Codebook

knitr::opts_chunk$set(
  warning = FALSE, # show warnings during codebook generation
  message = FALSE, # show messages during codebook generation
  error = TRUE, # do not interrupt codebook generation in case of errors,
                # usually better for debugging
  echo = TRUE  # show R code
)
ggplot2::theme_set(ggplot2::theme_bw())

# set base directory
basedir = "/home/ecco_rais/data/clean/RAIS-homogenized/output/"
# adjust as necessary
startyear = 2003
endyear = 2004

# libraries
library(codebook)
library(rio)

# Start the codebook loop

#for ( year in startyear:endyear) {
year = "2015"
    # for CSV
    codebook_data <- fread(file.path(basedir, paste0("harmo_", year, ".csv")))

    # omit the following lines, if your missing values are already properly labelled
    codebook_data <- detect_missing(codebook_data,
        only_labelled = TRUE, # only labelled values are autodetected as
                              # missing
        negative_values_are_missing = FALSE, # negative values are missing values
        ninety_nine_problems = TRUE,   # 99/999 are missing values, if they
                                      # are more than 5 MAD from the median
    )

    # If you are not using formr, the codebook package needs to guess which items
    # form a scale. The following line finds item aggregates with names like this:
    # scale = scale_1 + scale_2R + scale_3R
    # identifying these aggregates allows the codebook function to
    # automatically compute reliabilities.
    # However, it will not reverse items automatically.
    codebook_data <- detect_scales(codebook_data)

## Warning in detect_scales(codebook_data): cbo items found, but no aggregate

## Warning in detect_scales(codebook_data): cnae items found, but no aggregate

## Warning in detect_scales(codebook_data): active items found, but no aggregate

    codebook_data <- as.data.table(codebook_data)
    codebook(codebook_data)

## Warning: Couldn't find skimmers for class: integer64; No user-defined `sfl` provided. Falling
## back to `character`.

## Warning in grepl("^\\s+$", x): input string 1 is invalid in this locale

## Warning in grepl("^\\s+$", x): input string 2 is invalid in this locale

## Warning in grepl("^\\s+$", x): input string 3 is invalid in this locale

## Warning in grepl("^\\s+$", x): input string 4 is invalid in this locale

## Warning in grepl("^\\s+$", x): input string 5 is invalid in this locale

## Warning in max(f): no non-missing arguments to max; returning -Inf

## Warning: Couldn't find skimmers for class: integer64; No user-defined `sfl` provided. Falling
## back to `character`.

## Warning in max(f): no non-missing arguments to max; returning -Inf

## Warning: Couldn't find skimmers for class: integer64; No user-defined `sfl` provided. Falling
## back to `character`.

## Warning: Couldn't find skimmers for class: integer64; No user-defined `sfl` provided. Falling
## back to `character`.

## Warning: Couldn't find skimmers for class: integer64; No user-defined `sfl` provided. Falling
## back to `character`.

## Warning: Couldn't find skimmers for class: integer64; No user-defined `sfl` provided. Falling
## back to `character`.

## Warning: Couldn't find skimmers for class: integer64; No user-defined `sfl` provided. Falling
## back to `character`.

## Warning: Couldn't find skimmers for class: integer64; No user-defined `sfl` provided. Falling
## back to `character`.

## Warning in grepl("^\\s+$", x): input string 1 is invalid in this locale

## Warning in grepl("^\\s+$", x): input string 2 is invalid in this locale

## Warning in grepl("^\\s+$", x): input string 3 is invalid in this locale

## Warning in grepl("^\\s+$", x): input string 4 is invalid in this locale

## Warning in grepl("^\\s+$", x): input string 5 is invalid in this locale

## Warning: Couldn't find skimmers for class: integer64; No user-defined `sfl` provided. Falling
## back to `character`.

## Warning: Couldn't find skimmers for class: integer64; No user-defined `sfl` provided. Falling
## back to `character`.

## Warning: Couldn't find skimmers for class: integer64; No user-defined `sfl` provided. Falling
## back to `character`.

## Warning: Couldn't find skimmers for class: integer64; No user-defined `sfl` provided. Falling
## back to `character`.

## Warning in grepl("^\\s+$", x): input string 1 is invalid in this locale

## Warning in grepl("^\\s+$", x): input string 2 is invalid in this locale

## Warning in grepl("^\\s+$", x): input string 3 is invalid in this locale

## Warning in grepl("^\\s+$", x): input string 4 is invalid in this locale

## Warning in grepl("^\\s+$", x): input string 5 is invalid in this locale

Metadata

Description

Dataset name: codebook_data

The dataset has N=72175102 rows and 65 columns. 0 rows have no missing values on any column.

