Reusable modelling, pricing, governance, and reporting utilities.
Project description
Ins-Pricing 项目概览
本仓库包含风险建模与优化相关的 Notebook、脚本与可复用训练框架，重点模块为 ins_pricing/modelling/bayesopt。
目录结构（顶层）
Auto Info/：车辆信息相关的爬取、预处理与词向量实验GLM and LGB/：GLM/LightGBM 及业务建模实验OpenAI/：OpenAI 相关 Notebook 原型Python Code/：可直接运行的脚本工具others/：临时或杂项 Notebookins_pricing/：可复用训练框架与 CLI 工具（含 BayesOpt 子包）user_packages legacy/：历史版本快照
说明：ins_pricing/modelling/demo/ 仅在仓库中保留，PyPI 包不包含该目录。
快速开始
建议在仓库根目录运行以下命令：
python -m venv .venv
source .venv/bin/activate # Windows: .\\.venv\\Scripts\\activate
pip install pandas scikit-learn lightgbm seaborn matplotlib
启动 Notebook：
jupyter lab
BayesOpt 使用入口
- CLI 批量训练：
python ins_pricing/modelling/BayesOpt_entry.py --config-json <path> - 增量训练：
python ins_pricing/modelling/BayesOpt_incremental.py --config-json <path> - Python API：
from ins_pricing.modelling import BayesOptModel
测试
pytest -q
数据与输出
- 建议将共享数据放在
data/（如不存在可自行创建） - 训练输出默认写入
plot/、Results/、model/ - 密钥与大文件请放在仓库外，并使用环境变量或
.env管理
Release history Release notifications | RSS feed
Download files
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.
Source Distribution
ins_pricing-0.1.0.tar.gz
(136.1 kB
view details)
Built Distribution
Filter files by name, interpreter, ABI, and platform.
If you're not sure about the file name format, learn more about wheel file names.
Copy a direct link to the current filters
ins_pricing-0.1.0-py3-none-any.whl
(161.9 kB
view details)
File details
Details for the file ins_pricing-0.1.0.tar.gz.
File metadata
- Download URL: ins_pricing-0.1.0.tar.gz
- Upload date:
- Size: 136.1 kB
- Tags: Source
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/6.2.0 CPython/3.9.18
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 |
4881db004619e13e3c54858efc255aaaeb7a1dcfff971f9e51126c0812dc7ca1
|
|
| MD5 |
956e98584bdd9dd3e4af89931166411f
|
|
| BLAKE2b-256 |
9c444c7c3cbd5dc230440061cf062ec6cf42ac5c9657b0789d9a45bba858a6f3
|
File details
Details for the file ins_pricing-0.1.0-py3-none-any.whl.
File metadata
- Download URL: ins_pricing-0.1.0-py3-none-any.whl
- Upload date:
- Size: 161.9 kB
- Tags: Python 3
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/6.2.0 CPython/3.9.18
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 |
ef37ea98d66e6bc3863941196867f1f2cd49500737bb68a9abc6d33f64ff5ac0
|
|
| MD5 |
7d8d73615520a84ba3b8326f266ae9c3
|
|
| BLAKE2b-256 |
a488550ecdcb666c49fdd776a8c652b4533d6ec3d6800297aecd95c6f71b54a3
|
