📊 SiMLeng-Portfolio: AI & LLM Research + Machine Learning Applications

Automated AI/ML Portfolio Scanner & Analysis System
Developed and maintained by Dr. Ruperto Pedro Bonet Chaple

---

🎯 Overview

This repository serves dual purposes:

1. Portfolio Showcase: Curated collection of AI/ML, LLM, and Data Science projects
2. Portfolio Scanner: Automated GitHub Actions system that analyzes and documents AI/ML expertise across repositories

🤖 Automated Portfolio Analysis

The built-in AI Portfolio Scanner automatically:

• 🔍 Scans GitHub repositories for AI/ML frameworks (PyTorch, TensorFlow, LangChain, etc.)
• 📊 Generates comprehensive HTML/Markdown reports
• 🏆 Calculates expertise scores based on code quality and framework diversity
• 📈 Deploys interactive portfolio reports to GitHub Pages
• 🔄 Runs weekly automated scans with GitHub Actions

---

🧠 [2] AI & LLM Projects

Projects focused on large language models, NLP pipelines, and generative AI research.

🔬 Research & Development 📗 ai-llm-blog — Insights and use-cases for LLMs 🧠 LLM-HypatiaX — Custom LLM implementations 🌊 DeepSeek-R1 — Advanced reasoning models ⚡ Generative_AI — Generative AI experiments

🛠️ NLP & Processing 📝 NLP-Spacy-Transformers — Modern NLP pipelines 🔤 Python-NLTK — Natural language toolkit 💬 utterances — Comment system integration

Key Technologies: Transformers, SpaCy, NLTK, OpenAI, Anthropic, LangChain

---

📈 [1] Machine Learning Projects

A variety of applied ML use-cases across industries, platforms, and libraries.

🎓 Deep Learning & Neural Networks

• 🧠 deep-learning — Neural network architectures
• 🎯 Python-Coursera-AI-DEEP-LEARNING — AI/DL coursework
• 🖼️ Python-IMAGE-PROCESSING — Computer vision applications
• 🤖 tensorflow — TensorFlow implementations

📊 Time Series & Forecasting

• ⏰ Python-Sequences-Time-Series-and-Prediction
• 📉 Practical-Time-Series-with-R
• 🔄 TimeSeries_Seq2Seq

🎮 Reinforcement Learning

• 🎯 Python-Reinforcement-Learning
• 🧪 Practical_RL

💼 Applied ML & Industry Solutions

• 😊 customer_satisfaction_ai — Sentiment analysis
• 💰 Python-ML-Trade-Finance — Financial modeling
• 📊 QuantFinanceModels — Quantitative finance
• 🏖️ Tourism-Enhancer-Index-by-Neighbourhoods-in-London

🔧 Tools & Frameworks

• 🐍 CodeMastery-Python-Cpp-R-SQL
• 📦 Python-Package-Explained
• 🐘 Python-JAVA-HADOOP
• 📊 Python-ML-Statsmodels

📚 Datasets & Algorithms

• 💾 datasets
• 🧮 Python-ML-Algorithms
• 📍 Python-ML-Sample-Collocation
• 📈 Python-Genlogistic

🎓 Learning & Education

• 📖 coursera
• 📊 Python-DataScience-Coursera

🔬 Simulation & Modeling

• ⚙️ AI-ML-SIMULATION
• 🤖 simleng_ai

---

🚀 Portfolio Scanner Quick Start

Local Usage

# Install dependencies
pip install -r requirements.txt

# Scan your GitHub profile
python main.py --token YOUR_GITHUB_TOKEN --user sednabcn

# Scan specific repositories
python main.py --token YOUR_TOKEN --repos "sednabcn/LLM-HypatiaX,sednabcn/deep-learning"

GitHub Actions (Automated)

The repository includes three automated workflows:

1. AI Portfolio Scanner (ai-portfolio-scanner.yml)

   • Runs weekly on Sundays at 2:00 AM UTC
   • Manual trigger available in Actions tab
   • Generates HTML/Markdown reports
   • Deploys to GitHub Pages

