Data Science and ML Tutorials

A collection of tutorials covering data manipulation with Pandas and modern AI techniques like object detection and image segmentation.

Tutorials

1. Pandas Tutorial - I

This tutorial covers essential Pandas techniques for data extraction, preprocessing, and feature engineering using real-world data from the York Open Data API.

• Key Topics:
  • API Data Extraction
  • Data Cleaning & Preprocessing
  • Categorical Encoding
  • Time-series Analysis & Fiscal Year Mapping
  • Performance Optimization (Vectorization vs Apply)
• Links:
  • View on GitHub
  • 

---

2. Lion Identification (PhD Research)

A deep dive into advanced computer vision techniques for identifying and segmenting lions in natural environments.

• Key Topics:
  • Multi-modal models (Florence-2)
  • Image Segmentation (Segment Anything Model 2 - SAM-2)
  • Object Detection (OD)
  • Visualizing Masks, Points, and Bounding Boxes
• Links:
  • View on GitHub
  • 

Getting Started

To run these notebooks locally, ensure you have the following installed:

• Python 3.8+
• Jupyter Notebook or JupyterLab
• Pandas, NumPy, Matplotlib
• Transformers (for the Lion Identification notebook)

Alternatively, you can open them directly in Google Colab using the badges above.