self._equity_curve.empty:
+            return cost_report
+
+        total_arr = self._equity_curve["total"].to_numpy()
+        if len(total_arr) < 2 or total_arr[0] <= 0:
+            return cost_report
+
+        portfolio_return = float((total_arr[-1] / total_arr[0]) - 1)
+
+        # 基准收益
+        benchmark_return = 0.0
+        if "total" in self._benchmark.columns:
+            bench_arr = self._benchmark["total"].to_numpy()
+            if len(bench_arr) >= 2 and bench_arr[0] > 0:
+                benchmark_return = float((bench_arr[-1] / bench_arr[0]) - 1)
+
+        excess_return = portfolio_return - benchmark_return
+
+        # 如果有 groups 信息，按组计算
+        allocation = 0.0
+        selection = 0.0
+        interaction = 0.0
+
+        if self._groups is not None and not self._groups.empty:
+            # 按组分解（简化版）
+            allocation, selection, interaction = self._compute_grouped_brinson(
+                portfolio_return, benchmark_return,
+            )
+        else:
+            # 无分组信息时，将全部超额收益归为 selection
+            selection = excess_return
+
+        return AttributionReport(
+            total_return=portfolio_return,
+            allocation_return=allocation,
+            selection_return=selection,
+            interaction_return=interaction,
+            total_trade_cost=cost_report.total_trade_cost,
+            slippage_cost=cost_report.slippage_cost,
+            commission_cost=cost_report.commission_cost,
+            stamp_tax_cost=cost_report.stamp_tax_cost,
+        )
+
+    def _compute_grouped_brinson(
+        self, portfolio_return: float, benchmark_return: float,
+    ) -> tuple[float, float, float]:
+        """按组计算 Brinson 归因（简化版）。
+
+        当 groups 包含 weight 和 return 列时进行分解。
+        """
+        if self._groups is None or self._groups.empty:
+            return 0.0, portfolio_return - benchmark_return, 0.0
+
+        allocation = 0.0
+        selection = 0.0
+        interaction = 0.0
+
+        if "portfolio_weight" in self._groups.columns and "benchmark_weight" in self._groups.columns:
+            pw = self._groups["portfolio_weight"].to_numpy()
+            bw = self._groups["benchmark_weight"].to_numpy()
+
+            if "portfolio_return" in self._groups.columns and "benchmark_return" in self._groups.columns:
+                pr = self._groups["portfolio_return"].to_numpy()
+                br = self._groups["benchmark_return"].to_numpy()
+
+                allocation = float(np.sum((pw - bw) * br))
+                selection = float(np.sum(bw * (pr - br)))
+                interaction = float(np.sum((pw - bw) * (pr - br)))
+
+        return allocation, selection, interaction
+
+    def factor_attribution(self) -> AttributionReport:
+        """因子归因分解。
+
+        R = Σ(β_i × f_i) + α
+        β_i: 因子暴露度
+        f_i: 因子收益率
+        α: 特质收益
+
+        需要提供 factor_exposures 和 factor_returns。
+        """
+        cost_report = self.cost_attribution()
+
+        if self._factor_exposures is None or self._factor_returns is None:
+            return cost_report
+
+        if self._factor_exposures.empty or self._factor_returns.empty:
+            return cost_report
+
+        # 计算因子贡献
+        factor_contributions: dict[str, float] = {}
+
+        # 简化：按列名匹配
+        common_factors = set(self._factor_exposures.columns) & set(self._factor_returns.columns)
+        for factor_name in common_factors:
+            exposures = self._factor_exposures[factor_name].to_numpy()
+            returns = self._factor_returns[factor_name].to_numpy()
+            min_len = min(len(exposures), len(returns))