Metadata for search engines

• Date published: 2024-06-04

x adm_date yr_arrival cbo94 cbo02 cei zip_establishment cnae20 cnae20sub cnae95 firmID cnpj_root cpf dob termination_day schooling ibge_subsetor age cei_avail pat disabled simples alvara_ind termination_month separation_cause muni_job muni nationality legal_form name ctps pis hired_hours race_color estab_name sex establishment_size tenure adm_type disability_type firmID_type wage_type contract_type active1231 earn_april earn_august earn_feb earn_jan earn_july earn_june earn_may earn_march earn_nov earn_oct earn_sept earn_dec_mw earn_dec mean_earn_mw mean_earn hired_wage last_wage yr termination_year adm_day adm_month adm_year

#Variables

adm_date

Distribution

Distribution of values for adm_date

0 missing values.

Summary statistics

name	data_type	n_missing	complete_rate	min	median	max	mean	sd	hist	label
adm_date	numeric	0	1	1e+06	5062013	3.1e+07	8747048	8447186	▇▂▂▂▁	NA

yr_arrival

Distribution

Distribution of values for yr_arrival

0 missing values.

Summary statistics

name	data_type	n_missing	complete_rate	min	median	max	mean	sd	hist	label
yr_arrival	numeric	0	1	0	0	2015	6.201475	111.3594	▇▁▁▁▁	NA

cbo94

Distribution

## Error in if (stats::median(table(x)) == 1) {: missing value where TRUE/FALSE needed

## No non-missing values to show.

72175102 missing values.

Summary statistics

name	data_type	n_missing	complete_rate	count	label
cbo94	logical	72175102	0	:	NA

cbo02

Distribution

Distribution of values for cbo02

72464 missing values.

Summary statistics

name	data_type	n_missing	complete_rate	min	median	max	mean	sd	hist	label
cbo02	numeric	72464	0.998996	10105	514215	992225	504361.5	204871	▁▃▇▅▁	NA

cei

Distribution

## Error in `ggplot2::geom_histogram()`:
## ! Problem while computing position.
## ℹ Error occurred in the 1st layer.
## Caused by error in `if (...) NULL`:
## ! missing value where TRUE/FALSE needed

0 missing values.

Summary statistics

name	data_type	n_missing	complete_rate	n_unique	empty	min	max	whitespace	label
cei	character	0	1	57175	0	1	21	0	NA

zip_establishment

Distribution

Distribution of values for zip_establishment

0 missing values.

Summary statistics

name	data_type	n_missing	complete_rate	min	median	max	mean	sd	hist	label
zip_establishment	numeric	0	1	1e+06	4.2e+07	1e+08	46755146	31326630	▇▆▃▅▆	NA

cnae20

Distribution

Distribution of values for cnae20

0 missing values.

Summary statistics

name	data_type	n_missing	complete_rate	min	median	max	mean	sd	hist	label
cnae20	numeric	0	1	1113	49302	99008	55898.66	25688.7	▂▂▇▂▇	NA

cnae20sub

Distribution

Distribution of values for cnae20sub

0 missing values.

Summary statistics

name	data_type	n_missing	complete_rate	min	median	max	mean	sd	hist	label
cnae20sub	numeric	0	1	111301	4930201	9900800	5589874	2568868	▂▂▇▂▇	NA

cnae95

Distribution

Distribution of values for cnae95

0 missing values.

Summary statistics

name	data_type	n_missing	complete_rate	min	median	max	mean	sd	hist	label
cnae95	numeric	0	1	1112	55212	99007	56291.83	22343.31	▂▂▇▇▂	NA

firmID

Distribution

## Error in `ggplot2::geom_histogram()`:
## ! Problem while computing stat.
## ℹ Error occurred in the 1st layer.
## Caused by error in `seq_len()`:
## ! argument must be coercible to non-negative integer

0 missing values.

