(This is just a rough summary.)
You'll likely need: NLTK, sklearn, numpy, matplotlib, and several other packages...
- CSLB property norms
- McRae feature norms
- GloVe (Wikipedia 2014 + Gigaword 5, Common Crawl)
- Word2Vec (Google News)
The main directory has subgraphs, where we keep everything, and some empty folders that hold data. In subgraphs, all is where we keep our data outputs and intermediates.