R/utilities.R

basic_punct <-function() {
    c("(?!['-])[[:punct:]]", "\\n")
} 

#' @export
basic_stop_words <- function(){
  words <-  c("i've", "we've", "i", "me", "my", "myself", "we", "our", "ours", "ourselves", 
              "you", "your", "yours", "yourself", "yourselves", "he", "him", 
              "his", "himself", "she", "her", "hers", "herself", "it", "its", 
              "itself", "they", "them", "their", "theirs", "themselves", "what", 
              "which", "who", "whom", "this", "that", "these", "those", "am", "is", 
              "are", "was", "were", "be", "been", "being", "have", "has", "had", 
              "having", "do", "does", "did", "doing", "would", "should", "could",
              "ought", "i'm", "you're", "he's", "she's", "it's", "we're", "they're",
              "i've", "you've", "we've", "they've", "i'd", "you'd", "he'd", "she'd", 
              "we'd", "they'd", "i'll", "you'll", "he'll", "she'll", "we'll", "they'll", 
              "isn't", "aren't", "wasn't", "weren't", "hasn't", "haven't", "hadn't", 
              "doesn't", "don't", "didn't", "won't", "wouldn't", "shan't", "shouldn't",
              "can't", "cannot", "couldn't", "mustn't", "let's", "that's", "who's", 
              "what's", "here's", "there's", "when's", "where's", "why's", "how's", 
              "a", "an", "the", "and", "but", "if", "or", "because", "as", "until", 
              "while", "of", "at", "by", "for", "with", "about", "against", "between",
              "into", "through", "during", "before", "after", "above", "below", "to",
              "from", "up", "down", "in", "out", "on", "off", "over", "under", "again",
              "further", "then", "once", "here", "there", "when", "where", "why", "how",
              "all", "any", "both", "each", "few", "more", "most", "other", "some", "such",
              "no", "nor", "not", "only", "own", "same", "so", "than", "too", "very", "will",
              "like", "can")
  words
}


