This analysis uses a real-world health dataset to explore how different clinical and lifestyle factors influence diabetes risk. By examining variables such as BMI, fasting glucose, HbA1c, cholesterol, blood pressure, physical activity, smoking, and family history, we identify important patterns linked to diabetes. Through summary statistics, visualizations, group comparisons, and basic machine learning methods like clustering and KNN, the study highlights which factors differ most between high-risk and low-risk individuals. The results provide a clear, data-driven understanding of how metabolic and lifestyle indicators contribute to diabetes risk, helping support better health insights and decision-making.