Summary statistics

name	data_type	n_missing	complete_rate	n_unique	empty	min	max	whitespace	label
firmID	character	0	1	3917168	0	15	21	0	NA

cnpj_root

Distribution

Distribution of values for cnpj_root

0 missing values.

Summary statistics

name	data_type	n_missing	complete_rate	min	median	max	mean	sd	hist	label
cnpj_root	numeric	0	1	0	1.2e+07	1e+08	23921149	26140118	▇▁▁▁▁	NA

cpf

Distribution

## Error in `ggplot2::geom_histogram()`:
## ! Problem while computing position.
## ℹ Error occurred in the 1st layer.
## Caused by error in `if (...) NULL`:
## ! missing value where TRUE/FALSE needed

0 missing values.

Summary statistics

name	data_type	n_missing	complete_rate	n_unique	empty	min	max	whitespace	label
cpf	character	0	1	59715553	0	1	21	0	NA

dob

Distribution

Distribution of values for dob

0 missing values.

Summary statistics

name	data_type	n_missing	complete_rate	min	median	max	mean	sd	hist	label
dob	numeric	0	1	1e+06	1.6e+07	3.1e+07	15664215	8782781	▇▇▇▇▇	NA

termination_day

Distribution

Distribution of values for termination_day

0 missing values.

Summary statistics

name	data_type	n_missing	complete_rate	n_unique	empty	min	max	whitespace	label
termination_day	character	0	1	32	0	2	2	0	NA

schooling

Distribution

Distribution of values for schooling

0 missing values.

Summary statistics

name	data_type	n_missing	complete_rate	min	median	max	mean	sd	hist	label
schooling	numeric	0	1	1	7	11	6.624275	1.740355	▁▂▇▃▁	NA

ibge_subsetor

Distribution

Distribution of values for ibge_subsetor

0 missing values.

Summary statistics

name	data_type	n_missing	complete_rate	min	median	max	mean	sd	hist	label
ibge_subsetor	numeric	0	1	1	19	25	17.83081	5.34124	▁▁▃▇▇	NA

age

Distribution

Distribution of values for age

0 missing values.

Summary statistics

name	data_type	n_missing	complete_rate	min	median	max	mean	sd	hist	label
age	numeric	0	1	0	34	100	35.73383	11.69908	▁▇▃▁▁	NA

cei_avail

Distribution

Distribution of values for cei_avail

0 missing values.

Summary statistics

name	data_type	n_missing	complete_rate	min	median	max	mean	sd	hist	label
cei_avail	numeric	0	1	0	0	1	0.0196325	0.1387337	▇▁▁▁▁	NA

pat

Distribution

Distribution of values for pat

0 missing values.

Summary statistics

name	data_type	n_missing	complete_rate	min	median	max	mean	sd	hist	label
pat	numeric	0	1	0	0	1	0.2962584	0.4566063	▇▁▁▁▃	NA

disabled

Distribution

Distribution of values for disabled

0 missing values.

Summary statistics

name	data_type	n_missing	complete_rate	min	median	max	mean	sd	hist	label
disabled	numeric	0	1	0	0	1	0.0073619	0.085485	▇▁▁▁▁	NA

simples

Distribution

Distribution of values for simples

0 missing values.

Summary statistics

name	data_type	n_missing	complete_rate	min	median	max	mean	sd	hist	label
simples	numeric	0	1	0	0	1	0.2441982	0.4296108	▇▁▁▁▂	NA

alvara_ind

Distribution

Distribution of values for alvara_ind

0 missing values.

Summary statistics

name	data_type	n_missing	complete_rate	min	median	max	mean	sd	hist	label
alvara_ind	numeric	0	1	0	0	1	8.32e-05	0.0091233	▇▁▁▁▁	NA

termination_month

Distribution

Distribution of values for termination_month

0 missing values.

Summary statistics

name	data_type	n_missing	complete_rate	min	median	max	mean	sd	hist	label
termination_month	numeric	0	1	0	0	12	2.166322	3.668442	▇▁▁▁▁	NA

separation_cause

Distribution

Distribution of values for separation_cause

0 missing values.

Summary statistics

name	data_type	n_missing	complete_rate	min	median	max	mean	sd	hist	label
separation_cause	numeric	0	1	0	0	80	5.170032	8.830313	▇▁▁▁▁	NA

muni_job

Distribution

Distribution of values for muni_job

0 missing values.

