Detailed Data Cleaning Report of package bdclean'

In bdclean: A User-Friendly Biodiversity Data Cleaning App for the Inexperienced R User

knitr::opts_chunk$set(echo = TRUE)
suppressPackageStartupMessages(library(knitr))
suppressPackageStartupMessages(library(tools))

Data Summary

kable(data.summary)

Quality Checks Summary

spatialChecks <- 0
temporalChecks <- 0
taxonChecks <- 0
otherChecks <- 0

for (question in checks.records) {
    for (check in question$checks) {
        if (check$checkCategory == 'spatial') {
            spatialChecks = spatialChecks + 1
        } else if (check$checkCategory == 'temporal') {
            temporalChecks = temporalChecks + 1
        } else if (check$checkCategory == 'taxonomic') {
            taxonChecks = taxonChecks + 1
        } else {
            otherChecks = otherChecks + 1
        }
    }
}

Checks <-
    c(
        'Taxonomical quality Checks',
        'Spatial quality Checks',
        'Temporal quality Checks',
        'Total quality Checks'
    )
Count <-
    c(
        taxonChecks,
        spatialChecks,
        temporalChecks,
        (taxonChecks + spatialChecks + temporalChecks + otherChecks)
    )
check.summary <- data.frame(Checks, Count)
kable(check.summary)

Quality Checks

index <- 1
checkCount <- 1
for (question in checks.records) {
    cat(paste('###', index, '. ', question$question, '\n',  sep = ''))
    cat('\n')

    cat(paste('Received Response: ', question$answer, '\n', sep = ''))
    cat('\n')

    checkIndex <- 1
    for (check in question$checks) {
        cat(paste(
            '####',
            'Quality Check ',
            checkCount,
            ': ',
            names(question$checks[checkIndex]),
            sep = ''
        ))

        Type <-
            c('Description',
              'Sample Pass Data',
              'Sample Fail Data',
              'Target DwC Field',
              'Check Category',
              'Flagged Records')

        Value <-
            c(
                check$description,
                check$samplePassData,
                check$sampleFailData,
                check$targetDWCField,
                toTitleCase(check$checkCategory),
                check$affectedData
            )

        check.data.summary <- data.frame(Type, Value)
        print(kable(check.data.summary))
        cat('\n')
        checkIndex <- checkIndex + 1
        checkCount <- checkCount + 1
    }
    index <- index + 1
}

References

Tomer Gueta, Vijay Barve, Thiloshon Nagarajah, Ashwin Agrawal and Carmel Yohay (2018). bdclean: Biodiversity Data Cleaning Workflow. R package version 0.0.6.

R Core Team (2012). R: A language and environment for statistical computing. R Foundation for Statistical Computing, Vienna, Austria. ISBN 3-900051-07-0, URL http://www.R-project.org/

bdclean documentation built on May 1, 2019, 10:54 p.m.