Fix numerous spelling mistakes

Author: kbenoit

R/casechange-functions.R

@@ -1,7 +1,7 @@
 #' Convert the case of tokens
 #' 
 #' \code{tokens_tolower} and \code{tokens_toupper} convert the features of a
-#' \link{tokens} object and reindex the types.
+#' \link{tokens} object and re-index the types.
 #' @inheritParams char_tolower
 #' @importFrom stringi stri_trans_tolower
 #' @export

R/corpus_trim.R

@@ -106,7 +106,7 @@ char_trim.character <- function(x, what = c("sentences", "paragraphs", "document
 #'   a tokenized set of sentences if .  If the input was a corpus, then the all
 #'   docvars and metadata are preserved.  For documents whose sentences have
 #'   been removed entirely, a null string (\code{""}) will be returned.
-#' @note This function has been superceded by \code{\link{corpus_trim}}; use
+#' @note This function has been superseded by \code{\link{corpus_trim}}; use
 #'   that function instead.
 #' @export
 #' @keywords internal deprecated

R/dfm-methods.R

@@ -140,7 +140,7 @@ as.dfm.TermDocumentMatrix <- function(x){
                      dimnames = list(colnames(x), rownames(x))))
 }
 
-#' Conversts a Matrix to a dfm
+#' Converts a Matrix to a dfm
 #' @param x a Matrix
 #' @param slots slots a list of values to be assigned to slots
 #' @keywords internal

R/dfm.R

@@ -35,7 +35,7 @@
 #' @param verbose display messages if \code{TRUE}
 #' @param ... additional arguments passed to \link{tokens}; not used when \code{x}
 #'   is a \link{dfm}
-#' @details The default behavior for \code{remove}/\code{select} when 
+#' @details The default behaviour for \code{remove}/\code{select} when 
 #'   constructing ngrams using \code{dfm(x, } \emph{ngrams > 1}\code{)} is to 
 #'   remove/select any ngram constructed from a matching feature.  If you wish 
 #'   to remove these before constructing ngrams, you will need to first tokenize

R/dfm_trim.R

@@ -16,18 +16,18 @@
 #' across all documents, below/above which features will
 #'   be removed
 #' @param termfreq_type how \code{min_termfreq} and \code{max_termfreq} are
-#'   intepreted.  \code{"count"} sums the frequencies; \code{"prop"} devides the
-#'   term frequences by the total sum; \code{"rank"} is matched against the inverted
-#'   ranking of features in terms of overall frequency, so that 1, 2, ... are
-#'   the highest and second highest frequency features, and so on;
+#'   intepreted.  \code{"count"} sums the frequencies; \code{"prop"} divides the
+#'   term frequencies by the total sum; \code{"rank"} is matched against the
+#'   inverted ranking of features in terms of overall frequency, so that 1, 2,
+#'   ... are the highest and second highest frequency features, and so on;
 #'   \code{"quantile"} sets the cutoffs according to the quantiles (see
 #'   \code{\link{quantile}}) of term frequencies.
 #' @param min_docfreq,max_docfreq minimum/maximum values of a feature's document
 #'   frequency, below/above which features will be removed
 #' @param docfreq_type specify how \code{min_docfreq} and \code{max_docfreq} are
-#'   intepreted.   \code{"count"} is the same as \code{\link{docfreq}(x, scheme
-#'   = "count")}; \code{"prop"} devides the document frequences by the total sum;
-#'   \code{"rank"} is matched against the inverted ranking of document
+#'   interpreted.   \code{"count"} is the same as \code{\link{docfreq}(x, scheme
+#'   = "count")}; \code{"prop"} divides the document frequencies by the total
+#'   sum; \code{"rank"} is matched against the inverted ranking of document
 #'   frequency, so that 1, 2, ... are the features with the highest and second
 #'   highest document frequencies, and so on; \code{"quantile"} sets the cutoffs
 #'   according to the quantiles (see \code{\link{quantile}}) of document

