chickn: Compressed Hierarchical Clustering Toolbox

Routines for efficient cluster analysis of large scale data. The package implements the 'CHICKN' clustering algorithm, which clusters the data into K groups by relying on the compressed data version. The package provides functions for data compression, hierarchical clustering and result post processing. The used data compression procedure is based on the sketching learning N. 'Keriven', N. 'Tremblay', Y. 'Traonmilin', R. 'Gribonval' (2017) <arXiv:1606.02838v2> and 'Nystrom' kernel approximation S. Wang, A. 'Gittens', M. W. 'Mahoney' (2019) <arXiv:1706.02803v4>. Hierarchical clustering relies on the 'Compressive' K means algorithm N. 'Keriven', A. 'Bourrier', R. 'Gribonval', P. Perez (2017) <arXiv:1610.08738v4>.

Version: 1.2.2
Depends: R (≥ 3.5)
Imports: Rcpp, bigstatsr (≥ 1.2.3), RcppParallel, mvnfast, zipfR, MASS, pracma, nloptr, foreach, doRNG, parallel, doParallel, Rdpack
LinkingTo: Rcpp, RcppArmadillo, RcppParallel, bigstatsr (≥ 1.2.3), rmio
Published: 2020-11-12
Author: Olga Permiakova [aut, cre], Thomas Burger [aut]
Maintainer: Olga Permiakova <olga.permiakova at>
License: GPL-2 | GPL-3 [expanded from: GPL (≥ 2)]
NeedsCompilation: yes
SystemRequirements: C++11
Materials: README
CRAN checks: chickn results


Reference manual: chickn.pdf
Package source: chickn_1.2.2.tar.gz
Windows binaries: r-devel:, r-release:, r-oldrel:
macOS binaries: r-release: not available, r-oldrel: not available


Please use the canonical form to link to this page.