R Observatory: Metrics for mvrsquared version 0.1.6

Balamuta, James Joseph

doi:10.5281/zenodo.21843040

mvrsquared

0.1.6Package record

Compute the Coefficient of Determination for Vector or Matrix Outcomes

1packages depend

3.2Kdownloads / year

98.7%test coverage

13/13flavors OK

Overview

About

Maintained by Tommy JonesCRAN page ↗GitHub ↗Issues ↗

Compute the coefficient of determination for outcomes in n-dimensions. May be useful for multidimensional predictions (such as a multinomial model) or calculating goodness of fit from latent variable models such as probabilistic topic models like latent Dirichlet allocation or deterministic topic models like latent semantic analysis. Based on Jones (2019) doi:10.48550/arXiv.1911.11061.

Changes in 0.1.6

This patch addresses the issue with package documentation highlighted by CRAN and

described here

It also cites the arXiv paper in the DESCRIPTION by its DOI,

<doi:10.48550/arXiv.1911.11061>, rather than as <arXiv:1911.11061>, which

CRAN's checks had been flagging with a NOTE.

This patch also makes calc_rsquared() substantially faster, with no change to

its arguments or return value.

**Sparse y is no longer read as though it were dense.** The calculation visited every cell of y and read each one out of the sparse matrix, which costs a search per read; on a 70,676 x 20,926 matrix that was roughly three billion searches to read four million nonzeros. Both sums of squares split into a part over the nonzeros and a part that does not depend on y's values, and the second part has a closed form, so only the nonzeros need visiting. On that matrix with 100 latent dimensions: **194 s to 1.5 s single threaded, and 16.6 s to 0.34 s on twelve threads.**

Show all changes in 0.1.6Hide the rest of the changes in 0.1.6

**A yhat supplied directly no longer builds an identity matrix.** When yhat was given as a matrix rather than as two matrices to multiply, it was turned into a factorization by pairing it with an identity the width of y -- quadratic memory in the number of columns, and a matrix multiplication that did nothing. Such a yhat now goes to its own routine. At 20,926 columns the identity alone was 3.5 GB, so this case previously became unusable on wide outcomes well before it became slow.
**Results are unchanged**, to floating point tolerance. The sums are accumulated in a different order, so this is not bit-for-bit identical to 0.1.5; agreement with a dense reference calculation is to about 1e-14 relative, and R-squared is unchanged in every digit print() will show you.
**The note about parallelism and precision has been retired.** Results do not depend on threads: each observation writes its own slot and the totals are summed sequentially afterwards. Thread counts from 1 to 12 were verified to give bit-identical results, on both the factorized and direct paths.

From NEWS.md in the release

Install

R (CRAN)pak (dev)Ubuntu (r2u)Fedora (COPR)openSUSE (OBS)

install.packages("mvrsquared", repos = "https://cloud.r-project.org/")

Installs the current CRAN release. Prebuilt binaries on Windows and macOS.

if (!requireNamespace("pak", quietly = TRUE))
  install.packages("pak", repos = "https://cloud.r-project.org/")
pak::pak("TommyJones/mvrsquared")

Development version from TommyJones/mvrsquared. Installs pak first if it is not already available.

Release

# enable cranapt (r2u) if it is not already set up, then install
grep -rqs r2u.stat.illinois.edu /etc/apt/sources.list /etc/apt/sources.list.d/ \
  || curl -fsSL https://raw.githubusercontent.com/eddelbuettel/r2u/master/inst/scripts/add_cranapt_noble.sh | sudo bash
sudo apt install -y r-cran-mvrsquared

Fast Ubuntu binaries via r2u (no compilation). The cranapt setup runs once and is skipped when it is already enabled. We list this channel from recorded r2u download activity rather than from a live index of the repository, so treat it as last known rather than guaranteed.

bspm (used by r2u) also needs make: sudo apt install make

# enable the iucar/cran COPR if it is not already present, then install
ls /etc/yum.repos.d/*iucar*cran*.repo >/dev/null 2>&1 \
  || sudo dnf copr enable -y iucar/cran
sudo dnf install -y R-CRAN-mvrsquared

RPMs from the iucar/cran COPR, rebuilt from CRAN.

For install.packages() integration in R, also: sudo dnf install R-CoprManager

# add the autoCRAN OBS repo (Tumbleweed) if it is missing, then install
zypper -q lr | grep -qi autoCRAN \
  || sudo zypper addrepo https://download.opensuse.org/repositories/devel:/languages:/R:/autoCRAN/openSUSE_Tumbleweed/devel:languages:R:autoCRAN.repo
sudo zypper install -y R-mvrsquared

RPMs auto-built from CRAN on openSUSE OBS (Tumbleweed). We list this channel from recorded autoCRAN download activity rather than from a live index of the repository, so treat it as last known rather than guaranteed.

