This project is a Django-based web application for predicting house prices using a machine learning model. The application allows users to input various features of a house and get a predicted price based on a trained model.
- Predict house prices based on user-provided features.
- Dockerized deployment for easy scaling and management.
- Django
- Python
- Scikit-Learn
- Docker
- Clone the repository.
- Install dependencies using
pip install -r requirements.txt. - Run the Django server using
python manage.py runserver.
- Visit the web application.
- Enter the details of the house you want to predict the price for.
- View the predicted price.
- Deploy the application on a cloud platform.
- Use Docker for containerized deployment.
This House Price Prediction tool is an advanced machine learning project designed to estimate house prices based on various factors. Developed as a demonstration project, it incorporates the following key features:
- Data Source: Utilizes data from the 1990 California census.
- AI Model: Built using the RandomForestRegressor algorithm, a robust and reliable model for regression tasks.
- Book Reference: The model and techniques are derived from Aurélien Géron's acclaimed book "Hands-On Machine Learning with Scikit-Learn, Keras, and TensorFlow" (Second Edition), specifically Chapter 2 on End-to-End Machine Learning Projects.
- Key Factors Considered: The predictor takes into account location, ocean proximity, population density, median income, and median age.
- Included Resources: The model training dataset and Jupyter notebook are available in the
predictor/utilsdirectory.
The aim is to showcase the practical application of machine learning in real-world scenarios. While the predictions are based on historical data and advanced algorithms, they are intended for educational and demonstration purposes only. Explore the potential of AI in the real estate market with this tool.
Developer: This project was developed by Innocent Waluza.