electricsheepafrica/africa-wash-uganda

Water Point Data Exchange (UGA) 数据集是一个专注于乌干达农村水点（如井、泉水、水龙头）的众包数据集合，由Water Point Data Exchange平台发布。该平台整合了政府、非政府组织和研究人员提供的数据，并遵循WPdx数据标准进行清洗和标准化，形成可用于分析的稳健数据集。本数据集属于WPdx-Plus版本，是基础数据集的子集，针对乌干达等国家进行了额外清洗，常用于决策支持工具，以评估农村基本供水服务访问情况、优先修复水点建议、识别服务缺口区域和高风险水点。数据集包含两个主要文件：wpdx_adm_region_analysis提供各行政级别的人口服务概况（包括已服务、未服务和未测绘人口）及基于水点记录年龄的数据质量分析；wpdx_water_points提供每个水点的详细信息，包括所有WPdx数据标准参数以及修复优先级、服务缺口/新建和状态预测分析结果。数据集共98,768行、39列，涵盖地理、时间、人口统计、标识符等变量，如经纬度、报告日期、水来源、管理类型、人口数据等。数据已由Electric Sheep Africa处理为ML就绪的Parquet格式，分为训练集（79,014行）和测试集（19,753行）。

The Water Point Data Exchange (UGA) dataset is a crowdsourced collection focused on rural water points (e.g., wells, springs, tapstands) in Uganda, published by the Water Point Data Exchange platform. It consolidates data from governments, NGOs, and researchers, cleaned and harmonized using the WPdx Data Standard to create a robust analysis-ready dataset. This dataset is part of the WPdx-Plus version, a subset of the Basic dataset that undergoes additional cleaning for countries like Uganda and is used in decision support tools to assess rural basic water service access, prioritize water point repairs, highlight service gaps, and identify high-risk water points. It includes two main files: wpdx_adm_region_analysis provides an overview of population served, unserved, and uncharted at administrative levels along with data quality analysis based on water point record age; wpdx_water_points offers water point-level details with all WPdx standard parameters and results from Rehab Priority, Service Gap/New Construction, and Status Prediction analyses. The dataset contains 98,768 rows and 39 columns, covering geographic, temporal, demographic, and identifier variables such as latitude/longitude, report date, water source, management type, and population data. It has been curated into ML-ready Parquet format by Electric Sheep Africa, split into train (79,014 rows) and test (19,753 rows) sets.