reduction of timings of the examples of document_term_matrix, documen…

…t_term_frequencies, document_term_frequencies_statistics, cooccurrence, dtm_bind, keywords_collocation
bnosac · Nov 9, 2022 · 4f0a0f4 · 4f0a0f4
1 parent 22dbf67
commit 4f0a0f4
Show file tree

Hide file tree

Showing 9 changed files with 43 additions and 5 deletions.
diff --git a/NEWS.md b/NEWS.md
@@ -1,6 +1,7 @@
 ## CHANGES IN udpipe VERSION 0.8.10
 
 - use snprintf instead of sprintf to handle the R CMD check deprecating note on M1mac
+- reduction of timings of the examples of document_term_matrix, document_term_frequencies, document_term_frequencies_statistics, cooccurrence, dtm_bind, keywords_collocation
 
 ## CHANGES IN udpipe VERSION 0.8.9
 

diff --git a/R/nlp_collocation.R b/R/nlp_collocation.R
@@ -41,17 +41,20 @@
 #' @export
 #' @aliases keywords_collocation collocation
 #' @examples 
+#' \dontshow{
+#' data.table::setDTthreads(1)
+#' }
 #' data(brussels_reviews_anno)
-#' x <- subset(brussels_reviews_anno, language %in% "fr")
+#' x      <- subset(brussels_reviews_anno, language %in% "fr")
 #' colloc <- keywords_collocation(x, term = "lemma", group = c("doc_id", "sentence_id"), 
 #'                                ngram_max = 3, n_min = 10)
 #' head(colloc, 10)
 #' 
 #' ## Example on finding collocations of nouns preceded by an adjective
 #' library(data.table)
 #' x <- as.data.table(x)
-#' x[, xpos_previous := txt_previous(xpos, n = 1), by = list(doc_id, sentence_id)]
-#' x[, xpos_next := txt_next(xpos, n = 1), by = list(doc_id, sentence_id)]
+#' x <- x[, xpos_previous := txt_previous(xpos, n = 1), by = list(doc_id, sentence_id)]
+#' x <- x[, xpos_next     := txt_next(xpos, n = 1),     by = list(doc_id, sentence_id)]
 #' x <- subset(x, (xpos %in% c("NN") & xpos_previous %in% c("JJ")) | 
 #'                (xpos %in% c("JJ") & xpos_next %in% c("NN")))
 #' colloc <- keywords_collocation(x, term = "lemma", group = c("doc_id", "sentence_id"), 

diff --git a/R/nlp_cooccurrence.R b/R/nlp_cooccurrence.R
@@ -34,6 +34,9 @@
 #' for the combination of term1 and term2 how many times this combination occurred
 #' @export
 #' @examples 
+#' \dontshow{
+#' data.table::setDTthreads(1)
+#' }
 #' data(brussels_reviews_anno)
 #' 
 #' ## By document, which lemma's co-occur

diff --git a/R/nlp_flow.R b/R/nlp_flow.R
@@ -17,6 +17,9 @@
 #' will assume that freq is 1 for each row in the input dataset \code{x}.
 #' @export
 #' @examples 
+#' \dontshow{
+#' data.table::setDTthreads(1)
+#' }
 #' ##
 #' ## Calculate document_term_frequencies on a data.frame
 #' ##
@@ -119,6 +122,10 @@ document_term_frequencies.character <- function(x, document=paste("doc", seq_alo
 #' @export
 #' @examples 
 #' data(brussels_reviews_anno)
+#' \dontshow{
+#' data.table::setDTthreads(1)
+#' brussels_reviews_anno <- subset(brussels_reviews_anno, language %in% "nl")
+#' }
 #' x <- document_term_frequencies(brussels_reviews_anno[, c("doc_id", "token")])
 #' x <- document_term_frequencies_statistics(x)
 #' head(x)
@@ -170,6 +177,9 @@ document_term_frequencies_statistics <- function(x, k = 1.2, b = 0.75){
 #' @export
 #' @seealso \code{\link[Matrix]{sparseMatrix}}, \code{\link{document_term_frequencies}}
 #' @examples 
+#' \dontshow{
+#' data.table::setDTthreads(1)
+#' }
 #' x <- data.frame(doc_id = c(1, 1, 2, 3, 4), 
 #'  term = c("A", "C", "Z", "X", "G"), 
 #'  freq = c(1, 5, 7, 10, 0))
@@ -661,6 +671,9 @@ dtm_cor <- function(x) {
 #' @aliases dtm_rbind dtm_cbind
 #' @export
 #' @examples 
+#' \dontshow{
+#' data.table::setDTthreads(1)
+#' }
 #' data(brussels_reviews_anno)
 #' x <- brussels_reviews_anno
 #' 
@@ -681,7 +694,8 @@ dtm_cor <- function(x) {
 #' 
 #' ## cbind
 #' library(data.table)
-#' x <- as.data.table(brussels_reviews_anno)
+#' x <- subset(brussels_reviews_anno, language %in% c("nl", "fr"))
+#' x <- as.data.table(x)
 #' x <- x[, token_bigram  := txt_nextgram(token, n = 2), by = list(doc_id, sentence_id)]
 #' x <- x[, lemma_upos    := sprintf("%s//%s", lemma, upos)]
 #' dtm1 <- document_term_frequencies(x = x, document = "doc_id", term = c("token"))

diff --git a/man/cooccurrence.Rd b/man/cooccurrence.Rd
diff --git a/man/document_term_frequencies.Rd b/man/document_term_frequencies.Rd
diff --git a/man/document_term_frequencies_statistics.Rd b/man/document_term_frequencies_statistics.Rd
diff --git a/man/document_term_matrix.Rd b/man/document_term_matrix.Rd
diff --git a/man/dtm_bind.Rd b/man/dtm_bind.Rd