sdcTable (version 0.29)

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 levels and structure in both tables

  • first element: character vector of length 1 specifying the variable name in argument objectA

  • second element: character vector of length 1 specifying the variable name in argument objectB

  • third element: character vector of length 1 being with keyword ALL

• List-elements of length 4: Variable has different codes and levels in tables objectA and objectB

  • first element: character vector of length 1 specifying the variable name in argument objectA

  • second element: character vector of length 1 specifying the variable name in argument objectB

  • third element: character vector defining codes within objectA

  • fourth element: character vector with length that equals the length of the third list-element. The vector defines codes of the variable in objectB that match the codes given in the third list-element for objectA.

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

# NOT RUN {
# 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
d_region <- hier_create(root = "Tot", nodes = c("R1", "R2"))

# variable 'gender': exists in both datasets
d_gender <- hier_create(root = "Tot", nodes = c("m", "f"))

# variable 'eco1': exists only in microDat1
d_eco1 <- hier_create(root = "Tot", nodes = c("A", "B"))
d_eco1 <- hier_add(d_eco1, root = "A", nodes = c("Aa", "Ab"))
d_eco1 <- hier_add(d_eco1, root = "B", nodes = c("Ba", "Bb"))

# variable 'ecoNew': exists only in microDat2
d_eco2 <- hier_create(root = "Tot", nodes = c("C", "D"))
d_eco2 <- hier_add(d_eco2, root = "C", nodes = c("Ca", "Cb", "Cc"))
d_eco2 <- hier_add(d_eco2, root = "D", nodes = c("Da", "Db", "Dc"))

# creating objects holding information on dimensions
dl1 <- list(gender = d_gender, ecoOld = d_eco1)
dl2 <- list(region = d_region, gender = d_gender, ecoNew = d_eco2)

# creating input objects for further processing. For details have a look at
# \code{\link{makeProblem}}.
p1 <- makeProblem(
  data = microData1, 
  dimList = dl1, 
  dimVarInd = 1:2,
  numVarInd = 3
)
p2 <- makeProblem(
  data = microData2, 
  dimList = dl2, 
  dimVarInd = 1:3,
  numVarInd = 4
)

# the cell specified by gender == "Tot" and ecoOld == "A"
# is one of the common cells! -> we mark it as primary suppression
p1 <- changeCellStatus(
  object = p1, 
  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
p2 <- changeCellStatus(
  object = p2, 
  characteristics = c("Tot", "f", "C"),
  varNames = c("region", "gender", "ecoNew"), 
  rule = "u", 
  verbose = FALSE
)

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

# variable "gender"
common_cells$v.gender <- list()
common_cells$v.gender[[1]] <- "gender" # variable name in "p1"
common_cells$v.gender[[2]] <- "gender" # variable name in "p2"
# "gender" has equal characteristics on both datasets -> keyword "ALL"
common_cells$v.gender[[3]] <- "ALL"

# variables: "ecoOld" and "ecoNew"
common_cells$v.eco <- list()
common_cells$v.eco[[1]] <- "ecoOld"   # variable name in "p1"
common_cells$v.eco[[2]] <- "ecoNew"   # variable name in "p2"

# vector of common characteristics: "A" and "B" in variable "ecoOld" in 'p1'
common_cells$v.eco[[3]] <- c("A", "B")
# correspond to characteristics "C" and "D" in variable "ecoNew" in "p2"
common_cells$v.eco[[4]] <- c("C", "D")

# protect the linked data
result <- protectLinkedTables(
  objectA = p1, 
  objectB = p2, 
  commonCells = common_cells, 
  method = "HITAS", 
  verbose = TRUE
)

# having a look at the results
result.tab1 <- result[[1]]
result.tab2 <- result[[2]]
summary(result.tab1)
summary(result.tab2)
# }
# NOT RUN {
# }