chandank013/testForestFires

ML project using the Algerian Forest Fires Dataset to predict forest fire occurrences from meteorological data. # 🔥 Algerian Forest Fires Prediction ## 📘 Overview This project analyzes and predicts forest fire occurrences in Algeria using the **Algerian Forest Fires Dataset**. The dataset contains **244 instances** collected from two regions — **Bejaia (Northeast)** and **Sidi Bel-Abbes (Northwest)** — during **June to September 2012**. Each instance represents meteorological conditions used to classify whether a forest fire occurred (`fire`) or not (`not fire`). --- ## 📊 Dataset Information - **Total Instances:** 244 - **Regions:** Bejaia & Sidi Bel-Abbes - **Time Period:** June–September 2012 - **Attributes:** 11 input features + 1 output label - **Target Classes:** - `Fire` → 138 instances - `Not Fire` → 106 instances **Source:** UCI Machine Learning Repository – Algerian Forest Fires Dataset --- ## 🧠 Objective The goal of this project is to: - Analyze patterns in meteorological data related to fire occurrences. - Build machine learning models to **predict forest fires**. - Identify the most influential factors contributing to fires. --- ## ⚙️ Technologies Used - **Python** 🐍 - **Pandas**, **NumPy** – Data analysis - **Matplotlib**, **Seaborn** – Data visualization - **Scikit-learn** – Machine learning models - **Jupyter Notebook / Google Colab** – Development environment --- ## 🧩 Workflow 1. **Data Preprocessing** - Cleaning and handling missing values - Encoding categorical variables 2. **Exploratory Data Analysis (EDA)** - Visualizing temperature, humidity, wind speed, and other features 3. **Model Building** - Logistic Regression - Random Forest Classifier - Support Vector Machine (SVM) 4. **Model Evaluation** - Accuracy, Precision, Recall, F1-Score, ROC Curve --- ## 📈 Results - Models achieved high accuracy in predicting `fire` vs `not fire`. - Random Forest and SVM performed best on this dataset. - Key influencing features: **Temperature**, **Relative Humidity**, **Wind Speed**, **Rain**, and **DC/ISI indexes**. --- ## 🚀 Future Enhancements - Deploy the …