This function allows to generate required perturbation parameters that are used to perturb count variables.
ck_params_cnts(ptab, path = NULL)an object created with ptable::create_ptable(),
or ptable::create_cnt_ptable()
a scalar character specifying a path to which the parameters created with this functions should be written to (in yaml format)
an object suitable as input to method $params_cnts_set() for the perturbation
of counts and frequencies.
This function uses functionality from package
ptable (https://github.com/sdcTools/ptable), expecially
ptable::create_ptable() and
ptable::create_cnt_ptable(). More detailed information on the parameters
is available from the respective help-pages of these functions.
# \donttest{
x <- ck_create_testdata()
# create some 0/1 variables that should be perturbed later
x[, cnt_females := ifelse(sex == "male", 0, 1)]
#> urbrur roof walls water electcon relat sex age hhcivil expend
#> 1: 2 4 3 3 1 1 male age_group3 2 9093
#> 2: 2 4 3 3 1 2 female age_group3 2 2734
#> 3: 2 4 3 3 1 3 male age_group1 1 2652
#> 4: 2 4 3 3 1 3 male age_group1 1 1807
#> 5: 2 4 2 3 1 1 male age_group4 2 671
#> ---
#> 4576: 2 4 3 4 1 2 female age_group3 2 3696
#> 4577: 2 4 3 4 1 3 male age_group1 1 282
#> 4578: 2 4 3 4 1 3 male age_group1 1 840
#> 4579: 2 4 3 4 1 3 female age_group1 1 6258
#> 4580: 2 4 3 4 1 3 male age_group1 1 7019
#> income savings ori_hid sampling_weight household_weights cnt_females
#> 1: 5780 12 1 66 25.00000 0
#> 2: 2530 28 1 60 25.00000 1
#> 3: 6920 550 1 87 25.00000 0
#> 4: 7960 870 1 71 25.00000 0
#> 5: 9030 20 2 41 16.66667 0
#> ---
#> 4576: 7900 278 1000 40 16.66667 1
#> 4577: 1420 987 1000 27 16.66667 0
#> 4578: 8900 684 1000 95 16.66667 0
#> 4579: 3880 294 1000 71 16.66667 1
#> 4580: 4830 911 1000 23 16.66667 0
x[, cnt_males := ifelse(sex == "male", 1, 0)]
#> urbrur roof walls water electcon relat sex age hhcivil expend
#> 1: 2 4 3 3 1 1 male age_group3 2 9093
#> 2: 2 4 3 3 1 2 female age_group3 2 2734
#> 3: 2 4 3 3 1 3 male age_group1 1 2652
#> 4: 2 4 3 3 1 3 male age_group1 1 1807
#> 5: 2 4 2 3 1 1 male age_group4 2 671
#> ---
#> 4576: 2 4 3 4 1 2 female age_group3 2 3696
#> 4577: 2 4 3 4 1 3 male age_group1 1 282
#> 4578: 2 4 3 4 1 3 male age_group1 1 840
#> 4579: 2 4 3 4 1 3 female age_group1 1 6258
#> 4580: 2 4 3 4 1 3 male age_group1 1 7019
#> income savings ori_hid sampling_weight household_weights cnt_females
#> 1: 5780 12 1 66 25.00000 0
#> 2: 2530 28 1 60 25.00000 1
#> 3: 6920 550 1 87 25.00000 0
#> 4: 7960 870 1 71 25.00000 0
#> 5: 9030 20 2 41 16.66667 0
#> ---
#> 4576: 7900 278 1000 40 16.66667 1
#> 4577: 1420 987 1000 27 16.66667 0
#> 4578: 8900 684 1000 95 16.66667 0
#> 4579: 3880 294 1000 71 16.66667 1
#> 4580: 4830 911 1000 23 16.66667 0
#> cnt_males
#> 1: 1
#> 2: 0
#> 3: 1
#> 4: 1
#> 5: 1
#> ---
#> 4576: 0
#> 4577: 1
#> 4578: 1
#> 4579: 0
#> 4580: 1
x[, cnt_highincome := ifelse(income >= 9000, 1, 0)]
#> urbrur roof walls water electcon relat sex age hhcivil expend
#> 1: 2 4 3 3 1 1 male age_group3 2 9093
#> 2: 2 4 3 3 1 2 female age_group3 2 2734
#> 3: 2 4 3 3 1 3 male age_group1 1 2652
#> 4: 2 4 3 3 1 3 male age_group1 1 1807
#> 5: 2 4 2 3 1 1 male age_group4 2 671
#> ---
#> 4576: 2 4 3 4 1 2 female age_group3 2 3696
#> 4577: 2 4 3 4 1 3 male age_group1 1 282
#> 4578: 2 4 3 4 1 3 male age_group1 1 840
#> 4579: 2 4 3 4 1 3 female age_group1 1 6258
#> 4580: 2 4 3 4 1 3 male age_group1 1 7019
#> income savings ori_hid sampling_weight household_weights cnt_females
#> 1: 5780 12 1 66 25.00000 0
#> 2: 2530 28 1 60 25.00000 1
#> 3: 6920 550 1 87 25.00000 0
#> 4: 7960 870 1 71 25.00000 0
#> 5: 9030 20 2 41 16.66667 0
#> ---
#> 4576: 7900 278 1000 40 16.66667 1
#> 4577: 1420 987 1000 27 16.66667 0
#> 4578: 8900 684 1000 95 16.66667 0
#> 4579: 3880 294 1000 71 16.66667 1
#> 4580: 4830 911 1000 23 16.66667 0
#> cnt_males cnt_highincome
#> 1: 1 0
