I am Luna McBride. I am very interested in Data Science and AI. I attained my Master's Degree in Computer Science with a subplan in Data Science and Engineering from The Univeristy of Colorado Boulder in May 2024. I also received my Bachelor's Degree in Computer Science and Japanese from The University of Colorado Boulder in December 2019.
This GitHub was revamped for increased readability. Every class repository was moved into the School_Work Repository, retaining the structure of the original repositories. My more recent work has been using Kaggle datasets, which can be found in the Kaggle_Personal_Projects Repository. Each project is organized in folders by project type and have their own readme, so do not worry about getting lost.
If you want some projects I recommend, those would be:
-
My Natural Language Processing Speedup Study, which aimed to make model training more accessible by identifying free libraries and low-cost speedup options for those who want to get into the field but do not have the money they would expect is necessary to do so.
-
My Medicaid Spending Analysis Dashboard, which uses PowerBI to show which medications your taxpayer dollars are going toward.
-
Cheese Classification CV, where I trained a Keras model to distinguish between two different types of French cheeses by their images at near 100% accuracy.
-
Amazon Stock Time Series Analysis, where I used an ARIMA model to predict future Amazon Stocks.
-
Japanese NLP, where I test the functions required to process Japanese text. This was not easy to build due to how sparse information was on the topic, so I like to show this off for anyone who wants to try processing Japanese.
-
Serebii Scraping, where I scraped and analyzed type matchup data from serebii.net. I made special care to check the site's terms and robots.txt when scraping, so do not worry about that factor. I just thought the scraping process and analysis was interesting.
-
House Regression, where I compared various regression models for their accuracy in deciding which attributes made for a higher house price. I also compared those attributes between the Linear Regression and the highest preformer to see where it may have gone awry.
-
Bank Clustering, where I clustered bank data and took the mean of the clusters to describe the average user for each group. This one stands out to me because it came about from seeing the dataset, having no clue what was going on with it, followed by learning what clustering was as I went along.
-
Ramen Data Exploration, which explores ramen product data. It is a basic exploration, but it was done with R rather than Python. I am much better with Python, but I feel having knowledge with R as well rounds out my skillset a bit more.
These are just the current highlights, so I encourage you to go to the Kaggle_Personal_Projects Folder to see some more.
If you would like to reach me elsewhere, you can find me on: