数据集获取

git clone https://github.com/14Richa/Patient-Readmission-Analysis.git

curl -L -o repo.zip https://github.com/14Richa/Patient-Readmission-Analysis/archive/refs/heads/main.zip
unzip repo.zip

源站 README 摘录（使用方式）

Predictive Modeling for Hospital Readmission

Overview

This project focuses on predictive modeling to foresee hospital readmissions of diabetic patients within 30 days post-discharge. By leveraging a dataset spanning a decade (1999-2008) and covering records from 130 US hospitals, the aim is to enhance healthcare management and patient outcomes.

Data Sources

• The dataset spans a decade (1999-2008) and includes records from 130 US hospitals, focusing on diabetic patients.
• You can access the dataset via the following link: Diabetes 130-US hospitals for years 1999-2008

Project Structure

• diabetic_data.csv: Contains the dataset used in the analysis.
• Readmission_Predictions.ipynb: Includes Jupyter notebook used for exploratory data analysis, data cleaning, and modeling.
• requirements.txt: Lists the Python packages and their versions required for this project.
• Final_Report.pdf: Contains the final report summarizing the analysis, findings, and conclusions.

Python Version

This project was developed using Python 3.9.

Setting Up the Development Environment

Create a virtual environment

python3 -m venv env

Activate environment

source env/bin/activate

Install dependencies

pip install -r requirements.txt

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/14Richa/Patient-Readmission-Analysis