get_frex: Get FREX words

Description Usage Arguments

View source: R/get_frex.R

Description

Get frequent and exclusive words for a group of documents, relative to other groups, based on a probability matrix of word occurrence.

Usage

1
2
get_frex(prob_mtrx, group_num, group_membership = NULL, wt = 0.5,
  values = FALSE)

Arguments

prob_mtrx

A matrix with (named) columns for words, and rows for either documents or document groups. If each row represents a document, group_membership must be provided.

group_num

An integer corresponding to the document group of interest.

group_membership

An integer vector specifying the group membership of documents in prob_mtrx.

wt

A value between 0 and 1 specifying the weight to be given to word exclusivity in calculating FREX.

values

A logical specifying whether the function should return the actual FREX values or just words in decreasing FREX order.


dtburk/texanaaid documentation built on Nov. 12, 2019, 9:44 p.m.