This project uses the external emoji library, the nltk library, the gensim library, the pandas library, and the numpy library.
- co_oc*.py - Files that showcase the co-occurrence code.
- emoji_grame.py, emoji_grame2.py, n4ModE.py, n4ModN.py, trials.py, trials2.py, trials3.py - Files that all showcase n-grame code from n=1, n=2, n=3, and n=4.
- final_codings.csv - Encoding of top common emojis into their categories and hedonic and/or utilitarian characteristic.
- flattenModE.py - Flattens the heavy-duty dataset into a more streamlined version that's easier to load into memory.
- lda*.py, overallTM*.py, topicModelling*.py - Files that do LDA topic modelling