combine_vocabularies {text2vec}

Combines multiple vocabularies into one

Description

Combines multiple vocabularies into one

Usage

combine_vocabularies(..., combine_stopwords = function(x)
  unique(unlist(lapply(x, attr, which = "stopwords"), use.names = FALSE)),
  combine_ngram = function(x) attr(x[[1]], "ngram"),
  combine_sep_ngram = function(x) attr(x[[1]], "sep_ngram"))

Arguments

...

vocabulary objects created with create_vocabulary.

combine_stopwords

function to combine stopwords from input vocabularies. By default we take a union of all stopwords.

combine_ngram

function to combine lower and upper boundary for n-grams from input vocabularies. Usually these values should be the same, so we take this parameter from first vocabulary.

combine_sep_ngram

function to combine stopwords from input vocabularies. Usually these values should be the same, so we take this parameter from first vocabulary.

Value

text2vec_vocabulary see details in create_vocabulary.