🌸 FastAPI + Streamlit Iris Predictor (Week 2)

This project demonstrates how to serve a trained Iris species classifier with a FastAPI backend and an interactive Streamlit UI, all containerized with Docker & Docker Compose.

---

🚀 Run locally

uvicorn main:app --reload

Open API Docs: http://127.0.0.1:8000/docs

---

🐳 Run with Docker

docker build -t myfastapi:dev .
docker run --rm -p 8000:8000 myfastapi:dev

---

🐙 Run with Docker Compose

docker compose up --build
docker compose down

To run in background (detached mode):

docker compose up --build -d

Services

• API Docs: http://localhost:8000/docs
• Health Check: http://localhost:8000/health
• Streamlit UI: http://localhost:8501

---

📸 Screenshots

🌐 Streamlit UI

✅ Health Check Endpoint

📖 Swagger API Docs

🔍 Predictions

Versicolor

Virginica

Setosa

---

🏋️ Training the Model (first run only)

docker compose exec api python IrisWorking/train_iris.py

---

📦 Tech Stack

• FastAPI → API backend
• Streamlit → Frontend UI
• scikit-learn → Machine Learning model
• Docker + Docker Compose → Containerization & orchestration

---

✨ With this setup, you can interact with the Iris ML model via Swagger Docs or use the Streamlit web UI to visualize predictions.