This project predicts incident counts using a RandomForest model based on the month, district, and neighborhood. The model utilizes features such as time (encoded month or hour), normalized incident counts, and cluster information derived from K-means clustering, along with categorical data like police districts and neighborhoods.
You can find our app running at https://policeallocation.streamlit.app/
For running this repository locally
Ensure you have the following installed:
- Python 3.7+
- pandas
- numpy
- scikit-learn
- streamlit
- joblib
You can install the necessary libraries using pip:
pip install pandas numpy scikit-learn streamlitgit clone https://github.com/your-username/your-repository.git
cd your-repository
To run the Streamlit application:
streamlit run app.py
Navigate to http://localhost:8501 in your web browser to interact with the app.