fix: 全面修复代码质量和报告准确性问题

代码修复 (16 个模块):
- GARCH 模型统一改用 t 分布 + 收敛检查 (returns/volatility/anomaly)
- KS 检验替换为 Lilliefors 检验 (returns)
- 修复数据泄漏: StratifiedKFold→TimeSeriesSplit, scaler 逐折 fit (anomaly)
- 前兆标签 shift(-1) 预测次日异常 (anomaly)
- PSD 归一化加入采样频率和单边谱×2 (fft)
- AR(1) 红噪声基线经验缩放 (fft)
- 盒计数法独立 x/y 归一化, MF-DFA q=0 (fractal)
- ADF 平稳性检验 + 移除双重 Bonferroni (causality)
- R/S Hurst 添加 R² 拟合优度 (hurst)
- Prophet 递推预测避免信息泄露 (time_series)
- IC 计算过滤零信号, 中性形态 hit_rate=NaN (indicators/patterns)
- 聚类阈值自适应化 (clustering)
- 日历效应前后半段稳健性检查 (calendar)
- 证据评分标准文本与代码对齐 (visualization)
- 核心管道 NaN/空值防护 (data_loader/preprocessing/main)

报告修复 (docs/REPORT.md, 15 处):
- 标度指数 H_scaling 与 Hurst 指数消歧
- GBM 6 个月概率锥数值重算
- CLT 限定、减半措辞弱化、情景概率逻辑修正
- GPD 形状参数解读修正、异常 AUC 证据降级

Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>

src/clustering.py

@@ -250,24 +250,34 @@ def _interpret_clusters(df_clean: pd.DataFrame, labels: np.ndarray,
     print(f"{method_name} 聚类特征均值")
     print("=" * 60)
 
-    # 自动标注状态
+    # 自动标注状态（基于数据分布的自适应阈值）
     state_labels = {}
+
+    # 计算自适应阈值：基于聚类均值的标准差
+    lr_values = cluster_means["log_return"]
+    abs_r_values = cluster_means["abs_return"]
+    lr_std = lr_values.std() if len(lr_values) > 1 else 0.02
+    abs_r_std = abs_r_values.std() if len(abs_r_values) > 1 else 0.02
+    high_lr_threshold = max(0.005, lr_std)  # 至少 0.5% 作为下限
+    high_abs_threshold = max(0.005, abs_r_std)
+    mild_lr_threshold = max(0.002, high_lr_threshold * 0.25)
+
     for cid in cluster_means.index:
         row = cluster_means.loc[cid]
         lr = row["log_return"]
         vol = row["vol_7d"]
         abs_r = row["abs_return"]
 
-        # 基于收益率和波动率的规则判断
-        if lr > 0.02 and abs_r > 0.02:
+        # 基于自适应阈值的规则判断
+        if lr > high_lr_threshold and abs_r > high_abs_threshold:
             label = "surge"
-        elif lr < -0.02 and abs_r > 0.02:
+        elif lr < -high_lr_threshold and abs_r > high_abs_threshold:
             label = "crash"
-        elif lr > 0.005:
+        elif lr > mild_lr_threshold:
             label = "mild_up"
-        elif lr < -0.005:
+        elif lr < -mild_lr_threshold:
             label = "mild_down"
-        elif abs_r > 0.015 or vol > cluster_means["vol_7d"].median() * 1.5:
+        elif abs_r > high_abs_threshold * 0.75 or vol > cluster_means["vol_7d"].median() * 1.5:
             label = "high_vol"
         else:
             label = "sideways"