This project visualizes medical examination data with pandas, seaborn, and matplotlib. The analysis explores the relationship between cardiovascular disease, body measurements, blood markers, and lifestyle factors.
This is a strong health-data analytics project because it connects clinical risk factors with reproducible Python analysis. The work demonstrates data cleaning, BMI-based feature engineering, categorical normalization, exploratory visualization, and correlation analysis.
The most valuable portfolio angle is not just that charts were produced, but that the workflow shows how raw examination records can be transformed into interpretable evidence for cardiovascular risk review.
- Loaded
medical_examination.csvwith pandas. - Created an
overweightindicator from BMI. - Normalized
cholesterolandglucso0consistently represents a healthier result and1represents elevated risk. - Reshaped categorical health indicators into long format for grouped comparison.
- Cleaned implausible blood-pressure, height, and weight records before correlation analysis.
- Generated a masked correlation heatmap to reduce redundant visual noise.
This visualization compares counts for cholesterol, glucose, smoking, alcohol intake, physical activity, and overweight status across patients with and without cardiovascular disease.
The heatmap shows relationships among cleaned medical measurements and risk indicators. The masked upper triangle keeps the chart readable while preserving the major correlation patterns.
- Python data analysis
- pandas transformation and cleaning
- seaborn categorical plots
- matplotlib figure export
- health-data interpretation
- reproducible analytics workflow
medical_data_visualizer.py: analysis and plotting functionsmedical_examination.csv: source dataexamples/Figure_1.png: categorical plot referenceexamples/Figure_2.png: heatmap referencetest_module.py: validation tests

