text2vec: prune_vocabulary – R documentation

Become an expert in R — Interactive courses, Cheat Sheets, certificates and more!

prune_vocabulary

Prune vocabulary

Description

This function filters the input vocabulary and throws out very frequent and very infrequent terms. See examples in for the vocabulary function. The parameter vocab_term_max can also be used to limit the absolute size of the vocabulary to only the most frequently used terms.

Usage

prune_vocabulary(vocabulary, term_count_min = 1L, term_count_max = Inf,
  doc_proportion_min = 0, doc_proportion_max = 1, doc_count_min = 1L,
  doc_count_max = Inf, vocab_term_max = Inf)

Arguments

`vocabulary`	a vocabulary from the vocabulary function.
`term_count_min`	minimum number of occurences over all documents.
`term_count_max`	maximum number of occurences over all documents.
`doc_proportion_min`	minimum proportion of documents which should contain term.
`doc_proportion_max`	maximum proportion of documents which should contain term.
`doc_count_min`	term will be kept number of documents contain this term is larger than this value
`doc_count_max`	term will be kept number of documents contain this term is smaller than this value
`vocab_term_max`	maximum number of terms in vocabulary.

prune_vocabulary

Description

Usage

Arguments

See Also

text2vec

We don't support your browser anymore