title	MLOps Pipeline
emoji	🌸
colorFrom	green
colorTo	purple
sdk	docker
pinned	false

🌸 Iris Intelligence : MLOps Pipeline with Docker

Author: Aarica Raj GitHub: @Aaricacoding Live Demo: https://mlops-pipeline-py3l.onrender.com Tech Stack: Python · Scikit-learn · Flask · Docker · Docker Compose · Render

---

📸 Web Preview

---

🎥 Demo Video

Watch Demo Video

---

📌 What is this project?

Iris Intelligence is a complete end-to-end MLOps pipeline that:

• Trains a Random Forest ML model on the classic Iris dataset
• Serves predictions via a Flask REST API
• Features a stunning 3D UI with particle effects and card tilt animations
• Packaged in a Docker container runs anywhere!

The app predicts the Iris flower species (Setosa, Versicolor, Virginica) based on 4 measurements - accessible from any device through a public URL!

---

🎆 UI Features:

Feature	Detail
3D Spinning Flower	Colorful flower rotates in 3D at the top
Particle Network	60 floating particles with connecting lines
3D Card Tilt	Cards tilt in 3D on mouse hover
Gradient Text	Title shimmers with sage to blush gradient
Glowing Inputs	Inputs glow green when focused
Shimmer Button	Light sweeps across button on hover
Pulsing Result	Result card glows and pulses on prediction
Dark Theme	Deep dark background with color accents

---

🧠 How Does It Work? (Architecture)

┌─────────────────────────────────────────────────┐
│                Docker Container                  │
│                                                  │
│  ┌──────────────┐     ┌───────────────────────┐  │
│  │ train_       │     │     Flask REST API     │  │
│  │ model.py     │────▶│  GET  /  → 3D Web UI  │  │
│  │              │     │  POST /predict → ML    │  │
│  │ Trains &     │     │  GET  /health → Check  │  │
│  │ saves        │     └──────────┬────────────  │  │
│  │ model.pkl    │               │               │  │
│  └──────────────┘               ▼               │  │
│                    ┌────────────────────────┐   │  │
│                    │  Random Forest Model   │   │  │
│                    │  Accuracy: ~97%        │   │  │
│                    └────────────────────────┘   │  │
└─────────────────────────────────────────────────┘
         │
         ▼
  Browser / Phone / Any Device 🌍

Key Concepts:

Concept	Explanation
MLOps	Combining ML + DevOps for production deployment
Docker	Packages app + dependencies into portable container
Flask	Lightweight Python web framework for REST APIs
REST API	Standardized way for apps to communicate over HTTP
Random Forest	Ensemble ML model using multiple decision trees
Docker Compose	Tool to manage multi-container Docker apps

---

📁 Project Structure

mlops-pipeline/
│
├── app.py               ← Flask REST API + 3D Web UI
├── train_model.py       ← Train and save ML model
├── model.pkl            ← Saved trained model (auto-generated)
├── requirements.txt     ← Python dependencies
├── Dockerfile           ← Docker container configuration
├── docker-compose.yml   ← Docker Compose configuration
└── README.md            ← This documentation

---

⚙️ Setup & Run

Option 1 : Run with Docker 🐳 (Recommended)

# Step 1 : Clone repo
git clone https://github.com/Aaricacoding/mlops-pipeline.git
cd mlops-pipeline

# Step 2 : Build Docker image
docker build -t mlops-pipeline .

# Step 3 : Run container
docker run -p 8080:8080 mlops-pipeline

Option 2 : Run with Docker Compose

docker-compose up --build

Option 3 : Run without Docker

pip install -r requirements.txt
python train_model.py
python app.py

Open in Browser:

https://mlops-pipeline-py3l.onrender.com

---

🚀 API Endpoints

Endpoint	Method	Description
/	GET	3D Web UI — predict from browser
/predict	POST	Predict flower species
/health	GET	Check if API is running

Example API Request:

curl -X POST https://mlops-pipeline-py3l.onrender.com/predict \
  -H "Content-Type: application/json" \
  -d '{
    "sepal_length": 5.1,
    "sepal_width": 3.5,
    "petal_length": 1.4,
    "petal_width": 0.2
  }'

Example Response:

{
  "species": "Setosa",
  "confidence": 99.0,
  "prediction": 0
}

---

🧪 Example Predictions:

Sepal L	Sepal W	Petal L	Petal W	Species
5.1	3.5	1.4	0.2	🌸 Setosa
6.3	3.3	4.7	1.6	🌺 Versicolor
6.5	3.0	5.2	2.0	🌹 Virginica

---

🔧 Technologies Used:

Tool	Purpose
Python 3.10	Core programming language
Scikit-learn	ML model training (Random Forest)
Flask	REST API framework
Docker	Containerization
Docker Compose	Container orchestration
NumPy	Numerical computations

---

💡 What I Learned Building This:

• How to build a production-ready ML API using Flask
• How to containerize a Python app using Docker
• How Dockerfile works step by step
• How Docker Compose simplifies deployment
• How to create a REST API for ML models
• How to build a 3D interactive UI with vanilla CSS/JS
• End-to-end MLOps pipeline from training to deployment

---

🔮 Future Improvements:

• Add MLFlow for experiment tracking
• Add CI/CD pipeline with GitHub Actions
• Deploy on AWS/GCP/Azure cloud
• Add model versioning
• Add Kubernetes for scaling
• Add monitoring with Prometheus + Grafana
• Custom domain setup

---

📄 License

MIT License — free to use, modify, and share!

---

🙏 Acknowledgements

• Scikit-learn — for ML library
• Flask — for web framework
• Docker — for containerization