R/ck_params_nums.R
ck_flexparams.Rdck_flexparams() allows to define a flex function that is used to lookup perturbation
magnitudes (percentages) used when perturbing continuous variables.
ck_flexparams(fp, p = c(0.25, 0.05), epsilon = 1, q = 3)(numeric scalar); at which point should the noise coefficient
function reaches its desired maximum (defined by the first element of p)
a numeric vector of length 2 where both elements specify a percentage.
The first value refers to the desired maximum perturbation percentage for small
cells (depending on fp) while the second element refers to the desired maximum
perturbation percentage for large cells. Both values must be between 0 and 1 and
need to be in descending order.
a numeric vector in descending order with all values >= 0 and <= 1 with the first
element forced to equal 1. The length of this vector must correspond with the number top_k
specified in ck_params_nums() when creating parameters for type == "top_contr" which is
checked at runtime. This setting allows to use different flex-functions for the largest top_k contributors.
(numeric scalar); Parameter of the function; q needs to be >= 1
an object suitable as input for ck_params_nums().
details about the flex function can be found in Deliverable D4.2, Part I in SGA "Open Source tools for perturbative confidentiality methods"
# \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 96 25.00000 0
#> 2: 2530 28 1 75 25.00000 1
#> 3: 6920 550 1 68 25.00000 0
#> 4: 7960 870 1 29 25.00000 0
#> 5: 9030 20 2 34 16.66667 0
#> ---
#> 4576: 7900 278 1000 93 16.66667 1
#> 4577: 1420 987 1000 62 16.66667 0
#> 4578: 8900 684 1000 60 16.66667 0
#> 4579: 3880 294 1000 26 16.66667 1
#> 4580: 4830 911 1000 64 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 96 25.00000 0
#> 2: 2530 28 1 75 25.00000 1
#> 3: 6920 550 1 68 25.00000 0
#> 4: 7960 870 1 29 25.00000 0
#> 5: 9030 20 2 34 16.66667 0
#> ---
#> 4576: 7900 278 1000 93 16.66667 1
#> 4577: 1420 987 1000 62 16.66667 0
#> 4578: 8900 684 1000 60 16.66667 0
#> 4579: 3880 294 1000 26 16.66667 1
#> 4580: 4830 911 1000 64 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 96 25.00000 0
#> 2: 2530 28 1 75 25.00000 1
#> 3: 6920 550 1 68 25.00000 0
#> 4: 7960 870 1 29 25.00000 0
#> 5: 9030 20 2 34 16.66667 0
#> ---
#> 4576: 7900 278 1000 93 16.66667 1
#> 4577: 1420 987 1000 62 16.66667 0
#> 4578: 8900 684 1000 60 16.66667 0
#> 4579: 3880 294 1000 26 16.66667 1
#> 4580: 4830 911 1000 64 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 96 25.00000 0
#> 2: 2530 28 1 75 25.00000 1
#> 3: 6920 550 1 68 25.00000 0
#> 4: 7960 870 1 29 25.00000 0
#> 5: 9030 20 2 34 16.66667 0
#> ---
#> 4576: 7900 278 1000 93 16.66667 1
#> 4577: 1420 987 1000 62 16.66667 0
#> 4578: 8900 684 1000 60 16.66667 0
#> 4579: 3880 294 1000 26 16.66667 1
#> 4580: 4830 911 1000 64 16.66667 0
#> cnt_males cnt_highincome mixed
#> 1: 1 0 -9
#> 2: 0 0 2
#> 3: 1 0 -5
#> 4: 1 0 -2
#> 5: 1 1 10
#> ---
#> 4576: 0 0 -3
#> 4577: 1 0 3
#> 4578: 1 0 -3
#> 4579: 0 0 -7
#> 4580: 1 0 0
# 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$numvars()
#> [1] "expend" "income" "savings" "mixed"
# create perturbation parameters for "total" variable and
# write to yaml-file
# create a ptable using functionality from the ptable-pkg
f_yaml <- tempfile(fileext = ".yaml")
p_cnts1 <- ck_params_cnts(
ptab = ptable::pt_ex_cnts(),
path = f_yaml)
#> yaml configuration '/tmp/RtmpV7PINT/file19623d81aba1.yaml' successfully written.
