diff --git a/DESCRIPTION b/DESCRIPTION index a22f231..53da1c3 100644 --- a/DESCRIPTION +++ b/DESCRIPTION @@ -18,4 +18,4 @@ URL: https://CRAN.R-project.org/package=phonfieldwork, https://agricolamz.github BugReports: https://github.com/agricolamz/phonfieldwork/issues Encoding: UTF-8 LazyData: true -RoxygenNote: 7.0.2 +RoxygenNote: 7.1.0 diff --git a/NAMESPACE b/NAMESPACE index cb5c7e1..02d8a32 100644 --- a/NAMESPACE +++ b/NAMESPACE @@ -6,6 +6,7 @@ export(concatenate_soundfiles) export(create_image_look_up) export(create_presentation) export(create_sound_play) +export(create_subannotation) export(create_viewer) export(df_to_tier) export(draw_sound) diff --git a/NEWS b/NEWS index ab02bc8..297ef33 100755 --- a/NEWS +++ b/NEWS @@ -1,4 +1,5 @@ -phonfieldwork 0.0.4 (...2020) +phonfieldwork 0.0.4 (10.05.2020) + - add "create_subannotation()" function phonfieldwork 0.0.3 (07.01.2020) - vertically and horisontally center text in presentations created by "create_presentation()"; thx @Pandaklez #1 diff --git a/R/annotate_textgrid.R b/R/annotate_textgrid.R index 354e738..1c78fbd 100644 --- a/R/annotate_textgrid.R +++ b/R/annotate_textgrid.R @@ -19,6 +19,8 @@ #' #' @export #' +#' @importFrom tuneR readWave +#' annotate_textgrid <- function(annotation, textgrid, @@ -34,7 +36,6 @@ annotate_textgrid <- function(annotation, tg <- readLines(normalizePath(textgrid)) } - # get start and end info about tiers -------------------------------------- starts <- grep("item \\[\\d{1,}\\]:", tg) ends <- c(starts[-1]-1, length(tg)) @@ -92,7 +93,7 @@ annotate_textgrid <- function(annotation, tg[starts[tier_number]:ends[tier_number]] <- w_tier # write the result TextGrid ----------------------------------------------- - if (isTRUE(write)) { + if (write) { writeLines(tg, normalizePath(textgrid)) } else { return(tg) diff --git a/R/create_subannotation.R b/R/create_subannotation.R new file mode 100644 index 0000000..792c0a6 --- /dev/null +++ b/R/create_subannotation.R @@ -0,0 +1,57 @@ +#' Create boundaries in a texgrid tier +#' +#' +#' @author George Moroz +#' +#' @param textgrid character with a filename or path to the TextGrid +#' @param tier value that could be either ordinal number of the tier either name of the tier +#' @param new_tier_name a name of a new created tier +#' @param n_of_annotations number of new annotations per annotation to create +#' @param each non-negative integer. Each new blank annotation is repeated every first, second or ... times +#' @param omit_blank logical. If TRUE (by dafault) it doesn't create subannotation for empy annotations. +#' @param overwrite logical. If TRUE (by dafault) it overwrites an existing tier. +#' +#' @return a string that contain TextGrid. If argument write is \code{TRUE}, then no output. +#' +#' @examples +#' create_subannotation(textgrid = example_textgrid, tier = 1, overwrite = FALSE) +#' +#' @export +#' + +create_subannotation <- function(textgrid, + tier = 1, + new_tier_name = "", + n_of_annotations = 4, + each = 1, + omit_blank = TRUE, + overwrite = TRUE){ + +# read TextGrid ----------------------------------------------------------- + if(grepl("TextGrid", textgrid[2])){ + tg <- textgrid + } else{ + tg <- readLines(normalizePath(textgrid)) + } + + df <- phonfieldwork::tier_to_df(tg, tier = tier) + df + + if(omit_blank){ + df <- df[df$annotation != "",] + } + + lapply(1:nrow(df), function(i){ + t <- seq(df$start[i], df$end[i], length.out = each*(n_of_annotations+1)) + data.frame(start = t[-length(t)], + end = t[-1]) + }) -> + l + + final <- Reduce(rbind, l) + final <- cbind(id = 1:nrow(final), final, annotation = "") + phonfieldwork::df_to_tier(final, + textgrid = textgrid, + tier_name = new_tier_name, + overwrite = overwrite) +} diff --git a/R/create_viewer.R b/R/create_viewer.R index 6f27983..1eeacae 100644 --- a/R/create_viewer.R +++ b/R/create_viewer.R @@ -29,7 +29,7 @@ create_viewer <- function(audio_dir, tiers = 1, merge_column, caption_column = NULL, - about = "This page were created with the phonfieldworks package for R", + about = "This page were created with the `phonfieldworks` package (Moroz 2019) for R (R Core Team 2020).", output_dir, output_file = "stimuli_viewer", render = TRUE){ diff --git a/R/df_to_tier.R b/R/df_to_tier.R index b627f32..94c6a03 100644 --- a/R/df_to_tier.R +++ b/R/df_to_tier.R @@ -70,7 +70,7 @@ df_to_tier <- function(df, textgrid, tier_name = "", overwrite = TRUE){ paste0(tier_type, ": size = ", nrow(df), " "), unlist(all_annotations) ) - if(isTRUE(overwrite)){ + if(overwrite){ writeLines(append(tg, add_tier), textgrid) } else { append(tg, add_tier) diff --git a/docs/annotation_of_s1.csv b/docs/annotation_of_s1.csv index 33d4d8e..a36b9c6 100644 --- a/docs/annotation_of_s1.csv +++ b/docs/annotation_of_s1.csv @@ -1,8 +1,10 @@ -,id,start,end,annotation -1,1,0,0.108702066839713, -2,2,0.108702066839713,0.184762881187424, -3,3,0.184762881187424,0.577955857574024, -4,4,0.577955857574024,0.689276652082925, -5,5,0.689276652082925,1.03734416788977, -6,6,1.03734416788977,1.13213917296352, -7,7,1.13213917296352,1.39421768707483, +"","id","start","end","annotation" +"1",1,0,0.0981938873393881,"" +"2",2,0.0981938873393881,0.180033198124212,"ı" +"3",3,0.180033198124212,0.482154195011338,"" +"4",4,0.482154195011338,0.578069846032217,"" +"5",5,0.578069846032217,0.691528890529359,"æ" +"6",6,0.691528890529359,0.912063492063492,"" +"7",7,0.912063492063492,1.03562599269282,"" +"8",8,1.03562599269282,1.13048519382978,"ɒ" +"9",9,1.13048519382978,1.39421768707483,"" diff --git a/docs/first_example.html b/docs/first_example.html index d276892..2cb1ce4 100644 --- a/docs/first_example.html +++ b/docs/first_example.html @@ -3110,7 +3110,7 @@

