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 = "2012"
    # 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 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 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: 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`.

Metadata

Description

Dataset name: codebook_data

The dataset has N=73326485 rows and 47 columns. 0 rows have no missing values on any column.

Metadata for search engines
  • Date published: 2024-06-02
x
adm_date
cbo94
cbo02
cei
cnae20
cnae20sub
cnae95
firmID
cnpj_root
cpf
schooling
age
cei_avail
pat
disabled
simples
alvara_ind
termination_month
separation_cause
muni
nationality
legal_form
name
ctps
pis
hired_hours
race_color
sex
establishment_size
tenure
adm_type
disability_type
firmID_type
wage_type
contract_type
active1231
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

Distribution of values for adm_date

0 missing values.

Summary statistics

name data_type n_missing complete_rate n_unique empty min max whitespace label
adm_date character 0 1 28855 0 6 8 0 NA

cbo94

Distribution

## Error in if (stats::median(table(x)) == 1) {: missing value where TRUE/FALSE needed
## No non-missing values to show.

73326485 missing values.

Summary statistics

name data_type n_missing complete_rate count label
cbo94 logical 73326485 0 : NA

cbo02

Distribution

Distribution of values for cbo02

Distribution of values for cbo02

39968 missing values.

Summary statistics

name data_type n_missing complete_rate min median max mean sd hist label
cbo02 numeric 39968 0.9994549 10105 514320 992225 516968.2 204468.1 ▁▃▇▅▁ 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 52906 0 1 21 0 NA

cnae20

Distribution

Distribution of values for cnae20

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 47890 99008 54781.93 25910.94 ▂▂▇▂▆ NA

cnae20sub

Distribution

Distribution of values for cnae20sub

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 4789099 9900800 5478201 2591092 ▂▂▇▂▆ NA

cnae95

Distribution

Distribution of values for cnae95

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 55131 99007 55277.08 22611.28 ▂▂▇▇▂ 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 3645405 0 15 21 0 NA

cnpj_root

Distribution

Distribution of values for cnpj_root

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 1.1e+07 1e+08 23751922 26889545 ▇▁▁▁▁ 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 58541358 0 1 21 0 NA

schooling

Distribution

Distribution of values for schooling

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 6.411329 1.806316 ▁▃▇▃▁ NA

age

Distribution

Distribution of values for age

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 33 100 34.644 11.47028 ▁▇▃▁▁ NA

cei_avail

Distribution

Distribution of values for cei_avail

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 0.022903 0.1495942 ▇▁▁▁▁ NA

pat

Distribution

Distribution of values for pat

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 0.28962 0.453586 ▇▁▁▁▃ NA

disabled

Distribution

Distribution of values for disabled

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 0.0059813 0.0771072 ▇▁▁▁▁ NA

simples

Distribution

Distribution of values for simples

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 0.232165 0.4222137 ▇▁▁▁▂ NA

alvara_ind

Distribution

Distribution of values for alvara_ind

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 0.0001547 0.012436 ▇▁▁▁▁ NA

termination_month

Distribution

Distribution of values for termination_month

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 2.366234 3.826068 ▇▁▁▁▁ NA

separation_cause

Distribution

Distribution of values for separation_cause

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 5.43902 8.564867 ▇▁▁▁▁ NA

muni

Distribution

Distribution of values for muni

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 351870 530010 345204 86220.65 ▁▂▇▂▁ NA

nationality

Distribution

Distribution of values for nationality

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 10.04247 1.218521 ▇▁▁▁▁ NA

name

Distribution

Distribution of values for name

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 42150774 0 4 52 0 NA

ctps

Distribution

Distribution of values for ctps

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 61463 1e+08 1131617 4003854 ▇▁▁▁▁ 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 58738850 0 13 21 0 NA

hired_hours

Distribution

Distribution of values for hired_hours

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 41.32156 6.28172 ▁▁▁▁▇ NA

race_color

Distribution

Distribution of values for race_color

Distribution of values for race_color

9930334 missing values.

