# ------------------------------------------------
# CITATION.cff file created with {cffr} R package
# See also: https://docs.ropensci.org/cffr/
# ------------------------------------------------
 
cff-version: 1.2.0
message: 'To cite package "dataprep" in publications use:'
type: software
license: GPL-2.0-or-later
title: 'dataprep: Fast, Efficient, and Versatile Data Preprocessing and Reshaping
  with ''C++'', ''OpenMP'' & ''SIMD'''
version: 0.1.8
doi: 10.1016/j.scitotenv.2020.140923
identifiers:
- type: doi
  value: 10.32614/CRAN.package.dataprep
abstract: 'Fast, efficient, and versatile preprocessing and reshaping of tabular and
  time-series data. Most heavy routines are implemented in ''C++'' via ''Rcpp'', with
  optional ''OpenMP'' parallelization and ''SIMD'' acceleration (''AVX2'' / ''AVX-512'')
  on supported hardware. The 0.1.8 release rewrites the cleaning routines in ''C++''
  and delivers a 1.1–1146× speedup over 0.1.5. The ''melt()'' and ''dcast()'' reshaping
  functions achieve a 0.6×–1628.9× speedup for ''melt()'' and a 1.9×–799.8× speedup
  for ''dcast()'' relative to every one of the seven major alternatives in the R and
  Python ecosystems, at every tested scale (from 1,000 to 100,000,000 rows), and produce
  output identical to ''reshape2'', ''data.table'', ''tidyr'', ''pandas'', ''polars'',
  ''dask'', and ''duckdb''. Core preprocessing steps include variable deletion by
  missing fraction, observation deletion by consecutive missing runs, point-by-point
  weighted outlier removal via conditional extremum, traditional percentile-based
  outlier removal, and linear interpolation within short time periods. The package
  also provides fast reshaping, descriptive statistics, missing-value diagnosis, multiple
  imputation strategies, winsorization, several outlier detection methods (IQR, MAD,
  percentile), data transformation and standardization, categorical encoding, duplicate
  removal, data validation, data quality reporting, and stratified sampling. Feature-engineering
  helpers cover binning, high-correlation and low-variance filtering, and string cleaning.
  Time-series tools cover detrending, diurnal-cycle removal, rolling statistics, lag
  creation, resampling, simple decomposition, day/night and season flags, log returns,
  drift detection, and panel balancing. Fit/transform-style machine-learning interfaces
  prevent data leakage during preprocessing. Methods are based on, and improved from:
  Liang, C.-S., Wu, H., Li, H.-Y., Zhang, Q., Li, Z. & He, K.-B. (2020) <https://doi.org/10.1016/j.scitotenv.2020.140923>.
  This work was supported by the National Natural Science Foundation of China (No.
  12301674).'
authors:
- family-names: Liang
  given-names: Chun-Sheng
  email: chun-shengliang@qq.com
  orcid: https://orcid.org/0000-0002-7386-1958
- family-names: Wu
  given-names: Hao
- family-names: Li
  given-names: Hai-Yan
- family-names: Zhang
  given-names: Qiang
- family-names: Li
  given-names: Zhanqing
- family-names: He
  given-names: Ke-Bin
preferred-citation:
  type: article
  title: Efficient data preprocessing, episode classification, and source apportionment
    of particle number concentrations
  authors:
  - family-names: Liang
    given-names: Chun-Sheng
    email: chun-shengliang@qq.com
    orcid: https://orcid.org/0000-0002-7386-1958
  - family-names: Wu
    given-names: Hao
  - family-names: Li
    given-names: Hai-Yan
  - family-names: Zhang
    given-names: Qiang
  - family-names: Li
    given-names: Zhanqing
  - family-names: He
    given-names: Ke-Bin
  journal: Science of the Total Environment
  year: '2020'
  volume: '741'
  doi: 10.1016/j.scitotenv.2020.140923
  start: '140923'
repository: https://chunshengliang.r-universe.dev
repository-code: https://github.com/chunshengliang/dataprep
commit: a38d35d1ae567dec2b795a76e3532d64370fb665
url: https://chunshengliang.github.io/dataprep/
date-released: '2026-10-01'
contact:
- family-names: Liang
  given-names: Chun-Sheng
  email: chun-shengliang@qq.com
  orcid: https://orcid.org/0000-0002-7386-1958
references:
- type: manual
  title: 'dataprep: Efficient and Flexible Data Preprocessing Tools'
  authors:
  - family-names: Liang
    given-names: Chun-Sheng
  year: '2026'
  notes: R package version 0.1.8
  url: https://github.com/chunshengliang/dataprep