🌌 Celestial Object Classification 🚀

This project aims to develop a classification model that accurately identifies celestial objects—specifically stars, galaxies, and quasars—based on their spectral characteristics. Using a dataset of 100,000 observations from the Sloan Digital Sky Survey (SDSS), the model is trained to differentiate between these celestial objects, ensuring high accuracy and generalization for new, unseen data.

🔭 Data Source

Sloan Digital Sky Survey (SDSS) – A comprehensive survey of space, providing detailed imaging and spectroscopic data of celestial objects.

📊 Dataset Description

• Total Observations: 100,000
• Features: Spectral characteristics of celestial objects
• Classes:
  • ⭐ Stars
  • 🌌 Galaxies
  • 💫 Quasars

🏆 Classification Models Used

This project explores multiple classifiers to achieve the best results:

• Random Forest Classifier 🌲
• Support Vector Machine (SVM) 📈
• K-Nearest Neighbors (KNN) 📍
• Gradient Boosting Machines (GBM) ⚡
• Neural Networks (MLP) 🧠

🚀 Getting Started

1️⃣ Clone the Repository

git clone https://github.com/yourusername/celestial-object-classification.git

2️⃣ Install Dependencies

pip install -r requirements.txt

3️⃣ Run the Notebook

jupyter notebook notebooks/01_data_exploration.ipynb

📊 Applications

🔹 Astrophysics Research – Improve classification of celestial objects in space. 🔹 Automated Space Observation – Help telescopes identify objects in real-time. 🔹 Machine Learning in Astronomy – Leverage AI for space discovery!

💡 Unravel the mysteries of the universe with data! ✨🚀