Global Weather Forecasting and Anomaly Detection

Data science project using the Global Weather Repository dataset. It covers anomaly detection, feature importance, spatial mapping, and ensemble temperature forecasting.

What it includes

• Anomaly detection with Isolation Forest for extreme temperature and precipitation values
• Correlation analysis between air quality metrics and weather features
• Feature importance with Random Forest Regressor
• Interactive Folium map of temperatures across 200+ cities
• Ensemble forecasting with Linear Regression and Random Forest, evaluated with MAE

Stack

• Python
• Jupyter Notebook
• Pandas, NumPy
• Scikit-Learn
• Matplotlib, Seaborn, Folium

How to run

git clone https://github.com/agupta362/data-science.git
cd data-science
python -m venv venv

# Windows
.\venv\Scripts\activate

# Mac/Linux
source venv/bin/activate

pip install -r requirements.txt

Open Weather-Analysis.ipynb in VS Code or Jupyter and run the cells in order.

To view the map, open global_weather_map.html in a browser after it is generated.