ck_read_yaml() allows to create perturbation parameter inputs from yaml-files
that were previously created using ck_params_cnts() or ck_params_nums().
ck_read_yaml(path)a path to a yaml-input file
an object object suitable as input to method $params_nums_set() for the perturbation
of continous variables in case path was created using ck_params_nums() or an object
suitable as input for $params_cnts_set() for the perturbation
of counts and frequencies if the input file was generated using ck_params_cnts().
# \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 91 25.00000 0
#> 2: 2530 28 1 40 25.00000 1
#> 3: 6920 550 1 39 25.00000 0
#> 4: 7960 870 1 81 25.00000 0
#> 5: 9030 20 2 72 16.66667 0
#> ---
#> 4576: 7900 278 1000 83 16.66667 1
#> 4577: 1420 987 1000 86 16.66667 0
#> 4578: 8900 684 1000 60 16.66667 0
#> 4579: 3880 294 1000 75 16.66667 1
#> 4580: 4830 911 1000 80 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 91 25.00000 0
#> 2: 2530 28 1 40 25.00000 1
#> 3: 6920 550 1 39 25.00000 0
#> 4: 7960 870 1 81 25.00000 0
#> 5: 9030 20 2 72 16.66667 0
#> ---
#> 4576: 7900 278 1000 83 16.66667 1
#> 4577: 1420 987 1000 86 16.66667 0
#> 4578: 8900 684 1000 60 16.66667 0
#> 4579: 3880 294 1000 75 16.66667 1
#> 4580: 4830 911 1000 80 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 91 25.00000 0
#> 2: 2530 28 1 40 25.00000 1
#> 3: 6920 550 1 39 25.00000 0
#> 4: 7960 870 1 81 25.00000 0
#> 5: 9030 20 2 72 16.66667 0
#> ---
#> 4576: 7900 278 1000 83 16.66667 1
#> 4577: 1420 987 1000 86 16.66667 0
#> 4578: 8900 684 1000 60 16.66667 0
#> 4579: 3880 294 1000 75 16.66667 1
#> 4580: 4830 911 1000 80 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 91 25.00000 0
#> 2: 2530 28 1 40 25.00000 1
#> 3: 6920 550 1 39 25.00000 0
#> 4: 7960 870 1 81 25.00000 0
#> 5: 9030 20 2 72 16.66667 0
#> ---
#> 4576: 7900 278 1000 83 16.66667 1
#> 4577: 1420 987 1000 86 16.66667 0
#> 4578: 8900 684 1000 60 16.66667 0
#> 4579: 3880 294 1000 75 16.66667 1
#> 4580: 4830 911 1000 80 16.66667 0
#> cnt_males cnt_highincome mixed
#> 1: 1 0 4
#> 2: 0 0 5
#> 3: 1 0 1
#> 4: 1 0 5
#> 5: 1 1 10
#> ---
#> 4576: 0 0 -1
#> 4577: 1 0 5
#> 4578: 1 0 3
#> 4579: 0 0 0
#> 4580: 1 0 -5
# 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$numvars()
#> [1] "expend" "income" "savings" "mixed"
# create perturbation parameters for "total" variable and
# write to yaml-file
# create a ptable using functionality from the ptable-pkg
f_yaml <- tempfile(fileext = ".yaml")
p_cnts1 <- ck_params_cnts(
ptab = ptable::pt_ex_cnts(),
path = f_yaml)
#> yaml configuration '/tmp/RtmpV7PINT/file19626b539335.yaml' successfully written.
