Package 'occupationMeasurement'

Description

The Algorithm used here corresponds to Algorithm #10 in (Schierholz, 2019). Note: This function should not be used directly, but rather as a step / algorithm in get_job_suggestions.

Usage

algo_similarity_based_reasoning(
  text_processed,
  sim_name = "wordwise",
  probabilities = occupationMeasurement::pretrained_models$similarity_based_reasoning,
  ...
)

Arguments

Value

A data.table with suggestions or NULL if no suggestions were found.

References

Schierholz, M. (2019). New Methods for Job and Occupation Classification (Ph.D. Thesis). University of Mannheim.

See Also

get_job_suggestions()

Examples

## Not run: 
# Use with default settings
if (interactive()) {
  get_job_suggestions(
    "Arzt",
    steps = list(
      simbased_default = list(
        algorithm = algo_similarity_based_reasoning
      )
    )
  )
}

# Use with substring similarity
if (interactive()) {
 get_job_suggestions(
   "Arzt",
   steps = list(
     simbased_substring = list(
       algorithm = algo_similarity_based_reasoning,
       parameters = list(
         sim_name = "substring"
       )
     )
   )
 )
}

# Comparison of algo_similarity_based_reasoning() with get_job_suggestions()

# Example of using algo_similarity_based_reasoning() directly. Not recommended.
if (interactive()) {
  algo_similarity_based_reasoning(
    preprocess_string("Arzt"),
    sim_name = "wordwise"
  )[order(score, decreasing = TRUE)]
}

# Same output as before, but the function is more adaptable.
if (interactive()) {
  get_job_suggestions(
    "Arzt",
    suggestion_type = "kldb-2010",
    num_suggestions = 1500,
    steps = list(
      simbased_default = list(
        algorithm = algo_similarity_based_reasoning,
        parameters = list(
          sim_name = "wordwise"
        )
      )
    )
  )[, list(kldb_id, score, sim_name, kldb_id_title = title)]
}

## End(Not run)

Description

Start the occupation coding API.

Usage

api(
  start = TRUE,
  log_to_file = FALSE,
  file = system.file("plumber", "api", "plumber.R", package = "occupationMeasurement"),
  log_to_console = TRUE,
  log_filepath = file.path("output", "log_api.csv"),
  require_identifier = FALSE,
  allow_origin = NULL
)

Arguments

Value

A Plumber router

See Also

vignette("api")

Examples

if (interactive()) {
  # Get the plumber router
  router <- api(
    start = FALSE,
    # If this is TRUE, the log directory will immediately be created
    log_to_file = FALSE
  )
  # Start the router
  plumber::pr_run(router)
}

if (interactive()) {
  # Immediately start the API
  api(start = TRUE)
}

Description

Printing the returned instance or returning it without saving it in a variable will start the app.

Usage

app(
  questionnaire = questionnaire_web_survey(),
  app_settings = create_app_settings(save_to_file = TRUE),
  css_file = NULL,
  resource_dir = system.file("www", package = "occupationMeasurement"),
  ...
)

Arguments

Value

A shiny app instance.

See Also

vignette("app"), questionnaire_web_survey()

Examples

## Not run: 
app_instance <- app(
  app_settings = create_app_settings(
    # Important to save results from the app
    save_to_file = TRUE
  )
)

# Start the app
if (interactive()) {
  app_instance
}

## End(Not run)

Description

Berufs-Hilfsklassifikation mit Tätigkeitsbeschreibungen.

Usage

auxco

Format

A list with data.tables:

categories

data.table. Main list of AuxCO categories including their descriptions etc.

distinctions

data.table. List of highly similar AuxCO categories that one may want to present to disambiguate between them.

followup_questions

data.table. Follow-up questions to specify final codings based on AuxCO categories. Includes the questions' answer options as well as information on how to encode more complex occupations which depend on multiple answers.

mapping_from_isco

data.table. Mapping from ISCO-08 categories to AuxCO categories.

mapping_from_kldb

data.table. Mapping from KldB 2010 categories to AuxCO categories.

