Files
r-toolbox/warbleR_xeno-canto/warbleR_xeno-canto.r
2024-01-27 15:57:45 +01:00

70 lines
2.1 KiB
R

library(warbleR)
# Create a new folder inside a new tempdir and set it to your working dir
wd <- file.path(tempdir(), "xeno-canto_example")
dir.create(wd)
setwd(wd)
##
# Do the queries
##
# Query xeno-canto for all Phaethornis recordings (e.g., by genus)
Phae <- query_xc(qword = "Phaethornis", download = FALSE)
# Check out the structure of resulting the data frame
str(Phae)
# Query xeno-canto for all Phaethornis longirostris recordings
Phae.lon <- query_xc(qword = "Phaethornis longirostris", download = FALSE)
# Check out the structure of resulting the data frame
str(Phae.lon)
##
# filter xeno-canto recordings by quality, signal type and locality
##
# How many recordings are available for Phaethornis longirostris?
nrow(Phae.lon)
# How many signal types exist in the xeno-canto metadata?
unique(Phae.lon$Vocalization_type)
# How many recordings per signal type?
table(Phae.lon$Vocalization_type)
##
# Filter the metadata to select the signals we want to retain
##
# First by quality
Phae.lon <- Phae.lon[Phae.lon$Quality == "A", ]
nrow(Phae.lon)
# Then by signal type
Phae.lon.song <- Phae.lon[grep("song", Phae.lon$Vocalization_type, ignore.case = TRUE), ]
nrow(Phae.lon.song)
# Finally by locality
Phae.lon.LS <- Phae.lon.song[grep("La Selva Biological Station, Sarapiqui, Heredia", Phae.lon.song$Locality, ignore.case = FALSE), ]
nrow(Phae.lon.LS)
# Check resulting data frame, 3 recordings remain
str(Phae.lon.LS)
# check the location
map_xc(Phae.lon.LS, img = FALSE)
##
# Once we're sure the recordings fit, it's time to download the files, also save
# the metadata as .csv file
##
# Download sound files
query_xc(X = Phae.lon.LS)
# Save the metadata object as a .csv file
write.csv(Phae.lon.LS, "Phae_lon.LS.csv", row.names = FALSE)
##
# xeno-canto maintains recordings in mp3 format due to file size restrictions.
# However, we require wav format for all downstream analyses
##
# here we are downsampling the original sampling rate of 44.1 kHz
# to speed up downstream analyses in the vignette series
mp32wav(samp.rate = 22.05)
# Use checkwavs to see if wav files can be read
check_wavs()