developrishu-cell/forest-fire-fwi-prediction

End-to-end Machine Learning project using Ridge, Lasso, and ElasticNet Regression to predict the Fire Weather Index (FWI) from the Algerian Forest Fires dataset, with a Flask web application for real-time predictions. # Algerian Forest Fire Prediction using Machine Learning ## Overview This project is an end-to-end Machine Learning application that predicts the **Fire Weather Index (FWI)** using weather and environmental parameters from the Algerian Forest Fires Dataset. The project demonstrates the complete ML pipeline, including data preprocessing, exploratory data analysis, feature engineering, model training, model selection, and deployment through a Flask web application. --- ## Features - Data preprocessing and cleaning - Exploratory Data Analysis (EDA) - Feature Engineering - Model training using multiple regression algorithms - Ridge Regression - Lasso Regression - ElasticNet Regression - Model serialization using Pickle - Flask web application for predictions --- ## Dataset The project uses the **Algerian Forest Fires Dataset**, which contains meteorological and fire weather measurements collected from two regions of Algeria. Some of the important features include: - Temperature - Relative Humidity (RH) - Wind Speed (Ws) - Rain - FFMC - DMC - DC - ISI - Classes - Region Target Variable: - Fire Weather Index (FWI) --- ## Project Structure ``` Ridge,Lasso and ElasticNet/ │ ├── application.py # Flask application ├── requirements.txt # Project dependencies ├── README.md │ ├── data/ │ ├── Algerian_forest_fires_dataset_UPDATE.csv │ └── Algerian_forest_fires_dataset_Cleaned.csv │ ├── models/ │ ├── ridge.pkl │ └── scaler.pkl │ ├── notebooks/ │ ├── AlgerianForestFire.ipynb │ └── Model_training.ipynb │ └── templates/ ├── home.html └── index.html ``` --- ## Machine Learning Workflow 1. Data Collection 2. Data Cleaning 3. Exploratory Data Analysis 4. Feature Engineering 5. Feature Scaling 6. Model Training 7. Model Evaluation 8. Model Serialization 9. Flask Deployment --- ## Algorithms Used - Linear Regression - Ridge Regression - Lasso Regression - ElasticNet Regression Among these, the best-performing model is saved and …