In eworx-org/labourR: Classify Multilingual Labour Market Free-Text to Standardized Hierarchical Occupations

knitr::opts_chunk$set(
  collapse = TRUE,
  comment = "#>",
  fig.path = "man/figures/README-",
  out.width = "100%"
)

labourR

The goal of labourR is to map multilingual free-text of occupations, such as a job title in a Curriculum Vitae, to hierarchical ontologies provided by ESCO, the multilingual classification of European Skills, Competences, Qualifications and Occupations, and ISCO, the International Standard Classification of Occupations.

knitr::include_graphics("man/figures/ESCO_ISCO_hierarchy.png")

Computations are vectorised and the data.table package is used for high performance and memory efficiency.

See Articles section for details.

Installation

You can install the released version of labourR from CRAN with,

install.packages("labourR")

Examples

library(labourR)
corpus <- data.frame(
  id = 1:3,
  text = c("Data Scientist", "Junior Architect Engineer", "Cashier at McDonald's")
)

• If the ISCO level is specified, the top suggested ISCO group is returned. num_leaves specifies the number of ESCO occupations used for the k-NN classifier to perform a plurality vote,

classify_occupation(corpus = corpus, isco_level = 3, lang = "en", num_leaves = 5)

• If the ISCO level is not specified, the top num_leaves, in this case 5, suggested ESCO occupations are returned for each id,

classify_occupation(corpus = corpus, isco_level = NULL, lang = "en", num_leaves = 5)

eworx-org/labourR documentation built on Feb. 10, 2022, 12:35 a.m.