褚宏光
dab9768b3b
- Revised README.md to enhance clarity on core functionalities and usage instructions. - Updated USAGE.md to reflect the new pipeline script and its parameters. - Modified .gitignore to include additional output files for better management. - Removed outdated output files (all_results.csv, report.md, strong_breakout_up.csv, strong_breakout_down.csv) to streamline data handling. - Improved structure and descriptions in documentation for better user guidance.
2.2 KiB
2.2 KiB
使用说明
快速启动
.\.venv\Scripts\Activate.ps1
python scripts/pipeline_converging_triangle.py
1. 创建与激活虚拟环境
# 创建环境（首次）
python -m venv .venv
# 激活环境
.\.venv\Scripts\Activate.ps1
2. 安装依赖
pip install numpy pandas matplotlib
3. 运行脚本
一键流水线（推荐）
python scripts/pipeline_converging_triangle.py
常用参数：
# 指定日期
python scripts/pipeline_converging_triangle.py --date 20260120
# 跳过检测（仅生成报告与图表）
python scripts/pipeline_converging_triangle.py --skip-detection
仅批量检测
python scripts/run_converging_triangle.py
仅生成报告
python scripts/report_converging_triangles.py
仅绘制图表
python scripts/plot_converging_triangles.py
输出（已被 .gitignore 忽略，默认不推送远程）：
outputs/converging_triangles/all_results.csvoutputs/converging_triangles/strong_breakout_up.csvoutputs/converging_triangles/strong_breakout_down.csvoutputs/converging_triangles/report.mdoutputs/converging_triangles/charts/*.png
4. 参数调整
编辑 scripts/triangle_config.py（统一配置）：
DETECTION_PARAMS = ConvergingTriangleParams(
window=120, # 检测窗口大小
pivot_k=15, # 枢轴点检测窗口
shrink_ratio=0.6, # 收敛比阈值（严格模式）
# ...
)
RECENT_DAYS = 500 # 计算最近 N 天（None=全部历史）
DISPLAY_WINDOW = 500 # 图表显示范围
ONLY_VALID = True # 只输出有效三角形
5. 数据格式
数据文件位于 data/ 目录，格式为 pkl：
{
'mtx': ndarray (n_stocks, n_days), # 数据矩阵
'dtes': ndarray (n_days,), # 日期 (20050104)
'tkrs': ndarray (n_stocks,), # 股票代码 (SH600000)
'tkrs_name': ndarray (n_stocks,), # 股票名称
}
6. 备注
- 关闭环境：
deactivate - 权限问题（PowerShell）：
Set-ExecutionPolicy -ExecutionPolicy RemoteSigned -Scope CurrentUser