#' @export
smart_stop_words <- function(){
  
  words <- c("i've", "we've", "a", "a's", "able", "about", "above", "according", "accordingly", 
             "across", "actually", "after", "afterwards", "again", "against", 
             "ain't", "all", "allow", "allows", "almost", "alone", "along", 
             "already", "also", "although", "always", "am", "among", "amongst", 
             "an", "and", "another", "any", "anybody", "anyhow", "anyone", "anything",
             "anyway", "anyways", "anywhere", "apart", "appear", "appreciate", "appropriate", 
             "are", "aren't", "around", "as", "aside", "ask", "asking", "associated",
             "at", "available", "away", "awfully", "b", "be", "became", "because", "become",
             "becomes", "becoming", "been", "before", "beforehand", "behind", "being", 
             "believe", "below", "beside", "besides", "best", "better", "between", "beyond", 
             "both", "brief", "but", "by", "c", "c'mon", "c's", "came", "can", "can't", 
             "cannot", "cant", "cause", "causes", "certain", "certainly", "changes",
             "clearly", "co", "com", "come", "comes", "concerning", "consequently", 
             "consider", "considering", "contain", "containing", "contains", "corresponding",
             "could", "couldn't", "course", "currently", "d", "definitely", "described",
             "despite", "did", "didn't", "different", "do", "does", "doesn't", "doing", 
             "don't", "done", "down", "downwards", "during", "e", "each", "edu", "eg", "eight",
             "either", "else", "elsewhere", "enough", "entirely", "especially", "et", "etc",
             "even", "ever", "every", "everybody", "everyone", "everything", "everywhere", 
             "ex", "exactly", "example", "except", "f", "far", "few", "fifth", "first", 
             "five", "followed", "following", "follows", "for", "former", "formerly", 
             "forth", "four", "from", "further", "furthermore", "g", "get", "gets", "getting",
             "given", "gives", "go", "goes", "going", "gone", "got", "gotten", "greetings", "h", 
             "had", "hadn't", "happens", "hardly", "has", "hasn't", "have", "haven't", "having",
             "he", "he's", "hello", "help", "hence", "her", "here", "here's", "hereafter", "hereby",
             "herein", "hereupon", "hers", "herself", "hi", "him", "himself", "his", "hither",
             "hopefully", "how", "howbeit", "however","i'd", "i'll", "i'm", "i've", "ie", "i",
             "if", "ignored", "immediate", "in", "inasmuch", "inc", "indeed", "indicate", "indicated",
             "indicates", "inner", "insofar", "instead", "into", "inward", "is", "isn't", "it",
             "it'd", "it'll", "it's", "its", "itself", "j", "just", "k", "keep", "keeps", "kept",
             "know", "knows", "known", "l", "last", "lately", "later", "latter", "latterly", "least",
             "less", "lest", "let", "let's", "like", "liked", "likely", "little", "look", "looking",
             "looks", "ltd", "m", "mainly", "many", "may", "maybe", "me", "mean", "meanwhile", 
             "merely", "might", "more", "moreover", "most", "mostly", "much", "must", "my", "myself",
             "n", "name", "namely", "nd", "near", "nearly", "necessary", "need", "needs", "neither", 
             "never", "nevertheless", "new", "next", "nine", "no", "nobody", "non", "none", "noone",
             "nor", "normally", "not", "nothing", "novel", "now", "nowhere", "o", "obviously", "of",
             "off", "often", "oh", "ok", "okay", "old", "on", "once", "one", "ones", "only", "onto", 
             "or", "other", "others", "otherwise", "ought", "our", "ours", "ourselves", "out", 
             "outside", "over", "overall", "own", "p", "particular", "particularly", "per", "perhaps",
             "placed", "please", "plus", "possible", "presumably", "probably", "provides", "q",
             "que", "quite", "qv", "r", "rather", "rd", "re", "really", "reasonably", "regarding",
             "regardless", "regards", "relatively", "respectively", "right", "s", "said", "same", 
             "saw", "say", "saying", "says", "second", "secondly", "see", "seeing", "seem", "seemed",
             "seeming", "seems", "seen", "self", "selves", "sensible", "sent", "serious", "seriously",
             "seven", "several", "shall", "she", "should", "shouldn't", "since", "six", "so", "some",
             "somebody", "somehow", "someone", "something", "sometime", "sometimes", "somewhat",
             "somewhere", "soon", "sorry", "specified", "specify", "specifying", "still", "sub", 
             "such", "sup", "sure", "t", "t's", "take", "taken", "tell", "tends", "th", "than", "thank",
             "thanks", "thanx", "that", "that's", "thats", "the", "their", "theirs", "them", "themselves",
             "then", "thence", "there", "there's", "thereafter", "thereby", "therefore", "therein",
             "theres", "thereupon", "these", "they", "they'd", "they'll", "they're", "they've", "think",
             "third", "this", "thorough", "thoroughly", "those", "though", "three", "through", 
             "throughout", "thru", "thus", "to", "together", "too", "took", "toward", "towards", 
             "tried", "tries", "truly", "try", "trying", "twice", "two", "u", "un", "under", "unfortunately", 
             "unless", "unlikely", "until", "unto", "up", "upon", "us", "use", "used", "useful", "uses",
             "using", "usually", "uucp", "v", "value", "various", "very", "via", "viz", "vs", "w", "want",
             "wants", "was", "wasn't", "way", "we", "we'd", "we'll", "we're", "we've", "welcome", "well", 
             "went", "were", "weren't", "what", "what's", "whatever", "when", "whence", "whenever", "where", 
             "where's", "whereafter", "whereas", "whereby", "wherein", "whereupon", "wherever", "whether",
             "which", "while", "whither", "who", "who's", "whoever", "whole", "whom", "whose", "why", "will",
             "willing", "wish", "with", "within", "without", "won't", "wonder", "would", "would", "wouldn't",
             "x", "y", "yes", "yet", "you", "you'd", "you'll", "you're", "you've", "your", "yours", "yourself",
             "yourselves", "z", "zero")
  
  words
  
}


# only want to generate stopwords once when getting candidates from a vector
prep_stop_words <- function(split_words = stop_words(), split_punct = basic_punct(), remove_numbers = T) {
  if (is.null(split_words) && is.null(split_punct)) {
    stop("Please provide a vector of stop words or punctuation or use provided stopwords")
  } 
  
 words <- stringr::str_c("\\b(", split_words, ")(?![\\w-])", sep = "")
  if(remove_numbers == T){
    names <- c(split_punct, "\\(?[0-9,.]+\\)?", words)
  } else if(remove_numbers == F) {
    names <- c(words, split_punct)
  } else {
    stop("remove_numbers must be TRUE or FALSE")
  }
  splits <- rep("*", length(names))
  
  purrr::set_names(splits, names)
}
lmkirvan/rakeR documentation built on May 14, 2019, 1:46 p.m.