Personal Projects Repository

This repository contains a collection of personal projects demonstrating various programming languages and technologies including Artificial Intelligence, Java, and Python implementations.

📁 Repository Structure

PersProj/
├── Machine Learning/                 # Machine Learning & Neural Networks
├── Java/               # Java Applications & Algorithms
├── Python/             # Python Scripts & Utilities
└── README.md           # This file

🤖 Machine Learning Projects

Neural Network Implementation

• File: Machine Learning/nn.py
• Description: Complete neural network implementation for wine quality classification
• Features:
  • UCI Wine Quality dataset integration
  • Multi-layer perceptron with customizable architecture
  • Data visualization and preprocessing
  • Training with validation metrics tracking
  • PyTorch-based implementation

Dependencies: torch, pandas, numpy, matplotlib, seaborn, scikit-learn, ucimlrepo

🐍 Python Projects

Utilities & Scripts

• Data Processing: Scripts for data manipulation and analysis

Machine Learning Support

• Data Preprocessing: Feature engineering and data cleaning utilities
• Visualization: Custom plotting and chart generation
• Model Evaluation: Metrics calculation and performance analysis

Usage:

cd Python
python script_name.py

🚀 Getting Started

Prerequisites

• Python 3.8+
• Java 11+
• Git

Installation

1. Clone the repository:

git clone https://github.com/yourusername/PersProj.git
cd PersProj

2. Install Python dependencies:

python3 -m venv venv
source .venv/bin/activate
pip install -r requirements.txt

3. Set up Java environment:

# Ensure Java 11+ is installed
java -version

Quick Start Guide

1. AI Projects: Navigate to Machine Learning/ folder and run the neural network:

cd Machine Learning
python nn.py

2. Java Projects: Compile and run Java applications:

cd Java
javac *.java
java MainApplication

3. Python Scripts: Execute Python utilities:

cd Python
python python_script.py

📊 Project Highlights

Neural Network Performance

• Dataset: UCI Wine Quality (red wine)
• Architecture: Multi-layer perceptron with ReLU activation
• Training: Adam optimizer with cross-entropy loss
• Visualization: Automated generation of distribution plots and correlation heatmaps

Java Applications

• Object-Oriented Design: Clean separation of concerns
• Error Handling: Comprehensive exception management
• Performance: Optimized algorithms and data structures

Python Utilities

• Data Processing: Efficient pandas-based operations
• Automation: Streamlined workflows for repetitive tasks
• Integration: API clients and data pipeline components

🔧 Configuration

AI Projects

• Modify hyperparameters in nn.py
• Adjust data preprocessing parameters
• Configure visualization settings

Java Projects

• Update configuration files in respective project folders
• Modify build settings in project properties
• Adjust logging levels and output formats

Python Projects

• Edit configuration files or command-line arguments
• Modify API endpoints and credentials
• Adjust data processing parameters

🤝 Contact

For questions or collaboration opportunities, please reach out on kdngiorgos@gmail.com

Last updated: July 2025