Load packages

Formatting steps

Make sure names in files and annotations match
Downsample to 200 kHz
Split sound files in 5 minute clips (only for no-bedding files)
Split annotations to refer to 5 minute clips (only for no-bedding files)

Format no-bedding recording and annotations

mnl_sls <- imp_raven(path = "./data/raw/updated_annotations", warbler.format = TRUE, all.data = TRUE, name.from.file = TRUE, ext.case = "upper", unread = TRUE)

unread_l <- lapply(file.path("./data/raw/updated_annotations/", mnl_sls$unread_files), function(x) {
  X <- read.table(x, sep = ",", header = TRUE)
  X$selec.file <- X$sound.files <- basename(x)
  return(X)
  })

# remove 4 and 5 as those have only 1 selection and no frequency info
unread_l <- unread_l[1:3]

unread <- do.call(rbind, unread_l)
unread$type <- unread$subtype <- NA

unread <- relabel_colms(unread, hz.to.khz = TRUE)
unread <- sort_colms(unread)

head(unread)

mnl_sls <- sort_colms(mnl_sls$selections)

names(mnl_sls)
names(unread)
mnl_sls$`Begin File` <- NULL

mnl_sls <- rbind(mnl_sls, unread)

mnl_sls$sound.files <- gsub("A_AMPH_15-45_estres_parte2_AUDIO |A_AMPH_15-45_estres_parte2_Audio |A_AMPH_15-45_estres_parte2_AUDIO_", "", mnl_sls$sound.files)

mnl_sls$sound.files <- gsub("T000003.WAV", "T0000003.WAV", mnl_sls$sound.files)
mnl_sls$sound.files <- gsub("T000009.WAV", "T0000009.WAV", mnl_sls$sound.files)
mnl_sls$sound.files <- gsub("T000011.WAV", "T0000011.WAV", mnl_sls$sound.files)
mnl_sls$sound.files <- gsub("T000012.WAV", "T0000012.WAV", mnl_sls$sound.files)
mnl_sls$sound.files <- gsub("T000013.WAV", "T0000013.WAV", mnl_sls$sound.files)
mnl_sls$sound.files <- gsub("T000014.WAV", "T0000014.WAV", mnl_sls$sound.files)

mnl_sls$sound.files <- gsub(".txt$", ".WAV", mnl_sls$sound.files)

unique(mnl_sls$sound.files)

mnl_sls$selec <- 1:nrow(mnl_sls)

cs <- check_sels(mnl_sls)

# unique(cs$sound.files[grep("sound file not found", cs$check.res)])

# table(cs$check.res)

mnl_sls <- mnl_sls[cs$check.res == "OK", ]

cs <- check_sels(mnl_sls)


mnl_sls$bottom.freq[mnl_sls$selec == 2474] <- 48.9885
mnl_sls$top.freq[mnl_sls$selec == 2474] <- 73.8728
mnl_sls$bottom.freq[mnl_sls$selec == 2198] <- 59.6217
mnl_sls$top.freq[mnl_sls$selec == 2198] <- 74311.4
mnl_sls$top.freq[mnl_sls$selec == 1852] <- 111473.9

mnl_sls$top.freq[mnl_sls$top.freq > 100] <- 98

mnl_sls <- mnl_sls[mnl_sls$bottom.freq > 20,]

# export raven file to double check
# exp_raven(mnl_sls, path = "./data/processed", file.name = "pooled_manual_annotations", sound.file.path = .Options$warbleR$path)

# fix_path(path = "./data/processed/", sound.file.col = "Begin File", new.begin.path = "/home/m/Dropbox/Recordings/ratas_cin/full_recs/converted_sound_files")

manual_annot <- imp_raven("./data/processed/", warbler.format = TRUE, files = "fixed_pooled_manual_annotations_JE.txt")

cs <- check_sels(manual_annot, path = "~/Dropbox/Recordings/ratas_cin/recs/original_with_bedding/")

wav_info()

# fix_wavs(samp.rate = 200, bit.depth = 16)

# split in 5 min segments
split_sels <- split_sound_files(sgmt.dur = 5 * 60, only.sels = FALSE, X = manual_annot, parallel = 4)

cs <- check_sels(manual_annot, path = "~/Dropbox/Recordings/ratas_cin/recs/5-min_clips_no_bedding/")

split_sels <- split_sels[cs$check.res == "OK", ]

sp <- spectro_analysis(split_sels, wl = 512, parallel = 10, path = "~/Dropbox/Recordings/ratas_cin/recs/5-min_clips_no_bedding/")

split_sels$peak.freq <- sp$meanpeakf
split_sels$duration <- split_sels$end - split_sels$start


split_sels <- sig2noise(split_sels, mar = 0.005, parallel = 10, path = "~/Dropbox/Recordings/ratas_cin/recs/5-min_clips_no_bedding/")

write.csv(split_sels, "./data/processed/split_manual_annotations_5min.csv", row.names = FALSE)

# export raven file to double check
exp_raven(split_sels, path = "./data/processed", file.name = "split_manual_annotations_5min", sound.file.path = .Options$warbleR$path)

5 min clips metadata no-bedding

wi <- wav_info(path = "~/Dropbox/Recordings/ratas_cin/recs/5-min_clips_no_bedding/")

datatable(wi, editable = list(
  target = 'row'
), rownames = FALSE, style = "bootstrap",  filter = 'top', options = list(
  pageLength = 100, autoWidth = TRUE, dom = 'ft'
), autoHideNavigation = TRUE, escape = FALSE)

