TITLE :Rock vs Mine Prediction The motivation behind this project stems from the desire to apply machine learning to solve real-world classification problems. Sonar data is often used in underwater object detection, where classifying objects correctly (such as distinguishing between mines and rocks) is crucial. Machine learning - helps automate this process with a high level of accuracy. This project was built to demonstrate how data processing, logistic regression, and evaluation metrics like accuracy can be applied to a real dataset. It serves as a practical example for exploring how supervised learning models can classify objects based on input features—in this case, the sonar data. The project solves the problem of classifying sonar signals into two categories: mines or rocks. In a real-world scenario, this could be used for underwater exploration or Military applications, where distinguishing between DANGEROUS objects like mines and harmless objects like rocks is critical. Through this project, I learned how to: Load and explore datasets using Pandas. Preprocess the data by splitting it into training and testing sets. Apply Logistic Regression as a classification algorithm. Evaluate model performance using metrics like accuracy_score. Understand the workflow of machine learning: data loading, model training, prediction, and evaluation.