Summary statistics

name	data_type	n_missing	complete_rate	min	median	max	mean	sd	hist	label
muni_job	numeric	0	1	110001	351740	530010	344983.8	87857.74	▁▂▇▂▁	NA

muni

Distribution

Distribution of values for muni

0 missing values.

Summary statistics

name	data_type	n_missing	complete_rate	min	median	max	mean	sd	hist	label
muni	numeric	0	1	110001	351740	530010	344978.3	87850.64	▁▂▇▂▁	NA

nationality

Distribution

Distribution of values for nationality

0 missing values.

Summary statistics

name	data_type	n_missing	complete_rate	min	median	max	mean	sd	hist	label
nationality	numeric	0	1	10	10	80	10.09069	1.845928	▇▁▁▁▁	NA

legal_form

Distribution

Distribution of values for legal_form

0 missing values.

Summary statistics

name	data_type	n_missing	complete_rate	min	median	max	mean	sd	hist	label
legal_form	numeric	0	1	1015	2062	5037	2052.667	655.1724	▂▇▁▁▁	NA

name

Distribution

Distribution of values for name

0 missing values.

Summary statistics

name	data_type	n_missing	complete_rate	n_unique	empty	min	max	whitespace	label
name	character	0	1	43263289	0	2	52	0	NA

ctps

Distribution

Distribution of values for ctps

0 missing values.

Summary statistics

name	data_type	n_missing	complete_rate	min	median	max	mean	sd	hist	label
ctps	numeric	0	1	0	65647	1e+08	1378332	4196236	▇▁▁▁▁	NA

pis

Distribution

## Error in `ggplot2::geom_histogram()`:
## ! Problem while computing stat.
## ℹ Error occurred in the 1st layer.
## Caused by error in `seq_len()`:
## ! argument must be coercible to non-negative integer

0 missing values.

Summary statistics

name	data_type	n_missing	complete_rate	n_unique	empty	min	max	whitespace	label
pis	character	0	1	59856891	0	13	21	0	NA

hired_hours

Distribution

Distribution of values for hired_hours

0 missing values.

Summary statistics

name	data_type	n_missing	complete_rate	min	median	max	mean	sd	hist	label
hired_hours	numeric	0	1	1	44	44	41.06636	6.533493	▁▁▁▁▇	NA

race_color

Distribution

Distribution of values for race_color

10188449 missing values.

Summary statistics

name	data_type	n_missing	complete_rate	min	median	max	mean	sd	hist	label
race_color	numeric	10188449	0.8588371	1	2	9	4.802952	3.022193	▇▁▁▁▇	NA

estab_name

Distribution

Distribution of values for estab_name

0 missing values.

Summary statistics

name	data_type	n_missing	complete_rate	n_unique	empty	min	max	whitespace	label
estab_name	character	0	1	3571783	0	3	52	0	NA

sex

Distribution

Distribution of values for sex

0 missing values.

Summary statistics

name	data_type	n_missing	complete_rate	min	median	max	mean	sd	hist	label
sex	numeric	0	1	0	0	1	0.4247781	0.4943093	▇▁▁▁▆	NA

establishment_size

Distribution

Distribution of values for establishment_size

0 missing values.

Summary statistics

name	data_type	n_missing	complete_rate	min	median	max	mean	sd	hist	label
establishment_size	numeric	0	1	1	6	10	6.269162	2.827782	▃▅▆▅▇	NA

tenure

Distribution

Distribution of values for tenure

0 missing values.

Summary statistics

name	data_type	n_missing	complete_rate	min	median	max	mean	sd	hist	label
tenure	numeric	0	1	0	19	600	49.44531	76.07088	▇▁▁▁▁	NA

adm_type

Distribution

Distribution of values for adm_type

0 missing values.

Summary statistics

name	data_type	n_missing	complete_rate	min	median	max	mean	sd	hist	label
adm_type	numeric	0	1	0	0	14	0.6514072	1.027264	▇▁▁▁▁	NA

disability_type

Distribution

Distribution of values for disability_type

0 missing values.

