khajuriakrishna18-maker/algerian-forest-fires-fwi-prediction

ML project predicting the Fire Weather Index (FWI) of the Algerian Forest Fires dataset using Ridge Regression, deployed with Flask. # Algerian Forest Fires — Fire Weather Index (FWI) Prediction A machine learning project that predicts the **Fire Weather Index (FWI)** of the Algerian Forest Fires dataset using **Ridge Regression**. The project covers the full workflow — exploratory data analysis, data cleaning, feature selection, model training with regularization, and deployment as a **Flask** web application. ## Overview The Algerian Forest Fires dataset contains observations from two regions of Algeria (Bejaia and Sidi Bel-abbes) between June and September 2012. The goal of this project is to predict the Fire Weather Index (FWI) — a numeric rating of fire intensity — from weather and fuel-moisture measurements. ## Project Structure ``` algerian-forest-fires-fwi-prediction/ ├── application.py # Flask web app that serves the trained model ├── requirements.txt # Python dependencies ├── data/ │ ├── Algerian_forest_fires_dataset_UPDATE.csv # Raw dataset │ └── Algerian_forest_fires_cleaned_dataset.csv # Cleaned dataset ├── models/ │ ├── ridge.pkl # Trained Ridge Regression model │ └── scaler.pkl # Fitted StandardScaler ├── notebooks/ │ ├── 1_eda_and_data_cleaning.ipynb # EDA + data preprocessing │ └── 2_model_training.ipynb # Feature selection + model training └── templates/ ├── index.html └── home.html ``` ## Features Used The model takes the following inputs: | 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 | …