+            if min_len > 0:
+                contrib = float(np.sum(exposures[:min_len] * returns[:min_len]))
+                factor_contributions[factor_name] = contrib
+
+        total_factor_return = sum(factor_contributions.values())
+
+        # 总收益
+        total_arr = self._equity_curve["total"].to_numpy()
+        total_return = 0.0
+        if len(total_arr) >= 2 and total_arr[0] > 0:
+            total_return = float((total_arr[-1] / total_arr[0]) - 1)
+
+        specific_return = total_return - total_factor_return
+
+        return AttributionReport(
+            total_return=total_return,
+            factor_returns=factor_contributions,
+            specific_return=specific_return,
+            total_trade_cost=cost_report.total_trade_cost,
+            slippage_cost=cost_report.slippage_cost,
+            commission_cost=cost_report.commission_cost,
+            stamp_tax_cost=cost_report.stamp_tax_cost,
+        )
+
+    def full_report(self) -> AttributionReport:
+        """完整归因报告。
+
+        按优先级使用：
+        1. 因子归因（如果 factor_exposures/factor_returns 可用）
+        2. Brinson 归因（如果 benchmark 可用）
+        3. 成本归因（始终可用）
+        """
+        if self._factor_exposures is not None and self._factor_returns is not None:
+            return self.factor_attribution()
+        if self._benchmark is not None:
+            return self.brinson_attribution()
+        return self.cost_attribution()
+```
+
+- [ ] **Step 2: Write tests**
+
+```python
+"""归因分析单元测试。"""
+from __future__ import annotations
+
+import numpy as np
+import pandas as pd
+import pytest
+
+from easy_tdx.backtest.attribution import AttributionAnalyzer, AttributionReport
+
+
+def _make_trades(
+    n_buys: int = 2, n_sells: int = 2,
+    commission: float = 10.0, slippage: float = 5.0,
+) -> pd.DataFrame:
+    """构造测试交易记录。"""
+    trades: list[dict[str, object]] = []
+    for i in range(n_buys):
+        trades.append({
+            "datetime": 20240101 + i, "direction": "BUY",
+            "size": 100, "price": 100.0 + i,
+            "commission": commission, "slippage": slippage, "pnl": 0.0, "rejected": False,
+        })
+    for i in range(n_sells):
+        trades.append({
+            "datetime": 20240110 + i, "direction": "SELL",
+            "size": 100, "price": 110.0 + i,
+            "commission": commission, "slippage": slippage, "pnl": 500.0, "rejected": False,
+        })
+    return pd.DataFrame(trades)
+
+
+def _make_equity(initial: float = 100000.0, final: float = 110000.0, n: int = 20) -> pd.DataFrame:
+    """构造资金曲线。"""
+    total = np.linspace(initial, final, n)
+    return pd.DataFrame({
+        "datetime": [20240101 + i for i in range(n)],
+        "total": total,
+        "cash": total * 0.5,
+        "position_value": total * 0.5,
+    })
+
+
+def _make_benchmark(initial: float = 100000.0, final: float = 105000.0, n: int = 20) -> pd.DataFrame:
+    """构造基准资金曲线。"""
+    total = np.linspace(initial, final, n)
+    return pd.DataFrame({
+        "datetime": [20240101 + i for i in range(n)],
+        "total": total,
+    })
+
+
+class TestCostAttribution:
+    """成本归因。"""
+
+    def test_basic_cost_breakdown(self) -> None:
+        """基本成本分解。"""
+        trades = _make_trades(n_buys=2, n_sells=2, commission=10.0, slippage=5.0)
+        eq = _make_equity()
+        analyzer = AttributionAnalyzer(trades, eq)
+        report = analyzer.cost_attribution()
+        # 4 trades × 10.0 commission = 40.0
+        assert report.commission_cost == pytest.approx(40.0)
+        # 4 trades × 5.0 slippage = 20.0
