This week in class we discussed maximum likelihood, regression, and information criteria.
I was working a lot on the project this week. I implemented dimensionality reduction using t-SNE, PCA, and ISOMAP for the purpose of visualization and looking for clusters in the data. I also determined the Spearman Corrolatin coefficients between all the different features of interest and made a pair plot with all the features. We found strong evidence that there are no clusters though there are some strong correlations. I learned a lot about using Pandas, scipy, sk-learn, and Seaborn which are all things I’ve been meaning to work on for awhile but haven’t had the chance. Next week is finals week so I will likely be mostly writing my final paper then prepping and giving a presentation about this project.