# read parameters from yaml-file and set them for variable `"total"`
p_cnts1 <- ck_read_yaml(path = f_yaml)
tab$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 271794 4580 271794.0000
#> 2: Total age_group1 total 1969 115924 1971 116041.7491
#> 3: Total ag1a total 1969 115924 1971 116041.7491
#> 4: Total age_group2 total 1143 68184 1144 68243.6535
#> 5: Total ag2a total 1143 68184 1144 68243.6535
#> 6: Total age_group3 total 864 52054 866 52174.4954
#> 7: Total age_group4 total 423 24571 423 24571.0000
#> 8: Total age_group5 total 168 10321 169 10382.4345
#> 9: Total age_group6 total 13 740 12 683.0769
#> 10: male Total total 2296 135847 2298 135965.3336
#> 11: m Total total 2296 135847 2298 135965.3336
#> 12: male age_group1 total 1015 59743 1016 59801.8601
#> 13: m age_group1 total 1015 59743 1016 59801.8601
#> 14: male ag1a total 1015 59743 1016 59801.8601
#> 15: m ag1a total 1015 59743 1016 59801.8601
#> 16: male age_group2 total 571 33900 571 33900.0000
#> 17: m age_group2 total 571 33900 571 33900.0000
#> 18: male ag2a total 571 33900 571 33900.0000
#> 19: m ag2a total 571 33900 571 33900.0000
#> 20: male age_group3 total 424 25549 425 25609.2571
#> 21: m age_group3 total 424 25549 425 25609.2571
#> 22: male age_group4 total 195 11317 194 11258.9641
#> 23: m age_group4 total 195 11317 194 11258.9641
#> 24: male age_group5 total 84 4958 84 4958.0000
#> 25: m age_group5 total 84 4958 84 4958.0000
#> 26: male age_group6 total 7 380 6 325.7143
#> 27: m age_group6 total 7 380 6 325.7143
#> 28: female Total total 2284 135947 2284 135947.0000
#> 29: f Total total 2284 135947 2284 135947.0000
#> 30: female age_group1 total 954 56181 953 56122.1101
#> 31: f age_group1 total 954 56181 953 56122.1101
#> 32: female ag1a total 954 56181 953 56122.1101
#> 33: f ag1a total 954 56181 953 56122.1101
#> 34: female age_group2 total 572 34284 572 34284.0000
#> 35: f age_group2 total 572 34284 572 34284.0000
#> 36: female ag2a total 572 34284 572 34284.0000
#> 37: f ag2a total 572 34284 572 34284.0000
#> 38: female age_group3 total 440 26505 439 26444.7614
#> 39: f age_group3 total 440 26505 439 26444.7614
#> 40: female age_group4 total 228 13254 227 13195.8684
#> 41: f age_group4 total 228 13254 227 13195.8684
#> 42: female age_group5 total 84 5363 84 5363.0000
#> 43: f age_group5 total 84 5363 84 5363.0000
#> 44: female age_group6 total 6 360 5 300.0000
#> 45: f age_group6 total 6 360 5 300.0000
#> 46: Total Total cnt_males 2296 135847 2300 136083.6672
#> 47: Total age_group1 cnt_males 1015 59743 1016 59801.8601
#> 48: Total ag1a cnt_males 1015 59743 1016 59801.8601
#> 49: Total age_group2 cnt_males 571 33900 571 33900.0000
#> 50: Total ag2a cnt_males 571 33900 571 33900.0000
#> 51: Total age_group3 cnt_males 424 25549 426 25669.5142
#> 52: Total age_group4 cnt_males 195 11317 194 11258.9641
#> 53: Total age_group5 cnt_males 84 4958 84 4958.0000
#> 54: Total age_group6 cnt_males 7 380 5 271.4286
#> 55: male Total cnt_males 2296 135847 2300 136083.6672
#> 56: m Total cnt_males 2296 135847 2300 136083.6672