+        assert report.slippage_cost == pytest.approx(20.0)
+        # total = 60.0
+        assert report.total_trade_cost == pytest.approx(60.0)
+
+    def test_total_return(self) -> None:
+        """总收益计算。"""
+        trades = _make_trades()
+        eq = _make_equity(100000.0, 110000.0)
+        analyzer = AttributionAnalyzer(trades, eq)
+        report = analyzer.cost_attribution()
+        assert report.total_return == pytest.approx(0.1)
+
+    def test_empty_trades(self) -> None:
+        """空交易记录。"""
+        trades = pd.DataFrame(columns=["datetime", "direction", "size", "price", "commission", "slippage"])
+        eq = _make_equity()
+        analyzer = AttributionAnalyzer(trades, eq)
+        report = analyzer.cost_attribution()
+        assert report.total_trade_cost == 0.0
+        assert report.slippage_cost == 0.0
+
+    def test_stamp_tax_estimation(self) -> None:
+        """印花税估算（卖出 0.1%）。"""
+        trades = _make_trades(n_buys=0, n_sells=1, commission=0.0, slippage=0.0)
+        eq = _make_equity()
+        analyzer = AttributionAnalyzer(trades, eq)
+        report = analyzer.cost_attribution()
+        # 卖出 100 股 × 110 元 × 0.001 = 11.0
+        assert report.stamp_tax_cost == pytest.approx(11.0)
+
+
+class TestBrinsonAttribution:
+    """Brinson 归因。"""
+
+    def test_no_benchmark_returns_only_total(self) -> None:
+        """无基准时只返回总收益。"""
+        trades = _make_trades()
+        eq = _make_equity()
+        analyzer = AttributionAnalyzer(trades, eq, benchmark=None)
+        report = analyzer.brinson_attribution()
+        assert report.total_return == pytest.approx(0.1)
+        assert report.allocation_return == 0.0
+        assert report.selection_return == 0.0
+
+    def test_with_benchmark_selection(self) -> None:
+        """有基准时超额收益归为 selection。"""
+        trades = _make_trades()
+        eq = _make_equity(100000.0, 110000.0)  # +10%
+        bench = _make_benchmark(100000.0, 105000.0)  # +5%
+        analyzer = AttributionAnalyzer(trades, eq, benchmark=bench)
+        report = analyzer.brinson_attribution()
+        assert report.total_return == pytest.approx(0.1)
+        # excess = 10% - 5% = 5%, all attributed to selection
+        assert report.selection_return == pytest.approx(0.05)
+
+    def test_with_groups_decomposition(self) -> None:
+        """有分组时进行 Brinson 三因子分解。"""
+        trades = _make_trades()
+        eq = _make_equity(100000.0, 110000.0)
+        bench = _make_benchmark(100000.0, 105000.0)
+        groups = pd.DataFrame({
+            "portfolio_weight": [0.6, 0.4],
+            "benchmark_weight": [0.5, 0.5],
+            "portfolio_return": [0.15, 0.05],
+            "benchmark_return": [0.10, 0.0],
+        })
+        analyzer = AttributionAnalyzer(trades, eq, benchmark=bench, groups=groups)
+        report = analyzer.brinson_attribution()
+        # Allocation = (0.6-0.5)*0.10 + (0.4-0.5)*0.0 = 0.01
+        assert report.allocation_return == pytest.approx(0.01)
+        # Selection = 0.5*(0.15-0.10) + 0.5*(0.05-0.0) = 0.05
+        assert report.selection_return == pytest.approx(0.05)
+        # Interaction = (0.1)*0.05 + (-0.1)*0.05 = 0.0
+        assert report.interaction_return == pytest.approx(0.0)
+
+
+class TestFactorAttribution:
+    """因子归因。"""
+
+    def test_no_factors_returns_only_cost(self) -> None:
+        """无因子数据时只返回成本归因。"""
+        trades = _make_trades()
+        eq = _make_equity()
+        analyzer = AttributionAnalyzer(trades, eq)
+        report = analyzer.factor_attribution()
+        assert report.factor_returns == {}
+        assert report.specific_return == 0.0
+
