d480712b40
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 >
2026-02-04 01:07:50 +08:00
704cc2267d
Fix Chinese font rendering in all chart outputs
...
- Add src/font_config.py: centralized font detection that auto-selects
from Noto Sans SC > Hiragino Sans GB > STHeiti > Arial Unicode MS
- Replace hardcoded font lists in all 18 modules with unified config
- Add .gitignore for __pycache__, .DS_Store, venv, etc.
- Regenerate all 70 charts with correct Chinese rendering
Previously, 7 modules (fft, wavelet, acf, fractal, hurst, indicators,
patterns) had no Chinese font config at all, causing □□□ rendering.
The remaining 11 modules used a hardcoded fallback list that didn't
prioritize the best available system font.
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com >
2026-02-03 11:21:01 +08:00
f4c4408708
Add comprehensive BTC/USDT price analysis framework with 17 modules
...
Complete statistical analysis pipeline covering:
- FFT spectral analysis, wavelet CWT, ACF/PACF autocorrelation
- Returns distribution (fat tails, kurtosis=15.65), GARCH volatility modeling
- Hurst exponent (H=0.593), fractal dimension, power law corridor
- Volume-price causality (Granger), calendar effects, halving cycle analysis
- Technical indicator validation (0/21 pass FDR), candlestick pattern testing
- Market state clustering (K-Means/GMM), Markov chain transitions
- Time series forecasting (ARIMA/Prophet/LSTM benchmarks)
- Anomaly detection ensemble (IF+LOF+COPOD, AUC=0.9935)
Key finding: volatility is predictable (GARCH persistence=0.973),
but price direction is statistically indistinguishable from random walk.
Includes REPORT.md with 16-section analysis report and future projections,
70+ charts in output/, and all source modules in src/.
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com >
2026-02-03 10:29:54 +08:00
