Machine Learning

Screenshot of sample code used within the course

Machine Learning: CS 675

For the Fall 2021 semester, I learned about the basics of machine learning along with how you create, improve, and evaluate the model. It was interesting to not only learn the process, but to also apply the code to different data sets and see the results. The course provided an introduction to Python and showed us how to split data, do feature engineering, evaluate/interpret the results, and some tips on how to improve the model, and more.

Screenshot of code and output Shapley plot for random forest model of Kaggle competition project.

Projects

For the midterm and final projects of the class, we got into groups and worked on creating models for Kaggle competitions. Kaggle is an online data science community that is known for holding competitions that provide data sets, rules, and a leaderboard to see how your model compares against others. For our midterm project, we created a model to predict house prices, but we did not participate in the competition. For the final, we participated in the competition and created a model to predict which passengers of the Titanic survived. My group and I were able to create a submission that had a score of 0.78947 using a Random Forest model, which allowed us to score in the top 10% and receive an A in the class.

Click on the icon to go to my GitHub to see repositories for this website and Python projects/assignments!