anna-ringwood / cleaning-deduplicating-donor-data

This repository holds the code files used in an undergraduate data wrangling project from March - August 2021.

Wrangling Donor Data for a Georgia Nonprofit Organization

This project was carried out with the support of the Quantitative Theory and Methods Department (QTM) at Emory University in Atlanta, Georgia. A team of third- and fourth-year undergraduate QTM students, under the guidance of an industry mentor, worked to clean and derive insights from three data sets provided by a local nonprofit organization.

The project included 3 phases:

1. Exploration and Initial Insights
   a. Import and Explore Data.Rmd
   b. Insights Report.Rmd
2. Combining and/or Removing Duplicate Records
   a. Developing the Deduplicating Process.Rmd
   b. Finalizing the Deduplicating Process.Rmd
3. Supplementing Data and Presenting Results
   a. Final - Bloomerang.Rmd
   b. Final - Mailchimp.Rmd

The earlier files are included to demonstrate how the team progressed through the project-- starting with raw data and ending with a curated set of insights and solutions. If you are only interested in the finished product, all of the finalized code can be found in the files marked "Final".

Please note: Personal identifiable information, though used occasionally in the analyses, has been removed from all files here and are indicated by bracketed placeholders.