This project involves the application of a Random Forest algorithm to the High-Resolution Floating Solar PV dataset. The objective was to understand and predict patterns related to energy generation and other key performance indicators within a floating solar PV installation.

This project explores the application of image classification and clustering techniques using R. The dataset includes various images categorized by their attributes. We employ Artificial Neural Networks (ANN) to classify images based on their features and assess model performance through accuracy metrics.

The code analyzes the Haberman dataset, which contains information on patients who underwent surgery for breast cancer. The dataset includes three features: age of the patient at the time of surgery, year of the operation, and the number of positive axillary nodes detected, along with a survival status indicating whether the patient survived 5 years or more after surgery. The primary goal is to predict the survival status of patients using a neural network model. After cleaning and normalizing the data, the model is trained and evaluated on its ability to accurately classify survival outcomes. The model's performance metrics, including accuracy and Mean Squared Error (MSE), provide insight into its predictive power. Despite the challenges inherent in the dataset, the neural network is used to approximate the survival chances of patients based on the available features.