README.md

metadata

title: ML Auto Deployment
emoji: 🚀
colorFrom: blue
colorTo: indigo
sdk: docker
pinned: false

🚀 Automated ML Deployment System

A production-grade, fully automated end-to-end Machine Learning operations (MLOps) pipeline. This system automates the entire lifecycle of a model—from training to containerized deployment—ensuring that every code change triggers a fresh model iteration and a seamless update to a Premium Interactive Dashboard on Hugging Face Spaces.

✨ Key Features

• 🎨 Premium Interactive UI: A modern, glassmorphism-inspired dashboard for real-time model interaction.
• 🔄 Full CI/CD Pipeline: Automated training and deployment via GitHub Actions.
• 🧠 Auto-Training: Automatically retrains the Random Forest model on every push to main.
• 🐳 Containerized Serving: Uses Docker for consistent environments across development and production.
• ⚡ Real-time Predictions: Instant feedback as you adjust feature sliders on the web interface.
• ☁️ Serverless Deployment: Optimized for cost and performance on Hugging Face Spaces.

🏗️ Architecture Overview

graph TD
    A[Code Push to GitHub] --> B{GitHub Actions}
    B --> C[Install Dependencies]
    C --> D[Train Model - Scikit-Learn]
    D --> E[Export model.joblib]
    E --> F[Build Docker Image]
    F --> G[Deploy to Hugging Face Spaces]
    G --> H[Live FastAPI API & Static UI]
    H --> I[User Interaction via Sliders]
    I --> J[Real-time Prediction Result]

🛠️ Tech Stack

Category	Technology
Language	Python 3.10
ML Framework	Scikit-Learn, Pandas
Frontend	Vanilla HTML5, CSS3 (Glassmorphism), JavaScript (ES6+)
API Framework	FastAPI, Uvicorn
CI/CD	GitHub Actions
Containerization	Docker
Hosting	Hugging Face Spaces

🚀 Quick Start

Local Development

To run this project locally:

1. Clone & Setup:

   git clone https://github.com/SadeepSachintha/Automated-ML-Deployment-System.git
   cd "Automated ML Deployment System"
   python -m venv venv
   source venv/bin/activate  # venv\Scripts\activate on Windows
   

2. Install & Train:

   pip install -r model/requirements.txt
   pip install -r app/requirements.txt
   python model/train.py
   

3. Launch Dashboard:

   uvicorn app.main:app --reload --port 8000
   

   Visit http://localhost:8000 to see the interactive UI.

📡 API Documentation

While the primary interaction is via the web UI, the underlying API is fully accessible:

• Health Check: GET /health
• Prediction: POST /predict

  {
    "sepal_length": 5.1, "sepal_width": 3.5,
    "petal_length": 1.4, "petal_width": 0.2
  }
  

📂 Project Structure

• app/: FastAPI application and serving logic.
  • static/: [NEW] Premium frontend assets (HTML/CSS/JS).
  • model_data/: Serialized model binaries.
• model/: Training scripts and model definitions.
• .github/workflows/: CI/CD pipeline definitions.
• k8s/: Kubernetes manifests (Legacy AWS EKS config).
• Dockerfile: Production container configuration.

📝 License

MIT License - see the LICENSE file for details.