References

Schierholz, Malte; Brenner, Lorraine; Cohausz, Lea; Damminger, Lisa; Fast, Lisa; Hörig, Ann-Kathrin; Huber, Anna-Lena; Ludwig, Theresa; Petry, Annabell; Tschischka, Laura (2018): Vorstellung einer Hilfsklassifikation mit Tätigkeitsbeschreibungen für Zwecke der Berufskodierung. (IAB-Discussion Paper, 2018), Nürnberg, 45 S. https://www.iab.de/183/section.aspx/Publikation/k180509301

See Also

https://github.com/occupationMeasurement/auxiliary-classification, load_auxco()

Description

Buttons to navigate between pages.

Usage

button_next(label = "Weiter")

button_previous(label = "Zurück")

Arguments

Value

shiny Action Button

Functions

• button_previous(): Go to the previous page

See Also

new_page()

Examples

## Not run: 
very_simple_page <- new_page(
  page_id = "example",
  render = function(session, run_before_output, input, output, ...) {
    list(
      shiny::tags$h1("My test page"),
      button_previous(),
      button_next()
    )
  }
)

## End(Not run)

Description

This is the primary and most convenient way of configuring the app.

Usage

create_app_settings(
  save_to_file,
  suggestion_type = "auxco-1.2.x",
  default_num_suggestions = 5,
  require_respondent_id = FALSE,
  warn_before_leaving = FALSE,
  skip_followup_types = c(),
  response_output_dir = file.path("output", "responses"),
  handle_data = NULL,
  get_job_suggestion_params = NULL,
  display_page_ids = TRUE,
  default_tense = "present",
  default_extra_instructions = "on",
  verbose = TRUE,
  .validate = TRUE
)

Arguments

Value

A list of app_settings.

Examples

app_settings <- create_app_settings(
  # Important to save results from the app
  save_to_file = TRUE,
  require_respondent_id = TRUE
)

Description

The final occupation code will depend on the suggestion_id and, possibly, on followup_answers, depending on the suggestion_id provided. See occupationMeasurement::auxco$followup_questions for a list of suggestion_ids (=auxco_id) and their respective recommended follow-up questions.

Usage

get_final_codes(
  suggestion_id,
  followup_answers = list(),
  standardized_answer_levels = NULL,
  approximate_standardized_answer_levels = TRUE,
  code_type = c("isco_08", "kldb_10"),
  verbose = TRUE,
  suggestion_type = "auxco-1.2.x",
  suggestion_type_options = list()
)

Arguments

Details

The interview situation may not allow to ask these follow-up questions. Some default, but suboptimal occupation code is returned if followup_answers is missing.

If followup_answers is missing or incomplete, one may wish to insert/infer the missing information by using standardized_answer_levels.

Value

A named list corresponding to the code_type(s) specified. Includes a message if verbose = TRUE

Examples

## Not run: 
get_final_codes(
  # Führungsaufgaben mit Personalverantwortung  bei der Lebensmittelherstellung
  "9076",
  followup_answers = list(
    # The first answer option in the first followup question
    "Q9076_1" = 2
  )
)

# The same, but using standardized answer levels
get_final_codes(
  # Führungsaufgaben mit Personalverantwortung  bei der Lebensmittelherstellung
  "9076",
  standardized_answer_levels = list(
    # A response corresponding to the standard ISCO Level "supervisor"
    "isco_supervisor_manager" = "isco_supervisor"
  )
)

# Same example with approximate matching, due to conflicting information:
# External data suggest the person is not a supervisor, but the person still
# says she does supervisory tasks (Führungsaufgaben, as encoded in "9076").
# If approximate_standardized_answer_levels = TRUE (the default), the
# selected answer "9076" trumps the external data and we will code this
# person as a supervisor.
get_final_codes(
  # Führungsaufgaben mit Personalverantwortung  bei der Lebensmittelherstellung
  "9076",
  standardized_answer_levels = list(
    # A response corresponding to the standard ISCO Level "not manager nor supervisor"
    "isco_supervisor_manager" = "isco_not_supervising"
  )
)

## End(Not run)

Description

Get potential follow-up questions for a suggestion.

Usage

get_followup_questions(
  suggestion_id,
  tense = "present",
  suggestion_type = "auxco-1.2.x",
  suggestion_type_options = list(),
  include_answer_codes = FALSE
)

Arguments

Value

List of followup questions and their answer options.

