To learn more about collaborative development with version control systems as well as contributing to open source projects on GitHub, I made two contributions to the PySwarms project. PySwarms is a Python module for particle swarm optimization research.
I performed a detailed analysis of Wikipedia comments and built a model that classifies them as toxic or nontoxic. The final model is a support vector machine that uses a Naive Bayes feature weight transformer to improve performance. The data was obtained from Kaggle. 
This is an image classification project that I completed for my independent study at Old Dominion University. The dataset was obtained from Kaggle’s Galaxy Zoo Challenge. I chose astronomy datasets for my independent study because I enjoy learning about the topic and they presented an opportunity to sharpen my deep learning and PyTorch skills. 
ODUConnect is a web application built on a MSSQL Database / Flask API / ReactJS Front End stack. I let the front end and API development and built the continuous deployment, among other responsibilities.
This is a sequence analysis project that I completed for my independent study at Old Dominion University. I used the open source dataset from Kaggle’s PLAsTiCC Astronomical Classification Challenge. In the project I analyzed light curves, engineered over a hundred metadata features, and built a LightGBM model to predict the object classes. 