vpr_export.RdFormat and export VPR data for publication (IN DEVELOPMENT) Exports a csv file with standard column names based on British Oceanographic Data Centre, BODC::P01 and DarwinCore (DwC) naming conventions, and a JSON metadata file for station level metadata
vpr_export(data, metadata, columnNames, file)
if (FALSE) { # \dontrun{
data(category_conc_n)
metadata <- list(
"station_level" = list(
"title" = list("en" = "VPR data from the Scotian Shelf",
"fr" = "Données VPR de l'étagère néo-écossaise"),
"dataset_ID" = 1,
"decimalLatitudeStart" = 44.5,
"decimalLongitudeStart" = -64.5,
"decimalLatitudeEnd" = 45.5,
"decimalLongitudeEnd" = -65.5,
"maximumDepthInMeters" = 1000,
"eventDate" = "2019-08-11",
"eventTime" = "00:00:00",
"basisOfRecord" = "MachineObservation",
"associatedMedia" = "https://ecotaxa.obs-vlfr.fr/ipt/archive.do?r=iml2018051",
"identificationReferences" = "Iv3 model v3.3",
"instrument" = list("opticalSetting" = "S2",
"imageVolume" = 83663),
"resources" = list(
"data" = list("name" = "vpr123_station25.csv",
"creationDate" = "2023-01-01"),
"metadata" = list("name" = "vpr123_station25-metadata.json",
"creationDate" = "2023-01-01")
),
"dataAttributes" = list(
"eventID" = list(
"dataType" = "chr",
"definition" = "An identifier for the set of information associated
with a dwc:Event (something that occurs at a place and time). May be
a global unique identifier or an identifier specific to the data set.",
"vocabulary" = "dwc"
),
"minimumDepthInMeters" = list(
"dataType" = "float",
"definition" = "The lesser depth of a range of depth below the local",
"vocabulary" = "dwc"
),
"maximumDepthInMeters" = list(
"dataType" = "float",
"definition" = "The greater depth of a range of depth below the local",
"vocabulary" = "dwc"
),
"DEPHPRST" = list(
"dataType" = "float",
"definition" = "Depth (spatial coordinate) of sampling event start
relative to water surface in the water body by profiling pressure
sensor and conversion to depth using unspecified algorithm",
"vocabulary" = "BODC::P01"
),
"individualCount" = list(
"dataType" = "float",
"definition" = "The number of individuals present at the time of the
dwc:Occurrence.",
"vocabulary" = "dwc"
),
"verbatimIdentification" = list(
"dataType" = "chr",
"definition" = "A string representing the taxonomic identification as
it appeared in the original record.",
"vocabulary" = "dwc"
),
"SDBIOL01" = list(
"dataType" = "float",
"definition" = "Abundance of biological entity specified elsewhere
per unit volume of the water body",
"vocabulary" = "BODC::P01"
),
"TEMPST01" = list(
"dataType" = "float",
"definition" = "Temperature of the water body by CTD or STD",
"vocabulary" = "BODC::P01"
),
"PSALST01" = list(
"dataType" = "float",
"definition" = "Practical salinity of the water body by CTD and
computation using UNESCO 1983 algorithm",
"vocabulary" = "BODC::P01"
),
"POTDENS0" = list(
"dataType" = "float",
"definition" = "Density (potential) of the water body by computation
from salinity and potential temperature using UNESCO algorithm with
0 decibar reference pressure",
"vocabulary" = "BODC::P01"
),
"FLUOZZZZ" = list(
"dataType" = "float",
"definition" = "Fluorescence of the water body",
"vocabulary" = "BODC::P01"
),
"TURBXXXX" = list(
"dataType" = "float",
"definition" = "Turbidity of water in the water body",
"vocabulary" = "BODC::P01"
),
"sampleSizeValue" = list(
"dataType" = "float",
"definition" = "A numeric value for a measurement of the size (time
duration, length, area, or volume) of a sample in a sampling
dwc:Event.",
"vocabulary" = "dwc"
),
"sampleSizeUnit" = list(
"dataType" = "chr",
"definition" = "The unit of measurement of the size (time duration,
length, area, or volume) of a sample in a sampling dwc:Event.",
"vocabulary" = "dwc"
),
"scientificName" = list(
"dataType" = "chr",
"definition" = "The full scientific name, with authorship and date
