糖尿病数据集

数据集获取

git clone https://github.com/ssallonni/DiabetesDataset.git

curl -L -o repo.zip https://github.com/ssallonni/DiabetesDataset/archive/refs/heads/main.zip
unzip repo.zip

源站 README 摘录（使用方式）

Introduction:
Access to quick, inexpensive medical diagnostics is a major problem in many regions of the world, particularly in those where healthcare is privatized. Diabetes is a common chronic illness that needs to be managed closely from the beginning to avoid serious consequences. However, delayed diagnosis is frequently the result of high costs and restricted availability of routine medical examinations, especially for those living in underprivileged neighborhoods. This study aims to address the problem of limited access to affordable and timely medical diagnostics by creating multiple predictive algorithms that evaluate the risk of diabetes using easily accessible medical and demographic data. Our goal is to identify an algorithm that best offers a practical and cost-effective method to identify individuals at high risk of diabetes by focusing on the impacts of Body Mass Index (BMI) on diabetes outcomes, insulin levels, and glucose levels. This approach not only enhances early detection but also empowers individuals to proactively manage their health, leading to improved overall health outcomes and reduced strain on healthcare systems.
Problem Statement:
This research aims to create multiple predictive algorithms that evaluate the risk of diabetes using easily accessible medical and demographic data. We hope to find an algorithm that can best offer a practical and affordable way to identify those who are at high risk of diabetes by concentrating on the relationship between BMI, Insulin levels, and glucose levels.
Research Question:
What are the impacts of BMI on diabetes outcomes, insulin, and glucose levels, and which predictive model best demonstrates the strength of these relationships?
Hypothesis:
Higher BMI is associated with higher glucose levels and insulin resistance, leading to an increased likelihood of diabetes. By analyzing these interactions, we can create a predictive model to identify high-risk individuals.
Dataset Description:
Our dataset was sourced from the diabetes dataset on Kaggle and the The file we downloaded and used was diabetes.csv. Our Diabetes dataset holds various numerical values used to study indicators and outcomes. https://www.kaggle.com/datasets/mathchi/diabetes-data-set

数据加载示例（表格/文本类）

import pandas as pd, glob, os

files = (glob.glob(os.path.join(path, "**", "*.csv"), recursive=True)
       + glob.glob(os.path.join(path, "**", "*.tsv"), recursive=True)
       + glob.glob(os.path.join(path, "**", "*.xlsx"), recursive=True))
print("数据文件:", files)
df = pd.read_csv(files[0])
print(df.shape); print(df.columns.tolist()); print(df.head(3))

完整仓库：github.com/ssallonni/DiabetesDataset