Emails that matter: Insights from UIUC Mail Archives Using SAS Viya
This project aims to analyze and uncover trends within historical university emails distributed through the CITES Massmail system between October 22, 1999 to November 20, 2011.
# Clone this repository
$ git clone https://github.com/anushavc/uiuc_mail_analysis.git
# Install the requirements
$ pip install -r requirements.txt
# Run the massmail_scraper.py for scraping the mails
$ python massmail_scraper.py
# Run the mail_preprocessing.py for processing the scraped mail records
$ python mail_preprocessing.py
For an in-depth explanantion of the project, head on over to my medium:
Part 1: Explaining the scraping and pre-processing process
Part 2: Explaining the Text analytics pipeline and dashboard