Examples

## Not run: 
# Get followup questions for "Post- und Zustelldienste"
get_followup_questions("1004")

## End(Not run)

Description

Each page in the questionnaire can have multiple items on it.

Usage

get_item_data(
  session,
  page_id,
  item_id = NULL,
  key = c("all", "question_text", "response_text", "response_id"),
  default = NULL
)

Arguments

Value

The items's data.

See Also

set_item_data()

Examples

## Not run: 
# Set up a "fake" shiny session to store data
session <- shiny::MockShinySession$new()
session$userData <- list(
  current_page_id = "other_page",
  questionnaire_data = list(
    example_page = list()
  )
)

# This code is expected to be run in e.g. run_before or run_after
# It doesn't really make sense to run this code outside
set_item_data(
  session = session,
  page_id = "example_page",
  question_text = "How are you?"
)

# This code is expected to be run in e.g. run_before
get_item_data(
  session = session,
  page_id = "example_page"
)

## End(Not run)

Description

Given a text input, find up to num_suggestions possible occupation categories.

Usage

get_job_suggestions(
  text,
  suggestion_type = "auxco-1.2.x",
  num_suggestions = 5,
  suggestion_type_options = list(),
  aggregate_score_threshold = 0.02,
  item_score_threshold = 0,
  distinctions = TRUE,
  steps = list(simbased_wordwise = list(algorithm = algo_similarity_based_reasoning,
    parameters = list(sim_name = "wordwise")), simbased_substring = list(algorithm =
    algo_similarity_based_reasoning, parameters = list(sim_name = "substring"))),
  include_general_id = FALSE
)

Arguments

list(
  # try similarity "one word at most 1 letter different" first
  list(
    algorithm = algo_similarity_based_reasoning,
    parameters = list(
      sim_name = "wordwise",
      min_aggregate_prob = 0.535
    )
  ),
  # since everything else failed, try "substring" similarity
  list(
    algorithm = algo_similarity_based_reasoning,
    parameters = list(
      sim_name = "substring",
      min_aggregate_prob = 0.02
    )
  )
)

Details

The procedure implemented here is, roughly speaking, as follows:

1. Predict categories from KldB 2010, including their scores. The first algorithm mentioned in steps is used (default: algo_similarity_based_reasoning()).

2. Convert the predicted KldB 2010 categories to suggestion_type (default: ⁠auxco-1.2.x⁠, an n:m mapping, scores are mapped accordingly.). See internal function convert_suggestions() for details.

3. Remove predicted categories if their score is below item_score_threshold and only keep the num_suggestions top-ranked suggestions.

4. Start anew, trying the next algorithm in steps, if the the top-ranked suggestions have a low chance to be correct. (Technically, this happens if the summed score of the num_suggestions top-ranked suggestions is below aggregate_score_threshold.)

5. If suggestion_type == "auxco-1.2.x" and distinctions == TRUE, insert additional and (highly) similar categories or replace existing ones. See internal function add_distinctions_auxco(). Reorder and keep only the num_suggestions top-ranked suggestions. Auxco categories which were added during this step can be identified by their scores: It equals 0.05 for categories with high similarity and 0.005 for categories with medium similarity.

Value

A data.table with suggestions or NULL if no suggestions were found.

Examples

## Not run: 
if (interactive()) {
  get_job_suggestions("Koch")
}

if (interactive()) {
  get_job_suggestions("Schlosser")
}

## End(Not run)

Description

Expects data to be saved as files.

Usage

get_responses(app_settings = create_app_settings(save_to_file = TRUE))

Arguments

Value

A combined data.table of user data (based on results_overview) or NULL if there are no files.

Examples

## Not run: 
app_settings <- create_app_settings(save_to_file = TRUE)
if (interactive()) {
  get_responses(app_settings = app_settings)
}

## End(Not run)

Description

Categories from the International Standard Classification of Occupations - ISCO-08. ISCO-08 is a hierarchical classification, consisting of 10 (1-digit) major groups, 43 (2-digit) sub-major groups, 130 (3-digit) minor groups, and 436 (4-digit) unit groups, all of them included in this data set.