R/dfm_weight.R

@@ -65,7 +65,7 @@
 #'     cat("\n\n=== weight() TEST for:", w, "; class:", class(testw), "\n")
 #'     head(testw)
 #' }}
-#' @references Manning, Christopher D., Prabhakar Raghavan, and Hinrich Schutze.
+#' @references Manning, Christopher D., Prabhakar Raghavan, and Hinrich Schütze.
 #'   \emph{Introduction to Information Retrieval}. Vol. 1. Cambridge: Cambridge 
 #'   University Press, 2008.
 dfm_weight <- function(
@@ -259,7 +259,7 @@ dfm_smooth.dfm <- function(x, smoothing = 1) {
 #'   prevent a zero document count for a term
 #' @param base the base with respect to which logarithms in the inverse document
 #' frequency weightings are computed; default is 10 (see Manning, 
-#'   Raghavan, and Schutze 2008, p123).
+#'   Raghavan, and Schütze 2008, p123).
 #' @param threshold numeric value of the threshold \emph{above which} a feature 
 #'   will considered in the computation of document frequency.  The default is 
 #'   0, meaning that a feature's document frequency will be the number of 
@@ -290,7 +290,7 @@ dfm_smooth.dfm <- function(x, smoothing = 1) {
 #' docfreq(wiki_dfm, scheme = "unary")
 #' docfreq(wiki_dfm, scheme = "inversemax")
 #' docfreq(wiki_dfm, scheme = "inverseprob")
-#' @references Manning, C. D., Raghavan, P., & Schutze, H. (2008). 
+#' @references Manning, C. D., Raghavan, P., & Schütze, H. (2008). 
 #'   \emph{Introduction to Information Retrieval}. Cambridge University Press.
 docfreq <- function(x, scheme = c("count", "inverse", "inversemax", 
                                   "inverseprob", "unary"),
@@ -371,7 +371,7 @@ docfreq.dfm <- function(x, scheme = c("count", "inverse", "inversemax",
 #'   weighting.  The default is to use counts instead of normalized term
 #'   frequency (the relative term frequency within document), but this
 #'   can be overridden using \code{scheme_tf = "prop"}.
-#' @references Manning, C. D., Raghavan, P., & Schutze, H. (2008). 
+#' @references Manning, C. D., Raghavan, P., & Schütze, H. (2008). 
 #'   \emph{Introduction to Information Retrieval}. Cambridge University Press.
 #' @seealso \code{\link{dfm_weight}}, \code{\link{docfreq}}
 #' @keywords dfm weighting

R/fcm-methods.R

@@ -166,7 +166,7 @@ as.fcm <- function(x) {
     matrix2fcm(x)
 }
 
-#' Conversts a Matrix to a fcm
+#' Converts a Matrix to a fcm
 #' @param x a Matrix
 #' @param slots slots a list of values to be assigned to slots
 #' @keywords internal

R/textmodel_wordscores.R

@@ -124,8 +124,8 @@ textmodel_wordscores.dfm <- function(x, y, scale = c("linear", "logit"), smooth
 #' @param level tolerance/confidence level for intervals
 #' @param force make the feature set of \code{newdata} conform to the model
 #'   terms.  The default of \code{TRUE} means that a fitted model can be applied
-#'   to scale a dfm that doesn't contain a 1:1 match of features in the training
-#'   and prediction data.
+#'   to scale a dfm that does not contain a 1:1 match of features in the
+#'   training and prediction data.
 #' @param ... not used
 #' @return 
 #' \code{predict.textmodel_wordscores()} returns a named vector of predicted

