From a47af0f0ebec61daec381be3a26633e547a34aaa Mon Sep 17 00:00:00 2001 From: aszerW Date: Tue, 2 Jun 2026 01:32:43 +0800 Subject: [PATCH] docs(experiment): add select_num A/B/C comparison report (005) - Experiment: select_num = 1, 2, 3 comparison - Period: 2020-01-10 ~ 2026-06-02 (1546 trading days) - Key findings: - Top-1: highest return (600%), highest drawdown (-25.5%) - Top-3: best risk-adjusted return (Calmar 1.73, Sharpe 1.35) - Top-2: balanced middle ground (Calmar 1.69) - Add rotation/experiment_select_num.py experiment script - Save report to docs/experiments/005_select_num_comparison.md --- docs/experiments/005_select_num_comparison.md | 145 +++++++++++++ rotation/experiment_select_num.py | 193 ++++++++++++++++++ 2 files changed, 338 insertions(+) create mode 100644 docs/experiments/005_select_num_comparison.md create mode 100644 rotation/experiment_select_num.py diff --git a/docs/experiments/005_select_num_comparison.md b/docs/experiments/005_select_num_comparison.md new file mode 100644 index 0000000..a84fd05 --- /dev/null +++ b/docs/experiments/005_select_num_comparison.md @@ -0,0 +1,145 @@ +# 实验记录 005: select_num 参数对策略表现的影响 + +## 实验信息 + +| 项目 | 内容 | +|------|------| +| 实验编号 | 005 | +| 实验日期 | 2026-06-02 | +| 实验类型 | A/B/C 对比测试 | +| 研究问题 | `diversified=true` 模式下，`select_num` 取 1/2/3 时对策略收益与风险的影响 | +| 配置文件 | `rotation/config_simple.yaml` (L133 `select_num`) | +| 实验脚本 | `rotation/experiment_select_num.py` | + +--- + +## 1. 实验背景 + +### 策略选股流程 + +``` +Step 1: 类内竞争 → 每个 market 大类只保留得分最高的1只标的（大类冠军） +Step 2: 跨类排序 → 从大类冠军中按得分从高到低选 Top select_num +``` + +### 核心问题 + +`select_num` 控制最终持仓标的数量，直接影响集中度和分散度： +- `select_num=1`：单标的集中持仓，无分散化效果 +- `select_num=2`：持有 2 个大类的冠军标的 +- `select_num=3`：持有 3 个大类的冠军标的（当前默认配置） + +**理论预期**： +- 持仓数量越少，集中度越高，潜在收益和波动均放大 +- 持仓数量越多，分散化效果越好，回撤更小，但可能引入边际收益较低的标的 + +--- + +## 2. 实验设计 + +### A/B/C 组配置 + +| 组别 | select_num | 持仓数量 | 其他配置 | +|------|-----------|---------|---------| +| **A组** | 1 | 单标的 | 同对照组 | +| **B组** | 2 | 双标的 | 同对照组 | +| **C组** | 3 | 三标的 | 同对照组（当前默认） | + +### 固定配置（三组相同） + +```yaml +factor: + type: "weighted_momentum" + n_days: 25 + +rotation: + diversified: true + threshold: + mode: "dynamic" + reference: "931862.CSI" # 短债动量基准 +``` + +### 回测区间 + +2020-01-10 ~ 2026-06-02，共 **1546 个交易日** + +--- + +## 3. 回测结果 + +### 核心指标对比 + +| 指标 | Top-1（A组） | Top-2（B组） | Top-3（C组） | +|------|------------|------------|------------| +| 累计收益 | **600.31%** | 369.88% | 302.14% | +| 年化收益 | **37.34%** | 28.69% | 25.46% | +| 最大回撤 | -25.53% | -16.93% | **-14.74%** | +| 夏普比率 | 1.11 | 1.27 | **1.35** | +| Calmar比率 | 1.46 | 1.69 | **1.73** | +| 日胜率 | 54.49% | **55.35%** | 55.18% | +| 调仓次数 | 197 | 319 | 405 | + +### 关键观察 + +**收益维度：** +- Top-1 累计收益（600%）几乎是 Top-3（302%）的 2 倍 +- 集中持仓显著放大了收益，但也意味着更高的单标的依赖风险 + +**风险维度：** +- Top-3 最大回撤（-14.74%）比 Top-1（-25.53%）降低约 42% +- Top-2 居中（-16.93%），回撤控制效果明显 + +**风险调整收益（核心指标）：** +- Calmar 比率：Top-3（1.73）> Top-2（1.69）> Top-1（1.46） +- 夏普比率：Top-3（1.35）> Top-2（1.27）> Top-1（1.11） +- **分散化带来更优的风险收益比** + +**调仓频率：** +- Top-1 调仓次数最少（197 次），因为持仓切换需要单标的排名大幅变动 +- Top-3 调仓次数最多（405 次），持仓组合中任一标的变化都会触发调仓 + +--- + +## 4. NAV 曲线对比 + +![NAV 对比图](../../results/experiment_select_num/select_num_nav_comparison.png) + +![指标对比图](../../results/experiment_select_num/select_num_comparison.png) + +--- + +## 5. 