https://github.com/persteenolsen/fastapi-jwt-auth-ml-one

Python FastAPI with JWT Auth serving ML for House Price Prediction
https://github.com/persteenolsen/fastapi-jwt-auth-ml-one

fastapi jwt machine-learning python

Last synced: 9 days ago
JSON representation

Python FastAPI with JWT Auth serving ML for House Price Prediction

• Host: GitHub
• URL: https://github.com/persteenolsen/fastapi-jwt-auth-ml-one
• Owner: persteenolsen
• Created: 2026-04-14T15:35:56.000Z (2 months ago)
• Default Branch: main
• Last Pushed: 2026-04-14T16:30:46.000Z (2 months ago)
• Last Synced: 2026-04-14T17:27:06.036Z (2 months ago)
• Topics: fastapi, jwt, machine-learning, python
• Language: Python
• Homepage: https://fastapi-jwt-auth-ml-one.vercel.app/docs
• Size: 7.81 KB
• Stars: 0
• Watchers: 0
• Forks: 0
• Open Issues: 0
• Metadata Files:
  • Readme: README.md

Awesome Lists containing this project

README

          
# 🏠 v1 - House Price Prediction API (FastAPI + JWT + ML)

Last updated:

- 19-04-2026

A simple machine learning API built with FastAPI that predicts house prices based on house size and number of rooms.  

The API is secured using JWT authentication and serves a trained scikit-learn model.

---

## ✨ Features

- JWT authentication (login + protected routes)

- Machine Learning model (Linear Regression)

- FastAPI REST API

- Training pipeline using CSV dataset

- Model saved with Joblib

- Swagger UI (`/docs`) for testing

---

## 🧰 Tech Stack

- FastAPI

- Uvicorn

- Scikit-learn

- Pandas

- NumPy

- PyJWT

- Joblib

- Python-dotenv

---

## 📁 Project Structure

- app.py → FastAPI application (API + JWT + ML)

- train.py → Model training script

- data.csv → Training dataset

- model.pkl → Saved trained model

- requirements.txt → Dependencies

- .env → Environment variables

---

## ⚙️ Installation

### 1. Clone repository

git clone 

cd project

---

### 2. Create virtual environment (optional)

python -m venv venv

Activate:

- Windows:

  venv\Scripts\activate

- Mac/Linux:

  source venv/bin/activate

---

### 3. Install dependencies

pip install -r requirements.txt

---

### 4. Create .env file

SECRET_KEY=your_secret_key

FAKE_USERNAME=admin

FAKE_PASSWORD=1234

---

## 🧠 Train the Model

Run:

python train.py

This will:

- Load data.csv

- Train a Linear Regression model

- Save model as model.pkl

---

## 🚀 Run the API

Start server:

python app.py

Open:

http://localhost:8000

http://localhost:8000/docs

---

## 🔐 Authentication Flow

### Step 1: Login

POST /login

{

  "username": "admin",

  "password": "1234"

}

Response:

{

  "token": "your_jwt_token"

}

---

### Step 2: Authorize in Swagger

Click "Authorize 🔒" and enter:

Bearer 

---

## 🏠 Prediction Endpoint

POST /predict (protected)

Request:

{

  "size": 90,

  "rooms": 3

}

Response:

{

  "user": "admin",

  "input": {

    "size": 90,

    "rooms": 3

  },

  "predicted_price": 270000

}

---

## 🧠 How it works

- data.csv is used to train the model

- Linear Regression learns relationship between:

  - size

  - rooms

- Model is saved as model.pkl

- FastAPI loads model at startup

- JWT protects prediction endpoint

---

## 📈 What this project demonstrates

- Learn FastAPI + ML integration

- Build secure ML APIs

- Portfolio project

- Base for production ML services

---

## 🚀 Future Improvements

- Use real datasets (Kaggle)

- Add database (PostgreSQL)

- Add user roles

- Dockerize project

- Deploy to other cloud than Vercel if wanted

- Splitting the app.py into files and folders for better structure

---

## 👨‍💻 Author

Learning project combining:

FastAPI + JWT + Machine Learning

---

## 📜 License

Educational use only ...

Happy coding :-)