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 = "2003"
    # 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): cnae items found, but no aggregate
## Warning in detect_scales(codebook_data): active items found, but no aggregate
## Warning in detect_scales(codebook_data): cbo 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: 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 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`.

## 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=41969162 rows and 45 columns. 20649356 rows have no missing values on any column.

Metadata for search engines
  • Date published: 2024-05-29
x
adm_date
separation_cause
cei
cnae95
cpf
termination_day
dob
active1231
schooling
hired_hours
firmID
alvara_ind
cei_avail
pat
simples
termination_month
muni
nationality
legal_form
name
ctps
cbo02
cbo94
pis
disabled
race_color
cnpj_root
earn_dec
earn_dec_mw
mean_earn
mean_earn_mw
hired_wage
sex
establishment_size
tenure
adm_type
firmID_type
wage_type
contract_type
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 min median max mean sd hist label
adm_date numeric 0 1 1e+06 3092001 3.1e+07 7986312 8388226 ▇▂▂▁▁ 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 4.344405 8.062461 ▇▁▁▁▁ 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 28441 0 1 21 0 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 -1 55212 99007 54725.76 24550.18 ▃▂▆▇▂ 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 34076350 0 1 21 0 NA

termination_day

Distribution

Distribution of values for termination_day

Distribution of values for termination_day

0 missing values.

Summary statistics

name data_type n_missing complete_rate min median max mean sd hist label
termination_day numeric 0 1 0 0 30 4.477091 8.819438 ▇▁▁▁▁ NA

dob

Distribution

Distribution of values for dob

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 1.5e+07 5.1e+07 15600517 8784363 ▇▇▇▁▁ 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 0.7039675 0.4565055 ▃▁▁▁▇ 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 6 9 5.709067 2.076646 ▂▅▃▇▃ 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 41.13114 6.51599 ▁▁▁▁▇ 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 2504099 0 15 21 0 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 1 2 2 1.992487 0.0863501 ▁▁▁▁▇ 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 0.0156315 0.124045 ▇▁▁▁▁ 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 0.2371431 0.4253308 ▇▁▁▁▂ 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 0.2108438 0.4079077 ▇▁▁▁▂ 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 1.981249 3.605491 ▇▁▁▁▁ 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 351880 530010 347294.2 83056.92 ▁▂▇▂▁ 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 50 10.03835 1.065587 ▇▁▁▁▁ 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 26028581 0 4 30 0 NA

ctps

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
ctps character 0 1 26600366 0 1 21 0 NA

cbo02

Distribution

Distribution of values for cbo02

Distribution of values for cbo02

653643 missing values.

Summary statistics

name data_type n_missing complete_rate min median max mean sd hist label
cbo02 numeric 653643 0.9844256 111215 514225 992225 527182.8 206349.6 ▃▇▇▆▂ NA

cbo94

Distribution

Distribution of values for cbo94

Distribution of values for cbo94

2921305 missing values.

Summary statistics

name data_type n_missing complete_rate min median max mean sd hist label
cbo94 numeric 2921305 0.930394 12110 55125 99190 56414.28 25955.44 ▃▇▆▂▆ NA

pis

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
pis character 0 1 35925326 0 1 21 0 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 1 1 0.9946381 0.0730285 ▁▁▁▁▇ NA

race_color

Distribution

Distribution of values for race_color

Distribution of values for race_color

0 missing values.

Summary statistics

name data_type n_missing complete_rate min median max mean sd hist label
race_color numeric 0 1 1 2 9 4.172998 2.938517 ▇▁▁▁▅ 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 1.5e+07 1e+08 28880769 29827018 ▇▂▂▂▁ 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 0 396 36002 726.9348 1435.115 ▇▁▁▁▁ 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 1.6 150 3.022615 5.978124 ▇▁▁▁▁ 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 0 486 36002 869.1739 1367.313 ▇▁▁▁▁ 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 2.1 150 3.799902 6.046359 ▇▁▁▁▁ NA

hired_wage

Distribution

Distribution of values for hired_wage

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 0.01 367 1e+07 675.9455 8357.551 ▇▁▁▁▁ 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 0.379013 0.4851414 ▇▁▁▁▅ 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 0 5 9 5.225688 2.84131 ▃▅▆▆▇ 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 20 600 51.34289 72.97775 ▇▁▁▁▁ 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 5 0.6312428 0.9646586 ▇▃▁▁▁ 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 0.9540497 0.2093774 ▁▁▁▁▇ 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 1.494955 1.337739 ▇▁▁▁▁ 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 95 16.37234 12.15697 ▇▂▁▁▁ NA

last_wage

Distribution

Distribution of values for last_wage

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 2.2 150 4.245769 7.742004 ▇▁▁▁▁ 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 2003 2003 2003 2003 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 2003 2003 2003 2003 0 ▁▁▇▁▁ NA

adm_day

Distribution

Distribution of values for adm_day

Distribution of values for adm_day

19545097 missing values.

Summary statistics

name data_type n_missing complete_rate min median max mean sd hist label
adm_day numeric 19545097 0.5342986 1 13 31 13.59801 7.882264 ▇▇▇▅▂ NA

adm_month

Distribution

Distribution of values for adm_month

Distribution of values for adm_month

2954669 missing values.

