BPS 风湿与自身免疫采购数据集（1997–2025）

数据集获取

源站：https://doi.org/10.5281/zenodo.21650855

标准获取流程：

1. 访问源站链接，注册/登录账号；
2. 进入数据集详情页，按页面指引申请权限或直接下载；
3. 部分平台提供 SDK，例如：
   • OpenDataLab: pip install openxlab 后 openxlab.dataset.get(...)
   • ModelScope: pip install modelscope 后 modelscope download
   • 天池: 登录后页面提供直链下载
     以源站「数据下载/使用文档」页面为准。

数据集大小约 185.2 MB。

数据说明

Description The BPS Rheumatic and Autoimmune Procurement Dataset (BPS-RAPD) is a curated dataset derived from the Banco de Preços em Saúde (BPS), an official public information system maintained by the Brazilian Ministry of Health. The dataset contains public procurement records of high-cost medicines used in the treatment of rheumatic and autoimmune diseases. The original transactional records were extracted from the BPS database, processed, standardized, validated, and organized into structured analytical datasets suitable for statistical analysis, machine learning, and time series forecasting. The repository provides: - The processed analytical dataset used in the associated research article, available in Apache Parquet, CSV, and Microsoft Excel formats.- An additional dataset containing all medicine procurement records extracted from the BPS, with hospital supplies and other non-pharmaceutical healthcare products removed.- Historical (“Legacy”) and standardized (“Modern”) data used during the preprocessing stage.- Documentation describing the dataset structure and variables. The archived version corresponds to the exact datasets generated during the research project. Since the official BPS database is continuously updated by the Brazilian Ministry of Health, future extractions may differ from the versions preserved in this repository. ### Data Source The original data were obtained from the Banco de Preços em Saúde (BPS): https://www.gov.br/saude/pt-br/acesso-a-informacao/banco-de-precos ### Applications This dataset can support research in areas including: - Healthcare expenditure analysis- Public procurement analytics- Health economics- Machine learning- Time series forecasting- Public policy evaluation- Open government data- Reproducible research

数据加载示例（图像类）

from PIL import Image
import glob, os

files = (glob.glob(os.path.join(path, "**", "*.png"), recursive=True)
       + glob.glob(os.path.join(path, "**", "*.jpg"), recursive=True)
       + glob.glob(os.path.join(path, "**", "*.tif"), recursive=True))
print("图像文件数:", len(files))
img = Image.open(files[0]); print("尺寸/模式:", img.size, img.mode)

# torchvision Dataset 方式:
# from torchvision import datasets
# ds = datasets.ImageFolder(path)  # 要求 子目录=类别

目录组织与标注格式以源站说明和下载后实际文件为准。