https://github.com/adamrossnelson/collegeapps

Repo to support research related to college applications.
https://github.com/adamrossnelson/collegeapps

Last synced: 3 months ago
JSON representation

Repo to support research related to college applications.

• Host: GitHub
• URL: https://github.com/adamrossnelson/collegeapps
• Owner: adamrossnelson
• License: mit
• Created: 2018-04-09T16:28:09.000Z (about 7 years ago)
• Default Branch: master
• Last Pushed: 2018-05-24T23:22:39.000Z (almost 7 years ago)
• Last Synced: 2025-01-10T04:54:24.887Z (4 months ago)
• Language: Stata
• Size: 160 KB
• Stars: 0
• Watchers: 2
• Forks: 0
• Open Issues: 0
• Metadata Files:
  • Readme: README.md
  • License: LICENSE

Awesome Lists containing this project

README

        
# CollegeApps

Repo to support research related to college applications.

## File Descriptions

**Gathering data**

* `ColAppScrape.do` - Do file that prepares smaller version of `IPEDSDirInfo02to16.dta`.

* `ColAppScrape.jpynb` - Notebook designed to web scrape paper / pdf undergradute college applications. Uses the list of web domains provided by `ColAppScrape.do`.

* `ColEarlyDecScrape.ipynb` - Notebook that provided a prototype for `ColAppScrape.jpynb`.

**Processing data**

* `ColAppTextProc.ipynb` - Notebook that pre-processes text data scraped by `ColAppScrape.jpynb`.

* `ColAppTextProcDemo.ipynb` - Notebook that provides a prototype for `ColAppTextProc.ipynb`.

**Testing data**

* ` ColAppTester.ipynb` - Notebook that applies applies machine learning to predict if a pdf is an undergraduate application for admission.

**Subfolder `App_Rec_Train`**

* Scratch space used to prepare training data.