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

Python FastAPI with JWT Auth serving ML for House Price Prediction (v2)
https://github.com/persteenolsen/fastapi-jwt-auth-ml-two

fastapi jwt machine-learning python

Last synced: 9 days ago
JSON representation

Python FastAPI with JWT Auth serving ML for House Price Prediction (v2)

• Host: GitHub
• URL: https://github.com/persteenolsen/fastapi-jwt-auth-ml-two
• Owner: persteenolsen
• Created: 2026-04-18T13:40:39.000Z (2 months ago)
• Default Branch: main
• Last Pushed: 2026-05-04T09:25:44.000Z (about 2 months ago)
• Last Synced: 2026-05-04T11:28:45.165Z (about 2 months ago)
• Topics: fastapi, jwt, machine-learning, python
• Language: Python
• Homepage: https://fastapi-jwt-auth-ml-two.vercel.app/docs
• Size: 33.2 KB
• Stars: 0
• Watchers: 0
• Forks: 0
• Open Issues: 0
• Metadata Files:
  • Readme: README.md

Awesome Lists containing this project

README

          
# 🏠 v2 - House Price Prediction API (FastAPI + JWT + ML)

Last updated:

- 20-04-2026

A simple but production-style Machine Learning API built with FastAPI, JWT authentication, and a scikit-learn pipeline model.

This project demonstrates how to move from a basic ML script to a full backend service.

---

## 🚀 Features

- JWT authentication

- Machine Learning model (scikit-learn pipeline)

- Lazy-loaded model for performance

- Pydantic v2 request validation

- FastAPI REST API

- Synthetic housing dataset generator

---

## 📁 Project Structure

app.py → FastAPI backend (auth + prediction API)  

train.py → Model training script  

generate_data.py → Dataset generator (optional)  

housing_v2.csv → Generated dataset  

model.pkl → Trained ML model  

requirements.txt → Dependencies  

.env → Environment variables  

---

## ⚙️ Installation

### 1. Clone project

git clone   

cd   

---

### 2. Create virtual environment

python -m venv venv  

Activate virtual environment:

Windows:

venv\Scripts\activate  

Mac/Linux:

source venv/bin/activate  

---

### 3. Install dependencies

pip install -r requirements.txt  

---

## 🔐 Environment Variables (.env)

Create a file named `.env`:

SECRET_KEY=your_secret_key_here  

FAKE_USERNAME=admin  

FAKE_PASSWORD=1234  

---

## 🧠 Train the Model

(Optional) Generate dataset:

python generate_data.py  

Train model:

python train.py  

This creates:

model.pkl  

---

## 🚀 Run the API

python app.py  

API runs at:

http://127.0.0.1:8000  

---

## 📡 API Endpoints

### 🔐 Login

POST /login  

Request:

{

  "username": "admin",

  "password": "1234"

}

Response:

{

  "token": "your_jwt_token"

}

---

### 🏠 Predict House Price

POST /predict  

Header:

Authorization: Bearer   

Request:

{

  "size": 140,

  "rooms": 4,

  "year_built": 2005,

  "location": "suburb",

  "condition": "good"

}

Response:

{

  "user": "admin",

  "input": {

    "size": 140,

    "rooms": 4,

    "year_built": 2005,

    "location": "suburb",

    "condition": "good"

  },

  "predicted_price": 312450.55

}

---

## 🧠 Tech Stack

- FastAPI

- scikit-learn

- pandas

- PyJWT

- Uvicorn

- Pydantic v2

---

## 📈 What this project demonstrates

- ML pipelines (not just scripts)

- REST API design for ML systems

- JWT authentication

- Model deployment basics

- Data preprocessing with ColumnTransformer

---

## 🚀 Next improvements

- Add PostgreSQL for storing predictions

- Real user authentication system

- Model versioning

- Docker deployment

- Logging + monitoring

---

## 👨‍💻 Author

Built as a learning project for combining Machine Learning with backend engineering