# read parameters from yaml-file and set them for variable `"total"`
p_cnts1 <- ck_read_yaml(path = f_yaml)
tab$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 275314 4580 275314.0000
#> 2: Total age_group1 total 1969 118338 1969 118338.0000
#> 3: Total ag1a total 1969 118338 1969 118338.0000
#> 4: Total age_group2 total 1143 68779 1142 68718.8259
#> 5: Total ag2a total 1143 68779 1142 68718.8259
#> 6: Total age_group3 total 864 52029 865 52089.2188
#> 7: Total age_group4 total 423 25161 424 25220.4823
#> 8: Total age_group5 total 168 10255 168 10255.0000
#> 9: Total age_group6 total 13 752 13 752.0000
#> 10: male Total total 2296 137457 2298 137576.7361
#> 11: m Total total 2296 137457 2298 137576.7361
#> 12: male age_group1 total 1015 61151 1014 61090.7527
#> 13: m age_group1 total 1015 61151 1014 61090.7527
#> 14: male ag1a total 1015 61151 1014 61090.7527
#> 15: m ag1a total 1015 61151 1014 61090.7527
#> 16: male age_group2 total 571 34403 570 34342.7496
#> 17: m age_group2 total 571 34403 570 34342.7496
#> 18: male ag2a total 571 34403 570 34342.7496
#> 19: m ag2a total 571 34403 570 34342.7496
#> 20: male age_group3 total 424 24788 424 24788.0000
#> 21: m age_group3 total 424 24788 424 24788.0000
#> 22: male age_group4 total 195 11295 193 11179.1538
#> 23: m age_group4 total 195 11295 193 11179.1538
#> 24: male age_group5 total 84 5393 84 5393.0000
#> 25: m age_group5 total 84 5393 84 5393.0000
#> 26: male age_group6 total 7 427 8 488.0000
#> 27: m age_group6 total 7 427 8 488.0000
#> 28: female Total total 2284 137857 2284 137857.0000
#> 29: f Total total 2284 137857 2284 137857.0000
#> 30: female age_group1 total 954 57187 953 57127.0556
#> 31: f age_group1 total 954 57187 953 57127.0556
#> 32: female ag1a total 954 57187 953 57127.0556
#> 33: f ag1a total 954 57187 953 57127.0556
#> 34: female age_group2 total 572 34376 571 34315.9021
#> 35: f age_group2 total 572 34376 571 34315.9021
#> 36: female ag2a total 572 34376 571 34315.9021
#> 37: f ag2a total 572 34376 571 34315.9021
#> 38: female age_group3 total 440 27241 439 27179.0886
#> 39: f age_group3 total 440 27241 439 27179.0886
#> 40: female age_group4 total 228 13866 229 13926.8158
#> 41: f age_group4 total 228 13866 229 13926.8158
#> 42: female age_group5 total 84 4862 83 4804.1190
#> 43: f age_group5 total 84 4862 83 4804.1190
#> 44: female age_group6 total 6 325 7 379.1667
#> 45: f age_group6 total 6 325 7 379.1667
#> 46: Total Total cnt_males 2296 137457 2299 137636.6041
#> 47: Total age_group1 cnt_males 1015 61151 1014 61090.7527
#> 48: Total ag1a cnt_males 1015 61151 1014 61090.7527
#> 49: Total age_group2 cnt_males 571 34403 569 34282.4991
#> 50: Total ag2a cnt_males 571 34403 569 34282.4991
#> 51: Total age_group3 cnt_males 424 24788 424 24788.0000
#> 52: Total age_group4 cnt_males 195 11295 192 11121.2308
#> 53: Total age_group5 cnt_males 84 5393 83 5328.7976
#> 54: Total age_group6 cnt_males 7 427 8 488.0000
#> 55: male Total cnt_males 2296 137457 2299 137636.6041
#> 56: m Total cnt_males 2296 137457 2299 137636.6041
#> 57: male age_group1 cnt_males 1015 61151 1014 61090.7527
