Spaces:

dangminh214
/

Spam-Email-Classifier

Sleeping

App Files Files Community

Spam-Email-Classifier / README.md

dangminh214

try to fix fetch prob

e6ccabf 29 days ago

preview code

raw

history blame contribute delete

3.85 kB

metadata

title: Spam Email Classifier
emoji: 🦀
colorFrom: yellow
colorTo: red
sdk: docker
pinned: false

Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference

Spam Email Classifier

A simple Machine Learning project to classify spam email and normal email. This project is to understand basic concepts of LLM and deploy a model on a server using fastapi and interact with HTML UI

Dataset

This project utilizes the Spam Emails Dataset, a dataset in machine learning that contains many samples of Emails and messages, each classifier into two classes: ham(for legit email) and spam (for spam email)

Installation & Setup

Prerequisites

Python 3.8+
FastAPI
Scikit-learn
Pandas
HTML

Export classification model

To re-train or export new models run command:
```
python export_model.py 
```

Running Steps using Docker (Port 8888)

Clone the repository
Clone the project repository to your local machine.
```
git clone <repository-url>
cd <repository-folder>
```
Install dependencies
Install the required Python dependencies.
```
pip install -r requirements.txt
```
Build Docker Image
```
docker build -t app .
```
Run Docker Image
```
docker run -p 8888:8888 app
```

Running Steps Locally (If run locally, default port will be 8000)

Clone the repository
Clone the project repository to your local machine.
```
git clone <repository-url>
cd <repository-folder>
```
Install dependencies
Install the required Python dependencies.
```
pip install -r requirements.txt
```
Start the FastAPI server
Run the FastAPI server to serve the model (default port 8000).
```
127.0.0.1:8000
```
```
uvicorn server:app --reload
```
or
```
python -m uvicorn server:app --reload 
```
Access API Documentation
Open the following API documentation in your browser:
- Local Server:
  - Swagger UI: http://127.0.0.1:8000/docs
  - Redoc: http://127.0.0.1:8000/redoc
- Remote Sever using Hugging Face: https://dangminh214-spam-email-classifier.hf.space/docs
Run the client-side application
Open web/index.html in web browser

API Endpoints

POST `/predict`

Predicts the E-Mail if it is a Spam E-Mail or not

Request Body (JSON):
```
{
  "text": "Hi I am Minh"
}
```
Response:
```
{
  "prediction": "ham"
}
```

GET `/`

Give the information of project to user

Response:

{
  "info": "Welcome to Dang Minh EMail Spam Classifier Model, this is a personal project to practice my knowledge in NLP and MLops"
}

Deploy remotely on HF

Server URL bash https://dangminh214-spam-email-classifier.hf.space

Expandability

This project can be expanded beyond just the provided HTML file. It can be integrated with other web frameworks, such as ReactJS, to create an even more interactive and user-friendly interface. This will further enhance the usability and scalability of the application.

Demo Usage

Contributing

Contributions are welcome! If you find any issues or want to suggest improvements, feel free to open an issue or submit a pull request.

License

This project is licensed under the MIT License.