The focus of Project 2 is to practice the R packages tidyr and dplyr to prepare three different datasets for downstream analysis. Data Tidying and Transformation, incorporating your existing data-cleaning code and adding two important techniques: 1. Window functions: row_number(), min_rank(), dense_rank(), percent_rank(), lag(), lead(), and cumsum(). 2. Feature engineering: Creating new variables from existing variables to support downstream statistical analysis. The code works with your three datasets: AI Usage, College Majors, and Student Dropout Risk. Because the actual column names have not been provided, the code uses numerical variables that exist in each dataset rather than assuming specific columns are available.

Project 2 for CUNY MSDS Data 607, Fall 2026