Summary statistics

name data_type n_missing complete_rate min median max mean sd hist label
adm_month numeric 2954669 0.929599 1 6 12 5.924493 3.200054 ▇▅▅▅▅ 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 1924 2002 2003 1999.104 6.015582 ▁▁▁▁▇ 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": "2024-05-29",
  "description": "The dataset has N=41969162 rows and 45 columns.\n20649356 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|separation_cause   |NA    |         0|\n|cei                |NA    |         0|\n|cnae95             |NA    |         0|\n|cpf                |NA    |         0|\n|termination_day    |NA    |         0|\n|dob                |NA    |         0|\n|active1231         |NA    |         0|\n|schooling          |NA    |         0|\n|hired_hours        |NA    |         0|\n|firmID             |NA    |         0|\n|alvara_ind         |NA    |         0|\n|cei_avail          |NA    |         0|\n|pat                |NA    |         0|\n|simples            |NA    |         0|\n|termination_month  |NA    |         0|\n|muni               |NA    |         0|\n|nationality        |NA    |         0|\n|legal_form         |NA    |         0|\n|name               |NA    |         0|\n|ctps               |NA    |         0|\n|cbo02              |NA    |    653643|\n|cbo94              |NA    |   2921305|\n|pis                |NA    |         0|\n|disabled           |NA    |         0|\n|race_color         |NA    |         0|\n|cnpj_root          |NA    |         0|\n|earn_dec           |NA    |         0|\n|earn_dec_mw        |NA    |         0|\n|mean_earn          |NA    |         0|\n|mean_earn_mw       |NA    |         0|\n|hired_wage         |NA    |         0|\n|sex                |NA    |         0|\n|establishment_size |NA    |         0|\n|tenure             |NA    |         0|\n|adm_type           |NA    |         0|\n|firmID_type        |NA    |         0|\n|wage_type          |NA    |         0|\n|contract_type      |NA    |         0|\n|last_wage          |NA    |         0|\n|yr                 |NA    |         0|\n|termination_year   |NA    |         0|\n|adm_day            |NA    |  19545097|\n|adm_month          |NA    |   2954669|\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", "separation_cause", "cei", "cnae95", "cpf", "termination_day", "dob", "active1231", "schooling", "hired_hours", "firmID", "alvara_ind", "cei_avail", "pat", "simples", "termination_month", "muni", "nationality", "legal_form", "name", "ctps", "cbo02", "cbo94", "pis", "disabled", "race_color", "cnpj_root", "earn_dec", "earn_dec_mw", "mean_earn", "mean_earn_mw", "hired_wage", "sex", "establishment_size", "tenure", "adm_type", "firmID_type", "wage_type", "contract_type", "last_wage", "yr", "termination_year", "adm_day", "adm_month", "adm_year"],
  "@context": "http://schema.org/",
  "@type": "Dataset",
  "variableMeasured": [
    {
      "name": "adm_date",
      "@type": "propertyValue"
    },
    {
      "name": "separation_cause",
      "@type": "propertyValue"
    },
    {
      "name": "cei",
      "@type": "propertyValue"
    },
    {
      "name": "cnae95",
      "@type": "propertyValue"
    },
    {
      "name": "cpf",
      "@type": "propertyValue"
    },
    {
      "name": "termination_day",
      "@type": "propertyValue"
    },
    {
      "name": "dob",
      "@type": "propertyValue"
    },
    {
      "name": "active1231",
      "@type": "propertyValue"
    },
    {
      "name": "schooling",
      "@type": "propertyValue"
    },
    {
      "name": "hired_hours",
      "@type": "propertyValue"
    },
    {
      "name": "firmID",
      "@type": "propertyValue"
    },
    {
      "name": "alvara_ind",
      "@type": "propertyValue"
    },
    {
      "name": "cei_avail",
      "@type": "propertyValue"
    },
    {
      "name": "pat",
      "@type": "propertyValue"
    },
    {
      "name": "simples",
      "@type": "propertyValue"
    },
    {
      "name": "termination_month",
      "@type": "propertyValue"
    },
    {
      "name": "muni",
      "@type": "propertyValue"
    },
    {
      "name": "nationality",
      "@type": "propertyValue"
    },
    {
      "name": "legal_form",
      "@type": "propertyValue"
    },
    {
      "name": "name",
      "@type": "propertyValue"
    },
    {
      "name": "ctps",
      "@type": "propertyValue"
    },
    {
      "name": "cbo02",
      "@type": "propertyValue"
    },
    {
      "name": "cbo94",
      "@type": "propertyValue"
    },
    {
      "name": "pis",
      "@type": "propertyValue"
    },
    {
      "name": "disabled",
      "@type": "propertyValue"
    },
    {
      "name": "race_color",
      "@type": "propertyValue"
    },
    {
      "name": "cnpj_root",
      "@type": "propertyValue"
    },
    {
      "name": "earn_dec",
      "@type": "propertyValue"
    },
    {
      "name": "earn_dec_mw",
      "@type": "propertyValue"
    },
    {
      "name": "mean_earn",
      "@type": "propertyValue"
    },
    {
      "name": "mean_earn_mw",
      "@type": "propertyValue"
    },
    {
      "name": "hired_wage",
      "@type": "propertyValue"
    },
    {
      "name": "sex",
      "@type": "propertyValue"
    },
    {
      "name": "establishment_size",
      "@type": "propertyValue"
    },
    {
      "name": "tenure",
      "@type": "propertyValue"
    },
    {
      "name": "adm_type",
      "@type": "propertyValue"
    },
    {
      "name": "firmID_type",
      "@type": "propertyValue"
    },
    {
      "name": "wage_type",
      "@type": "propertyValue"
    },
    {
      "name": "contract_type",
      "@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