Usage

isco_08_en

Format

A data frame with 619 rows and 3 variables:

code

character. Unique ISCO-08 identifier / code.

label

character. Short label / title for the category.

description

character. Detailed description of the category.

Details

Source: https://esco.ec.europa.eu This service uses the ESCO classification of the European Commission. The descriptions used here are taken from the ESCO classification (v1.1, Occupations pillar) of the European Commission, which is based on ISCO-08.

More information on the ISCO-08: https://isco-ilo.netlify.app/en/isco-08/, https://www.ilo.org/public/english/bureau/stat/isco/isco08/

Description

This function loads the Auxiliary Classification of Occupations (AuxCO) by reading CSVs from the specified directory, while loading e.g. ids in the correct format. Data is loaded into a named list matching the format expected by other functions in this package.

Usage

load_auxco(dir, add_explanations = TRUE)

Arguments

Details

This package also includes an already loaded version of the auxco, which can be used straight away without calling this function.

Value

A list with multiple data.tables.

See Also

https://github.com/occupationMeasurement/auxiliary-classification, auxco

Examples

## Not run: 
# This function expects the CSV files from
# https://github.com/occupationMeasurement/auxiliary-classification/releases/
# to be there.
path_to_auxco <- "auxco"
if (dir.exists(path_to_auxco)) {
  load_auxco(path_to_auxco)
}

## End(Not run)

Description

Use load_kldb_raw() to load the whole dataset.

Usage

load_kldb_raw(
  cache_dir = getOption("occupationMeasurement.cache_dir", tempdir())
)

load_kldb(cache_dir = getOption("occupationMeasurement.cache_dir", tempdir()))

Arguments

Details

Source: https://www.klassifikationsserver.de/klassService/index.jsp?variant=kldb2010

More information on the KldB 2010: https://statistik.arbeitsagentur.de/DE/Navigation/Grundlagen/Klassifikationen/Klassifikation-der-Berufe/KldB2010-Fassung2020/KldB2010-Fassung2020-Nav.html The KldB 2010 has been revised in 2020. These changes have not been implemented here yet.

Value

A cleaned / slimmed version of the KldB 2010.

Functions

• load_kldb_raw(): Load raw KldB 2010 dataset.

Examples

## Not run: 
# We recommend using a non-temporary directory for caching, so data is
# downloaded only once and not time and time again
cache_dir <- tempdir()
# Note: The dataset will be downloaded from the internet
# Load the cleaned dataset
load_kldb(cache_dir = cache_dir)
# Load the raw dataset
load_kldb_raw(cache_dir = cache_dir)

## End(Not run)

Description

Each page corresponds to a page within the app/questionnaire.

Usage

new_page(
  page_id,
  render,
  condition = NULL,
  run_before = NULL,
  render_before = NULL,
  render_after = NULL,
  run_after = NULL
)

Arguments

Details

Pages are rendered by calling the different life-cycle functions one after another. The order in which they are called is as follows:

1. condition (session) Only if this evaluated to TRUE, continue.

2. run_before (session)

3. render_before (session, run_before_output, input, output)

4. render (session, run_before_output, input, output)

5. render_after (session, run_before_output, input, output) The outputs from render_before, render & render_after are stitched together to produce the final HTML output of the page.

6. run_after (session, input, output) Run when the user leaves the page (=clicks the next button). Any user input has to be handled here. For each question asked, one will typically call set_item_data() to save the collected data internally.

Each of the life-cycle functions above is annotated with the paramaters it has access to. session, input and output are passed directly from shiny and correspond to the objects made available by shiny::shinyServer(), run_before_output is available for convenience and corresponds to whatever is returned by run_before.

Some side-effects occur:

• occupationMeasurement:::init_page_data is called before 1. run_before. It sets up an internal representation of the page data to be saved.

• occupationMeasurement:::finalize_data is called before 6. run_before.

• occupationMeasurement:::save_page_data is called after 6. run_before. It saves the responses on a hard drive, i.e. it appends the responses from this page to table_name == "answers". See the vignette and create_app_settings() for details.

Use of render_before, render_after is discouraged if not necessary, as these two life-cycle functions have only been added to allow for easier modification and extension of existing pages.

Value

A new page object.

