rm_number(text.var, trim = !extract, clean = TRUE, pattern = "@rm_number", replacement = "", extract = FALSE, dictionary = getOption("regex.library"), ...)
TRUE removes leading and trailing white
spaces.TRUE extra white spaces and escaped
character will be removed.fixed = TRUE) to be matched in the given
character vector. Default, @rm_number uses the
rm_number regex from the regular expression dictionary from
the dictionary argument.pattern.TRUE the numbers are extracted into a
list of vectors.pattern begins with "@rm_".gsub.Remove/replace/extract number from a string (works on numbers with commas, decimals and negatives).
The number regular expression was taken from: http://stackoverflow.com/a/5917250/1000343 authored by Justin Morgan.
x <- c("-2 is an integer. -4.3 and 3.33 are not.", "123,456 is a lot more than -.2", "hello world -.q") rm_number(x)[1] "is an integer. and are not." "is a lot more than" "hello world -.q"rm_number(x, extract=TRUE)[[1]] [1] "-2" "-4.3" "3.33" [[2]] [1] "123,456" "-.2" [[3]] [1] NA
gsub,
stri_extract_all_regex
Other rm_.functions: rm_abbreviation;
rm_angle, rm_bracket,
rm_bracket_multiple,
rm_curly, rm_round,
rm_square; rm_between,
rm_between_multiple;
rm_caps_phrase; rm_caps;
rm_citation_tex; rm_citation;
rm_city_state_zip;
rm_city_state; rm_date;
rm_default; rm_dollar;
rm_email; rm_emoticon;
rm_endmark; rm_hash;
rm_nchar_words; rm_non_ascii;
rm_percent; rm_phone;
rm_postal_code;
rm_repeated_characters;
rm_repeated_phrases;
rm_repeated_words; rm_tag;
rm_time; rm_title_name;
rm_twitter_url, rm_url;
rm_white, rm_white_bracket,
rm_white_colon,
rm_white_comma,
rm_white_endmark,
rm_white_lead,
rm_white_lead_trail,
rm_white_multiple,
rm_white_punctuation,
rm_white_trail; rm_zip