K-means Clustering on College Data

Task

The data was obtained from kaggle https://www.kaggle.com/flyingwombat/us-news-and-world-reports-college-data. Working with this data, it required myself to clean the data into a more usable way by removing and identifying possible outliers. This then assisted with creating k-means clusters on the data to create findings.

Findings about identified clusters

Graduation rate is the probability that they will graduate in % while outstate is the amount of people in the college that went for out-state tuition. By clustering, 2 groups have been identified.

Full report can be found on my github: https://github.com/TingHanGan/college_kmeans_kaggle