Examples

## Not run: 
very_simple_page <- new_page(
  page_id = "example",
  render = function(session, run_before_output, input, output, ...) {
    list(
      shiny::tags$h1("My test page"),
      button_previous(),
      button_next()
    )
  }
)

# Example where we also save some data
page_that_saves_two_items <- new_page(
  page_id = "questions_1_and_2",
  render = function(session, run_before_output, page, input, output, ...) {
    list(
      shiny::tags$h1("Questions"),
      shiny::textAreaInput(
        inputId = "day_freetext",
        label = "How was your day? Please give a detailed answer.",
        value = get_item_data(
          session = session, page_id = page$page_id,
          item_id = "day_freetext",
          key = "response_text"
        )
      ),
      shiny::tags$p("How would you rate your day? On a scale of 1 - 4"),
      radioButtons(
        inputId = "day_radio",
        label = NULL,
        width = "100%",
        choices = list(One = 1, Two = 2, Three = 3, Four = 4),
        selected = get_item_data(
          session = session,
          page_id = page$page_id,
          item_id = "day_radio",
          key = "response_id",
          default = character(0)
        )
      ),
      button_previous(),
      button_next()
    )
  },
  run_after = function(session, page, input, ...) {
    set_item_data(
      session = session,
      page_id = page$page_id,
      item_id = "day_freetext",
      response_text = input$day_freetext
    )
    set_item_data(
      session = session,
      page_id = page$page_id,
      item_id = "day_radio",
      response_id = input$day_radio
    )
  }
)

questionnaire_that_saves_two_items <- list(
  page_that_saves_two_items,
  # So we have a next page to go to
  very_simple_page
)

if (interactive()) {
  app(questionnaire = questionnaire_that_saves_two_items)
}

## End(Not run)

Description

Show a page with multiple radio button options where once can be picked.

Usage

page_choose_one_option(
  page_id,
  question_text = "Please pick one of the following options",
  list_of_choices = list(One = 1, Two = 2, Three = 3),
  choice_labels = NULL,
  next_button = TRUE,
  previous_button = TRUE,
  run_before = NULL,
  run_after = NULL,
  ...
)

Arguments

Value

A page object.

See Also

new_page()

Examples

## Not run: 
one_page_questionnaire <- list(
  page_choose_one_option(
    "test_page_radio",
    question_text = "Hello there! Please pick your favorite number from the options below:",
    list_of_choices = list(One = 1, Two = 2, Three = 3)
  ),
  page_final()
)
if (interactive()) {
  app(questionnaire = one_page_questionnaire)
}

## End(Not run)

Description

Page to receive feedback on how well the chosen suggestion fits

Usage

page_feedback(is_interview = FALSE, ...)

Arguments

Value

A page object.

Examples

## Not run: 
my_questionnaire <- list(
  page_first_freetext(),
  page_select_suggestion(),
  page_feedback()
)
if (interactive()) {
  app(questionnaire = my_questionnaire)
}

## End(Not run)

Description

This page saves data in results_overview and marks the questionnaire as complete.

Usage

page_final(...)

Arguments

Value

A page object.

See Also

new_page()

Examples

## Not run: 
my_questionnaire <- list(
  page_final()
)
if (interactive()) {
  app(questionnaire = my_questionnaire)
}

## End(Not run)

Description

Here, the description of the job can be entered in an open freetext field and suggestions will be generated based on the input.

Usage

page_first_freetext(
  is_interview = FALSE,
  aggregate_score_threshold = 0.535,
  ...
)

Arguments

Value

A page object.

See Also

new_page()

Examples

## Not run: 
my_questionnaire <- list(
  page_first_freetext(),
  page_second_freetext(),
  page_select_suggestion(),
  page_none_selected_freetext(),
  page_followup(1),
  page_followup(2)
)
if (interactive()) {
  app(questionnaire = my_questionnaire)
}

## End(Not run)

Description

To disambiguate between similar occupations. Depending on the suggestion, multiple followup questions can be shown.

Usage

page_followup(index, is_interview = FALSE, ...)

Arguments

Value

A page object.

