pcpetty/Algerian-Forest-Fires-Regression-Analysis

This repository contains a comprehensive analysis of forest fire data from Algeria, focusing on predicting fire intensity using multiple linear regression. The project aims to identify key environmental factors contributing to forest fires and develop a predictive model to support effective prevention strategies. # Algerian Forest Fires - Regression Analysis ## Problem Statement Forest fires are a major environmental concern, especially in regions with dense vegetation. Understanding the factors contributing to these fires is crucial for prevention and mitigation. This project aims to use historical data to build a predictive model for forest fire intensity based on multiple environmental variables. ## Dataset - **Source:** Abid, (2019). Algerian Forest Fires [UCI Machine Learning Repository]. doi.org - **Description:** The dataset contains various environmental attributes such as temperature, humidity, wind speed, and rainfall, recorded over multiple years. ## Key Features - **Temperature:** Recorded in degrees Celsius. - **Humidity:** Relative humidity percentage. - **Wind Speed:** Speed of the wind in km/h. - **Rainfall:** Precipitation in mm. ## Methodology 1. **Data Cleaning:** Handling missing values, outliers, and transforming variables. 2. **Exploratory Data Analysis (EDA):** Visualization and statistical analysis to identify trends and patterns. 3. **Feature Engineering:** Creating new features to improve model performance. 4. **Model Building:** Implementing multiple linear regression to predict forest fire intensity. 5. **Model Evaluation:** Using metrics like R-squared, RMSE, and MAE to evaluate the model's performance. ## Technologies Used - **Python:** For data processing and analysis. - **Pandas & NumPy:** For data manipulation. - **Matplotlib & Seaborn:** For data visualization. - **Scikit-learn:** For building and evaluating the regression model. ## Results The multiple linear regression model achieved an R-squared score of `0.651`, indicating the proportion of variance in the dependent variable explained by the independent variables. ## License This project is licensed under the MIT License - see the LICENSE file for details. ## How to Run 1. **Clone the repository:** ```bash git clone github.com …