R/RcppExports.R

In sdcTools/sdcMicro: Statistical Disclosure Control Methods for Anonymization of Data and Risk Estimation

# Generated by using Rcpp::compileAttributes() -> do not edit by hand
# Generator token: 10BE3573-1514-4C36-9D1C-5A225CD40393

LocalRecProg_cpp <- function(data, K_Level_R, FindLowestK_R, ancestor_R, weight_R, range_R, categoryCount_R, LowMemory_R, g_MissingValue_R) {
    .Call(`_sdcMicro_LocalRecProg_cpp`, data, K_Level_R, FindLowestK_R, ancestor_R, weight_R, range_R, categoryCount_R, LowMemory_R, g_MissingValue_R)
}

Mdav <- function(data, data2, g_MissingValue_R, weights_R, g_K_R) {
    .Call(`_sdcMicro_Mdav`, data, data2, g_MissingValue_R, weights_R, g_K_R)
}

measure_hierachical <- function(data) {
    .Call(`_sdcMicro_measure_hierachical`, data)
}

measure_risk_cpp <- function(data, weighted_R, n_key_vars_R, l_recurs_c_R, ldiv_index_R, missing_value_R) {
    .Call(`_sdcMicro_measure_risk_cpp`, data, weighted_R, n_key_vars_R, l_recurs_c_R, ldiv_index_R, missing_value_R)
}

measure_threshold <- function(data, global_risk_R) {
    .Call(`_sdcMicro_measure_threshold`, data, global_risk_R)
}

RankSwap <- function(data, data2, g_MissingValue_R, g_TopRatio_R, g_BottomRatio_R, g_K0_R, g_R0_R, g_P_R, seed_R) {
    .Call(`_sdcMicro_RankSwap`, data, data2, g_MissingValue_R, g_TopRatio_R, g_BottomRatio_R, g_K0_R, g_R0_R, g_P_R, seed_R)
}

Suda2 <- function(data, g_MissingValueALEX_R, MaxK_R, DisFraction_R, elliot_scores) {
    .Call(`_sdcMicro_Suda2`, data, g_MissingValueALEX_R, MaxK_R, DisFraction_R, elliot_scores)
}

cpp_calcSuppInds <- function(inp, checkVals, params) {
    .Call(`_sdcMicro_cpp_calcSuppInds`, inp, checkVals, params)
}

microaggregation_argus_cpp <- function(inp, k, useOptimal) {
    .Call(`_sdcMicro_microaggregation_argus_cpp`, inp, k, useOptimal)
}

rankSwap_argus_cpp <- function(inp, perc) {
    .Call(`_sdcMicro_rankSwap_argus_cpp`, inp, perc)
}

#' @title Targeted Record Swapping
#'
#' @description Applies targeted record swapping on micro data set, see \code{?recordSwap} for details.
#' \cr
#' \strong{NOTE:} This is an internal function called by the R-function \code{recordSwap()}. It's only purpose is to include the C++-function recordSwap() using Rcpp.
#'
#' @param data micro data set containing only integer values. A data.frame or data.table from R needs to be transposed beforehand so that data.size() ~ number of records - data.[0].size ~ number of varaibles per record.
#' \strong{NOTE:} \emph{data has to be ordered by hid beforehand.}
#' @param similar_cpp List where each entry corresponds to column indices of variables in \code{data} which should be considered when swapping households.
#' @param hierarchy column indices of variables in \code{data} which refers to the geographic hierarchy in the micro data set. For instance county > municipality > district.
#' @param risk_variables column indices of variables in \code{data} which will be considered for estimating the risk.
#' @param hid column index in \code{data} which refers to the household identifier.
#' @param k_anonymity integer defining the threshold of high risk households (k-anonymity). This is used as k_anonymity <= counts.
#' @param swaprate double between 0 and 1 defining the proportion of households which should be swapped, see details for more explanations
#' @param risk_threshold double indicating risk threshold above every household needs to be swapped.
#' @param risk vector of vectors containing risks of each individual in each hierarchy level.
#' @param carry_along integer vector indicating additional variables to swap besides to hierarchy variables.
#' These variables do not interfere with the procedure of finding a record to swap with or calculating risk.
#' This parameter is only used at the end of the procedure when swapping the hierarchies.
#' @param log_file_name character, path for writing a log file. The log file contains a list of household IDs (`hid`) which could not have been swapped and is only created if any such households exist.
#' @param seed integer defining the seed for the random number generator, for reproducibility.
#'
#' @return Returns data set with swapped records.
recordSwap_cpp <- function(data, hid, hierarchy, similar_cpp, swaprate, risk, risk_threshold, k_anonymity, risk_variables, carry_along, log_file_name, seed = 123456L) {
    .Call(`_sdcMicro_recordSwap_cpp`, data, hid, hierarchy, similar_cpp, swaprate, risk, risk_threshold, k_anonymity, risk_variables, carry_along, log_file_name, seed)
}

