In order to run our program pip install -r requirements.txt python -m sleep_nerd Sleep Nerd is a desktop wellness application developed during the MadData Hackathon that combines behavioral input, stress modeling, and machine learning to estimate sleep disorder risk and provide personalized health insights. The application features an interactive Tkinter-based intake form where users enter lifestyle factors such as sleep duration, stress levels, caffeine consumption, exercise frequency, and screen time. These inputs are processed through a trained machine learning model built using scikit-learn, along with a stress estimation engine that applies weighted behavioral factors to generate a wellness assessment.

Based on the results, the app presents risk predictions, tailored recommendations, and dynamic avatar feedback that visually reflects the user’s predicted state. User data is stored locally through JSON persistence, enabling continued tracking and personalized responses over time. The backend integrates data preprocessing, Random Forest classification, and stored model artifacts trained on real sleep health and student stress datasets. The project is built with Python 3.11 using Tkinter for the graphical interface and common data science libraries including Pandas, NumPy, Joblib, and Pillow. Sleep Nerd is designed as a wellness-support tool and is not intended to provide medical diagnosis or replace professional healthcare guidance.

Sleep Nerd is a desktop wellness application developed during the MadData Hackathon that combines behavioral input, stress modeling, and machine learning to estimate sleep disorder risk and provide personalized health insights. The application features an interactive Tkinter-based intake form where users enter lifestyle factors such as sleep duration, stress levels, caffeine consumption, exercise frequency, and screen time. These inputs are processed through a trained machine learning model built using scikit-learn, along with a stress estimation engine that applies weighted behavioral factors to generate a wellness assessment. Based on the results, the app presents risk predictions, tailored recommendations, and dynamic avatar feedback that visually reflects the user’s predicted state. User data is stored locally through JSON persistence, enabling continued tracking and personalized responses over time. The backend integrates data preprocessing, Random Forest classification, and stored model artifacts trained on real sleep health and student stress datasets. The project is built with Python 3.11 using Tkinter for the graphical interface and common data science libraries including Pandas, NumPy, Joblib, and Pillow. Sleep Nerd is designed as a wellness-support tool and is not intended to provide medical diagnosis or replace professional healthcare guidance.