data-professional-taiyabkhan/algerian_fire_forest_ML

# Algerian Forest Fire — FWI Prediction (ML Web App) A machine learning web application that predicts the **Fire Weather Index (FWI)** for Algerian forest regions using a Ridge Regression model. Built with Flask and deployed on Render. --- ## Project Overview Forest fires are a critical environmental hazard in Algeria. This project uses the **Algerian Forest Fires Dataset** to train a regression model that predicts FWI — a key indicator of fire danger — based on meteorological and fire behavior features. The trained model is served via a Flask web application with a clean UI for real-time predictions. --- ## 🧠 ML Pipeline - **Dataset:** Algerian Forest Fires Dataset (Bejaia & Sidi Bel-abbes regions) - **Target Variable:** FWI (Fire Weather Index) - **Algorithm:** Ridge Regression - **Preprocessing:** StandardScaler for feature normalization - **EDA:** Detailed exploratory analysis in `EDA.ipynb` ### Input Features | Feature | Description | |--------------|--------------------------------------| | Temperature | Temperature in °C | | RH | Relative Humidity (%) | | Ws | Wind Speed (km/h) | | Rain | Rainfall (mm) | | FFMC | Fine Fuel Moisture Code | | DMC | Duff Moisture Code | | ISI | Initial Spread Index | | Classes | Fire / Not Fire (encoded) | | Region | Bejaia (0) or Sidi Bel-abbes (1) | --- ## 🚀 Getting Started ### Prerequisites - Python 3.8+ - pip ### Installation ```bash git clone github.com cd algerian_fire_forest_ML pip install -r requirement.txt ``` ### Run Locally ```bash python app.py ``` Visit `localhost` in your browser. --- ## ☁️ Deployment This app is configured for **AWS Elastic Beanstalk** deployment via the `.ebextension …