Replication Data and Code for: Predicting Structural Sanitary Vulnerability Through Machine Learning: A Proxy Means Testing Approach With Imbalanced Data in Peru

This repository contains the R replication script and datasets required to reproduce the machine learning models and high-resolution figures presented in the manuscript. The raw data is sourced from the National Household Survey (ENAHO) 2025.本仓库收录了复现该论文手稿中所述机器学习模型与高分辨率图件所需的R语言复现脚本及配套数据集。原始数据取自2025年全国住户调查（National Household Survey, ENAHO）。