#> 57: male age_group1 cnt_males 1015 59743 1016 59801.8601
#> 58: m age_group1 cnt_males 1015 59743 1016 59801.8601
#> 59: male ag1a cnt_males 1015 59743 1016 59801.8601
#> 60: m ag1a cnt_males 1015 59743 1016 59801.8601
#> 61: male age_group2 cnt_males 571 33900 571 33900.0000
#> 62: m age_group2 cnt_males 571 33900 571 33900.0000
#> 63: male ag2a cnt_males 571 33900 571 33900.0000
#> 64: m ag2a cnt_males 571 33900 571 33900.0000
#> 65: male age_group3 cnt_males 424 25549 426 25669.5142
#> 66: m age_group3 cnt_males 424 25549 426 25669.5142
#> 67: male age_group4 cnt_males 195 11317 194 11258.9641
#> 68: m age_group4 cnt_males 195 11317 194 11258.9641
#> 69: male age_group5 cnt_males 84 4958 84 4958.0000
#> 70: m age_group5 cnt_males 84 4958 84 4958.0000
#> 71: male age_group6 cnt_males 7 380 5 271.4286
#> 72: m age_group6 cnt_males 7 380 5 271.4286
#> 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/file196210088919.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 1362164655 1362309587
#> 2: Total age_group1 income 9810547 576139868 576201080
#> 3: Total ag1a income 9810547 576139868 576201080
#> 4: Total age_group2 income 5692119 339190840 339210606
#> 5: Total ag2a income 5692119 339190840 339210606
#> 6: Total age_group3 income 4406946 266009840 265934534
#> 7: Total age_group4 income 2133543 124517758 124388087
#> 8: Total age_group5 income 848151 52502198 52538133
#> 9: Total age_group6 income 61672 3804151 3997489
#> 10: male Total income 11262049 669230647 669162762
#> 11: m Total income 11262049 669230647 669162762
#> 12: male age_group1 income 4877164 287875791 287821837
#> 13: m age_group1 income 4877164 287875791 287821837
#> 14: male ag1a income 4877164 287875791 287821837
#> 15: m ag1a income 4877164 287875791 287821837
#> 16: male age_group2 income 2811379 167710504 167779242
#> 17: m age_group2 income 2811379 167710504 167779242
#> 18: male ag2a income 2811379 167710504 167779242
#> 19: m ag2a income 2811379 167710504 167779242
#> 20: male age_group3 income 2168169 130878177 130799853
#> 21: m age_group3 income 2168169 130878177 130799853
#> 22: male age_group4 income 978510 57071677 56976920
#> 23: m age_group4 income 978510 57071677 56976920
#> 24: male age_group5 income 393134 23652582 23252574
#> 25: m age_group5 income 393134 23652582 23252574
#> 26: male age_group6 income 33693 2041916 2180102
#> 27: m age_group6 income 33693 2041916 2180102
#> 28: female Total income 11690929 692934008 693064101
#> 29: f Total income 11690929 692934008 693064101
#> 30: female age_group1 income 4933383 288264077 288175524
#> 31: f age_group1 income 4933383 288264077 288175524
#> 32: female ag1a income 4933383 288264077 288175524
#> 33: f ag1a income 4933383 288264077 288175524
#> 34: female age_group2 income 2880740 171480336 171525493
#> 35: f age_group2 income 2880740 171480336 171525493
#> 36: female ag2a income 2880740 171480336 171525493
#> 37: f ag2a income 2880740 171480336 171525493
#> 38: female age_group3 income 2238777 135131663 135018748
