build_llm_prompt

Constructs a prompt for the LLM using metadata and optional codebook and data-sharing context.

internal

Data from statistical agencies and other institutions are mostly
confidential. This package, introduced in Templ, Kowarik and Meindl (2017) <doi:10.18637/jss.v067.i04>, can be used for the generation of anonymized
(micro)data, i.e. for the creation of public- and scientific-use files.
The theoretical basis for the methods implemented can be found in Templ (2017) <doi:10.1007/978-3-319-50272-4>.
Various risk estimation and anonymization methods are included. Note that the package
includes a graphical user interface published in Meindl and Templ (2019) <doi:10.3390/a12090191> that allows to use various methods of this
package.

Matthias Templ

sdcMicro

Statistical Disclosure Control Methods for Anonymization of Data
and Risk Estimation

Bernhard Meindl

Alexander Kowarik

Johannes Gussenbauer

Organisation For Economic Co-Operation And Development 

Statistics Netherlands 

Pascal Heus 

build_llm_prompt function

<dl><dt>meta</dt>
<dd>A data.frame with variable metadata (name, class, cardinality).</dd>
<dt>policy</dt>
<dd>One of `"open"`, `"restricted"`, or `"confidential"`.</dd>
<dt>codebook</dt>
<dd>Optional path to a CSV, TSV, YAML, JSON, TXT, or PDF file describing variable definitions.</dd></dl>

Arguments

Author

Build LLM Prompt for Variable Role Classification — build_llm_prompt

<dl>

<dt>meta</dt>
<dd>A data.frame with variable metadata (name, class, cardinality).</dd>


<dt>policy</dt>
<dd>One of `"open"`, `"restricted"`, or `"confidential"`.</dd>


<dt>codebook</dt>
<dd>Optional path to a CSV, TSV, YAML, JSON, TXT, or PDF file describing variable definitions.</dd>

</dl>

Build LLM Prompt for Variable Role Classification

build_llm_prompt: Build LLM Prompt for Variable Role Classification

Description

Usage

Value

Arguments

Author