The original dataset comes from the Student Alcohol Consumption dataset on Kaggle. Source: https://www.kaggle.com/datasets/uciml/student-alcohol-consumption
The Jupyter notebeook (StudentPerformanceAnalytics.ipynb) uses classifcation algorithms such as naive bayes, random forest and decision trees to reveal the correlation of different attributes hypothesized to affect student academic performance. Then two plots were made to visualize these correlations.
The Python dashboard (SPADashboard.py) displays further interesting data visualizations in an interactive dashboard that allows all visualizations to be adjusted based on selected gender.