#> 39: f age_group3 income 2238777 135131663 135018748
#> 40: female age_group4 income 1155033 67446081 67447018
#> 41: f age_group4 income 1155033 67446081 67447018
#> 42: female age_group5 income 455017 28849616 28870115
#> 43: f age_group5 income 455017 28849616 28870115
#> 44: female age_group6 income 27979 1762235 1572808
#> 45: f age_group6 income 27979 1762235 1572808
#> sex age vname uws ws pws
tab$numtab("income", mean_before_sum = FALSE)
#> sex age vname uws ws pws
#> 1: Total Total income 22952978 1362164655 1362237119
#> 2: Total age_group1 income 9810547 576139868 576170473
#> 3: Total ag1a income 9810547 576139868 576170473
#> 4: Total age_group2 income 5692119 339190840 339200723
#> 5: Total ag2a income 5692119 339190840 339200723
#> 6: Total age_group3 income 4406946 266009840 265972184
#> 7: Total age_group4 income 2133543 124517758 124452906
#> 8: Total age_group5 income 848151 52502198 52520162
#> 9: Total age_group6 income 61672 3804151 3899622
#> 10: male Total income 11262049 669230647 669196704
#> 11: m Total income 11262049 669230647 669196704
#> 12: male age_group1 income 4877164 287875791 287848813
#> 13: m age_group1 income 4877164 287875791 287848813
#> 14: male ag1a income 4877164 287875791 287848813
#> 15: m ag1a income 4877164 287875791 287848813
#> 16: male age_group2 income 2811379 167710504 167744869
#> 17: m age_group2 income 2811379 167710504 167744869
#> 18: male ag2a income 2811379 167710504 167744869
#> 19: m ag2a income 2811379 167710504 167744869
#> 20: male age_group3 income 2168169 130878177 130839009
#> 21: m age_group3 income 2168169 130878177 130839009
#> 22: male age_group4 income 978510 57071677 57024279
#> 23: m age_group4 income 978510 57071677 57024279
#> 24: male age_group5 income 393134 23652582 23451725
#> 25: m age_group5 income 393134 23652582 23451725
#> 26: male age_group6 income 33693 2041916 2109878
#> 27: m age_group6 income 33693 2041916 2109878
#> 28: female Total income 11690929 692934008 692999051
#> 29: f Total income 11690929 692934008 692999051
#> 30: female age_group1 income 4933383 288264077 288219797
#> 31: f age_group1 income 4933383 288264077 288219797
#> 32: female ag1a income 4933383 288264077 288219797
#> 33: f ag1a income 4933383 288264077 288219797
#> 34: female age_group2 income 2880740 171480336 171502913
#> 35: f age_group2 income 2880740 171480336 171502913
#> 36: female ag2a income 2880740 171480336 171502913
#> 37: f ag2a income 2880740 171480336 171502913
#> 38: female age_group3 income 2238777 135131663 135075194
#> 39: f age_group3 income 2238777 135131663 135075194
#> 40: female age_group4 income 1155033 67446081 67446549
#> 41: f age_group4 income 1155033 67446081 67446549
#> 42: female age_group5 income 455017 28849616 28859864
#> 43: f age_group5 income 455017 28849616 28859864
#> 44: female age_group6 income 27979 1762235 1664830
#> 45: f age_group6 income 27979 1762235 1664830
#> sex age vname uws ws pws
tab$numtab("savings")
#> sex age vname uws ws pws
#> 1: Total Total savings 2273532 134518023 134513574.8
