为什么值得关注

这是一个自包含的教育项目，将公认的排放因子与运行时训练的 scikit-learn 模型结合，用户无需外部数据集即可查看当前碳足迹和未来预测。

适合谁使用

希望获得大致碳足迹估算的家庭用户
寻找小型可运行示例的 Python/Streamlit 学习者
需要简单排放基准演示的可持续发展教育者
对在 Web 应用中集成轻量 ML 模型感兴趣的开发者

典型使用场景

估算家庭在用电、车辆出行和饮食习惯方面的碳排放
在电网逐步脱碳的假设下预测未来 1–10 年的个人碳足迹
通过滑块模拟行为变化并比较不同情景
下载纯文本碳足迹报告，供个人或课程作业使用

项目优势

无需下载外部数据集，排放因子使用公开常量
交互式可视化包括饼图分解、基准对比、生态评分和排序建议
趋势模型自包含：运行时用 scikit-learn 在合成数据上训练
包含清晰的本地运行、GitHub 上传和部署说明

使用前须知

排放因子是广泛引用的近似值，并非认证碳核算
AI 预测基于运行时生成的合成数据，而非真实历史数据
需要配置 Python 环境并手动启动；仓库中未包含已托管的演示链接

README 快速开始

🌍 Carbon Footprint Analyzer

A Streamlit web app that estimates your household's carbon emissions from electricity usage, vehicle travel, and food habits — then uses a small regression model to project your yearly impact, benchmarks you against national/global averages, and gives a ranked improvement plan.

✨ Features

Emission breakdown (pie chart) across electricity / travel / food
Benchmark comparison vs. Average Indian, Global Average, Paris Agreement target
AI trend projection: a scikit-learn regression model (trained on synthetic data generated at runtime) projects your footprint 1–10 years ahead, factoring in gradual grid decarbonisation
Eco Score (A–F grade)
Ranked, personalised improvement tips
"What-if" simulator — drag sliders to see the impact of behaviour changes
Downloadable plain-text report

No external dataset download is required. All emission factors are well-established public constants (see app.py), and the "AI" trend model trains itself on synthetically generated data each time the app starts (see model.py).

🗂️ Project Structure

carbon-footprint-analyzer/
├── app.py              # Streamlit UI + calculations
├── model.py            # Synthetic-data regression model (the "AI" part)
├── requirements.txt    # Python dependencies
├── .gitignore
└── README.md

🖥️ Running it locally in VS Code

Yes — this project runs perfectly in VS Code. Steps:

Install prerequisites
- Python 3.9+
- VS Code with the official Python extension installed.
Open the project folder in VS Code File → Open Folder… → select carbon-footprint-analyzer.
Create a virtual environment (open a VS Code terminal: Ctrl+`)
```
python -m venv venv
```
Activate it:
- Windows: venv\Scripts\activate
- macOS/Linux: source venv/bin/activate VS Code will usually prompt "Select this environment" — click yes.
Install dependencies
```
pip install -r requirements.txt
```
Run the app
```
streamlit run app.py
```
It opens automatically at http://localhost:8501.

⬆️ Uploading this project to GitHub

Checklist of what a project needs before pushing (all already included here): README.md, .gitignore, requirements.txt, and cle

carbon-footprint-analyzer