electricsheepafrica/africa-health-facilities-all

塞拉利昂卫生设施数据集提供了塞拉利昂公共卫生设施的详细信息，包括地理、时间和管理单元观察数据。数据集包含1,731行和22列，其中3列为数值型，19列为分类变量。数据分为训练集（1,384行）和测试集（346行）。地理范围涵盖非洲多个国家，数据最后更新于2023年11月30日。数据集包含卫生设施的类型、状态、位置、管理单位等信息，并已转换为适合机器学习的Parquet格式。需要注意的是，部分列存在较高的缺失值比例，建模时应谨慎处理。

The Sierra Leone Health Facilities dataset provides detailed information on public health facilities in Sierra Leone, including geographic, temporal, and administrative unit observations. The dataset contains 1,731 rows and 22 columns, with 3 numeric and 19 categorical columns. It is split into a training set (1,384 rows) and a test set (346 rows). The geographic scope covers multiple countries in Africa, with the data last updated on November 30, 2023. The dataset includes information on the type, status, location, and administrative units of health facilities and has been converted into a machine-learning-ready Parquet format. Note that some columns have a high percentage of missing values and should be treated with caution in modeling.