#> 58: m age_group1 cnt_males 1015 61151 1014 61090.7527
#> 59: male ag1a cnt_males 1015 61151 1014 61090.7527
#> 60: m ag1a cnt_males 1015 61151 1014 61090.7527
#> 61: male age_group2 cnt_males 571 34403 569 34282.4991
#> 62: m age_group2 cnt_males 571 34403 569 34282.4991
#> 63: male ag2a cnt_males 571 34403 569 34282.4991
#> 64: m ag2a cnt_males 571 34403 569 34282.4991
#> 65: male age_group3 cnt_males 424 24788 424 24788.0000
#> 66: m age_group3 cnt_males 424 24788 424 24788.0000
#> 67: male age_group4 cnt_males 195 11295 192 11121.2308
#> 68: m age_group4 cnt_males 195 11295 192 11121.2308
#> 69: male age_group5 cnt_males 84 5393 83 5328.7976
#> 70: m age_group5 cnt_males 84 5393 83 5328.7976
#> 71: male age_group6 cnt_males 7 427 8 488.0000
#> 72: m age_group6 cnt_males 7 427 8 488.0000
#> 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/file196212550349.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 1371133298 1371188562
#> 2: Total age_group1 income 9810547 589771142 589676502
#> 3: Total ag1a income 9810547 589771142 589676502
#> 4: Total age_group2 income 5692119 340593269 340673243
#> 5: Total ag2a income 5692119 340593269 340673243
#> 6: Total age_group3 income 4406946 259564658 259615518
#> 7: Total age_group4 income 2133543 127402640 127326590
#> 8: Total age_group5 income 848151 50226475 50385460
#> 9: Total age_group6 income 61672 3575114 3760484
#> 10: male Total income 11262049 669913462 669807221
#> 11: m Total income 11262049 669913462 669807221
#> 12: male age_group1 income 4877164 293952134 293934782
#> 13: m age_group1 income 4877164 293952134 293934782
#> 14: male ag1a income 4877164 293952134 293934782
#> 15: m ag1a income 4877164 293952134 293934782
#> 16: male age_group2 income 2811379 170935848 171009368
#> 17: m age_group2 income 2811379 170935848 171009368
#> 18: male ag2a income 2811379 170935848 171009368
#> 19: m ag2a income 2811379 170935848 171009368
#> 20: male age_group3 income 2168169 123293888 123248660
#> 21: m age_group3 income 2168169 123293888 123248660
#> 22: male age_group4 income 978510 55380341 55374435
#> 23: m age_group4 income 978510 55380341 55374435
#> 24: male age_group5 income 393134 24274471 24304497
#> 25: m age_group5 income 393134 24274471 24304497
#> 26: male age_group6 income 33693 2076780 2278093
#> 27: m age_group6 income 33693 2076780 2278093
#> 28: female Total income 11690929 701219836 701238876
#> 29: f Total income 11690929 701219836 701238876
#> 30: female age_group1 income 4933383 295819008 295737452
#> 31: f age_group1 income 4933383 295819008 295737452
#> 32: female ag1a income 4933383 295819008 295737452
#> 33: f ag1a income 4933383 295819008 295737452
#> 34: female age_group2 income 2880740 169657421 169731190
#> 35: f age_group2 income 2880740 169657421 169731190
#> 36: female ag2a income 2880740 169657421 169731190
#> 37: f ag2a income 2880740 169657421 169731190
#> 38: female age_group3 income 2238777 136270770 136308068
#> 39: f age_group3 income 2238777 136270770 136308068
#> 40: female age_group4 income 1155033 72022299 72128182
#> 41: f age_group4 income 1155033 72022299 72128182
