Water quality assessment is crucial for public health, particularly in India, where access to safe drinking water is often compromised. Traditional methods of water testing are time-consuming and costly. This study explores the use of machine learning (ML) techniques to assess water potability across Indian regions, aiming for a more efficient and scalable solution. By analyzing datasets containing water quality parameters like pH, turbidity, microbial contamination, and chemical pollutants, ML models such as Random Forest, Support Vector Machines, and K-Nearest Neighbor are trained to predict whether water is potable or non-potable. The study also incorporates geographic information systems (GIS) to identify high-risk areas prone to contamination. The machine learning-driven approach offers faster, cost-effective, and accurate water quality assessments, facilitating real-time monitoring and alerts. This can aid policymakers, environmental agencies, and communities in improving water management practices and ensuring access to safe drinking water.