#> 2: 0 0
#> 3: 1 0
#> 4: 1 0
#> 5: 1 1
#> ---
#> 4576: 0 0
#> 4577: 1 0
#> 4578: 1 0
#> 4579: 0 0
#> 4580: 1 0
# a variable with positive and negative contributions
x[, mixed := sample(-10:10, nrow(x), replace = TRUE)]
#> urbrur roof walls water electcon relat sex age hhcivil expend
#> 1: 2 4 3 3 1 1 male age_group3 2 9093
#> 2: 2 4 3 3 1 2 female age_group3 2 2734
#> 3: 2 4 3 3 1 3 male age_group1 1 2652
#> 4: 2 4 3 3 1 3 male age_group1 1 1807
#> 5: 2 4 2 3 1 1 male age_group4 2 671
#> ---
#> 4576: 2 4 3 4 1 2 female age_group3 2 3696
#> 4577: 2 4 3 4 1 3 male age_group1 1 282
#> 4578: 2 4 3 4 1 3 male age_group1 1 840
#> 4579: 2 4 3 4 1 3 female age_group1 1 6258
#> 4580: 2 4 3 4 1 3 male age_group1 1 7019
#> income savings ori_hid sampling_weight household_weights cnt_females
#> 1: 5780 12 1 66 25.00000 0
#> 2: 2530 28 1 60 25.00000 1
#> 3: 6920 550 1 87 25.00000 0
#> 4: 7960 870 1 71 25.00000 0
#> 5: 9030 20 2 41 16.66667 0
#> ---
#> 4576: 7900 278 1000 40 16.66667 1
#> 4577: 1420 987 1000 27 16.66667 0
#> 4578: 8900 684 1000 95 16.66667 0
#> 4579: 3880 294 1000 71 16.66667 1
#> 4580: 4830 911 1000 23 16.66667 0
#> cnt_males cnt_highincome mixed
#> 1: 1 0 6
#> 2: 0 0 -9
#> 3: 1 0 4
#> 4: 1 0 0
#> 5: 1 1 -7
#> ---
#> 4576: 0 0 4
#> 4577: 1 0 7
#> 4578: 1 0 -9
#> 4579: 0 0 -4
#> 4580: 1 0 -3
# create record keys
x$rkey <- ck_generate_rkeys(dat = x)
# define required inputs
# hierarchy with some bogus codes
d_sex <- hier_create(root = "Total", nodes = c("male", "female"))
d_sex <- hier_add(d_sex, root = "female", "f")
d_sex <- hier_add(d_sex, root = "male", "m")
d_age <- hier_create(root = "Total", nodes = paste0("age_group", 1:6))
d_age <- hier_add(d_age, root = "age_group1", "ag1a")
d_age <- hier_add(d_age, root = "age_group2", "ag2a")
# define the cell key object
countvars <- c("cnt_females", "cnt_males", "cnt_highincome")
numvars <- c("expend", "income", "savings", "mixed")
tab <- ck_setup(
x = x,
rkey = "rkey",
dims = list(sex = d_sex, age = d_age),
w = "sampling_weight",
countvars = countvars,
numvars = numvars)
#> computing contributing indices | rawdata <--> table; this might take a while
# show some information about this table instance
tab$print() # identical with print(tab)
#> ── Table Information ───────────────────────────────────────────────────────────
#> ✔ 45 cells in 2 dimensions ('sex', 'age')
#> ✔ weights: yes
#> ── Tabulated / Perturbed countvars ─────────────────────────────────────────────
#> ☐ 'total'
#> ☐ 'cnt_females'
#> ☐ 'cnt_males'
#> ☐ 'cnt_highincome'
#> ── Tabulated / Perturbed numvars ───────────────────────────────────────────────
#> ☐ 'expend'
#> ☐ 'income'
#> ☐ 'savings'
#> ☐ 'mixed'
# information about the hierarchies
tab$hierarchy_info()
#> $sex
#> code level is_leaf parent
#> 1: Total 1 FALSE Total
#> 2: male 2 FALSE Total
#> 3: m 3 TRUE male
#> 4: female 2 FALSE Total
#> 5: f 3 TRUE female
#>
#> $age
#> code level is_leaf parent
#> 1: Total 1 FALSE Total
#> 2: age_group1 2 FALSE Total
#> 3: ag1a 3 TRUE age_group1
#> 4: age_group2 2 FALSE Total
#> 5: ag2a 3 TRUE age_group2
#> 6: age_group3 2 TRUE Total
#> 7: age_group4 2 TRUE Total
#> 8: age_group5 2 TRUE Total
#> 9: age_group6 2 TRUE Total
#>
# which variables have been defined?
tab$allvars()
#> $cntvars
#> [1] "total" "cnt_females" "cnt_males" "cnt_highincome"
#>
#> $numvars
#> [1] "expend" "income" "savings" "mixed"
#>
# count variables
tab$cntvars()
#> [1] "total" "cnt_females" "cnt_males" "cnt_highincome"
# continuous variables
tab$numvars()
#> [1] "expend" "income" "savings" "mixed"
# create perturbation parameters for "total" variable and
# write to yaml-file
# create a ptable using functionality from the ptable-pkg
f_yaml <- tempfile(fileext = ".yaml")
p_cnts1 <- ck_params_cnts(
ptab = ptable::pt_ex_cnts(),
path = f_yaml)
#> yaml configuration '/tmp/RtmpV7PINT/file19627d88b994.yaml' successfully written.
