This project focuses on predicting the fire weather index for two regions in Algeria. By leveraging machine learning algorithms and analyzing environmental data, the aim is to enhance preparedness and minimize damage caused by wildfires. The project involves data preprocessing, feature selection, and the implementation of supervised learning models to accurately forecast the fire weather index.

This project utilizes machine learning techniques to predict diabetes. It involves preprocessing the dataset, including handling missing values and feature engineering. The logistic regression model is trained, tested, and tuned using GridSearchCV. The model's performance is evaluated using metrics such as accuracy, precision, recall, and F1 score. The project is deployed using Streamlit, providing users with a live demo and access to the code on GitHub.

This project utilizes machine learning techniques to predict diabetes. It involves preprocessing the dataset, including handling missing values and feature engineering. The logistic regression model is trained, tested, and tuned using GridSearchCV. The model's performance is evaluated using metrics such as accuracy, precision, recall, and F1 score. The project is deployed using Streamlit, providing users with a live demo and access to the code on GitHub.