# --------------------------------------------
# CITATION file created with {cffr} R package
# See also: https://docs.ropensci.org/cffr/
# --------------------------------------------
 
cff-version: 1.2.0
message: 'To cite package "pickmax" in publications use:'
type: software
license: GPL-3.0-only
title: 'pickmax: Split and Coalesce Duplicated Records'
version: 0.1.0
doi: 10.32614/CRAN.package.pickmax
abstract: Deduplicates datasets by retaining the most complete and informative records.
  Identifies duplicated entries based on a specified key column, calculates completeness
  scores for each row, and compares values within groups. When differences between
  duplicates exceed a user-defined threshold, records are split into unique IDs; otherwise,
  they are coalesced into a single, most complete entry. Returns a list containing
  the original duplicates, the split entries, and the final coalesced dataset. Useful
  for cleaning survey or administrative data where duplicated IDs may reflect minor
  data entry inconsistencies.
authors:
- family-names: Chamane
  given-names: Sbonelo
  email: SChamane@hsrc.ac.za
  orcid: https://orcid.org/0000-0001-5350-5203
- family-names: Mabaso
  given-names: Musawenkosi
- family-names: Sewpaul
  given-names: Ronel
- family-names: Jooste
  given-names: Sean
- family-names: Skhosana
  given-names: Kutloano
- family-names: Zuma
  given-names: Khangelani
repository: https://cran.r-universe.dev
commit: 2df14f241ea011b3776e96265415f6b763ccb95c
date-released: '2025-07-15'
contact:
- family-names: Chamane
  given-names: Sbonelo
  email: SChamane@hsrc.ac.za
  orcid: https://orcid.org/0000-0001-5350-5203