harshsinha-12/Algerian_Fire_EndtoEndPrediction

Flask App live link Project Overview This project involves deploying machine learning models to predict fire weather indices in Algeria. It includes two versions: a Flask application and a Streamlit application, each utilizing a Ridge regression model trained on the Algerian forest fire dataset. Users can input weather and land conditions to receive fire weather index predictions. Live Application Links • Flask App: algerian-fire-endtoendpredi… • Streamlit App: algerianfire.streamlit.app • Flask App: Uses app.py for its operation. • Streamlit App: Operates through main.py. Directory Structure • Models/ • ridge.pkl - Serialized Ridge regression model. • scaler.pkl - Serialized standard scaler for feature normalization. • Notebooks/ • 26.1-AlgerianFireClean.ipynb - Jupyter notebook for data cleaning. • 26.2-ModelTraining.ipynb - Jupyter notebook for model training. • templates/ • home.html - HTML template for displaying predictions. • index.html - Initial landing page template. • application.py - Flask application script that defines routes and server logic. • README.md - Documentation providing project setup and usage details. • requirements.txt - List of dependencies required for the project. Flask Web Application The Flask application provides a simple interface for entering weather and vegetation parameters, processed by a pre-trained Ridge regression model to predict the fire weather index. Installation and Execution 1. Install required Python packages: pip install -r requirements.txt 2. Start the Flask application: python application.py The server will run on localhost, accessible via localhost. Using the Web Application • Navigate to localhost to access the input form. • Input the required parameters: • Temperature (°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 severity …