# read parameters from yaml-file and set them for variable `"total"`
p_cnts1 <- ck_read_yaml(path = f_yaml)
tab$params_cnts_set(val = p_cnts1, v = "total")
#> --> setting perturbation parameters for variable 'total'
# create alternative perturbation parameters by specifying parameters
para2 <- ptable::create_cnt_ptable(
D = 8, V = 3, js = 2, create = FALSE)
p_cnts2 <- ck_params_cnts(ptab = para2)
# use these ptable it for the remaining variables
tab$params_cnts_set(val = p_cnts2, v = countvars)
#> --> setting perturbation parameters for variable 'cnt_females'
#> --> setting perturbation parameters for variable 'cnt_males'
#> --> setting perturbation parameters for variable 'cnt_highincome'
# perturb a variable
tab$perturb(v = "total")
#> Count variable 'total' was perturbed.
# multiple variables can be perturbed as well
tab$perturb(v = c("cnt_males", "cnt_highincome"))
#> Count variable 'cnt_males' was perturbed.
#> Count variable 'cnt_highincome' was perturbed.
# return weighted and unweighted results
tab$freqtab(v = c("total", "cnt_males"))
#> sex age vname uwc wc puwc pwc
#> 1: Total Total total 4580 272100 4581 272159.4105
#> 2: Total age_group1 total 1969 117044 1970 117103.4434
#> 3: Total ag1a total 1969 117044 1970 117103.4434
#> 4: Total age_group2 total 1143 67505 1141 67386.8810
#> 5: Total ag2a total 1143 67505 1141 67386.8810
#> 6: Total age_group3 total 864 51289 866 51407.7245
#> 7: Total age_group4 total 423 25206 423 25206.0000
#> 8: Total age_group5 total 168 10140 167 10079.6429
#> 9: Total age_group6 total 13 916 13 916.0000
#> 10: male Total total 2296 135673 2296 135673.0000
#> 11: m Total total 2296 135673 2296 135673.0000
#> 12: male age_group1 total 1015 60163 1015 60163.0000
#> 13: m age_group1 total 1015 60163 1015 60163.0000
#> 14: male ag1a total 1015 60163 1015 60163.0000
#> 15: m ag1a total 1015 60163 1015 60163.0000
#> 16: male age_group2 total 571 33439 571 33439.0000
#> 17: m age_group2 total 571 33439 571 33439.0000
#> 18: male ag2a total 571 33439 571 33439.0000
#> 19: m ag2a total 571 33439 571 33439.0000
#> 20: male age_group3 total 424 25289 423 25229.3561
#> 21: m age_group3 total 424 25289 423 25229.3561
#> 22: male age_group4 total 195 11353 196 11411.2205
#> 23: m age_group4 total 195 11353 196 11411.2205
#> 24: male age_group5 total 84 5026 84 5026.0000
#> 25: m age_group5 total 84 5026 84 5026.0000
#> 26: male age_group6 total 7 403 8 460.5714
#> 27: m age_group6 total 7 403 8 460.5714
#> 28: female Total total 2284 136427 2284 136427.0000
#> 29: f Total total 2284 136427 2284 136427.0000
#> 30: female age_group1 total 954 56881 953 56821.3763
#> 31: f age_group1 total 954 56881 953 56821.3763
#> 32: female ag1a total 954 56881 953 56821.3763
#> 33: f ag1a total 954 56881 953 56821.3763
#> 34: female age_group2 total 572 34066 572 34066.0000
#> 35: f age_group2 total 572 34066 572 34066.0000
#> 36: female ag2a total 572 34066 572 34066.0000
#> 37: f ag2a total 572 34066 572 34066.0000
#> 38: female age_group3 total 440 26000 441 26059.0909
#> 39: f age_group3 total 440 26000 441 26059.0909
#> 40: female age_group4 total 228 13853 228 13853.0000
#> 41: f age_group4 total 228 13853 228 13853.0000
#> 42: female age_group5 total 84 5114 85 5174.8810
#> 43: f age_group5 total 84 5114 85 5174.8810
#> 44: female age_group6 total 6 513 6 513.0000
#> 45: f age_group6 total 6 513 6 513.0000
#> 46: Total Total cnt_males 2296 135673 2295 135613.9090
#> 47: Total age_group1 cnt_males 1015 60163 1016 60222.2739
#> 48: Total ag1a cnt_males 1015 60163 1016 60222.2739
#> 49: Total age_group2 cnt_males 571 33439 570 33380.4378
#> 50: Total ag2a cnt_males 571 33439 570 33380.4378
#> 51: Total age_group3 cnt_males 424 25289 422 25169.7123
#> 52: Total age_group4 cnt_males 195 11353 197 11469.4410
#> 53: Total age_group5 cnt_males 84 5026 84 5026.0000
#> 54: Total age_group6 cnt_males 7 403 8 460.5714
#> 55: male Total cnt_males 2296 135673 2295 135613.9090
#> 56: m Total cnt_males 2296 135673 2295 135613.9090
#> 57: male age_group1 cnt_males 1015 60163 1016 60222.2739
#> 58: m age_group1 cnt_males 1015 60163 1016 60222.2739
#> 59: male ag1a cnt_males 1015 60163 1016 60222.2739
#> 60: m ag1a cnt_males 1015 60163 1016 60222.2739
#> 61: male age_group2 cnt_males 571 33439 570 33380.4378
#> 62: m age_group2 cnt_males 571 33439 570 33380.4378
#> 63: male ag2a cnt_males 571 33439 570 33380.4378
