This is a Algerian_forest_fires Prediction Using Linear, Ridge, Lasso Regression Models
# Algerian Forest Fires Prediction System
A complete end-to-end machine learning project with Flask web application and AWS deployment for predicting Fire Weather Index (FWI) using environmental and meteorological data.
## 📋 Project Overview
This project predicts the **Fire Weather Index (FWI)** using environmental and meteorological data from two Algerian regions:
- **Bejaia Region**
- **Sidi-Bel Abbes Regions**
The system includes:
- **Data Analysis**: Jupyter notebook with comprehensive EDA using ydata-profiling
- **Machine Learning**: Multiple regression models (Linear, Ridge, Lasso, ElasticNet)
- **Web Application**: Flask-based REST API with HTML interface
- **Cloud Deployment**: AWS Elastic Beanstalk with CodePipeline CI/CD
- **Interactive Dashboard**: Prediction interface and EDA report viewer
## 📊 Dataset
### Features
**Input Features (11):**
- `day` - Day of the month
- `month` - Month of the year
- `year` - Year of observation
- `Temperature` - Temperature in °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
**Target Features:**
- `FWI` - Fire Weather Index (for regression)
- `Classes` - Fire/Not Fire classification (for classification)
### Files
- `Algerian_forest_fires_dataset.csv` - Original raw dataset
- `Algerian_forest_fires_cleaned_dataset.csv` - Cleaned and processed dataset
## 🔧 Technologies & Libraries
**Core Data Science:**
- **Python 3.10**
- **pandas** - Data manipulation and analysis
- **numpy** - Numerical computations
- **scikit-learn** - Machine learning algorithms
- **matplotlib** - Data visualization
- **seaborn** - Statistical visualization
- **plotly** - Interactive visualizations
- **ydata-profiling** - Automated EDA reports
- **ipykernel** - Jupyter kernel support
- **ipywidgets** - Interactive widgets
**Web Framework & Deployment:**
- **Flask** - …