2. Cleanup Old Portfolios (cleanup-old-portfolios.yml)

   • Runs monthly to remove old artifacts
   • Closes stale issues automatically

3. Portfolio Scan Matrix (portfolio-scan-matrix.yml)

   • Scan multiple GitHub users in parallel
   • Bulk analysis capabilities

Setup Instructions

1. Enable GitHub Actions

   # Workflows are pre-configured in .github/workflows/
   # Just enable them in repository settings

2. Configure Permissions

   • Go to Settings > Actions > General
   • Enable "Read and write permissions"

3. Run Your First Scan

   • Go to Actions > AI Portfolio Scanner
   • Click "Run workflow"
   • Enter target username: sednabcn

📚 Full Setup Guide: See GITHUB_ACTIONS_SETUP.md

---

📊 Scanner Output Examples

After running, the scanner generates:

portfolio-output/
└── ai_portfolio_scan_20250126_120000/
    ├── portfolio_report.html          # Interactive web report
    ├── executive_summary.md           # High-level overview
    ├── portfolio_data.json            # Raw scan data
    ├── framework_analysis.md          # Framework usage details
    └── code_samples/                  # Example code snippets
        ├── tensorflow_example.py
        ├── pytorch_example.py
        └── langchain_example.py

Example Metrics

📊 Portfolio Analysis Results
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━

Statistics:
  • Repositories scanned: 42
  • AI/ML relevant: 28
  • Expertise score: 8.7/10
  • Total files analyzed: 1,247

🔥 Top Frameworks Detected:
  1. TensorFlow (15 repos)
  2. PyTorch (12 repos)
  3. Transformers (8 repos)
  4. Pandas (25 repos)
  5. NumPy (28 repos)

---

🌐 Main Projects & Hubs

SiMLeng-Portfolio This repository

stem-ai-tutoring Main education site

MATHS-STATISTICS Teaching resources

AQU-Portfolio Coastal modeling

LLM-HypatiaX Custom LLMs

---

🛠️ Tech Stack

Languages & Frameworks

AI/ML Libraries

LLM & NLP

---

📁 Repository Structure

SiMLeng-Portfolio/
├── .github/
│   └── workflows/
│       ├── ai-portfolio-scanner.yml       # Main automation workflow
│       ├── cleanup-old-portfolios.yml     # Maintenance workflow
│       └── portfolio-scan-matrix.yml      # Bulk scanning workflow
├── src/
│   ├── code_analyzer.py                   # Code analysis engine
│   ├── config_loader.py                   # Configuration management
│   ├── data_models.py                     # Data structures
│   ├── framework_detector.py              # Framework identification
│   ├── portfolio_builder.py               # Report generation
│   ├── repo_analyzer.py                   # Repository scanner
│   ├── scanner_base.py                    # Base scanner class
│   └── status_detector.py                 # Status detection
├── main.py                                # CLI entry point
├── config.yaml                            # Scanner configuration
├── requirements.txt                       # Python dependencies
├── README.md                              # This file
└── GITHUB_ACTIONS_SETUP.md               # Detailed setup guide

---

🎓 About Dr. Ruperto Pedro Bonet Chaple

Research Interests:

• 🧠 Large Language Models & Generative AI
• 📊 Machine Learning & Deep Learning
• 📈 Time Series Analysis & Forecasting
• 💰 Quantitative Finance & Trading
• 🌊 Computational Modeling
• 🎓 STEM Education & AI Tutoring

Expertise:

• Python, R, C++, SQL
• TensorFlow, PyTorch, Transformers
• NLP, Computer Vision, Reinforcement Learning
• Statistical Modeling & Data Science
• Scientific Computing & Simulation

---

📫 Contact

📧 Email ruperto.bonet@modelphysmat.com

💼 LinkedIn Dr. Ruperto Pedro Bonet Chaple

🌐 Portfolio @sednabcn

---

📜 License

This project is licensed under the MIT License - see individual repository licenses for specific project details.

---

🙏 Acknowledgments

• GitHub API for repository access
• PyGithub for Python GitHub integration
• All open-source AI/ML frameworks featured in this portfolio
• The AI/ML research community

---

⭐ Star this repository if you find it useful!
_{Built with ❤️ for the AI/ML community}

⬆️ Back to Top