An interactive dashboard for analyzing real estate properties with geospatial visualization and investment scoring.
- Interactive map with property locations
- Price per square foot visualization
- XGBoost-based investment scoring
- 12-month price projections
- Filters for:
- Zipcode
- Bedrooms/Bathrooms/Floors
- Square footage range
- Price range
- Python 3.7 or higher
- pip package manager
pip install dash plotly pandas scikit-learn xgboost joblib| Package | Version | Purpose |
|---|---|---|
| dash | >=2.0.0 | Web framework |
| plotly | >=5.0.0 | Interactive visualizations |
| pandas | >=1.0.0 | Data processing |
| scikit-learn | >=1.0.0 | Model support |
| xgboost | >=1.5.0 | ML model |
| joblib | >=1.0.0 | Model serialization |
- Clone the repository:
git clone https://github.com/yourusername/GeoProp-Analyzer.git
cd GeoProp-Analyzer- Create and activate virtual environment:
python -m venv .venv
# On Windows:
.venv\Scripts\activate
# On macOS/Linux:
source .venv/bin/activate- Install dependencies:
pip install -r requirements.txtGeoProp-Analyzer/
├── data/
│ └── filtered_real_estate_data.csv # Sample dataset
├── gui/
│ ├── main_window.py # Dashboard implementation
│ └── xgboost_investment_model.pkl # Trained model
├── models/
│ ├── data_processor.py # Data handling
│ └── real_estate.py # Property class
├── main.py # Entry point
└── README.md # Documentation
- Start the server:
python main.py- Access the dashboard:
- Open your web browser
- Navigate to:
http://localhost:8050/
If the page doesn't load:
- Verify the server is running (you should see output in your terminal)
- Check your firewall settings
- The application requires the model file (
xgboost_investment_model.pkl) to be present in the gui folder - Sample data should be placed in the data folder
- First run may take longer as it loads the ML model