See Also

new_page()

Examples

## Not run: 
my_questionnaire <- list(
  page_first_freetext(),
  page_second_freetext(),
  page_select_suggestion(),
  page_none_selected_freetext(),
  page_followup(1),
  page_followup(2)
)
if (interactive()) {
  app(questionnaire = my_questionnaire)
}

## End(Not run)

Description

Show a page with a text field where free text can be entered.

Usage

page_freetext(
  page_id,
  question_text = "Please enter your answer in the box below",
  is_interview = FALSE,
  no_answer_checkbox = TRUE,
  next_button = TRUE,
  previous_button = TRUE,
  trigger_next_on_enter = TRUE,
  render_question_text = TRUE,
  run_before = NULL,
  run_after = NULL,
  ...
)

Arguments

Value

A page object.

See Also

new_page()

Examples

## Not run: 
page_freetext(
  "test_page_freetext",
  question_text = "Hello there! Please fill in your name below:",
  no_answer_checkbox = TRUE
)

## End(Not run)

Description

An additional freetext page to show when no suggestion has been selected.

Usage

page_none_selected_freetext(is_interview = FALSE, ...)

Arguments

Value

A page object.

See Also

new_page()

Examples

## Not run: 
my_questionnaire <- list(
  page_first_freetext(),
  page_second_freetext(),
  page_select_suggestion(),
  page_none_selected_freetext(),
  page_followup(1),
  page_followup(2)
)
if (interactive()) {
  app(questionnaire = my_questionnaire)
}

## End(Not run)

Description

This page is only meant for demonstration purposes. Users can see what they entered and which code was being saved. The page is only included in the questionnaire_demo(), but not in the other questionnaire templates.

Usage

page_results(...)

Arguments

Value

A page object.

See Also

new_page()

Examples

## Not run: 
my_questionnaire <- list(
  page_first_freetext(),
  page_second_freetext(),
  page_select_suggestion(),
  page_none_selected_freetext(),
  page_followup(1),
  page_followup(2),
  page_results()
)
if (interactive()) {
  app(questionnaire = my_questionnaire)
}

## End(Not run)

Description

If the first freetext question didn't provide satisfactory results, ask for more details and try again.

Usage

page_second_freetext(
  combine_input_with_first = TRUE,
  is_interview = FALSE,
  aggregate_score_threshold = 0.02,
  ...
)

Arguments

Value

A page object.

See Also

new_page()

Examples

## Not run: 
my_questionnaire <- list(
  page_first_freetext(),
  page_second_freetext(),
  page_select_suggestion(),
  page_none_selected_freetext(),
  page_followup(1),
  page_followup(2)
)
if (interactive()) {
  app(questionnaire = my_questionnaire)
}

## End(Not run)

Description

Display the generated suggestions for the user to pick one.

Usage

page_select_suggestion(is_interview = FALSE, ...)

Arguments

Value

A page object.

See Also

new_page()

Examples

## Not run: 
my_questionnaire <- list(
  page_first_freetext(),
  page_second_freetext(),
  page_select_suggestion(),
  page_none_selected_freetext(),
  page_followup(1),
  page_followup(2)
)
if (interactive()) {
  app(questionnaire = my_questionnaire)
}

## End(Not run)

Description

Providing an introduction and greeting participants.

Usage

page_welcome(
  title = "Herzlich Willkommen zum Modul zur automatischen Berufskodierung!",
  ...
)

Arguments

Value

A page object.

See Also

new_page()

Examples

## Not run: 
my_questionnaire <- list(page_welcome)
if (interactive()) {
  app(questionnaire = my_questionnaire)
}

## End(Not run)

Description

Replace some common characters / character sequences (e.g., Ä, Ü, "DIPL.-ING.") with their uppercase equivalents and removes punctuation, empty spaces and the word "Diplom".

Usage

preprocess_string(verbatim, lang = "de")

Arguments

Details

charToRaw() helps to find UTF-8 characters.

Value

The same character vector after processing

Examples

## Not run: 
preprocess_string(c(
  "Verkauf von B\u00fcchern, Schreibwaren",
  "Fach\u00e4rztin f\u00fcr Kinder- und Jugendmedizin im \u00f6ffentlichen Gesundheitswesen",
  "Industriemechaniker",
  "Dipl.-Ing. - Agrarwirtschaft (Landwirtschaft)"
))

## End(Not run)

Description

Pretrained ML models to be used with the package.