R/textplot_wordcloud.R

@@ -21,8 +21,8 @@
 #'   dropped.
 #' @param color color of words from least to most frequent
 #' @param font font-family of words and labels. Use default font if \code{NULL}.
-#' @param adjust ajust sizes of words by a constant. Useful for non-Engish words
-#'   for which R fails to obtain correct sizes.
+#' @param adjust adjust sizes of words by a constant. Useful for non-English
+#'   words for which R fails to obtain correct sizes.
 #' @param rotation proportion of words with 90 degree rotation
 #' @param random_order plot words in random order. If \code{FALSE}, they will be
 #'   plotted in decreasing frequency.
@@ -36,8 +36,8 @@
 #'   \code{comparison=TRUE}.
 #' @param fixed_aspect if \code{TRUE}, the aspect ratio is fixed. Variable
 #'   aspect ratio only supported if rotation = 0.
-#' @param comparison if \code{TRUE}, plot a wordclound that compares documents
-#'   in the same way as \code{\link[wordcloud]{comparison.cloud}}
+#' @param comparison if \code{TRUE}, plot a wordcloud that compares documents in
+#'   the same way as \code{\link[wordcloud]{comparison.cloud}}
 #' @param ... additional parameters. Only used to make it compatible with
 #'   \pkg{wordcloud}
 #' @examples
@@ -140,7 +140,7 @@ textplot_wordcloud.dfm <- function(x,
 
 #' Internal function for textplot_wordcloud
 #'
-#' This function impliments wordcloud without dependecies. Code is adopted from 
+#' This function implements wordcloud without dependencies. Code is adopted from 
 #' \code{\link[wordcloud]{wordcloud}}.
 #' @inheritParams textplot_wordcloud
 #' @param scale deprecated argument
@@ -153,7 +153,7 @@ textplot_wordcloud.dfm <- function(x,
 #' @param use.r.layout deprecated argument
 #' @param fixed.asp deprecated argument
 #' @keywords internal
-#' @author Kohei Watanabe, builting on code from Ian Fellows's \pkg{wordcloud} package.
+#' @author Kohei Watanabe, building on code from Ian Fellows's \pkg{wordcloud} package.
 wordcloud <- function(x, min_size, max_size, min_count, max_words, 
                       color, font, adjust, rotation,
                       random_order, random_color, ordered_color,
@@ -309,8 +309,8 @@ wordcloud <- function(x, min_size, max_size, min_count, max_words,
 
 #' Internal function for textplot_wordcloud
 #'
-#' This function impliments wordcloud that compares documents. Code is adopted from
-#' \code{\link[wordcloud]{comparison.cloud}}.
+#' This function implements wordcloud that compares documents. Code is adopted
+#' from \code{\link[wordcloud]{comparison.cloud}}.
 #' @inheritParams textplot_wordcloud
 #' @param scale deprecated argument
 #' @param min.freq deprecated argument

R/tokens.R

@@ -769,10 +769,10 @@ tokens_character <- function(txt,
 #' This function recompiles a serialized tokens object when the vocabulary has
 #' been changed in a way that makes some of its types identical, such as
 #' lowercasing when a lowercased version of the type already exists in the type
-#' table, or introduces gaps in the integer map of the types.  It also reindexes
-#' the types attribute to account for types that may have become duplicates,
-#' through a procedure such as stemming or lowercasing; or the addition of new
-#' tokens through compounding.
+#' table, or introduces gaps in the integer map of the types.  It also
+#' re-indexes the types attribute to account for types that may have become
+#' duplicates, through a procedure such as stemming or lowercasing; or the
+#' addition of new tokens through compounding.
 #' @param x the \link{tokens} object to be recompiled
 #' @param gap if \code{TRUE}, remove gaps between token IDs
 #' @param dup if \code{TRUE}, merge duplicated token types into the same ID 

R/utils.R

@@ -230,7 +230,7 @@ unused_dots <- function(...) {
 
 
 #' Return an error message
-#' @param key type of erro message
+#' @param key type of error message
 #' @keywords internal
 message_error <- function(key = NULL) {
     msg <- c("dfm_empty" = "dfm must have at least one non-zero value",