#> 2: Total age_group1 savings 982386 57935027 57935605.0
#> 3: Total ag1a savings 982386 57935027 57935605.0
#> 4: Total age_group2 savings 552336 32523348 32525608.1
#> 5: Total ag2a savings 552336 32523348 32525608.1
#> 6: Total age_group3 savings 437101 26265889 26272668.8
#> 7: Total age_group4 savings 214661 12467508 12464910.1
#> 8: Total age_group5 savings 80451 4960971 4962553.6
#> 9: Total age_group6 savings 6597 365280 369217.0
#> 10: male Total savings 1159816 68512317 68515227.4
#> 11: m Total savings 1159816 68512317 68515227.4
#> 12: male age_group1 savings 517660 30546216 30543797.5
#> 13: m age_group1 savings 517660 30546216 30543797.5
#> 14: male ag1a savings 517660 30546216 30543797.5
#> 15: m ag1a savings 517660 30546216 30543797.5
#> 16: male age_group2 savings 280923 16551066 16553928.8
#> 17: m age_group2 savings 280923 16551066 16553928.8
#> 18: male ag2a savings 280923 16551066 16553928.8
#> 19: m ag2a savings 280923 16551066 16553928.8
#> 20: male age_group3 savings 214970 12836619 12842366.6
#> 21: m age_group3 savings 214970 12836619 12842366.6
#> 22: male age_group4 savings 99420 5795677 5790691.0
#> 23: m age_group4 savings 99420 5795677 5790691.0
#> 24: male age_group5 savings 43233 2604461 2589031.6
#> 25: m age_group5 savings 43233 2604461 2589031.6
#> 26: male age_group6 savings 3610 178278 179192.5
#> 27: m age_group6 savings 3610 178278 179192.5
#> 28: female Total savings 1113716 66005706 66009443.1
#> 29: f Total savings 1113716 66005706 66009443.1
#> 30: female age_group1 savings 464726 27388811 27394755.1
#> 31: f age_group1 savings 464726 27388811 27394755.1
#> 32: female ag1a savings 464726 27388811 27394755.1
#> 33: f ag1a savings 464726 27388811 27394755.1
#> 34: female age_group2 savings 271413 15972282 15974225.2
#> 35: f age_group2 savings 271413 15972282 15974225.2
#> 36: female ag2a savings 271413 15972282 15974225.2
#> 37: f ag2a savings 271413 15972282 15974225.2
#> 38: female age_group3 savings 222131 13429270 13423492.6
#> 39: f age_group3 savings 222131 13429270 13423492.6
#> 40: female age_group4 savings 115241 6671831 6673815.4
#> 41: f age_group4 savings 115241 6671831 6673815.4
#> 42: female age_group5 savings 37218 2356510 2357421.8
#> 43: f age_group5 savings 37218 2356510 2357421.8
#> 44: female age_group6 savings 2987 187002 180198.5
#> 45: f age_group6 savings 2987 187002 180198.5
#> 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 271794 4580 271794.0000
#> 2: Total age_group1 total 1969 115924 1971 116041.7491
#> 3: Total ag1a total 1969 115924 1971 116041.7491
#> 4: Total age_group2 total 1143 68184 1144 68243.6535
#> 5: Total ag2a total 1143 68184 1144 68243.6535
#> 6: Total age_group3 total 864 52054 866 52174.4954
#> 7: Total age_group4 total 423 24571 423 24571.0000
#> 8: Total age_group5 total 168 10321 169 10382.4345
#> 9: Total age_group6 total 13 740 12 683.0769
#> 10: male Total total 2296 135847 2298 135965.3336
#> 11: m Total total 2296 135847 2298 135965.3336