+    def test_basic_factor_decomposition(self) -> None:
+        """基本因子分解。"""
+        trades = _make_trades()
+        eq = _make_equity(100000.0, 110000.0)
+        exposures = pd.DataFrame({
+            "momentum": [0.5, 0.3, 0.2],
+            "volatility": [0.1, -0.1, 0.0],
+        })
+        returns = pd.DataFrame({
+            "momentum": [0.05, 0.03, 0.02],
+            "volatility": [0.01, -0.02, 0.0],
+        })
+        analyzer = AttributionAnalyzer(
+            trades, eq,
+            factor_exposures=exposures, factor_returns=returns,
+        )
+        report = analyzer.factor_attribution()
+        # momentum: sum(0.5*0.05, 0.3*0.03, 0.2*0.02) = 0.025+0.009+0.004 = 0.038
+        assert report.factor_returns["momentum"] == pytest.approx(0.038)
+        # volatility: sum(0.1*0.01, -0.1*-0.02, 0*0) = 0.001+0.002+0 = 0.003
+        assert report.factor_returns["volatility"] == pytest.approx(0.003)
+        # total_return = 0.1
+        # specific = 0.1 - 0.038 - 0.003 = 0.059
+        assert report.specific_return == pytest.approx(0.059)
+
+    def test_empty_factor_data(self) -> None:
+        """空因子数据。"""
+        trades = _make_trades()
+        eq = _make_equity()
+        exposures = pd.DataFrame()
+        returns = pd.DataFrame()
+        analyzer = AttributionAnalyzer(
+            trades, eq,
+            factor_exposures=exposures, factor_returns=returns,
+        )
+        report = analyzer.factor_attribution()
+        assert report.factor_returns == {}
+
+
+class TestFullReport:
+    """完整报告。"""
+
+    def test_prefers_factor_over_brinson(self) -> None:
+        """有因子数据时优先使用因子归因。"""
+        trades = _make_trades()
+        eq = _make_equity(100000.0, 110000.0)
+        bench = _make_benchmark(100000.0, 105000.0)
+        exposures = pd.DataFrame({"momentum": [0.5]})
+        returns = pd.DataFrame({"momentum": [0.05]})
+        analyzer = AttributionAnalyzer(
+            trades, eq, benchmark=bench,
+            factor_exposures=exposures, factor_returns=returns,
+        )
+        report = analyzer.full_report()
+        assert "momentum" in report.factor_returns
+        assert report.specific_return != 0.0  # 因子归因有 specific
+
+    def test_falls_back_to_cost_only(self) -> None:
+        """无基准无因子时只返回成本归因。"""
+        trades = _make_trades()
+        eq = _make_equity()
+        analyzer = AttributionAnalyzer(trades, eq)
+        report = analyzer.full_report()
+        assert report.total_trade_cost > 0
+        assert report.factor_returns == {}
+        assert report.allocation_return == 0.0
+```
+
+- [ ] **Step 3: Run tests**
+
+```bash
+python -m pytest tests/unit/test_backtest_attribution.py -v --no-header
+```
+
+- [ ] **Step 4: ruff check**
+
+```bash
+ruff check src/easy_tdx/backtest/attribution.py tests/unit/test_backtest_attribution.py
+ruff format --check src/easy_tdx/backtest/attribution.py tests/unit/test_backtest_attribution.py
+```
+
+- [ ] **Step 5: Full test suite**
+
+```bash
+python -m pytest tests/unit/ -q --no-header
+```
+
+- [ ] **Step 6: Commit**
+
+```bash
+git add src/easy_tdx/backtest/attribution.py tests/unit/test_backtest_attribution.py
+git commit -m "feat(backtest): add AttributionAnalyzer with Brinson, factor, cost attribution"
+```
+
+---
+
+### Task 2: 版本号 bump + 最终验证
+
+- [ ] **Step 1**: Update pyproject.toml version from `1.14.0` to `1.15.0`
+
+- [ ] **Step 2**: Run full test suite
+
+```bash
+python -m pytest tests/unit/ -q --no-header
+```
+
+- [ ] **Step 3**: Commit
+
+```bash
+git add pyproject.toml
+git commit -m "chore: bump version to v1.15.0"
+```