#> 42: female age_group5 income 455017 25952004 25810397
#> 43: f age_group5 income 455017 25952004 25810397
#> 44: female age_group6 income 27979 1498334 1752194
#> 45: f age_group6 income 27979 1498334 1752194
#> sex age vname uws ws pws
tab$numtab("income", mean_before_sum = FALSE)
#> sex age vname uws ws pws
#> 1: Total Total income 22952978 1371133298 1371160930
#> 2: Total age_group1 income 9810547 589771142 589723820
#> 3: Total ag1a income 9810547 589771142 589723820
#> 4: Total age_group2 income 5692119 340593269 340633254
#> 5: Total ag2a income 5692119 340593269 340633254
#> 6: Total age_group3 income 4406946 259564658 259590087
#> 7: Total age_group4 income 2133543 127402640 127364609
#> 8: Total age_group5 income 848151 50226475 50305905
#> 9: Total age_group6 income 61672 3575114 3666628
#> 10: male Total income 11262049 669913462 669860339
#> 11: m Total income 11262049 669913462 669860339
#> 12: male age_group1 income 4877164 293952134 293943458
#> 13: m age_group1 income 4877164 293952134 293943458
#> 14: male ag1a income 4877164 293952134 293943458
#> 15: m ag1a income 4877164 293952134 293943458
#> 16: male age_group2 income 2811379 170935848 170972604
#> 17: m age_group2 income 2811379 170935848 170972604
#> 18: male ag2a income 2811379 170935848 170972604
#> 19: m ag2a income 2811379 170935848 170972604
#> 20: male age_group3 income 2168169 123293888 123271272
#> 21: m age_group3 income 2168169 123293888 123271272
#> 22: male age_group4 income 978510 55380341 55377388
#> 23: m age_group4 income 978510 55380341 55377388
#> 24: male age_group5 income 393134 24274471 24289479
#> 25: m age_group5 income 393134 24274471 24289479
#> 26: male age_group6 income 33693 2076780 2175109
#> 27: m age_group6 income 33693 2076780 2175109
#> 28: female Total income 11690929 701219836 701229356
#> 29: f Total income 11690929 701219836 701229356
#> 30: female age_group1 income 4933383 295819008 295778227
#> 31: f age_group1 income 4933383 295819008 295778227
#> 32: female ag1a income 4933383 295819008 295778227
#> 33: f ag1a income 4933383 295819008 295778227
#> 34: female age_group2 income 2880740 169657421 169694302
#> 35: f age_group2 income 2880740 169657421 169694302
#> 36: female ag2a income 2880740 169657421 169694302
#> 37: f ag2a income 2880740 169657421 169694302
#> 38: female age_group3 income 2238777 136270770 136289418
#> 39: f age_group3 income 2238777 136270770 136289418
#> 40: female age_group4 income 1155033 72022299 72075221
#> 41: f age_group4 income 1155033 72022299 72075221
#> 42: female age_group5 income 455017 25952004 25881104
#> 43: f age_group5 income 455017 25952004 25881104
#> 44: female age_group6 income 27979 1498334 1620300
#> 45: f age_group6 income 27979 1498334 1620300
#> sex age vname uws ws pws
tab$numtab("savings")
#> sex age vname uws ws pws
#> 1: Total Total savings 2273532 136880706 136882379.4
#> 2: Total age_group1 savings 982386 58893463 58891342.4
#> 3: Total ag1a savings 982386 58893463 58891342.4
#> 4: Total age_group2 savings 552336 33224872 33229680.4
#> 5: Total ag2a savings 552336 33224872 33229680.4