#> 64: m ag2a cnt_males 571 33439 570 33380.4378
#> 65: male age_group3 cnt_males 424 25289 422 25169.7123
#> 66: m age_group3 cnt_males 424 25289 422 25169.7123
#> 67: male age_group4 cnt_males 195 11353 197 11469.4410
#> 68: m age_group4 cnt_males 195 11353 197 11469.4410
#> 69: male age_group5 cnt_males 84 5026 84 5026.0000
#> 70: m age_group5 cnt_males 84 5026 84 5026.0000
#> 71: male age_group6 cnt_males 7 403 8 460.5714
#> 72: m age_group6 cnt_males 7 403 8 460.5714
#> 73: female Total cnt_males 0 0 0 0.0000
#> 74: f Total cnt_males 0 0 0 0.0000
#> 75: female age_group1 cnt_males 0 0 0 0.0000
#> 76: f age_group1 cnt_males 0 0 0 0.0000
#> 77: female ag1a cnt_males 0 0 0 0.0000
#> 78: f ag1a cnt_males 0 0 0 0.0000
#> 79: female age_group2 cnt_males 0 0 0 0.0000
#> 80: f age_group2 cnt_males 0 0 0 0.0000
#> 81: female ag2a cnt_males 0 0 0 0.0000
#> 82: f ag2a cnt_males 0 0 0 0.0000
#> 83: female age_group3 cnt_males 0 0 0 0.0000
#> 84: f age_group3 cnt_males 0 0 0 0.0000
#> 85: female age_group4 cnt_males 0 0 0 0.0000
#> 86: f age_group4 cnt_males 0 0 0 0.0000
#> 87: female age_group5 cnt_males 0 0 0 0.0000
#> 88: f age_group5 cnt_males 0 0 0 0.0000
#> 89: female age_group6 cnt_males 0 0 0 0.0000
#> 90: f age_group6 cnt_males 0 0 0 0.0000
#> sex age vname uwc wc puwc pwc
# numerical variables (positive variables using flex-function)
# we also write the config to a yaml file
f_yaml <- tempfile(fileext = ".yaml")
# create a ptable using functionality from the ptable-pkg
# a single ptable for all cells
ptab1 <- ptable::pt_ex_nums(parity = TRUE, separation = FALSE)
# a single ptab for all cells except for very small ones
ptab2 <- ptable::pt_ex_nums(parity = TRUE, separation = TRUE)
# different ptables for cells with even/odd number of contributors
# and very small cells
ptab3 <- ptable::pt_ex_nums(parity = FALSE, separation = TRUE)
p_nums1 <- ck_params_nums(
ptab = ptab1,
type = "top_contr",
top_k = 3,
mult_params = ck_flexparams(
fp = 1000,
p = c(0.30, 0.03),
epsilon = c(1, 0.5, 0.2),
q = 3),
mu_c = 2,
same_key = FALSE,
use_zero_rkeys = FALSE,
path = f_yaml)
#> yaml configuration '/tmp/RtmpV7PINT/file19627c3e8f63.yaml' successfully written.
# we read the parameters from the yaml-file
p_nums1 <- ck_read_yaml(path = f_yaml)
# for variables with positive and negative values
p_nums2 <- ck_params_nums(
ptab = ptab2,
type = "top_contr",
top_k = 3,
mult_params = ck_flexparams(
fp = 1000,
p = c(0.15, 0.02),
epsilon = c(1, 0.4, 0.15),
q = 3),
mu_c = 2,
same_key = FALSE)
# simple perturbation parameters (not using the flex-function approach)
p_nums3 <- ck_params_nums(
ptab = ptab3,
type = "mean",
mult_params = ck_simpleparams(p = 0.25),
mu_c = 2,
same_key = FALSE)
# use `p_nums1` for all variables
tab$params_nums_set(p_nums1, c("savings", "income", "expend"))
#> --> setting perturbation parameters for variable 'savings'
#> --> setting perturbation parameters for variable 'income'
#> --> setting perturbation parameters for variable 'expend'
# use different parameters for variable `mixed`
tab$params_nums_set(p_nums2, v = "mixed")
#> --> setting perturbation parameters for variable 'mixed'
# identify sensitive cells to which extra protection (`mu_c`) is added.
tab$supp_p(v = "income", p = 85)
#> computing contributing indices | rawdata <--> table; this might take a while
#> p%-rule: 0 new sensitive cells (incl. duplicates) found (total: 0)
tab$supp_pq(v = "income", p = 85, q = 90)
#> computing contributing indices | rawdata <--> table; this might take a while
#> pq-rule: 0 new sensitive cells (incl. duplicates) found (total: 0)
tab$supp_nk(v = "income", n = 2, k = 90)
#> computing contributing indices | rawdata <--> table; this might take a while
#> nk-rule: 0 new sensitive cells (incl. duplicates) found (total: 0)
tab$supp_freq(v = "income", n = 14, weighted = FALSE)
#> freq-rule: 5 new sensitive cells (incl. duplicates) found (total: 5)
tab$supp_val(v = "income", n = 10000, weighted = TRUE)
#> val-rule: 0 new sensitive cells (incl. duplicates) found (total: 5)
tab$supp_cells(
v = "income",
inp = data.frame(
sex = c("female", "female"),
"age" = c("age_group1", "age_group3")
)
)
#> cell-rule: 2 new sensitive cells (incl. duplicates) found (total: 7)
# perturb variables
tab$perturb(v = c("income", "savings"))
#> Numeric variable 'income' was perturbed.
#> Numeric variable 'savings' was perturbed.