information if known. When forming part of a dwc:Identification, this
should be the name in lowest level taxonomic rank that can be
determined. This term should not contain identification
qualifications, which should instead be supplied in the
dwc:identificationQualifier term.",
"vocabulary" = "dwc"
),
"identifiedBy" = list(
"dataType" = "chr",
"definition" = "A list (concatenated and separated) of names of
people, groups, or organisations who assigned the Taxon to the subject.",
"vocabulary" = "dwc"
),
"identificationVerificationStatus" = list(
"dataType" = "chr",
"definition" = "A categorical indicator of the extent to which the
taxonomic identification has been verified to be correct.",
"vocabulary" = "dwc"
),
"depthDifferenceMeters" = list(
"dataType" = "float",
"definition" = "Difference between maximumDepthInMeters and
minimumDepthInMeters of an individual data bin, in meters",
"vocabulary" = "BIO"
),
"minimumTimeSeconds" = list(
"dataType" = "float",
"definition" = "minimum time value in a data bin, measured in seconds
from the start of the day of sampling",
"vocabulary" = "BIO"
),
"maximumTimeSeconds" = list(
"dataType" = "float",
"definition" = "maximum time value in a data bin, measured in seconds
from the start of the day of sampling",
"vocabulary" = "BIO"
),
"timeDifferenceSeconds" = list(
"dataType" = "float",
"definition" = "Difference between maximumTimeSeconds and
minimumTimeSeconds of an individual data bin, in seconds",
"vocabulary" = "BIO"
),
"numberOfFrames" = list(
"dataType" = "float",
"definition" = "number of VPR frames captured within an individual data bin",
"vocabulary" = "BIO"
),
"timeMilliseconds" = list(
"dataType" = "float",
"definition" = "Time measured in milliseconds since the start of the sampling day",
"vocabulary" = "BIO"
),
"towyoID" = list(
"dataType" = "chr",
"definition" = "A string identifying the section of the cast to which
the data point belongs",
"vocabulary" = "BIO"
),
"maximumCastDepthInMeters" = list(
"dataType" = "float",
"definition" = "Maximum depth in Meters of the cast dataset",
"vocabulary" = "BIO"
)
)
)
)
# new_name = old_name
columnNames = list( "DEPHPRST" = "depth" ,
"verbatimIdentification" = "category",
"eventID" = "station",
"minimumDepthInMeters" = "min_depth",
"maximumDepthInMeters" = "max_depth",
"individualCount" = "n_roi_bin",
"SDBIOL01" = "conc_m3",
"TEMPST01" = "temperature",
"PSALST01" = "salinity",
"POTDENS0" = "density",
"FLUOZZZZ" = "fluorescence",
"TURBXXXX" = "turbidity",
"sampleSizeValue" = "vol_sampled_bin_m3",
"depthDifferenceMeters" = "depth_diff",
"minimumTimeSeconds" = "min_time_s",
"maximumTimeSeconds" = "max_time_s",
"timeDifferenceSeconds" = "time_diff_s",
"numberOfFrames" = "n_frames",
"timeMilliseconds" = "time_ms",
"towyoID" = "towyo",
"maximumCastDepthInMeters" = "max_cast_depth"
)
# add any new data columns required
# (eg. sampleSizeUnit, scientificName, identifiedBy, identificationVerificationStatus)
sampleSizeUnit <- "cubic metre"
identifiedBy <- "K. Sorochan"
identificationVerificationStatus <- "ValidatedByHuman"
data <- category_conc_n %>%
mutate(., identifiedBy = identifiedBy,
sampleSizeUnit = sampleSizeUnit,
identificationVerificationStatus = identificationVerificationStatus)
# Define the mapping between category and scientific name
# scientific names based ecotaxa taxonomic system
scientificName <- list("blurry" = "bad_image_blurry",
"artefact" = c("bad_image_malfunction", "bad_image_strobe"),
"Calanus" = "Calanus")
# Create a new column of data called scientificName based on matches to category
data <- data %>%
dplyr::mutate(., scientificName = case_when(
category %in% scientificName[["blurry"]] ~ "blurry",
category %in% scientificName[["artefact"]] ~ "artefact",
category == scientificName[["Calanus"]] ~ "Calanus",
TRUE ~ NA
))
vpr_export(data, metadata, columnNames, file = "vpr123_station25")
} # }