#> 6: Total age_group3 savings 437101 26553122 26554972.4
#> 7: Total age_group4 savings 214661 12821576 12817603.4
#> 8: Total age_group5 savings 80451 5024979 5036847.2
#> 9: Total age_group6 savings 6597 362694 366843.4
#> 10: male Total savings 1159816 69509585 69507895.3
#> 11: m Total savings 1159816 69509585 69507895.3
#> 12: male age_group1 savings 517660 31214171 31212487.2
#> 13: m age_group1 savings 517660 31214171 31212487.2
#> 14: male ag1a savings 517660 31214171 31212487.2
#> 15: m ag1a savings 517660 31214171 31212487.2
#> 16: male age_group2 savings 280923 16884564 16886843.3
#> 17: m age_group2 savings 280923 16884564 16886843.3
#> 18: male ag2a savings 280923 16884564 16886843.3
#> 19: m ag2a savings 280923 16884564 16886843.3
#> 20: male age_group3 savings 214970 12534750 12533498.5
#> 21: m age_group3 savings 214970 12534750 12533498.5
#> 22: male age_group4 savings 99420 5837760 5837329.7
#> 23: m age_group4 savings 99420 5837760 5837329.7
#> 24: male age_group5 savings 43233 2829005 2833021.4
#> 25: m age_group5 savings 43233 2829005 2833021.4
#> 26: male age_group6 savings 3610 209335 213965.4
#> 27: m age_group6 savings 3610 209335 213965.4
#> 28: female Total savings 1113716 67371121 67369521.1
#> 29: f Total savings 1113716 67371121 67369521.1
#> 30: female age_group1 savings 464726 27679292 27687740.8
#> 31: f age_group1 savings 464726 27679292 27687740.8
#> 32: female ag1a savings 464726 27679292 27687740.8
#> 33: f ag1a savings 464726 27679292 27687740.8
#> 34: female age_group2 savings 271413 16340308 16346175.2
#> 35: f age_group2 savings 271413 16340308 16346175.2
#> 36: female ag2a savings 271413 16340308 16346175.2
#> 37: f ag2a savings 271413 16340308 16346175.2
#> 38: female age_group3 savings 222131 14018372 14020002.4
#> 39: f age_group3 savings 222131 14018372 14020002.4
#> 40: female age_group4 savings 115241 6983816 6988153.0
#> 41: f age_group4 savings 115241 6983816 6988153.0
#> 42: female age_group5 savings 37218 2195974 2190677.8
#> 43: f age_group5 savings 37218 2195974 2190677.8
#> 44: female age_group6 savings 2987 153359 160998.0
#> 45: f age_group6 savings 2987 153359 160998.0
#> 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 275314 4580 275314.0000
#> 2: Total age_group1 total 1969 118338 1969 118338.0000
#> 3: Total ag1a total 1969 118338 1969 118338.0000
#> 4: Total age_group2 total 1143 68779 1142 68718.8259
#> 5: Total ag2a total 1143 68779 1142 68718.8259
#> 6: Total age_group3 total 864 52029 865 52089.2188
#> 7: Total age_group4 total 423 25161 424 25220.4823
#> 8: Total age_group5 total 168 10255 168 10255.0000
#> 9: Total age_group6 total 13 752 13 752.0000
#> 10: male Total total 2296 137457 2298 137576.7361
#> 11: m Total total 2296 137457 2298 137576.7361
#> 12: male age_group1 total 1015 61151 1014 61090.7527
#> 13: m age_group1 total 1015 61151 1014 61090.7527
#> 14: male ag1a total 1015 61151 1014 61090.7527
#> 15: m ag1a total 1015 61151 1014 61090.7527
#> 16: male age_group2 total 571 34403 570 34342.7496
#> 17: m age_group2 total 571 34403 570 34342.7496
#> 18: male ag2a total 571 34403 570 34342.7496