Summary statistics

name	data_type	n_missing	complete_rate	min	median	max	mean	sd	hist	label
disability_type	numeric	0	1	0	0	6	0.0159849	0.2289816	▇▁▁▁▁	NA

firmID_type

Distribution

Distribution of values for firmID_type

0 missing values.

Summary statistics

name	data_type	n_missing	complete_rate	min	median	max	mean	sd	hist	label
firmID_type	numeric	0	1	0	1	1	0.9727843	0.1627113	▁▁▁▁▇	NA

wage_type

Distribution

Distribution of values for wage_type

0 missing values.

Summary statistics

name	data_type	n_missing	complete_rate	min	median	max	mean	sd	hist	label
wage_type	numeric	0	1	1	1	7	1.327841	1.130185	▇▁▁▁▁	NA

contract_type

Distribution

Distribution of values for contract_type

0 missing values.

Summary statistics

name	data_type	n_missing	complete_rate	min	median	max	mean	sd	hist	label
contract_type	numeric	0	1	10	10	97	16.11409	14.17813	▇▂▁▁▁	NA

active1231

Distribution

Distribution of values for active1231

0 missing values.

Summary statistics

name	data_type	n_missing	complete_rate	min	median	max	mean	sd	hist	label
active1231	numeric	0	1	0	1	1	0.6658918	0.4716778	▅▁▁▁▇	NA

earn_april

Distribution

Distribution of values for earn_april

0 missing values.

Summary statistics

name	data_type	n_missing	complete_rate	min	median	max	mean	sd	hist	label
earn_april	numeric	0	1	0	1058	118165	1665.544	2988.929	▇▁▁▁▁	NA

earn_august

Distribution

Distribution of values for earn_august

0 missing values.

Summary statistics

name	data_type	n_missing	complete_rate	min	median	max	mean	sd	hist	label
earn_august	numeric	0	1	0	1079	118191	1680.54	2987.61	▇▁▁▁▁	NA

earn_feb

Distribution

Distribution of values for earn_feb

0 missing values.

Summary statistics

name	data_type	n_missing	complete_rate	min	median	max	mean	sd	hist	label
earn_feb	numeric	0	1	0	1024	118208	1625.066	2979.878	▇▁▁▁▁	NA

earn_jan

Distribution

Distribution of values for earn_jan

0 missing values.

Summary statistics

name	data_type	n_missing	complete_rate	min	median	max	mean	sd	hist	label
earn_jan	numeric	0	1	0	1031	118200	1674.546	3147.286	▇▁▁▁▁	NA

earn_july

Distribution

Distribution of values for earn_july

0 missing values.

Summary statistics

name	data_type	n_missing	complete_rate	min	median	max	mean	sd	hist	label
earn_july	numeric	0	1	0	1080	118200	1703.237	3053.299	▇▁▁▁▁	NA

earn_june

Distribution

Distribution of values for earn_june

0 missing values.

Summary statistics

name	data_type	n_missing	complete_rate	min	median	max	mean	sd	hist	label
earn_june	numeric	0	1	0	1074	118195	1691.764	3017.097	▇▁▁▁▁	NA

earn_may

Distribution

Distribution of values for earn_may

0 missing values.

Summary statistics

name	data_type	n_missing	complete_rate	min	median	max	mean	sd	hist	label
earn_may	numeric	0	1	0	1070	118155	1680.595	2990.088	▇▁▁▁▁	NA

earn_march

Distribution

Distribution of values for earn_march

0 missing values.

Summary statistics

name	data_type	n_missing	complete_rate	min	median	max	mean	sd	hist	label
earn_march	numeric	0	1	0	1048	118183	1655.898	3015.72	▇▁▁▁▁	NA

earn_nov

Distribution

Distribution of values for earn_nov

0 missing values.

Summary statistics

name	data_type	n_missing	complete_rate	min	median	max	mean	sd	hist	label
earn_nov	numeric	0	1	0	1086	118206	1708.75	3070.842	▇▁▁▁▁	NA

earn_oct

Distribution

Distribution of values for earn_oct

0 missing values.

Summary statistics

name	data_type	n_missing	complete_rate	min	median	max	mean	sd	hist	label
earn_oct	numeric	0	1	0	1085	118192	1689.309	3012.413	▇▁▁▁▁	NA

earn_sept

Distribution

Distribution of values for earn_sept

0 missing values.

