Bind the count of the number of documents where a term occurs. The tbl
argument is assumed to
be the output of a call to tidytext::bind_tf_idf()
. This can be useful when filtering for noise
words that should be excluded from downstream analyses for not appearing in enough documents in a
corpus.
Arguments
- tbl
A data frame, typically obtained from a call to
tidytext::bind_tf_idf()
.- document
Column containing document identifiers, as a string or symbol.
- idf
Column containing the inverse document frequencies, as a string or symbol.