Health

CRAN checks

13OK

CRAN check page ↗

Slowest check: 3.7 min · r-devel-windows-x86_64

Status changes

OK13 OK2026-09-05
NOTE11 OK, 2 NOTE2026-06-09
ERROR11 OK, 1 NOTE, 1 ERROR2026-06-08
WARNING11 OK, 1 NOTE, 1 WARNING2026-06-07
NOTE12 OK, 2 NOTE2026-04-22

Show 4 earlier changesHide 4 earlier changes

ERROR11 OK, 2 NOTE, 1 ERROR2026-04-18
NOTE12 OK, 2 NOTE2026-04-10
ERROR12 OK, 1 NOTE, 1 ERROR2026-04-09
NOTE12 OK, 2 NOTE2026-03-10

Advisories

none known

How this is measured·How advisories are found

Documentation

In release 0.1.6

READMEYes · 232 wordsVignettesYes · 1 · dynamicNEWSYes · 100% structured · mentions 0.1.6Citation fileNoWebsitenot declared in DESCRIPTION

Help pages: 2 (1 internal)includes a package overview page
Examples that run: 100%1 run in a plain check
Exported functions with examples: 100%
Documented parameters: 100%
Return-value docs: 100%
Help pages citing references: 0%

Vignettes (1)

Getting Started With mvrsquared HTML

How these are measured

Downloads

3.2K

CRAN downloads in the past year

Rank #9,174 · ~9/day · ~268/mo

Releases R versions

Daily download trend is not available in this view yet.

40230 days

1.1K90 days

3.2K1 year

Compare downloads with other packages →

Also on391 r2u1 autocran

How downloads are counted

Repository

tommyjones/mvrsquared ↗Account: TommyJones

0Stars

1Forks

2Open issues

0Open PRs

5Releases

108Commits

2Commit identities

108 commits · Last activity 2026-08-31 · Default branch at 0.1.6.999, ahead of CRAN 0.1.6 (checked 2026-10-21)

Responsiveness

How these are sampled

PRs merged (all time): 100%
Median days to close, 50 most recently updated closed issues: 7
Median days to close, 50 most recently updated closed PRs: 0

Forks over time

2021-06-27 · 12026-07-07 · 1

How these are measured

PracticesBeta

6 development-tooling and community-health practices detected across 4 families in the upstream repository

Checks run against github.com/tommyjones/mvrsquared on 2026-10-21.

Continuous integration (2)

GitHub ActionsR CMD check workflow

The R CMD check workflow runs on Linux

Coverage (1)

Coverage reporting (Codecov)

CRAN release process (2)

cran-comments.mdCRAN-SUBMISSION

Lint, format, editor (1)

RStudio project

How this is detected·Detection ruleset v4 (2026-10-20)

AI coding toolsBeta

This repository shows signs of AI coding tools.

Claude Codefirst seen 2026-08-30
Commits: at least 4 crediting it in the message

Models named in its commits

Claude Opus 54 commits · Aug 2026

Counts are commits, not lines of code. Commits by a tool's accounts count once across all of its accounts. Commits crediting it are the largest count among its credit lines, a minimum.How this is detected·Detection ruleset v4 (updated 2026-09-27)

Dependencies

Declared dependencies

13 external dependencies (excludes base and recommended)

Installing mvrsquared adds 3 packages (3 with compiled code, 3.1 MB of source tarballs). Heaviest: Rcpp 1.8 MB, RcppArmadillo 1.0 MB, RcppThread 308 KB.

Depends (1)

R >= 3.0.2

Imports (3)

MatrixmethodsRcpp

LinkingTo (3)

Rcpp RcppArmadillo RcppThread

Suggests (13)

dplyr furrr knitrMASSnnetparallelrmarkdownstatsstringr testthat textmineR tidytext spelling

Enhances (0)

none

Dependency license breakdown →

Reverse dependencies

1direct

0indirect

Imports 1

Depends, Imports or LinkingTo, most downloaded first

tidylda

How these are counted

Code & Tests

People & History

People (2)

Tommy Jones

Author, Maintainer since 0.0.3 (2020)

Thomas Nagler

Contributor · added in 0.1.4

Releases (7)

Pick two releases to compare their code metrics.

0.1.6Latest
record
2026-08-31 · current release · diff ↗
R
R 4.6.0 released · 2026-04-24
R
R 4.5.0 released · 2025-04-11
R
R 4.4.0 released · 2024-04-24
0.1.5
record
2023-07-15 · diff ↗
R
R 4.3.0 released · 2023-04-21
0.1.4
record
2022-06-01 · diff ↗
R
R 4.2.0 released · 2022-04-22
0.1.2
record
2021-09-20 · diff ↗
R
R 4.1.0 released · 2021-05-18
0.1.1
record
2020-10-21 · diff ↗
0.1.0
record
2020-06-25 · diff ↗
R
R 4.0.0 released · 2020-04-24
0.0.3
record
2020-02-20
R
R 3.6.0 released · 2019-04-26

Package metadata

First published: 2020-02-20
Total releases: 7 / 6 yrs
License: MIT + file LICENSE OSI
Minimum R: ≥ 3.0.2
Download size: 122 KB

Cite

Cite this package

Run in R for the authors' preferred citation:

citation("mvrsquared")

Format

Jones, T., & Nagler, T. (2026). mvrsquared: Compute the Coefficient of Determination for Vector or Matrix Outcomes (Version 0.1.6) [Computer software]. https://doi.org/10.32614/CRAN.package.mvrsquared

This package has no citation file, so citation() returns this entry built from DESCRIPTION.

Cite the R Observatory

For a number measured here: a download total, a coverage figure, an archival date.

Format

APA

Balamuta, J. J. (2026). R Observatory: Metrics for mvrsquared version 0.1.6 [Data set]. HJJB, LLC. Data release v2026-10-23. https://doi.org/10.5281/zenodo.21843040

From data release v2026-10-23, which the citation names so these numbers can be found later. More on citing and the projects behind them.

Report a problem with this page →