pretrained_models

Pretrained ML models to be used with the package.

datasets

Perform interactive occupation coding during interviews as
described in Peycheva, D., Sakshaug, J., Calderwood, L. (2021) <doi:10.2478/jos-2021-0042>
and Schierholz, M., Gensicke, M., Tschersich, N., Kreuter, F. (2018) <doi:10.1111/rssa.12297>.
Generate suggestions for occupational categories based on free text
input, with pre-trained machine learning models in German and a ready-to-use
shiny application provided for quick and easy data collection.

Jan Simson

occupationMeasurement

Interactively Measure Occupations in Interviews and Beyond

Olga Kononykhina

Malte Schierholz

pretrained_models function

A nested list with pretrained machine learning models:<dl>
<dt><code>similarity_based_reasoning</code></dt>
<dd>list. Contains pretrained models to be used with <code>algo_similarity_based_reasoning()</code>.</dd><dt><code>similarity_based_reasoning$wordwise</code></dt>
<dd>list. Contains the pretrained model to be used for providing suggestions using full wordwise matching.</dd><dt><code>similarity_based_reasoning$substring</code></dt>
<dd>list. Contains the pretrained model to be used for providing suggestions using substring matching.</dd>
</dl>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'.

Format

Pretrained ML models to be used with the package. — pretrained_models

A nested list with pretrained machine learning models:<dl>
<dt><code>similarity_based_reasoning</code></dt>
<dd>list. Contains pretrained models to be used with <code>algo_similarity_based_reasoning()</code>.</dd>

<dt><code>similarity_based_reasoning$wordwise</code></dt>
<dd>list. Contains the pretrained model to be used for providing suggestions using full wordwise matching.</dd>

<dt><code>similarity_based_reasoning$substring</code></dt>
<dd>list. Contains the pretrained model to be used for providing suggestions using substring matching.</dd>


</dl>

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'.

pretrained_models: Pretrained ML models to be used with the package.

Description

Usage

Arguments

Format

See Also