#' @title Define Swap-Levels
#'
#' @description Define hierarchy levels over which record needs to be swapped according to risk variables.
#' \cr
#' \strong{NOTE:} This is an internal function used for testing the C++-function \code{setLevels()} which is applied inside \code{recordSwap()}.
#'
#'
#' @param risk vector of vectors containing risks of each individual in each hierarchy level. \code{risk[0]} returns the vector of risks for the first unit over all hierarchy levels.
#' \code{risk[1]} the vector if risks for all hierarchy level of unit 2, and so on.
#' @param risk_threshold double defining the risk threshold beyond which a record/household needs to be swapped. This is understood as risk>=risk_threshhold.
#'
#' @return Integer vector with hierarchy level over which record needs to be swapped with.
setLevels_cpp <- function(risk, risk_threshold) {
    .Call(`_sdcMicro_setLevels_cpp`, risk, risk_threshold)
}

#' @title Reorder data
#'
#' @description Reorders the data according to a column in the data set.
#' \cr
#' \strong{NOTE:} This is an internal function used for testing the C++-function \code{orderData} which is used inside the C++-function \code{recordSwap()} to speed up performance.
#'
#' @param data micro data set containing only numeric values.
#' @param orderIndex column index in \code{data} refering to the column by which data should be ordered.
#'
#' @return ordered data set.
orderData_cpp <- function(data, orderIndex) {
    .Call(`_sdcMicro_orderData_cpp`, data, orderIndex)
}

#' @title Calculate Risk
#'
#' @description Calculate risk for records to be swapped and donor records.  Risks are defined by 1/counts, where counts is the number of records with the same values for specified \code{risk_variables} in the each geographic hierarchy.
#' This risk will be used as sampling probability for both sampling set and donor set.
#' \cr
#' \strong{NOTE:} This is an internal function used for testing the C++-function \code{setRisk} which is used inside the C++-function \code{recordSwap()}.
#'
#' @param data micro data set containing only numeric values.
#' @param hierarchy column indices of variables in \code{data} which refere to the geographic hierarchy in the micro data set. For instance county > municipality > district.
#' @param risk_variables column indices of variables in \code{data} which will be considered for estimating the risk.
#' @param hid column index in \code{data} which refers to the household identifier.
#'
setRisk_cpp <- function(data, hierarchy, risk_variables, hid) {
    .Call(`_sdcMicro_setRisk_cpp`, data, hierarchy, risk_variables, hid)
}

#' @title Random Sampling
#'
#' @description Randomly select records given a probability weight vector \code{prob}.
#' \cr
#' \strong{NOTE:} This is an internal function used for testing the C++-function \code{randSample} which is used inside the C++-function \code{recordSwap()}.
#'
#' @param ID vector containing record IDs from which to sample
#' @param N integer defining the number of records to be sampled
#' @param prob a vector of probability weights for obtaining the elements of the vector being sampled.
#' @param IDused vector containing IDs which must not be sampled
#' @param seed integer setting the sampling seed
#'
randSample_cpp <- function(ID, N, prob, IDused, seed) {
    .Call(`_sdcMicro_randSample_cpp`, ID, N, prob, IDused, seed)
}