Summary statistics

name	data_type	n_missing	complete_rate	min	median	max	mean	sd	hist	label
earn_sept	numeric	0	1	0	1081	118194	1684.6	3009.316	▇▁▁▁▁	NA

earn_dec_mw

Distribution

Distribution of values for earn_dec_mw

0 missing values.

Summary statistics

name	data_type	n_missing	complete_rate	min	median	max	mean	sd	hist	label
earn_dec_mw	numeric	0	1	0	1.4	150	2.215333	4.139668	▇▁▁▁▁	NA

earn_dec

Distribution

Distribution of values for earn_dec

0 missing values.

Summary statistics

name	data_type	n_missing	complete_rate	min	median	max	mean	sd	hist	label
earn_dec	numeric	0	1	0	1087	118204	1748.198	3262.792	▇▁▁▁▁	NA

mean_earn_mw

Distribution

Distribution of values for mean_earn_mw

0 missing values.

Summary statistics

name	data_type	n_missing	complete_rate	min	median	max	mean	sd	hist	label
mean_earn_mw	numeric	0	1	0	1.7	150	2.781386	4.007913	▇▁▁▁▁	NA

mean_earn

Distribution

Distribution of values for mean_earn

0 missing values.

Summary statistics

name	data_type	n_missing	complete_rate	min	median	max	mean	sd	hist	label
mean_earn	numeric	0	1	0	1335	118200	2198.187	3158.532	▇▁▁▁▁	NA

hired_wage

Distribution

Distribution of values for hired_wage

0 missing values.

Summary statistics

name	data_type	n_missing	complete_rate	min	median	max	mean	sd	hist	label
hired_wage	numeric	0	1	0	1113	9742640	1705.213	5866.853	▇▁▁▁▁	NA

last_wage

Distribution

Distribution of values for last_wage

0 missing values.

Summary statistics

name	data_type	n_missing	complete_rate	min	median	max	mean	sd	hist	label
last_wage	numeric	0	1	0	1099	1e+07	1844.551	8579.984	▇▁▁▁▁	NA

yr

Distribution

Distribution of values for yr

0 missing values.

Summary statistics

name	data_type	n_missing	complete_rate	min	median	max	mean	sd	hist	label
yr	numeric	0	1	2015	2015	2015	2015	0	▁▁▇▁▁	NA

termination_year

Distribution

Distribution of values for termination_year

0 missing values.

Summary statistics

name	data_type	n_missing	complete_rate	min	median	max	mean	sd	hist	label
termination_year	numeric	0	1	2015	2015	2015	2015	0	▁▁▇▁▁	NA

adm_day

Distribution

Distribution of values for adm_day

0 missing values.

Summary statistics

name	data_type	n_missing	complete_rate	min	median	max	mean	sd	hist	label
adm_day	numeric	0	1	1	5	31	8.682133	8.447796	▇▂▂▂▁	NA

adm_month

Distribution

Distribution of values for adm_month

0 missing values.

Summary statistics

name	data_type	n_missing	complete_rate	min	median	max	mean	sd	hist	label
adm_month	numeric	0	1	1	6	12	6.290397	3.418843	▇▅▅▅▆	NA

adm_year

Distribution

Distribution of values for adm_year

0 missing values.

Summary statistics

name	data_type	n_missing	complete_rate	min	median	max	mean	sd	hist	label
adm_year	numeric	0	1	1938	2014	2015	2011.242	6.273478	▁▁▁▁▇	NA

Missingness report

Codebook table

JSON-LD metadata

The following JSON-LD can be found by search engines, if you share this codebook publicly on the web.

