📊 Comprehensive Data Science & AI Portfolio

This repository houses a collection of projects and coursework assignments developed as part of the Computer Engineering curriculum at the University of Tehran. The implementations trace the complete data pipeline—from foundational applied data science and big data processing to advanced deep learning and large language model fine-tuning.

Contributors

Shahab Sherafat
Sepanta Ghonoodi
Mahdi Yari

📁 Repository Structure

The repository is organized into distinct Computer Assignment (CA) modules, each focusing on a specific domain within the data science and artificial intelligence landscape:

• CA0-Applied-Data-Science Foundational data analysis, data cleaning, exploratory data analysis (EDA), and basic statistical modeling.
• CA1-Tableau-Computational-Sampling Interactive data visualization techniques utilizing Tableau, alongside computational sampling methods and probability distributions.
• CA2-Big-Data Techniques, concepts, and frameworks necessary for handling, processing, and analyzing large-scale datasets efficiently.
• CA3-MachineLearning Implementation and evaluation of classical machine learning algorithms. This module covers supervised paradigms (classification/regression) and unsupervised learning (clustering/dimensionality reduction).
• CA4-DeepLearning Exploration of neural network architectures, training methodologies, and deep learning applications for complex pattern recognition tasks.
• CA5-NLP-LLM-Vision Advanced, state-of-the-art applications. This folder includes tasks on Natural Language Processing (semantic search), Large Language Model adaptation (In-Context Learning and LoRA fine-tuning), and Computer Vision (unsupervised image segmentation).

Note: Each individual directory contains its own dedicated README and documentation detailing the specific methodologies, datasets, and execution instructions for that respective assignment.