🧠 AI Programming Using Python – Workshop Repository

Instructor: Rasoul Ameri
Workshop Title: AI Programming Using Python
Focus Areas: Python for Machine Learning • Data Preprocessing • Model Development • Explainable AI (SHAP)

---

🎯 Overview

This repository contains the complete materials from the AI Programming Using Python workshop conducted at the
International Graduate School of Artificial Intelligence (YunTech).

The program introduces participants to the fundamentals of AI programming through a hands-on, application-oriented approach.
It builds essential skills in data analysis, machine learning model development, and model interpretability, forming the foundation for a professional career in AI and Data Science.

Learning Outcomes

• Configure and manage Python environments using Anaconda
• Utilize NumPy, Pandas, and Matplotlib for numerical computation and data visualization
• Perform data cleaning and preprocessing
• Implement core machine learning algorithms for classification and regression using scikit-learn
• Apply Explainable AI (XAI) techniques using SHAP to interpret model predictions

---

🗺️ Repository Structure for Machine learning via Explainability

The materials follow a progressive learning roadmap, designed to guide learners from basic programming toward advanced model interpretability and deployment.

Phase	Topic	Folder	Key Materials	Status
🧩 1	Environment Setup	1_Anaconda	Anaconda	✅
🐍 2	Python Foundations	2_Python Tutorial	Python Basics, Numpy, Pandas, MatPlotlib	✅
🧹 3	Data Cleaning & Preparation	Data Cleaning and Preparation	Data Cleaning and Preparation	✅
🔍 4	Classification vs Regression	4_Classification Vs Regression	Classification vs Regression [ppt]	✅
🤖 5	Supervised Learning Algorithms	5_Classification	Includes major classifiers such as Logistic Regression, KNN, SVM, Naive Bayes, Decision Tree, and Random Forest	✅
🧠 6	Explainable AI (XAI)	SHAP	SHAP	✅
⚙️ 7	Feature Engineering & Dimensionality Reduction	Coming Soon	(to be added)	⏳
🔧 8	Regression Algorithms	Coming Soon	(Linear, Polynomial, Ridge, Lasso)	⏳
🌐 9	Unsupervised Learning	Coming Soon	(K-Means, PCA, Hierarchical Clustering)	⏳
🚀 10	Deployment (MLOps)	Coming Soon	(Streamlit, Docker, CI/CD)	⏳
🔍 11	Advanced Explainable AI (LIME, DeepSHAP, ELI5)	Coming Soon	(to be added)	⏳

---

🤖 Module 5 – Classification Algorithms

This module covers the core supervised learning algorithms used in AI and Data Science projects.

Algorithm	Folder	Key Notebooks
Logistic Regression	51_Logistic Regression	Logistic Regression
K-Nearest Neighbors (KNN)	52_KNN	1_KNN, 2_KNN GridSearchCV, 3_Shapey_values
Support Vector Machine (SVM)	53 - SVM	SVM
Naive Bayes	54 - Naive Bayse	Naive Bayse
Decision Tree & Random Forest	55 - Decision Tree and Random Forest	Decission Tree and Random Forest

---

🧩 Explainable AI (XAI)

Explainable AI (XAI) helps understand how models make decisions, improving transparency and trust.
This workshop introduced SHAP (SHapley Additive exPlanations) to interpret model predictions at both the global and local level.

Topics Covered

• Local and Global Interpretability
• Feature Importance Visualization
• SHAP Value Computation
• Transparency in Non-Linear Models
• Example Notebook → 3_Shapey_values.ipynb

---

🔮 Future Additions

Planned topics to expand the AI Programming and Machine Learning Engineer Roadmap include:

• 📊 Feature Engineering & Dimensionality Reduction
• 🔧 Hyperparameter Optimization (GridSearch, Bayesian Search)
• 🧮 Model Evaluation and Bias Detection
• ☁️ MLOps and Streamlit Deployment
• 🔍 Advanced Explainability Techniques (LIME, DeepSHAP, ELI5)

---

📫 Contact

Rasoul Ameri
📧 rasoulameri90@gmail.com
🔗 GitHub Profile

---