{
  "name": "codebook_data",
  "datePublished": "2024-06-04",
  "description": "The dataset has N=72175102 rows and 65 columns.\n0 rows have no missing values on any column.\n\n\n## Table of variables\nThis table contains variable names, labels, and number of missing values.\nSee the complete codebook for more.\n\n|name               |label | n_missing|\n|:------------------|:-----|---------:|\n|adm_date           |NA    |         0|\n|yr_arrival         |NA    |         0|\n|cbo94              |NA    |  72175102|\n|cbo02              |NA    |     72464|\n|cei                |NA    |         0|\n|zip_establishment  |NA    |         0|\n|cnae20             |NA    |         0|\n|cnae20sub          |NA    |         0|\n|cnae95             |NA    |         0|\n|firmID             |NA    |         0|\n|cnpj_root          |NA    |         0|\n|cpf                |NA    |         0|\n|dob                |NA    |         0|\n|termination_day    |NA    |         0|\n|schooling          |NA    |         0|\n|ibge_subsetor      |NA    |         0|\n|age                |NA    |         0|\n|cei_avail          |NA    |         0|\n|pat                |NA    |         0|\n|disabled           |NA    |         0|\n|simples            |NA    |         0|\n|alvara_ind         |NA    |         0|\n|termination_month  |NA    |         0|\n|separation_cause   |NA    |         0|\n|muni_job           |NA    |         0|\n|muni               |NA    |         0|\n|nationality        |NA    |         0|\n|legal_form         |NA    |         0|\n|name               |NA    |         0|\n|ctps               |NA    |         0|\n|pis                |NA    |         0|\n|hired_hours        |NA    |         0|\n|race_color         |NA    |  10188449|\n|estab_name         |NA    |         0|\n|sex                |NA    |         0|\n|establishment_size |NA    |         0|\n|tenure             |NA    |         0|\n|adm_type           |NA    |         0|\n|disability_type    |NA    |         0|\n|firmID_type        |NA    |         0|\n|wage_type          |NA    |         0|\n|contract_type      |NA    |         0|\n|active1231         |NA    |         0|\n|earn_april         |NA    |         0|\n|earn_august        |NA    |         0|\n|earn_feb           |NA    |         0|\n|earn_jan           |NA    |         0|\n|earn_july          |NA    |         0|\n|earn_june          |NA    |         0|\n|earn_may           |NA    |         0|\n|earn_march         |NA    |         0|\n|earn_nov           |NA    |         0|\n|earn_oct           |NA    |         0|\n|earn_sept          |NA    |         0|\n|earn_dec_mw        |NA    |         0|\n|earn_dec           |NA    |         0|\n|mean_earn_mw       |NA    |         0|\n|mean_earn          |NA    |         0|\n|hired_wage         |NA    |         0|\n|last_wage          |NA    |         0|\n|yr                 |NA    |         0|\n|termination_year   |NA    |         0|\n|adm_day            |NA    |         0|\n|adm_month          |NA    |         0|\n|adm_year           |NA    |         0|\n\n### Note\nThis dataset was automatically described using the [codebook R package](https://rubenarslan.github.io/codebook/) (version 0.9.2).",
  "keywords": ["adm_date", "yr_arrival", "cbo94", "cbo02", "cei", "zip_establishment", "cnae20", "cnae20sub", "cnae95", "firmID", "cnpj_root", "cpf", "dob", "termination_day", "schooling", "ibge_subsetor", "age", "cei_avail", "pat", "disabled", "simples", "alvara_ind", "termination_month", "separation_cause", "muni_job", "muni", "nationality", "legal_form", "name", "ctps", "pis", "hired_hours", "race_color", "estab_name", "sex", "establishment_size", "tenure", "adm_type", "disability_type", "firmID_type", "wage_type", "contract_type", "active1231", "earn_april", "earn_august", "earn_feb", "earn_jan", "earn_july", "earn_june", "earn_may", "earn_march", "earn_nov", "earn_oct", "earn_sept", "earn_dec_mw", "earn_dec", "mean_earn_mw", "mean_earn", "hired_wage", "last_wage", "yr", "termination_year", "adm_day", "adm_month", "adm_year"],
  "@context": "http://schema.org/",
  "@type": "Dataset",
  "variableMeasured": [
    {
      "name": "adm_date",
      "@type": "propertyValue"
    },
    {
      "name": "yr_arrival",
      "@type": "propertyValue"
    },
    {
      "name": "cbo94",
      "@type": "propertyValue"
    },
    {
      "name": "cbo02",