Summary statistics

name data_type n_missing complete_rate min median max mean sd hist label
race_color numeric 9930334 0.8645737 1 2 9 4.50638 2.96366 ▇▁▁▁▆ NA

sex

Distribution

Distribution of values for sex

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 0.4097623 0.4917898 ▇▁▁▁▆ NA

establishment_size

Distribution

Distribution of values for establishment_size

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 6.345128 2.800326 ▃▅▆▅▇ NA

tenure

Distribution

Distribution of values for tenure

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 15 600 44.39622 72.75392 ▇▁▁▁▁ NA

adm_type

Distribution

Distribution of values for adm_type

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 0.7519328 1.045491 ▇▁▁▁▁ NA

disability_type

Distribution

Distribution of values for disability_type

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 0.0126359 0.2038038 ▇▁▁▁▁ NA

firmID_type

Distribution

Distribution of values for firmID_type

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 0.9711921 0.1672663 ▁▁▁▁▇ NA

wage_type

Distribution

Distribution of values for wage_type

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 1.385696 1.213779 ▇▁▁▁▁ NA

contract_type

Distribution

Distribution of values for contract_type

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 15.86891 13.56804 ▇▂▁▁▁ NA

active1231

Distribution

Distribution of values for active1231

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 0.6472247 0.4778335 ▅▁▁▁▇ NA

earn_dec_mw

Distribution

Distribution of values for earn_dec_mw

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 1.3 150 2.17115 4.142518 ▇▁▁▁▁ NA

earn_dec

Distribution

Distribution of values for earn_dec

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 0 819 93302 1352.408 2577.222 ▇▁▁▁▁ NA

mean_earn_mw

Distribution

Distribution of values for mean_earn_mw

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 1.6 150 2.729041 3.923236 ▇▁▁▁▁ NA

mean_earn

Distribution

Distribution of values for mean_earn

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 1022 93300 1702.501 2440.484 ▇▁▁▁▁ NA

hired_wage

Distribution

Distribution of values for hired_wage

Distribution of values for hired_wage

193 missing values.

Summary statistics

name data_type n_missing complete_rate min median max mean sd hist label
hired_wage numeric 193 0.9999974 0 840 1e+06 1289.912 2514.446 ▇▁▁▁▁ NA

last_wage

Distribution

Distribution of values for last_wage

Distribution of values for last_wage

182 missing values.

Summary statistics

name data_type n_missing complete_rate min median max mean sd hist label
last_wage numeric 182 0.9999975 0 805 975856 1371.333 3022.457 ▇▁▁▁▁ NA

yr

Distribution

Distribution of values for yr

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 2012 2012 2012 2012 0 ▁▁▇▁▁ NA

termination_year

Distribution

Distribution of values for termination_year

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 2012 2012 2012 2012 0 ▁▁▇▁▁ NA

adm_day

Distribution

Distribution of values for adm_day

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 4 31 8.456173 8.450072 ▇▂▂▂▁ NA

adm_month

Distribution

Distribution of values for adm_month

Distribution of values for adm_month

1196787 missing values.

Summary statistics

name data_type n_missing complete_rate min median max mean sd hist label
adm_month numeric 1196787 0.9836787 1 5 12 5.591772 3.544309 ▇▃▃▃▃ NA

adm_year

Distribution

Distribution of values for adm_year

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 2011 2012 2008.651 5.992353 ▁▁▁▁▇ 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": "2024-06-02",
  "description": "The dataset has N=73326485 rows and 47 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|cbo94              |NA    |  73326485|\n|cbo02              |NA    |     39968|\n|cei                |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|schooling          |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               |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    |   9930334|\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_dec_mw        |NA    |         0|\n|earn_dec           |NA    |         0|\n|mean_earn_mw       |NA    |         0|\n|mean_earn          |NA    |         0|\n|hired_wage         |NA    |       193|\n|last_wage          |NA    |       182|\n|yr                 |NA    |         0|\n|termination_year   |NA    |         0|\n|adm_day            |NA    |         0|\n|adm_month          |NA    |   1196787|\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", "cbo94", "cbo02", "cei", "cnae20", "cnae20sub", "cnae95", "firmID", "cnpj_root", "cpf", "schooling", "age", "cei_avail", "pat", "disabled", "simples", "alvara_ind", "termination_month", "separation_cause", "muni", "nationality", "legal_form", "name", "ctps", "pis", "hired_hours", "race_color", "sex", "establishment_size", "tenure", "adm_type", "disability_type", "firmID_type", "wage_type", "contract_type", "active1231", "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": "cbo94",
      "@type": "propertyValue"
    },
    {
      "name": "cbo02",
      "@type": "propertyValue"
    },
    {
      "name": "cei",
      "@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": "schooling",
      "@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",
      "@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": "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_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