Welcome to my GitHub profile! I'm a Software Engineer specialized in data science. I'm developing my skills in data science, machine learning, and artificial intelligence. I am passionate about applying data-driven solutions to real-world problems and continuously expanding my knowledge in the field.
- 🎓 Education: Bachelor’s in Information Technology from Institute Southern Punjab | Data Science Mastery Program at Data Seekho
- 💻 Skills: Python, SQL, Machine Learning, Data Visualization, Pandas, NumPy, Scikit-Learn, TensorFlow, Matplotlib, Seaborn
- 🌱 Currently Learning: Deep Learning, NLP, and Advanced Data Science techniques
- 🤝 Looking to collaborate on: Open-source data science projects and machine learning competitions
- 🏆 Achievements: Completed multiple data science projects, participated in [Competitions/Challenges] on Kaggle
- 🔭 Research Interests: Data Science, AI Ethics, Predictive Modeling, Generative AI
- 📫 How to reach me: sobianoor087@gmail.com | Sobia Noor
Type: Full Stack | Tech: Next.js 14, React 18, TypeScript, FastAPI
- Description: An enterprise-grade multi-agent workflow system for automated investment analysis and risk assessment. Orchestrates a specialized team of autonomous AI agents providing real-time transparency through a cinematic "War Room" user interface.
System Architecture:
-
Frontend: Next.js 14, React 18, TypeScript, Framer Motion
-
Backend: FastAPI (Python 3.11+), WebSockets
-
AI Agent Layer: Planner, Analyst, Reviewer, Finalizer
I'm passionate about sharing knowledge and have delivered the following workshops and training sessions:
| Workshop | Topic | Description |
|---|---|---|
| HPC Malware Detection | Hardware Performance Counters | Workshop on using HPCs for malware detection with Python & ML (95%+ accuracy) |
| DSA Training | LeetCode | Technical sessions on Data Structures & Algorithms at iCodeGuru |
| Web Development Training | Full-Stack Web | Technical sessions on HTML, CSS, and PHP at iCodeGuru |
| IELTS Preparation | English Proficiency | Teaching IELTS to underprivileged students at iCodeGuru |
🔬 HPC Malware Detection Workshop
- Hardware Performance Counters for behavioral malware detection
- Python + Google Colab implementation
- 95%+ ML classification accuracy
- Research preparation for PhD
📂 GitHub Repository 📺 YouTube Workshop
Here are some of the key projects I’ve been working on during my learning journey in data science. Feel free to explore the code, read the documentation, and reach out if you have any questions!
- Description: A customer segmentation project using K-Means clustering to group customers based on purchasing behavior.
- Technologies Used: Python, Pandas, Scikit-Learn, Matplotlib, Power BI
- Key Steps: Data Cleaning, Exploratory Data Analysis (EDA), Model Training, and Evaluation
- Results: Found distinct customer segments that will help drive targeted marketing strategies.
- 📂 Link to Project Repository
- Description: A predictive framework for COVID-19 mortality based on clinical and demographic data. Addressed significant class imbalance using Random Undersampling to improve model sensitivity for identifying high-risk patients.
- Technologies Used: Python, Scikit-learn, Pandas, Matplotlib, Seaborn
- Key Steps: Data Preprocessing, Feature Engineering, Model Training
- Results: Logistic Regression achieved balanced F1-scores (Death: 0.85, Survival: 0.84) after resampling, prioritizing sensitivity over raw accuracy.
- 📂 Link to Project Repository
- Description: Example: "A web scraping project to collect and analyze product reviews from e-commerce websites using BeautifulSoup and Pandas."
- Technologies Used: Python, BeautifulSoup, Pandas
- Key Steps: Web Scraping, Data Collection, Sentiment Analysis
- Results: Successfully extracted and analyzed over 1,000 reviews for sentiment trends.
- 📂 Link to Project Repository
Here are the technologies and tools that I use most frequently. My expertise is constantly evolving as I explore new areas of data science and machine learning.
- Languages: Python, SQL
- Libraries & Frameworks:
- Data Analysis: Pandas, NumPy
- Machine Learning: Scikit-Learn, TensorFlow, Keras
- Data Visualization: Matplotlib, Seaborn, Plotly
- Web Scraping: BeautifulSoup, Scrapy
- Databases: MySQL, PostgreSQL
- Tools: Jupyter Notebooks, Google Colab, Git, Docker
- Cloud Platforms: AWS (S3, EC2), Google Cloud
I believe in continuous learning to stay up-to-date with the latest trends in data science. Here's what I'm currently focused on:
- Deep Learning: Building models using TensorFlow and Keras
- NLP (Natural Language Processing): Exploring sentiment analysis, text classification, and transformers
- Generative AI: Understanding the applications and limitations of generative models like GPT and DALL·E
| Certification | Issuer |
|---|---|
| Data Science Mastery Program (DSMP) | Data Seekho |
| Pandas | Kaggle |
| How to Get Into Robotics | FutureLearn |
| Data Science & Analytics | HP LIFE |
| How to Get Into AI | FutureLearn |
Read my blogs :
I enjoy connecting with fellow data enthusiasts, so feel free to reach out to me! Whether it’s to collaborate, discuss projects, or exchange knowledge, I’m always open to new connections.
- LinkedIn: Sobia Noor
- Email: sobianoor087@gmail.com
Thank you for visiting my profile, and I hope you find my projects insightful!
Aside from coding, I enjoy cycling, playing cricket, and reading about AI trends!