#' @title Distribute number of swaps
#'
#' @description Distribute number of swaps across lowest hierarchy level according to a predefined \code{swaprate}. The swaprate is applied such that a single swap counts as swapping 2 households.
#' Number of swaps are randomly rounded up or down, if needed, such that the total number of swaps is in coherence with the swaprate.
#' \cr
#' \strong{NOTE:} This is an internal function used for testing the C++-function \code{distributeDraws} which is used inside the C++-function \code{recordSwap()}.
#'
#' @param data micro data containing the hierarchy levels and household ID
#' @param hierarchy column indices of variables in \code{data} which refers to the geographic hierarchy in the micro data set. For instance county > municipality > district.
#' @param hid column index in \code{data} which refers to the household identifier.
#' @param swaprate double between 0 and 1 defining the proportion of households which should be swapped, see details for more explanations
#' @param seed integer setting the sampling seed
#'
distributeDraws_cpp <- function(data, hierarchy, hid, swaprate, seed = 123456L) {
    .Call(`_sdcMicro_distributeDraws_cpp`, data, hierarchy, hid, swaprate, seed)
}

distributeDraws2_cpp <- function(data, risk, hierarchy, hid, swaprate, seed = 123456L) {
    .Call(`_sdcMicro_distributeDraws2_cpp`, data, risk, hierarchy, hid, swaprate, seed)
}

#' @title Random sample for donor records
#'
#' @description Randomly select donor records given a probability weight vector. This sampling procedure is implemented differently than \code{\link{randSample_cpp}} to speed up performance of C++-function \code{recordSwap()}.
#' \cr
#' \strong{NOTE:} This is an internal function used for testing the C++-function \code{sampleDonor} which is used inside the C++-function \code{recordSwap()}.
#'
#' @param data micro data containing the hierarchy levels and household ID
#' @param similar_cpp List where each entry corresponds to column indices of variables in \code{data} which should be considered when swapping households.
#' @param hid column index in \code{data} which refers to the household identifier.
#' @param IDswap vector containing records for which a donor needs to be sampled
#' @param IDswap_pool_vec set from which `IDswap` was drawn
#' @param prob a vector of probability weights for obtaining the elements of the vector being sampled.
#' @param seed integer setting the sampling seed
#'
sampleDonor_cpp <- function(data, similar_cpp, hid, IDswap, IDswap_pool_vec, prob, seed = 123456L) {
    .Call(`_sdcMicro_sampleDonor_cpp`, data, similar_cpp, hid, IDswap, IDswap_pool_vec, prob, seed)
}

#' @title Distribute
#'
#' @description Distribute `totalDraws` using ratio/probability vector `inputRatio` and randomly round each entry up or down such that the distribution results in an integer vector.
#' Returns an integer vector containing the number of units in `totalDraws` distributetd according to proportions in `inputRatio`.
#' \cr
#' \strong{NOTE:} This is an internal function used for testing the C++-function \code{distributeRandom} which is used inside the C++-function \code{recordSwap()}.
#'
#' @param inputRatio vector containing ratios which are used to distribute number units in `totalDraws`.
#' @param totalDraws number of units to distribute
#' @param seed integer setting the sampling seed
#'
distributeRandom_cpp <- function(inputRatio, totalDraws, seed) {
    .Call(`_sdcMicro_distributeRandom_cpp`, inputRatio, totalDraws, seed)
}

testLoop_cpp <- function(inputGroup, risk) {
    .Call(`_sdcMicro_testLoop_cpp`, inputGroup, risk)
}

test_prioqueue <- function(x_vec, prob, mustSwap_vec, n, seed) {
    .Call(`_sdcMicro_test_prioqueue`, x_vec, prob, mustSwap_vec, n, seed)
}

test_comparator <- function(x_vec, prob, mustSwap_vec, n, seed) {
    .Call(`_sdcMicro_test_comparator`, x_vec, prob, mustSwap_vec, n, seed)
}