结论与建议 + +### 核心结论 + +| 目标 | 推荐配置 | 原因 | +|------|---------|------| +| 追求绝对收益 | `select_num=1` | 累计收益最高，但需承受更大回撤 | +| 追求风险调整收益 | `select_num=3` | Calmar/夏普最优，回撤可控 | +| 平衡两者 | `select_num=2` | 收益与回撤的折中方案 | + +### 实践建议 + +- **当前默认配置 `select_num=3` 是合理的选择**，Calmar 比率最优，适合长期持有 +- 若资金规模较小、风险承受能力强，可考虑 `select_num=1` 追求高弹性 +- `select_num=2` 的 Calmar（1.69）与 Top-3（1.73）非常接近，但收益更高（369% vs 302%），值得进一步观察 + +--- + +## 6. 实验数据位置 + +``` +results/experiment_select_num/ +├── select_1/ +│ ├── simple_rotation_nav.csv +│ ├── simple_rotation_signals.csv +│ ├── simple_rotation_detail.json +│ └── simple_rotation_metrics.json +├── select_2/ +│ └── ... (同上) +├── select_3/ +│ └── ... (同上) +├── select_num_comparison.png # 指标对比柱状图 +├── select_num_nav_comparison.png # NAV 叠加曲线图 +└── experiment_metrics.json # 三组指标汇总 +``` diff --git a/rotation/experiment_select_num.py b/rotation/experiment_select_num.py new file mode 100644 index 0000000..f3e341d --- /dev/null +++ b/rotation/experiment_select_num.py @@ -0,0 +1,193 @@ +#!/usr/bin/env python3 +""" +select_num A/B 实验：对比 Top-1 / Top-2 / Top-3 的表现 + +用法: + python rotation/experiment_select_num.py +""" + +import os +import sys +import yaml +import json +import tempfile +import numpy as np +import pandas as pd +from pathlib import Path +from datetime import datetime + +PROJECT_ROOT = Path(__file__).parent.parent +sys.path.insert(0, str(PROJECT_ROOT)) + +from rotation.simple_rotation import SimpleRotationStrategy + + +def run_with_select_num(config_path: str, select_num: int, output_dir: Path) -> dict: + """运行一次策略，覆盖 select_num""" + print(f"\n{'='*60}") + print(f" 实验: select_num = {select_num}") + print(f"{'='*60}\n") + + # 读取原始配置，修改 select_num，写入临时文件 + with open(config_path, 'r', encoding='utf-8') as f: + cfg = yaml.safe_load(f) + cfg['rotation']['select_num'] = select_num + + tmp_path = output_dir / f'config_select_{select_num}.yaml' + with open(tmp_path, 'w', encoding='utf-8') as f: + yaml.dump(cfg, f, default_flow_style=False, allow_unicode=True) + + strategy = SimpleRotationStrategy(config_path=str(tmp_path)) + result = strategy.run() + + if result: + # 导出到子目录 + sub_dir = output_dir / f'select_{select_num}' + sub_dir.mkdir(parents=True, exist_ok=True) + strategy.export_results(output_dir=str(sub_dir)) + return result.get('metrics', {}) + return {} + + +def print_comparison(all_metrics: dict): + """打印对比表格""" + print(f"\n\n{'='*80}") + print(f" select_num 实验对比结果") + print(f"{'='*80}\n") + + header = f"{'指标':<16}" + for n in sorted(all_metrics.keys()): + header += f"{'Top-'+str(n):>12}" + print(header) + print("-" * (16 + 12 * len(all_metrics))) + + rows = [ + ('累计收益', 'total_return', '{:.2%}'), + ('年化收益', 'annual_return', '{:.2%}'), + ('最大回撤', 'max_drawdown', '{:.2%}'), + ('夏普比率', 'sharpe_ratio', '{:.2f}'), + ('Calmar比率', 'calmar_ratio', '{:.2f}'), + ('日胜率', 'win_rate', '{:.2%}'), + ('交易日数', 'n_days', '{}'), + ('调仓次数', 'rebalance_count', '{}'), + ] + + for label, key, fmt in rows: + row = f"{label:<16}" + for n in sorted(all_metrics.keys()): + val = all_metrics[n].get(key, 0) + row += f"{fmt.format(val):>12}" + print(row) + + print(f"\n{'='*80}") + + +def plot_comparison(all_metrics: dict, output_dir: Path): + """生成对比图表""" + import matplotlib + matplotlib.use("Agg") + import matplotlib.pyplot as plt + + fig, axes = plt.subplots(1, 3, figsize=(16, 5)) + fig.suptitle("select_num A/B Experiment", fontsize=14, fontweight="bold") + + nums = sorted(all_metrics.keys()) + colors = ['#E74C3C', '#3498DB', '#2ECC71'] + + # 1. 