Example data with zero-inflated variables

An artificial dataset, intended for presenting the extended features of dataMaid, which is a toolset for identifying potential errors in a dataset.

exampleData

Format

A data.frame with 300 observations on the following 6 variables.

addresses

a factor with fictitious US addresses

binomial

a numeric vector with a binomial distributed variable

poisson

a numeric vector with a Poisson distributed variable

gauss

a numeric vector with a Gaussian distributed variable

zigauss

a numeric vector with a zero-inflated Gaussian distributed variable

bpinteraction

a factor with interactions between binomial and poisson values

Source

Artificial data

Examples

# NOT RUN {
isID <- function(v, nMax = NULL, ...) {
  out <- list(problem = FALSE, message = "")
  if (class(v) %in% c("character", "factor", "labelled", "numeric", "integer")) {
    v <- as.character(v)
    lengths <- nchar(v)
    if (all(lengths > 10) & length(unique(lengths)) == 1) {
      out$problem <- TRUE
      out$message <- "Warning: This variable seems to contain ID codes!"
    }
  }
  out
}


countZeros <- function(v, ...) {
  res <- length(which(v == 0))
  summaryResult(list(feature = "No. zeros", result = res, value = res))
}
countZeros <- summaryFunction(countZeros, description = "Count number of zeros",
                              classes = allClasses())
summarize(toyData, numericSummaries = c(defaultNumericSummaries()))


mosaicVisual <- function(v, vnam, doEval) {
  thisCall <- call("mosaicplot", table(v), main = vnam, xlab = "")
  if (doEval) {
    return(eval(thisCall))
  } else return(deparse(thisCall))
}
mosaicVisual <- visualFunction(mosaicVisual,
                               description = "Mosaic plots using graphics",
                               classes = allClasses())

identifyColons <- function(v, nMax = Inf, ... ) {
  v <- unique(na.omit(v))
  problemMessage <- "Note: The following values include colons:"
  problem <- FALSE
  problemValues <- NULL

  problemValues <- v[sapply(gregexpr("[[:xdigit:]]:[[:xdigit:]]", v),
                            function(x) all(x != -1))]

  if (length(problemValues) > 0) {
    problem <- TRUE
  }

  problemStatus <- list(problem = problem,
                        problemValues = problemValues)
  outMessage <- messageGenerator(problemStatus, problemMessage, nMax)

  checkResult(list(problem = problem,
                   message = outMessage,
                   problemValues = problemValues))
}

identifyColons <- checkFunction(identifyColons,
                               description = "Identify non-suffixed nor -prefixed colons",
                               classes = c("character", "factor", "labelled"))
makeDataReport(exampleData, replace = TRUE,
      preChecks = c("isKey", "isEmpty", "isID"),
      allVisuals = "mosaicVisual",
      characterSummaries = c(defaultCharacterSummaries(), "countZeros"),
      factorSummaries = c(defaultFactorSummaries(), "countZeros"),
      labelledSummaries = c(defaultLabelledSummaries(), "countZeros"),
      numericSummaries = c(defaultNumericSummaries(), "countZeros"),
      integerSummaries = c(defaultIntegerSummaries(), "countZeros"),
      characterChecks = c(defaultCharacterChecks(), "identifyColons"),
      factorChecks = c(defaultFactorChecks(), "identifyColons"),
      labelledCheck = c(defaultLabelledChecks(), "identifyColons"))



# }