#> 19: m ag2a total 571 34403 570 34342.7496
#> 20: male age_group3 total 424 24788 424 24788.0000
#> 21: m age_group3 total 424 24788 424 24788.0000
#> 22: male age_group4 total 195 11295 193 11179.1538
#> 23: m age_group4 total 195 11295 193 11179.1538
#> 24: male age_group5 total 84 5393 84 5393.0000
#> 25: m age_group5 total 84 5393 84 5393.0000
#> 26: male age_group6 total 7 427 8 488.0000
#> 27: m age_group6 total 7 427 8 488.0000
#> 28: female Total total 2284 137857 2284 137857.0000
#> 29: f Total total 2284 137857 2284 137857.0000
#> 30: female age_group1 total 954 57187 953 57127.0556
#> 31: f age_group1 total 954 57187 953 57127.0556
#> 32: female ag1a total 954 57187 953 57127.0556
#> 33: f ag1a total 954 57187 953 57127.0556
#> 34: female age_group2 total 572 34376 571 34315.9021
#> 35: f age_group2 total 572 34376 571 34315.9021
#> 36: female ag2a total 572 34376 571 34315.9021
#> 37: f ag2a total 572 34376 571 34315.9021
#> 38: female age_group3 total 440 27241 439 27179.0886
#> 39: f age_group3 total 440 27241 439 27179.0886
#> 40: female age_group4 total 228 13866 229 13926.8158
#> 41: f age_group4 total 228 13866 229 13926.8158
#> 42: female age_group5 total 84 4862 83 4804.1190
#> 43: f age_group5 total 84 4862 83 4804.1190
#> 44: female age_group6 total 6 325 7 379.1667
#> 45: f age_group6 total 6 325 7 379.1667
#> 46: Total Total cnt_males 2296 137457 2298 137576.7361
#> 47: Total age_group1 cnt_males 1015 61151 1014 61090.7527
#> 48: Total ag1a cnt_males 1015 61151 1014 61090.7527
#> 49: Total age_group2 cnt_males 571 34403 570 34342.7496
#> 50: Total ag2a cnt_males 571 34403 570 34342.7496
#> 51: Total age_group3 cnt_males 424 24788 424 24788.0000
#> 52: Total age_group4 cnt_males 195 11295 193 11179.1538
#> 53: Total age_group5 cnt_males 84 5393 84 5393.0000
#> 54: Total age_group6 cnt_males 7 427 8 488.0000
#> 55: male Total cnt_males 2296 137457 2298 137576.7361
#> 56: m Total cnt_males 2296 137457 2298 137576.7361
#> 57: male age_group1 cnt_males 1015 61151 1014 61090.7527
#> 58: m age_group1 cnt_males 1015 61151 1014 61090.7527
#> 59: male ag1a cnt_males 1015 61151 1014 61090.7527
#> 60: m ag1a cnt_males 1015 61151 1014 61090.7527
#> 61: male age_group2 cnt_males 571 34403 570 34342.7496
#> 62: m age_group2 cnt_males 571 34403 570 34342.7496
#> 63: male ag2a cnt_males 571 34403 570 34342.7496
#> 64: m ag2a cnt_males 571 34403 570 34342.7496
#> 65: male age_group3 cnt_males 424 24788 424 24788.0000
#> 66: m age_group3 cnt_males 424 24788 424 24788.0000
#> 67: male age_group4 cnt_males 195 11295 193 11179.1538
#> 68: m age_group4 cnt_males 195 11295 193 11179.1538
#> 69: male age_group5 cnt_males 84 5393 84 5393.0000
#> 70: m age_group5 cnt_males 84 5393 84 5393.0000
#> 71: male age_group6 cnt_males 7 427 8 488.0000
#> 72: m age_group6 cnt_males 7 427 8 488.0000
#> 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 2 0.04444444
#> 2: -1 8 0.17777778
#> 3: 0 11 0.24444444
#> 4: 1 22 0.48888889
#> 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 1.000 0.001 0.016
#> 5: Q40 1.000 0.001 0.016
#> 6: Mean 0.844 0.016 0.034