# extract results
tab$numtab("income", mean_before_sum = TRUE)
#> sex age vname uws ws pws
#> 1: Total Total income 22952978 1359983951 1360134579
#> 2: Total age_group1 income 9810547 577588504 577478133
#> 3: Total ag1a income 9810547 577588504 577478133
#> 4: Total age_group2 income 5692119 339267248 339210791
#> 5: Total ag2a income 5692119 339267248 339210791
#> 6: Total age_group3 income 4406946 260501177 260435755
#> 7: Total age_group4 income 2133543 128141218 128105840
#> 8: Total age_group5 income 848151 50483631 50626796
#> 9: Total age_group6 income 61672 4002173 3855253
#> 10: male Total income 11262049 661571824 661559373
#> 11: m Total income 11262049 661571824 661559373
#> 12: male age_group1 income 4877164 285031644 285099183
#> 13: m age_group1 income 4877164 285031644 285099183
#> 14: male ag1a income 4877164 285031644 285099183
#> 15: m ag1a income 4877164 285031644 285099183
#> 16: male age_group2 income 2811379 166292035 166417241
#> 17: m age_group2 income 2811379 166292035 166417241
#> 18: male ag2a income 2811379 166292035 166417241
#> 19: m ag2a income 2811379 166292035 166417241
#> 20: male age_group3 income 2168169 129229861 129110697
#> 21: m age_group3 income 2168169 129229861 129110697
#> 22: male age_group4 income 978510 56934088 56954090
#> 23: m age_group4 income 978510 56934088 56954090
#> 24: male age_group5 income 393134 22423083 22396848
#> 25: m age_group5 income 393134 22423083 22396848
#> 26: male age_group6 income 33693 1661113 1686102
#> 27: m age_group6 income 33693 1661113 1686102
#> 28: female Total income 11690929 698412127 698388207
#> 29: f Total income 11690929 698412127 698388207
#> 30: female age_group1 income 4933383 292556860 292548783
#> 31: f age_group1 income 4933383 292556860 292548783
#> 32: female ag1a income 4933383 292556860 292548783
#> 33: f ag1a income 4933383 292556860 292548783
#> 34: female age_group2 income 2880740 172975213 172976307
#> 35: f age_group2 income 2880740 172975213 172976307
#> 36: female ag2a income 2880740 172975213 172976307
#> 37: f ag2a income 2880740 172975213 172976307
#> 38: female age_group3 income 2238777 131271316 131158274
#> 39: f age_group3 income 2238777 131271316 131158274
#> 40: female age_group4 income 1155033 71207130 71160151
#> 41: f age_group4 income 1155033 71207130 71160151
#> 42: female age_group5 income 455017 28060548 28056010
#> 43: f age_group5 income 455017 28060548 28056010
#> 44: female age_group6 income 27979 2341060 2082684
#> 45: f age_group6 income 27979 2341060 2082684
#> sex age vname uws ws pws
tab$numtab("income", mean_before_sum = FALSE)
#> sex age vname uws ws pws
#> 1: Total Total income 22952978 1359983951 1360059263
#> 2: Total age_group1 income 9810547 577588504 577533316
#> 3: Total ag1a income 9810547 577588504 577533316
#> 4: Total age_group2 income 5692119 339267248 339239018
#> 5: Total ag2a income 5692119 339267248 339239018
#> 6: Total age_group3 income 4406946 260501177 260468464
#> 7: Total age_group4 income 2133543 128141218 128123528
#> 8: Total age_group5 income 848151 50483631 50555163
#> 9: Total age_group6 income 61672 4002173 3928026
#> 10: male Total income 11262049 661571824 661565598
#> 11: m Total income 11262049 661571824 661565598
#> 12: male age_group1 income 4877164 285031644 285065411
#> 13: m age_group1 income 4877164 285031644 285065411
#> 14: male ag1a income 4877164 285031644 285065411
#> 15: m ag1a income 4877164 285031644 285065411
#> 16: male age_group2 income 2811379 166292035 166354626
#> 17: m age_group2 income 2811379 166292035 166354626
#> 18: male ag2a income 2811379 166292035 166354626
#> 19: m ag2a income 2811379 166292035 166354626
#> 20: male age_group3 income 2168169 129229861 129170265
#> 21: m age_group3 income 2168169 129229861 129170265
#> 22: male age_group4 income 978510 56934088 56944088
#> 23: m age_group4 income 978510 56934088 56944088
#> 24: male age_group5 income 393134 22423083 22409962
#> 25: m age_group5 income 393134 22423083 22409962
#> 26: male age_group6 income 33693 1661113 1673561
#> 27: m age_group6 income 33693 1661113 1673561
#> 28: female Total income 11690929 698412127 698400167
#> 29: f Total income 11690929 698412127 698400167
#> 30: female age_group1 income 4933383 292556860 292552822
#> 31: f age_group1 income 4933383 292556860 292552822
#> 32: female ag1a income 4933383 292556860 292552822
#> 33: f ag1a income 4933383 292556860 292552822
#> 34: female age_group2 income 2880740 172975213 172975760
