skdreier / NIrelandNLP

British Justifications for Internment without Trial: NLP Approaches to Analyzing Government Archives (Ongoing Project)

MIT License

1 stars 1 forks source link

Plan for 01/21 and beyond #6

Closed skdreier closed 4 years ago

skdreier commented 4 years ago

Update py code and file (denial_long_parsed.csv) with all justification text:

Rename: justifications_parsed.csv
Add columns with number of references per doc
Correct image / file naming issue (using Sarah's code from Thursday)

Merging with date codes

Merge justification csv with file date range (on hand-coded excel)
Upload an Nvivo example of a date code doc and write a summary of what is at issue with the different approaches to dating the documents.

Getting full text corpus

Upload all 8500 docs into OneDrive
Write a script that saves each PDF as a .txt
Get all text into the csv format (image, file, document text)

Start to think about how to use this data!