saurav997/Algerian_Forest_Fires

# Algerian Forest Fires Prediction: An End-to-End Prediction model ## Project Overview The Algerian Forest Fires Prediction project aims to predict the Fire Weather Index (FWI), an indicator of potential fire intensity, using meteorological data. This application provides a user-friendly interface for predicting FWI values based on input parameters such as temperature, relative humidity, wind speed, and other relevant factors. The project employs a LassoCV regression model for its predictions, with features carefully selected to optimize model performance. ## Dataset Details The dataset used in this project is the Algerian Forest Fires dataset, which includes data collected from two regions in Algeria, Bejaia and Sidi Bel-Abbes, during the period from June to September 2012. The dataset consists of several meteorological factors that influence forest fires. The features used in the dataset are: - **Temperature (°C)**: The temperature at noon (in Celsius degrees). - **Relative Humidity (%)**: The relative humidity (in percentage). - **Wind Speed (km/h)**: The wind speed (in kilometers per hour). - **Rain (mm)**: The total daily rain (in millimeters). - **Fine Fuel Moisture Code (FFMC)**: An index from the Fire Weather Index (FWI) system indicating the moisture content of surface litter and fine fuels. - **Duff Moisture Code (DMC)**: An index from the FWI system indicating the moisture content of decomposed organic material in the upper soil layer. - **Initial Spread Index (ISI)**: An index that combines the effects of wind and the FFMC to predict the rate of fire spread. - **Region**: Categorical variable indicating the region of data collection (0 for Bejaia and 1 for Sidi Bel-Abbes). - **Classes**: Binary variable indicating the occurrence of a fire (0 for no fire and 1 for fire). ## Methodology ### Data Preprocessing The dataset underwent several preprocessing steps to ensure its suitability for the predictive model: 1. **Feature Selection**: Initially, al …