summarize_llr: Summarize the log-likelihood ratio across a grouped data...

Description Usage Arguments Value

Description

Summarize the log-likelihood ratio across a grouped data frame

Usage

1
summarize_llr(data, token, count = rep(1, n()))

Arguments

data

A data frame

token

The column indicating a token.

count

The column indicating wordcount data.

Value

A dataframe with the supplied grouping and a log-likelihood for each token in that grouping. Strongly positive numbers are over-represented; strongly negative numbers are under-represented.


HumanitiesDataAnalysis/TEIdy documentation built on May 11, 2019, 7:25 p.m.