Data Science Projects Repository

This repository documents my journey to become a machine learning engineer. It contains a collection of projects showcasing my skills and progress through various stages of data science and machine learning journey.

Contents

The repository includes projects covering:

1. Data Analysis
2. Data Visualization
3. Machine Learning Algorithms
4. Deep Learning
5. Natural Language Processing
6. Computer Vision
7. Time Series Analysis

Each project folder contains:

• Source code
• Dataset (or link to dataset in code)
• Jupyter notebooks (where applicable)

Project List

1. California Housing Price Regression
2. MNIST Classification
3. IMDb Review Sentiment Classification
4. Glaucoma UNet image segmentation
5. Finetuning Llama 3.1 8B on OCR dataset

Skills Demonstrated

• Python programming
• Data preprocessing and cleaning
• Exploratory Data Analysis (EDA)
• Feature engineering
• Model selection and evaluation
• Hyperparameter tuning
• Deployment of machine learning models
• Finetuning LLMs

Tools and Libraries

• Python
• Pandas, NumPy
• Scikit-learn
• TensorFlow, Keras
• PyTorch
• Matplotlib, Seaborn
• NLTK, spaCy
• unsloth

Future Goals

Creating complex solutions to solve real world problems and provide business solutions.

Contact

Muhammad Mobeen

Email: muhammad.mobeen100@gmail.com

LinkedIn: mobeen0

Website: Portfolio

Feel free to explore the projects and reach out if you have any questions or suggestions!