79ff6dcccb
refactor: 开源化项目重构
...
- 删除无用文件: PYEOF, PLAN.md, HURST_ENHANCEMENT_SUMMARY.md
- 移动 REPORT.md → docs/REPORT.md，更新 53 处图片路径
- 移动 test_hurst_15scales.py → tests/，修复路径引用
- 清理 output/ 中未被报告引用的 60 个文件
- 重写 README.md 为开源标准格式（Badge、结构树、模块表等）
- 添加 MIT LICENSE
- 更新 .gitignore 排除运行时生成文件
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com >
2026-02-04 01:07:28 +08:00
24d14a0b44
feat: 添加8个多尺度分析模块并完善研究报告
...
新增分析模块:
- microstructure: 市场微观结构分析 (Roll价差, VPIN, Kyle's Lambda)
- intraday_patterns: 日内模式分析 (U型曲线, 三时区对比)
- scaling_laws: 统计标度律 (15尺度波动率标度, R²=0.9996)
- multi_scale_vol: 多尺度已实现波动率 (HAR-RV模型)
- entropy_analysis: 信息熵分析
- extreme_value: 极端值与尾部风险 (GEV/GPD, VaR回测)
- cross_timeframe: 跨时间尺度关联分析
- momentum_reversion: 动量与均值回归检验
现有模块增强:
- hurst_analysis: 扩展至15个时间尺度，新增Hurst vs log(Δt)标度图
- fft_analysis: 扩展至15个粒度，支持瀑布图
- returns/acf/volatility/patterns/anomaly/fractal: 多尺度增强
研究报告更新:
- 新增第16章: 基于全量数据的深度规律挖掘 (15尺度综合)
- 完善第17章: 价格推演添加实际案例 (2020-2021牛市, 2022熊市等)
- 新增16.10节: 可监控的实证指标与预警信号
- 添加VPIN/波动率/Hurst等指标的实时监控阈值和案例
数据覆盖: 全部15个K线粒度 (1m~1mo), 440万条记录
关键发现: Hurst随尺度单调递增 (1m:0.53→1mo:0.72), 极端风险不对称
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com >
2026-02-03 16:35:08 +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
3ab7ba6c7f
Initial commit
2026-02-03 02:27:32 +08:00