#> 12: male age_group1 total 1015 59743 1016 59801.8601
#> 13: m age_group1 total 1015 59743 1016 59801.8601
#> 14: male ag1a total 1015 59743 1016 59801.8601
#> 15: m ag1a total 1015 59743 1016 59801.8601
#> 16: male age_group2 total 571 33900 571 33900.0000
#> 17: m age_group2 total 571 33900 571 33900.0000
#> 18: male ag2a total 571 33900 571 33900.0000
#> 19: m ag2a total 571 33900 571 33900.0000
#> 20: male age_group3 total 424 25549 425 25609.2571
#> 21: m age_group3 total 424 25549 425 25609.2571
#> 22: male age_group4 total 195 11317 194 11258.9641
#> 23: m age_group4 total 195 11317 194 11258.9641
#> 24: male age_group5 total 84 4958 84 4958.0000
#> 25: m age_group5 total 84 4958 84 4958.0000
#> 26: male age_group6 total 7 380 6 325.7143
#> 27: m age_group6 total 7 380 6 325.7143
#> 28: female Total total 2284 135947 2284 135947.0000
#> 29: f Total total 2284 135947 2284 135947.0000
#> 30: female age_group1 total 954 56181 953 56122.1101
#> 31: f age_group1 total 954 56181 953 56122.1101
#> 32: female ag1a total 954 56181 953 56122.1101
#> 33: f ag1a total 954 56181 953 56122.1101
#> 34: female age_group2 total 572 34284 572 34284.0000
#> 35: f age_group2 total 572 34284 572 34284.0000
#> 36: female ag2a total 572 34284 572 34284.0000
#> 37: f ag2a total 572 34284 572 34284.0000
#> 38: female age_group3 total 440 26505 439 26444.7614
#> 39: f age_group3 total 440 26505 439 26444.7614
#> 40: female age_group4 total 228 13254 227 13195.8684
#> 41: f age_group4 total 228 13254 227 13195.8684
#> 42: female age_group5 total 84 5363 84 5363.0000
#> 43: f age_group5 total 84 5363 84 5363.0000
#> 44: female age_group6 total 6 360 5 300.0000
#> 45: f age_group6 total 6 360 5 300.0000
#> 46: Total Total cnt_males 2296 135847 2298 135965.3336
#> 47: Total age_group1 cnt_males 1015 59743 1016 59801.8601
#> 48: Total ag1a cnt_males 1015 59743 1016 59801.8601
#> 49: Total age_group2 cnt_males 571 33900 571 33900.0000
#> 50: Total ag2a cnt_males 571 33900 571 33900.0000
#> 51: Total age_group3 cnt_males 424 25549 425 25609.2571
#> 52: Total age_group4 cnt_males 195 11317 194 11258.9641
#> 53: Total age_group5 cnt_males 84 4958 84 4958.0000
#> 54: Total age_group6 cnt_males 7 380 6 325.7143
#> 55: male Total cnt_males 2296 135847 2298 135965.3336
#> 56: m Total cnt_males 2296 135847 2298 135965.3336
#> 57: male age_group1 cnt_males 1015 59743 1016 59801.8601
#> 58: m age_group1 cnt_males 1015 59743 1016 59801.8601
#> 59: male ag1a cnt_males 1015 59743 1016 59801.8601
#> 60: m ag1a cnt_males 1015 59743 1016 59801.8601
#> 61: male age_group2 cnt_males 571 33900 571 33900.0000
#> 62: m age_group2 cnt_males 571 33900 571 33900.0000
#> 63: male ag2a cnt_males 571 33900 571 33900.0000
#> 64: m ag2a cnt_males 571 33900 571 33900.0000
#> 65: male age_group3 cnt_males 424 25549 425 25609.2571
#> 66: m age_group3 cnt_males 424 25549 425 25609.2571
#> 67: male age_group4 cnt_males 195 11317 194 11258.9641
#> 68: m age_group4 cnt_males 195 11317 194 11258.9641
#> 69: male age_group5 cnt_males 84 4958 84 4958.0000
