Project Highlights
Election ETL
01.
Election ETL
This repo demonstrates the use of data cleaning skills with pandas, the restructuring of the data to be in a useful form, and the loading of the data into a postgreSQL database. Multiple queries were created that generate summaries of the data.
Citibike Visualizations
02.
Citibike Visualizations
Tableau is a useful tool to create summaries. In this case I created a dashboard to show the differences between male and female ridership. I also included a Leaflet example that I use as a tutorial when teaching javascript.
Myopia ML Predictions
03.
Myopia ML Predictions
I noticed that in 2020 there were still academic journal publications about the myopia dataset. I used the dataset to test different pre-processing techniques and algorithms knowing that there is a pretty clear limit to what can be predicted based on the literature.
Production Optimization
04.
Production Optimization
I am very interested in simulations and optimization problems. This is an example of where I redesigned an example from a highly rated Udemy course that had flaws in organization and process. This is very similar to chemical production scheduling that I did early in my career.
Cloud & ML Operations
05.
Cloud & ML Operations
MLOps is an area that I am just beginning to explore. Here are several examples:
- Amazon Reviews: Used PySpark to manage a large amount of data and create a cloud database.
- Food Inspections: Used scikit-learn pipelines to run the model.
- DevOps: Experimenting with Git hooks, GitHub Actions, and Unit Testing.
These are just a few of the projects that I really like. I am still adding content, testing new features, and updating past work. For more information, check out the career page to learn more about my studies or my projects page to learn about my other repositories.