Data Exploration and Analysis on Cambridge Colleges

Language used: Python
Python libraries used: Pandas Numpy Matplotlib Seaborn
IDE used: Jupyter Notebook

Overview

In this project, I analysed the dataset (link to dataset) of postgraduate applicants to the University of Cambridge over 5 years (2015-2020) using Python. Some of my findings, together with the Kaggle notebook are shown below.

Some Key Findings:
  • Number of applicants and admittance has been increasing from 2015 to 2018, with the highest jump of 5219 applicants in 2017.
  • Drop in number of applicants (-259) and admittance (-57) in 2019 compared to 2018.
  • The proportion of applicants without a college preference is on a rise since 2016.
  • The biggest jump in proportion of applicants without a college preference was in 2017, with an increase of 15.3% from 2016.
  • From those who had a college preference, Trinity College had the highest percentage of applicants (18.6%) followed by King's College (9.7%), St John's College (6.9%), Churchill College (4.7%), and Darwin College (4.3%).
  • Top 5 colleges had a combined 44.2% first choice applications, excluding applicants who did not have a college preference.