sdcTable (version 0.20.5)

protectLinkedTables: protect two sdcProblem-class objects that have common cells

Description

protectLinkedTables can be used to protect tables, that have common cells. It is of course required that after the anonymization process has finished, all common cells have the same anonymization state in both tables.

Usage

protectLinkedTables(objectA, objectB, commonCells, method, ...)

Arguments

objectA

a sdcProblem-class object

objectB

a sdcProblem-class object

commonCells

a list object defining common cells in objectA and objectB. For each variable that has one or more common codes in both tables, a list element needs to be specified.

• List-elements of length 3: Variable has exact same leve

method

a character vector of length 1 specifying the algorithm that should be used to protect the primary sensitive table cells. Allowed values are:

• HITAS:
• SIMPLEHEURISTIC:
• OPT:

...

additional arguments to control the secondary cell suppression algorithm. For details, see protectTable.

Value

• a list of length 2 with each list-element being an safeObj-class object

See Also

protectTable

Examples

# load micro data for further processing
sp <- searchpaths()
fn <- paste(sp[grep("sdcTable", sp)], "/data/microData2.RData", sep="")
microData <- get(load(fn))

# table1: defined by variables 'gender' and 'ecoOld'
microData1 <- microData[,c(2,3,5)]

# table2: defined by variables 'region', 'gender' and 'ecoNew'
microData2 <- microData[,c(1,2,4,5)]

# we need to create information on the hierarchies
# variable 'region': exists only in microDat2
dim.region <- data.frame(h=c('@','@@','@@'), l=c('Tot', 'R1','R2'))

# variable 'gender': exists in both datasets
dim.gender <- data.frame(h=c('@','@@','@@'), l=c('Tot', 'm','f'))

# variable 'ecoOld': exists only in microDat1
dim.ecoOld <- data.frame(
 h=c('@','@@','@@@','@@@','@@','@@@','@@@'),
 l=c('Tot','A','Aa','Ab','B','Ba','Bb'))

# variable 'ecoNew': exists only in microDat2
dim.ecoNew <- data.frame(
 h=c('@','@@','@@@','@@@','@@@','@@','@@@','@@@','@@@'),
 l=c('Tot','C','Ca','Cb','Cc','D','Da','Db','Dc'))

# creating objects holding information on dimensions
dimList1 <- list(gender=dim.gender, ecoOld=dim.ecoOld)
dimList2 <- list(region=dim.region, gender=dim.gender, ecoNew=dim.ecoNew)

# creating input objects for further processing. For details have a look at
# \code{\link{makeProblem}}.
problem1 <- makeProblem(data=microData1, dimList=dimList1, dimVarInd=c(1,2),
         numVarInd=3)
problem2 <- makeProblem(data=microData2, dimList=dimList2, dimVarInd=c(1,2,3),
         numVarInd=4)

# the cell specified by gender=='Tot' and ecoOld=='A'
# is one of the common cells! -> we mark it as primary suppression
problem1 <- changeCellStatus(problem1, characteristics=c('Tot', 'A'),
     varNames=c('gender','ecoOld'), rule='u', verbose=FALSE)

# the cell specified by region=='Tot' and gender=='f' and ecoNew=='C'
# is one of the common cells! -> we mark it as primary suppression
problem2 <- changeCellStatus(problem2, characteristics=c('Tot', 'f', 'C'),
 varNames=c('region','gender', 'ecoNew'), rule='u', verbose=FALSE)

# specifying input to define common cells
commonCells <- list()

# variable "gender"
commonCells$v.gender <- list()
commonCells$v.gender[[1]] <- 'gender' # variable name in 'problem1'
commonCells$v.gender[[2]] <- 'gender' # variable name in 'problem2'
# 'gender' has equal characteristics on both datasets -> keyword 'ALL'
commonCells$v.gender[[3]] <- 'ALL'

# variable: ecoOld and ecoNew
commonCells$v.eco <- list()
commonCells$v.eco[[1]] <- 'ecoOld'   # variable name in 'problem1'
commonCells$v.eco[[2]] <- 'ecoNew'   # variable name in 'problem2'

# vector of common characteristics: A and B in variable 'ecoOld' in 'problem1'
commonCells$v.eco[[3]] <- c("A","B")
# correspond to characteristics 'C' and 'D' in variable 'ecoNew' in 'problem2'
commonCells$v.eco[[4]] <- c("C","D")

# protect the linked data
result <- protectLinkedTables(problem1, problem2, commonCells, method='HITAS', verbose=TRUE)

# having a look at the results
result.tab1 <- result[[1]]
result.tab2 <- result[[2]]
summary(result.tab1)
summary(result.tab2)