sumeet-016/Algerian-Forest-Fire

# 🔥 Algerian Forest Fire Weather Index (FWI) Prediction An end-to-end **machine learning project** designed to predict the **Fire Weather Index (FWI)** using meteorological and fuel moisture data. The project covers **data analysis, model development, pipeline creation, and deployment** through a Streamlit web application. --- ## 📌 Project Objective The Fire Weather Index (FWI) is a standard indicator used worldwide to estimate forest fire risk. This project aims to: - Analyze historical forest fire data from Algeria - Build a reliable machine learning regression model - Deploy the trained model using a Streamlit web interface - Classify fire danger levels for practical interpretation --- ## 🗂️ Project Structure ``` ├── app.py ├── requirements.txt ├── linear_regression_pipeline.joblib ├── Algerian_forest_fires_dataset.csv ├── Algerian_forest_fires_update_dataset.csv ├── EDA Notebook.ipynb ├── Model Training.ipynb ├── dataset-cover.jpg └── README.md ``` --- ## 📊 Dataset Description The dataset consists of daily weather and fuel moisture observations collected from two regions in Algeria: - **Bejaia** - **Sidi-Bel Abbes** ### Features | Feature | Description | |-------|-------------| | Temperature | Daily temperature (°C) | | RH | Relative Humidity (%) | | Ws | Wind Speed (km/h) | | Rain | Rainfall (mm) | | FFMC | Fine Fuel Moisture Code | | DMC | Duff Moisture Code | | DC | Drought Code | | ISI | Initial Spread Index | | BUI | Buildup Index | | Region | Bejaia (0), Sidi-Bel Abbes (1) | | FWI | Target Variable | --- ## 🔍 Exploratory Data Analysis Exploratory analysis was performed in `EDA Notebook.ipynb`, including: - Missing value analysis - Distribution and correlation analysis - Feature impact on Fire Weather Index - Region-wise comparison - Outlier detection --- ## 🤖 Model Development Model development was carried out in `Model Training.ipynb`: - Data preprocessing using Scikit-learn Pipelines - Feature scaling and transformation - Evaluation …