the-bipu/algerian-fire-prediction

Machine Learning web application for predicting the Fire Weather Index (FWI) using the Algerian Forest Fires dataset with Flask and Scikit-learn. # 🔥 Algerian Forest Fire Prediction A Machine Learning web application that predicts the Fire Weather Index (FWI) using the Algerian Forest Fires dataset. The project demonstrates an end-to-end ML workflow including data preprocessing, exploratory data analysis, model training, evaluation, and deployment using Flask. ## 📌 Project Overview This project leverages weather and environmental features to predict the Fire Weather Index (FWI), which helps estimate the likelihood and intensity of forest fires. Multiple regression algorithms were explored, including: - Linear Regression - Ridge Regression - Lasso Regression - ElasticNet Regression After comparing model performance, the best-performing regression model was integrated into a Flask web application for real-time predictions. ## 🚀 Features - Data cleaning and preprocessing - Exploratory Data Analysis (EDA) - Feature engineering - Model training and evaluation - Regression model comparison - Interactive Flask web application - Production-ready deployment setup ## 📊 Dataset The project uses the **Algerian Forest Fires Dataset**, which contains meteorological observations collected from two regions in Algeria during the 2012 fire season. ### Input Features - Temperature - Relative Humidity (RH) - Wind Speed (Ws) - Rain - FFMC - DMC - ISI - Classes - Region ### Target - Fire Weather Index (FWI) ## 🛠️ Tech Stack - Python - Flask - Pandas - NumPy - Scikit-learn - Matplotlib - Seaborn - HTML/CSS - Jupyter Notebook ## 📁 Project Structure ``` ├── application.py ├── models/ ├── notebooks/ ├── templates/ ├── static/ ├── requirements.txt ├── README.md └── artifacts/ ``` ## ⚙️ Installation Clone the repository: ```bash git clone github.com ``` Navigate to the project directory: ```bash cd algerian-fire-prediction ``` Create a virtual environment: ```bash python -m venv venv ``` Activate the environment: **Windows** ```bash venv\Scripts\activate ``` **Lin …