Description

Explore how term-document matrices and weightings can be used for document classification. You will be attempting to distinguish between documents from different categories in the Brown corpus.
Use the provided script as a starting point. Before beginning, read and understand what it’s doing. Then implement three sorts of document vectors:
1. Raw counts of terms in each document.
2. TF-IDF weighting, using the specific scheme described by Jurafsky and Martin (ch. 6).
Page 1 of 1