A Streamlit learning demo for exploring synthetic academic data, visualizing patterns, evaluating a Random Forest classifier, and trying example predictions.
- Interactive attendance and outcome filters
- KPI cards and outcome/score charts
- Feature relationship scatter plots and correlation heatmap
- Train/test split, accuracy, confusion matrix, and feature importance
- Interactive prediction form with class probabilities
The app generates synthetic demo data. It does not use real student records, and model results should not be used to make real educational decisions.
python -m venv .venv
# Windows: .venv\Scripts\activate
# macOS/Linux: source .venv/bin/activate
pip install -r requirements.txt
streamlit run app.py- Create a new public GitHub repository named
student-performance-analytics. - Upload
app.py,requirements.txt, andREADME.md(or push this folder with Git). - Open https://share.streamlit.io/ and sign in with GitHub.
- Choose the repository, branch
main, and main file pathapp.py, then deploy. - Copy the real repository and app URLs into your presentation/report.
No GitHub or Streamlit deployment URLs are included here because publishing must happen from an authenticated account; never use a guessed URL.