Preprocess Document

Preprocess the document, note that this replaces the object in place.

prepare(text, ...)

# S3 method for document
prepare(text, remove_corrupt_utf8 = TRUE,
  remove_case = TRUE, strip_stopwords = TRUE, strip_numbers = TRUE,
  strip_html_tags = TRUE, strip_punctuation = TRUE,
  remove_words = NULL, strip_non_letters = FALSE,
  strip_sparse_terms = FALSE, strip_frequent_terms = FALSE,
  strip_articles = FALSE, strip_indefinite_articles = FALSE,
  strip_definite_articles = FALSE, strip_preposition = FALSE,
  strip_pronouns = FALSE, ...)

# S3 method for documents
prepare(text, remove_corrupt_utf8 = TRUE,
  remove_case = TRUE, strip_stopwords = TRUE, strip_numbers = TRUE,
  strip_html_tags = TRUE, strip_punctuation = TRUE,
  remove_words = NULL, strip_non_letters = FALSE,
  strip_sparse_terms = FALSE, strip_frequent_terms = FALSE,
  strip_articles = FALSE, strip_indefinite_articles = FALSE,
  strip_definite_articles = FALSE, strip_preposition = FALSE,
  strip_pronouns = FALSE, ...)

# S3 method for corpus
prepare(text, remove_corrupt_utf8 = TRUE,
  remove_case = TRUE, strip_stopwords = TRUE, strip_numbers = TRUE,
  strip_html_tags = TRUE, strip_punctuation = TRUE,
  remove_words = NULL, strip_non_letters = FALSE,
  strip_sparse_terms = FALSE, strip_frequent_terms = FALSE,
  strip_articles = FALSE, strip_indefinite_articles = FALSE,
  strip_definite_articles = FALSE, strip_preposition = FALSE,
  strip_pronouns = FALSE, ..., update_lexicon = TRUE,
  update_inverse_index = TRUE)

Arguments

text	An object inheriting of class document or corpus.
...	Other special classes
remove_corrupt_utf8	Remove corrupt UTF8 characters.
remove_case	Convert to lowercase.
strip_stopwords	Remove stopwords, i.e.: "all", "almost", "alone".
strip_numbers	Remove numbers.
strip_html_tags	Remove html tags, including the style and script tags.
strip_punctuation	Remove punctuation.
remove_words	Remove the occurences of words from `doc`.
strip_non_letters	Remove anything non-numeric.
strip_sparse_terms	Remove sparse terms.
strip_frequent_terms	Remove frequent terms.
strip_articles	Remove articles: "a", "an", "the".
strip_indefinite_articles	Removes indefinite articles: "a", "an".
strip_definite_articles	Remove "the".
strip_preposition	Remove preprositions, i.e.: "across", "around", "before".
strip_pronouns	Remove pronounces, i.e.: "I", "you", "he", "she".
update_lexicon	Whether to update the lexicon of the corpus, see update_lexicon.
update_inverse_index	Whether to update the inverse index of the corpus, see update_inverse_index.

See also

stem_words to stem your document.

Examples

# NOT RUN {
init_textanalysis()

# build document
doc <- string_document("This <span>is</span> a very short document!.!")

# replaces in place!
prepare(doc)
get_text(doc)
# }