🤖 AI/ML Python Workspace

Exploring the core Python libraries used in AI & ML through practical examples, custom projects, and real datasets.

---

🎯 Objectives

• Learn how major Python libraries work under the hood
• Build hands-on projects and mini-experiments
• Understand usage in real-world datasets and model workflows
• Transition from beginner to deployment-ready AI/ML developer

---

🧪 Libraries Covered

Category	Libraries/Frameworks
Data Manipulation	NumPy, Pandas, OpenCV
Data Visualization	Matplotlib, Seaborn, Plotly
Machine Learning	Scikit-learn, XGBoost, LightGBM
Deep Learning	TensorFlow, Keras, PyTorch
NLP	NLTK, spaCy, Transformers (HuggingFace)
Model Deployment	Flask, Streamlit, FastAPI

---

🚀 Sample Projects

Project Name	Tech Stack	Status
Iris Classification	Scikit-learn, Matplotlib	✅ Done
House Price Prediction	Pandas, XGBoost, Seaborn	✅ Done
Sentiment Analysis (Tweets)	NLTK, WordCloud, Flask	🚧 Ongoing
Face Detection App	OpenCV, Streamlit	⏳ Planned

---

📌 Learning Sources

• 📘 Books: "Hands-On ML with Scikit-Learn, Keras & TensorFlow", "Deep Learning with PyTorch"
• 🌐 Courses: Coursera ML by Andrew Ng, Fast.ai
• 📁 Kaggle: Datasets, Notebooks, Competitions
• 🧠 Papers: arXiv, PapersWithCode

---

🛠️ Environment

OS: Ubuntu 22.04
Language: Python 3.10+
Tools: VS Code, Jupyter Notebook, Conda/venv
GPU Support: ✅ (NVIDIA CUDA)