Usage

pretrained_models

Format

A nested list with pretrained machine learning models:

similarity_based_reasoning

list. Contains pretrained models to be used with algo_similarity_based_reasoning().

similarity_based_reasoning$wordwise

list. Contains the pretrained model to be used for providing suggestions using full wordwise matching.

similarity_based_reasoning$substring

list. Contains the pretrained model to be used for providing suggestions using substring matching.

This training data always predicts a 5-digit code from the 2010 German Classification of Occupations, with some exceptions: -0004 stands for 'Not precise enough/uncodable', -0006 stands for 'Multiple Jobs', -0012 stands for 'Blue-collar workers', -0019 stands for 'Volunteer/Social Service', and -0030 stands for 'Student assistant'.

Source

Data from the following surveys were pooled:

Antoni, M., Drasch, K., Kleinert, C., Matthes, B., Ruland, M. and Trahms, A. (2010): Arbeiten und Lernen im Wandel * Teil 1: Überblick über die Studie, FDZ-Methodenreport 05/2010, Forschungsdatenzentrum der Bundesagentur für Arbeit im Institut für Arbeitsmarkt- und Berufsforschung, Nuremberg.

Rohrbach-Schmidt, D., Hall, A. (2013): BIBB/BAuA Employment Survey 2012, BIBB-FDZ Data and Methodological Reports Nr. 1/2013. Version 4.1, Federal Institute for Vocational Education and Training (Research Data Centre), Bonn.

Lange, C., Finger, J., Allen, J., Born, S., Hoebel, J., Kuhnert, R., Müters, S., Thelen, J., Schmich, P., Varga, M., von der Lippe, E., Wetzstein, M., Ziese, T. (2017): Implementation of the European Health Interview Survey (EHIS) into the German Health Update (GEDA), Archives of Public Health, 75, 1–14.

Hoffmann, R., Lange, M., Butschalowsky, H., Houben, R., Schmich, P., Allen, J., Kuhnert, R., Schaffrath Rosario, A., Gößwald, A. (2018): KiGGS Wave 2 Cross-Sectional Study—Participant Acquisition, Response Rates and Representativeness, Journal of Health Monitoring, 3, 78–91. (only wave 2)

Trappmann, M., Beste, J., Bethmann, A., Müller, G. (2013): The PASS Panel Survey after Six Waves, Journal for Labour Market Research, 46, 275–281. (only wave 10)

Job titles were taken from the following publication:

Bundesagentur für Arbeit (2019). Gesamtberufsliste der Bundesagentur für Arbeit. Stand: 03.01.2019. https://download-portal.arbeitsagentur.de/files/.

Basically, leaving some data anonymization steps aside, we count for each job title from the Gesamtberufsliste (and some additional titles/texts) how many responses from all surveys are similar to this job title, separately for each coded category. Similarity is calculated in two ways, implying that we obtain two different counts: SubstringSimilarity refers to situations where the job title from the Gesamtberufsliste is a substring of the verbal answer; WordwiseSimilarity refers to situations where a word from the verbal answer is identical to a job title from the Gesamtberufsliste, except that one character from this word is allowed to change (Levenshtein distance). These counts are available as two separate files in the data-raw/training-data/ directory of this package. The algorithm to create these counts is available inside an R-package at https://github.com/malsch/occupationCoding, along with further documentation.

train_similarity_based_reasoning() is then used to train the ML models. See data-raw/pretrained_models.R for the raw counts and further details.

See Also

algo_similarity_based_reasoning(), train_similarity_based_reasoning(), https://github.com/malsch/occupationCoding

Description

View the function's code itself to see the used pages.

Usage

questionnaire_demo(show_feedback_page = TRUE)

Arguments

Details

Note, that this function has more complex code to create the additional pages.

Value

A questionnaire for app() i.e. a list of pages.

Examples

## Not run: 
# Inspect the code to create the questionnaire_demo
print(questionnaire_demo)

if (interactive()) {
  # Run the app with the questionnaire_demo
  app(questionnaire = questionnaire_demo())
}

## End(Not run)

Description

A questionnaire for Computer-assisted Interviewing (CAI), i.e. telephone interviewing or personal interviewing. In both modes, interviewer asks questions to an interviewee.

