This repository investigates the work of Boris Yarkho Comedies and Tragedies of Corneille and attempts to recreate his calculations on his original corpus of French dramatic texts (corneille-corpus-analysis.ipynb) and an extended corpus (extended-corpus-analysis.ipynb). Along with the analyses, this repository also contains the corpora.
Some functions are situated in the dracoranalysis.py file.
Topic modeling's results are dealt with in topics.ipynb. preprocessed folder contains Corneille's plays gone through the FreEM TreeTagger model.
wordclouds folder contains 30 images of the resulting topic wordclouds.
preprocessed_topics_30_full.txt contains information on word distribution of the 30 topics.