#> 35: f age_group2 income 2880740 172975213 172975760
#> 36: female ag2a income 2880740 172975213 172975760
#> 37: f ag2a income 2880740 172975213 172975760
#> 38: female age_group3 income 2238777 131271316 131214783
#> 39: f age_group3 income 2238777 131271316 131214783
#> 40: female age_group4 income 1155033 71207130 71183637
#> 41: f age_group4 income 1155033 71207130 71183637
#> 42: female age_group5 income 455017 28060548 28058279
#> 43: f age_group5 income 455017 28060548 28058279
#> 44: female age_group6 income 27979 2341060 2208096
#> 45: f age_group6 income 27979 2341060 2208096
#> sex age vname uws ws pws
tab$numtab("savings")
#> sex age vname uws ws pws
#> 1: Total Total savings 2273532 135170381 135166646.2
#> 2: Total age_group1 savings 982386 58643412 58638680.7
#> 3: Total ag1a savings 982386 58643412 58638680.7
#> 4: Total age_group2 savings 552336 32444387 32442052.1
#> 5: Total ag2a savings 552336 32444387 32442052.1
#> 6: Total age_group3 savings 437101 25955604 25954971.3
#> 7: Total age_group4 savings 214661 12644077 12641532.9
#> 8: Total age_group5 savings 80451 4967875 4971042.4
#> 9: Total age_group6 savings 6597 515026 506122.5
#> 10: male Total savings 1159816 68649082 68650410.8
#> 11: m Total savings 1159816 68649082 68650410.8
#> 12: male age_group1 savings 517660 30885609 30887281.0
#> 13: m age_group1 savings 517660 30885609 30887281.0
#> 14: male ag1a savings 517660 30885609 30887281.0
#> 15: m ag1a savings 517660 30885609 30887281.0
#> 16: male age_group2 savings 280923 16380629 16385418.9
#> 17: m age_group2 savings 280923 16380629 16385418.9
#> 18: male ag2a savings 280923 16380629 16385418.9
#> 19: m ag2a savings 280923 16380629 16385418.9
#> 20: male age_group3 savings 214970 12897451 12893166.7
#> 21: m age_group3 savings 214970 12897451 12893166.7
#> 22: male age_group4 savings 99420 5602822 5605660.0
#> 23: m age_group4 savings 99420 5602822 5605660.0
#> 24: male age_group5 savings 43233 2635701 2634651.3
#> 25: m age_group5 savings 43233 2635701 2634651.3
#> 26: male age_group6 savings 3610 246870 247909.9
#> 27: m age_group6 savings 3610 246870 247909.9
#> 28: female Total savings 1113716 66521299 66524978.9
#> 29: f Total savings 1113716 66521299 66524978.9
#> 30: female age_group1 savings 464726 27757803 27759435.7
#> 31: f age_group1 savings 464726 27757803 27759435.7
#> 32: female ag1a savings 464726 27757803 27759435.7
#> 33: f ag1a savings 464726 27757803 27759435.7
#> 34: female age_group2 savings 271413 16063758 16065574.7
#> 35: f age_group2 savings 271413 16063758 16065574.7
#> 36: female ag2a savings 271413 16063758 16065574.7
#> 37: f ag2a savings 271413 16063758 16065574.7
#> 38: female age_group3 savings 222131 13058153 13051506.2
#> 39: f age_group3 savings 222131 13058153 13051506.2
#> 40: female age_group4 savings 115241 7041255 7039494.2
#> 41: f age_group4 savings 115241 7041255 7039494.2
#> 42: female age_group5 savings 37218 2332174 2332090.1
#> 43: f age_group5 savings 37218 2332174 2332090.1
#> 44: female age_group6 savings 2987 268156 259820.0
#> 45: f age_group6 savings 2987 268156 259820.0
#> sex age vname uws ws pws
# results can be resetted, too
tab$reset_cntvars(v = "cnt_males")
# we can then set other parameters and perturb again
tab$params_cnts_set(val = p_cnts1, v = "cnt_males")
#> --> setting perturbation parameters for variable 'cnt_males'
tab$perturb(v = "cnt_males")
#> Count variable 'cnt_males' was perturbed.
# write results to a .csv file
tab$freqtab(
v = c("total", "cnt_males"),
path = file.path(tempdir(), "outtab.csv")
)
#> File '/tmp/RtmpV7PINT/outtab.csv' successfully written to disk.
#> NULL
# show results containing weighted and unweighted results
tab$freqtab(v = c("total", "cnt_males"))
#> sex age vname uwc wc puwc pwc
#> 1: Total Total total 4580 272100 4581 272159.4105
#> 2: Total age_group1 total 1969 117044 1970 117103.4434
#> 3: Total ag1a total 1969 117044 1970 117103.4434
#> 4: Total age_group2 total 1143 67505 1141 67386.8810
#> 5: Total ag2a total 1143 67505 1141 67386.8810
#> 6: Total age_group3 total 864 51289 866 51407.7245
#> 7: Total age_group4 total 423 25206 423 25206.0000
#> 8: Total age_group5 total 168 10140 167 10079.6429
#> 9: Total age_group6 total 13 916 13 916.0000
#> 10: male Total total 2296 135673 2296 135673.0000
#> 11: m Total total 2296 135673 2296 135673.0000
#> 12: male age_group1 total 1015 60163 1015 60163.0000