收益对比 + ax = axes[0] + annuals = [all_metrics[n].get('annual_return', 0) for n in nums] + totals = [all_metrics[n].get('total_return', 0) for n in nums] + x = np.arange(len(nums)) + w = 0.35 + ax.bar(x - w/2, [a*100 for a in annuals], w, label='Annual %', color='#E74C3C', alpha=0.8) + ax.bar(x + w/2, [t*100 for t in totals], w, label='Total %', color='#3498DB', alpha=0.8) + ax.set_xticks(x) + ax.set_xticklabels([f'Top-{n}' for n in nums]) + ax.set_ylabel('Return (%)') + ax.set_title('Returns') + ax.legend() + ax.grid(True, alpha=0.3) + + # 2. 风险对比 + ax = axes[1] + dds = [abs(all_metrics[n].get('max_drawdown', 0)) * 100 for n in nums] + ax.bar(x, dds, color='#E74C3C', alpha=0.7) + ax.set_xticks(x) + ax.set_xticklabels([f'Top-{n}' for n in nums]) + ax.set_ylabel('Max Drawdown (%)') + ax.set_title('Risk') + ax.grid(True, alpha=0.3) + + # 3. 夏普 & Calmar + ax = axes[2] + sharpes = [all_metrics[n].get('sharpe_ratio', 0) for n in nums] + calmars = [all_metrics[n].get('calmar_ratio', 0) for n in nums] + ax.bar(x - w/2, sharpes, w, label='Sharpe', color='#2ECC71', alpha=0.8) + ax.bar(x + w/2, calmars, w, label='Calmar', color='#F39C12', alpha=0.8) + ax.set_xticks(x) + ax.set_xticklabels([f'Top-{n}' for n in nums]) + ax.set_ylabel('Ratio') + ax.set_title('Risk-Adjusted') + ax.legend() + ax.grid(True, alpha=0.3) + + plt.tight_layout() + chart_path = output_dir / 'select_num_comparison.png' + plt.savefig(str(chart_path), dpi=150, bbox_inches="tight") + plt.close() + print(f"\n + Chart: {chart_path}") + + +def plot_nav_comparison(output_dir: Path): + """加载三组 NAV 画在同一张图上""" + import matplotlib + matplotlib.use("Agg") + import matplotlib.pyplot as plt + + fig, ax = plt.subplots(figsize=(14, 6)) + colors = {'1': '#E74C3C', '2': '#3498DB', '3': '#2ECC71'} + + for n in [1, 2, 3]: + nav_path = output_dir / f'select_{n}' / 'simple_rotation_nav.csv' + if nav_path.exists(): + df = pd.read_csv(nav_path, parse_dates=['date']) + ax.plot(df['date'], df['nav'], label=f'Top-{n}', linewidth=1.5, color=colors[str(n)]) + + ax.set_title("NAV Curve Comparison (select_num)", fontsize=14, fontweight="bold") + ax.set_ylabel("NAV") + ax.set_yscale("log") + ax.legend(fontsize=11) + ax.grid(True, alpha=0.3) + plt.tight_layout() + + nav_chart = output_dir / 'select_num_nav_comparison.png' + plt.savefig(str(nav_chart), dpi=150, bbox_inches="tight") + plt.close() + print(f" + NAV Chart: {nav_chart}") + + +if __name__ == "__main__": + if 'FLASK_API_URL' not in os.environ: + os.environ['FLASK_API_URL'] = 'https://k3s.tokenpluse.xyz' + + config_path = str(Path(__file__).parent / 'config_simple.yaml') + output_dir = PROJECT_ROOT / 'results' / 'experiment_select_num' + output_dir.mkdir(parents=True, exist_ok=True) + + all_metrics = {} + for n in [1, 2, 3]: + metrics = run_with_select_num(config_path, n, output_dir) + if metrics: + all_metrics[n] = metrics + + if all_metrics: + print_comparison(all_metrics) + plot_comparison(all_metrics, output_dir) + plot_nav_comparison(output_dir) + + # 保存原始指标 + metrics_path = output_dir / 'experiment_metrics.json' + with open(metrics_path, 'w', encoding='utf-8') as f: + json.dump({str(k): v for k, v in all_metrics.items()}, f, ensure_ascii=False, indent=2) + print(f" + Metrics: {metrics_path}")