      "@type": "propertyValue"
    },
    {
      "name": "cei",
      "@type": "propertyValue"
    },
    {
      "name": "zip_establishment",
      "@type": "propertyValue"
    },
    {
      "name": "cnae20",
      "@type": "propertyValue"
    },
    {
      "name": "cnae20sub",
      "@type": "propertyValue"
    },
    {
      "name": "cnae95",
      "@type": "propertyValue"
    },
    {
      "name": "firmID",
      "@type": "propertyValue"
    },
    {
      "name": "cnpj_root",
      "@type": "propertyValue"
    },
    {
      "name": "cpf",
      "@type": "propertyValue"
    },
    {
      "name": "dob",
      "@type": "propertyValue"
    },
    {
      "name": "termination_day",
      "@type": "propertyValue"
    },
    {
      "name": "schooling",
      "@type": "propertyValue"
    },
    {
      "name": "ibge_subsetor",
      "@type": "propertyValue"
    },
    {
      "name": "age",
      "@type": "propertyValue"
    },
    {
      "name": "cei_avail",
      "@type": "propertyValue"
    },
    {
      "name": "pat",
      "@type": "propertyValue"
    },
    {
      "name": "disabled",
      "@type": "propertyValue"
    },
    {
      "name": "simples",
      "@type": "propertyValue"
    },
    {
      "name": "alvara_ind",
      "@type": "propertyValue"
    },
    {
      "name": "termination_month",
      "@type": "propertyValue"
    },
    {
      "name": "separation_cause",
      "@type": "propertyValue"
    },
    {
      "name": "muni_job",
      "@type": "propertyValue"
    },
    {
      "name": "muni",
      "@type": "propertyValue"
    },
    {
      "name": "nationality",
      "@type": "propertyValue"
    },
    {
      "name": "legal_form",
      "@type": "propertyValue"
    },
    {
      "name": "name",
      "@type": "propertyValue"
    },
    {
      "name": "ctps",
      "@type": "propertyValue"
    },
    {
      "name": "pis",
      "@type": "propertyValue"
    },
    {
      "name": "hired_hours",
      "@type": "propertyValue"
    },
    {
      "name": "race_color",
      "@type": "propertyValue"
    },
    {
      "name": "estab_name",
      "@type": "propertyValue"
    },
    {
      "name": "sex",
      "@type": "propertyValue"
    },
    {
      "name": "establishment_size",
      "@type": "propertyValue"
    },
    {
      "name": "tenure",
      "@type": "propertyValue"
    },
    {
      "name": "adm_type",
      "@type": "propertyValue"
    },
    {
      "name": "disability_type",
      "@type": "propertyValue"
    },
    {
      "name": "firmID_type",
      "@type": "propertyValue"
    },
    {
      "name": "wage_type",
      "@type": "propertyValue"
    },
    {
      "name": "contract_type",
      "@type": "propertyValue"
    },
    {
      "name": "active1231",
      "@type": "propertyValue"
    },
    {
      "name": "earn_april",
      "@type": "propertyValue"
    },
    {
      "name": "earn_august",
      "@type": "propertyValue"
    },
    {
      "name": "earn_feb",
      "@type": "propertyValue"
    },
    {
      "name": "earn_jan",
      "@type": "propertyValue"
    },
    {
      "name": "earn_july",
      "@type": "propertyValue"
    },
    {
      "name": "earn_june",
      "@type": "propertyValue"
    },
    {
      "name": "earn_may",
      "@type": "propertyValue"
    },
    {
      "name": "earn_march",
      "@type": "propertyValue"
    },
    {
      "name": "earn_nov",
      "@type": "propertyValue"
    },
    {
      "name": "earn_oct",
      "@type": "propertyValue"
    },
    {
      "name": "earn_sept",
      "@type": "propertyValue"
    },
    {
      "name": "earn_dec_mw",
      "@type": "propertyValue"
    },
    {
      "name": "earn_dec",
      "@type": "propertyValue"
    },
    {
      "name": "mean_earn_mw",
      "@type": "propertyValue"
    },
    {
      "name": "mean_earn",
      "@type": "propertyValue"
    },
    {
      "name": "hired_wage",
      "@type": "propertyValue"
    },
    {
      "name": "last_wage",
      "@type": "propertyValue"
    },
    {
      "name": "yr",
      "@type": "propertyValue"
    },
    {
      "name": "termination_year",
      "@type": "propertyValue"
    },
    {
      "name": "adm_day",
      "@type": "propertyValue"
    },
    {
      "name": "adm_month",
      "@type": "propertyValue"
    },
    {
      "name": "adm_year",
      "@type": "propertyValue"
    }
  ]
}`

 # } # end year loop