House Price Predictor

A machine learning web app that predicts California house prices based on neighbourhood and property details.

Built as Project 3 of a 4-project Machine Learning series using the Zero to Mastery ML course as a learning foundation.

• Takes 8 neighbourhood/house inputs
• Uses a trained Random Forest Regressor to predict the house value
• Displays the estimated price in USD
• Includes example values to try out

pip install flask scikit-learn numpy joblib

python3 train_model.py

python3 app.py

http://127.0.0.1:5000

house-price-predictor/
├── train_model.py       # Loads dataset, trains and saves the model
├── app.py               # Flask web server
├── model.joblib         # Saved trained model (generated after training)
├── templates/
│   └── index.html       # Web page with input form and result
└── static/
    └── style.css        # Styling

Affordable Area:

• Income: 2.0, Age: 40, Rooms: 4, Beds: 2, Pop: 800, Occupants: 3, Lat: 36, Lon: -120

Expensive Area (San Francisco):

• Income: 8.0, Age: 10, Rooms: 7, Beds: 3, Pop: 500, Occupants: 2, Lat: 37.77, Lon: -122.4

California Housing Dataset built into Scikit-Learn (sklearn.datasets.fetch_california_housing). Originally from the 1990 California census.