#> 13: m age_group1 total 1015 60163 1015 60163.0000
#> 14: male ag1a total 1015 60163 1015 60163.0000
#> 15: m ag1a total 1015 60163 1015 60163.0000
#> 16: male age_group2 total 571 33439 571 33439.0000
#> 17: m age_group2 total 571 33439 571 33439.0000
#> 18: male ag2a total 571 33439 571 33439.0000
#> 19: m ag2a total 571 33439 571 33439.0000
#> 20: male age_group3 total 424 25289 423 25229.3561
#> 21: m age_group3 total 424 25289 423 25229.3561
#> 22: male age_group4 total 195 11353 196 11411.2205
#> 23: m age_group4 total 195 11353 196 11411.2205
#> 24: male age_group5 total 84 5026 84 5026.0000
#> 25: m age_group5 total 84 5026 84 5026.0000
#> 26: male age_group6 total 7 403 8 460.5714
#> 27: m age_group6 total 7 403 8 460.5714
#> 28: female Total total 2284 136427 2284 136427.0000
#> 29: f Total total 2284 136427 2284 136427.0000
#> 30: female age_group1 total 954 56881 953 56821.3763
#> 31: f age_group1 total 954 56881 953 56821.3763
#> 32: female ag1a total 954 56881 953 56821.3763
#> 33: f ag1a total 954 56881 953 56821.3763
#> 34: female age_group2 total 572 34066 572 34066.0000
#> 35: f age_group2 total 572 34066 572 34066.0000
#> 36: female ag2a total 572 34066 572 34066.0000
#> 37: f ag2a total 572 34066 572 34066.0000
#> 38: female age_group3 total 440 26000 441 26059.0909
#> 39: f age_group3 total 440 26000 441 26059.0909
#> 40: female age_group4 total 228 13853 228 13853.0000
#> 41: f age_group4 total 228 13853 228 13853.0000
#> 42: female age_group5 total 84 5114 85 5174.8810
#> 43: f age_group5 total 84 5114 85 5174.8810
#> 44: female age_group6 total 6 513 6 513.0000
#> 45: f age_group6 total 6 513 6 513.0000
#> 46: Total Total cnt_males 2296 135673 2296 135673.0000
#> 47: Total age_group1 cnt_males 1015 60163 1015 60163.0000
#> 48: Total ag1a cnt_males 1015 60163 1015 60163.0000
#> 49: Total age_group2 cnt_males 571 33439 571 33439.0000
#> 50: Total ag2a cnt_males 571 33439 571 33439.0000
#> 51: Total age_group3 cnt_males 424 25289 423 25229.3561
#> 52: Total age_group4 cnt_males 195 11353 196 11411.2205
#> 53: Total age_group5 cnt_males 84 5026 84 5026.0000
#> 54: Total age_group6 cnt_males 7 403 8 460.5714
#> 55: male Total cnt_males 2296 135673 2296 135673.0000
#> 56: m Total cnt_males 2296 135673 2296 135673.0000
#> 57: male age_group1 cnt_males 1015 60163 1015 60163.0000
#> 58: m age_group1 cnt_males 1015 60163 1015 60163.0000
#> 59: male ag1a cnt_males 1015 60163 1015 60163.0000
#> 60: m ag1a cnt_males 1015 60163 1015 60163.0000
#> 61: male age_group2 cnt_males 571 33439 571 33439.0000
#> 62: m age_group2 cnt_males 571 33439 571 33439.0000
#> 63: male ag2a cnt_males 571 33439 571 33439.0000
#> 64: m ag2a cnt_males 571 33439 571 33439.0000
#> 65: male age_group3 cnt_males 424 25289 423 25229.3561
#> 66: m age_group3 cnt_males 424 25289 423 25229.3561
#> 67: male age_group4 cnt_males 195 11353 196 11411.2205
#> 68: m age_group4 cnt_males 195 11353 196 11411.2205
#> 69: male age_group5 cnt_males 84 5026 84 5026.0000
#> 70: m age_group5 cnt_males 84 5026 84 5026.0000
#> 71: male age_group6 cnt_males 7 403 8 460.5714
#> 72: m age_group6 cnt_males 7 403 8 460.5714
#> 73: female Total cnt_males 0 0 0 0.0000
#> 74: f Total cnt_males 0 0 0 0.0000
#> 75: female age_group1 cnt_males 0 0 0 0.0000
#> 76: f age_group1 cnt_males 0 0 0 0.0000
#> 77: female ag1a cnt_males 0 0 0 0.0000
#> 78: f ag1a cnt_males 0 0 0 0.0000
#> 79: female age_group2 cnt_males 0 0 0 0.0000
#> 80: f age_group2 cnt_males 0 0 0 0.0000
#> 81: female ag2a cnt_males 0 0 0 0.0000
#> 82: f ag2a cnt_males 0 0 0 0.0000
#> 83: female age_group3 cnt_males 0 0 0 0.0000
#> 84: f age_group3 cnt_males 0 0 0 0.0000
#> 85: female age_group4 cnt_males 0 0 0 0.0000
#> 86: f age_group4 cnt_males 0 0 0 0.0000
#> 87: female age_group5 cnt_males 0 0 0 0.0000
#> 88: f age_group5 cnt_males 0 0 0 0.0000
#> 89: female age_group6 cnt_males 0 0 0 0.0000
#> 90: f age_group6 cnt_males 0 0 0 0.0000
#> sex age vname uwc wc puwc pwc
# utility measures for a count variable
tab$measures_cnts(v = "total", exclude_zeros = TRUE)
#> $overview
#> noise cnt pct
#> 1: -2 1 0.02222222
#> 2: -1 11 0.24444444
#> 3: 0 24 0.53333333
#> 4: 1 7 0.15555556
#> 5: 2 2 0.04444444
#>
#> $measures
#> what d1 d2 d3
#> 1: Min 0.000 0.000 0.000
#> 2: Q10 0.000 0.000 0.000
#> 3: Q20 0.000 0.000 0.000
#> 4: Q30 0.000 0.000 0.000
#> 5: Q40 0.000 0.000 0.000
#> 6: Mean 0.533 0.008 0.019
#> 7: Median 0.000 0.000 0.000
#> 8: Q60 1.000 0.001 0.013
#> 9: Q70 1.000 0.002 0.022
