Compute log ratios for usage of tokens between two entities.
compute_logratios_facet_wide_at(data = NULL, token = NULL, facet = NULL, cnt_min = 10) compute_logratios_facet_wide(data = NULL, token = NULL, facet = NULL, cnt_min = 10)
data | data.frame. |
---|---|
token | bare for NSE; character for SE. Name of column in |
facet | character. Name of column in |
cnt_min | numeric. If not null, serves as a filter for which to compute log ratios. |
data.frame.
Note that an attempt was made to make this function flexible enough,
to consider a num_top
or top_pct
parameter that might be used if
cnt_min = NULL
, but this can be troublesome because do.call()
does not seem to handle NULL
in ...
.
https://www.tidytextmining.com/twitter.html#comparing-token-usage. http://varianceexplained.org/r/trump-tweets/.