The diabetes dataset is based on a study conducted in Arizona on Pima Indian females since 1965 National Institute of Diabetes and Digestive and Kidney Diseases. There is a set of 8 features available such as glucose concentration, Blood Pressure, age ete. The target of this project is to explore the relationships between the features and occurance of diabetes. Use various machine lerning models to arrive at the most accurate model to predict whether the subject is diabetic or non-diabetic.