🌲 UN SDG Goal 15 – Mountain Forest Cover

Comprehensive Exploratory Data Analysis & Preprocessing Pipeline

A Python-based end-to-end Exploratory Data Analysis (EDA) project aligned with UN Sustainable Development Goal 15 – Life on Land, focusing on Mountain Forest Cover and Degraded Mountain Land.

The project delivers a complete EDA + preprocessing pipeline that transforms raw SDG data into clean, insightful, and machine-learning-ready outputs.

---

🎯 Project Objective

• Analyze mountain land degradation trends
• Identify geographic, temporal, and environmental patterns
• Generate high-quality visual insights
• Prepare clean and ML-ready datasets
• Ensure reproducibility using requirements.txt

---

🚀 Key Features

📊 Exploratory Data Analysis

• Dataset structure & feature inspection
• Numerical vs categorical feature separation
• Summary statistics and profiling

🔬 Data Quality Analysis

• Missing value detection
• Duplicate identification
• Outlier detection using IQR method

🧹 Data Cleaning

• Duplicate removal
• Median imputation (numerical)
• Mode imputation (categorical)

📈 Statistical & Pattern Analysis

• Most affected geographic regions
• Degradation by bioclimatic belt
• Land cover distribution
• Temporal trend analysis
• Correlation analysis

📊 Automated Visualizations

• Geographic degradation ranking
• Bioclimatic & land cover plots
• Time-series trends
• Distribution & correlation plots

🤖 Machine Learning Preparation

• Label encoding of categorical features
• Feature scaling using StandardScaler
• Dimensionality reduction with PCA
• ML-ready dataset export

📋 Report Generation

• Auto-generated EDA report
• Cleaned dataset export
• ML-ready dataset export

---

🛠️ Tech Stack

• Python 3.9+
• Pandas – Data manipulation
• NumPy – Numerical computation
• Matplotlib & Seaborn – Visualization
• SciPy – Statistical analysis
• Scikit-learn – Scaling, Encoding & PCA
• OpenPyXL – Excel file handling

---

📁 Project Structure

SDG_ExploratoryDataAnalysis/
│
├── data/
│   └── Goal15.xlsx
│
├── outputs/
│   ├── plots/
│   │   ├── geographic_analysis.png
│   │   ├── bioclimatic_landcover.png
│   │   ├── temporal_trends.png
│   │   └── comprehensive_analysis.png
│   │
│   └── results/
│       ├── cleaned_data.csv
│       ├── ml_ready_data.csv
│       └── eda_report.txt
│
├── main.py
├── requirements.txt
└── README.md

---

⚙️ System Requirements

• Python 3.9 or higher
• pip package manager

---

📦 Dependencies

All required libraries are listed in requirements.txt.

Install them using:

pip install -r requirements.txt

This ensures environment consistency and reproducibility.

---

⚡ Quick Start

1️⃣ Clone the Repository

git clone https://github.com/AnkeshGG/SDG_ExploratoryDataAnalysis.git
cd SDG_ExploratoryDataAnalysis

2️⃣ Install Dependencies

pip install -r requirements.txt

3️⃣ Run the EDA Pipeline

python main.py

---

📦 Generated Outputs

📊 Visualizations

• Geographic degradation ranking
• Bioclimatic belt & land cover analysis
• Temporal degradation trends
• Correlation and distribution plots

📁 Datasets

• cleaned_data.csv – Cleaned dataset
• ml_ready_data.csv – Encoded & scaled dataset

📄 Report

• eda_report.txt – Detailed EDA summary and insights

---

📌 Dataset Description

UN SDG Goal: 15 – Life on Land
Indicator: 15.4 – Mountain land degradation

Key Attributes:

• Geographic Area
• Time Period
• Bioclimatic Belt
• Land Cover Type
• Degraded Area (sq. km)

Note: If the dataset file is missing, the pipeline automatically generates realistic sample data for demonstration purposes.

---

💡 Use Cases

• Environmental & sustainability analysis
• Climate and forest degradation studies
• Machine learning feature engineering
• Academic mini/major projects

---

🧪 Future Enhancements

• Interactive dashboards (Streamlit / Plotly)
• Degradation trend forecasting
• Region-wise clustering
• Integration with live UN SDG APIs
• Predictive ML models

---

🤝 Contributing

Contributions are welcome!

1. Fork the repository
2. Create a feature branch
3. Commit your changes
4. Push to your fork
5. Submit a pull request

---

📄 License

This project is licensed under the MIT License.

---

👨‍💻 Author

Ankesh Kumar
CSE Undergraduate | Data & ML Enthusiast

• 🌐 GitHub: AnkeshGG
• 💼 LinkedIn: Ankesh Kumar
• 🔗 Medium: ankeshGG

---

🌍 Final Note

This project demonstrates how structured EDA and preprocessing pipelines can convert raw sustainability data into insightful, reproducible, and ML-ready outputs, contributing toward UN SDG Goal 15 – Life on Land.

⭐ If you found this useful, consider starring the repository.