Data Science and Software Engineering Projects

The list showcases sample projects related to data analysis, machine learning, deep learning, and software engineering created by Vilmantas Gėgžna.

Data Science Projects

1. Age and Gender Prediction from Images (deep learning project 🧩)

   • Main tools: Python | Repository | HTML report
   • Highlights: computer vision, multi-task learning (classification + regression), custom loss function

2. Classification of Toxic Comments (deep learning project 🧩)

   • Main tools: Python | Repository | HTML report
   • Highlights: natural language processing (NLP), multi-label classification, transfer learning, Hugging face

3. Mushrooms Classification: Common Genus's Images (deep learning project 🧩)

   • Main tools: Python | Repository | HTML report
   • Highlights: computer vision, multi-class classification, transfer learning

4. Lending Club Loan Data Analysis (machine learning project 💡)

   • Main tools: Python | Repository | HTML report | Flask app
   • Highlights: classification and regression, model selection and deployment on Google Cloud Platform (GCP)

5. Home Credit Default Risk Prediction (machine learning project 💡)

   • Main tools: Python | Repository | HTML report | Flask app
   • Highlights: classification, model selection, explainability and deployment on GCP

6. Stroke Risk Prediction (machine learning project 💡)

   • Main tools: Python | Repository | HTML report | Flask app
   • Highlights: classification, hyperparameter tuning, model selection, and deployment on Render.com

7. Travel Insurance Claim Prediction (machine learning project 💡)

   • Main tools: Python | Repository | HTML report
   • Highlights: classification, hyperparameter tuning, model selection

8. The Insights on European Football (data analysis project 📈)

   • Main tools: Python, SQL | Repository | HTML report
   • Highlights: exploratory data analysis (EDA), inferential statistics, and predictive modeling

9. Red Wine Quality Prediction (data analysis project 📈)

   • Main tools: R, Python | Repository | HTML report
   • Highlights: linear and logistic regression, exploratory PCA (principal component analysis)

10. The Analysis of Apple Podcasts Reviews (data analysis project 📈)

    • Main tools: Python, R | Repository | HTML report
    • Highlights: inferential statistics

11. Mental Health in Tech Industry (data analysis project 📈)

    • Main tools: Python, SQL | Repository | HTML report
    • Highlights: categorical data analysis

Software Engineering Projects

1. Simple Calculator in Python (Python package: example 🛠️) :

   • Python, CI/CD on GitHub Actions, Unit testing, Docker | Repository

2. addins.rmd: A Set of RStudio Add-ins (R package 🛠️):

   • R, CI/CD on GitHub Actions | Repository

3. RcmdrPlugin.biostat: Plug-in for R Commander (R package 🛠️):

   • R, GUI programming (via R's Tcl/Tk interface) | Repository