-

+

diff --git a/docs/images/03_annotate_textgrid_result.png b/docs/images/03_annotate_textgrid_result.png index 13cd7f6..e8ca319 100644 Binary files a/docs/images/03_annotate_textgrid_result.png and b/docs/images/03_annotate_textgrid_result.png differ diff --git a/docs/images/04_annotate_textgrid_result.png b/docs/images/04_annotate_textgrid_result.png index a3b17dd..93ec51d 100644 Binary files a/docs/images/04_annotate_textgrid_result.png and b/docs/images/04_annotate_textgrid_result.png differ diff --git a/docs/images/05_annotate_textgrid_result.png b/docs/images/05_annotate_textgrid_result.png new file mode 100644 index 0000000..a3b17dd Binary files /dev/null and b/docs/images/05_annotate_textgrid_result.png differ diff --git a/docs/index.Rmd b/docs/index.Rmd index f516865..d14bfaf 100644 --- a/docs/index.Rmd +++ b/docs/index.Rmd @@ -219,28 +219,38 @@ annotate_textgrid(annotation = my_stimuli_df$stimuli, As you can see in the example, the `annotate_textgrid()` function creates a backup of the tier and adds a new tier on top of the previous one. It is possible to prevent the function from doing so by setting the `backup` argument to `FALSE`. -It is possible to annotate every second (third, fourth, etc.) interval. Imagine that someone annotated each vowel in the recording, so the TextGrid will look as follows: +Imagine that we are interested in annotation of vowels. The most common solution will be open Praat and create new annotations. But it is also possible to create them in advance using subannotations. The idea that you choose some baseline tier that later will be automatically cutted into smaller pieces on the other tier. -```{r, include=FALSE} -annotation <- read.csv("annotation_of_s1.csv") -annotation$annotation <- "" -df_to_tier(df = annotation, textgrid = "s1/s1_all.TextGrid") +```{r} +create_subannotation(textgrid = "s1/s1_all.TextGrid", + tier = 1, # this is a baseline tier + n_of_annotations = 3) # how many empty annotations per unit? ``` ![](images/03_annotate_textgrid_result.png) -Now you can use the second column in `my_stimuli_df`, which contains vowels. +Now we can annotate created tier: ```{r} -my_stimuli_df$vowel -annotate_textgrid(annotation = my_stimuli_df$vowel, +annotate_textgrid(annotation = c("", "ı", "", "", "æ", "", "", "ɒ", ""), textgrid = "s1/s1_all.TextGrid", - each = 2, tier = 3, backup = FALSE) ``` ![](images/04_annotate_textgrid_result.png) + +You can see that we created a third tier with annotation. The only thing left is to move annotation boundaries in Praat (this can not be automated): + +```{r, include=FALSE} +writeLines(readLines("s1/s1_all.TextGrid")[1:44], "s1/s1_all.TextGrid") +df_to_tier(df = read.csv("annotation_of_s1.csv"), + textgrid = "s1/s1_all.TextGrid", + overwrite = TRUE) +``` + +![](images/05_annotate_textgrid_result.png) + You can see from the last figure that no backup tier was created (`backup = FALSE`), that the third tier was annotated (`tier = 3`), and that an annotation was performed in every second interval (`each = 2`). ## Extracting your data diff --git a/docs/index.html b/docs/index.html index 1ada27c..a178d6a 100644 --- a/docs/index.html +++ b/docs/index.html @@ -1656,7 +1656,7 @@

2 Install the package

library("phonfieldwork")

This tutorial was made using the following version of phonfieldwork:

packageVersion("phonfieldwork")
-
## [1] '0.0.3'
+
## [1] '0.0.4'

This tutorial can be cited as follows:

citation("phonfieldwork")
## 
@@ -1712,7 +1712,7 @@ 
4.1 Make a list of your stimuli