Usage

questionnaire_interviewer_administered(show_feedback_page = TRUE)

Arguments

Details

View the function's code to see the used pages. This function is meant as a template that can be changed to meet your requirements.

Value

A questionnaire for app() i.e. a list of pages.

Examples

## Not run: 
# Inspect the code to create the questionnaire_interviewer_administered
print(questionnaire_interviewer_administered)

if (interactive()) {
  # Run the app with the questionnaire_interviewer_administered
  app(questionnaire = questionnaire_interviewer_administered())
}

## End(Not run)

Description

The basic default questionnaire. View the function's code to see the used pages. This function is meant as a template that can be changed to meet your requirements.

Usage

questionnaire_web_survey(show_feedback_page = TRUE)

Arguments

Value

A questionnaire for app(), i.e. a list of pages.

Examples

## Not run: 
# Inspect the code to create the questionnaire_web_survey
print(questionnaire_web_survey)

if (interactive()) {
  # Run the app with the questionnaire_web_survey
  app(questionnaire = questionnaire_web_survey())
}

if (interactive()) {
  # This is used by default within app
  app()
}

## End(Not run)

Description

There can be multiple items on any given page. Items can be different questions, or multiple variables that need to be saved from a single question. The question_text is typically saved in run_before and the reply (response_text and/or response_id) is typically saved in run_after.

Usage

set_item_data(
  session,
  page_id,
  item_id = NULL,
  question_text = NULL,
  response_text = NULL,
  response_id = NULL
)

Arguments

Value

nothing

See Also

get_item_data()

Examples

## Not run: 
# Set up a "fake" shiny session to store data
session <- shiny::MockShinySession$new()
session$userData <- list(
  current_page_id = "other_page",
  questionnaire_data = list(
    example_page = list()
  )
)

# This code is expected to be run in e.g. run_before or run_after
# It doesn't really make sense to run this code outside
set_item_data(
  session = session,
  page_id = "example_page",
  question_text = "How are you?"
)

set_item_data(
  session = session,
  page_id = "example_page",
  response_id = 3,
  response_text = "I'm doing great! (response_id = 3)"
)

## End(Not run)

Description

This function requires the mvtnorm package.

Usage

train_similarity_based_reasoning(
  anonymized_data,
  num_allowed_codes = 1291,
  coding_index_w_codes,
  coding_index_without_codes = NULL,
  preprocessing = list(stopwords = NULL, stemming = NULL, strPreprocessing = TRUE,
    removePunct = FALSE),
  dist_type = c("wordwise", "substring", "fulltext"),
  dist_control = list(method = "osa", weight = c(d = 1, i = 1, s = 1, t = 1)),
  threshold = c(max = 3, use = 1),
  simulation_control = list(n.draws = 250, check_normality = FALSE)
)

Arguments

Value

a list with components

prediction.datasets$modelProb

Contains all entries from the coding index. dist = "official" if the entry stems from coding_index_w_codes and dist = selfcreated if the entry stems from coding_index_without_codes. string.prob is used for weighting purposes (model averaging) if a new verbal answer is similar to multiple strings. unobserved.mean.theta gives a probability (usually very low) for any category that was not observed in the training data together with this string.

prediction.datasets$categoryProb

mean.theta is the probability for code given that an incoming verbal answer is similar to string. Only available if this code was at least a single time observed with this string (Use unobserved.mean.theta otherwise).

num_allowed_codes

Number of categories in the classification.

preprocessing

The input parameter stored to replicate preprocessing with incoming data.

dist_type

The input parameter stored to replicate distance calculations with incoming data.

dist_control

The input parameter stored to replicate distance calculations with incoming data.

threshold

The input parameter stored to replicate distance calculations with incoming data.

simulation_control

The input parameters controlling the Monte Carlo simulation.

References

Schierholz, Malte (2019): New methods for job and occupation classification. Dissertation, Mannheim. https://madoc.bib.uni-mannheim.de/50617/, pp. 206-208 and p. 268, pp. 308-320

https://github.com/malsch/occupationCoding (function trainSimilarityBasedReasoning2 is implemented here)

See Also

pretrained_models, which were created using this function.