#> 70: m age_group5 cnt_males 84 4958 84 4958.0000
#> 71: male age_group6 cnt_males 7 380 6 325.7143
#> 72: m age_group6 cnt_males 7 380 6 325.7143
#> 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 5 0.1111111
#> 2: -1 9 0.2000000
#> 3: 0 16 0.3555556
#> 4: 1 15 0.3333333
#>
#> $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 1.000 0.001 0.015
#> 6: Mean 0.756 0.017 0.034
#> 7: Median 1.000 0.001 0.016
#> 8: Q60 1.000 0.001 0.021
#> 9: Q70 1.000 0.002 0.024
#> 10: Q80 1.000 0.004 0.033
#> 11: Q90 1.600 0.049 0.100
#> 12: Q95 2.000 0.143 0.196
#> 13: Q99 2.000 0.167 0.213
#> 14: Max 2.000 0.167 0.213
#>
#> $cumdistr_d1
#> cat cnt pct
#> 1: 0 16 0.3555556
#> 2: 1 40 0.8888889
#> 3: 2 45 1.0000000
#>
#> $cumdistr_d2
#> cat cnt pct
#> 1: [0,0.02] 40 0.8888889
#> 2: (0.02,0.05] 40 0.8888889
#> 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] 26 0.5777778
#> 2: (0.02,0.05] 40 0.8888889
#> 3: (0.05,0.1] 40 0.8888889
#> 4: (0.1,0.2] 43 0.9555556
#> 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 0.4611279 total
#> 2: Total age_group1 17 2 0.9584550 total
#> 3: Total ag1a 17 2 0.9584550 total
#> 4: Total age_group2 16 1 0.9296913 total
#> 5: Total ag2a 16 1 0.9296913 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 Max
#> 1: total -1 -1 -1 -1 0 0.089 0 0 0.8 1 1.6 2.0 2 2
#> 2: cnt_highincome -1 -1 -1 0 0 0.311 0 1 1.0 1 2.0 2.0 2 2
#> 3: cnt_males -1 -1 0 0 0 0.200 0 0 0.0 1 1.0 1.8 2 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 0.000 0.000 0.000
#> 5: Q40 1.000 0.001 0.015
#> 6: Mean 0.756 0.017 0.034
#> 7: Median 1.000 0.001 0.016
#> 8: Q60 1.000 0.001 0.021
#> 9: Q70 1.000 0.002 0.024
#> 10: Q80 1.000 0.004 0.033
#> 11: Q90 1.600 0.049 0.100
#> 12: Q95 2.000 0.143 0.196
#> 13: Q99 2.000 0.167 0.213
#> 14: Max 2.000 0.167 0.213
#>
#> ✔ 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 1.000 0.001 0.016
#> 6: Mean 0.778 0.017 0.034
#> 7: Median 1.000 0.001 0.016
#> 8: Q60 1.000 0.001 0.021
#> 9: Q70 1.000 0.002 0.024
#> 10: Q80 1.000 0.005 0.034
#> 11: Q90 1.400 0.060 0.100
#> 12: Q95 2.000 0.143 0.196
#> 13: Q99 2.000 0.143 0.196
#> 14: Max 2.000 0.143 0.196
#>
#> ✔ 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 0.008 0.045
#> 5: Q40 1.0 0.010 0.052
#> 6: Mean 0.9 0.024 0.065
#> 7: Median 1.0 0.011 0.054
#> 8: Q60 1.0 0.015 0.061
#> 9: Q70 1.0 0.024 0.078
#> 10: Q80 1.0 0.035 0.127
#> 11: Q90 2.0 0.067 0.131
#> 12: Q95 2.0 0.075 0.135
#> 13: Q99 2.0 0.143 0.196
#> 14: Max 2.0 0.143 0.196
#>
#> ┌──────────────────────────────────────────────────┐
#> │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 -200856.60 -61499.112 -44903.362 -39167.964 -29764.378 -12354.064
#> 3: savings -15429.42 -5777.418 -2967.973 -1819.231 913.437 237.221
#> 4: mixed Inf NA NA NA NA NaN
#> Median Q60 Q70 Q80 Q90 Q95 Q99
#> 1: NA NA NA NA NA NA NA
#> 2: 468.356 10247.663 22577.239 34365.341 65043.398 67961.875 85347.938
#> 3: 1943.244 2094.693 2862.792 3737.088 5865.515 5944.149 6412.108
#> 4: NA NA NA NA NA NA NA
#> Max
#> 1: -Inf
#> 2: 95471.07
#> 3: 6779.79
#> 4: -Inf
# }