Format bedding recording and annotations

mnl_sls <- imp_raven(path = "./data/raw/with_bedding", warbler.format = TRUE, all.data = TRUE, name.from.file = TRUE, ext.case = "upper", unread = FALSE)

mnl_sls$sound.files <- gsub("\\.WAV", ".wav", mnl_sls$sound.files)


fls <- list.files("~/Dropbox/Recordings/ratas_cin/recs/original_with_bedding/")

file.rename(from = file.path("~/Dropbox/Recordings/ratas_cin/recs/original_with_bedding/", fls), to = file.path("~/Dropbox/Recordings/ratas_cin/recs/original_with_bedding/", paste0(substr(fls, 0, 5), ".wav")))

mnl_sls$sound.files <- paste0(substr(mnl_sls$sound.files, 0, 5), ".wav")

cs <- check_sels(mnl_sls, path = "~/Dropbox/Recordings/ratas_cin/recs/original_with_bedding/")

table(cs$check.res)

mnl_sls <- mnl_sls[cs$check.res == "OK", ]

mnl_sls$top.freq[mnl_sls$top.freq > 100] <- 98

mnl_sls <- mnl_sls[mnl_sls$bottom.freq > 20,]

# export raven file to double check
exp_raven(mnl_sls, path = "./data/processed", file.name = "pooled_manual_annotations_with_bedding", sound.file.path = "~/Dropbox/Recordings/ratas_cin/recs/original_with_bedding/")

Sound files metadata no-bedding

wi <- wav_info(path = "~/Dropbox/Recordings/ratas_cin/recs/200_kHz_bedding/")

datatable(wi, editable = list(
  target = 'row'
), rownames = FALSE, style = "bootstrap",  filter = 'top', options = list(
  pageLength = 100, autoWidth = TRUE, dom = 'ft'
), autoHideNavigation = TRUE, escape = FALSE)

Session information

## R version 4.1.0 (2021-05-18)
## Platform: x86_64-pc-linux-gnu (64-bit)
## Running under: Ubuntu 20.04.2 LTS
## 
## Matrix products: default
## BLAS:   /usr/lib/x86_64-linux-gnu/atlas/libblas.so.3.10.3
## LAPACK: /usr/lib/x86_64-linux-gnu/atlas/liblapack.so.3.10.3
## 
## locale:
##  [1] LC_CTYPE=pt_BR.UTF-8       LC_NUMERIC=C              
##  [3] LC_TIME=es_CR.UTF-8        LC_COLLATE=pt_BR.UTF-8    
##  [5] LC_MONETARY=es_CR.UTF-8    LC_MESSAGES=pt_BR.UTF-8   
##  [7] LC_PAPER=es_CR.UTF-8       LC_NAME=C                 
##  [9] LC_ADDRESS=C               LC_TELEPHONE=C            
## [11] LC_MEASUREMENT=es_CR.UTF-8 LC_IDENTIFICATION=C       
## 
## attached base packages:
## [1] stats     graphics  grDevices utils     datasets  methods   base     
## 
## other attached packages:
## [1] DT_0.18            Rraven_1.0.13      warbleR_1.1.27     NatureSounds_1.0.4
## [5] knitr_1.33         seewave_2.1.8      tuneR_1.3.3.1      devtools_2.4.2    
## [9] usethis_2.0.1     
## 
## loaded via a namespace (and not attached):
##  [1] xfun_0.25         bslib_0.2.5.1     remotes_2.4.0     purrr_0.3.4      
##  [5] pbapply_1.4-3     testthat_3.0.4    htmltools_0.5.2   yaml_2.2.1       
##  [9] rlang_0.4.11      pkgbuild_1.2.0    jquerylib_0.1.4   glue_1.4.2       
## [13] withr_2.4.2       sessioninfo_1.1.1 lifecycle_1.0.0   stringr_1.4.0    
## [17] htmlwidgets_1.5.3 memoise_2.0.0     evaluate_0.14     callr_3.7.0      
## [21] fastmap_1.1.0     fftw_1.0-6        crosstalk_1.1.1   ps_1.6.0         
## [25] parallel_4.1.0    Rcpp_1.0.7        cachem_1.0.5      desc_1.3.0       
## [29] pkgload_1.2.1     jsonlite_1.7.2    fs_1.5.0          rjson_0.2.20     
## [33] digest_0.6.27     stringi_1.7.4     processx_3.5.2    dtw_1.22-3       
## [37] rprojroot_2.0.2   cli_3.0.1         tools_4.1.0       bitops_1.0-7     
## [41] magrittr_2.0.1    sass_0.4.0        RCurl_1.98-1.4    proxy_0.4-26     
## [45] crayon_1.4.1      ellipsis_0.3.2    MASS_7.3-54       prettyunits_1.1.1
## [49] rmarkdown_2.10    rstudioapi_0.13   R6_2.5.0          signal_0.7-7     
## [53] compiler_4.1.0

Format USVs recordings

Rat ultrasonic vocalizations

Marcelo Araya-Salas, PhD

20-09-2021

Load packages

Formatting steps

Format no-bedding recording and annotations

5 min clips metadata no-bedding

Format bedding recording and annotations

Sound files metadata no-bedding