Diabetes, Hypertension and Stroke Prediction

All datasets are cleaned, augmented, and have balanced classes. Data Sources: [diabetes_data](https://www.kaggle.com/datasets/alexteboul/diabetes-health-indicators-dataset) [hypertension_data](https://smellydatascience.com/teaching/python-for-data-science/evaluation/heart_disease.csv) [stroke_data](https://gist.github.com/aishwarya8615/d2107f828d3f904839cbcb7eaa85bd04)所有数据集均经过清洗、增强，且类别分布均衡。 数据来源： [糖尿病数据集](https://www.kaggle.com/datasets/alexteboul/diabetes-health-indicators-dataset) [高血压数据集](https://smellydatascience.com/teaching/python-for-data-science/evaluation/heart_disease.csv) [中风数据集](https://gist.github.com/aishwarya8615/d2107f828d3f904839cbcb7eaa85bd04)

搜集汇总

背景与挑战

背景概述

该数据集包含70,692个来自2015年BRFSS的清理调查响应，用于糖尿病、高血压和中风的预测任务。数据集经过清理和增强，具有平衡的类别，包括年龄、性别、BMI、生活习惯等17个特征变量和1个目标变量，适用于分类模型的训练和健康研究。