SurajKhodade15/algerian-fire-forest-eda-ml

algerian-fire-forest-eda-ml # 🔥 Algerian Forest Fire Prediction - EDA & Machine Learning ## 📋 Project Overview This project analyzes and predicts forest fires in Algeria using machine learning techniques. The dataset includes 244 instances from two regions of Algeria (Bejaia and Sidi Bel-abbes) covering the period from June 2012 to September 2012. ### 🎯 Objectives - **Data Cleaning & Preprocessing**: Handle missing values, encode categorical variables, and prepare data for analysis - **Exploratory Data Analysis (EDA)**: Understand patterns, correlations, and distributions in forest fire data - **Feature Engineering**: Select relevant features and handle multicollinearity - **Machine Learning**: Build and evaluate regression models to predict Fire Weather Index (FWI) - **Model Comparison**: Compare Linear, Lasso, Ridge, and ElasticNet regression models ## 📊 Dataset Information ### Dataset Details - **Total Instances**: 244 (122 per region) - **Features**: 11 attributes + 1 output attribute - **Time Period**: June 2012 - September 2012 - **Regions**: - Bejaia (Northeast Algeria) - Region 0 - Sidi Bel-abbes (Northwest Algeria) - Region 1 - **Target Classes**: Fire (138 instances) and Not Fire (106 instances) ### Features Description | Feature | Description | Range | |---------|-------------|-------| | **Date** | Day/Month/Year | June-September 2012 | | **Temperature** | Noon temperature (°C) | 22-42 | | **RH** | Relative Humidity (%) | 21-90 | | **Ws** | Wind Speed (km/h) | 6-29 | | **Rain** | Total daily rainfall (mm) | 0-16.8 | | **FFMC** | Fine Fuel Moisture Code | 28.6-92.5 | | **DMC** | Duff Moisture Code | 1.1-65.9 | | **DC** | Drought Code | 7-220.4 | | **ISI** | Initial Spread Index | 0-18.5 | | **BUI** | Buildup Index | 1.1-68 | | **FWI** | Fire Weather Index | 0-31.1 | | **Classes** | Fire occurrence (Fire/Not Fire) | Binary | ## 🔄 Project Workflow ### Phase 1: Data Cleaning & Exploratory Data Analysis **Key Steps:** 1. **Data Loading & Initial Inspection** - Load dataset …