This project focuses on the deployment phase of the Machine Learning lifecycle. I have converted a Sales Prediction model into a production-ready RESTful API using Flask. This allows any web or mobile application to send data and receive sales forecasts in real-time.
- Model-as-a-Service: The model is no longer just a script; it functions as a live backend service.
- Dockerized Environment: Included a
Dockerfileto ensure the application runs consistently across different operating systems and cloud providers. - Efficient Edge Computing: The entire backend server was successfully deployed and tested within the Pydroid 3 environment on a mobile device.
- Framework: Flask (Python)
- Containerization: Docker
- Libraries: NumPy, Scikit-learn
- Environment: Pydroid 3
- Clone the repository.
- Install dependencies:
pip install -r requirements.txt. - Run the application:
python app.py. - The API will be live at
http://127.0.0.1:5000.
- Endpoint:
/predict - Method:
POST - Input Format (JSON): ```json { "tv": 230.1, "radio": 37.8, "newspaper": 69.2 }