Abstract

In the world of medicine, drug classification holds immense importance as it helps determine the most suitable drugs for patients based on their unique characteristics and medical history. The dataset containing various features plays a vital role in assessing which drugs are best suited for individuals. This process is known as multi-class drug classification, where drugs are categorized into different classes based on their specific uses and therapeutic effects. Traditionally, drug classification has been carried out through manual or rule-based approaches, where physicians and medical experts rely on their knowledge and experience to prescribe drugs based on patient attributes. However, this method can be time-consuming and may not be efficient when dealing with a large number of drugs and patients. That's where machine learning comes in to revolutionize the process. Machine learning models are capable of analyzing vast amounts of data, learning complex patterns, and making predictions in a more automated and effective manner. The main objective of this project is to develop a machine learning model that accurately classifies drugs into multiple classes using specific features like Age, Sex, Blood Pressure (BP), Cholesterol level, and the Sodium to Potassium ratio. The target variable, in this case, is the "Drug," representing the name or class of the drug. Additionally, this project also involves exploratory data analytics, which focuses on data visualization and representation techniques. By exploring and visualizing the data, we can gain valuable insights and better understand the relationships between the features and drug classes, which will ultimately aid in building a robust and accurate machine learning model for drug classification.

Description