AI Lab

A hands-on AI, machine learning, deep learning, computer vision, and data analytics lab built for learners who want practical projects, readable code, and a clear roadmap.

AI Lab is an educational repository with 100+ practical Python projects across the modern AI stack. It started as a collection of learning exercises and has been organized into a GitHub-ready lab with reusable utilities, tests, docs, and topic-based project folders.

The goal is simple: help learners move from Python basics to applied AI projects without losing the thread.

What You Will Learn

• Build machine learning models for classification, regression, clustering, recommendation, and reinforcement learning.
• Train and run computer vision projects for face detection, OCR, gesture recognition, object detection, and leaf disease detection.
• Explore deep learning concepts including CNNs, RNNs, LSTMs, transfer learning, YOLO, and model interpretability.
• Practice data analytics with statistics, visualization, CSV workflows, and database examples.
• Learn how to structure AI code with configuration, validation, reusable helpers, and tests.

Repository Structure

ai-lab/
├── ai_master/              # Reusable Python package: config, core utilities, helpers
├── src/                    # Topic-based learning modules and original project code
│   ├── python_basics/
│   ├── data_analytics/
│   ├── machine_learning/
│   ├── deep_learning/
│   └── computer_vision/
├── projects/               # Larger applied projects
│   ├── agriculture/
│   └── chatbot/
├── docs/                   # Learning paths, project index, roadmap, and publishing notes
├── requirements/           # Split dependency sets for base, dev, notebook, and optional use
├── tests/                  # Pytest suite for the reusable package
└── datasets/               # Local/sample data folder, ignored by default for GitHub safety

Featured Areas

Area	Example Topics
Python Basics	Functions, file handling, scripts, notebooks
Data Analytics	Statistics, visualization, Power Query, MongoDB
Machine Learning	Titanic survival, breast cancer detection, salary prediction, clustering
Deep Learning	CNNs, LSTMs, transfer learning, YOLO, model interpretability
Computer Vision	Face detection, face recognition, OCR, hand gestures, leaf disease
Applied Projects	Agriculture disease detection, Dialogflow chatbot assets

See docs/PROJECT_INDEX.md for the full project map.

Quick Start

git clone https://github.com/Tuhin-SnapD/ai-lab.git
cd ai-lab

python -m venv .venv
.venv\Scripts\activate

pip install -r requirements/base.txt
pip install -e .

pytest

On macOS/Linux, activate the environment with:

source .venv/bin/activate

For the longer setup guide, read QUICKSTART.md.

Learning Paths

Start with the path that fits your level:

• Beginner: Python basics, data loading, plotting, and small ML models.
• Intermediate: classification, regression, clustering, evaluation, and feature workflows.
• Advanced: computer vision, deep learning, transfer learning, and applied projects.

Follow the detailed guide in docs/LEARNING_PATH.md.

How To Use This Repo

1. Pick a topic from docs/PROJECT_INDEX.md.
2. Install only the dependency group you need.
3. Run the smallest script first.
4. Read the nearby code and improve one thing: metrics, logging, plots, model accuracy, or documentation.
5. Share what you learned in an issue, discussion, pull request, or your own project notes.

GitHub Publishing Notes

This repo intentionally ignores large datasets, trained models, binary media, local environments, notebooks with outputs, and generated artifacts. Keep the public repository fast to clone and easy to review.

Use docs/GITHUB_READY.md before your first public push.

Contributing

Contributions are welcome. Good educational contributions include:

• clearer explanations,
• beginner-friendly notebooks,
• project READMEs,
• better evaluation metrics,
• cleaned scripts,
• reproducible datasets,
• tests for shared utilities.

Read CONTRIBUTING.md before opening a pull request.

Roadmap

The public roadmap is in docs/ROADMAP.md. The main priorities are project-level READMEs, lightweight notebooks, better dataset instructions, and more reproducible training/evaluation workflows.

Credits

Original learning material and project collection by Pantech Solutions. This repository is organized as an educational AI lab for learners, builders, and contributors.

License

This project is licensed under the MIT License. See LICENSE.