#> 10: Q80 1.000 0.002 0.030
#> 11: Q90 1.000 0.006 0.037
#> 12: Q95 1.800 0.012 0.054
#> 13: Q99 2.000 0.143 0.183
#> 14: Max 2.000 0.143 0.183
#>
#> $cumdistr_d1
#> cat cnt pct
#> 1: 0 24 0.5333333
#> 2: 1 42 0.9333333
#> 3: 2 45 1.0000000
#>
#> $cumdistr_d2
#> cat cnt pct
#> 1: [0,0.02] 43 0.9555556
#> 2: (0.02,0.05] 43 0.9555556
#> 3: (0.05,0.1] 43 0.9555556
#> 4: (0.1,0.2] 45 1.0000000
#> 5: (0.2,0.3] 45 1.0000000
#> 6: (0.3,0.4] 45 1.0000000
#> 7: (0.4,0.5] 45 1.0000000
#> 8: (0.5,Inf] 45 1.0000000
#>
#> $cumdistr_d3
#> cat cnt pct
#> 1: [0,0.02] 31 0.6888889
#> 2: (0.02,0.05] 41 0.9111111
#> 3: (0.05,0.1] 43 0.9555556
#> 4: (0.1,0.2] 45 1.0000000
#> 5: (0.2,0.3] 45 1.0000000
#> 6: (0.3,0.4] 45 1.0000000
#> 7: (0.4,0.5] 45 1.0000000
#> 8: (0.5,Inf] 45 1.0000000
#>
#> $false_zero
#> [1] 0
#>
#> $false_nonzero
#> [1] 0
#>
#> $exclude_zeros
#> [1] TRUE
#>
# modifications for perturbed count variables
tab$mod_cnts()
#> sex age row_nr pert ckey countvar
#> 1: Total Total 16 1 0.69925386 total
#> 2: Total age_group1 16 1 0.70477037 total
#> 3: Total ag1a 16 1 0.70477037 total
#> 4: Total age_group2 13 -2 0.03503265 total
#> 5: Total ag2a 13 -2 0.03503265 total
#> ---
#> 131: f age_group4 -1 0 0.00000000 cnt_males
#> 132: female age_group5 -1 0 0.00000000 cnt_males
#> 133: f age_group5 -1 0 0.00000000 cnt_males
#> 134: female age_group6 -1 0 0.00000000 cnt_males
#> 135: f age_group6 -1 0 0.00000000 cnt_males
# display a summary about utility measures
tab$summary()
#> ┌──────────────────────────────────────────────┐
#> │Utility measures for perturbed count variables│
#> └──────────────────────────────────────────────┘
#> ── Distribution statistics of perturbations ────────────────────────────────────
#> countvar Min Q10 Q20 Q30 Q40 Mean Median Q60 Q70 Q80 Q90 Q95 Q99
#> 1: total -2 -1 -0.2 0.0 0 0.044 0 0 0 1 1 1 1.56
#> 2: cnt_highincome -3 -2 -1.0 -0.8 0 -0.178 0 0 1 1 1 1 1.00
#> 3: cnt_males -1 0 0.0 0.0 0 0.067 0 0 0 0 1 1 1.00
#> Max
#> 1: 2
#> 2: 1
#> 3: 1
#>
#> ── Distance-based measures ─────────────────────────────────────────────────────
#> ✔ Variable: 'total'
#>
#> what d1 d2 d3
#> 1: Min 0.000 0.000 0.000
#> 2: Q10 0.000 0.000 0.000
#> 3: Q20 0.000 0.000 0.000
#> 4: Q30 0.000 0.000 0.000
#> 5: Q40 0.000 0.000 0.000
#> 6: Mean 0.533 0.008 0.019
#> 7: Median 0.000 0.000 0.000
#> 8: Q60 1.000 0.001 0.013
#> 9: Q70 1.000 0.002 0.022
#> 10: Q80 1.000 0.002 0.030
#> 11: Q90 1.000 0.006 0.037
#> 12: Q95 1.800 0.012 0.054
#> 13: Q99 2.000 0.143 0.183
#> 14: Max 2.000 0.143 0.183
#>
#> ✔ Variable: 'cnt_males'
#>
#> what d1 d2 d3
#> 1: Min 0.000 0.000 0.000
#> 2: Q10 0.000 0.000 0.000
#> 3: Q20 0.000 0.000 0.000
#> 4: Q30 0.000 0.000 0.000
#> 5: Q40 0.000 0.000 0.000
#> 6: Mean 0.333 0.017 0.027
#> 7: Median 0.000 0.000 0.000
#> 8: Q60 0.000 0.000 0.000
#> 9: Q70 1.000 0.002 0.024
#> 10: Q80 1.000 0.005 0.033
#> 11: Q90 1.000 0.060 0.095
#> 12: Q95 1.000 0.143 0.183
#> 13: Q99 1.000 0.143 0.183
#> 14: Max 1.000 0.143 0.183
#>
#> ✔ Variable: 'cnt_highincome'
#>
#> what d1 d2 d3
#> 1: Min 0.0 0.000 0.000
#> 2: Q10 0.0 0.000 0.000
#> 3: Q20 0.0 0.000 0.000
#> 4: Q30 1.0 0.005 0.034
#> 5: Q40 1.0 0.007 0.041
#> 6: Mean 1.0 0.022 0.069
#> 7: Median 1.0 0.010 0.049
#> 8: Q60 1.0 0.018 0.066
#> 9: Q70 1.0 0.024 0.078
#> 10: Q80 1.0 0.045 0.117
#> 11: Q90 2.1 0.053 0.187
#> 12: Q95 3.0 0.067 0.187
#> 13: Q99 3.0 0.113 0.242
#> 14: Max 3.0 0.143 0.278
#>
#> ┌──────────────────────────────────────────────────┐
#> │Utility measures for perturbed numerical variables│
#> └──────────────────────────────────────────────────┘
#> ── Distribution statistics of perturbations ────────────────────────────────────
#> Warning: no non-missing arguments to min; returning Inf
#> Warning: no non-missing arguments to max; returning -Inf
#> Warning: no non-missing arguments to min; returning Inf
#> Warning: no non-missing arguments to max; returning -Inf
#> vname Min Q10 Q20 Q30 Q40 Mean
#> 1: expend Inf NA NA NA NA NaN
#> 2: income -132963.842 -58370.720 -37208.028 -22332.659 -11960.26 -7566.71
#> 3: savings -8903.494 -5880.621 -3844.714 -1760.751 -303.40 -304.11
#> 4: mixed Inf NA NA NA NA NaN
#> Median Q60 Q70 Q80 Q90 Q95 Q99
#> 1: NA NA NA NA NA NA NA
#> 2: -4038.389 -1142.775 8109.591 33767.314 62591.315 62591.315 73648.595
#> 3: 1328.848 1632.681 1671.965 2020.916 3679.869 4789.947 4789.947
#> 4: NA NA NA NA NA NA NA
#> Max
#> 1: -Inf
#> 2: 75311.868
#> 3: 4789.947
#> 4: -Inf
# }