Add Yule (1944), linting

Author: kbenoit

R/textstat_lexdiv.R

@@ -36,7 +36,7 @@
 #'   \left[ -\frac{1}{N} + \sum_{i=1}^{V} f_v(i, N) \left( \frac{i}{N} \right)^2 \right] }}
 #'
 #'   \item{\code{"I"}:}{Yule's \emph{I}  (Yule, 1944) is calculated by: \deqn{I = \frac{V^2}{M_2 - V}}
-#'   \deqn{M_2 = \sum_{i=1}^{V} i^2 * f_v(i, N)}
+#'   \deqn{M_2 = \sum_{i=1}^{V} i^2 * f_v(i, N)}}
 #'   
 #'   \item{\code{"D"}:}{Simpson's \emph{D}  (Simpson 1949, as presented in
 #'   Tweedie & Baayen, 1998, Eq. 17) is calculated by:
@@ -61,8 +61,9 @@
 #'   halves of the text.}
 #'   
 #'   \item{\code{"MATTR"}:}{The Moving-Average Type-Token Ratio (Covington &
-#'   McFall, 2010) calculates TTRs for a moving window of tokens from the first to the last token, computing a TTR for each window. 
-#'   The MATTR is the mean of the TTRs of each window.}
+#'   McFall, 2010) calculates TTRs for a moving window of tokens from the first
+#'   to the last token, computing a TTR for each window. The MATTR is the mean
+#'   of the TTRs of each window.}
 #'   
 #'   \item{\code{"MSTTR"}:}{Mean Segmental Type-Token Ratio (sometimes referred
 #'   to as \emph{Split TTR}) splits the tokens into segments of the given size,
@@ -127,6 +128,9 @@
 #'   Variable May a Constant Be? Measures of Lexical Richness in Perspective}. \emph{Computers and the 
 #'   Humanities}, 32(5), 323--352.
 #'   
+#'   Yule, G. U. (1944)  \emph{The Statistical Study of Literary Vocabulary.}
+#'   Cambridge: Cambridge University Press.
+#'   
 #' @return A data.frame of documents and their lexical diversity scores.
 #' @export
 #' @examples
@@ -145,7 +149,7 @@
 #' toks <- tokens(corpus_subset(data_corpus_inaugural, Year > 2000))
 #' textstat_lexdiv(toks, c("CTTR", "TTR", "MATTR"), MATTR_window = 100)
 textstat_lexdiv <- function(x,
-                            measure = c("TTR", "C", "R", "CTTR", "U", "S", "K", "I","D",
+                            measure = c("TTR", "C", "R", "CTTR", "U", "S", "K", "I", "D",
                                         "Vm", "Maas", "MATTR", "MSTTR", "all"),
                             remove_numbers = TRUE, remove_punct = TRUE,
                             remove_symbols = TRUE, remove_hyphens = FALSE,
@@ -324,7 +328,7 @@ compute_lexdiv_dfm_stats <- function(x, measure = NULL, log.base = 10) {
         M_2 <- vapply(ViN, function(y) sum(y$ViN * y$i^2), numeric(1))
         M_1 <- temp$n_types
         yule_i <- (M_1 ^ 2) / (M_2 - M_1)
-        yule_i[yule_i== Inf] <- 0
+        yule_i[is.infinite(yule_i)] <- 0
         temp[, I := yule_i]
     }
 

man/textstat_lexdiv.Rd

@@ -10,7 +10,7 @@ test_that("textstat_lexdiv computation is correct", {
         )
 })
 
-test_that("textstat_lexdiv CTTR works correct", {
+test_that("textstat_lexdiv CTTR works correctly", {
     mydfm <- dfm(c(d1 = "b a b a b a b a",
                    d2 = "a a b b"))
 
@@ -21,7 +21,7 @@ test_that("textstat_lexdiv CTTR works correct", {
     )
 })
 
-test_that("textstat_lexdiv R works correct", {
+test_that("textstat_lexdiv R works correctly", {
     mydfm <- dfm(c(d1 = "b a b a b a b a",
                    d2 = "a a b b"))
 
@@ -32,7 +32,7 @@ test_that("textstat_lexdiv R works correct", {
     )
 })
 
-test_that("textstat_lexdiv C works correct", {
+test_that("textstat_lexdiv C works correctly", {
     mydfm <- dfm(c(d1 = "b a b a b a b a",
                    d2 = "a a b b"))
 
@@ -43,7 +43,7 @@ test_that("textstat_lexdiv C works correct", {
     )
 })
 
-test_that("textstat_lexdiv Maas works correct", {
+test_that("textstat_lexdiv Maas works correctly", {
     mydfm <- dfm(c(d1 = "b a b a b a b a",
                    d2 = "a a b b"))
 
@@ -54,7 +54,7 @@ test_that("textstat_lexdiv Maas works correct", {
     )
 })
 
-test_that("textstat_lexdiv I works correct", {
+test_that("textstat_lexdiv Yule's I works correctly", {
     mydfm <- dfm(c(d1 = "a b c",
                    d2 = "a a b b c"))
     expect_equivalent(
@@ -269,7 +269,7 @@ test_that("textstat_lexdiv.tokens raises errors if parameters for moving measure
     # )
 })
 
-test_that("textstat_lexdiv.tokens MATTR works correct on its own", {
+test_that("textstat_lexdiv.tokens MATTR works correctly on its own", {
     mytxt <- "one one two one one two one"
     mytoken <- tokens(mytxt)
     wsize2_MATTR <- (1/2 + 1 + 1 + 1/2 + 1 + 1) / 6
@@ -290,7 +290,7 @@ test_that("textstat_lexdiv.tokens MATTR works correct on its own", {
     )
 })
 
-test_that("textstat_lexdiv.tokens MATTR works correct in conjunction with static measures", {
+test_that("textstat_lexdiv.tokens MATTR works correctly in conjunction with static measures", {
     mytxt <- "one one two one one two one"
     mytoken <- tokens(mytxt)
     wsize2_MATTR <- (1/2 + 1 + 1 + 1/2 + 1 + 1) / 6
@@ -301,7 +301,7 @@ test_that("textstat_lexdiv.tokens MATTR works correct in conjunction with static
     )
 })
 
-test_that("textstat_lexdiv.tokens MSTTR works correct on its own", {
+test_that("textstat_lexdiv.tokens MSTTR works correctly on its own", {
     mytxt <- "apple orange apple orange pear pear apple orange"
     mytoken <- tokens(mytxt)
     wsize2_MSTTR <- (2/2 + 2/2 + 1/2 + 2/2) / 4
@@ -329,7 +329,7 @@ test_that("textstat_lexdiv.tokens MSTTR works correct on its own", {
                       textstat_lexdiv(mytoken, measure = "TTR")[[2]])
 })
 
-test_that("textstat_lexdiv.tokens MSTTR works correct in conjunction with static measures", {
+test_that("textstat_lexdiv.tokens MSTTR works correctly in conjunction with static measures", {
     mytxt <- "apple orange apple orange pear pear apple orange"
     mytoken <- tokens(mytxt)
     wsize2_MSTTR <- (2/2 + 2/2 + 1/2 + 2/2) / 4