Merge pull request #62 from MarcinKosinski/master

Polish language available as an additional language in serVis

DESCRIPTION

@@ -33,3 +33,4 @@ LazyData: true
 VignetteBuilder: knitr
 URL: https://github.com/cpsievert/LDAvis
 BugReports: https://github.com/cpsievert/LDAvis/issues
+RoxygenNote: 5.0.1

NAMESPACE

@@ -1,8 +1,9 @@
-# Generated by roxygen2 (4.1.1): do not edit by hand
+# Generated by roxygen2: do not edit by hand
 
 export(createJSON)
 export(jsPCA)
 export(renderVis)
 export(runShiny)
 export(serVis)
 export(visOutput)
+importFrom(utils,read.csv)

NEWS

@@ -2,6 +2,8 @@
 
 A new argument, reorder.topics, was added to createJSON(). For details, see #51
 
+It is possible to use different language than english in the final visualization (polish so far). See [[#60]](https://github.com/cpsievert/LDAvis/issues/60).
+
   CHANGES IN LDAvis VERSION 0.3.2
 
 BUG FIX

R/imports.R

@@ -4,3 +4,4 @@
 #' @importFrom proxy dist
 #' @importFrom utils packageVersion browseURL
 #' @importFrom stats cmdscale
+#' @importFrom utils read.csv

R/serVis.R

@@ -20,11 +20,13 @@
 #' interactive login if the GITHUB_PAT environment variable is not set. For more
 #' details, see \url{https://github.com/ropensci/gistr#authentication}.
 #' @param ... arguments passed onto \code{gistr::gist_create}
+#' @param language Which language to use in visualization? So far: \code{english} or \code{polish}.
 #' 
 #' @return An invisible object.
 #' @seealso \link{createJSON}
 #' @export
 #' @author Carson Sievert
+#' @importFrom utils read.csv
 #' @examples
 #' 
 #' \dontrun{
@@ -33,14 +35,33 @@
 #' }
 
 serVis <- function(json, out.dir = tempfile(), open.browser = interactive(), 
-                   as.gist = FALSE, ...) {
+                   as.gist = FALSE, language = "english", ...) {
 
+  stopifnot(is.character(language), length(language) == 1, language %in% c('english', 'polish'))
+
   ## Copy html/js/css files to out.dir
   dir.create(out.dir)
   src.dir <- system.file("htmljs", package = "LDAvis")
   to.copy <- Sys.glob(file.path(src.dir, "*"))
   file.copy(to.copy, out.dir, overwrite = TRUE, recursive = TRUE)
 
+  ## Substitute words to different language if required
+  if (language != 'english') {
+    ldavis.js <- readLines(file.path(out.dir, "ldavis.js")) # changes are made only in this file
+    lang.dict <- read.csv(system.file("languages/dictionary.txt",
+                                      package = "LDAvis")) # read the dictionary
+    for (i in 1:nrow(lang.dict)){ # substitute sentences row by row
+      ldavis.js <- gsub(x  = ldavis.js, pattern = lang.dict[i, 1], 
+                        replacement = lang.dict[i, language], fixed = TRUE)
+    }
+    # lambda coordinate to display its value
+    if (language == 'polish') {
+      ldavis.js[674] <- gsub(ldavis.js[674], pattern = "80", replacement ="175", fixed = TRUE)
+    }
+    # save new language version
+    write(ldavis.js, file = file.path(out.dir, "ldavis.js"))
+  }
+
   ## Write json to out.dir
   cat(json, file = file.path(out.dir, "lda.json"))
 

inst/htmljs/ldavis.js

@@ -334,7 +334,7 @@ LDAvis = function(to_select, json_file) {
             .attr('class', "circleGuideTitle")
             .style("text-anchor", "left")
             .style("fontWeight", "bold")
-            .text("Marginal topic distribtion");
+            .text("Marginal topic distribution");
         d3.select("#leftpanel").append("text")
             .attr("x", cx2 + 10)
             .attr("y", mdsheight + 2 * newSmall)

inst/languages/dictionary.txt

@@ -0,0 +1,17 @@
+base, polish
+"Marginal topic distribution", "Rozkład brzegowy tematów"
+"Intertopic Distance Map (via multidimensional scaling)", "Mapa odległości między tematami (na bazie skalowania wielowymiarowego)"
+"Overall term frequency", "Całkowita częstość terminu"
+"Estimated term frequency within the selected topic", "Przewidywana częstość terminu w wybranym temacie"
+"1. saliency(term w) = frequency(w) * [sum_t p(t | w) * log(p(t | w)/p(t))] for topics t; see Chuang et. al (2012)", "1. widoczność(terminu w) = częstość(w) * [sum_t p(t | w) * log(p(t | w)/p(t))] dla tematu t; Chuang et. al (2012)",
+""2. relevance(term w | topic t) = \u03BB * p(w | t) + (1 - \u03BB) * p(w | t)/p(w); see Sievert & Shirley (2014)"", "2. związek(terminu w | temat t) = \u03BB * p(w | t) + (1 - \u03BB) * p(w | t)/p(w); Sievert & Shirley (2014)",
+" Most Salient Terms", " Najbardziej Widocznych Terminów "
+"Slide to adjust relevance metric:", "Dopasuj miarę związku terminów z tematami"
+" Most Relevant Terms for Topic ", " Najbardziej Związaych Terminy z Tematem "
+"% of tokens)", "% wyrazów)"
+"Conditional topic distribution given term = '", "Warunkowy rozkład tematów przy zadanym terminie = '"
+"Previous Topic", "Poprzedni Temat"
+"Next Topic", "Następny Temat"
+"Clear Topic", "Wyczyść"
+"Selected Topic: <span", "Wybrany Temat: <span"
+"mdswidth = 530", "mdswidth = 620"