#> 7: Median 1.000 0.001 0.021
#> 8: Q60 1.000 0.002 0.021
#> 9: Q70 1.000 0.002 0.021
#> 10: Q80 1.000 0.004 0.033
#> 11: Q90 1.000 0.012 0.072
#> 12: Q95 2.000 0.143 0.183
#> 13: Q99 2.000 0.167 0.196
#> 14: Max 2.000 0.167 0.196
#>
#> $cumdistr_d1
#> cat cnt pct
#> 1: 0 11 0.2444444
#> 2: 1 41 0.9111111
#> 3: 2 45 1.0000000
#>
#> $cumdistr_d2
#> cat cnt pct
#> 1: [0,0.02] 41 0.9111111
#> 2: (0.02,0.05] 41 0.9111111
#> 3: (0.05,0.1] 41 0.9111111
#> 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] 22 0.4888889
#> 2: (0.02,0.05] 37 0.8222222
#> 3: (0.05,0.1] 41 0.9111111
#> 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 15 0 0.3252413 total
#> 2: Total age_group1 15 0 0.4125616 total
#> 3: Total ag1a 15 0 0.4125616 total
#> 4: Total age_group2 14 -1 0.1858044 total
#> 5: Total ag2a 14 -1 0.1858044 total
#> ---
#> 131: f age_group4 -1 0 0.0000000 cnt_males
#> 132: female age_group5 -1 0 0.0000000 cnt_males
#> 133: f age_group5 -1 0 0.0000000 cnt_males
#> 134: female age_group6 -1 0 0.0000000 cnt_males
#> 135: f age_group6 -1 0 0.0000000 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 -1 -1.0 -1 -0.311 -1 0 0 1 1 1.0 2
#> 2: cnt_highincome -3 -3 -2 -1.8 -1 -0.289 -1 0 0 2 3 4.0 4
#> 3: cnt_males -2 -1 -1 -1.0 0 -0.200 0 0 0 0 1 1.8 2
#> Max
#> 1: 2
#> 2: 4
#> 3: 2
#>
#> ── 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 1.000 0.001 0.016
#> 5: Q40 1.000 0.001 0.016
#> 6: Mean 0.844 0.016 0.034
#> 7: Median 1.000 0.001 0.021
#> 8: Q60 1.000 0.002 0.021
#> 9: Q70 1.000 0.002 0.021
#> 10: Q80 1.000 0.004 0.033
#> 11: Q90 1.000 0.012 0.072
#> 12: Q95 2.000 0.143 0.183
#> 13: Q99 2.000 0.167 0.196
#> 14: Max 2.000 0.167 0.196
#>
#> ✔ Variable: 'cnt_males'
#>
#> what d1 d2 d3
#> 1: Min 0.0 0.000 0.000
#> 2: Q10 0.0 0.000 0.000
#> 3: Q20 0.2 0.000 0.003
#> 4: Q30 1.0 0.001 0.016
#> 5: Q40 1.0 0.001 0.016
#> 6: Mean 1.0 0.018 0.039
#> 7: Median 1.0 0.001 0.021
#> 8: Q60 1.0 0.002 0.021
#> 9: Q70 1.0 0.002 0.021
#> 10: Q80 1.8 0.009 0.062
#> 11: Q90 2.0 0.063 0.116
#> 12: Q95 2.0 0.143 0.183
#> 13: Q99 2.0 0.143 0.183
#> 14: Max 2.0 0.143 0.183
#>
#> ✔ Variable: 'cnt_highincome'
#>
#> what d1 d2 d3
#> 1: Min 0.000 0.000 0.000
#> 2: Q10 1.000 0.005 0.036
#> 3: Q20 1.000 0.011 0.053
#> 4: Q30 1.000 0.015 0.091
#> 5: Q40 2.000 0.029 0.116
#> 6: Mean 2.075 0.057 0.151
#> 7: Median 2.000 0.035 0.134
#> 8: Q60 2.000 0.041 0.150
#> 9: Q70 3.000 0.055 0.170
#> 10: Q80 3.000 0.063 0.239
#> 11: Q90 3.100 0.149 0.254
#> 12: Q95 4.000 0.204 0.357
#> 13: Q99 4.000 0.286 0.409
#> 14: Max 4.000 0.286 0.409
#>
#> ┌──────────────────────────────────────────────────┐
#> │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 -70900.468 -47321.762 -40780.843 -8675.895 -2952.858 13369.314
#> 3: savings -5296.212 -1948.211 -1683.762 -1251.550 1630.368 2323.595
#> 4: mixed Inf NA NA NA NA NaN
#> Median Q60 Q70 Q80 Q90 Q95 Q99
#> 1: NA NA NA NA NA NA NA
#> 2: 15008.297 31281.306 36855.631 39984.565 86680.04 98328.793 121965.95
#> 3: 2279.252 4069.622 4630.368 5867.219 8124.92 8448.834 10363.69
#> 4: NA NA NA NA NA NA NA
#> Max
#> 1: -Inf
#> 2: 121965.95
#> 3: 11868.22
#> 4: -Inf
# }