Aadarsh-60/algerian-forest-fire-prediction

# Algerian Forest Fire Regression Model This project is a machine learning web application that predicts the Fire Weather Index (FWI) for Algerian forest fire data. It uses a trained Ridge Regression model and a Flask frontend where users can enter weather and fire index values to get a prediction. ## Project Overview Forest fires are strongly affected by weather conditions such as temperature, humidity, wind speed, and rainfall. This project uses the Algerian Forest Fires dataset to build a regression model that estimates the fire risk index from environmental features. The application includes: - Data cleaning and exploratory data analysis notebooks - Feature engineering and model training notebook - Trained Ridge Regression model saved as a pickle file - Standard scaler saved as a pickle file - Flask web application for real-time prediction ## Tech Stack - Python - Flask - NumPy - Pandas - Scikit-learn - HTML and CSS ## Project Structure ```text ALGERIAN_FOREST_FIRE_REGRESSION_MODEL/ ├── app.py ├── requirement.txt ├── README.md ├── MODELS/ │ ├── ridge.pkl │ └── scaler.pkl ├── NOTEBOOK/ │ ├── Algerian_forest_fires_dataset_UPDATE.csv │ ├── Algerian_forest_fires_cleaned_dataset.csv │ ├── 2.0-EDA And FE Algerian Forest Fires.ipynb │ └── 3.0-Model Training.ipynb └── templates/ ├── home.html └── index.html ``` ## Input Features The model takes the following input values: - Temperature - RH: Relative Humidity - Ws: Wind Speed - Rain - FFMC: Fine Fuel Moisture Code - DMC: Duff Moisture Code - ISI: Initial Spread Index - Classes: Fire or not fire class value - Region: Region value ## Output The application predicts the Fire Weather Index (FWI), which indicates forest fire risk based on the entered conditions. ## Installation 1. Clone the repository: ```bash git clone github.com cd algerian-forest-fire-regression ``` 2. Create and activate a virtual environment: ```bash python -m venv …