Mahdibenj22/Tunisian-Property-Price-Predictor

A machine learning-based web application for categorizing Tunisian property prices into low, mid, and high categories. # Tunisian-Property-Price-Predictor A machine learning-based web application for categorizing Tunisian property prices into low, mid, and high categories. ## Table of Contents - Overview - Features - Technologies Used - Installation - File Structure - Future Enhancements - Contributing - License ## Overview The Tunisian Property Price Predictor is a machine learning-based application that predicts property price categories (Low, Mid, High) based on features such as the number of rooms, bathrooms, size, and region. This tool aims to enhance transparency in the Tunisian real estate market by providing both users and agencies with a reliable price estimation system. ## Features - Predicts property price categories (Low, Mid, High). - User-friendly interface for feature input and result visualization. - Highlights feature importance in prediction. - Interactive charts to display prediction confidence. ## Technologies Used - Python - Streamlit - Scikit-learn - XGBoost - Pandas and NumPy for data manipulation - Matplotlib and Seaborn for visualizations ## Installation 1. Clone the repository: ```bash git clone github.com 2. Navigate to the project directory: ```bash cd Tunisian-Property-Price-Predictor 3. Install the required dependencies: ```bash pip install -r requirements.txt 4. Run the application: ```bash streamlit run app.py ## File Structure - `app.py`: Main application script that powers the web interface for property price prediction using Streamlit. - `Tunisian_Category_Price_Prediction.ipynb`: Jupyter notebook used for developing and testing the machine learning model. - `xgb_classification_model.pkl`: Pre-trained XGBoost classification model for predicting property price categories. - `Property Prices in Tunisia.csv`: Dataset containing property details used for training and testing the model. - `README.md`: Documentation file that describes the project, its features, installation instructions, …